Index: src/java/org/apache/lucene/queryParser/parser/EscapeQuerySyntax.java =================================================================== --- src/java/org/apache/lucene/queryParser/parser/EscapeQuerySyntax.java (revision 0) +++ src/java/org/apache/lucene/queryParser/parser/EscapeQuerySyntax.java (revision 0) @@ -0,0 +1,39 @@ +package org.apache.lucene.queryParser.parser; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Locale; + +/** + * A parser needs to implement {@link EscapeQuerySyntax} to allow the + * QueryNode to escape the queries, when the toQueryString method is + * called. + */ +public interface EscapeQuerySyntax { + public enum Type { + STRING, NORMAL; + } + + /** + * @param text - text to be escaped + * @param locale - locale for the current query + * @param type - select the type of escape operation to use + * @return escaped text + */ + CharSequence escape(CharSequence text, Locale locale, Type type); +} Index: src/java/org/apache/lucene/queryParser/parser/Parser.java =================================================================== --- src/java/org/apache/lucene/queryParser/parser/Parser.java (revision 0) +++ src/java/org/apache/lucene/queryParser/parser/Parser.java (revision 0) @@ -0,0 +1,33 @@ +package org.apache.lucene.queryParser.parser; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeParseException; +import org.apache.lucene.queryParser.nodes.QueryNode; + +/** + * A parser needs to implement {@link Parser} interface + */ +public interface Parser { + /** + * @param Query - query data to be parsed + * @param field - default field name + * @return QueryNode tree + */ + public QueryNode parse(CharSequence query, CharSequence field) throws QueryNodeParseException; +} Index: src/java/org/apache/lucene/queryParser/parser/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/parser/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/parser/package.html (revision 0) @@ -0,0 +1,41 @@ + + + + + + + +

Parser

+

+The package org.apache.lucene.queryParser.parser contains interfaces +that should be implemented by the parsers. + +Parsers produce QueryNode Trees from a string object. +These package still needs some work to add support to for multiple parsers. + +Features that should be supported for the future, related with the parser: +- QueryNode tree should be able convertible to any parser syntax. +- The query syntax should support calling other parsers. +- QueryNode tree created by multiple parsers. + +

+

+ +

+ + Index: src/java/org/apache/lucene/queryParser/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/package.html (revision 757685) +++ src/java/org/apache/lucene/queryParser/package.html (working copy) @@ -1,31 +0,0 @@ - - - - - - - - -A simple query parser implemented with JavaCC. -

Note that JavaCC defines lots of public classes, methods and fields -that do not need to be public.  These clutter the documentation.  -Sorry. -

Note that because JavaCC defines a class named Token, org.apache.lucene.analysis.Token -must always be fully qualified in source code in this package. - - Index: src/java/org/apache/lucene/queryParser/TokenMgrError.java =================================================================== --- src/java/org/apache/lucene/queryParser/TokenMgrError.java (revision 757685) +++ src/java/org/apache/lucene/queryParser/TokenMgrError.java (working copy) @@ -1,140 +0,0 @@ -/* Generated By:JavaCC: Do not edit this line. TokenMgrError.java Version 4.1 */ -/* JavaCCOptions: */ -package org.apache.lucene.queryParser; - -/** Token Manager Error. */ -public class TokenMgrError extends Error -{ - - /* - * Ordinals for various reasons why an Error of this type can be thrown. - */ - - /** - * Lexical error occurred. - */ - static final int LEXICAL_ERROR = 0; - - /** - * An attempt was made to create a second instance of a static token manager. - */ - static final int STATIC_LEXER_ERROR = 1; - - /** - * Tried to change to an invalid lexical state. - */ - static final int INVALID_LEXICAL_STATE = 2; - - /** - * Detected (and bailed out of) an infinite loop in the token manager. - */ - static final int LOOP_DETECTED = 3; - - /** - * Indicates the reason why the exception is thrown. It will have - * one of the above 4 values. - */ - int errorCode; - - /** - * Replaces unprintable characters by their escaped (or unicode escaped) - * equivalents in the given string - */ - protected static final String addEscapes(String str) { - StringBuffer retval = new StringBuffer(); - char ch; - for (int i = 0; i < str.length(); i++) { - switch (str.charAt(i)) - { - case 0 : - continue; - case '\b': - retval.append("\\b"); - continue; - case '\t': - retval.append("\\t"); - continue; - case '\n': - retval.append("\\n"); - continue; - case '\f': - retval.append("\\f"); - continue; - case '\r': - retval.append("\\r"); - continue; - case '\"': - retval.append("\\\""); - continue; - case '\'': - retval.append("\\\'"); - continue; - case '\\': - retval.append("\\\\"); - continue; - default: - if ((ch = str.charAt(i)) < 0x20 || ch > 0x7e) { - String s = "0000" + Integer.toString(ch, 16); - retval.append("\\u" + s.substring(s.length() - 4, s.length())); - } else { - retval.append(ch); - } - continue; - } - } - return retval.toString(); - } - - /** - * Returns a detailed message for the Error when it is thrown by the - * token manager to indicate a lexical error. - * Parameters : - * EOFSeen : indicates if EOF caused the lexical error - * curLexState : lexical state in which this error occurred - * errorLine : line number when the error occurred - * errorColumn : column number when the error occurred - * errorAfter : prefix that was seen before this error occurred - * curchar : the offending character - * Note: You can customize the lexical error message by modifying this method. - */ - protected static String LexicalError(boolean EOFSeen, int lexState, int errorLine, int errorColumn, String errorAfter, char curChar) { - return("Lexical error at line " + - errorLine + ", column " + - errorColumn + ". Encountered: " + - (EOFSeen ? " " : ("\"" + addEscapes(String.valueOf(curChar)) + "\"") + " (" + (int)curChar + "), ") + - "after : \"" + addEscapes(errorAfter) + "\""); - } - - /** - * You can also modify the body of this method to customize your error messages. - * For example, cases like LOOP_DETECTED and INVALID_LEXICAL_STATE are not - * of end-users concern, so you can return something like : - * - * "Internal Error : Please file a bug report .... " - * - * from this method for such cases in the release version of your parser. - */ - public String getMessage() { - return super.getMessage(); - } - - /* - * Constructors of various flavors follow. - */ - - /** No arg constructor. */ - public TokenMgrError() { - } - - /** Constructor with message and reason. */ - public TokenMgrError(String message, int reason) { - super(message); - errorCode = reason; - } - - /** Full Constructor. */ - public TokenMgrError(boolean EOFSeen, int lexState, int errorLine, int errorColumn, String errorAfter, char curChar, int reason) { - this(LexicalError(EOFSeen, lexState, errorLine, errorColumn, errorAfter, curChar), reason); - } -} -/* JavaCC - OriginalChecksum=55cddb2336a66b376c0bb59d916b326d (do not edit this line) */ Index: src/java/org/apache/lucene/queryParser/QueryNodeException.java =================================================================== --- src/java/org/apache/lucene/queryParser/QueryNodeException.java (revision 0) +++ src/java/org/apache/lucene/queryParser/QueryNodeException.java (revision 0) @@ -0,0 +1,75 @@ +package org.apache.lucene.queryParser; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Locale; + +import org.apache.lucene.messages.Message; +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.messages.NLSException; +import org.apache.lucene.queryParser.messages.QueryParserMessages; + + +/** + * + */ +public class QueryNodeException extends Exception implements NLSException { + + private static final long serialVersionUID = -5962648855261624214L; + + protected Message message = new MessageImpl(QueryParserMessages.EMPTY_MESSAGE); + + public QueryNodeException(Message message) { + super(message.getKey()); + + this.message = message; + + } + + public QueryNodeException(Throwable throwable) { + super(throwable); + } + + public QueryNodeException(Message message, Throwable throwable) { + super(message.getKey(), throwable); + + this.message = message; + + } + + public Message getMessageObject() { + return this.message; + } + + public String getMessage() { + return getLocalizedMessage(); + } + + public String getLocalizedMessage() { + return getLocalizedMessage(Locale.getDefault()); + } + + public String getLocalizedMessage(Locale locale) { + return this.message.getLocalizedMessage(locale); + } + + public String toString() { + return this.message.getKey() + ": " + getLocalizedMessage(); + } + +} Index: src/java/org/apache/lucene/queryParser/QueryParser.jj =================================================================== --- src/java/org/apache/lucene/queryParser/QueryParser.jj (revision 757685) +++ src/java/org/apache/lucene/queryParser/QueryParser.jj (working copy) @@ -1,1480 +0,0 @@ -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -options { - STATIC=false; - JAVA_UNICODE_ESCAPE=true; - USER_CHAR_STREAM=true; -} - -PARSER_BEGIN(QueryParser) - -package org.apache.lucene.queryParser; - -import java.io.IOException; -import java.io.StringReader; -import java.text.Collator; -import java.text.DateFormat; -import java.util.ArrayList; -import java.util.Calendar; -import java.util.Date; -import java.util.HashMap; -import java.util.List; -import java.util.Locale; -import java.util.Map; -import java.util.Vector; - -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.CachingTokenFilter; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute; -import org.apache.lucene.analysis.tokenattributes.TermAttribute; -import org.apache.lucene.document.DateField; -import org.apache.lucene.document.DateTools; -import org.apache.lucene.index.Term; -import org.apache.lucene.search.BooleanClause; -import org.apache.lucene.search.BooleanQuery; -import org.apache.lucene.search.ConstantScoreRangeQuery; -import org.apache.lucene.search.FuzzyQuery; -import org.apache.lucene.search.MatchAllDocsQuery; -import org.apache.lucene.search.MultiPhraseQuery; -import org.apache.lucene.search.PhraseQuery; -import org.apache.lucene.search.PrefixQuery; -import org.apache.lucene.search.Query; -import org.apache.lucene.search.RangeQuery; -import org.apache.lucene.search.TermQuery; -import org.apache.lucene.search.WildcardQuery; -import org.apache.lucene.util.Parameter; - -/** - * This class is generated by JavaCC. The most important method is - * {@link #parse(String)}. - * - * The syntax for query strings is as follows: - * A Query is a series of clauses. - * A clause may be prefixed by: - *

- * - * A clause may be either: - * - * - * Thus, in BNF, the query grammar is: - * 
- *   Query  ::= ( Clause )*
- *   Clause ::= ["+", "-"] [<TERM> ":"] ( <TERM> | "(" Query ")" )
- *
- * - *

- * Examples of appropriately formatted queries can be found in the query syntax - * documentation. - *

- * - *

- * In {@link RangeQuery}s, QueryParser tries to detect date values, e.g. - * date:[6/1/2005 TO 6/4/2005] produces a range query that searches - * for "date" fields between 2005-06-01 and 2005-06-04. Note that the format - * of the accepted input depends on {@link #setLocale(Locale) the locale}. - * By default a date is converted into a search term using the deprecated - * {@link DateField} for compatibility reasons. - * To use the new {@link DateTools} to convert dates, a - * {@link org.apache.lucene.document.DateTools.Resolution} has to be set. - *

- *

- * The date resolution that shall be used for RangeQueries can be set - * using {@link #setDateResolution(DateTools.Resolution)} - * or {@link #setDateResolution(String, DateTools.Resolution)}. The former - * sets the default date resolution for all fields, whereas the latter can - * be used to set field specific date resolutions. Field specific date - * resolutions take, if set, precedence over the default date resolution. - *

- *

- * If you use neither {@link DateField} nor {@link DateTools} in your - * index, you can create your own - * query parser that inherits QueryParser and overwrites - * {@link #getRangeQuery(String, String, String, boolean)} to - * use a different method for date conversion. - *

- * - *

Note that QueryParser is not thread-safe.

- */ -public class QueryParser { - - private static final int CONJ_NONE = 0; - private static final int CONJ_AND = 1; - private static final int CONJ_OR = 2; - - private static final int MOD_NONE = 0; - private static final int MOD_NOT = 10; - private static final int MOD_REQ = 11; - - // make it possible to call setDefaultOperator() without accessing - // the nested class: - /** Alternative form of QueryParser.Operator.AND */ - public static final Operator AND_OPERATOR = Operator.AND; - /** Alternative form of QueryParser.Operator.OR */ - public static final Operator OR_OPERATOR = Operator.OR; - - /** The actual operator that parser uses to combine query terms */ - private Operator operator = OR_OPERATOR; - - boolean lowercaseExpandedTerms = true; - boolean constantScoreRewrite= true; - boolean allowLeadingWildcard = false; - boolean enablePositionIncrements = false; - - Analyzer analyzer; - String field; - int phraseSlop = 0; - float fuzzyMinSim = FuzzyQuery.defaultMinSimilarity; - int fuzzyPrefixLength = FuzzyQuery.defaultPrefixLength; - Locale locale = Locale.getDefault(); - - // the default date resolution - DateTools.Resolution dateResolution = null; - // maps field names to date resolutions - Map fieldToDateResolution = null; - - // The collator to use when determining range inclusion, - // for use when constructing RangeQuerys. - Collator rangeCollator = null; - - /** The default operator for parsing queries. - * Use {@link QueryParser#setDefaultOperator} to change it. - */ - static public final class Operator extends Parameter { - private Operator(String name) { - super(name); - } - static public final Operator OR = new Operator("OR"); - static public final Operator AND = new Operator("AND"); - } - - - /** Constructs a query parser. - * @param f the default field for query terms. - * @param a used to find terms in the query text. - */ - public QueryParser(String f, Analyzer a) { - this(new FastCharStream(new StringReader(""))); - analyzer = a; - field = f; - } - - /** Parses a query string, returning a {@link org.apache.lucene.search.Query}. - * @param query the query string to be parsed. - * @throws ParseException if the parsing fails - */ - public Query parse(String query) throws ParseException { - ReInit(new FastCharStream(new StringReader(query))); - try { - // TopLevelQuery is a Query followed by the end-of-input (EOF) - Query res = TopLevelQuery(field); - return res!=null ? res : newBooleanQuery(false); - } - catch (ParseException tme) { - // rethrow to include the original query: - throw new ParseException("Cannot parse '" +query+ "': " + tme.getMessage()); - } - catch (TokenMgrError tme) { - throw new ParseException("Cannot parse '" +query+ "': " + tme.getMessage()); - } - catch (BooleanQuery.TooManyClauses tmc) { - throw new ParseException("Cannot parse '" +query+ "': too many boolean clauses"); - } - } - - /** - * @return Returns the analyzer. - */ - public Analyzer getAnalyzer() { - return analyzer; - } - - /** - * @return Returns the field. - */ - public String getField() { - return field; - } - - /** - * Get the minimal similarity for fuzzy queries. - */ - public float getFuzzyMinSim() { - return fuzzyMinSim; - } - - /** - * Set the minimum similarity for fuzzy queries. - * Default is 0.5f. - */ - public void setFuzzyMinSim(float fuzzyMinSim) { - this.fuzzyMinSim = fuzzyMinSim; - } - - /** - * Get the prefix length for fuzzy queries. - * @return Returns the fuzzyPrefixLength. - */ - public int getFuzzyPrefixLength() { - return fuzzyPrefixLength; - } - - /** - * Set the prefix length for fuzzy queries. Default is 0. - * @param fuzzyPrefixLength The fuzzyPrefixLength to set. - */ - public void setFuzzyPrefixLength(int fuzzyPrefixLength) { - this.fuzzyPrefixLength = fuzzyPrefixLength; - } - - /** - * Sets the default slop for phrases. If zero, then exact phrase matches - * are required. Default value is zero. - */ - public void setPhraseSlop(int phraseSlop) { - this.phraseSlop = phraseSlop; - } - - /** - * Gets the default slop for phrases. - */ - public int getPhraseSlop() { - return phraseSlop; - } - - - /** - * Set to true to allow leading wildcard characters. - *

- * When set, * or ? are allowed as - * the first character of a PrefixQuery and WildcardQuery. - * Note that this can produce very slow - * queries on big indexes. - *

- * Default: false. - */ - public void setAllowLeadingWildcard(boolean allowLeadingWildcard) { - this.allowLeadingWildcard = allowLeadingWildcard; - } - - /** - * @see #setAllowLeadingWildcard(boolean) - */ - public boolean getAllowLeadingWildcard() { - return allowLeadingWildcard; - } - - /** - * Set to true to enable position increments in result query. - *

- * When set, result phrase and multi-phrase queries will - * be aware of position increments. - * Useful when e.g. a StopFilter increases the position increment of - * the token that follows an omitted token. - *

- * Default: false. - */ - public void setEnablePositionIncrements(boolean enable) { - this.enablePositionIncrements = enable; - } - - /** - * @see #setEnablePositionIncrements(boolean) - */ - public boolean getEnablePositionIncrements() { - return enablePositionIncrements; - } - - /** - * Sets the boolean operator of the QueryParser. - * In default mode (OR_OPERATOR) terms without any modifiers - * are considered optional: for example capital of Hungary is equal to - * capital OR of OR Hungary.
- * In AND_OPERATOR mode terms are considered to be in conjunction: the - * above mentioned query is parsed as capital AND of AND Hungary - */ - public void setDefaultOperator(Operator op) { - this.operator = op; - } - - - /** - * Gets implicit operator setting, which will be either AND_OPERATOR - * or OR_OPERATOR. - */ - public Operator getDefaultOperator() { - return operator; - } - - - /** - * Whether terms of wildcard, prefix, fuzzy and range queries are to be automatically - * lower-cased or not. Default is true. - */ - public void setLowercaseExpandedTerms(boolean lowercaseExpandedTerms) { - this.lowercaseExpandedTerms = lowercaseExpandedTerms; - } - - - /** - * @see #setLowercaseExpandedTerms(boolean) - */ - public boolean getLowercaseExpandedTerms() { - return lowercaseExpandedTerms; - } - - /** - * @deprecated Please use {@link #setConstantScoreRewrite} instead. - */ - public void setUseOldRangeQuery(boolean useOldRangeQuery) { - constantScoreRewrite = !useOldRangeQuery; - } - - - /** - * @deprecated Please use {@link #getConstantScoreRewrite} instead. - */ - public boolean getUseOldRangeQuery() { - return !constantScoreRewrite; - } - - /** - * By default QueryParser uses constant-score rewriting - * when creating a PrefixQuery, WildcardQuery or RangeQuery. This implementation is generally preferable because it - * a) Runs faster b) Does not have the scarcity of terms unduly influence score - * c) avoids any "TooManyBooleanClauses" exception. - * However, if your application really needs to use the - * old-fashioned BooleanQuery expansion rewriting and the above - * points are not relevant then set this option to true - * Default is false. - */ - public void setConstantScoreRewrite(boolean v) { - constantScoreRewrite = v; - } - - - /** - * @see #setConstantScoreRewrite(boolean) - */ - public boolean getConstantScoreRewrite() { - return constantScoreRewrite; - } - - /** - * Set locale used by date range parsing. - */ - public void setLocale(Locale locale) { - this.locale = locale; - } - - /** - * Returns current locale, allowing access by subclasses. - */ - public Locale getLocale() { - return locale; - } - - /** - * Sets the default date resolution used by RangeQueries for fields for which no - * specific date resolutions has been set. Field specific resolutions can be set - * with {@link #setDateResolution(String, DateTools.Resolution)}. - * - * @param dateResolution the default date resolution to set - */ - public void setDateResolution(DateTools.Resolution dateResolution) { - this.dateResolution = dateResolution; - } - - /** - * Sets the date resolution used by RangeQueries for a specific field. - * - * @param fieldName field for which the date resolution is to be set - * @param dateResolution date resolution to set - */ - public void setDateResolution(String fieldName, DateTools.Resolution dateResolution) { - if (fieldName == null) { - throw new IllegalArgumentException("Field cannot be null."); - } - - if (fieldToDateResolution == null) { - // lazily initialize HashMap - fieldToDateResolution = new HashMap(); - } - - fieldToDateResolution.put(fieldName, dateResolution); - } - - /** - * Returns the date resolution that is used by RangeQueries for the given field. - * Returns null, if no default or field specific date resolution has been set - * for the given field. - * - */ - public DateTools.Resolution getDateResolution(String fieldName) { - if (fieldName == null) { - throw new IllegalArgumentException("Field cannot be null."); - } - - if (fieldToDateResolution == null) { - // no field specific date resolutions set; return default date resolution instead - return this.dateResolution; - } - - DateTools.Resolution resolution = (DateTools.Resolution) fieldToDateResolution.get(fieldName); - if (resolution == null) { - // no date resolutions set for the given field; return default date resolution instead - resolution = this.dateResolution; - } - - return resolution; - } - - /** - * Sets the collator used to determine index term inclusion in ranges - * for RangeQuerys. - *

- * WARNING: Setting the rangeCollator to a non-null - * collator using this method will cause every single index Term in the - * Field referenced by lowerTerm and/or upperTerm to be examined. - * Depending on the number of index Terms in this Field, the operation could - * be very slow. - * - * @param rc the collator to use when constructing RangeQuerys - */ - public void setRangeCollator(Collator rc) { - rangeCollator = rc; - } - - /** - * @return the collator used to determine index term inclusion in ranges - * for RangeQuerys. - */ - public Collator getRangeCollator() { - return rangeCollator; - } - - /** - * @deprecated use {@link #addClause(List, int, int, Query)} instead. - */ - protected void addClause(Vector clauses, int conj, int mods, Query q) { - addClause((List) clauses, conj, mods, q); - } - - protected void addClause(List clauses, int conj, int mods, Query q) { - boolean required, prohibited; - - // If this term is introduced by AND, make the preceding term required, - // unless it's already prohibited - if (clauses.size() > 0 && conj == CONJ_AND) { - BooleanClause c = (BooleanClause) clauses.get(clauses.size()-1); - if (!c.isProhibited()) - c.setOccur(BooleanClause.Occur.MUST); - } - - if (clauses.size() > 0 && operator == AND_OPERATOR && conj == CONJ_OR) { - // If this term is introduced by OR, make the preceding term optional, - // unless it's prohibited (that means we leave -a OR b but +a OR b-->a OR b) - // notice if the input is a OR b, first term is parsed as required; without - // this modification a OR b would parsed as +a OR b - BooleanClause c = (BooleanClause) clauses.get(clauses.size()-1); - if (!c.isProhibited()) - c.setOccur(BooleanClause.Occur.SHOULD); - } - - // We might have been passed a null query; the term might have been - // filtered away by the analyzer. - if (q == null) - return; - - if (operator == OR_OPERATOR) { - // We set REQUIRED if we're introduced by AND or +; PROHIBITED if - // introduced by NOT or -; make sure not to set both. - prohibited = (mods == MOD_NOT); - required = (mods == MOD_REQ); - if (conj == CONJ_AND && !prohibited) { - required = true; - } - } else { - // We set PROHIBITED if we're introduced by NOT or -; We set REQUIRED - // if not PROHIBITED and not introduced by OR - prohibited = (mods == MOD_NOT); - required = (!prohibited && conj != CONJ_OR); - } - if (required && !prohibited) - clauses.add(newBooleanClause(q, BooleanClause.Occur.MUST)); - else if (!required && !prohibited) - clauses.add(newBooleanClause(q, BooleanClause.Occur.SHOULD)); - else if (!required && prohibited) - clauses.add(newBooleanClause(q, BooleanClause.Occur.MUST_NOT)); - else - throw new RuntimeException("Clause cannot be both required and prohibited"); - } - - - /** - * @exception ParseException throw in overridden method to disallow - */ - protected Query getFieldQuery(String field, String queryText) throws ParseException { - // Use the analyzer to get all the tokens, and then build a TermQuery, - // PhraseQuery, or nothing based on the term count - - TokenStream source = analyzer.tokenStream(field, new StringReader(queryText)); - CachingTokenFilter buffer = new CachingTokenFilter(source); - TermAttribute termAtt = null; - PositionIncrementAttribute posIncrAtt = null; - int numTokens = 0; - - org.apache.lucene.analysis.Token reusableToken = null; - org.apache.lucene.analysis.Token nextToken = null; - - - boolean useNewAPI = TokenStream.useNewAPIDefault(); - - if (useNewAPI) { - boolean success = false; - try { - buffer.reset(); - success = true; - } catch (IOException e) { - // success==false if we hit an exception - } - if (success) { - if (buffer.hasAttribute(TermAttribute.class)) { - termAtt = (TermAttribute) buffer.getAttribute(TermAttribute.class); - } - if (buffer.hasAttribute(PositionIncrementAttribute.class)) { - posIncrAtt = (PositionIncrementAttribute) buffer.getAttribute(PositionIncrementAttribute.class); - } - } - } else { - reusableToken = new org.apache.lucene.analysis.Token(); - } - - int positionCount = 0; - boolean severalTokensAtSamePosition = false; - - if (useNewAPI) { - if (termAtt != null) { - try { - while (buffer.incrementToken()) { - numTokens++; - int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() : 1; - if (positionIncrement != 0) { - positionCount += positionIncrement; - } else { - severalTokensAtSamePosition = true; - } - } - } catch (IOException e) { - // ignore - } - } - } else { - while (true) { - try { - nextToken = buffer.next(reusableToken); - } - catch (IOException e) { - nextToken = null; - } - if (nextToken == null) - break; - numTokens++; - if (nextToken.getPositionIncrement() != 0) - positionCount += nextToken.getPositionIncrement(); - else - severalTokensAtSamePosition = true; - } - } - try { - // rewind the buffer stream - buffer.reset(); - - // close original stream - all tokens buffered - source.close(); - } - catch (IOException e) { - // ignore - } - - if (numTokens == 0) - return null; - else if (numTokens == 1) { - String term = null; - try { - - if (useNewAPI) { - boolean hasNext = buffer.incrementToken(); - assert hasNext == true; - term = termAtt.term(); - } else { - nextToken = buffer.next(reusableToken); - assert nextToken != null; - term = nextToken.term(); - } - } catch (IOException e) { - // safe to ignore, because we know the number of tokens - } - return newTermQuery(new Term(field, term)); - } else { - if (severalTokensAtSamePosition) { - if (positionCount == 1) { - // no phrase query: - BooleanQuery q = newBooleanQuery(true); - for (int i = 0; i < numTokens; i++) { - String term = null; - try { - if (useNewAPI) { - boolean hasNext = buffer.incrementToken(); - assert hasNext == true; - term = termAtt.term(); - } else { - nextToken = buffer.next(reusableToken); - assert nextToken != null; - term = nextToken.term(); - } - } catch (IOException e) { - // safe to ignore, because we know the number of tokens - } - - Query currentQuery = newTermQuery( - new Term(field, term)); - q.add(currentQuery, BooleanClause.Occur.SHOULD); - } - return q; - } - else { - // phrase query: - MultiPhraseQuery mpq = newMultiPhraseQuery(); - mpq.setSlop(phraseSlop); - List multiTerms = new ArrayList(); - int position = -1; - for (int i = 0; i < numTokens; i++) { - String term = null; - int positionIncrement = 1; - try { - if (useNewAPI) { - boolean hasNext = buffer.incrementToken(); - assert hasNext == true; - term = termAtt.term(); - if (posIncrAtt != null) { - positionIncrement = posIncrAtt.getPositionIncrement(); - } - } else { - nextToken = buffer.next(reusableToken); - assert nextToken != null; - term = nextToken.term(); - positionIncrement = nextToken.getPositionIncrement(); - } - } catch (IOException e) { - // safe to ignore, because we know the number of tokens - } - - if (positionIncrement > 0 && multiTerms.size() > 0) { - if (enablePositionIncrements) { - mpq.add((Term[])multiTerms.toArray(new Term[0]),position); - } else { - mpq.add((Term[])multiTerms.toArray(new Term[0])); - } - multiTerms.clear(); - } - position += positionIncrement; - multiTerms.add(new Term(field, term)); - } - if (enablePositionIncrements) { - mpq.add((Term[])multiTerms.toArray(new Term[0]),position); - } else { - mpq.add((Term[])multiTerms.toArray(new Term[0])); - } - return mpq; - } - } - else { - PhraseQuery pq = newPhraseQuery(); - pq.setSlop(phraseSlop); - int position = -1; - - - for (int i = 0; i < numTokens; i++) { - String term = null; - int positionIncrement = 1; - - try { - if (useNewAPI) { - - boolean hasNext = buffer.incrementToken(); - assert hasNext == true; - term = termAtt.term(); - if (posIncrAtt != null) { - positionIncrement = posIncrAtt.getPositionIncrement(); - } - } else { - nextToken = buffer.next(reusableToken); - assert nextToken != null; - term = nextToken.term(); - positionIncrement = nextToken.getPositionIncrement(); - } - } catch (IOException e) { - // safe to ignore, because we know the number of tokens - } - - if (enablePositionIncrements) { - position += positionIncrement; - pq.add(new Term(field, term),position); - } else { - pq.add(new Term(field, term)); - } - } - return pq; - } - } - } - - - - /** - * Base implementation delegates to {@link #getFieldQuery(String,String)}. - * This method may be overridden, for example, to return - * a SpanNearQuery instead of a PhraseQuery. - * - * @exception ParseException throw in overridden method to disallow - */ - protected Query getFieldQuery(String field, String queryText, int slop) - throws ParseException { - Query query = getFieldQuery(field, queryText); - - if (query instanceof PhraseQuery) { - ((PhraseQuery) query).setSlop(slop); - } - if (query instanceof MultiPhraseQuery) { - ((MultiPhraseQuery) query).setSlop(slop); - } - - return query; - } - - - /** - * @exception ParseException throw in overridden method to disallow - */ - protected Query getRangeQuery(String field, - String part1, - String part2, - boolean inclusive) throws ParseException - { - if (lowercaseExpandedTerms) { - part1 = part1.toLowerCase(); - part2 = part2.toLowerCase(); - } - try { - DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT, locale); - df.setLenient(true); - Date d1 = df.parse(part1); - Date d2 = df.parse(part2); - if (inclusive) { - // The user can only specify the date, not the time, so make sure - // the time is set to the latest possible time of that date to really - // include all documents: - Calendar cal = Calendar.getInstance(locale); - cal.setTime(d2); - cal.set(Calendar.HOUR_OF_DAY, 23); - cal.set(Calendar.MINUTE, 59); - cal.set(Calendar.SECOND, 59); - cal.set(Calendar.MILLISECOND, 999); - d2 = cal.getTime(); - } - DateTools.Resolution resolution = getDateResolution(field); - if (resolution == null) { - // no default or field specific date resolution has been set, - // use deprecated DateField to maintain compatibilty with - // pre-1.9 Lucene versions. - part1 = DateField.dateToString(d1); - part2 = DateField.dateToString(d2); - } else { - part1 = DateTools.dateToString(d1, resolution); - part2 = DateTools.dateToString(d2, resolution); - } - } - catch (Exception e) { } - - return newRangeQuery(field, part1, part2, inclusive); - } - - /** - * Builds a new BooleanQuery instance - * @param disableCoord disable coord - * @return new BooleanQuery instance - */ - protected BooleanQuery newBooleanQuery(boolean disableCoord) { - return new BooleanQuery(disableCoord); - } - - /** - * Builds a new BooleanClause instance - * @param q sub query - * @param occur how this clause should occur when matching documents - * @return new BooleanClause instance - */ - protected BooleanClause newBooleanClause(Query q, BooleanClause.Occur occur) { - return new BooleanClause(q, occur); - } - - /** - * Builds a new TermQuery instance - * @param term term - * @return new TermQuery instance - */ - protected Query newTermQuery(Term term){ - return new TermQuery(term); - } - - /** - * Builds a new PhraseQuery instance - * @return new PhraseQuery instance - */ - protected PhraseQuery newPhraseQuery(){ - return new PhraseQuery(); - } - - /** - * Builds a new MultiPhraseQuery instance - * @return new MultiPhraseQuery instance - */ - protected MultiPhraseQuery newMultiPhraseQuery(){ - return new MultiPhraseQuery(); - } - - /** - * Builds a new PrefixQuery instance - * @param prefix Prefix term - * @return new PrefixQuery instance - */ - protected Query newPrefixQuery(Term prefix){ - PrefixQuery query = new PrefixQuery(prefix); - query.setConstantScoreRewrite(constantScoreRewrite); - return query; - } - - /** - * Builds a new FuzzyQuery instance - * @param term Term - * @param minimumSimilarity minimum similarity - * @param prefixLength prefix length - * @return new FuzzyQuery Instance - */ - protected Query newFuzzyQuery(Term term, float minimumSimilarity, int prefixLength) { - // FuzzyQuery doesn't yet allow constant score rewrite - return new FuzzyQuery(term,minimumSimilarity,prefixLength); - } - - /** - * Builds a new RangeQuery instance - * @param field Field - * @param part1 min - * @param part2 max - * @param inclusive true if range is inclusive - * @return new RangeQuery instance - */ - protected Query newRangeQuery(String field, String part1, String part2, boolean inclusive) { - RangeQuery query; - - if (constantScoreRewrite) { - // TODO: remove in Lucene 3.0 - query = new ConstantScoreRangeQuery(field, part1, part2, inclusive, inclusive, rangeCollator); - } else { - query = new RangeQuery(field, part1, part2, inclusive, inclusive, rangeCollator); - } - query.setConstantScoreRewrite(constantScoreRewrite); - return query; - } - - /** - * Builds a new MatchAllDocsQuery instance - * @return new MatchAllDocsQuery instance - */ - protected Query newMatchAllDocsQuery() { - return new MatchAllDocsQuery(); - } - - /** - * Builds a new WildcardQuery instance - * @param t wildcard term - * @return new WildcardQuery instance - */ - protected Query newWildcardQuery(Term t) { - WildcardQuery query = new WildcardQuery(t); - query.setConstantScoreRewrite(constantScoreRewrite); - return query; - } - - /** - * Factory method for generating query, given a set of clauses. - * By default creates a boolean query composed of clauses passed in. - * - * Can be overridden by extending classes, to modify query being - * returned. - * - * @param clauses List that contains {@link BooleanClause} instances - * to join. - * - * @return Resulting {@link Query} object. - * @exception ParseException throw in overridden method to disallow - * @deprecated use {@link #getBooleanQuery(List)} instead - */ - protected Query getBooleanQuery(Vector clauses) throws ParseException { - return getBooleanQuery((List) clauses, false); - } - - /** - * Factory method for generating query, given a set of clauses. - * By default creates a boolean query composed of clauses passed in. - * - * Can be overridden by extending classes, to modify query being - * returned. - * - * @param clauses List that contains {@link BooleanClause} instances - * to join. - * - * @return Resulting {@link Query} object. - * @exception ParseException throw in overridden method to disallow - */ - protected Query getBooleanQuery(List clauses) throws ParseException { - return getBooleanQuery(clauses, false); - } - - /** - * Factory method for generating query, given a set of clauses. - * By default creates a boolean query composed of clauses passed in. - * - * Can be overridden by extending classes, to modify query being - * returned. - * - * @param clauses List that contains {@link BooleanClause} instances - * to join. - * @param disableCoord true if coord scoring should be disabled. - * - * @return Resulting {@link Query} object. - * @exception ParseException throw in overridden method to disallow - * @deprecated use {@link #getBooleanQuery(List, boolean)} instead - */ - protected Query getBooleanQuery(Vector clauses, boolean disableCoord) - throws ParseException - { - return getBooleanQuery((List) clauses, disableCoord); - } - - /** - * Factory method for generating query, given a set of clauses. - * By default creates a boolean query composed of clauses passed in. - * - * Can be overridden by extending classes, to modify query being - * returned. - * - * @param clauses List that contains {@link BooleanClause} instances - * to join. - * @param disableCoord true if coord scoring should be disabled. - * - * @return Resulting {@link Query} object. - * @exception ParseException throw in overridden method to disallow - */ - protected Query getBooleanQuery(List clauses, boolean disableCoord) - throws ParseException - { - if (clauses.size()==0) { - return null; // all clause words were filtered away by the analyzer. - } - BooleanQuery query = newBooleanQuery(disableCoord); - for (int i = 0; i < clauses.size(); i++) { - query.add((BooleanClause)clauses.get(i)); - } - return query; - } - - /** - * Factory method for generating a query. Called when parser - * parses an input term token that contains one or more wildcard - * characters (? and *), but is not a prefix term token (one - * that has just a single * character at the end) - *

- * Depending on settings, prefix term may be lower-cased - * automatically. It will not go through the default Analyzer, - * however, since normal Analyzers are unlikely to work properly - * with wildcard templates. - *

- * Can be overridden by extending classes, to provide custom handling for - * wildcard queries, which may be necessary due to missing analyzer calls. - * - * @param field Name of the field query will use. - * @param termStr Term token that contains one or more wild card - * characters (? or *), but is not simple prefix term - * - * @return Resulting {@link Query} built for the term - * @exception ParseException throw in overridden method to disallow - */ - protected Query getWildcardQuery(String field, String termStr) throws ParseException - { - if ("*".equals(field)) { - if ("*".equals(termStr)) return newMatchAllDocsQuery(); - } - if (!allowLeadingWildcard && (termStr.startsWith("*") || termStr.startsWith("?"))) - throw new ParseException("'*' or '?' not allowed as first character in WildcardQuery"); - if (lowercaseExpandedTerms) { - termStr = termStr.toLowerCase(); - } - Term t = new Term(field, termStr); - return newWildcardQuery(t); - } - - /** - * Factory method for generating a query (similar to - * {@link #getWildcardQuery}). Called when parser parses an input term - * token that uses prefix notation; that is, contains a single '*' wildcard - * character as its last character. Since this is a special case - * of generic wildcard term, and such a query can be optimized easily, - * this usually results in a different query object. - *

- * Depending on settings, a prefix term may be lower-cased - * automatically. It will not go through the default Analyzer, - * however, since normal Analyzers are unlikely to work properly - * with wildcard templates. - *

- * Can be overridden by extending classes, to provide custom handling for - * wild card queries, which may be necessary due to missing analyzer calls. - * - * @param field Name of the field query will use. - * @param termStr Term token to use for building term for the query - * (without trailing '*' character!) - * - * @return Resulting {@link Query} built for the term - * @exception ParseException throw in overridden method to disallow - */ - protected Query getPrefixQuery(String field, String termStr) throws ParseException - { - if (!allowLeadingWildcard && termStr.startsWith("*")) - throw new ParseException("'*' not allowed as first character in PrefixQuery"); - if (lowercaseExpandedTerms) { - termStr = termStr.toLowerCase(); - } - Term t = new Term(field, termStr); - return newPrefixQuery(t); - } - - /** - * Factory method for generating a query (similar to - * {@link #getWildcardQuery}). Called when parser parses - * an input term token that has the fuzzy suffix (~) appended. - * - * @param field Name of the field query will use. - * @param termStr Term token to use for building term for the query - * - * @return Resulting {@link Query} built for the term - * @exception ParseException throw in overridden method to disallow - */ - protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws ParseException - { - if (lowercaseExpandedTerms) { - termStr = termStr.toLowerCase(); - } - Term t = new Term(field, termStr); - return newFuzzyQuery(t, minSimilarity, fuzzyPrefixLength); - } - - /** - * Returns a String where the escape char has been - * removed, or kept only once if there was a double escape. - * - * Supports escaped unicode characters, e. g. translates - * \\u0041 to A. - * - */ - private String discardEscapeChar(String input) throws ParseException { - // Create char array to hold unescaped char sequence - char[] output = new char[input.length()]; - - // The length of the output can be less than the input - // due to discarded escape chars. This variable holds - // the actual length of the output - int length = 0; - - // We remember whether the last processed character was - // an escape character - boolean lastCharWasEscapeChar = false; - - // The multiplier the current unicode digit must be multiplied with. - // E. g. the first digit must be multiplied with 16^3, the second with 16^2... - int codePointMultiplier = 0; - - // Used to calculate the codepoint of the escaped unicode character - int codePoint = 0; - - for (int i = 0; i < input.length(); i++) { - char curChar = input.charAt(i); - if (codePointMultiplier > 0) { - codePoint += hexToInt(curChar) * codePointMultiplier; - codePointMultiplier >>>= 4; - if (codePointMultiplier == 0) { - output[length++] = (char)codePoint; - codePoint = 0; - } - } else if (lastCharWasEscapeChar) { - if (curChar == 'u') { - // found an escaped unicode character - codePointMultiplier = 16 * 16 * 16; - } else { - // this character was escaped - output[length] = curChar; - length++; - } - lastCharWasEscapeChar = false; - } else { - if (curChar == '\\') { - lastCharWasEscapeChar = true; - } else { - output[length] = curChar; - length++; - } - } - } - - if (codePointMultiplier > 0) { - throw new ParseException("Truncated unicode escape sequence."); - } - - if (lastCharWasEscapeChar) { - throw new ParseException("Term can not end with escape character."); - } - - return new String(output, 0, length); - } - - /** Returns the numeric value of the hexadecimal character */ - private static final int hexToInt(char c) throws ParseException { - if ('0' <= c && c <= '9') { - return c - '0'; - } else if ('a' <= c && c <= 'f'){ - return c - 'a' + 10; - } else if ('A' <= c && c <= 'F') { - return c - 'A' + 10; - } else { - throw new ParseException("None-hex character in unicode escape sequence: " + c); - } - } - - /** - * Returns a String where those characters that QueryParser - * expects to be escaped are escaped by a preceding \. - */ - public static String escape(String s) { - StringBuffer sb = new StringBuffer(); - for (int i = 0; i < s.length(); i++) { - char c = s.charAt(i); - // These characters are part of the query syntax and must be escaped - if (c == '\\' || c == '+' || c == '-' || c == '!' || c == '(' || c == ')' || c == ':' - || c == '^' || c == '[' || c == ']' || c == '\"' || c == '{' || c == '}' || c == '~' - || c == '*' || c == '?' || c == '|' || c == '&') { - sb.append('\\'); - } - sb.append(c); - } - return sb.toString(); - } - - /** - * Command line tool to test QueryParser, using {@link org.apache.lucene.analysis.SimpleAnalyzer}. - * Usage:
- * java org.apache.lucene.queryParser.QueryParser <input> - */ - public static void main(String[] args) throws Exception { - if (args.length == 0) { - System.out.println("Usage: java org.apache.lucene.queryParser.QueryParser "); - System.exit(0); - } - QueryParser qp = new QueryParser("field", - new org.apache.lucene.analysis.SimpleAnalyzer()); - Query q = qp.parse(args[0]); - System.out.println(q.toString("field")); - } -} - -PARSER_END(QueryParser) - -/* ***************** */ -/* Token Definitions */ -/* ***************** */ - -<*> TOKEN : { - <#_NUM_CHAR: ["0"-"9"] > -// every character that follows a backslash is considered as an escaped character -| <#_ESCAPED_CHAR: "\\" ~[] > -| <#_TERM_START_CHAR: ( ~[ " ", "\t", "\n", "\r", "\u3000", "+", "-", "!", "(", ")", ":", "^", - "[", "]", "\"", "{", "}", "~", "*", "?", "\\" ] - | <_ESCAPED_CHAR> ) > -| <#_TERM_CHAR: ( <_TERM_START_CHAR> | <_ESCAPED_CHAR> | "-" | "+" ) > -| <#_WHITESPACE: ( " " | "\t" | "\n" | "\r" | "\u3000") > -| <#_QUOTED_CHAR: ( ~[ "\"", "\\" ] | <_ESCAPED_CHAR> ) > -} - - SKIP : { - < <_WHITESPACE>> -} - - TOKEN : { - -| -| -| -| -| -| -| -| -| : Boost -| )* "\""> -| (<_TERM_CHAR>)* > -| )+ ( "." (<_NUM_CHAR>)+ )? )? > -| (<_TERM_CHAR>)* "*" ) > -| | [ "*", "?" ]) (<_TERM_CHAR> | ( [ "*", "?" ] ))* > -| : RangeIn -| : RangeEx -} - - TOKEN : { -)+ ( "." (<_NUM_CHAR>)+ )? > : DEFAULT -} - - TOKEN : { - -| : DEFAULT -| -| -} - - TOKEN : { - -| : DEFAULT -| -| -} - -// * Query ::= ( Clause )* -// * Clause ::= ["+", "-"] [ ":"] ( | "(" Query ")" ) - -int Conjunction() : { - int ret = CONJ_NONE; -} -{ - [ - { ret = CONJ_AND; } - | { ret = CONJ_OR; } - ] - { return ret; } -} - -int Modifiers() : { - int ret = MOD_NONE; -} -{ - [ - { ret = MOD_REQ; } - | { ret = MOD_NOT; } - | { ret = MOD_NOT; } - ] - { return ret; } -} - -// This makes sure that there is no garbage after the query string -Query TopLevelQuery(String field) : -{ - Query q; -} -{ - q=Query(field) - { - return q; - } -} - -Query Query(String field) : -{ - List clauses = new ArrayList(); - Query q, firstQuery=null; - int conj, mods; -} -{ - mods=Modifiers() q=Clause(field) - { - addClause(clauses, CONJ_NONE, mods, q); - if (mods == MOD_NONE) - firstQuery=q; - } - ( - conj=Conjunction() mods=Modifiers() q=Clause(field) - { addClause(clauses, conj, mods, q); } - )* - { - if (clauses.size() == 1 && firstQuery != null) - return firstQuery; - else { - return getBooleanQuery(clauses); - } - } -} - -Query Clause(String field) : { - Query q; - Token fieldToken=null, boost=null; -} -{ - [ - LOOKAHEAD(2) - ( - fieldToken= {field=discardEscapeChar(fieldToken.image);} - | {field="*";} - ) - ] - - ( - q=Term(field) - | q=Query(field) ( boost=)? - - ) - { - if (boost != null) { - float f = (float)1.0; - try { - f = Float.valueOf(boost.image).floatValue(); - q.setBoost(f); - } catch (Exception ignored) { } - } - return q; - } -} - - -Query Term(String field) : { - Token term, boost=null, fuzzySlop=null, goop1, goop2; - boolean prefix = false; - boolean wildcard = false; - boolean fuzzy = false; - Query q; -} -{ - ( - ( - term= - | term= { wildcard=true; } - | term= { prefix=true; } - | term= { wildcard=true; } - | term= - ) - [ fuzzySlop= { fuzzy=true; } ] - [ boost= [ fuzzySlop= { fuzzy=true; } ] ] - { - String termImage=discardEscapeChar(term.image); - if (wildcard) { - q = getWildcardQuery(field, termImage); - } else if (prefix) { - q = getPrefixQuery(field, - discardEscapeChar(term.image.substring - (0, term.image.length()-1))); - } else if (fuzzy) { - float fms = fuzzyMinSim; - try { - fms = Float.valueOf(fuzzySlop.image.substring(1)).floatValue(); - } catch (Exception ignored) { } - if(fms < 0.0f || fms > 1.0f){ - throw new ParseException("Minimum similarity for a FuzzyQuery has to be between 0.0f and 1.0f !"); - } - q = getFuzzyQuery(field, termImage,fms); - } else { - q = getFieldQuery(field, termImage); - } - } - | ( ( goop1=|goop1= ) - [ ] ( goop2=|goop2= ) - ) - [ boost= ] - { - if (goop1.kind == RANGEIN_QUOTED) { - goop1.image = goop1.image.substring(1, goop1.image.length()-1); - } - if (goop2.kind == RANGEIN_QUOTED) { - goop2.image = goop2.image.substring(1, goop2.image.length()-1); - } - q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), true); - } - | ( ( goop1=|goop1= ) - [ ] ( goop2=|goop2= ) - ) - [ boost= ] - { - if (goop1.kind == RANGEEX_QUOTED) { - goop1.image = goop1.image.substring(1, goop1.image.length()-1); - } - if (goop2.kind == RANGEEX_QUOTED) { - goop2.image = goop2.image.substring(1, goop2.image.length()-1); - } - - q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), false); - } - | term= - [ fuzzySlop= ] - [ boost= ] - { - int s = phraseSlop; - - if (fuzzySlop != null) { - try { - s = Float.valueOf(fuzzySlop.image.substring(1)).intValue(); - } - catch (Exception ignored) { } - } - q = getFieldQuery(field, discardEscapeChar(term.image.substring(1, term.image.length()-1)), s); - } - ) - { - if (boost != null) { - float f = (float) 1.0; - try { - f = Float.valueOf(boost.image).floatValue(); - } - catch (Exception ignored) { - /* Should this be handled somehow? (defaults to "no boost", if - * boost number is invalid) - */ - } - - // avoid boosting null queries, such as those caused by stop words - if (q != null) { - q.setBoost(f); - } - } - return q; - } -} Index: src/java/org/apache/lucene/queryParser/Token.java =================================================================== --- src/java/org/apache/lucene/queryParser/Token.java (revision 757685) +++ src/java/org/apache/lucene/queryParser/Token.java (working copy) @@ -1,124 +0,0 @@ -/* Generated By:JavaCC: Do not edit this line. Token.java Version 4.1 */ -/* JavaCCOptions:TOKEN_EXTENDS=,KEEP_LINE_COL=null */ -package org.apache.lucene.queryParser; - -/** - * Describes the input token stream. - */ - -public class Token { - - /** - * An integer that describes the kind of this token. This numbering - * system is determined by JavaCCParser, and a table of these numbers is - * stored in the file ...Constants.java. - */ - public int kind; - - /** The line number of the first character of this Token. */ - public int beginLine; - /** The column number of the first character of this Token. */ - public int beginColumn; - /** The line number of the last character of this Token. */ - public int endLine; - /** The column number of the last character of this Token. */ - public int endColumn; - - /** - * The string image of the token. - */ - public String image; - - /** - * A reference to the next regular (non-special) token from the input - * stream. If this is the last token from the input stream, or if the - * token manager has not read tokens beyond this one, this field is - * set to null. This is true only if this token is also a regular - * token. Otherwise, see below for a description of the contents of - * this field. - */ - public Token next; - - /** - * This field is used to access special tokens that occur prior to this - * token, but after the immediately preceding regular (non-special) token. - * If there are no such special tokens, this field is set to null. - * When there are more than one such special token, this field refers - * to the last of these special tokens, which in turn refers to the next - * previous special token through its specialToken field, and so on - * until the first special token (whose specialToken field is null). - * The next fields of special tokens refer to other special tokens that - * immediately follow it (without an intervening regular token). If there - * is no such token, this field is null. - */ - public Token specialToken; - - /** - * An optional attribute value of the Token. - * Tokens which are not used as syntactic sugar will often contain - * meaningful values that will be used later on by the compiler or - * interpreter. This attribute value is often different from the image. - * Any subclass of Token that actually wants to return a non-null value can - * override this method as appropriate. - */ - public Object getValue() { - return null; - } - - /** - * No-argument constructor - */ - public Token() {} - - /** - * Constructs a new token for the specified Image. - */ - public Token(int kind) - { - this(kind, null); - } - - /** - * Constructs a new token for the specified Image and Kind. - */ - public Token(int kind, String image) - { - this.kind = kind; - this.image = image; - } - - /** - * Returns the image. - */ - public String toString() - { - return image; - } - - /** - * Returns a new Token object, by default. However, if you want, you - * can create and return subclass objects based on the value of ofKind. - * Simply add the cases to the switch for all those special cases. - * For example, if you have a subclass of Token called IDToken that - * you want to create if ofKind is ID, simply add something like : - * - * case MyParserConstants.ID : return new IDToken(ofKind, image); - * - * to the following switch statement. Then you can cast matchedToken - * variable to the appropriate type and use sit in your lexical actions. - */ - public static Token newToken(int ofKind, String image) - { - switch(ofKind) - { - default : return new Token(ofKind, image); - } - } - - public static Token newToken(int ofKind) - { - return newToken(ofKind, null); - } - -} -/* JavaCC - OriginalChecksum=37b1923f964a5a434f5ea3d6952ff200 (do not edit this line) */ Index: src/java/org/apache/lucene/queryParser/messages/QueryParserMessages.java =================================================================== --- src/java/org/apache/lucene/queryParser/messages/QueryParserMessages.java (revision 0) +++ src/java/org/apache/lucene/queryParser/messages/QueryParserMessages.java (revision 0) @@ -0,0 +1,50 @@ +package org.apache.lucene.queryParser.messages; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.messages.NLS; + +/** + * Flexible Query Parser message bundle class + */ +public class QueryParserMessages extends NLS { + + private static final String BUNDLE_NAME= QueryParserMessages.class.getName(); + + private QueryParserMessages() { + // Do not instantiate + } + + static { + // register all string ids with NLS class and initialize static string values + NLS.initializeMessages(BUNDLE_NAME, QueryParserMessages.class); + } + + // static string must match the strings in the property files. + public static String INVALID_SYNTAX; + public static String INVALID_SYNTAX_CANNOT_PARSE; + public static String INVALID_SYNTAX_FUZZY_LIMITS; + public static String INVALID_SYNTAX_ESCAPE_UNICODE_TRUNCATION; + public static String INVALID_SYNTAX_ESCAPE_CHARACTER; + public static String INVALID_SYNTAX_ESCAPE_NONE_HEX_UNICODE; + public static String NODE_ACTION_NOT_SUPPORTED; + public static String PARAMETER_VALUE_NOT_SUPPORTED; + public static String LUCENE_QUERY_CONVERSION_ERROR; + public static String EMPTY_MESSAGE; + +} Index: src/java/org/apache/lucene/queryParser/messages/QueryParserMessages.properties =================================================================== --- src/java/org/apache/lucene/queryParser/messages/QueryParserMessages.properties (revision 0) +++ src/java/org/apache/lucene/queryParser/messages/QueryParserMessages.properties (revision 0) @@ -0,0 +1,52 @@ + # Licensed to the Apache Software Foundation (ASF) under one or more + # contributor license agreements. See the NOTICE file distributed with + # this work for additional information regarding copyright ownership. + # The ASF licenses this file to You under the Apache License, Version 2.0 + # (the "License"); you may not use this file except in compliance with + # the License. You may obtain a copy of the License at + # + # http://www.apache.org/licenses/LICENSE-2.0 + # + # Unless required by applicable law or agreed to in writing, software + # distributed under the License is distributed on an "AS IS" BASIS, + # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + # See the License for the specific language governing permissions and + # limitations under the License. + +# This resource bundle contains Flexible Query Parser messages. + +#Apache Lucene Community +# +INVALID_SYNTAX = Syntax Error: {0} + +#Apache Lucene Community +# +# +INVALID_SYNTAX_CANNOT_PARSE = Syntax Error, cannot parse '{0}': {1} + +#Apache Lucene Community +INVALID_SYNTAX_FUZZY_LIMITS = The similarity value for a fuzzy search must be between 0.0 and 1.0. + +#Apache Lucene Community +INVALID_SYNTAX_ESCAPE_UNICODE_TRUNCATION = Truncated unicode escape sequence. + +#Apache Lucene Community +INVALID_SYNTAX_ESCAPE_CHARACTER = Term can not end with escape character. + +#Apache Lucene Community +INVALID_SYNTAX_ESCAPE_NONE_HEX_UNICODE = None-hex character in unicode escape sequence: {0} + +#Apache Lucene Community +NODE_ACTION_NOT_SUPPORTED = This node does not support this action. + +#Apache Lucene Community +PARAMETER_VALUE_NOT_SUPPORTED = Parameter '{1}' with value '{0}' not supported. + +#Apache Lucene Community +# +# +LUCENE_QUERY_CONVERSION_ERROR = Cannot convert query to lucene syntax: '{0}' error: '{1}' + +#Apache Lucene Community +EMPTY_MESSAGE = + Index: src/java/org/apache/lucene/queryParser/messages/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/messages/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/messages/package.html (revision 0) @@ -0,0 +1,25 @@ + + + + + + + +Messages for the Flexible Query Parser, using org.apache.lucene.messages.NLS API. + + Index: src/java/org/apache/lucene/queryParser/lucene2/MultiFieldQueryParserWrapper.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/MultiFieldQueryParserWrapper.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/MultiFieldQueryParserWrapper.java (revision 0) @@ -0,0 +1,250 @@ +package org.apache.lucene.queryParser.lucene2; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Map; + +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.queryParser.lucene2.config.LuceneMultiFieldQueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.MultiFieldQueryNodeProcessor; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorPipeline; +import org.apache.lucene.queryParser.MultiFieldQueryParser; +import org.apache.lucene.queryParser.ParseException; +import org.apache.lucene.queryParser.QueryParser; +import org.apache.lucene.search.BooleanClause; +import org.apache.lucene.search.BooleanQuery; +import org.apache.lucene.search.Query; + + +/** + * This class behaves as the {@link MultiFieldQueryParser}, but uses the new query parser + * interface instead of the old one. + *

+ * This class should be used when the new query parser features are needed and also keep + * at the same time the old query parser interface. + *
+ * @depracated this class will be removed soon, it's a temporary class to be used + * along the transition from the old query parser to the new one + */ +public class MultiFieldQueryParserWrapper extends QueryParserWrapper { + protected String[] fields; + + protected Map boosts; + + /** + * Creates a MultiFieldQueryParser. + * Allows passing of a map with term to Boost, and the boost to apply to each term. + * + *

It will, when parse(String query) + * is called, construct a query like this (assuming the query consists of + * two terms and you specify the two fields title and body):

+ * + * + * (title:term1 body:term1) (title:term2 body:term2) + * + * + *

When setDefaultOperator(AND_OPERATOR) is set, the result will be:

+ * + * + * +(title:term1 body:term1) +(title:term2 body:term2) + * + * + *

When you pass a boost (title=>5 body=>10) you can get

+ * + * + * +(title:term1^5.0 body:term1^10.0) +(title:term2^5.0 body:term2^10.0) + * + * + *

In other words, all the query's terms must appear, but it doesn't matter in + * what fields they appear.

+ */ + public MultiFieldQueryParserWrapper(String[] fields, Analyzer analyzer, Map boosts) { + this(fields, analyzer); + this.boosts = boosts; + this.fields = fields; + + setQueryConfig(new LuceneMultiFieldQueryConfigHandler(this, null, + fields, boosts)); + + } + + /** + * Creates a MultiFieldQueryParser. + * + *

It will, when parse(String query) + * is called, construct a query like this (assuming the query consists of + * two terms and you specify the two fields title and body):

+ * + * + * (title:term1 body:term1) (title:term2 body:term2) + * + * + *

When setDefaultOperator(AND_OPERATOR) is set, the result will be:

+ * + * + * +(title:term1 body:term1) +(title:term2 body:term2) + * + * + *

In other words, all the query's terms must appear, but it doesn't matter in + * what fields they appear.

+ */ + public MultiFieldQueryParserWrapper(String[] fields, Analyzer analyzer) { + super(null, analyzer); + + this.fields = fields; + setQueryConfig(new LuceneMultiFieldQueryConfigHandler(this, null, + fields, null)); + + QueryNodeProcessorPipeline newProcessorPipeline = new QueryNodeProcessorPipeline(); + newProcessorPipeline.addProcessor(new MultiFieldQueryNodeProcessor()); + newProcessorPipeline.addProcessor(getQueryProcessor()); + + setQueryProcessor(newProcessorPipeline); + + } + + /** + * Parses a query which searches on the fields specified. + *

+ * If x fields are specified, this effectively constructs: + * 

+     * 
+     * (field1:query1) (field2:query2) (field3:query3)...(fieldx:queryx)
+     * 
+     *
+ * @param queries Queries strings to parse + * @param fields Fields to search on + * @param analyzer Analyzer to use + * @throws ParseException if query parsing fails + * @throws IllegalArgumentException if the length of the queries array differs + * from the length of the fields array + */ + public static Query parse(String[] queries, String[] fields, + Analyzer analyzer) throws ParseException { + if (queries.length != fields.length) + throw new IllegalArgumentException( + "queries.length != fields.length"); + BooleanQuery bQuery = new BooleanQuery(); + for (int i = 0; i < fields.length; i++) { + QueryParserWrapper qp = new QueryParserWrapper(fields[i], analyzer); + Query q = qp.parse(queries[i]); + if (q != null && // q never null, just being defensive + (!(q instanceof BooleanQuery) || ((BooleanQuery) q).getClauses().length > 0)) { + bQuery.add(q, BooleanClause.Occur.SHOULD); + } + } + return bQuery; + } + + /** + * Parses a query, searching on the fields specified. + * Use this if you need to specify certain fields as required, + * and others as prohibited. + * 

+     * Usage:
+     * 
+     * String[] fields = {"filename", "contents", "description"};
+     * BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD,
+     *                BooleanClause.Occur.MUST,
+     *                BooleanClause.Occur.MUST_NOT};
+     * MultiFieldQueryParser.parse("query", fields, flags, analyzer);
+     * 
+     *
+ *

+ * The code above would construct a query: + * 

+     * 
+     * (filename:query) +(contents:query) -(description:query)
+     * 
+     *
+ * + * @param query Query string to parse + * @param fields Fields to search on + * @param flags Flags describing the fields + * @param analyzer Analyzer to use + * @throws ParseException if query parsing fails + * @throws IllegalArgumentException if the length of the fields array differs + * from the length of the flags array + */ + public static Query parse(String query, String[] fields, + BooleanClause.Occur[] flags, Analyzer analyzer) + throws ParseException { + if (fields.length != flags.length) + throw new IllegalArgumentException("fields.length != flags.length"); + BooleanQuery bQuery = new BooleanQuery(); + for (int i = 0; i < fields.length; i++) { + QueryParserWrapper qp = new QueryParserWrapper(fields[i], analyzer); + Query q = qp.parse(query); + if (q != null && // q never null, just being defensive + (!(q instanceof BooleanQuery) || ((BooleanQuery) q).getClauses().length > 0)) { + bQuery.add(q, flags[i]); + } + } + return bQuery; + } + + /** + * Parses a query, searching on the fields specified. + * Use this if you need to specify certain fields as required, + * and others as prohibited. + * 

+     * Usage:
+     * 
+     * String[] query = {"query1", "query2", "query3"};
+     * String[] fields = {"filename", "contents", "description"};
+     * BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD,
+     *                BooleanClause.Occur.MUST,
+     *                BooleanClause.Occur.MUST_NOT};
+     * MultiFieldQueryParser.parse(query, fields, flags, analyzer);
+     * 
+     *
+ *

+ * The code above would construct a query: + * 

+     * 
+     * (filename:query1) +(contents:query2) -(description:query3)
+     * 
+     *
+ * + * @param queries Queries string to parse + * @param fields Fields to search on + * @param flags Flags describing the fields + * @param analyzer Analyzer to use + * @throws ParseException if query parsing fails + * @throws IllegalArgumentException if the length of the queries, fields, + * and flags array differ + */ + public static Query parse(String[] queries, String[] fields, + BooleanClause.Occur[] flags, Analyzer analyzer) + throws ParseException { + if (!(queries.length == fields.length && queries.length == flags.length)) + throw new IllegalArgumentException( + "queries, fields, and flags array have have different length"); + BooleanQuery bQuery = new BooleanQuery(); + for (int i = 0; i < fields.length; i++) { + QueryParserWrapper qp = new QueryParserWrapper(fields[i], analyzer); + Query q = qp.parse(queries[i]); + if (q != null && // q never null, just being defensive + (!(q instanceof BooleanQuery) || ((BooleanQuery) q).getClauses().length > 0)) { + bQuery.add(q, flags[i]); + } + } + return bQuery; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/QueryParserWrapper.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/QueryParserWrapper.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/QueryParserWrapper.java (revision 0) @@ -0,0 +1,360 @@ +package org.apache.lucene.queryParser.lucene2; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.text.Collator; +import java.util.List; +import java.util.Locale; + +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.document.DateTools.Resolution; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.FieldConfig; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.builders.LuceneQueryBuilder; +import org.apache.lucene.queryParser.lucene2.builders.LuceneQueryTreeBuilder; +import org.apache.lucene.queryParser.lucene2.config.AllowLeadingWildcardAttribute; +import org.apache.lucene.queryParser.lucene2.config.ConstantScoreRewriteAttribute; +import org.apache.lucene.queryParser.lucene2.config.DateResolutionAttribute; +import org.apache.lucene.queryParser.lucene2.config.DefaultOperatorAttribute; +import org.apache.lucene.queryParser.lucene2.config.DefaultPhraseSlopAttribute; +import org.apache.lucene.queryParser.lucene2.config.LocaleAttribute; +import org.apache.lucene.queryParser.lucene2.config.LowercaseExpandedTermsAttribute; +import org.apache.lucene.queryParser.lucene2.config.LuceneQueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.config.PositionIncrementsAttribute; +import org.apache.lucene.queryParser.lucene2.config.RangeCollatorAttribute; +import org.apache.lucene.queryParser.lucene2.processors.LuceneQueryNodeProcessorPipeline; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessor; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorPipeline; +import org.apache.lucene.queryParser.ParseException; +import org.apache.lucene.queryParser.QueryParser; +import org.apache.lucene.search.Query; + +/** + * This class extends {@link QueryParser} and overrides every method. It performs the + * query parsing using the new query parser instead of the old one. + *

+ * This class should be used when the new query parser features are needed and also keep + * at the same time the old query parser interface. + *
+ * @depracated this class will be removed soon, it's a temporary class to be used + * along the transition from the old query parser to the new one + */ +public class QueryParserWrapper extends QueryParser { + + private org.apache.lucene.queryParser.lucene2.parser.QueryParser luceneQueryParser = new org.apache.lucene.queryParser.lucene2.parser.QueryParser(); + + private LuceneQueryConfigHandler config; + + private QueryNodeProcessor processorPipeline; + + private LuceneQueryBuilder builder = new LuceneQueryTreeBuilder(); + + public QueryParserWrapper(String defaultField, Analyzer analizer) { + super(defaultField, analizer); + this.config = new LuceneQueryConfigHandler(this, null); + this.processorPipeline = new LuceneQueryNodeProcessorPipeline( + this.config); + + } + + /** + * Sets the {@link LuceneQueryBuilder} used to generate a {@link Query} object + * from the parsed and processed query node tree. + * + * @param builder the builder + * @see QueryParserWrapper#setQueryProcessor(QueryNodeProcessor) + */ + public void setQueryBuilder(LuceneQueryBuilder builder) { + this.builder = builder; + } + + /** + * Sets the {@link QueryNodeProcessor} used to process the + * query node tree generated by the {@link org.apache.lucene.queryParser.lucene2.parser.QueryParser}, the + * {@link QueryConfigHandler} already set to this object + * is automatically set to the new processor. + * + * @param processor the processor + * @see QueryParserWrapper#setQueryBuilder(LuceneQueryBuilder) + * @see QueryParserWrapper#setQueryConfig(LuceneQueryConfigHandler) + */ + public void setQueryProcessor(QueryNodeProcessor processor) { + this.processorPipeline = processor; + this.processorPipeline.setQueryConfigHandler(this.config); + + } + + /** + * Sets the {@link QueryConfigHandler} used by the {@link QueryNodeProcessor} + * set to this object. + * + * @param queryConfig the query config handler + * @see QueryParserWrapper#setQueryProcessor(QueryNodeProcessor) + */ + public void setQueryConfig(LuceneQueryConfigHandler queryConfig) { + this.config = queryConfig; + + if (this.processorPipeline != null) { + this.processorPipeline.setQueryConfigHandler(this.config); + } + + } + + /** + * Returns {@link QueryNodeProcessor} used to process the query + * node tree generated by the {@link org.apache.lucene.queryParser.lucene2.parser.QueryParser}. + * + * @return + */ + public QueryNodeProcessor getQueryProcessor() { + return this.processorPipeline; + } + + public ParseException generateParseException() { + return null; + } + + public boolean getAllowLeadingWildcard() { + + if (this.config != null && this.config.hasAttribute(AllowLeadingWildcardAttribute.class)) { + return ((AllowLeadingWildcardAttribute) this.config.getAttribute(AllowLeadingWildcardAttribute.class)).isAllowLeadingWildcard(); + } + + return super.getAllowLeadingWildcard(); + + } + + public boolean getConstantScoreRewrite() { + + if (this.config != null && this.config.hasAttribute(ConstantScoreRewriteAttribute.class)) { + return ((ConstantScoreRewriteAttribute) this.config.getAttribute(ConstantScoreRewriteAttribute.class)).isConstantScoreRewrite(); + } + + return super.getConstantScoreRewrite(); + + } + + public Resolution getDateResolution(String fieldName) { + + if (this.config != null) { + FieldConfig fieldConfig = this.config.getFieldConfig(fieldName); + + if (fieldConfig != null) { + + if (this.config.hasAttribute(DateResolutionAttribute.class)) { + return ((DateResolutionAttribute) this.config.getAttribute(DateResolutionAttribute.class)).getDateResolution(); + } + + } + + } + + return null; + + } + + public boolean getEnablePositionIncrements() { + + if (this.config != null && this.config.hasAttribute(PositionIncrementsAttribute.class)) { + return ((PositionIncrementsAttribute) this.config.getAttribute(PositionIncrementsAttribute.class)).isPositionIncrementsEnabled(); + } + + return super.getEnablePositionIncrements(); + + } + + public float getFuzzyMinSim() { + return super.getFuzzyMinSim(); + } + + public int getFuzzyPrefixLength() { + return super.getFuzzyPrefixLength(); + } + + public Locale getLocale() { + + if (this.config != null && this.config.hasAttribute(LocaleAttribute.class)) { + return ((LocaleAttribute) this.config.getAttribute(LocaleAttribute.class)).getLocale(); + } + + return super.getLocale(); + + } + + public boolean getLowercaseExpandedTerms() { + + if (this.config != null && this.config.hasAttribute(LowercaseExpandedTermsAttribute.class)) { + return ((LowercaseExpandedTermsAttribute) this.config.getAttribute(LowercaseExpandedTermsAttribute.class)).isLowercaseExpandedTerms(); + } + + return super.getLowercaseExpandedTerms(); + + } + + public int getPhraseSlop() { + + if (this.config != null && this.config.hasAttribute(AllowLeadingWildcardAttribute.class)) { + return ((DefaultPhraseSlopAttribute) this.config.getAttribute(DefaultPhraseSlopAttribute.class)).getDefaultPhraseSlop(); + } + + return super.getPhraseSlop(); + + } + + public Collator getRangeCollator() { + + if (this.config != null && this.config.hasAttribute(RangeCollatorAttribute.class)) { + return ((RangeCollatorAttribute) this.config.getAttribute(RangeCollatorAttribute.class)).getRangeCollator(); + } + + return super.getRangeCollator(); + + } + + public boolean getUseOldRangeQuery() { + return !getConstantScoreRewrite(); + } + + public Query parse(String query) throws ParseException { + + try { + QueryNode queryTree = this.luceneQueryParser.parse(query, getField()); + queryTree = this.processorPipeline.process(queryTree); + return (Query) this.builder.build(queryTree); + + } catch (QueryNodeException e) { + throw new ParseException("parse exception"); + } + + } + + public void setAllowLeadingWildcard(boolean allowLeadingWildcard) { + this.config.setAllowLeadingWildcard(allowLeadingWildcard); + } + + public void setConstantScoreRewrite(boolean constantScoreRewrite) { + this.config.setConstantScoreRewrite(constantScoreRewrite); + } + + public void setDateResolution(Resolution dateResolution) { + this.config.setDateResolution(dateResolution); + } + + public void setDateResolution(String fieldName, Resolution dateResolution) { + this.config.setDateResolution(fieldName, dateResolution); + } + + public void setDefaultOperator(QueryParserWrapper.Operator op) { + this.config.setDefaultOperator(op); + } + + public QueryParserWrapper.Operator getDefaultOperator() { + + if (this.config != null && this.config.hasAttribute(DefaultOperatorAttribute.class)) { + return ((DefaultOperatorAttribute) this.config.getAttribute(DefaultOperatorAttribute.class)).getDefaultOperator(); + } + + return super.getDefaultOperator(); + + } + + public void setEnablePositionIncrements(boolean enable) { + this.config.setPositionIncrementsEnabled(enable); + } + + public void setFuzzyMinSim(float fuzzyMinSim) { + // TODO Auto-generated method stub + + } + + public void setFuzzyPrefixLength(int fuzzyPrefixLength) { + // TODO Auto-generated method stub + + } + + public void setLocale(Locale locale) { + this.config.setLocale(locale); + } + + public void setLowercaseExpandedTerms(boolean lowercaseExpandedTerms) { + this.config.setLowercaseExpandedTerms(lowercaseExpandedTerms); + } + + public void setPhraseSlop(int phraseSlop) { + this.config.setDefaultPhraseSlop(phraseSlop); + } + + public void setRangeCollator(Collator rc) { + this.config.setRangeCollator(rc); + } + + public void setUseOldRangeQuery(boolean useOldRangeQuery) { + super.setUseOldRangeQuery(useOldRangeQuery); + } + + protected Query getPrefixQuery(String field, String termStr) + throws ParseException { + throw new UnsupportedOperationException(); + } + + protected Query getWildcardQuery(String field, String termStr) + throws ParseException { + throw new UnsupportedOperationException(); + } + + protected Query getFuzzyQuery(String field, String termStr, + float minSimilarity) throws ParseException { + throw new UnsupportedOperationException(); + } + + /** + * @exception ParseException throw in overridden method to disallow + */ + protected Query getFieldQuery(String field, String queryText) + throws ParseException { + throw new UnsupportedOperationException(); + } + + protected Query getBooleanQuery(List clauses, boolean disableCoord) + throws ParseException { + throw new UnsupportedOperationException(); + } + + /** + * Base implementation delegates to {@link #getFieldQuery(String,String)}. + * This method may be overridden, for example, to return + * a SpanNearQuery instead of a PhraseQuery. + * + * @exception ParseException throw in overridden method to disallow + */ + protected Query getFieldQuery(String field, String queryText, int slop) + throws ParseException { + throw new UnsupportedOperationException(); + } + + /** + * @exception ParseException throw in overridden method to disallow + */ + protected Query getRangeQuery(String field, String part1, String part2, + boolean inclusive) throws ParseException { + throw new UnsupportedOperationException(); + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/builders/BooleanQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/BooleanQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/BooleanQueryNodeBuilder.java (revision 0) @@ -0,0 +1,107 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.BooleanClause; +import org.apache.lucene.search.BooleanQuery; +import org.apache.lucene.search.Query; +import org.apache.lucene.search.BooleanQuery.TooManyClauses; + + +/** + * Builds a {@link BooleanQuery} object from a {@link BooleanQueryNode} object. + * Every children in the {@link BooleanQueryNode} object must be already + * tagged using {@link QueryTreeBuilder#QUERY_TREE_BUILDER_TAGID} with + * a {@link Query} object. + *

+ * It takes in consideration if the children is a {@link ModifierQueryNode} + * to define the {@link BooleanClause}. + */ +public class BooleanQueryNodeBuilder implements LuceneQueryBuilder { + + public BooleanQueryNodeBuilder() { + // empty constructor + } + + public BooleanQuery build(QueryNode queryNode) throws QueryNodeException { + BooleanQueryNode booleanNode = (BooleanQueryNode) queryNode; + + BooleanQuery bQuery = new BooleanQuery(); + List children = booleanNode.getChildren(); + + if (children != null) { + + for (QueryNode child : children) { + Object obj = child.getTag(QueryTreeBuilder.QUERY_TREE_BUILDER_TAGID); + + if (obj != null) { + Query query = (Query) obj; + + try { + bQuery.add(query, getModifierValue(child)); + } catch (TooManyClauses ex) { + + // TODO: create a good message for this exception + throw new QueryNodeException(new MessageImpl( + QueryParserMessages.EMPTY_MESSAGE), ex); + + } + + } + + } + + } + + return bQuery; + + } + + private static BooleanClause.Occur getModifierValue(QueryNode node) + throws QueryNodeException { + + if (node instanceof ModifierQueryNode) { + ModifierQueryNode mNode = ((ModifierQueryNode) node); + switch (mNode.getModifier()) { + case MOD_REQ: + return BooleanClause.Occur.MUST; + case MOD_NOT: + return BooleanClause.Occur.MUST_NOT; + + // TODO: what should be the best way to get the default modifier + case MOD_NONE: + return BooleanClause.Occur.SHOULD; + + } + + } + + return BooleanClause.Occur.SHOULD; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/BoostQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/BoostQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/BoostQueryNodeBuilder.java (revision 0) @@ -0,0 +1,52 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.nodes.BoostQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.Query; + +/** + * This builder basically reads the {@link Query} object set on the {@link BoostQueryNode} child + * using {@link QueryTreeBuilder#QUERY_TREE_BUILDER_TAGID} and applies + * the boost value defined in the {@link BoostQueryNode}. + */ +public class BoostQueryNodeBuilder implements LuceneQueryBuilder { + + public BoostQueryNodeBuilder() { + // empty constructor + } + + public Query build(QueryNode queryNode) throws QueryNodeException { + BoostQueryNode boostNode = (BoostQueryNode) queryNode; + QueryNode child = boostNode.getChild(); + + if (child == null) { + return null; + } + + Query query = (Query) child.getTag(QueryTreeBuilder.QUERY_TREE_BUILDER_TAGID); + query.setBoost(boostNode.getValue()); + + return query; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/FieldQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/FieldQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/FieldQueryNodeBuilder.java (revision 0) @@ -0,0 +1,43 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.index.Term; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.TermQuery; + + +/** + * Builds a {@link TermQuery} object from a {@link AbstractTermQueryNode} object. + */ +public class FieldQueryNodeBuilder implements LuceneQueryBuilder { + + public FieldQueryNodeBuilder() { + // empty constructor + } + + public TermQuery build(QueryNode queryNode) throws QueryNodeException { + FieldQueryNode fieldNode = (FieldQueryNode) queryNode; + + return new TermQuery(new Term(fieldNode.getFieldAsString(), fieldNode.getTextAsString())); + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/FuzzyQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/FuzzyQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/FuzzyQueryNodeBuilder.java (revision 0) @@ -0,0 +1,45 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.index.Term; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.FuzzyQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.FuzzyQuery; + + +/** + * Builds a {@link FuzzyQuery} object from a {@link FuzzyQueryNode} object. + */ +public class FuzzyQueryNodeBuilder implements LuceneQueryBuilder { + + public FuzzyQueryNodeBuilder() { + // empty constructor + } + + public FuzzyQuery build(QueryNode queryNode) throws QueryNodeException { + FuzzyQueryNode fuzzyNode = (FuzzyQueryNode) queryNode; + + // TODO: the prefix length should be extracted from the FuzzyQueryNode instead of using the default one + return new FuzzyQuery(new Term(fuzzyNode.getFieldAsString(), fuzzyNode.getTextAsString()), + fuzzyNode.getSimilarity(), FuzzyQuery.defaultPrefixLength); + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/GroupQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/GroupQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/GroupQueryNodeBuilder.java (revision 0) @@ -0,0 +1,45 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.nodes.GroupQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.Query; + + +/** + * Builds no object, it only returns the {@link Query} object + * set on the {@link GroupQueryNode} object using a {@link QueryTreeBuilder#QUERY_TREE_BUILDER_TAGID} + * tag. + */ +public class GroupQueryNodeBuilder implements LuceneQueryBuilder { + + public GroupQueryNodeBuilder() { + // empty constructor + } + + public Query build(QueryNode queryNode) throws QueryNodeException { + GroupQueryNode groupNode = (GroupQueryNode) queryNode; + + return (Query) (groupNode).getChild().getTag(QueryTreeBuilder.QUERY_TREE_BUILDER_TAGID); + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/LuceneBooleanQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/LuceneBooleanQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/LuceneBooleanQueryNodeBuilder.java (revision 0) @@ -0,0 +1,108 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.lucene2.nodes.LuceneBooleanQueryNode; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode.Modifier; +import org.apache.lucene.search.BooleanClause; +import org.apache.lucene.search.BooleanQuery; +import org.apache.lucene.search.Query; +import org.apache.lucene.search.Similarity; +import org.apache.lucene.search.BooleanQuery.TooManyClauses; + + +/** + * This builder does the same as the {@link BooleanQueryNodeBuilder}, but this + * considers if the built {@link BooleanQuery} should have its coord + * disabled or not. + *
+ * @see BooleanQueryNodeBuilder + * @see BooleanQuery + * @see Similarity#coord(int, int) + */ +public class LuceneBooleanQueryNodeBuilder implements LuceneQueryBuilder { + + public LuceneBooleanQueryNodeBuilder() { + // empty constructor + } + + public BooleanQuery build(QueryNode queryNode) throws QueryNodeException { + LuceneBooleanQueryNode booleanNode = (LuceneBooleanQueryNode) queryNode; + + BooleanQuery bQuery = new BooleanQuery(booleanNode.isDisableCoord()); + List children = booleanNode.getChildren(); + + if (children != null) { + + for (QueryNode child : children) { + Object obj = child.getTag(QueryTreeBuilder.QUERY_TREE_BUILDER_TAGID); + + if (obj != null) { + Query query = (Query) obj; + + try { + bQuery.add(query, getModifierValue(child)); + } catch (TooManyClauses ex) { + + // TODO: create a good message for this exception + throw new QueryNodeException(new MessageImpl( + QueryParserMessages.EMPTY_MESSAGE), ex); + + } + + } + + } + + } + + return bQuery; + + } + + private static BooleanClause.Occur getModifierValue(QueryNode node) + throws QueryNodeException { + + if (node instanceof ModifierQueryNode) { + ModifierQueryNode mNode = ((ModifierQueryNode) node); + Modifier modifier = mNode.getModifier(); + + if (Modifier.MOD_NONE.equals(modifier)) { + return BooleanClause.Occur.SHOULD; + + } else if (Modifier.MOD_NOT.equals(modifier)) { + return BooleanClause.Occur.MUST_NOT; + + } else { + return BooleanClause.Occur.MUST; + } + } + + return BooleanClause.Occur.SHOULD; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/LuceneQueryBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/LuceneQueryBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/LuceneQueryBuilder.java (revision 0) @@ -0,0 +1,38 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryBuilder; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.Query; + + +/** + * This interface should be implemented by every class that wants to build + * {@link Query} objects from a {@link QueryNode} object. + *
+ * @see QueryBuilder + * @see QueryTreeBuilder + */ +public interface LuceneQueryBuilder extends QueryBuilder { + + public Query build(QueryNode queryNode) throws QueryNodeException; + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/LuceneQueryTreeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/LuceneQueryTreeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/LuceneQueryTreeBuilder.java (revision 0) @@ -0,0 +1,75 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.lucene2.nodes.LuceneBooleanQueryNode; +import org.apache.lucene.queryParser.lucene2.nodes.MultiPhraseQueryNode; +import org.apache.lucene.queryParser.lucene2.nodes.RangeQueryNode; +import org.apache.lucene.queryParser.lucene2.processors.LuceneQueryNodeProcessorPipeline; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.BoostQueryNode; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.FuzzyQueryNode; +import org.apache.lucene.queryParser.nodes.GroupQueryNode; +import org.apache.lucene.queryParser.nodes.MatchAllDocsQueryNode; +import org.apache.lucene.queryParser.nodes.MatchNoDocsQueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.SlopQueryNode; +import org.apache.lucene.queryParser.nodes.PrefixWildcardQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.TokenizedPhraseQueryNode; +import org.apache.lucene.queryParser.nodes.WildcardQueryNode; +import org.apache.lucene.search.Query; + + +/** + * This query tree builder only defines the necessary map to build a {@link Query} object. + * It should be used to generate a {@link Query} object from a query node tree processed by + * a {@link LuceneQueryNodeProcessorPipeline}. + *
+ * @see QueryTreeBuilder + * @see LuceneQueryNodeProcessorPipeline + */ +public class LuceneQueryTreeBuilder extends QueryTreeBuilder implements LuceneQueryBuilder { + + public LuceneQueryTreeBuilder() { + setBuilder(GroupQueryNode.class, new GroupQueryNodeBuilder()); + setBuilder(FieldQueryNode.class, new FieldQueryNodeBuilder()); + setBuilder(BooleanQueryNode.class, new BooleanQueryNodeBuilder()); + setBuilder(FuzzyQueryNode.class, new FuzzyQueryNodeBuilder()); + setBuilder(BoostQueryNode.class, new BoostQueryNodeBuilder()); + setBuilder(ModifierQueryNode.class, new ModifierQueryNodeBuilder()); + setBuilder(WildcardQueryNode.class, new WildcardQueryNodeBuilder()); + setBuilder(TokenizedPhraseQueryNode.class, new PhraseQueryNodeBuilder()); + setBuilder(MatchNoDocsQueryNode.class, new MatchNoDocsQueryNodeBuilder()); + setBuilder(PrefixWildcardQueryNode.class, new PrefixWildcardQueryNodeBuilder()); + setBuilder(RangeQueryNode.class, new RangeQueryNodeBuilder()); + setBuilder(SlopQueryNode.class, new SlopQueryNodeBuilder()); + setBuilder(LuceneBooleanQueryNode.class, new LuceneBooleanQueryNodeBuilder()); + setBuilder(MultiPhraseQueryNode.class, new MultiPhraseQueryNodeBuilder()); + setBuilder(MatchAllDocsQueryNode.class, new MatchAllDocsQueryNodeBuilder()); + + } + + public Query build(QueryNode queryNode) throws QueryNodeException { + return (Query) super.build(queryNode); + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/MatchAllDocsQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/MatchAllDocsQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/MatchAllDocsQueryNodeBuilder.java (revision 0) @@ -0,0 +1,50 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.MatchAllDocsQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.MatchAllDocsQuery; + + +/** + * Builds a {@link MatchAllDocsQuery} object from a {@link MatchAllDocsQueryNode} object. + */ +public class MatchAllDocsQueryNodeBuilder implements LuceneQueryBuilder { + + public MatchAllDocsQueryNodeBuilder() { + // empty constructor + } + + public MatchAllDocsQuery build(QueryNode queryNode) throws QueryNodeException { + + // validates node + if (!(queryNode instanceof MatchAllDocsQueryNode)) { + + // TODO: node should be converted to a readable query instead of just invoking node.toString() + throw new QueryNodeException(new MessageImpl("Q0019E.LUCENE_QUERY_CONVERSION_ERROR", queryNode.toString(), queryNode.getClass().getName())); + + } + + return new MatchAllDocsQuery(); + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/MatchNoDocsQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/MatchNoDocsQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/MatchNoDocsQueryNodeBuilder.java (revision 0) @@ -0,0 +1,50 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.MatchNoDocsQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.BooleanQuery; + + +/** + * Builds an empty {@link BooleanQuery} object from a {@link MatchNoDocsQueryNode} object. + */ +public class MatchNoDocsQueryNodeBuilder implements LuceneQueryBuilder { + + public MatchNoDocsQueryNodeBuilder() { + // empty constructor + } + + public BooleanQuery build(QueryNode queryNode) throws QueryNodeException { + + // validates node + if (!(queryNode instanceof MatchNoDocsQueryNode)) { + + // TODO: node should be converted to a readable query instead of just invoking node.toString() + throw new QueryNodeException(new MessageImpl("Q0019E.LUCENE_QUERY_CONVERSION_ERROR", queryNode.toString(), queryNode.getClass().getName())); + + } + + return new BooleanQuery(); + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/ModifierQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/ModifierQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/ModifierQueryNodeBuilder.java (revision 0) @@ -0,0 +1,45 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.Query; + + +/** + * Builds no object, it only returns the {@link Query} object + * set on the {@link ModifierQueryNode} object using a {@link QueryTreeBuilder#QUERY_TREE_BUILDER_TAGID} + * tag. + */ +public class ModifierQueryNodeBuilder implements LuceneQueryBuilder { + + public ModifierQueryNodeBuilder() { + // empty constructor + } + + public Query build(QueryNode queryNode) throws QueryNodeException { + ModifierQueryNode modifierNode = (ModifierQueryNode) queryNode; + + return (Query) (modifierNode).getChild().getTag(QueryTreeBuilder.QUERY_TREE_BUILDER_TAGID); + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/MultiPhraseQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/MultiPhraseQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/MultiPhraseQueryNodeBuilder.java (revision 0) @@ -0,0 +1,81 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.LinkedList; +import java.util.List; +import java.util.TreeMap; + +import org.apache.lucene.index.Term; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.lucene2.nodes.MultiPhraseQueryNode; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.MultiPhraseQuery; +import org.apache.lucene.search.TermQuery; + + +/** + * Builds a {@link MultiPhraseQuery} object from a {@link MultiPhraseQueryNode} object. + */ +public class MultiPhraseQueryNodeBuilder implements LuceneQueryBuilder { + + public MultiPhraseQueryNodeBuilder() { + // empty constructor + } + + public MultiPhraseQuery build(QueryNode queryNode) throws QueryNodeException { + MultiPhraseQueryNode phraseNode = (MultiPhraseQueryNode) queryNode; + + MultiPhraseQuery phraseQuery = new MultiPhraseQuery(); + + List children = phraseNode.getChildren(); + + if (children != null) { + TreeMap> positionTermMap = new TreeMap>(); + + for (QueryNode child : children) { + FieldQueryNode termNode = (FieldQueryNode) child; + TermQuery termQuery = (TermQuery) termNode.getTag(QueryTreeBuilder.QUERY_TREE_BUILDER_TAGID); + List termList = positionTermMap.get(termNode.getPositionIncrement()); + + if (termList == null) { + termList = new LinkedList(); + positionTermMap.put(termNode.getPositionIncrement(), termList); + + } + + termList.add(termQuery.getTerm()); + + } + + for (int positionIncrement : positionTermMap.keySet()) { + List termList = positionTermMap.get(positionIncrement); + + phraseQuery.add(termList.toArray(new Term[termList.size()]), positionIncrement); + + } + + } + + return phraseQuery; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/PhraseQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/PhraseQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/PhraseQueryNodeBuilder.java (revision 0) @@ -0,0 +1,64 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.TokenizedPhraseQueryNode; +import org.apache.lucene.search.PhraseQuery; +import org.apache.lucene.search.TermQuery; + + +/** + * Builds a {@link PhraseQuery} object from a {@link TokenizedPhraseQueryNode} object. + */ +public class PhraseQueryNodeBuilder implements LuceneQueryBuilder { + + public PhraseQueryNodeBuilder() { + // empty constructor + } + + public PhraseQuery build(QueryNode queryNode) throws QueryNodeException { + TokenizedPhraseQueryNode phraseNode = (TokenizedPhraseQueryNode) queryNode; + + PhraseQuery phraseQuery = new PhraseQuery(); + + List children = phraseNode.getChildren(); + + if (children != null) { + + for (QueryNode child : children) { + TermQuery termQuery = (TermQuery) child.getTag(QueryTreeBuilder.QUERY_TREE_BUILDER_TAGID); + FieldQueryNode termNode = (FieldQueryNode) child; + + phraseQuery.add(termQuery.getTerm(), termNode.getPositionIncrement()); + + } + + + } + + return phraseQuery; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/PrefixWildcardQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/PrefixWildcardQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/PrefixWildcardQueryNodeBuilder.java (revision 0) @@ -0,0 +1,43 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.index.Term; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.PrefixWildcardQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.PrefixQuery; + + +/** + * Builds a {@link PrefixQuery} object from a {@link PrefixWildcardQueryNode} object. + */ +public class PrefixWildcardQueryNodeBuilder implements LuceneQueryBuilder { + + public PrefixWildcardQueryNodeBuilder() { + // empty constructor + } + + public PrefixQuery build(QueryNode queryNode) throws QueryNodeException { + PrefixWildcardQueryNode wildcardNode = (PrefixWildcardQueryNode) queryNode; + + return new PrefixQuery(new Term(wildcardNode.getFieldAsString(), wildcardNode.getTextAsString())); + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/RangeQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/RangeQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/RangeQueryNodeBuilder.java (revision 0) @@ -0,0 +1,62 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.lucene2.nodes.RangeQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.ParametricQueryNode.CompareOperator; +import org.apache.lucene.search.RangeQuery; + +/** + * Builds a {@link RangeQuery} object from a {@link RangeQueryNode} object. + */ +public class RangeQueryNodeBuilder implements LuceneQueryBuilder { + + public RangeQueryNodeBuilder() { + // empty constructor + } + + public RangeQuery build(QueryNode queryNode) throws QueryNodeException { + RangeQueryNode rangeNode = (RangeQueryNode) queryNode; + ParametricQueryNode upper = rangeNode.getUpperBound(); + ParametricQueryNode lower = rangeNode.getLowerBound(); + + boolean lowerInclusive = false; + boolean upperInclusive = false; + + if (upper.getOperator() == CompareOperator.LE) { + upperInclusive = true; + } + + if (lower.getOperator() == CompareOperator.GE) { + lowerInclusive = true; + } + + String field = rangeNode.getField().toString(); + + RangeQuery rangeQuery = new RangeQuery(field, lower.getTextAsString(), upper.getTextAsString(), lowerInclusive, upperInclusive, rangeNode.getCollator()); + + rangeQuery.setConstantScoreRewrite(rangeNode.isConstantScoreRewrite()); + + return rangeQuery; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/SlopQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/SlopQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/SlopQueryNodeBuilder.java (revision 0) @@ -0,0 +1,56 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.nodes.SlopQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.MultiPhraseQuery; +import org.apache.lucene.search.PhraseQuery; +import org.apache.lucene.search.Query; + + +/** + * This builder basically reads the {@link Query} object set on the {@link SlopQueryNode} child + * using {@link QueryTreeBuilder#QUERY_TREE_BUILDER_TAGID} and applies + * the slop value defined in the {@link SlopQueryNode}. + */ +public class SlopQueryNodeBuilder implements LuceneQueryBuilder { + + public SlopQueryNodeBuilder() { + // empty constructor + } + + public Query build(QueryNode queryNode) throws QueryNodeException { + SlopQueryNode phraseSlopNode = (SlopQueryNode) queryNode; + + Query query = (Query) phraseSlopNode.getChild().getTag(QueryTreeBuilder.QUERY_TREE_BUILDER_TAGID); + + if (query instanceof PhraseQuery) { + ((PhraseQuery) query).setSlop(phraseSlopNode.getValue()); + + } else { + ((MultiPhraseQuery) query).setSlop(phraseSlopNode.getValue()); + } + + return query; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/WildcardQueryNodeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/WildcardQueryNodeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/WildcardQueryNodeBuilder.java (revision 0) @@ -0,0 +1,43 @@ +package org.apache.lucene.queryParser.lucene2.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.index.Term; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.WildcardQueryNode; +import org.apache.lucene.search.WildcardQuery; + + +/** + * Builds a {@link WildcardQuery} object from a {@link WildcardQueryNode} object. + */ +public class WildcardQueryNodeBuilder implements LuceneQueryBuilder { + + public WildcardQueryNodeBuilder() { + // empty constructor + } + + public WildcardQuery build(QueryNode queryNode) throws QueryNodeException { + WildcardQueryNode wildcardNode = (WildcardQueryNode) queryNode; + + return new WildcardQuery(new Term(wildcardNode.getFieldAsString(), wildcardNode.getTextAsString())); + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/builders/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/builders/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/builders/package.html (revision 0) @@ -0,0 +1,35 @@ + + + + + + + + +

Lucene 2 Query Node Builders

+

+The package org.apache.lucene.queryParser.lucene2.builders contains all the builders needed +to build a Lucene Query object from a query node tree. These builders expect the query node tree was +already processed by the LuceneQueryNodeProcessorPipeline. +

+

+LuceneQueryTreeBuilder is a builder that already contains a defined map that maps each QueryNode object +with its respective builder. +

+ + Index: src/java/org/apache/lucene/queryParser/lucene2/config/AllowLeadingWildcardAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/AllowLeadingWildcardAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/AllowLeadingWildcardAttribute.java (revision 0) @@ -0,0 +1,77 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.AllowLeadingWildcardProcessor; +import org.apache.lucene.util.Attribute; + +/** + * This attribute is used by {@link AllowLeadingWildcardProcessor} processor and must be defined in + * the {@link QueryConfigHandler}. It basically tells the processor if it should allow leading wildcard. + *
+ * @see QueryParser#setAllowLeadingWildcard(boolean) + */ +public class AllowLeadingWildcardAttribute extends Attribute { + + private static final long serialVersionUID = -2804763012723049527L; + + private boolean allowLeadingWildcard = true; + + public AllowLeadingWildcardAttribute() { + // empty constructor + } + + void setAllowLeadingWildcard(boolean allowLeadingWildcard) { + this.allowLeadingWildcard = allowLeadingWildcard; + } + + public boolean isAllowLeadingWildcard() { + return this.allowLeadingWildcard; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof AllowLeadingWildcardAttribute && + ((AllowLeadingWildcardAttribute) other).allowLeadingWildcard == this.allowLeadingWildcard) { + + return true; + + } + + return false; + + } + + public int hashCode() { + return this.allowLeadingWildcard ? -1 : Integer.MAX_VALUE; + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/AnalyzerAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/AnalyzerAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/AnalyzerAttribute.java (revision 0) @@ -0,0 +1,84 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.AnalyzerQueryNodeProcessor; +import org.apache.lucene.util.Attribute; + +/** + * This attribute is used by {@link AnalyzerQueryNodeProcessor} processor and must be defined in + * the {@link QueryConfigHandler}. It provides to this processor the {@link Analyzer}, if there is one, + * which will be used to analyze the query terms. + *
+ * @see QueryParser#getAnalyzer() + */ +public class AnalyzerAttribute extends Attribute { + + private static final long serialVersionUID = -6804760312723049526L; + + private Analyzer analyzer; + + public AnalyzerAttribute() { + // empty constructor + } + + void setAnalyzer(Analyzer analyzer) { + this.analyzer = analyzer; + } + + public Analyzer getAnalyzer() { + return this.analyzer; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof AnalyzerAttribute) { + AnalyzerAttribute analyzerAttr = (AnalyzerAttribute) other; + + if (analyzerAttr.analyzer == this.analyzer + || (this.analyzer != null && analyzerAttr.analyzer != null && this.analyzer.equals(analyzerAttr.analyzer))) { + + return true; + + } + + } + + return false; + + } + + public int hashCode() { + return (this.analyzer == null) ? 0 : this.analyzer.hashCode(); + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/BoostAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/BoostAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/BoostAttribute.java (revision 0) @@ -0,0 +1,78 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.config.FieldConfig; +import org.apache.lucene.queryParser.lucene2.processors.MultiFieldQueryNodeProcessor; +import org.apache.lucene.util.Attribute; + +/** + * This attribute is used by {@link MultiFieldQueryNodeProcessor} processor and it should + * be defined in a {@link FieldConfig}. This processor uses this attribute to define + * which boost a specific field should have when none is defined to it. + *

+ * @see MultiFieldQueryParser + */ +public class BoostAttribute extends Attribute { + + private static final long serialVersionUID = -2104763012523049527L; + + private float boost = 1.0f; + + public BoostAttribute() { + // empty constructor + } + + void setBoost(float boost) { + this.boost = boost; + } + + public float getBoost() { + return this.boost; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof BoostAttribute && other != null && + ((BoostAttribute) other).boost == this.boost) { + + return true; + + } + + return false; + + } + + public int hashCode() { + return Float.valueOf(this.boost).hashCode(); + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/ConstantScoreRewriteAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/ConstantScoreRewriteAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/ConstantScoreRewriteAttribute.java (revision 0) @@ -0,0 +1,78 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.ParametricRangeQueryNodeProcessor; +import org.apache.lucene.util.Attribute; + +/** + * This attribute is used by {@link ParametricRangeQueryNodeProcessor} processor and + * should be defined in the {@link QueryConfigHandler} used by this processor. It + * basically tells the processor if the constant score rewrite is enabled. + *
+ * @see QueryParser#setConstantScoreRewrite(boolean) + */ +public class ConstantScoreRewriteAttribute extends Attribute { + + private static final long serialVersionUID = -2104763012723049527L; + + private boolean constantScoreRewrite = true; + + public ConstantScoreRewriteAttribute() { + // empty constructor + } + + void setConstantScoreRewrite(boolean constantScoreRewrite) { + this.constantScoreRewrite = constantScoreRewrite; + } + + public boolean isConstantScoreRewrite() { + return this.constantScoreRewrite; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof ConstantScoreRewriteAttribute && + ((ConstantScoreRewriteAttribute) other).constantScoreRewrite == this.constantScoreRewrite) { + + return true; + + } + + return false; + + } + + public int hashCode() { + return this.constantScoreRewrite ? -1 : Integer.MAX_VALUE; + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/DateResolutionAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/DateResolutionAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/DateResolutionAttribute.java (revision 0) @@ -0,0 +1,86 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.document.DateTools; +import org.apache.lucene.document.DateTools.Resolution; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.ParametricRangeQueryNodeProcessor; +import org.apache.lucene.util.Attribute; + +/** + * This attribute is used by {@link ParametricRangeQueryNodeProcessor} processor and + * must be defined in the {@link QueryConfigHandler}. This attribute tells the + * processor which {@link Resolution} to use when parsing the date. + *
+ * @see QueryParser#setDateResolution(Resolution) + */ +public class DateResolutionAttribute extends Attribute { + + private static final long serialVersionUID = -6804360312723049526L; + + private DateTools.Resolution dateResolution; + + public DateResolutionAttribute() { + // empty constructor + } + + void setDateResolution(DateTools.Resolution dateResolution) { + this.dateResolution = dateResolution; + } + + public DateTools.Resolution getDateResolution() { + return this.dateResolution; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof DateResolutionAttribute) { + DateResolutionAttribute dateResAttr = (DateResolutionAttribute) other; + + if (dateResAttr.getDateResolution() == getDateResolution() + || dateResAttr.getDateResolution().equals( + getDateResolution())) { + + return true; + + } + + } + + return false; + + } + + public int hashCode() { + return (this.dateResolution == null) ? 0 : this.dateResolution.hashCode(); + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/DefaultOperatorAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/DefaultOperatorAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/DefaultOperatorAttribute.java (revision 0) @@ -0,0 +1,85 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.util.Attribute; +import org.apache.lucene.queryParser.QueryParser.Operator; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.GroupQueryNodeProcessor; + +/** + * This attribute is used by {@link GroupQueryNodeProcessor} processor and + * must be defined in the {@link QueryConfigHandler}. This attribute tells the + * processor which is the default boolean operator when no operator is defined between + * terms. + *
+ * @see QueryParser#setDefaultOperator(Operator) + */ +public class DefaultOperatorAttribute extends Attribute { + + private static final long serialVersionUID = -6804760312723049526L; + + private Operator operator; + + public DefaultOperatorAttribute() { + // empty constructor + } + + void setDefaultOperator(Operator operator) { + this.operator = operator; + } + + public Operator getDefaultOperator() { + return this.operator; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof DefaultOperatorAttribute) { + DefaultOperatorAttribute defaultOperatorAttr = (DefaultOperatorAttribute) other; + + if (defaultOperatorAttr.operator == this.operator + || (this.operator != null && defaultOperatorAttr.operator != null && this.operator.equals(defaultOperatorAttr.operator))) { + + return true; + + } + + } + + return false; + + } + + public int hashCode() { + return (this.operator == null) ? 0 : this.operator.hashCode(); + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/DefaultPhraseSlopAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/DefaultPhraseSlopAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/DefaultPhraseSlopAttribute.java (revision 0) @@ -0,0 +1,78 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.PhraseSlopQueryNodeProcessor; +import org.apache.lucene.util.Attribute; + +/** + * This attribute is used by {@link PhraseSlopQueryNodeProcessor} processor and + * must be defined in the {@link QueryConfigHandler}. This attribute tells the + * processor what is the default phrase slop when no slop is defined in a phrase. + *
+ * @see QueryParser#setPhraseSlop(int) + */ +public class DefaultPhraseSlopAttribute extends Attribute { + + private static final long serialVersionUID = -2104763012527049527L; + + private int defaultPhraseSlop = 1; + + public DefaultPhraseSlopAttribute() { + // empty constructor + } + + void setDefaultPhraseSlop(int defaultPhraseSlop) { + this.defaultPhraseSlop = defaultPhraseSlop; + } + + public int getDefaultPhraseSlop() { + return this.defaultPhraseSlop; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof DefaultPhraseSlopAttribute && other != null && + ((DefaultPhraseSlopAttribute) other).defaultPhraseSlop == this.defaultPhraseSlop) { + + return true; + + } + + return false; + + } + + public int hashCode() { + return Integer.valueOf(this.defaultPhraseSlop).hashCode(); + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/LocaleAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/LocaleAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/LocaleAttribute.java (revision 0) @@ -0,0 +1,85 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Locale; + +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.ParametricRangeQueryNodeProcessor; +import org.apache.lucene.util.Attribute; + +/** + * This attribute is used by processor {@link ParametricRangeQueryNodeProcessor} and + * must be defined in the {@link QueryConfigHandler}. This attribute tells the + * processor what is the default {@link Locale} used to parse a date. + *
+ * @see QueryParser#setLocale(Locale) + */ +public class LocaleAttribute extends Attribute { + + private static final long serialVersionUID = -6804760312720049526L; + + private Locale locale = Locale.getDefault(); + + public LocaleAttribute() { + // empty constructor + } + + void setLocale(Locale locale) { + this.locale = locale; + } + + public Locale getLocale() { + return this.locale; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof LocaleAttribute) { + LocaleAttribute localeAttr = (LocaleAttribute) other; + + if (localeAttr.locale == this.locale + || (this.locale != null && localeAttr.locale != null && this.locale.equals(localeAttr.locale))) { + + return true; + + } + + } + + return false; + + } + + public int hashCode() { + return (this.locale == null) ? 0 : this.locale.hashCode(); + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/LowercaseExpandedTermsAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/LowercaseExpandedTermsAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/LowercaseExpandedTermsAttribute.java (revision 0) @@ -0,0 +1,80 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Locale; + +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.ParametricRangeQueryNodeProcessor; +import org.apache.lucene.util.Attribute; + +/** + * This attribute is used by processor {@link ParametricRangeQueryNodeProcessor} and + * must be defined in the {@link QueryConfigHandler}. This attribute tells the + * processor what is the default {@link Locale} used to parse a date. + *
+ * @see QueryParser#setLowercaseExpandedTerms(boolean) + */ +public class LowercaseExpandedTermsAttribute extends Attribute { + + private static final long serialVersionUID = -2804760312723049527L; + + private boolean lowercaseExpandedTerms = true; + + public LowercaseExpandedTermsAttribute() { + // empty constructor + } + + void setLowercaseExpandedTerms(boolean lowercaseExpandedTerms) { + this.lowercaseExpandedTerms = lowercaseExpandedTerms; + } + + public boolean isLowercaseExpandedTerms() { + return this.lowercaseExpandedTerms; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof LowercaseExpandedTermsAttribute && + ((LowercaseExpandedTermsAttribute) other).lowercaseExpandedTerms == this.lowercaseExpandedTerms) { + + return true; + + } + + return false; + + } + + public int hashCode() { + return this.lowercaseExpandedTerms ? -1 : Integer.MAX_VALUE; + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/LuceneMultiFieldQueryConfigHandler.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/LuceneMultiFieldQueryConfigHandler.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/LuceneMultiFieldQueryConfigHandler.java (revision 0) @@ -0,0 +1,72 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Map; + +import org.apache.lucene.document.DateTools.Resolution; +import org.apache.lucene.queryParser.QueryParser; +import org.apache.lucene.queryParser.config.FieldConfig; +import org.apache.lucene.queryParser.lucene2.MultiFieldQueryParserWrapper; + + +/** + * This configuration handler holds every configuration supported by {@link LuceneQueryConfigHandler} + * plus a field boost mapping and the list of fields that should be used to expand each term. + *
+ * @see MultiFieldQueryParser + * @see MultiFieldQueryParserWrapper + */ +public class LuceneMultiFieldQueryConfigHandler extends LuceneQueryConfigHandler { + + private Map boosts; + + /** + * @param queryParser + * @param defaultDateResolution + */ + public LuceneMultiFieldQueryConfigHandler(QueryParser queryParser, + Resolution defaultDateResolution, CharSequence[] fields, Map boosts) { + + super(queryParser, defaultDateResolution); + + MultiFieldAttribute multiFieldAttr = (MultiFieldAttribute) addAttribute(MultiFieldAttribute.class); + multiFieldAttr.setFields(fields); + + this.boosts = boosts; + + } + + public FieldConfig getFieldConfig(CharSequence fieldName) { + FieldConfig fc = super.getFieldConfig(fieldName); + + if (this.boosts != null) { + BoostAttribute boostAttr = (BoostAttribute) fc.addAttribute(BoostAttribute.class); + Float boost = this.boosts.get(fieldName); + + if (boost != null) { + boostAttr.setBoost(boost.floatValue()); + } + + } + + return fc; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/config/LuceneQueryConfigHandler.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/LuceneQueryConfigHandler.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/LuceneQueryConfigHandler.java (revision 0) @@ -0,0 +1,186 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.text.Collator; +import java.util.HashMap; +import java.util.Locale; + +import org.apache.lucene.document.DateTools; +import org.apache.lucene.queryParser.config.FieldConfig; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.QueryParserWrapper; +import org.apache.lucene.queryParser.lucene2.processors.LuceneQueryNodeProcessorPipeline; +import org.apache.lucene.queryParser.QueryParser; +import org.apache.lucene.queryParser.QueryParser.Operator; + + +/** + * This query configuration handler is used for almost every processor defined + * in the {@link LuceneQueryNodeProcessorPipeline} processor pipeline. It holds + * attributes that reproduces the configuration that could be set on the + * old query parser: {@link QueryParser}. + *
+ * @see QueryParser + * @see LuceneQueryNodeProcessorPipeline + * @see QueryParserWrapper + */ +public class LuceneQueryConfigHandler extends QueryConfigHandler { + + private LowercaseExpandedTermsAttribute lowercaseExpandedTermsAttr; + + private DefaultOperatorAttribute defaultOperatorAttribute; + + private AllowLeadingWildcardAttribute allowLeadingWildcardAttribute; + + private DefaultPhraseSlopAttribute defaultPhraseSlopAttribute; + + private PositionIncrementsAttribute positionIncrementsAttribute; + + private ConstantScoreRewriteAttribute constantScoreRewriteAttribute; + + private RangeCollatorAttribute rangeCollatorAttribute; + + private DateTools.Resolution defaultDateResolution; + + private LocaleAttribute localeAttribute; + + private HashMap dateResolutions; + + public LuceneQueryConfigHandler(QueryParser queryParser, DateTools.Resolution defaultDateResolution) { + Operator op = queryParser.getDefaultOperator(); + Collator collator = queryParser.getRangeCollator(); + Locale locale = queryParser.getLocale(); + int defaultPhraseSlop = queryParser.getPhraseSlop(); + boolean lowercaseExpandedTerms = queryParser.getLowercaseExpandedTerms(); + boolean allowLeadingWildcard = queryParser.getAllowLeadingWildcard(); + + boolean constantScoreRewrite = queryParser.getConstantScoreRewrite(); + + boolean positionIncrementsEnabled = queryParser.getEnablePositionIncrements(); + this.defaultDateResolution = defaultDateResolution; + + this.rangeCollatorAttribute = ((RangeCollatorAttribute) addAttribute(RangeCollatorAttribute.class)); + this.rangeCollatorAttribute.setDateResolution(collator); + + this.defaultOperatorAttribute = ((DefaultOperatorAttribute) addAttribute(DefaultOperatorAttribute.class)); + this.defaultOperatorAttribute.setDefaultOperator(op); + + AnalyzerAttribute analyzerAttr = ((AnalyzerAttribute) addAttribute(AnalyzerAttribute.class)); + analyzerAttr.setAnalyzer(queryParser.getAnalyzer()); + + this.lowercaseExpandedTermsAttr = ((LowercaseExpandedTermsAttribute) addAttribute(LowercaseExpandedTermsAttribute.class)); + this.lowercaseExpandedTermsAttr.setLowercaseExpandedTerms(lowercaseExpandedTerms); + + this.constantScoreRewriteAttribute = ((ConstantScoreRewriteAttribute) addAttribute(ConstantScoreRewriteAttribute.class)); + this.constantScoreRewriteAttribute.setConstantScoreRewrite(constantScoreRewrite); + + this.allowLeadingWildcardAttribute = ((AllowLeadingWildcardAttribute) addAttribute(AllowLeadingWildcardAttribute.class)); + this.allowLeadingWildcardAttribute.setAllowLeadingWildcard(allowLeadingWildcard); + + this.positionIncrementsAttribute = ((PositionIncrementsAttribute) addAttribute(PositionIncrementsAttribute.class)); + this.positionIncrementsAttribute.setPositionIncrementsEnabled(positionIncrementsEnabled); + + this.localeAttribute = ((LocaleAttribute) addAttribute(LocaleAttribute.class)); + this.localeAttribute.setLocale(locale); + + this.defaultPhraseSlopAttribute = ((DefaultPhraseSlopAttribute) addAttribute(DefaultPhraseSlopAttribute.class)); + this.defaultPhraseSlopAttribute.setDefaultPhraseSlop(defaultPhraseSlop); + + } + + public FieldConfig getFieldConfig(CharSequence fieldName) { + // TODO: cache a field config when it's constructed for the first time, + // consecutive calls could return the cached object + + if (fieldName != null) { + FieldConfig fieldConfig = new FieldConfig(fieldName); + + DateResolutionAttribute dateResolutionAttr = (DateResolutionAttribute) fieldConfig.addAttribute(DateResolutionAttribute.class); + DateTools.Resolution dateRes = null; + + if (this.dateResolutions != null) { + dateRes = this.dateResolutions.get(fieldName.toString()); + } + + if (dateRes == null) { + dateRes = this.defaultDateResolution; + } + + dateResolutionAttr.setDateResolution(dateRes); + + return fieldConfig; + + } + + return null; + + } + + public void setRangeCollator(Collator collator) { + this.rangeCollatorAttribute.setDateResolution(collator); + } + + public void setDefaultOperator(Operator op) { + this.defaultOperatorAttribute.setDefaultOperator(op); + } + + public void setLowercaseExpandedTerms(boolean lowercaseExpandedTerms) { + this.lowercaseExpandedTermsAttr.setLowercaseExpandedTerms(lowercaseExpandedTerms); + } + + /** + * @param allowLeadingWildcard + */ + public void setAllowLeadingWildcard(boolean allowLeadingWildcard) { + this.allowLeadingWildcardAttribute.setAllowLeadingWildcard(allowLeadingWildcard); + } + + public void setPositionIncrementsEnabled(boolean enabled) { + this.positionIncrementsAttribute.setPositionIncrementsEnabled(enabled); + } + + public void setConstantScoreRewrite(boolean constantScoreRewrite) { + this.constantScoreRewriteAttribute.setConstantScoreRewrite(constantScoreRewrite); + } + + public void setDateResolution(DateTools.Resolution dateResolution) { + this.defaultDateResolution = dateResolution; + } + + public void setLocale(Locale locale) { + this.localeAttribute.setLocale(locale); + } + + public void setDefaultPhraseSlop(int defaultPhraseSlop) { + this.defaultPhraseSlopAttribute.setDefaultPhraseSlop(defaultPhraseSlop); + } + + public void setDateResolution(String fieldName, DateTools.Resolution dateResolution) { + + if (this.dateResolutions == null) { + this.dateResolutions = new HashMap(); + } + + if (fieldName != null) { + this.dateResolutions.put(fieldName.toString(), dateResolution); + } + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/config/MultiFieldAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/MultiFieldAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/MultiFieldAttribute.java (revision 0) @@ -0,0 +1,81 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Arrays; + +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.MultiFieldQueryNodeProcessor; +import org.apache.lucene.util.Attribute; + + +/** + * This attribute is used by {@link MultiFieldQueryNodeProcessor} processor and + * must be defined in the {@link QueryConfigHandler}. This attribute tells the + * processor to which fields the terms in the query should be expanded. + *
+ * @see MultiFieldQueryParser + */ +public class MultiFieldAttribute extends Attribute { + + private static final long serialVersionUID = -6809760312720049526L; + + private CharSequence[] fields; + + public MultiFieldAttribute() { + // empty constructor + } + + void setFields(CharSequence[] fields) { + this.fields = fields; + } + + public CharSequence[] getFields() { + return this.fields; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof MultiFieldAttribute) { + MultiFieldAttribute fieldsAttr = (MultiFieldAttribute) other; + + return Arrays.equals(this.fields, fieldsAttr.fields); + + } + + return false; + + } + + public int hashCode() { + return Arrays.hashCode(this.fields); + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/PositionIncrementsAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/PositionIncrementsAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/PositionIncrementsAttribute.java (revision 0) @@ -0,0 +1,78 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.AnalyzerQueryNodeProcessor; +import org.apache.lucene.util.Attribute; + +/** + * This attribute is used by {@link AnalyzerQueryNodeProcessor} processor and + * must be defined in the {@link QueryConfigHandler}. This attribute tells the + * processor if the position increment is enabled. + *
+ * @see QueryParser#setEnablePositionIncrements(boolean) + */ +public class PositionIncrementsAttribute extends Attribute { + + private static final long serialVersionUID = -2804763012793049527L; + + private boolean positionIncrementsEnabled = true; + + public PositionIncrementsAttribute() { + // empty constructor + } + + void setPositionIncrementsEnabled(boolean positionIncrementsEnabled) { + this.positionIncrementsEnabled = positionIncrementsEnabled; + } + + public boolean isPositionIncrementsEnabled() { + return this.positionIncrementsEnabled; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof PositionIncrementsAttribute && other != null && + ((PositionIncrementsAttribute) other).positionIncrementsEnabled == this.positionIncrementsEnabled) { + + return true; + + } + + return false; + + } + + public int hashCode() { + return this.positionIncrementsEnabled ? -1 : Integer.MAX_VALUE; + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/RangeCollatorAttribute.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/RangeCollatorAttribute.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/RangeCollatorAttribute.java (revision 0) @@ -0,0 +1,88 @@ +package org.apache.lucene.queryParser.lucene2.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.text.Collator; + +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.processors.ParametricRangeQueryNodeProcessor; +import org.apache.lucene.search.RangeQuery; +import org.apache.lucene.util.Attribute; + + +/** + * This attribute is used by {@link ParametricRangeQueryNodeProcessor} processor and + * must be defined in the {@link QueryConfigHandler}. This attribute tells the + * processor which {@link Collator} should be used for a {@link RangeQuery} + *
+ * @see QueryParser#setRangeCollator(Collator) + */ +public class RangeCollatorAttribute extends Attribute { + + private static final long serialVersionUID = -6804360312723049526L; + + private Collator rangeCollator; + + public RangeCollatorAttribute() { + // empty constructor + } + + void setDateResolution(Collator rangeCollator) { + this.rangeCollator = rangeCollator; + } + + public Collator getRangeCollator() { + return this.rangeCollator; + } + + public void clear() { + throw new UnsupportedOperationException(); + } + + public void copyTo(Attribute target) { + throw new UnsupportedOperationException(); + } + + public boolean equals(Object other) { + + if (other instanceof RangeCollatorAttribute) { + RangeCollatorAttribute rangeCollatorAttr = (RangeCollatorAttribute) other; + + if (rangeCollatorAttr.rangeCollator == this.rangeCollator + || rangeCollatorAttr.rangeCollator.equals( + this.rangeCollator)) { + + return true; + + } + + } + + return false; + + } + + public int hashCode() { + return (this.rangeCollator == null) ? 0 : this.rangeCollator.hashCode(); + } + + public String toString() { + return ""; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/config/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/config/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/config/package.html (revision 0) @@ -0,0 +1,34 @@ + + + + + + + + +

Lucene 2 Query Configuration

+

+The package org.apache.lucene.queryParser.lucene2.config contains the Lucene +query configuration handler and all the attributes used by it. This configuration +handler reproduces almost everything that could be set on the old query parser. +

+

+LuceneQueryConfigHandler is the class that should be used to configure the LuceneQueryNodeProcessorPipeline. +

+ + Index: src/java/org/apache/lucene/queryParser/lucene2/nodes/BooleanModifierNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/nodes/BooleanModifierNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/nodes/BooleanModifierNode.java (revision 0) @@ -0,0 +1,39 @@ +package org.apache.lucene.queryParser.lucene2.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.lucene2.processors.GroupQueryNodeProcessor; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; + +/** + * A {@link BooleanModifierNode} has the same behaviour as {@link ModifierQueryNode}, + * it only indicates that this modifier was added by {@link GroupQueryNodeProcessor} + * and not by the user. + *
+ * @see ModifierQueryNode + */ +public class BooleanModifierNode extends ModifierQueryNode { + + private static final long serialVersionUID = -557816496416587068L; + + public BooleanModifierNode(QueryNode node, Modifier mod) { + super(node, mod); + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/nodes/LuceneBooleanQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/nodes/LuceneBooleanQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/nodes/LuceneBooleanQueryNode.java (revision 0) @@ -0,0 +1,56 @@ +package org.apache.lucene.queryParser.lucene2.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.BooleanQuery; +import org.apache.lucene.search.Similarity; + + +/** + * A {@link LuceneBooleanQueryNode} has the same behavior as {@link BooleanQueryNode}. + * It only indicates if the coord should be enabled or not for this + * boolean query. + *
+ * @see Similarity#coord(int, int) + * @see BooleanQuery + */ +public class LuceneBooleanQueryNode extends BooleanQueryNode { + + private static final long serialVersionUID = 1938287817191138787L; + + private boolean disableCoord; + + /** + * @param clauses + */ + public LuceneBooleanQueryNode(List clauses, boolean disableCoord) { + super(clauses); + + this.disableCoord = disableCoord; + + } + + public boolean isDisableCoord() { + return this.disableCoord; + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/nodes/MultiPhraseQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/nodes/MultiPhraseQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/nodes/MultiPhraseQueryNode.java (revision 0) @@ -0,0 +1,109 @@ +package org.apache.lucene.queryParser.lucene2.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.nodes.FieldableNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.QueryNodeImpl; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; +import org.apache.lucene.search.MultiPhraseQuery; +import org.apache.lucene.search.PhraseQuery; + + +/** + * A {@link MultiPhraseQueryNode} indicates that its children should be used to build a {@link MultiPhraseQuery} + * instead of {@link PhraseQuery}. + */ +public class MultiPhraseQueryNode extends QueryNodeImpl implements FieldableNode { + + private static final long serialVersionUID = -2138501723963320158L; + + public MultiPhraseQueryNode () { + setLeaf(false); + allocate(); + + } + + public String toString() { + if (getChildren() == null || getChildren().size() == 0) + return ""; + StringBuilder sb = new StringBuilder(); + sb.append(""); + for (QueryNode child : getChildren()) { + sb.append("\n"); + sb.append(child.toString()); + } + sb.append("\n"); + return sb.toString(); + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + if (getChildren() == null || getChildren().size() == 0) + return ""; + + StringBuilder sb = new StringBuilder(); + String filler = ""; + for (QueryNode child : getChildren()) { + sb.append(filler).append(child.toQueryString(escapeSyntaxParser)); + filler = ","; + } + + return "[MTP[" + sb.toString() + "]]"; + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + MultiPhraseQueryNode clone=(MultiPhraseQueryNode)super.cloneTree(); + + //nothing to do + + return clone; + } + + public CharSequence getField() { + List children = getChildren(); + + if (children == null || children.size() == 0) { + return null; + + } else { + return ((FieldableNode) children.get(0)).getField(); + } + + + } + + public void setField(CharSequence fieldName) { + List children = getChildren(); + + if (children != null) { + + for (QueryNode child : children) { + + if (child instanceof FieldableNode) { + ((FieldableNode) child).setField(fieldName); + } + + } + + } + + } + +} // end class MultitermQueryNode Index: src/java/org/apache/lucene/queryParser/lucene2/nodes/RangeQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/nodes/RangeQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/nodes/RangeQueryNode.java (revision 0) @@ -0,0 +1,78 @@ +package org.apache.lucene.queryParser.lucene2.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.text.Collator; + +import org.apache.lucene.queryParser.nodes.ParametricQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricRangeQueryNode; + + +/** + * This query node represents a Lucene range query. It also holds which + * collator will be used by the range query and if the constant score rewrite is enabled. + *
+ * @see QueryParser#setConstantScoreRewrite(boolean) + * @see QueryParser#setRangeCollator(Collator) + * @see org.apache.lucene.search.RangeQuery + */ +public class RangeQueryNode extends ParametricRangeQueryNode { + + private static final long serialVersionUID = 7400866652044314657L; + + private Collator collator; + + private boolean constantScoreRewrite; + + /** + * @param lower + * @param upper + */ + public RangeQueryNode(ParametricQueryNode lower, ParametricQueryNode upper, Collator collator, boolean constantScoreRewrite) { + super(lower, upper); + + this.constantScoreRewrite = constantScoreRewrite; + this.collator = collator; + + } + + public String toString() { + StringBuilder sb = new StringBuilder("\n\t"); + sb.append(this.getUpperBound()).append("\n\t"); + sb.append(this.getLowerBound()).append("\n"); + sb.append("\n"); + + return sb.toString(); + + } + + /** + * @return the collator + */ + public Collator getCollator() { + return this.collator; + } + + /** + * @return the constantScoreRewrite + */ + public boolean isConstantScoreRewrite() { + return this.constantScoreRewrite; + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/nodes/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/nodes/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/nodes/package.html (revision 0) @@ -0,0 +1,31 @@ + + + + + + + + +

Lucene 2 Query Nodes

+

+The package org.apache.lucene.queryParser.lucene2.nodes contains QueryNode classes +that are used specifically for Lucene query node tree. Any other generic QueryNode is +defined under org.apache.lucene.queryParser.nodes. +

+ + Index: src/java/org/apache/lucene/queryParser/lucene2/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/package.html (revision 0) @@ -0,0 +1,44 @@ + + + + + + + + +

Lucene Flexible Query Parser

+

+The old Lucene query parser used to have only one class that performed +all the parsing operations. In the new query parser structure, the +parsing was divided in 3 steps: parsing (syntax), processing (semantic) +and building. +

+

+The classes contained in the package org.apache.lucene.queryParser.lucene2 +are used to reproduce the same behaviour as the old query parser. +

+ +

+There are 2 wrapper classes that extends QueryParser and MultiFieldQueryParser. +The classes implement internally the new query parser structure. These 2 +classes are deprecated and should only be used when there is a need to use the +old query parser interface. +

+ + + Index: src/java/org/apache/lucene/queryParser/lucene2/parser/EscapeQuerySyntaxImpl.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/EscapeQuerySyntaxImpl.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/EscapeQuerySyntaxImpl.java (revision 0) @@ -0,0 +1,283 @@ +package org.apache.lucene.queryParser.lucene2.parser; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Locale; + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; +import org.apache.lucene.queryParser.util.UnescapedCharSequence; + + +/** + */ +public class EscapeQuerySyntaxImpl implements EscapeQuerySyntax { + + private static final char[] wildcardChars = {'*', '?'}; + + private static final String[] escapableTermExtraFirstChars = { + "+", "-", "@"}; + + private static final String[] escapableTermChars = { + "\"", "<", ">", "=", "!", "(", ")", "^", "[", "{", ":", + "]", "}", "~" }; + + // TODO: check what to do with these "*", "?", "\\" + private static final String[] escapableQuotedChars = { "\"" }; + private static final String[] escapableWhiteChars = { + " ", "\t", "\n", "\r", "\f", "\b", "\u3000" }; + private static final String[] escapableWordTokens = { + "AND", "OR", "NOT", "TO", "WITHIN", "SENTENCE", "PARAGRAPH" , "INORDER"}; + + private static final CharSequence escapeChar(CharSequence str, Locale locale) { + if (str == null || str.length() == 0) + return str; + + CharSequence buffer = str; + + // regular escapable Char for terms + for (int i = 0 ; i < escapableTermChars.length ; i++) { + buffer = replaceIgnoreCase(buffer, escapableTermChars[i].toLowerCase(), "\\", + locale); + } + + // First Character of a term as more escaping chars + for (int i = 0 ; i < escapableTermExtraFirstChars.length ; i++) { + if (buffer.charAt(0) == escapableTermExtraFirstChars[i].charAt(0)){ + buffer = "\\" + buffer.charAt(0) + buffer.subSequence(1, buffer.length()); + break; + } + } + + return buffer; + } + + private final CharSequence escapeQuoted(CharSequence str, Locale locale) { + if (str == null || str.length() == 0) + return str; + + CharSequence buffer = str; + + for (int i = 0 ; i < escapableQuotedChars.length ; i++) { + buffer = replaceIgnoreCase(buffer, escapableTermChars[i].toLowerCase(), "\\", + locale); + } + return buffer; + } + + private static final CharSequence escapeTerm(CharSequence term, Locale locale) { + if (term == null) + return term; + + // Escape single Chars + term = escapeChar(term, locale); + term = escapeWhiteChar(term, locale); + + // Escape Parser Words + for (int i = 0 ; i < escapableWordTokens.length ; i++) { + if (escapableWordTokens[i].equalsIgnoreCase(term.toString())) + return "\\" + term; + } + return term; + } + + /** + * replace with ignore case + * @param stringOrig string to get replaced + * @param sequence1 the old character sequence in lowercase + * @param escapeChar the new character to prefix sequence1 in return string. + * @return the new String + */ + private static CharSequence replaceIgnoreCase(CharSequence string, + CharSequence sequence1, CharSequence escapeChar, Locale locale) { + if (escapeChar == null || sequence1 == null || string == null) + throw new NullPointerException(); + + // empty string case + int count = string.length(); + int sequence1Length = sequence1.length(); + if (sequence1Length == 0) { + StringBuilder result = new StringBuilder((count + 1) * escapeChar.length()); + result.append(escapeChar); + for (int i = 0; i < count; i++) { + result.append(string.charAt(i)); + result.append(escapeChar); + } + return result.toString(); + } + + // normal case + StringBuilder result = new StringBuilder(); + char first = sequence1.charAt(0); + int start = 0, copyStart = 0, firstIndex; + while (start < count) { + if ((firstIndex = string.toString().toLowerCase(locale).indexOf(first, start)) == -1) + break; + boolean found = true; + if (sequence1.length() > 1) { + if (firstIndex + sequence1Length > count) + break; + for (int i = 1; i < sequence1Length; i++) { + if (string.toString().toLowerCase(locale).charAt(firstIndex + i) != sequence1.charAt(i)) { + found = false; + break; + } + } + } + if (found) { + result.append(string.toString().substring(copyStart, firstIndex)); + result.append(escapeChar); + result.append(string.toString().substring(firstIndex,firstIndex + sequence1Length)); + copyStart = start = firstIndex + sequence1Length; + } else { + start = firstIndex + 1; + } + } + if (result.length() == 0 && copyStart == 0) return string; + result.append(string.toString().substring(copyStart)); + return result.toString(); + } + + /** + * escape all tokens that are part of the parser syntax on a given string + * @param string string to get replaced + * @param locale locale to be used when performing string compares + * @return the new String + */ + private static final CharSequence escapeWhiteChar(CharSequence str, Locale locale) { + if (str == null || str.length() == 0) + return str; + + CharSequence buffer = str; + + for (int i = 0 ; i < escapableWhiteChars.length ; i++) { + buffer = replaceIgnoreCase(buffer, escapableWhiteChars[i].toLowerCase(), "\\", + locale); + } + return buffer; + } + + public CharSequence escape(CharSequence text, Locale locale, Type type) { + if (text == null || text.length() == 0) + return text; + + // escape wildcards and the escape char (this has to be perform before anything else) + // since we need to preserve the UnescapedCharSequence and escape the original escape chars + if(text instanceof UnescapedCharSequence){ + text = ((UnescapedCharSequence)text).toStringEscaped(wildcardChars); + } else { + text = new UnescapedCharSequence(text).toStringEscaped(wildcardChars); + } + + if (type == Type.STRING) { + return escapeQuoted(text, locale); + } + else { + return escapeTerm(text, locale); + } + } + + /** + * Returns a String where the escape char has been + * removed, or kept only once if there was a double escape. + * + * Supports escaped unicode characters, e. g. translates + * A to A. + * + */ + public static UnescapedCharSequence discardEscapeChar(CharSequence input) + throws ParseException { + // Create char array to hold unescaped char sequence + char[] output = new char[input.length()]; + boolean[] wasEscaped = new boolean[input.length()]; + + // The length of the output can be less than the input + // due to discarded escape chars. This variable holds + // the actual length of the output + int length = 0; + + // We remember whether the last processed character was + // an escape character + boolean lastCharWasEscapeChar = false; + + // The multiplier the current unicode digit must be multiplied with. + // E. g. the first digit must be multiplied with 16^3, the second with 16^2... + int codePointMultiplier = 0; + + // Used to calculate the codepoint of the escaped unicode character + int codePoint = 0; + + for (int i = 0; i < input.length(); i++) { + char curChar = input.charAt(i); + if (codePointMultiplier > 0) { + codePoint += hexToInt(curChar) * codePointMultiplier; + codePointMultiplier >>>= 4; + if (codePointMultiplier == 0) { + output[length++] = (char) codePoint; + codePoint = 0; + } + } else if (lastCharWasEscapeChar) { + if (curChar == 'u') { + // found an escaped unicode character + codePointMultiplier = 16 * 16 * 16; + } else { + // this character was escaped + output[length] = curChar; + wasEscaped[length] = true; + length++; + } + lastCharWasEscapeChar = false; + } else { + if (curChar == '\\') { + lastCharWasEscapeChar = true; + } else { + output[length] = curChar; + length++; + } + } + } + + if (codePointMultiplier > 0) { + throw new ParseException(new MessageImpl( + QueryParserMessages.INVALID_SYNTAX_ESCAPE_UNICODE_TRUNCATION)); + } + + if (lastCharWasEscapeChar) { + throw new ParseException(new MessageImpl( + QueryParserMessages.INVALID_SYNTAX_ESCAPE_CHARACTER)); + } + + return new UnescapedCharSequence(output, wasEscaped, 0, length); + } + + /** Returns the numeric value of the hexadecimal character */ + private static final int hexToInt(char c) throws ParseException { + if ('0' <= c && c <= '9') { + return c - '0'; + } else if ('a' <= c && c <= 'f') { + return c - 'a' + 10; + } else if ('A' <= c && c <= 'F') { + return c - 'A' + 10; + } else { + throw new ParseException(new MessageImpl( + QueryParserMessages.INVALID_SYNTAX_ESCAPE_NONE_HEX_UNICODE, c)); + } + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/parser/JavaCharStream.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/JavaCharStream.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/JavaCharStream.java (revision 0) @@ -0,0 +1,634 @@ +/* Generated By:JavaCC: Do not edit this line. JavaCharStream.java Version 4.1 */ +/* JavaCCOptions:STATIC=false,SUPPORT_CLASS_VISIBILITY_PUBLIC=true */ +package org.apache.lucene.queryParser.lucene2.parser; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * An implementation of interface CharStream, where the stream is assumed to + * contain only ASCII characters (with java-like unicode escape processing). + */ + +public +class JavaCharStream +{ + /** Whether parser is static. */ + public static final boolean staticFlag = false; + + static final int hexval(char c) throws java.io.IOException { + switch(c) + { + case '0' : + return 0; + case '1' : + return 1; + case '2' : + return 2; + case '3' : + return 3; + case '4' : + return 4; + case '5' : + return 5; + case '6' : + return 6; + case '7' : + return 7; + case '8' : + return 8; + case '9' : + return 9; + + case 'a' : + case 'A' : + return 10; + case 'b' : + case 'B' : + return 11; + case 'c' : + case 'C' : + return 12; + case 'd' : + case 'D' : + return 13; + case 'e' : + case 'E' : + return 14; + case 'f' : + case 'F' : + return 15; + } + + throw new java.io.IOException(); // Should never come here + } + +/** Position in buffer. */ + public int bufpos = -1; + int bufsize; + int available; + int tokenBegin; + protected int bufline[]; + protected int bufcolumn[]; + + protected int column = 0; + protected int line = 1; + + protected boolean prevCharIsCR = false; + protected boolean prevCharIsLF = false; + + protected java.io.Reader inputStream; + + protected char[] nextCharBuf; + protected char[] buffer; + protected int maxNextCharInd = 0; + protected int nextCharInd = -1; + protected int inBuf = 0; + protected int tabSize = 8; + + protected void setTabSize(int i) { tabSize = i; } + protected int getTabSize(int i) { return tabSize; } + + protected void ExpandBuff(boolean wrapAround) + { + char[] newbuffer = new char[bufsize + 2048]; + int newbufline[] = new int[bufsize + 2048]; + int newbufcolumn[] = new int[bufsize + 2048]; + + try + { + if (wrapAround) + { + System.arraycopy(buffer, tokenBegin, newbuffer, 0, bufsize - tokenBegin); + System.arraycopy(buffer, 0, newbuffer, bufsize - tokenBegin, bufpos); + buffer = newbuffer; + + System.arraycopy(bufline, tokenBegin, newbufline, 0, bufsize - tokenBegin); + System.arraycopy(bufline, 0, newbufline, bufsize - tokenBegin, bufpos); + bufline = newbufline; + + System.arraycopy(bufcolumn, tokenBegin, newbufcolumn, 0, bufsize - tokenBegin); + System.arraycopy(bufcolumn, 0, newbufcolumn, bufsize - tokenBegin, bufpos); + bufcolumn = newbufcolumn; + + bufpos += (bufsize - tokenBegin); + } + else + { + System.arraycopy(buffer, tokenBegin, newbuffer, 0, bufsize - tokenBegin); + buffer = newbuffer; + + System.arraycopy(bufline, tokenBegin, newbufline, 0, bufsize - tokenBegin); + bufline = newbufline; + + System.arraycopy(bufcolumn, tokenBegin, newbufcolumn, 0, bufsize - tokenBegin); + bufcolumn = newbufcolumn; + + bufpos -= tokenBegin; + } + } + catch (Throwable t) + { + throw new Error(t.getMessage()); + } + + available = (bufsize += 2048); + tokenBegin = 0; + } + + protected void FillBuff() throws java.io.IOException + { + int i; + if (maxNextCharInd == 4096) + maxNextCharInd = nextCharInd = 0; + + try { + if ((i = inputStream.read(nextCharBuf, maxNextCharInd, + 4096 - maxNextCharInd)) == -1) + { + inputStream.close(); + throw new java.io.IOException(); + } + else + maxNextCharInd += i; + return; + } + catch(java.io.IOException e) { + if (bufpos != 0) + { + --bufpos; + backup(0); + } + else + { + bufline[bufpos] = line; + bufcolumn[bufpos] = column; + } + throw e; + } + } + + protected char ReadByte() throws java.io.IOException + { + if (++nextCharInd >= maxNextCharInd) + FillBuff(); + + return nextCharBuf[nextCharInd]; + } + +/** @return starting character for token. */ + public char BeginToken() throws java.io.IOException + { + if (inBuf > 0) + { + --inBuf; + + if (++bufpos == bufsize) + bufpos = 0; + + tokenBegin = bufpos; + return buffer[bufpos]; + } + + tokenBegin = 0; + bufpos = -1; + + return readChar(); + } + + protected void AdjustBuffSize() + { + if (available == bufsize) + { + if (tokenBegin > 2048) + { + bufpos = 0; + available = tokenBegin; + } + else + ExpandBuff(false); + } + else if (available > tokenBegin) + available = bufsize; + else if ((tokenBegin - available) < 2048) + ExpandBuff(true); + else + available = tokenBegin; + } + + protected void UpdateLineColumn(char c) + { + column++; + + if (prevCharIsLF) + { + prevCharIsLF = false; + line += (column = 1); + } + else if (prevCharIsCR) + { + prevCharIsCR = false; + if (c == '\n') + { + prevCharIsLF = true; + } + else + line += (column = 1); + } + + switch (c) + { + case '\r' : + prevCharIsCR = true; + break; + case '\n' : + prevCharIsLF = true; + break; + case '\t' : + column--; + column += (tabSize - (column % tabSize)); + break; + default : + break; + } + + bufline[bufpos] = line; + bufcolumn[bufpos] = column; + } + +/** Read a character. */ + public char readChar() throws java.io.IOException + { + if (inBuf > 0) + { + --inBuf; + + if (++bufpos == bufsize) + bufpos = 0; + + return buffer[bufpos]; + } + + char c; + + if (++bufpos == available) + AdjustBuffSize(); + + if ((buffer[bufpos] = c = ReadByte()) == '\\') + { + UpdateLineColumn(c); + + int backSlashCnt = 1; + + for (;;) // Read all the backslashes + { + if (++bufpos == available) + AdjustBuffSize(); + + try + { + if ((buffer[bufpos] = c = ReadByte()) != '\\') + { + UpdateLineColumn(c); + // found a non-backslash char. + if ((c == 'u') && ((backSlashCnt & 1) == 1)) + { + if (--bufpos < 0) + bufpos = bufsize - 1; + + break; + } + + backup(backSlashCnt); + return '\\'; + } + } + catch(java.io.IOException e) + { + // We are returning one backslash so we should only backup (count-1) + if (backSlashCnt > 1) + backup(backSlashCnt-1); + + return '\\'; + } + + UpdateLineColumn(c); + backSlashCnt++; + } + + // Here, we have seen an odd number of backslash's followed by a 'u' + try + { + while ((c = ReadByte()) == 'u') + ++column; + + buffer[bufpos] = c = (char)(hexval(c) << 12 | + hexval(ReadByte()) << 8 | + hexval(ReadByte()) << 4 | + hexval(ReadByte())); + + column += 4; + } + catch(java.io.IOException e) + { + throw new Error("Invalid escape character at line " + line + + " column " + column + "."); + } + + if (backSlashCnt == 1) + return c; + else + { + backup(backSlashCnt - 1); + return '\\'; + } + } + else + { + UpdateLineColumn(c); + return c; + } + } + + @Deprecated + /** + * @deprecated + * @see #getEndColumn + */ + public int getColumn() { + return bufcolumn[bufpos]; + } + + @Deprecated + /** + * @deprecated + * @see #getEndLine + */ + public int getLine() { + return bufline[bufpos]; + } + +/** Get end column. */ + public int getEndColumn() { + return bufcolumn[bufpos]; + } + +/** Get end line. */ + public int getEndLine() { + return bufline[bufpos]; + } + +/** @return column of token start */ + public int getBeginColumn() { + return bufcolumn[tokenBegin]; + } + +/** @return line number of token start */ + public int getBeginLine() { + return bufline[tokenBegin]; + } + +/** Retreat. */ + public void backup(int amount) { + + inBuf += amount; + if ((bufpos -= amount) < 0) + bufpos += bufsize; + } + +/** Constructor. */ + public JavaCharStream(java.io.Reader dstream, + int startline, int startcolumn, int buffersize) + { + inputStream = dstream; + line = startline; + column = startcolumn - 1; + + available = bufsize = buffersize; + buffer = new char[buffersize]; + bufline = new int[buffersize]; + bufcolumn = new int[buffersize]; + nextCharBuf = new char[4096]; + } + +/** Constructor. */ + public JavaCharStream(java.io.Reader dstream, + int startline, int startcolumn) + { + this(dstream, startline, startcolumn, 4096); + } + +/** Constructor. */ + public JavaCharStream(java.io.Reader dstream) + { + this(dstream, 1, 1, 4096); + } +/** Reinitialise. */ + public void ReInit(java.io.Reader dstream, + int startline, int startcolumn, int buffersize) + { + inputStream = dstream; + line = startline; + column = startcolumn - 1; + + if (buffer == null || buffersize != buffer.length) + { + available = bufsize = buffersize; + buffer = new char[buffersize]; + bufline = new int[buffersize]; + bufcolumn = new int[buffersize]; + nextCharBuf = new char[4096]; + } + prevCharIsLF = prevCharIsCR = false; + tokenBegin = inBuf = maxNextCharInd = 0; + nextCharInd = bufpos = -1; + } + +/** Reinitialise. */ + public void ReInit(java.io.Reader dstream, + int startline, int startcolumn) + { + ReInit(dstream, startline, startcolumn, 4096); + } + +/** Reinitialise. */ + public void ReInit(java.io.Reader dstream) + { + ReInit(dstream, 1, 1, 4096); + } +/** Constructor. */ + public JavaCharStream(java.io.InputStream dstream, String encoding, int startline, + int startcolumn, int buffersize) throws java.io.UnsupportedEncodingException + { + this(encoding == null ? new java.io.InputStreamReader(dstream) : new java.io.InputStreamReader(dstream, encoding), startline, startcolumn, buffersize); + } + +/** Constructor. */ + public JavaCharStream(java.io.InputStream dstream, int startline, + int startcolumn, int buffersize) + { + this(new java.io.InputStreamReader(dstream), startline, startcolumn, 4096); + } + +/** Constructor. */ + public JavaCharStream(java.io.InputStream dstream, String encoding, int startline, + int startcolumn) throws java.io.UnsupportedEncodingException + { + this(dstream, encoding, startline, startcolumn, 4096); + } + +/** Constructor. */ + public JavaCharStream(java.io.InputStream dstream, int startline, + int startcolumn) + { + this(dstream, startline, startcolumn, 4096); + } + +/** Constructor. */ + public JavaCharStream(java.io.InputStream dstream, String encoding) throws java.io.UnsupportedEncodingException + { + this(dstream, encoding, 1, 1, 4096); + } + +/** Constructor. */ + public JavaCharStream(java.io.InputStream dstream) + { + this(dstream, 1, 1, 4096); + } + +/** Reinitialise. */ + public void ReInit(java.io.InputStream dstream, String encoding, int startline, + int startcolumn, int buffersize) throws java.io.UnsupportedEncodingException + { + ReInit(encoding == null ? new java.io.InputStreamReader(dstream) : new java.io.InputStreamReader(dstream, encoding), startline, startcolumn, buffersize); + } + +/** Reinitialise. */ + public void ReInit(java.io.InputStream dstream, int startline, + int startcolumn, int buffersize) + { + ReInit(new java.io.InputStreamReader(dstream), startline, startcolumn, buffersize); + } +/** Reinitialise. */ + public void ReInit(java.io.InputStream dstream, String encoding, int startline, + int startcolumn) throws java.io.UnsupportedEncodingException + { + ReInit(dstream, encoding, startline, startcolumn, 4096); + } +/** Reinitialise. */ + public void ReInit(java.io.InputStream dstream, int startline, + int startcolumn) + { + ReInit(dstream, startline, startcolumn, 4096); + } +/** Reinitialise. */ + public void ReInit(java.io.InputStream dstream, String encoding) throws java.io.UnsupportedEncodingException + { + ReInit(dstream, encoding, 1, 1, 4096); + } + +/** Reinitialise. */ + public void ReInit(java.io.InputStream dstream) + { + ReInit(dstream, 1, 1, 4096); + } + + /** @return token image as String */ + public String GetImage() + { + if (bufpos >= tokenBegin) + return new String(buffer, tokenBegin, bufpos - tokenBegin + 1); + else + return new String(buffer, tokenBegin, bufsize - tokenBegin) + + new String(buffer, 0, bufpos + 1); + } + + /** @return suffix */ + public char[] GetSuffix(int len) + { + char[] ret = new char[len]; + + if ((bufpos + 1) >= len) + System.arraycopy(buffer, bufpos - len + 1, ret, 0, len); + else + { + System.arraycopy(buffer, bufsize - (len - bufpos - 1), ret, 0, + len - bufpos - 1); + System.arraycopy(buffer, 0, ret, len - bufpos - 1, bufpos + 1); + } + + return ret; + } + + /** Set buffers back to null when finished. */ + public void Done() + { + nextCharBuf = null; + buffer = null; + bufline = null; + bufcolumn = null; + } + + /** + * Method to adjust line and column numbers for the start of a token. + */ + public void adjustBeginLineColumn(int newLine, int newCol) + { + int start = tokenBegin; + int len; + + if (bufpos >= tokenBegin) + { + len = bufpos - tokenBegin + inBuf + 1; + } + else + { + len = bufsize - tokenBegin + bufpos + 1 + inBuf; + } + + int i = 0, j = 0, k = 0; + int nextColDiff = 0, columnDiff = 0; + + while (i < len && bufline[j = start % bufsize] == bufline[k = ++start % bufsize]) + { + bufline[j] = newLine; + nextColDiff = columnDiff + bufcolumn[k] - bufcolumn[j]; + bufcolumn[j] = newCol + columnDiff; + columnDiff = nextColDiff; + i++; + } + + if (i < len) + { + bufline[j] = newLine++; + bufcolumn[j] = newCol + columnDiff; + + while (i++ < len) + { + if (bufline[j = start % bufsize] != bufline[++start % bufsize]) + bufline[j] = newLine++; + else + bufline[j] = newLine; + } + } + + line = bufline[j]; + column = bufcolumn[j]; + } + +} +/* JavaCC - OriginalChecksum=e61bd5c730f749861216d7199a74d372 (do not edit this line) */ Index: src/java/org/apache/lucene/queryParser/lucene2/parser/ParseException.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/ParseException.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/ParseException.java (revision 0) @@ -0,0 +1,197 @@ +/* Generated By:JavaCC: Do not edit this line. ParseException.java Version 4.1 */ +/* JavaCCOptions:KEEP_LINE_COL=null */ +package org.apache.lucene.queryParser.lucene2.parser; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.messages.Message; +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeParseException; +import org.apache.lucene.queryParser.messages.QueryParserMessages; + +/** + * This exception is thrown when parse errors are encountered. + * You can explicitly create objects of this exception type by + * calling the method generateParseException in the generated + * parser. + * + * You can modify this class to customize your error reporting + * mechanisms so long as you retain the public fields. + */ +public class ParseException extends QueryNodeParseException { + + /** + * The version identifier for this Serializable class. + * Increment only if the serialized form of the + * class changes. + */ + private static final long serialVersionUID = 1L; + + /** + * This constructor is used by the method "generateParseException" + * in the generated parser. Calling this constructor generates + * a new object of this type with the fields "currentToken", + * "expectedTokenSequences", and "tokenImage" set. + */ + public ParseException(Token currentTokenVal, + int[][] expectedTokenSequencesVal, + String[] tokenImageVal + ) + { + super(new MessageImpl(QueryParserMessages.INVALID_SYNTAX, initialise(currentTokenVal, expectedTokenSequencesVal, tokenImageVal))); + this.currentToken = currentTokenVal; + this.expectedTokenSequences = expectedTokenSequencesVal; + this.tokenImage = tokenImageVal; + } + + public ParseException(Message message) { + super(message); + } + + public ParseException() { + super(new MessageImpl(QueryParserMessages.INVALID_SYNTAX, "Error")); + } + + /** + * This is the last token that has been consumed successfully. If + * this object has been created due to a parse error, the token + * followng this token will (therefore) be the first error token. + */ + private Token currentToken; + + /** + * Each entry in this array is an array of integers. Each array + * of integers represents a sequence of tokens (by their ordinal + * values) that is expected at this point of the parse. + */ + private int[][] expectedTokenSequences; + + /** + * This is a reference to the "tokenImage" array of the generated + * parser within which the parse error occurred. This array is + * defined in the generated ...Constants interface. + */ + private String[] tokenImage; + + /** + * It uses "currentToken" and "expectedTokenSequences" to generate a parse + * error message and returns it. If this object has been created + * due to a parse error, and you do not catch it (it gets thrown + * from the parser) the correct error message + * gets displayed. + */ + private static String initialise(Token currentToken, + int[][] expectedTokenSequences, + String[] tokenImage) { + String eol = System.getProperty("line.separator", "\n"); + StringBuffer expected = new StringBuffer(); + int maxSize = 0; + for (int i = 0; i < expectedTokenSequences.length; i++) { + if (maxSize < expectedTokenSequences[i].length) { + maxSize = expectedTokenSequences[i].length; + } + for (int j = 0; j < expectedTokenSequences[i].length; j++) { + expected.append(tokenImage[expectedTokenSequences[i][j]]).append(' '); + } + if (expectedTokenSequences[i][expectedTokenSequences[i].length - 1] != 0) { + expected.append("..."); + } + expected.append(eol).append(" "); + } + String retval = "Encountered \""; + Token tok = currentToken.next; + for (int i = 0; i < maxSize; i++) { + if (i != 0) retval += " "; + if (tok.kind == 0) { + retval += tokenImage[0]; + break; + } + retval += " " + tokenImage[tok.kind]; + retval += " \""; + retval += add_escapes(tok.image); + retval += " \""; + tok = tok.next; + } + retval += "\" at line " + currentToken.next.beginLine + ", column " + currentToken.next.beginColumn; + retval += "." + eol; + if (expectedTokenSequences.length == 1) { + retval += "Was expecting:" + eol + " "; + } else { + retval += "Was expecting one of:" + eol + " "; + } + retval += expected.toString(); + return retval; + } + + /** + * The end of line string for this machine. + */ + private String eol = System.getProperty("line.separator", "\n"); + + /** + * Used to convert raw characters to their escaped version + * when these raw version cannot be used as part of an ASCII + * string literal. + */ + static private String add_escapes(String str) { + StringBuffer retval = new StringBuffer(); + char ch; + for (int i = 0; i < str.length(); i++) { + switch (str.charAt(i)) + { + case 0 : + continue; + case '\b': + retval.append("\\b"); + continue; + case '\t': + retval.append("\\t"); + continue; + case '\n': + retval.append("\\n"); + continue; + case '\f': + retval.append("\\f"); + continue; + case '\r': + retval.append("\\r"); + continue; + case '\"': + retval.append("\\\""); + continue; + case '\'': + retval.append("\\\'"); + continue; + case '\\': + retval.append("\\\\"); + continue; + default: + if ((ch = str.charAt(i)) < 0x20 || ch > 0x7e) { + String s = "0000" + Integer.toString(ch, 16); + retval.append("\\u" + s.substring(s.length() - 4, s.length())); + } else { + retval.append(ch); + } + continue; + } + } + return retval.toString(); + } + +} +/* JavaCC - OriginalChecksum=c04ac45b94787832e67e6d1b49d8774c (do not edit this line) */ Index: src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParser.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParser.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParser.java (revision 0) @@ -0,0 +1,938 @@ +/* Generated By:JavaCC: Do not edit this line. QueryParser.java */ +package org.apache.lucene.queryParser.lucene2.parser; + +import java.io.StringReader; +import java.util.ArrayList; +import java.util.List; +import java.util.Vector; + +import org.apache.lucene.messages.Message; +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeError; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.QueryNodeParseException; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.nodes.AndQueryNode; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.BoostQueryNode; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.FuzzyQueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.GroupQueryNode; +import org.apache.lucene.queryParser.nodes.OpaqueQueryNode; +import org.apache.lucene.queryParser.nodes.OrQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricRangeQueryNode; +import org.apache.lucene.queryParser.nodes.PrefixWildcardQueryNode; +import org.apache.lucene.queryParser.nodes.SlopQueryNode; +import org.apache.lucene.queryParser.nodes.ProximityQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.QueryNodeImpl; +import org.apache.lucene.queryParser.nodes.QuotedFieldQueryNode; +import org.apache.lucene.queryParser.nodes.WildcardQueryNode; +import org.apache.lucene.queryParser.parser.Parser; + +@SuppressWarnings("all") +public class QueryParser implements Parser, QueryParserConstants { + + private static final int CONJ_NONE =0; + private static final int CONJ_AND =2; + private static final int CONJ_OR =2; + + + // query parser constructor + public QueryParser() { + this(new StringReader("")); + } + /** Parses a query string, returning a {@link com.ibm.es.nuvo.search.query.tree.QueryNode}. + * @param query the query string to be parsed. + * @throws ParseException if the parsing fails + */ + public QueryNode parse(CharSequence query, CharSequence field) throws QueryNodeParseException { + ReInit(new StringReader(query.toString())); + try { + // TopLevelQuery is a Query followed by the end-of-input (EOF) + QueryNode querynode = TopLevelQuery(field); + return querynode; + } + catch (ParseException tme) { + tme.setQuery(query); + throw tme; + } + catch (Error tme) { + Message message = new MessageImpl(QueryParserMessages.INVALID_SYNTAX_CANNOT_PARSE, query, tme.getMessage()); + QueryNodeParseException e = new QueryNodeParseException(tme); + e.setQuery(query); + e.setNonLocalizedMessage(message); + throw e; + } + } + +// * Query ::= ( Clause )* +// * Clause ::= ["+", "-"] [ ":"] ( | "(" Query ")" ) + final public int Conjunction() throws ParseException { + int ret = CONJ_NONE; + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case AND: + case OR: + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case AND: + jj_consume_token(AND); + ret = CONJ_AND; + break; + case OR: + jj_consume_token(OR); + ret = CONJ_OR; + break; + default: + jj_la1[0] = jj_gen; + jj_consume_token(-1); + throw new ParseException(); + } + break; + default: + jj_la1[1] = jj_gen; + ; + } + {if (true) return ret;} + throw new Error("Missing return statement in function"); + } + + final public ModifierQueryNode.Modifier Modifiers() throws ParseException { + ModifierQueryNode.Modifier ret = ModifierQueryNode.Modifier.MOD_NONE; + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case NOT: + case PLUS: + case MINUS: + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case PLUS: + jj_consume_token(PLUS); + ret = ModifierQueryNode.Modifier.MOD_REQ; + break; + case MINUS: + jj_consume_token(MINUS); + ret = ModifierQueryNode.Modifier.MOD_NOT; + break; + case NOT: + jj_consume_token(NOT); + ret = ModifierQueryNode.Modifier.MOD_NOT; + break; + default: + jj_la1[2] = jj_gen; + jj_consume_token(-1); + throw new ParseException(); + } + break; + default: + jj_la1[3] = jj_gen; + ; + } + {if (true) return ret;} + throw new Error("Missing return statement in function"); + } + +// This makes sure that there is no garbage after the query string + final public QueryNode TopLevelQuery(CharSequence field) throws ParseException { + QueryNode q; + q = Query(field); + jj_consume_token(0); + {if (true) return q;} + throw new Error("Missing return statement in function"); + } + +// These changes were made to introduce operator precedence: +// - Clause() now returns a QueryNode. +// - The modifiers are consumed by Clause() and returned as part of the QueryNode Object +// - Query does not consume conjunctions (AND, OR) anymore. +// - This is now done by two new non-terminals: ConjClause and DisjClause +// The parse tree looks similar to this: +// Query ::= DisjQuery ( DisjQuery )* +// DisjQuery ::= ConjQuery ( OR ConjQuery )* +// ConjQuery ::= Clause ( AND Clause )* +// Clause ::= [ Modifier ] ... + final public QueryNode Query(CharSequence field) throws ParseException { + Vector clauses = null; + QueryNode c, first=null; + first = DisjQuery(field); + label_1: + while (true) { + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case NOT: + case PLUS: + case MINUS: + case LPAREN: + case STAR: + case QUOTED: + case TERM: + case PREFIXTERM: + case WILDTERM: + case RANGEIN_START: + case RANGEEX_START: + case NUMBER: + ; + break; + default: + jj_la1[4] = jj_gen; + break label_1; + } + c = DisjQuery(field); + if (clauses == null) { + clauses = new Vector(); + clauses.addElement(first); + } + clauses.addElement(c); + } + if (clauses != null) { + {if (true) return new BooleanQueryNode(clauses);} + } else { + {if (true) return first;} + } + throw new Error("Missing return statement in function"); + } + + final public QueryNode DisjQuery(CharSequence field) throws ParseException { + QueryNode first, c; + Vector clauses = null; + first = ConjQuery(field); + label_2: + while (true) { + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case OR: + ; + break; + default: + jj_la1[5] = jj_gen; + break label_2; + } + jj_consume_token(OR); + c = ConjQuery(field); + if (clauses == null) { + clauses = new Vector(); + clauses.addElement(first); + } + clauses.addElement(c); + } + if (clauses != null) { + {if (true) return new OrQueryNode(clauses);} + } else { + {if (true) return first;} + } + throw new Error("Missing return statement in function"); + } + + final public QueryNode ConjQuery(CharSequence field) throws ParseException { + QueryNode first, c; + Vector clauses = null; + first = ModClause(field); + label_3: + while (true) { + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case AND: + ; + break; + default: + jj_la1[6] = jj_gen; + break label_3; + } + jj_consume_token(AND); + c = ModClause(field); + if (clauses == null) { + clauses = new Vector(); + clauses.addElement(first); + } + clauses.addElement(c); + } + if (clauses != null) { + {if (true) return new AndQueryNode(clauses);} + } else { + {if (true) return first;} + } + throw new Error("Missing return statement in function"); + } + +// QueryNode Query(CharSequence field) : +// { +// List clauses = new ArrayList(); +// List modifiers = new ArrayList(); +// QueryNode q, firstQuery=null; +// ModifierQueryNode.Modifier mods; +// int conj; +// } +// { +// mods=Modifiers() q=Clause(field) +// { +// if (mods == ModifierQueryNode.Modifier.MOD_NONE) firstQuery=q; +// +// // do not create modifier nodes with MOD_NONE +// if (mods != ModifierQueryNode.Modifier.MOD_NONE) { +// q = new ModifierQueryNode(q, mods); +// } +// clauses.add(q); +// } +// ( +// conj=Conjunction() mods=Modifiers() q=Clause(field) +// { +// // do not create modifier nodes with MOD_NONE +// if (mods != ModifierQueryNode.Modifier.MOD_NONE) { +// q = new ModifierQueryNode(q, mods); +// } +// clauses.add(q); +// //TODO: figure out what to do with AND and ORs +// } +// )* +// { +// if (clauses.size() == 1 && firstQuery != null) +// return firstQuery; +// else { +// return new BooleanQueryNode(clauses); +// } +// } +// } + final public QueryNode ModClause(CharSequence field) throws ParseException { + QueryNode q; + ModifierQueryNode.Modifier mods; + mods = Modifiers(); + q = Clause(field); + if (mods != ModifierQueryNode.Modifier.MOD_NONE) { + q = new ModifierQueryNode(q, mods); + } + {if (true) return q;} + throw new Error("Missing return statement in function"); + } + + final public QueryNode Clause(CharSequence field) throws ParseException { + QueryNode q; + Token fieldToken=null, boost=null; + boolean group = false; + if (jj_2_1(2)) { + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case TERM: + fieldToken = jj_consume_token(TERM); + jj_consume_token(COLON); + field=EscapeQuerySyntaxImpl.discardEscapeChar(fieldToken.image); + break; + case STAR: + jj_consume_token(STAR); + jj_consume_token(COLON); + field="*"; + break; + default: + jj_la1[7] = jj_gen; + jj_consume_token(-1); + throw new ParseException(); + } + } else { + ; + } + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case STAR: + case QUOTED: + case TERM: + case PREFIXTERM: + case WILDTERM: + case RANGEIN_START: + case RANGEEX_START: + case NUMBER: + q = Term(field); + break; + case LPAREN: + jj_consume_token(LPAREN); + q = Query(field); + jj_consume_token(RPAREN); + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case CARAT: + jj_consume_token(CARAT); + boost = jj_consume_token(NUMBER); + break; + default: + jj_la1[8] = jj_gen; + ; + } + group=true; + break; + default: + jj_la1[9] = jj_gen; + jj_consume_token(-1); + throw new ParseException(); + } + if (boost != null) { + float f = (float)1.0; + try { + f = Float.valueOf(boost.image).floatValue(); + // avoid boosting null queries, such as those caused by stop words + if (q != null) { + q = new BoostQueryNode(q, f); + } + } catch (Exception ignored) { + /* Should this be handled somehow? (defaults to "no boost", if + * boost number is invalid) + */ + } + } + if (group) { q = new GroupQueryNode(q);} + {if (true) return q;} + throw new Error("Missing return statement in function"); + } + + final public QueryNode Term(CharSequence field) throws ParseException { + Token term, boost=null, fuzzySlop=null, goop1, goop2; + boolean prefix = false; + boolean wildcard = false; + boolean fuzzy = false; + QueryNode q =null; + ParametricQueryNode qLower, qUpper; + float defaultMinSimilarity = 0.5f; + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case STAR: + case TERM: + case PREFIXTERM: + case WILDTERM: + case NUMBER: + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case TERM: + term = jj_consume_token(TERM); + q = new FieldQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image), term.beginColumn, term.endColumn); + break; + case STAR: + term = jj_consume_token(STAR); + wildcard=true; q = new WildcardQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image), term.beginColumn, term.endColumn); + break; + case PREFIXTERM: + term = jj_consume_token(PREFIXTERM); + prefix=true; q = new PrefixWildcardQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image), term.beginColumn, term.endColumn); + break; + case WILDTERM: + term = jj_consume_token(WILDTERM); + wildcard=true; q = new WildcardQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image), term.beginColumn, term.endColumn); + break; + case NUMBER: + term = jj_consume_token(NUMBER); + break; + default: + jj_la1[10] = jj_gen; + jj_consume_token(-1); + throw new ParseException(); + } + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case FUZZY_SLOP: + fuzzySlop = jj_consume_token(FUZZY_SLOP); + fuzzy=true; + break; + default: + jj_la1[11] = jj_gen; + ; + } + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case CARAT: + jj_consume_token(CARAT); + boost = jj_consume_token(NUMBER); + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case FUZZY_SLOP: + fuzzySlop = jj_consume_token(FUZZY_SLOP); + fuzzy=true; + break; + default: + jj_la1[12] = jj_gen; + ; + } + break; + default: + jj_la1[13] = jj_gen; + ; + } + if (!wildcard && !prefix && fuzzy) { + float fms = defaultMinSimilarity; + try { + fms = Float.valueOf(fuzzySlop.image.substring(1)).floatValue(); + } catch (Exception ignored) { } + if(fms < 0.0f || fms > 1.0f){ + {if (true) throw new ParseException(new MessageImpl(QueryParserMessages.INVALID_SYNTAX_FUZZY_LIMITS));} + } + q = new FuzzyQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image), fms, term.beginColumn, term.endColumn); + } + break; + case RANGEIN_START: + jj_consume_token(RANGEIN_START); + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case RANGEIN_GOOP: + goop1 = jj_consume_token(RANGEIN_GOOP); + break; + case RANGEIN_QUOTED: + goop1 = jj_consume_token(RANGEIN_QUOTED); + break; + default: + jj_la1[14] = jj_gen; + jj_consume_token(-1); + throw new ParseException(); + } + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case RANGEIN_TO: + jj_consume_token(RANGEIN_TO); + break; + default: + jj_la1[15] = jj_gen; + ; + } + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case RANGEIN_GOOP: + goop2 = jj_consume_token(RANGEIN_GOOP); + break; + case RANGEIN_QUOTED: + goop2 = jj_consume_token(RANGEIN_QUOTED); + break; + default: + jj_la1[16] = jj_gen; + jj_consume_token(-1); + throw new ParseException(); + } + jj_consume_token(RANGEIN_END); + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case CARAT: + jj_consume_token(CARAT); + boost = jj_consume_token(NUMBER); + break; + default: + jj_la1[17] = jj_gen; + ; + } + if (goop1.kind == RANGEIN_QUOTED) { + goop1.image = goop1.image.substring(1, goop1.image.length()-1); + } + if (goop2.kind == RANGEIN_QUOTED) { + goop2.image = goop2.image.substring(1, goop2.image.length()-1); + } + + qLower = new ParametricQueryNode(field, ParametricQueryNode.CompareOperator.GE, + EscapeQuerySyntaxImpl.discardEscapeChar(goop1.image), goop1.beginColumn, goop1.endColumn); + qUpper = new ParametricQueryNode(field, ParametricQueryNode.CompareOperator.LE, + EscapeQuerySyntaxImpl.discardEscapeChar(goop2.image), goop2.beginColumn, goop2.endColumn); + q = new ParametricRangeQueryNode(qLower, qUpper); + break; + case RANGEEX_START: + jj_consume_token(RANGEEX_START); + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case RANGEEX_GOOP: + goop1 = jj_consume_token(RANGEEX_GOOP); + break; + case RANGEEX_QUOTED: + goop1 = jj_consume_token(RANGEEX_QUOTED); + break; + default: + jj_la1[18] = jj_gen; + jj_consume_token(-1); + throw new ParseException(); + } + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case RANGEEX_TO: + jj_consume_token(RANGEEX_TO); + break; + default: + jj_la1[19] = jj_gen; + ; + } + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case RANGEEX_GOOP: + goop2 = jj_consume_token(RANGEEX_GOOP); + break; + case RANGEEX_QUOTED: + goop2 = jj_consume_token(RANGEEX_QUOTED); + break; + default: + jj_la1[20] = jj_gen; + jj_consume_token(-1); + throw new ParseException(); + } + jj_consume_token(RANGEEX_END); + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case CARAT: + jj_consume_token(CARAT); + boost = jj_consume_token(NUMBER); + break; + default: + jj_la1[21] = jj_gen; + ; + } + if (goop1.kind == RANGEEX_QUOTED) { + goop1.image = goop1.image.substring(1, goop1.image.length()-1); + } + if (goop2.kind == RANGEEX_QUOTED) { + goop2.image = goop2.image.substring(1, goop2.image.length()-1); + } + qLower = new ParametricQueryNode(field, ParametricQueryNode.CompareOperator.GT, + EscapeQuerySyntaxImpl.discardEscapeChar(goop1.image), goop1.beginColumn, goop1.endColumn); + qUpper = new ParametricQueryNode(field, ParametricQueryNode.CompareOperator.LT, + EscapeQuerySyntaxImpl.discardEscapeChar(goop2.image), goop2.beginColumn, goop2.endColumn); + q = new ParametricRangeQueryNode(qLower, qUpper); + break; + case QUOTED: + term = jj_consume_token(QUOTED); + q = new QuotedFieldQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image.substring(1, term.image.length()-1)), term.beginColumn + 1, term.endColumn - 1); + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case FUZZY_SLOP: + fuzzySlop = jj_consume_token(FUZZY_SLOP); + break; + default: + jj_la1[22] = jj_gen; + ; + } + switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { + case CARAT: + jj_consume_token(CARAT); + boost = jj_consume_token(NUMBER); + break; + default: + jj_la1[23] = jj_gen; + ; + } + int phraseSlop = 0; + + if (fuzzySlop != null) { + try { + phraseSlop = Float.valueOf(fuzzySlop.image.substring(1)).intValue(); + q = new SlopQueryNode(q, phraseSlop); + } + catch (Exception ignored) { + /* Should this be handled somehow? (defaults to "no PhraseSlop", if + * slop number is invalid) + */ + } + } + break; + default: + jj_la1[24] = jj_gen; + jj_consume_token(-1); + throw new ParseException(); + } + if (boost != null) { + float f = (float)1.0; + try { + f = Float.valueOf(boost.image).floatValue(); + // avoid boosting null queries, such as those caused by stop words + if (q != null) { + q = new BoostQueryNode(q, f); + } + } catch (Exception ignored) { + /* Should this be handled somehow? (defaults to "no boost", if + * boost number is invalid) + */ + } + } + {if (true) return q;} + throw new Error("Missing return statement in function"); + } + + private boolean jj_2_1(int xla) { + jj_la = xla; jj_lastpos = jj_scanpos = token; + try { return !jj_3_1(); } + catch(LookaheadSuccess ls) { return true; } + finally { jj_save(0, xla); } + } + + private boolean jj_3R_5() { + if (jj_scan_token(STAR)) return true; + if (jj_scan_token(COLON)) return true; + return false; + } + + private boolean jj_3R_4() { + if (jj_scan_token(TERM)) return true; + if (jj_scan_token(COLON)) return true; + return false; + } + + private boolean jj_3_1() { + Token xsp; + xsp = jj_scanpos; + if (jj_3R_4()) { + jj_scanpos = xsp; + if (jj_3R_5()) return true; + } + return false; + } + + /** Generated Token Manager. */ + public QueryParserTokenManager token_source; + JavaCharStream jj_input_stream; + /** Current token. */ + public Token token; + /** Next token. */ + public Token jj_nt; + private int jj_ntk; + private Token jj_scanpos, jj_lastpos; + private int jj_la; + private int jj_gen; + final private int[] jj_la1 = new int[25]; + static private int[] jj_la1_0; + static private int[] jj_la1_1; + static { + jj_la1_init_0(); + jj_la1_init_1(); + } + private static void jj_la1_init_0() { + jj_la1_0 = new int[] {0x300,0x300,0x1c00,0x1c00,0x3ed3c00,0x200,0x100,0x90000,0x20000,0x3ed2000,0x2690000,0x100000,0x100000,0x20000,0x30000000,0x4000000,0x30000000,0x20000,0x0,0x40000000,0x0,0x20000,0x100000,0x20000,0x3ed0000,}; + } + private static void jj_la1_init_1() { + jj_la1_1 = new int[] {0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x3,0x0,0x3,0x0,0x0,0x0,0x0,}; + } + final private JJCalls[] jj_2_rtns = new JJCalls[1]; + private boolean jj_rescan = false; + private int jj_gc = 0; + + /** Constructor with InputStream. */ + public QueryParser(java.io.InputStream stream) { + this(stream, null); + } + /** Constructor with InputStream and supplied encoding */ + public QueryParser(java.io.InputStream stream, String encoding) { + try { jj_input_stream = new JavaCharStream(stream, encoding, 1, 1); } catch(java.io.UnsupportedEncodingException e) { throw new RuntimeException(e); } + token_source = new QueryParserTokenManager(jj_input_stream); + token = new Token(); + jj_ntk = -1; + jj_gen = 0; + for (int i = 0; i < 25; i++) jj_la1[i] = -1; + for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls(); + } + + /** Reinitialise. */ + public void ReInit(java.io.InputStream stream) { + ReInit(stream, null); + } + /** Reinitialise. */ + public void ReInit(java.io.InputStream stream, String encoding) { + try { jj_input_stream.ReInit(stream, encoding, 1, 1); } catch(java.io.UnsupportedEncodingException e) { throw new RuntimeException(e); } + token_source.ReInit(jj_input_stream); + token = new Token(); + jj_ntk = -1; + jj_gen = 0; + for (int i = 0; i < 25; i++) jj_la1[i] = -1; + for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls(); + } + + /** Constructor. */ + public QueryParser(java.io.Reader stream) { + jj_input_stream = new JavaCharStream(stream, 1, 1); + token_source = new QueryParserTokenManager(jj_input_stream); + token = new Token(); + jj_ntk = -1; + jj_gen = 0; + for (int i = 0; i < 25; i++) jj_la1[i] = -1; + for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls(); + } + + /** Reinitialise. */ + public void ReInit(java.io.Reader stream) { + jj_input_stream.ReInit(stream, 1, 1); + token_source.ReInit(jj_input_stream); + token = new Token(); + jj_ntk = -1; + jj_gen = 0; + for (int i = 0; i < 25; i++) jj_la1[i] = -1; + for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls(); + } + + /** Constructor with generated Token Manager. */ + public QueryParser(QueryParserTokenManager tm) { + token_source = tm; + token = new Token(); + jj_ntk = -1; + jj_gen = 0; + for (int i = 0; i < 25; i++) jj_la1[i] = -1; + for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls(); + } + + /** Reinitialise. */ + public void ReInit(QueryParserTokenManager tm) { + token_source = tm; + token = new Token(); + jj_ntk = -1; + jj_gen = 0; + for (int i = 0; i < 25; i++) jj_la1[i] = -1; + for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls(); + } + + private Token jj_consume_token(int kind) throws ParseException { + Token oldToken; + if ((oldToken = token).next != null) token = token.next; + else token = token.next = token_source.getNextToken(); + jj_ntk = -1; + if (token.kind == kind) { + jj_gen++; + if (++jj_gc > 100) { + jj_gc = 0; + for (int i = 0; i < jj_2_rtns.length; i++) { + JJCalls c = jj_2_rtns[i]; + while (c != null) { + if (c.gen < jj_gen) c.first = null; + c = c.next; + } + } + } + return token; + } + token = oldToken; + jj_kind = kind; + throw generateParseException(); + } + + static private final class LookaheadSuccess extends java.lang.Error { } + final private LookaheadSuccess jj_ls = new LookaheadSuccess(); + private boolean jj_scan_token(int kind) { + if (jj_scanpos == jj_lastpos) { + jj_la--; + if (jj_scanpos.next == null) { + jj_lastpos = jj_scanpos = jj_scanpos.next = token_source.getNextToken(); + } else { + jj_lastpos = jj_scanpos = jj_scanpos.next; + } + } else { + jj_scanpos = jj_scanpos.next; + } + if (jj_rescan) { + int i = 0; Token tok = token; + while (tok != null && tok != jj_scanpos) { i++; tok = tok.next; } + if (tok != null) jj_add_error_token(kind, i); + } + if (jj_scanpos.kind != kind) return true; + if (jj_la == 0 && jj_scanpos == jj_lastpos) throw jj_ls; + return false; + } + + +/** Get the next Token. */ + final public Token getNextToken() { + if (token.next != null) token = token.next; + else token = token.next = token_source.getNextToken(); + jj_ntk = -1; + jj_gen++; + return token; + } + +/** Get the specific Token. */ + final public Token getToken(int index) { + Token t = token; + for (int i = 0; i < index; i++) { + if (t.next != null) t = t.next; + else t = t.next = token_source.getNextToken(); + } + return t; + } + + private int jj_ntk() { + if ((jj_nt=token.next) == null) + return (jj_ntk = (token.next=token_source.getNextToken()).kind); + else + return (jj_ntk = jj_nt.kind); + } + + private java.util.List jj_expentries = new java.util.ArrayList(); + private int[] jj_expentry; + private int jj_kind = -1; + private int[] jj_lasttokens = new int[100]; + private int jj_endpos; + + private void jj_add_error_token(int kind, int pos) { + if (pos >= 100) return; + if (pos == jj_endpos + 1) { + jj_lasttokens[jj_endpos++] = kind; + } else if (jj_endpos != 0) { + jj_expentry = new int[jj_endpos]; + for (int i = 0; i < jj_endpos; i++) { + jj_expentry[i] = jj_lasttokens[i]; + } + jj_entries_loop: for (java.util.Iterator it = jj_expentries.iterator(); it.hasNext();) { + int[] oldentry = (int[])(it.next()); + if (oldentry.length == jj_expentry.length) { + for (int i = 0; i < jj_expentry.length; i++) { + if (oldentry[i] != jj_expentry[i]) { + continue jj_entries_loop; + } + } + jj_expentries.add(jj_expentry); + break jj_entries_loop; + } + } + if (pos != 0) jj_lasttokens[(jj_endpos = pos) - 1] = kind; + } + } + + /** Generate ParseException. */ + public ParseException generateParseException() { + jj_expentries.clear(); + boolean[] la1tokens = new boolean[34]; + if (jj_kind >= 0) { + la1tokens[jj_kind] = true; + jj_kind = -1; + } + for (int i = 0; i < 25; i++) { + if (jj_la1[i] == jj_gen) { + for (int j = 0; j < 32; j++) { + if ((jj_la1_0[i] & (1< jj_gen) { + jj_la = p.arg; jj_lastpos = jj_scanpos = p.first; + switch (i) { + case 0: jj_3_1(); break; + } + } + p = p.next; + } while (p != null); + } catch(LookaheadSuccess ls) { } + } + jj_rescan = false; + } + + private void jj_save(int index, int xla) { + JJCalls p = jj_2_rtns[index]; + while (p.gen > jj_gen) { + if (p.next == null) { p = p.next = new JJCalls(); break; } + p = p.next; + } + p.gen = jj_gen + xla - jj_la; p.first = token; p.arg = xla; + } + + static final class JJCalls { + int gen; + Token first; + int arg; + JJCalls next; + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParser.jj =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParser.jj (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParser.jj (revision 0) @@ -0,0 +1,486 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Original file is based on the QueryParser.jj from lucene 2.3 + */ + +//this is based on revision 535448 + +options { + STATIC=false; + JAVA_UNICODE_ESCAPE=true; + USER_CHAR_STREAM=false; + IGNORE_CASE=false; + JDK_VERSION="1.5"; +} + +PARSER_BEGIN(QueryParser) +package org.apache.lucene.queryParser.lucene2.parser; + +import java.io.StringReader; +import java.util.ArrayList; +import java.util.List; +import java.util.Vector; + +import org.apache.lucene.messages.Message; +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeError; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.QueryNodeParseException; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.nodes.AndQueryNode; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.BoostQueryNode; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.FuzzyQueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.GroupQueryNode; +import org.apache.lucene.queryParser.nodes.OpaqueQueryNode; +import org.apache.lucene.queryParser.nodes.OrQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricRangeQueryNode; +import org.apache.lucene.queryParser.nodes.PrefixWildcardQueryNode; +import org.apache.lucene.queryParser.nodes.SlopQueryNode; +import org.apache.lucene.queryParser.nodes.ProximityQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.QueryNodeImpl; +import org.apache.lucene.queryParser.nodes.QuotedFieldQueryNode; +import org.apache.lucene.queryParser.nodes.WildcardQueryNode; +import org.apache.lucene.queryParser.parser.Parser; + +@SuppressWarnings("all") +public class QueryParser implements Parser { + + private static final int CONJ_NONE =0; + private static final int CONJ_AND =2; + private static final int CONJ_OR =2; + + + // query parser constructor + public QueryParser() { + this(new StringReader("")); + } + /** Parses a query string, returning a {@link com.ibm.es.nuvo.search.query.tree.QueryNode}. + * @param query the query string to be parsed. + * @throws ParseException if the parsing fails + */ + public QueryNode parse(CharSequence query, CharSequence field) throws QueryNodeParseException { + ReInit(new StringReader(query.toString())); + try { + // TopLevelQuery is a Query followed by the end-of-input (EOF) + QueryNode querynode = TopLevelQuery(field); + return querynode; + } + catch (ParseException tme) { + tme.setQuery(query); + throw tme; + } + catch (Error tme) { + Message message = new MessageImpl(QueryParserMessages.INVALID_SYNTAX_CANNOT_PARSE, query, tme.getMessage()); + QueryNodeParseException e = new QueryNodeParseException(tme); + e.setQuery(query); + e.setNonLocalizedMessage(message); + throw e; + } + } + +} + +PARSER_END(QueryParser) + +/* ***************** */ +/* Token Definitions */ +/* ***************** */ + +<*> TOKEN : { + <#_NUM_CHAR: ["0"-"9"] > +// every character that follows a backslash is considered as an escaped character +| <#_ESCAPED_CHAR: "\\" ~[] > +| <#_TERM_START_CHAR: ( ~[ " ", "\t", "\n", "\r", "\u3000", "+", "-", "!", "(", ")", ":", "^", + "[", "]", "\"", "{", "}", "~", "*", "?", "\\" ] + | <_ESCAPED_CHAR> ) > +| <#_TERM_CHAR: ( <_TERM_START_CHAR> | <_ESCAPED_CHAR> | "-" | "+" ) > +| <#_WHITESPACE: ( " " | "\t" | "\n" | "\r" | "\u3000") > +| <#_QUOTED_CHAR: ( ~[ "\"", "\\" ] | <_ESCAPED_CHAR> ) > +} + + SKIP : { + < <_WHITESPACE>> +} + + TOKEN : { + +| +| +| +| +| +| +| +| +| : Boost +| )* "\""> +| (<_TERM_CHAR>)* > +| )+ ( "." (<_NUM_CHAR>)+ )? )? > +| (<_TERM_CHAR>)* "*" ) > +| | [ "*", "?" ]) (<_TERM_CHAR> | ( [ "*", "?" ] ))* > +| : RangeIn +| : RangeEx +} + + TOKEN : { +)+ ( "." (<_NUM_CHAR>)+ )? > : DEFAULT +} + + TOKEN : { + +| : DEFAULT +| +| +} + + TOKEN : { + +| : DEFAULT +| +| +} + +// * Query ::= ( Clause )* +// * Clause ::= ["+", "-"] [ ":"] ( | "(" Query ")" ) + +int Conjunction() : { + int ret = CONJ_NONE; +} +{ + [ + { ret = CONJ_AND; } + | { ret = CONJ_OR; } + ] + { return ret; } +} + +ModifierQueryNode.Modifier Modifiers() : { + ModifierQueryNode.Modifier ret = ModifierQueryNode.Modifier.MOD_NONE; +} +{ + [ + { ret = ModifierQueryNode.Modifier.MOD_REQ; } + | { ret = ModifierQueryNode.Modifier.MOD_NOT; } + | { ret = ModifierQueryNode.Modifier.MOD_NOT; } + ] + { return ret; } +} + +// This makes sure that there is no garbage after the query string +QueryNode TopLevelQuery(CharSequence field) : +{ + QueryNode q; +} +{ + q=Query(field) + { + return q; + } +} + +// These changes were made to introduce operator precedence: +// - Clause() now returns a QueryNode. +// - The modifiers are consumed by Clause() and returned as part of the QueryNode Object +// - Query does not consume conjunctions (AND, OR) anymore. +// - This is now done by two new non-terminals: ConjClause and DisjClause +// The parse tree looks similar to this: +// Query ::= DisjQuery ( DisjQuery )* +// DisjQuery ::= ConjQuery ( OR ConjQuery )* +// ConjQuery ::= Clause ( AND Clause )* +// Clause ::= [ Modifier ] ... + + +QueryNode Query(CharSequence field) : +{ + Vector clauses = null; + QueryNode c, first=null; +} +{ + first=DisjQuery(field) + ( + c=DisjQuery(field) + { + if (clauses == null) { + clauses = new Vector(); + clauses.addElement(first); + } + clauses.addElement(c); + } + )* + { + if (clauses != null) { + return new BooleanQueryNode(clauses); + } else { + return first; + } + } +} + +QueryNode DisjQuery(CharSequence field) : { + QueryNode first, c; + Vector clauses = null; +} +{ + first = ConjQuery(field) + ( + c=ConjQuery(field) + { + if (clauses == null) { + clauses = new Vector(); + clauses.addElement(first); + } + clauses.addElement(c); + } + )* + { + if (clauses != null) { + return new OrQueryNode(clauses); + } else { + return first; + } + } +} + +QueryNode ConjQuery(CharSequence field) : { + QueryNode first, c; + Vector clauses = null; +} +{ + first = ModClause(field) + ( + c=ModClause(field) + { + if (clauses == null) { + clauses = new Vector(); + clauses.addElement(first); + } + clauses.addElement(c); + } + )* + { + if (clauses != null) { + return new AndQueryNode(clauses); + } else { + return first; + } + } +} + +// QueryNode Query(CharSequence field) : +// { +// List clauses = new ArrayList(); +// List modifiers = new ArrayList(); +// QueryNode q, firstQuery=null; +// ModifierQueryNode.Modifier mods; +// int conj; +// } +// { +// mods=Modifiers() q=Clause(field) +// { +// if (mods == ModifierQueryNode.Modifier.MOD_NONE) firstQuery=q; +// +// // do not create modifier nodes with MOD_NONE +// if (mods != ModifierQueryNode.Modifier.MOD_NONE) { +// q = new ModifierQueryNode(q, mods); +// } +// clauses.add(q); +// } +// ( +// conj=Conjunction() mods=Modifiers() q=Clause(field) +// { +// // do not create modifier nodes with MOD_NONE +// if (mods != ModifierQueryNode.Modifier.MOD_NONE) { +// q = new ModifierQueryNode(q, mods); +// } +// clauses.add(q); +// //TODO: figure out what to do with AND and ORs +// } +// )* +// { +// if (clauses.size() == 1 && firstQuery != null) +// return firstQuery; +// else { +// return new BooleanQueryNode(clauses); +// } +// } +// } + +QueryNode ModClause(CharSequence field) : { + QueryNode q; + ModifierQueryNode.Modifier mods; +} +{ + mods=Modifiers() q= Clause(field) { + if (mods != ModifierQueryNode.Modifier.MOD_NONE) { + q = new ModifierQueryNode(q, mods); + } + return q; + } +} + +QueryNode Clause(CharSequence field) : { + QueryNode q; + Token fieldToken=null, boost=null; + boolean group = false; +} +{ + [ + LOOKAHEAD(2) + ( + fieldToken= {field=EscapeQuerySyntaxImpl.discardEscapeChar(fieldToken.image);} + | {field="*";} + ) + ] + + ( + q=Term(field) + | q=Query(field) ( boost=)? {group=true;} + + ) + { + if (boost != null) { + float f = (float)1.0; + try { + f = Float.valueOf(boost.image).floatValue(); + // avoid boosting null queries, such as those caused by stop words + if (q != null) { + q = new BoostQueryNode(q, f); + } + } catch (Exception ignored) { + /* Should this be handled somehow? (defaults to "no boost", if + * boost number is invalid) + */ + } + } + if (group) { q = new GroupQueryNode(q);} + return q; + } +} + + +QueryNode Term(CharSequence field) : { + Token term, boost=null, fuzzySlop=null, goop1, goop2; + boolean prefix = false; + boolean wildcard = false; + boolean fuzzy = false; + QueryNode q =null; + ParametricQueryNode qLower, qUpper; + float defaultMinSimilarity = 0.5f; +} +{ + ( + ( + term= { q = new FieldQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image), term.beginColumn, term.endColumn); } + | term= { wildcard=true; q = new WildcardQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image), term.beginColumn, term.endColumn); } + | term= { prefix=true; q = new PrefixWildcardQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image), term.beginColumn, term.endColumn); } + | term= { wildcard=true; q = new WildcardQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image), term.beginColumn, term.endColumn); } + | term= + ) + [ fuzzySlop= { fuzzy=true; } ] + [ boost= [ fuzzySlop= { fuzzy=true; } ] ] + { + if (!wildcard && !prefix && fuzzy) { + float fms = defaultMinSimilarity; + try { + fms = Float.valueOf(fuzzySlop.image.substring(1)).floatValue(); + } catch (Exception ignored) { } + if(fms < 0.0f || fms > 1.0f){ + throw new ParseException(new MessageImpl(QueryParserMessages.INVALID_SYNTAX_FUZZY_LIMITS)); + } + q = new FuzzyQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image), fms, term.beginColumn, term.endColumn); + } + } + | ( ( goop1=|goop1= ) + [ ] ( goop2=|goop2= ) + ) + [ boost= ] + { + if (goop1.kind == RANGEIN_QUOTED) { + goop1.image = goop1.image.substring(1, goop1.image.length()-1); + } + if (goop2.kind == RANGEIN_QUOTED) { + goop2.image = goop2.image.substring(1, goop2.image.length()-1); + } + + qLower = new ParametricQueryNode(field, ParametricQueryNode.CompareOperator.GE, + EscapeQuerySyntaxImpl.discardEscapeChar(goop1.image), goop1.beginColumn, goop1.endColumn); + qUpper = new ParametricQueryNode(field, ParametricQueryNode.CompareOperator.LE, + EscapeQuerySyntaxImpl.discardEscapeChar(goop2.image), goop2.beginColumn, goop2.endColumn); + q = new ParametricRangeQueryNode(qLower, qUpper); + } + | ( ( goop1=|goop1= ) + [ ] ( goop2=|goop2= ) + ) + [ boost= ] + { + if (goop1.kind == RANGEEX_QUOTED) { + goop1.image = goop1.image.substring(1, goop1.image.length()-1); + } + if (goop2.kind == RANGEEX_QUOTED) { + goop2.image = goop2.image.substring(1, goop2.image.length()-1); + } + qLower = new ParametricQueryNode(field, ParametricQueryNode.CompareOperator.GT, + EscapeQuerySyntaxImpl.discardEscapeChar(goop1.image), goop1.beginColumn, goop1.endColumn); + qUpper = new ParametricQueryNode(field, ParametricQueryNode.CompareOperator.LT, + EscapeQuerySyntaxImpl.discardEscapeChar(goop2.image), goop2.beginColumn, goop2.endColumn); + q = new ParametricRangeQueryNode(qLower, qUpper); + } + | term= {q = new QuotedFieldQueryNode(field, EscapeQuerySyntaxImpl.discardEscapeChar(term.image.substring(1, term.image.length()-1)), term.beginColumn + 1, term.endColumn - 1);} + [ fuzzySlop= ] + [ boost= ] + { + int phraseSlop = 0; + + if (fuzzySlop != null) { + try { + phraseSlop = Float.valueOf(fuzzySlop.image.substring(1)).intValue(); + q = new SlopQueryNode(q, phraseSlop); + } + catch (Exception ignored) { + /* Should this be handled somehow? (defaults to "no PhraseSlop", if + * slop number is invalid) + */ + } + } + + } + ) + { + if (boost != null) { + float f = (float)1.0; + try { + f = Float.valueOf(boost.image).floatValue(); + // avoid boosting null queries, such as those caused by stop words + if (q != null) { + q = new BoostQueryNode(q, f); + } + } catch (Exception ignored) { + /* Should this be handled somehow? (defaults to "no boost", if + * boost number is invalid) + */ + } + } + return q; + } +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParserConstants.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParserConstants.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParserConstants.java (revision 0) @@ -0,0 +1,125 @@ +/* Generated By:JavaCC: Do not edit this line. QueryParserConstants.java */ +package org.apache.lucene.queryParser.lucene2.parser; + + +/** + * Token literal values and constants. + * Generated by org.javacc.parser.OtherFilesGen#start() + */ +public interface QueryParserConstants { + + /** End of File. */ + int EOF = 0; + /** RegularExpression Id. */ + int _NUM_CHAR = 1; + /** RegularExpression Id. */ + int _ESCAPED_CHAR = 2; + /** RegularExpression Id. */ + int _TERM_START_CHAR = 3; + /** RegularExpression Id. */ + int _TERM_CHAR = 4; + /** RegularExpression Id. */ + int _WHITESPACE = 5; + /** RegularExpression Id. */ + int _QUOTED_CHAR = 6; + /** RegularExpression Id. */ + int AND = 8; + /** RegularExpression Id. */ + int OR = 9; + /** RegularExpression Id. */ + int NOT = 10; + /** RegularExpression Id. */ + int PLUS = 11; + /** RegularExpression Id. */ + int MINUS = 12; + /** RegularExpression Id. */ + int LPAREN = 13; + /** RegularExpression Id. */ + int RPAREN = 14; + /** RegularExpression Id. */ + int COLON = 15; + /** RegularExpression Id. */ + int STAR = 16; + /** RegularExpression Id. */ + int CARAT = 17; + /** RegularExpression Id. */ + int QUOTED = 18; + /** RegularExpression Id. */ + int TERM = 19; + /** RegularExpression Id. */ + int FUZZY_SLOP = 20; + /** RegularExpression Id. */ + int PREFIXTERM = 21; + /** RegularExpression Id. */ + int WILDTERM = 22; + /** RegularExpression Id. */ + int RANGEIN_START = 23; + /** RegularExpression Id. */ + int RANGEEX_START = 24; + /** RegularExpression Id. */ + int NUMBER = 25; + /** RegularExpression Id. */ + int RANGEIN_TO = 26; + /** RegularExpression Id. */ + int RANGEIN_END = 27; + /** RegularExpression Id. */ + int RANGEIN_QUOTED = 28; + /** RegularExpression Id. */ + int RANGEIN_GOOP = 29; + /** RegularExpression Id. */ + int RANGEEX_TO = 30; + /** RegularExpression Id. */ + int RANGEEX_END = 31; + /** RegularExpression Id. */ + int RANGEEX_QUOTED = 32; + /** RegularExpression Id. */ + int RANGEEX_GOOP = 33; + + /** Lexical state. */ + int Boost = 0; + /** Lexical state. */ + int RangeEx = 1; + /** Lexical state. */ + int RangeIn = 2; + /** Lexical state. */ + int DEFAULT = 3; + + /** Literal token values. */ + String[] tokenImage = { + "", + "<_NUM_CHAR>", + "<_ESCAPED_CHAR>", + "<_TERM_START_CHAR>", + "<_TERM_CHAR>", + "<_WHITESPACE>", + "<_QUOTED_CHAR>", + "", + "", + "", + "", + "\"+\"", + "\"-\"", + "\"(\"", + "\")\"", + "\":\"", + "\"*\"", + "\"^\"", + "", + "", + "", + "", + "", + "\"[\"", + "\"{\"", + "", + "\"TO\"", + "\"]\"", + "", + "", + "\"TO\"", + "\"}\"", + "", + "", + }; + +} Index: src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParserTokenManager.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParserTokenManager.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/QueryParserTokenManager.java (revision 0) @@ -0,0 +1,1258 @@ +/* Generated By:JavaCC: Do not edit this line. QueryParserTokenManager.java */ +package org.apache.lucene.queryParser.lucene2.parser; +import java.io.StringReader; +import java.util.ArrayList; +import java.util.List; +import java.util.Vector; +import org.apache.lucene.messages.Message; +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeError; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.QueryNodeParseException; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.nodes.AndQueryNode; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.BoostQueryNode; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.FuzzyQueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.GroupQueryNode; +import org.apache.lucene.queryParser.nodes.OpaqueQueryNode; +import org.apache.lucene.queryParser.nodes.OrQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricRangeQueryNode; +import org.apache.lucene.queryParser.nodes.PrefixWildcardQueryNode; +import org.apache.lucene.queryParser.nodes.SlopQueryNode; +import org.apache.lucene.queryParser.nodes.ProximityQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.QueryNodeImpl; +import org.apache.lucene.queryParser.nodes.QuotedFieldQueryNode; +import org.apache.lucene.queryParser.nodes.WildcardQueryNode; +import org.apache.lucene.queryParser.parser.Parser; + +/** Token Manager. */ +public class QueryParserTokenManager implements QueryParserConstants +{ + + /** Debug output. */ + public java.io.PrintStream debugStream = System.out; + /** Set debug output. */ + public void setDebugStream(java.io.PrintStream ds) { debugStream = ds; } +private final int jjStopStringLiteralDfa_3(int pos, long active0) +{ + switch (pos) + { + default : + return -1; + } +} +private final int jjStartNfa_3(int pos, long active0) +{ + return jjMoveNfa_3(jjStopStringLiteralDfa_3(pos, active0), pos + 1); +} +private int jjStopAtPos(int pos, int kind) +{ + jjmatchedKind = kind; + jjmatchedPos = pos; + return pos + 1; +} +private int jjMoveStringLiteralDfa0_3() +{ + switch(curChar) + { + case 40: + return jjStopAtPos(0, 13); + case 41: + return jjStopAtPos(0, 14); + case 42: + return jjStartNfaWithStates_3(0, 16, 36); + case 43: + return jjStopAtPos(0, 11); + case 45: + return jjStopAtPos(0, 12); + case 58: + return jjStopAtPos(0, 15); + case 91: + return jjStopAtPos(0, 23); + case 94: + return jjStopAtPos(0, 17); + case 123: + return jjStopAtPos(0, 24); + default : + return jjMoveNfa_3(0, 0); + } +} +private int jjStartNfaWithStates_3(int pos, int kind, int state) +{ + jjmatchedKind = kind; + jjmatchedPos = pos; + try { curChar = input_stream.readChar(); } + catch(java.io.IOException e) { return pos + 1; } + return jjMoveNfa_3(state, pos + 1); +} +static final long[] jjbitVec0 = { + 0x1L, 0x0L, 0x0L, 0x0L +}; +static final long[] jjbitVec1 = { + 0xfffffffffffffffeL, 0xffffffffffffffffL, 0xffffffffffffffffL, 0xffffffffffffffffL +}; +static final long[] jjbitVec3 = { + 0x0L, 0x0L, 0xffffffffffffffffL, 0xffffffffffffffffL +}; +static final long[] jjbitVec4 = { + 0xfffefffffffffffeL, 0xffffffffffffffffL, 0xffffffffffffffffL, 0xffffffffffffffffL +}; +private int jjMoveNfa_3(int startState, int curPos) +{ + int startsAt = 0; + jjnewStateCnt = 36; + int i = 1; + jjstateSet[0] = startState; + int kind = 0x7fffffff; + for (;;) + { + if (++jjround == 0x7fffffff) + ReInitRounds(); + if (curChar < 64) + { + long l = 1L << curChar; + do + { + switch(jjstateSet[--i]) + { + case 36: + case 25: + if ((0xfbfffcf8ffffd9ffL & l) == 0L) + break; + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + break; + case 0: + if ((0xfbffd4f8ffffd9ffL & l) != 0L) + { + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + } + else if ((0x100002600L & l) != 0L) + { + if (kind > 7) + kind = 7; + } + else if (curChar == 34) + jjCheckNAddStates(0, 2); + else if (curChar == 33) + { + if (kind > 10) + kind = 10; + } + if ((0x7bffd0f8ffffd9ffL & l) != 0L) + { + if (kind > 19) + kind = 19; + jjCheckNAddStates(3, 7); + } + else if (curChar == 42) + { + if (kind > 21) + kind = 21; + } + if (curChar == 38) + jjstateSet[jjnewStateCnt++] = 4; + break; + case 4: + if (curChar == 38 && kind > 8) + kind = 8; + break; + case 5: + if (curChar == 38) + jjstateSet[jjnewStateCnt++] = 4; + break; + case 13: + if (curChar == 33 && kind > 10) + kind = 10; + break; + case 14: + if (curChar == 34) + jjCheckNAddStates(0, 2); + break; + case 15: + if ((0xfffffffbffffffffL & l) != 0L) + jjCheckNAddStates(0, 2); + break; + case 17: + jjCheckNAddStates(0, 2); + break; + case 18: + if (curChar == 34 && kind > 18) + kind = 18; + break; + case 20: + if ((0x3ff000000000000L & l) == 0L) + break; + if (kind > 20) + kind = 20; + jjAddStates(8, 9); + break; + case 21: + if (curChar == 46) + jjCheckNAdd(22); + break; + case 22: + if ((0x3ff000000000000L & l) == 0L) + break; + if (kind > 20) + kind = 20; + jjCheckNAdd(22); + break; + case 23: + if (curChar == 42 && kind > 21) + kind = 21; + break; + case 24: + if ((0xfbffd4f8ffffd9ffL & l) == 0L) + break; + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + break; + case 27: + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + break; + case 28: + if ((0x7bffd0f8ffffd9ffL & l) == 0L) + break; + if (kind > 19) + kind = 19; + jjCheckNAddStates(3, 7); + break; + case 29: + if ((0x7bfff8f8ffffd9ffL & l) == 0L) + break; + if (kind > 19) + kind = 19; + jjCheckNAddTwoStates(29, 30); + break; + case 31: + if (kind > 19) + kind = 19; + jjCheckNAddTwoStates(29, 30); + break; + case 32: + if ((0x7bfff8f8ffffd9ffL & l) != 0L) + jjCheckNAddStates(10, 12); + break; + case 34: + jjCheckNAddStates(10, 12); + break; + default : break; + } + } while(i != startsAt); + } + else if (curChar < 128) + { + long l = 1L << (curChar & 077); + do + { + switch(jjstateSet[--i]) + { + case 36: + if ((0x97ffffff87ffffffL & l) != 0L) + { + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + } + else if (curChar == 92) + jjCheckNAddTwoStates(27, 27); + break; + case 0: + if ((0x97ffffff87ffffffL & l) != 0L) + { + if (kind > 19) + kind = 19; + jjCheckNAddStates(3, 7); + } + else if (curChar == 92) + jjCheckNAddStates(13, 15); + else if (curChar == 126) + { + if (kind > 20) + kind = 20; + jjstateSet[jjnewStateCnt++] = 20; + } + if ((0x97ffffff87ffffffL & l) != 0L) + { + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + } + if (curChar == 78) + jjstateSet[jjnewStateCnt++] = 11; + else if (curChar == 124) + jjstateSet[jjnewStateCnt++] = 8; + else if (curChar == 79) + jjstateSet[jjnewStateCnt++] = 6; + else if (curChar == 65) + jjstateSet[jjnewStateCnt++] = 2; + break; + case 1: + if (curChar == 68 && kind > 8) + kind = 8; + break; + case 2: + if (curChar == 78) + jjstateSet[jjnewStateCnt++] = 1; + break; + case 3: + if (curChar == 65) + jjstateSet[jjnewStateCnt++] = 2; + break; + case 6: + if (curChar == 82 && kind > 9) + kind = 9; + break; + case 7: + if (curChar == 79) + jjstateSet[jjnewStateCnt++] = 6; + break; + case 8: + if (curChar == 124 && kind > 9) + kind = 9; + break; + case 9: + if (curChar == 124) + jjstateSet[jjnewStateCnt++] = 8; + break; + case 10: + if (curChar == 84 && kind > 10) + kind = 10; + break; + case 11: + if (curChar == 79) + jjstateSet[jjnewStateCnt++] = 10; + break; + case 12: + if (curChar == 78) + jjstateSet[jjnewStateCnt++] = 11; + break; + case 15: + if ((0xffffffffefffffffL & l) != 0L) + jjCheckNAddStates(0, 2); + break; + case 16: + if (curChar == 92) + jjstateSet[jjnewStateCnt++] = 17; + break; + case 17: + jjCheckNAddStates(0, 2); + break; + case 19: + if (curChar != 126) + break; + if (kind > 20) + kind = 20; + jjstateSet[jjnewStateCnt++] = 20; + break; + case 24: + if ((0x97ffffff87ffffffL & l) == 0L) + break; + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + break; + case 25: + if ((0x97ffffff87ffffffL & l) == 0L) + break; + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + break; + case 26: + if (curChar == 92) + jjCheckNAddTwoStates(27, 27); + break; + case 27: + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + break; + case 28: + if ((0x97ffffff87ffffffL & l) == 0L) + break; + if (kind > 19) + kind = 19; + jjCheckNAddStates(3, 7); + break; + case 29: + if ((0x97ffffff87ffffffL & l) == 0L) + break; + if (kind > 19) + kind = 19; + jjCheckNAddTwoStates(29, 30); + break; + case 30: + if (curChar == 92) + jjCheckNAddTwoStates(31, 31); + break; + case 31: + if (kind > 19) + kind = 19; + jjCheckNAddTwoStates(29, 30); + break; + case 32: + if ((0x97ffffff87ffffffL & l) != 0L) + jjCheckNAddStates(10, 12); + break; + case 33: + if (curChar == 92) + jjCheckNAddTwoStates(34, 34); + break; + case 34: + jjCheckNAddStates(10, 12); + break; + case 35: + if (curChar == 92) + jjCheckNAddStates(13, 15); + break; + default : break; + } + } while(i != startsAt); + } + else + { + int hiByte = (int)(curChar >> 8); + int i1 = hiByte >> 6; + long l1 = 1L << (hiByte & 077); + int i2 = (curChar & 0xff) >> 6; + long l2 = 1L << (curChar & 077); + do + { + switch(jjstateSet[--i]) + { + case 36: + case 25: + if (!jjCanMove_2(hiByte, i1, i2, l1, l2)) + break; + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + break; + case 0: + if (jjCanMove_0(hiByte, i1, i2, l1, l2)) + { + if (kind > 7) + kind = 7; + } + if (jjCanMove_2(hiByte, i1, i2, l1, l2)) + { + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + } + if (jjCanMove_2(hiByte, i1, i2, l1, l2)) + { + if (kind > 19) + kind = 19; + jjCheckNAddStates(3, 7); + } + break; + case 15: + case 17: + if (jjCanMove_1(hiByte, i1, i2, l1, l2)) + jjCheckNAddStates(0, 2); + break; + case 24: + if (!jjCanMove_2(hiByte, i1, i2, l1, l2)) + break; + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + break; + case 27: + if (!jjCanMove_1(hiByte, i1, i2, l1, l2)) + break; + if (kind > 22) + kind = 22; + jjCheckNAddTwoStates(25, 26); + break; + case 28: + if (!jjCanMove_2(hiByte, i1, i2, l1, l2)) + break; + if (kind > 19) + kind = 19; + jjCheckNAddStates(3, 7); + break; + case 29: + if (!jjCanMove_2(hiByte, i1, i2, l1, l2)) + break; + if (kind > 19) + kind = 19; + jjCheckNAddTwoStates(29, 30); + break; + case 31: + if (!jjCanMove_1(hiByte, i1, i2, l1, l2)) + break; + if (kind > 19) + kind = 19; + jjCheckNAddTwoStates(29, 30); + break; + case 32: + if (jjCanMove_2(hiByte, i1, i2, l1, l2)) + jjCheckNAddStates(10, 12); + break; + case 34: + if (jjCanMove_1(hiByte, i1, i2, l1, l2)) + jjCheckNAddStates(10, 12); + break; + default : break; + } + } while(i != startsAt); + } + if (kind != 0x7fffffff) + { + jjmatchedKind = kind; + jjmatchedPos = curPos; + kind = 0x7fffffff; + } + ++curPos; + if ((i = jjnewStateCnt) == (startsAt = 36 - (jjnewStateCnt = startsAt))) + return curPos; + try { curChar = input_stream.readChar(); } + catch(java.io.IOException e) { return curPos; } + } +} +private final int jjStopStringLiteralDfa_1(int pos, long active0) +{ + switch (pos) + { + case 0: + if ((active0 & 0x40000000L) != 0L) + { + jjmatchedKind = 33; + return 6; + } + return -1; + default : + return -1; + } +} +private final int jjStartNfa_1(int pos, long active0) +{ + return jjMoveNfa_1(jjStopStringLiteralDfa_1(pos, active0), pos + 1); +} +private int jjMoveStringLiteralDfa0_1() +{ + switch(curChar) + { + case 84: + return jjMoveStringLiteralDfa1_1(0x40000000L); + case 125: + return jjStopAtPos(0, 31); + default : + return jjMoveNfa_1(0, 0); + } +} +private int jjMoveStringLiteralDfa1_1(long active0) +{ + try { curChar = input_stream.readChar(); } + catch(java.io.IOException e) { + jjStopStringLiteralDfa_1(0, active0); + return 1; + } + switch(curChar) + { + case 79: + if ((active0 & 0x40000000L) != 0L) + return jjStartNfaWithStates_1(1, 30, 6); + break; + default : + break; + } + return jjStartNfa_1(0, active0); +} +private int jjStartNfaWithStates_1(int pos, int kind, int state) +{ + jjmatchedKind = kind; + jjmatchedPos = pos; + try { curChar = input_stream.readChar(); } + catch(java.io.IOException e) { return pos + 1; } + return jjMoveNfa_1(state, pos + 1); +} +private int jjMoveNfa_1(int startState, int curPos) +{ + int startsAt = 0; + jjnewStateCnt = 7; + int i = 1; + jjstateSet[0] = startState; + int kind = 0x7fffffff; + for (;;) + { + if (++jjround == 0x7fffffff) + ReInitRounds(); + if (curChar < 64) + { + long l = 1L << curChar; + do + { + switch(jjstateSet[--i]) + { + case 0: + if ((0xfffffffeffffffffL & l) != 0L) + { + if (kind > 33) + kind = 33; + jjCheckNAdd(6); + } + if ((0x100002600L & l) != 0L) + { + if (kind > 7) + kind = 7; + } + else if (curChar == 34) + jjCheckNAddTwoStates(2, 4); + break; + case 1: + if (curChar == 34) + jjCheckNAddTwoStates(2, 4); + break; + case 2: + if ((0xfffffffbffffffffL & l) != 0L) + jjCheckNAddStates(16, 18); + break; + case 3: + if (curChar == 34) + jjCheckNAddStates(16, 18); + break; + case 5: + if (curChar == 34 && kind > 32) + kind = 32; + break; + case 6: + if ((0xfffffffeffffffffL & l) == 0L) + break; + if (kind > 33) + kind = 33; + jjCheckNAdd(6); + break; + default : break; + } + } while(i != startsAt); + } + else if (curChar < 128) + { + long l = 1L << (curChar & 077); + do + { + switch(jjstateSet[--i]) + { + case 0: + case 6: + if ((0xdfffffffffffffffL & l) == 0L) + break; + if (kind > 33) + kind = 33; + jjCheckNAdd(6); + break; + case 2: + jjAddStates(16, 18); + break; + case 4: + if (curChar == 92) + jjstateSet[jjnewStateCnt++] = 3; + break; + default : break; + } + } while(i != startsAt); + } + else + { + int hiByte = (int)(curChar >> 8); + int i1 = hiByte >> 6; + long l1 = 1L << (hiByte & 077); + int i2 = (curChar & 0xff) >> 6; + long l2 = 1L << (curChar & 077); + do + { + switch(jjstateSet[--i]) + { + case 0: + if (jjCanMove_0(hiByte, i1, i2, l1, l2)) + { + if (kind > 7) + kind = 7; + } + if (jjCanMove_1(hiByte, i1, i2, l1, l2)) + { + if (kind > 33) + kind = 33; + jjCheckNAdd(6); + } + break; + case 2: + if (jjCanMove_1(hiByte, i1, i2, l1, l2)) + jjAddStates(16, 18); + break; + case 6: + if (!jjCanMove_1(hiByte, i1, i2, l1, l2)) + break; + if (kind > 33) + kind = 33; + jjCheckNAdd(6); + break; + default : break; + } + } while(i != startsAt); + } + if (kind != 0x7fffffff) + { + jjmatchedKind = kind; + jjmatchedPos = curPos; + kind = 0x7fffffff; + } + ++curPos; + if ((i = jjnewStateCnt) == (startsAt = 7 - (jjnewStateCnt = startsAt))) + return curPos; + try { curChar = input_stream.readChar(); } + catch(java.io.IOException e) { return curPos; } + } +} +private int jjMoveStringLiteralDfa0_0() +{ + return jjMoveNfa_0(0, 0); +} +private int jjMoveNfa_0(int startState, int curPos) +{ + int startsAt = 0; + jjnewStateCnt = 3; + int i = 1; + jjstateSet[0] = startState; + int kind = 0x7fffffff; + for (;;) + { + if (++jjround == 0x7fffffff) + ReInitRounds(); + if (curChar < 64) + { + long l = 1L << curChar; + do + { + switch(jjstateSet[--i]) + { + case 0: + if ((0x3ff000000000000L & l) == 0L) + break; + if (kind > 25) + kind = 25; + jjAddStates(19, 20); + break; + case 1: + if (curChar == 46) + jjCheckNAdd(2); + break; + case 2: + if ((0x3ff000000000000L & l) == 0L) + break; + if (kind > 25) + kind = 25; + jjCheckNAdd(2); + break; + default : break; + } + } while(i != startsAt); + } + else if (curChar < 128) + { + long l = 1L << (curChar & 077); + do + { + switch(jjstateSet[--i]) + { + default : break; + } + } while(i != startsAt); + } + else + { + int hiByte = (int)(curChar >> 8); + int i1 = hiByte >> 6; + long l1 = 1L << (hiByte & 077); + int i2 = (curChar & 0xff) >> 6; + long l2 = 1L << (curChar & 077); + do + { + switch(jjstateSet[--i]) + { + default : break; + } + } while(i != startsAt); + } + if (kind != 0x7fffffff) + { + jjmatchedKind = kind; + jjmatchedPos = curPos; + kind = 0x7fffffff; + } + ++curPos; + if ((i = jjnewStateCnt) == (startsAt = 3 - (jjnewStateCnt = startsAt))) + return curPos; + try { curChar = input_stream.readChar(); } + catch(java.io.IOException e) { return curPos; } + } +} +private final int jjStopStringLiteralDfa_2(int pos, long active0) +{ + switch (pos) + { + case 0: + if ((active0 & 0x4000000L) != 0L) + { + jjmatchedKind = 29; + return 6; + } + return -1; + default : + return -1; + } +} +private final int jjStartNfa_2(int pos, long active0) +{ + return jjMoveNfa_2(jjStopStringLiteralDfa_2(pos, active0), pos + 1); +} +private int jjMoveStringLiteralDfa0_2() +{ + switch(curChar) + { + case 84: + return jjMoveStringLiteralDfa1_2(0x4000000L); + case 93: + return jjStopAtPos(0, 27); + default : + return jjMoveNfa_2(0, 0); + } +} +private int jjMoveStringLiteralDfa1_2(long active0) +{ + try { curChar = input_stream.readChar(); } + catch(java.io.IOException e) { + jjStopStringLiteralDfa_2(0, active0); + return 1; + } + switch(curChar) + { + case 79: + if ((active0 & 0x4000000L) != 0L) + return jjStartNfaWithStates_2(1, 26, 6); + break; + default : + break; + } + return jjStartNfa_2(0, active0); +} +private int jjStartNfaWithStates_2(int pos, int kind, int state) +{ + jjmatchedKind = kind; + jjmatchedPos = pos; + try { curChar = input_stream.readChar(); } + catch(java.io.IOException e) { return pos + 1; } + return jjMoveNfa_2(state, pos + 1); +} +private int jjMoveNfa_2(int startState, int curPos) +{ + int startsAt = 0; + jjnewStateCnt = 7; + int i = 1; + jjstateSet[0] = startState; + int kind = 0x7fffffff; + for (;;) + { + if (++jjround == 0x7fffffff) + ReInitRounds(); + if (curChar < 64) + { + long l = 1L << curChar; + do + { + switch(jjstateSet[--i]) + { + case 0: + if ((0xfffffffeffffffffL & l) != 0L) + { + if (kind > 29) + kind = 29; + jjCheckNAdd(6); + } + if ((0x100002600L & l) != 0L) + { + if (kind > 7) + kind = 7; + } + else if (curChar == 34) + jjCheckNAddTwoStates(2, 4); + break; + case 1: + if (curChar == 34) + jjCheckNAddTwoStates(2, 4); + break; + case 2: + if ((0xfffffffbffffffffL & l) != 0L) + jjCheckNAddStates(16, 18); + break; + case 3: + if (curChar == 34) + jjCheckNAddStates(16, 18); + break; + case 5: + if (curChar == 34 && kind > 28) + kind = 28; + break; + case 6: + if ((0xfffffffeffffffffL & l) == 0L) + break; + if (kind > 29) + kind = 29; + jjCheckNAdd(6); + break; + default : break; + } + } while(i != startsAt); + } + else if (curChar < 128) + { + long l = 1L << (curChar & 077); + do + { + switch(jjstateSet[--i]) + { + case 0: + case 6: + if ((0xffffffffdfffffffL & l) == 0L) + break; + if (kind > 29) + kind = 29; + jjCheckNAdd(6); + break; + case 2: + jjAddStates(16, 18); + break; + case 4: + if (curChar == 92) + jjstateSet[jjnewStateCnt++] = 3; + break; + default : break; + } + } while(i != startsAt); + } + else + { + int hiByte = (int)(curChar >> 8); + int i1 = hiByte >> 6; + long l1 = 1L << (hiByte & 077); + int i2 = (curChar & 0xff) >> 6; + long l2 = 1L << (curChar & 077); + do + { + switch(jjstateSet[--i]) + { + case 0: + if (jjCanMove_0(hiByte, i1, i2, l1, l2)) + { + if (kind > 7) + kind = 7; + } + if (jjCanMove_1(hiByte, i1, i2, l1, l2)) + { + if (kind > 29) + kind = 29; + jjCheckNAdd(6); + } + break; + case 2: + if (jjCanMove_1(hiByte, i1, i2, l1, l2)) + jjAddStates(16, 18); + break; + case 6: + if (!jjCanMove_1(hiByte, i1, i2, l1, l2)) + break; + if (kind > 29) + kind = 29; + jjCheckNAdd(6); + break; + default : break; + } + } while(i != startsAt); + } + if (kind != 0x7fffffff) + { + jjmatchedKind = kind; + jjmatchedPos = curPos; + kind = 0x7fffffff; + } + ++curPos; + if ((i = jjnewStateCnt) == (startsAt = 7 - (jjnewStateCnt = startsAt))) + return curPos; + try { curChar = input_stream.readChar(); } + catch(java.io.IOException e) { return curPos; } + } +} +static final int[] jjnextStates = { + 15, 16, 18, 29, 32, 23, 33, 30, 20, 21, 32, 23, 33, 31, 34, 27, + 2, 4, 5, 0, 1, +}; +private static final boolean jjCanMove_0(int hiByte, int i1, int i2, long l1, long l2) +{ + switch(hiByte) + { + case 48: + return ((jjbitVec0[i2] & l2) != 0L); + default : + return false; + } +} +private static final boolean jjCanMove_1(int hiByte, int i1, int i2, long l1, long l2) +{ + switch(hiByte) + { + case 0: + return ((jjbitVec3[i2] & l2) != 0L); + default : + if ((jjbitVec1[i1] & l1) != 0L) + return true; + return false; + } +} +private static final boolean jjCanMove_2(int hiByte, int i1, int i2, long l1, long l2) +{ + switch(hiByte) + { + case 0: + return ((jjbitVec3[i2] & l2) != 0L); + case 48: + return ((jjbitVec1[i2] & l2) != 0L); + default : + if ((jjbitVec4[i1] & l1) != 0L) + return true; + return false; + } +} + +/** Token literal values. */ +public static final String[] jjstrLiteralImages = { +"", null, null, null, null, null, null, null, null, null, null, "\53", "\55", +"\50", "\51", "\72", "\52", "\136", null, null, null, null, null, "\133", "\173", +null, "\124\117", "\135", null, null, "\124\117", "\175", null, null, }; + +/** Lexer state names. */ +public static final String[] lexStateNames = { + "Boost", + "RangeEx", + "RangeIn", + "DEFAULT", +}; + +/** Lex State array. */ +public static final int[] jjnewLexState = { + -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, -1, -1, -1, -1, -1, 2, 1, + 3, -1, 3, -1, -1, -1, 3, -1, -1, +}; +static final long[] jjtoToken = { + 0x3ffffff01L, +}; +static final long[] jjtoSkip = { + 0x80L, +}; +protected JavaCharStream input_stream; +private final int[] jjrounds = new int[36]; +private final int[] jjstateSet = new int[72]; +protected char curChar; +/** Constructor. */ +public QueryParserTokenManager(JavaCharStream stream){ + if (JavaCharStream.staticFlag) + throw new Error("ERROR: Cannot use a static CharStream class with a non-static lexical analyzer."); + input_stream = stream; +} + +/** Constructor. */ +public QueryParserTokenManager(JavaCharStream stream, int lexState){ + this(stream); + SwitchTo(lexState); +} + +/** Reinitialise parser. */ +public void ReInit(JavaCharStream stream) +{ + jjmatchedPos = jjnewStateCnt = 0; + curLexState = defaultLexState; + input_stream = stream; + ReInitRounds(); +} +private void ReInitRounds() +{ + int i; + jjround = 0x80000001; + for (i = 36; i-- > 0;) + jjrounds[i] = 0x80000000; +} + +/** Reinitialise parser. */ +public void ReInit(JavaCharStream stream, int lexState) +{ + ReInit(stream); + SwitchTo(lexState); +} + +/** Switch to specified lex state. */ +public void SwitchTo(int lexState) +{ + if (lexState >= 4 || lexState < 0) + throw new TokenMgrError("Error: Ignoring invalid lexical state : " + lexState + ". State unchanged.", TokenMgrError.INVALID_LEXICAL_STATE); + else + curLexState = lexState; +} + +protected Token jjFillToken() +{ + final Token t; + final String curTokenImage; + final int beginLine; + final int endLine; + final int beginColumn; + final int endColumn; + String im = jjstrLiteralImages[jjmatchedKind]; + curTokenImage = (im == null) ? input_stream.GetImage() : im; + beginLine = input_stream.getBeginLine(); + beginColumn = input_stream.getBeginColumn(); + endLine = input_stream.getEndLine(); + endColumn = input_stream.getEndColumn(); + t = Token.newToken(jjmatchedKind, curTokenImage); + + t.beginLine = beginLine; + t.endLine = endLine; + t.beginColumn = beginColumn; + t.endColumn = endColumn; + + return t; +} + +int curLexState = 3; +int defaultLexState = 3; +int jjnewStateCnt; +int jjround; +int jjmatchedPos; +int jjmatchedKind; + +/** Get the next Token. */ +public Token getNextToken() +{ + Token matchedToken; + int curPos = 0; + + EOFLoop : + for (;;) + { + try + { + curChar = input_stream.BeginToken(); + } + catch(java.io.IOException e) + { + jjmatchedKind = 0; + matchedToken = jjFillToken(); + return matchedToken; + } + + switch(curLexState) + { + case 0: + jjmatchedKind = 0x7fffffff; + jjmatchedPos = 0; + curPos = jjMoveStringLiteralDfa0_0(); + break; + case 1: + jjmatchedKind = 0x7fffffff; + jjmatchedPos = 0; + curPos = jjMoveStringLiteralDfa0_1(); + break; + case 2: + jjmatchedKind = 0x7fffffff; + jjmatchedPos = 0; + curPos = jjMoveStringLiteralDfa0_2(); + break; + case 3: + jjmatchedKind = 0x7fffffff; + jjmatchedPos = 0; + curPos = jjMoveStringLiteralDfa0_3(); + break; + } + if (jjmatchedKind != 0x7fffffff) + { + if (jjmatchedPos + 1 < curPos) + input_stream.backup(curPos - jjmatchedPos - 1); + if ((jjtoToken[jjmatchedKind >> 6] & (1L << (jjmatchedKind & 077))) != 0L) + { + matchedToken = jjFillToken(); + if (jjnewLexState[jjmatchedKind] != -1) + curLexState = jjnewLexState[jjmatchedKind]; + return matchedToken; + } + else + { + if (jjnewLexState[jjmatchedKind] != -1) + curLexState = jjnewLexState[jjmatchedKind]; + continue EOFLoop; + } + } + int error_line = input_stream.getEndLine(); + int error_column = input_stream.getEndColumn(); + String error_after = null; + boolean EOFSeen = false; + try { input_stream.readChar(); input_stream.backup(1); } + catch (java.io.IOException e1) { + EOFSeen = true; + error_after = curPos <= 1 ? "" : input_stream.GetImage(); + if (curChar == '\n' || curChar == '\r') { + error_line++; + error_column = 0; + } + else + error_column++; + } + if (!EOFSeen) { + input_stream.backup(1); + error_after = curPos <= 1 ? "" : input_stream.GetImage(); + } + throw new TokenMgrError(EOFSeen, curLexState, error_line, error_column, error_after, curChar, TokenMgrError.LEXICAL_ERROR); + } +} + +private void jjCheckNAdd(int state) +{ + if (jjrounds[state] != jjround) + { + jjstateSet[jjnewStateCnt++] = state; + jjrounds[state] = jjround; + } +} +private void jjAddStates(int start, int end) +{ + do { + jjstateSet[jjnewStateCnt++] = jjnextStates[start]; + } while (start++ != end); +} +private void jjCheckNAddTwoStates(int state1, int state2) +{ + jjCheckNAdd(state1); + jjCheckNAdd(state2); +} + +private void jjCheckNAddStates(int start, int end) +{ + do { + jjCheckNAdd(jjnextStates[start]); + } while (start++ != end); +} + +} Index: src/java/org/apache/lucene/queryParser/lucene2/parser/Readme.txt =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/Readme.txt (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/Readme.txt (revision 0) @@ -0,0 +1,50 @@ + +To build the QueryParser, run JavaCC on QueryParser.jj. That will generate: +- QueryParser.java +- QueryParserConstants.java +- QueryParserTokenManager.java +- TokenMgrError.java + +It would also generate +- JavaCharStream.java +- ParseException.java +- Token.java +- JavaCharStream.java + +If you change anything in QueryParser.jj, run JavaCC on it, you need check in +at least QueryParser.java. If you modified token definitions, you also need to +check in QueryParserTokenmanager.java. If you add new rules, you probably need +to check in QueryParserConstants, too. The other files usually don't change. + +Also, to avoid lots of warnings in the generated code: +- add @SupressWarnings("all") to QueryParserTokenManager.java, tokenMgrError.java, + JavaCharStream.java, Token.java and JavaCharStream.java + immediately preceding the class declaration. +- remove all imports from TokenMgrError.java +- edit the ParseException class to extend from QueryNodeParseException class + "public class ParseException extends QueryNodeParseException". + Recreate the all the constructors like this: + public ParseException(Token currentTokenVal, + int[][] expectedTokenSequencesVal, + String[] tokenImageVal + ) + { + super(new MessageImpl(QueryParserMessages.INVALID_SYNTAX, initialise(currentTokenVal, expectedTokenSequencesVal, tokenImageVal))); + this.currentToken = currentTokenVal; + this.expectedTokenSequences = expectedTokenSequencesVal; + this.tokenImage = tokenImageVal; + } + + public ParseException(Message message) { + super(message); + } + + public ParseException() { + super(new MessageImpl(QueryParserMessages.INVALID_SYNTAX, "Error")); + } + +This needs to be done after each time these files are generated by javacc. If you don't +change the grammar, don't check out QueryParserTokenManager.java and it should +be fine. Also, TokenMgrError.java will only be generated if it did not exist. +So, there is hope that for most changes to QueryParser.jj, this is not needed. + Index: src/java/org/apache/lucene/queryParser/lucene2/parser/Token.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/Token.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/Token.java (revision 0) @@ -0,0 +1,148 @@ +/* Generated By:JavaCC: Do not edit this line. Token.java Version 4.1 */ +/* JavaCCOptions:TOKEN_EXTENDS=,KEEP_LINE_COL=null,SUPPORT_CLASS_VISIBILITY_PUBLIC=true */ +package org.apache.lucene.queryParser.lucene2.parser; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * Describes the input token stream. + */ + +public class Token implements java.io.Serializable { + + /** + * The version identifier for this Serializable class. + * Increment only if the serialized form of the + * class changes. + */ + private static final long serialVersionUID = 1L; + + /** + * An integer that describes the kind of this token. This numbering + * system is determined by JavaCCParser, and a table of these numbers is + * stored in the file ...Constants.java. + */ + public int kind; + + /** The line number of the first character of this Token. */ + public int beginLine; + /** The column number of the first character of this Token. */ + public int beginColumn; + /** The line number of the last character of this Token. */ + public int endLine; + /** The column number of the last character of this Token. */ + public int endColumn; + + /** + * The string image of the token. + */ + public String image; + + /** + * A reference to the next regular (non-special) token from the input + * stream. If this is the last token from the input stream, or if the + * token manager has not read tokens beyond this one, this field is + * set to null. This is true only if this token is also a regular + * token. Otherwise, see below for a description of the contents of + * this field. + */ + public Token next; + + /** + * This field is used to access special tokens that occur prior to this + * token, but after the immediately preceding regular (non-special) token. + * If there are no such special tokens, this field is set to null. + * When there are more than one such special token, this field refers + * to the last of these special tokens, which in turn refers to the next + * previous special token through its specialToken field, and so on + * until the first special token (whose specialToken field is null). + * The next fields of special tokens refer to other special tokens that + * immediately follow it (without an intervening regular token). If there + * is no such token, this field is null. + */ + public Token specialToken; + + /** + * An optional attribute value of the Token. + * Tokens which are not used as syntactic sugar will often contain + * meaningful values that will be used later on by the compiler or + * interpreter. This attribute value is often different from the image. + * Any subclass of Token that actually wants to return a non-null value can + * override this method as appropriate. + */ + public Object getValue() { + return null; + } + + /** + * No-argument constructor + */ + public Token() {} + + /** + * Constructs a new token for the specified Image. + */ + public Token(int kind) + { + this(kind, null); + } + + /** + * Constructs a new token for the specified Image and Kind. + */ + public Token(int kind, String image) + { + this.kind = kind; + this.image = image; + } + + /** + * Returns the image. + */ + public String toString() + { + return image; + } + + /** + * Returns a new Token object, by default. However, if you want, you + * can create and return subclass objects based on the value of ofKind. + * Simply add the cases to the switch for all those special cases. + * For example, if you have a subclass of Token called IDToken that + * you want to create if ofKind is ID, simply add something like : + * + * case MyParserConstants.ID : return new IDToken(ofKind, image); + * + * to the following switch statement. Then you can cast matchedToken + * variable to the appropriate type and use sit in your lexical actions. + */ + public static Token newToken(int ofKind, String image) + { + switch(ofKind) + { + default : return new Token(ofKind, image); + } + } + + public static Token newToken(int ofKind) + { + return newToken(ofKind, null); + } + +} +/* JavaCC - OriginalChecksum=c7458f48213af7d4c6a887e945d19ece (do not edit this line) */ Index: src/java/org/apache/lucene/queryParser/lucene2/parser/TokenMgrError.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/TokenMgrError.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/TokenMgrError.java (revision 0) @@ -0,0 +1,164 @@ +/* Generated By:JavaCC: Do not edit this line. TokenMgrError.java Version 4.1 */ +/* JavaCCOptions: */ +package org.apache.lucene.queryParser.lucene2.parser; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** Token Manager Error. */ +public class TokenMgrError extends Error +{ + + /** + * The version identifier for this Serializable class. + * Increment only if the serialized form of the + * class changes. + */ + private static final long serialVersionUID = 1L; + + /* + * Ordinals for various reasons why an Error of this type can be thrown. + */ + + /** + * Lexical error occurred. + */ + static final int LEXICAL_ERROR = 0; + + /** + * An attempt was made to create a second instance of a static token manager. + */ + static final int STATIC_LEXER_ERROR = 1; + + /** + * Tried to change to an invalid lexical state. + */ + static final int INVALID_LEXICAL_STATE = 2; + + /** + * Detected (and bailed out of) an infinite loop in the token manager. + */ + static final int LOOP_DETECTED = 3; + + /** + * Indicates the reason why the exception is thrown. It will have + * one of the above 4 values. + */ + int errorCode; + + /** + * Replaces unprintable characters by their escaped (or unicode escaped) + * equivalents in the given string + */ + protected static final String addEscapes(String str) { + StringBuffer retval = new StringBuffer(); + char ch; + for (int i = 0; i < str.length(); i++) { + switch (str.charAt(i)) + { + case 0 : + continue; + case '\b': + retval.append("\\b"); + continue; + case '\t': + retval.append("\\t"); + continue; + case '\n': + retval.append("\\n"); + continue; + case '\f': + retval.append("\\f"); + continue; + case '\r': + retval.append("\\r"); + continue; + case '\"': + retval.append("\\\""); + continue; + case '\'': + retval.append("\\\'"); + continue; + case '\\': + retval.append("\\\\"); + continue; + default: + if ((ch = str.charAt(i)) < 0x20 || ch > 0x7e) { + String s = "0000" + Integer.toString(ch, 16); + retval.append("\\u" + s.substring(s.length() - 4, s.length())); + } else { + retval.append(ch); + } + continue; + } + } + return retval.toString(); + } + + /** + * Returns a detailed message for the Error when it is thrown by the + * token manager to indicate a lexical error. + * Parameters : + * EOFSeen : indicates if EOF caused the lexical error + * curLexState : lexical state in which this error occurred + * errorLine : line number when the error occurred + * errorColumn : column number when the error occurred + * errorAfter : prefix that was seen before this error occurred + * curchar : the offending character + * Note: You can customize the lexical error message by modifying this method. + */ + protected static String LexicalError(boolean EOFSeen, int lexState, int errorLine, int errorColumn, String errorAfter, char curChar) { + return("Lexical error at line " + + errorLine + ", column " + + errorColumn + ". Encountered: " + + (EOFSeen ? " " : ("\"" + addEscapes(String.valueOf(curChar)) + "\"") + " (" + (int)curChar + "), ") + + "after : \"" + addEscapes(errorAfter) + "\""); + } + + /** + * You can also modify the body of this method to customize your error messages. + * For example, cases like LOOP_DETECTED and INVALID_LEXICAL_STATE are not + * of end-users concern, so you can return something like : + * + * "Internal Error : Please file a bug report .... " + * + * from this method for such cases in the release version of your parser. + */ + public String getMessage() { + return super.getMessage(); + } + + /* + * Constructors of various flavors follow. + */ + + /** No arg constructor. */ + public TokenMgrError() { + } + + /** Constructor with message and reason. */ + public TokenMgrError(String message, int reason) { + super(message); + errorCode = reason; + } + + /** Full Constructor. */ + public TokenMgrError(boolean EOFSeen, int lexState, int errorLine, int errorColumn, String errorAfter, char curChar, int reason) { + this(LexicalError(EOFSeen, lexState, errorLine, errorColumn, errorAfter, curChar), reason); + } +} +/* JavaCC - OriginalChecksum=300228b3ff2a8227a4e823b29d23ad93 (do not edit this line) */ Index: src/java/org/apache/lucene/queryParser/lucene2/parser/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/parser/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/parser/package.html (revision 0) @@ -0,0 +1,33 @@ + + + + + + + + +

Lucene Query Parser

+

+The package org.apache.lucene.queryParser.lucene2.parser contains the query parser. +

+

+This new query parser only performs the syntax validation and create an QueryNode tree +from a string of text. +

+ + Index: src/java/org/apache/lucene/queryParser/lucene2/processors/AllowLeadingWildcardProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/AllowLeadingWildcardProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/AllowLeadingWildcardProcessor.java (revision 0) @@ -0,0 +1,96 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.config.AllowLeadingWildcardAttribute; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.WildcardQueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + + +/** + * This processor verifies if the attribute {@link AllowLeadingWildcardAttribute} is defined + * in the {@link QueryConfigHandler}. If it is and leading wildcard is not allowed, it looks + * for every {@link WildcardQueryNode} contained in the query node tree and throws an exception + * if any of them has a leading wildcard ('*' or '?'). + *
+ * @see QueryParser#setAllowLeadingWildcard(boolean) + * @see AllowLeadingWildcardAttribute + */ +public class AllowLeadingWildcardProcessor extends QueryNodeProcessorImpl { + + public AllowLeadingWildcardProcessor() { + // empty constructor + } + + public QueryNode process(QueryNode queryTree) throws QueryNodeException { + + if (getQueryConfigHandler().hasAttribute(AllowLeadingWildcardAttribute.class)) { + + if (!((AllowLeadingWildcardAttribute) getQueryConfigHandler().getAttribute(AllowLeadingWildcardAttribute.class)).isAllowLeadingWildcard()) { + return super.process(queryTree); + } + + } + + return queryTree; + + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof WildcardQueryNode) { + WildcardQueryNode wildcardNode = (WildcardQueryNode) node; + + switch (wildcardNode.getText().charAt(0)) { + + case '*' : + case '?' : + // TODO: create a message for this exception: "'*' not allowed as first character in PrefixQuery" + throw new QueryNodeException(new MessageImpl(QueryParserMessages.EMPTY_MESSAGE)); + + } + + } + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/AnalyzerQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/AnalyzerQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/AnalyzerQueryNodeProcessor.java (revision 0) @@ -0,0 +1,336 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.IOException; +import java.io.StringReader; +import java.util.ArrayList; +import java.util.LinkedList; +import java.util.List; + +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.analysis.CachingTokenFilter; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute; +import org.apache.lucene.analysis.tokenattributes.TermAttribute; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.config.AnalyzerAttribute; +import org.apache.lucene.queryParser.lucene2.config.PositionIncrementsAttribute; +import org.apache.lucene.queryParser.lucene2.nodes.LuceneBooleanQueryNode; +import org.apache.lucene.queryParser.lucene2.nodes.MultiPhraseQueryNode; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.FuzzyQueryNode; +import org.apache.lucene.queryParser.nodes.GroupQueryNode; +import org.apache.lucene.queryParser.nodes.NoTokenFoundQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.TokenizedPhraseQueryNode; +import org.apache.lucene.queryParser.nodes.WildcardQueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + +/** + * This processor verifies if the attribute {@link AnalyzerQueryNodeProcessor} is defined + * in the {@link QueryConfigHandler}. If it is and the analyzer is not null, it looks + * for every {@link FieldQueryNode} that is not {@link WildcardQueryNode}, + * {@link FuzzyQueryNode} or {@link ParametricQueryNode} contained in the query node tree, then + * it applies the analyzer to that {@link FieldQueryNode} object. + *

+ * If the analyzer return only one term, the returned term is set to the {@link FieldQueryNode} + * and it's returned. + *

+ * If the analyzer return more than one term, a {@link TokenizedPhraseQueryNode} + * or {@link MultiPhraseQueryNode} is created, whether there is one or more terms at the same + * position, and it's returned. + *

+ * If no term is returned by the analyzer a {@link NoTokenFoundQueryNode} object is returned. + *
+ * @see Analyzer + * @see TokenStream + */ +public class AnalyzerQueryNodeProcessor extends QueryNodeProcessorImpl { + + private Analyzer analyzer; + + private boolean positionIncrementsEnabled; + + public AnalyzerQueryNodeProcessor() { + // empty constructor + } + + public QueryNode process(QueryNode queryTree) throws QueryNodeException { + + if (getQueryConfigHandler().hasAttribute(AnalyzerAttribute.class)) { + + this.analyzer = ((AnalyzerAttribute) getQueryConfigHandler().getAttribute( + AnalyzerAttribute.class)).getAnalyzer(); + + this.positionIncrementsEnabled = false; + + if (getQueryConfigHandler().hasAttribute( + PositionIncrementsAttribute.class)) { + + if (((PositionIncrementsAttribute) getQueryConfigHandler().getAttribute( + PositionIncrementsAttribute.class)).isPositionIncrementsEnabled()) { + + this.positionIncrementsEnabled = true; + + } + + } + + if (this.analyzer != null) { + return super.process(queryTree); + } + + } + + return queryTree; + + } + + @Override + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + // TODO: it should check if it's an instance of "TextableNode" interface instead of FieldQueryNode + if (node instanceof FieldQueryNode + && !(node instanceof WildcardQueryNode) + && !(node instanceof FuzzyQueryNode) + && !(node instanceof ParametricQueryNode)) { + + FieldQueryNode fieldNode = ((FieldQueryNode) node); + String text = fieldNode.getTextAsString(); + String field = fieldNode.getFieldAsString(); + + TokenStream source = this.analyzer.tokenStream(field, + new StringReader(text)); + CachingTokenFilter buffer = new CachingTokenFilter(source); + + PositionIncrementAttribute posIncrAtt = null; + int numTokens = 0; + int positionCount = 0; + boolean severalTokensAtSamePosition = false; + + if (buffer.hasAttribute(PositionIncrementAttribute.class)) { + posIncrAtt = (PositionIncrementAttribute) buffer.getAttribute(PositionIncrementAttribute.class); + } + + try { + + while (buffer.incrementToken()) { + numTokens++; + int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() + : 1; + if (positionIncrement != 0) { + positionCount += positionIncrement; + + } else { + severalTokensAtSamePosition = true; + } + + } + + } catch (IOException e) { + // ignore + } + + try { + // rewind the buffer stream + buffer.reset(); + + // close original stream - all tokens buffered + source.close(); + } catch (IOException e) { + // ignore + } + + if (!buffer.hasAttribute(TermAttribute.class)) { + return new NoTokenFoundQueryNode(); + } + + TermAttribute termAtt = (TermAttribute) buffer.getAttribute(TermAttribute.class); + + if (numTokens == 0) { + return new NoTokenFoundQueryNode(); + + } else if (numTokens == 1) { + String term = null; + try { + boolean hasNext; + hasNext = buffer.incrementToken(); + assert hasNext == true; + term = termAtt.term(); + + } catch (IOException e) { + // safe to ignore, because we know the number of tokens + } + + fieldNode.setText(term); + + return fieldNode; + + } else if (severalTokensAtSamePosition) { + if (positionCount == 1) { + // no phrase query: + LinkedList children = new LinkedList(); + + for (int i = 0; i < numTokens; i++) { + String term = null; + try { + boolean hasNext = buffer.incrementToken(); + assert hasNext == true; + term = termAtt.term(); + + } catch (IOException e) { + // safe to ignore, because we know the number of tokens + } + + children.add(new FieldQueryNode(field, term, -1, -1)); + + } + + return new GroupQueryNode(new LuceneBooleanQueryNode( + children, true)); + + } else { + // phrase query: + MultiPhraseQueryNode mpq = new MultiPhraseQueryNode(); + + List multiTerms = new ArrayList(); + int position = -1; + int i = 0; + for (; i < numTokens; i++) { + String term = null; + int positionIncrement = 1; + try { + boolean hasNext = buffer.incrementToken(); + assert hasNext == true; + term = termAtt.term(); + if (posIncrAtt != null) { + positionIncrement = posIncrAtt.getPositionIncrement(); + } + + } catch (IOException e) { + // safe to ignore, because we know the number of tokens + } + + if (positionIncrement > 0 && multiTerms.size() > 0) { + + for (FieldQueryNode termNode : multiTerms) { + + if (this.positionIncrementsEnabled) { + termNode.setPositionIncrement(position); + + } else { + termNode.setPositionIncrement(i); + } + + mpq.add(termNode); + + } + + multiTerms.clear(); + + } + + position += positionIncrement; + multiTerms.add(new FieldQueryNode(field, term, -1, -1)); + + } + + for (FieldQueryNode termNode : multiTerms) { + + if (this.positionIncrementsEnabled) { + termNode.setPositionIncrement(position); + + } else { + termNode.setPositionIncrement(i); + } + + mpq.add(termNode); + + } + + return mpq; + + } + + } else { + + TokenizedPhraseQueryNode pq = new TokenizedPhraseQueryNode(); + + int position = -1; + + for (int i = 0; i < numTokens; i++) { + String term = null; + int positionIncrement = 1; + + try { + boolean hasNext = buffer.incrementToken(); + assert hasNext == true; + term = termAtt.term(); + + if (posIncrAtt != null) { + positionIncrement = posIncrAtt.getPositionIncrement(); + } + + } catch (IOException e) { + // safe to ignore, because we know the number of tokens + } + + FieldQueryNode newFieldNode = new FieldQueryNode(field, + term, -1, -1); + + if (this.positionIncrementsEnabled) { + position += positionIncrement; + newFieldNode.setPositionIncrement(position); + + } else { + newFieldNode.setPositionIncrement(i); + } + + pq.add(newFieldNode); + + } + + return pq; + + } + + } + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/BooleanSingleChildOptimizationQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/BooleanSingleChildOptimizationQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/BooleanSingleChildOptimizationQueryNodeProcessor.java (revision 0) @@ -0,0 +1,90 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.lucene2.nodes.BooleanModifierNode; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode.Modifier; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + + +/** + * This processor removes every {@link BooleanQueryNode} that contains only one + * child and returns this child. If this child is {@link ModifierQueryNode} + * that was defined by the user. A modifier is not defined by the user when it's a {@link BooleanModifierNode} + *
+ * @see ModifierQueryNode + */ +public class BooleanSingleChildOptimizationQueryNodeProcessor extends QueryNodeProcessorImpl { + + public BooleanSingleChildOptimizationQueryNodeProcessor() { + // empty constructor + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof BooleanQueryNode) { + List children = node.getChildren(); + + if (children != null && children.size() == 1) { + QueryNode child = children.get(0); + + if (child instanceof ModifierQueryNode) { + ModifierQueryNode modNode = (ModifierQueryNode) child; + + if (modNode instanceof BooleanModifierNode || + modNode.getModifier() == Modifier.MOD_NONE) { + + return child; + + } + + + } else { + return child; + } + + } + + } + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/DefaultPhraseSlopQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/DefaultPhraseSlopQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/DefaultPhraseSlopQueryNodeProcessor.java (revision 0) @@ -0,0 +1,117 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.config.DefaultPhraseSlopAttribute; +import org.apache.lucene.queryParser.lucene2.nodes.MultiPhraseQueryNode; +import org.apache.lucene.queryParser.nodes.SlopQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.TokenizedPhraseQueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + + +/** + * This processor verifies if the attribute {@link DefaultPhraseSlopAttribute} is defined + * in the {@link QueryConfigHandler}. If it is, it looks + * for every {@link TokenizedPhraseQueryNode} and {@link MultiPhraseQueryNode} that does + * not have any {@link SlopQueryNode} applied to it and creates an {@link SlopQueryNode} + * and apply to it. The new {@link SlopQueryNode} has the same slop value defined in the attribute. + *
+ * @see SlopQueryNode + * @see DefaultPhraseSlopAttribute + * @see QueryParser#setPhraseSlop(int) + */ +public class DefaultPhraseSlopQueryNodeProcessor extends QueryNodeProcessorImpl { + + private boolean processChildren = true; + + private int defaultPhraseSlop; + + public DefaultPhraseSlopQueryNodeProcessor() { + // empty constructor + } + + public QueryNode process(QueryNode queryTree) throws QueryNodeException { + QueryConfigHandler queryConfig = getQueryConfigHandler(); + + if (queryConfig != null) { + + if (queryConfig.hasAttribute(DefaultPhraseSlopAttribute.class)) { + this.defaultPhraseSlop = ((DefaultPhraseSlopAttribute) queryConfig.getAttribute(DefaultPhraseSlopAttribute.class)).getDefaultPhraseSlop(); + + return super.process(queryTree); + + } + + } + + return queryTree; + + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof TokenizedPhraseQueryNode || + node instanceof MultiPhraseQueryNode) { + + return new SlopQueryNode(node, this.defaultPhraseSlop); + + } + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof SlopQueryNode) { + this.processChildren = false; + + } + + return node; + + } + + protected void processChildren(QueryNode queryTree) + throws QueryNodeException { + + if (this.processChildren) { + super.processChildren(queryTree); + + } else { + this.processChildren = true; + } + + } + + @Override + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/GroupQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/GroupQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/GroupQueryNodeProcessor.java (revision 0) @@ -0,0 +1,223 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.ArrayList; +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.config.DefaultOperatorAttribute; +import org.apache.lucene.queryParser.lucene2.nodes.BooleanModifierNode; +import org.apache.lucene.queryParser.nodes.AndQueryNode; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.GroupQueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.OrQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode.Modifier; +import org.apache.lucene.queryParser.processors.QueryNodeProcessor; +import org.apache.lucene.queryParser.QueryParser; +import org.apache.lucene.queryParser.QueryParser.Operator; + + +/** + * The {@link org.apache.lucene.queryParser.lucene2.parser.QueryParser} generates + * query node trees that consider the boolean operator precedence, but Lucene current + * syntax does not support boolean precedence, so this processor remove all the precedence + * and apply the equivalent modifier according to the boolean operation defined on an specific + * query node. + *

+ * If there is a {@link GroupQueryNode} in the query node tree, the query node tree is not merged + * with the one above it. + * + * Example: + * TODO: describe a good example to show how this processor works + * + * @see QueryParser + */ +public class GroupQueryNodeProcessor implements QueryNodeProcessor { + + private ArrayList queryNodeList; + + private Operator defaultOperator = null; + + private boolean latestNodeVerified; + + private QueryConfigHandler queryConfig; + + public GroupQueryNodeProcessor() { + // empty constructor + } + + public QueryNode process(QueryNode queryTree) throws QueryNodeException { + + if (this.defaultOperator == null) { + + if (!getQueryConfigHandler().hasAttribute(DefaultOperatorAttribute.class)) { + throw new IllegalArgumentException("DefaultOperatorAttribute should be set on the QueryConfigHandler"); + } + + this.defaultOperator = ((DefaultOperatorAttribute) getQueryConfigHandler().getAttribute(DefaultOperatorAttribute.class)).getDefaultOperator(); + + } + + if (queryTree instanceof GroupQueryNode) { + queryTree = ((GroupQueryNode) queryTree).getChild(); + } + + this.queryNodeList = new ArrayList(); + this.latestNodeVerified = false; + readTree(queryTree); + + List actualQueryNodeList = this.queryNodeList; + + for (int i = 0 ; i < actualQueryNodeList.size() ; i++) { + QueryNode node = actualQueryNodeList.get(i); + + if (node instanceof GroupQueryNode) { + actualQueryNodeList.set(i, process(node)); + } + + } + + this.defaultOperator = null; + + if (queryTree instanceof BooleanQueryNode) { + queryTree.set(actualQueryNodeList); + + return queryTree; + + } else { + return new BooleanQueryNode(actualQueryNodeList); + } + + } + + /** + * @param node + * @return + */ + private QueryNode applyModifier(QueryNode node, QueryNode parent) { + + if (this.defaultOperator == QueryParser.AND_OPERATOR) { + + if (parent instanceof OrQueryNode) { + + if (node instanceof ModifierQueryNode) { + + ModifierQueryNode modNode = (ModifierQueryNode) node; + + if (modNode.getModifier() == Modifier.MOD_REQ) { + return modNode.getChild(); + } + + } + + } else { + + if (node instanceof ModifierQueryNode) { + + ModifierQueryNode modNode = (ModifierQueryNode) node; + + if (modNode.getModifier() == Modifier.MOD_NONE) { + return new BooleanModifierNode(modNode.getChild(), Modifier.MOD_REQ); + } + + } else { + return new BooleanModifierNode(node, Modifier.MOD_REQ); + } + + } + + } else { + + if (node.getParent() instanceof AndQueryNode) { + + if (node instanceof ModifierQueryNode) { + + ModifierQueryNode modNode = (ModifierQueryNode) node; + + if (modNode.getModifier() == Modifier.MOD_NONE) { + return new BooleanModifierNode(modNode.getChild(), Modifier.MOD_REQ); + } + + } else { + return new BooleanModifierNode(node, Modifier.MOD_REQ); + } + + } + + } + + return node; + + } + + private void readTree(QueryNode node) { + + if (node instanceof BooleanQueryNode) { + List children = node.getChildren(); + + if (children != null && children.size() > 0) { + + for (int i = 0 ; i < children.size() - 1 ; i++) { + readTree(children.get(i)); + } + + processNode(node); + readTree(children.get(children.size() - 1)); + + } else { + processNode(node); + } + + } else { + processNode(node); + } + + } + + private void processNode(QueryNode node) { + + if (node instanceof AndQueryNode || + node instanceof OrQueryNode) { + + if (!this.latestNodeVerified && !this.queryNodeList.isEmpty()) { + this.queryNodeList.add(applyModifier(this.queryNodeList.remove(this.queryNodeList.size() - 1), node)); + this.latestNodeVerified = true; + + } + + } else if (!(node instanceof BooleanQueryNode)) { + this.queryNodeList.add(applyModifier(node, node.getParent())); + this.latestNodeVerified = false; + + } + + } + + public QueryConfigHandler getQueryConfigHandler() { + return this.queryConfig; + } + + public void setQueryConfigHandler(QueryConfigHandler queryConfigHandler) { + this.queryConfig = queryConfigHandler; + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/LowercaseExpandedTermsQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/LowercaseExpandedTermsQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/LowercaseExpandedTermsQueryNodeProcessor.java (revision 0) @@ -0,0 +1,94 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.QueryParser; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.config.AllowLeadingWildcardAttribute; +import org.apache.lucene.queryParser.lucene2.config.LowercaseExpandedTermsAttribute; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.FuzzyQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.WildcardQueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + + +/** + * This processor verifies if the attribute {@link LowercaseExpandedTermsAttribute} is defined + * in the {@link QueryConfigHandler}. If it is and the expanded terms should be lowercased, it looks + * for every {@link WildcardQueryNode}, {@link FuzzyQueryNode} and {@link ParametricQueryNode} and + * lowercase its term. + *
+ * @see QueryParser#setLowercaseExpandedTerms(boolean) + * @see LowercaseExpandedTermsAttribute + */ +public class LowercaseExpandedTermsQueryNodeProcessor extends QueryNodeProcessorImpl { + + public LowercaseExpandedTermsQueryNodeProcessor() { + // empty constructor + } + + public QueryNode process(QueryNode queryTree) throws QueryNodeException { + + if (getQueryConfigHandler().hasAttribute(LowercaseExpandedTermsAttribute.class)) { + + if (((LowercaseExpandedTermsAttribute) getQueryConfigHandler().getAttribute(LowercaseExpandedTermsAttribute.class)).isLowercaseExpandedTerms()) { + return super.process(queryTree); + } + + } + + return queryTree; + + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof WildcardQueryNode || + node instanceof FuzzyQueryNode || + node instanceof ParametricQueryNode) { + + FieldQueryNode fieldNode = (FieldQueryNode) node; + fieldNode.setText(fieldNode.getText().toString().toLowerCase()); + + } + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/LuceneQueryNodeProcessorPipeline.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/LuceneQueryNodeProcessorPipeline.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/LuceneQueryNodeProcessorPipeline.java (revision 0) @@ -0,0 +1,65 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.builders.LuceneQueryTreeBuilder; +import org.apache.lucene.queryParser.lucene2.config.LuceneQueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.parser.QueryParser; +import org.apache.lucene.queryParser.processors.NoChildOptimizationQueryNodeProcessor; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorPipeline; +import org.apache.lucene.queryParser.processors.RemoveDeletedQueryNodesProcessor; +import org.apache.lucene.search.Query; + +/** + * This pipeline has all the processors needed to process a query node tree + * generated by {@link QueryParser} already assembled. + *

+ * The order they are assembled affects the results. + *

+ * This processor pipeline was designed to work with {@link LuceneQueryConfigHandler}. + *

+ * The result query node tree can be used to build a {@link Query} object + * using {@link LuceneQueryTreeBuilder}. + *
+ * @see LuceneQueryTreeBuilder + * @see LuceneQueryConfigHandler + * @see QueryParser + */ +public class LuceneQueryNodeProcessorPipeline extends QueryNodeProcessorPipeline { + + public LuceneQueryNodeProcessorPipeline(QueryConfigHandler queryConfig) { + super(queryConfig); + + addProcessor(new MatchAllDocsQueryNodeProcessor()); + addProcessor(new LowercaseExpandedTermsQueryNodeProcessor()); + addProcessor(new ParametricRangeQueryNodeProcessor()); + addProcessor(new AllowLeadingWildcardProcessor()); + addProcessor(new PrefixWildcardQueryNodeProcessor()); + addProcessor(new AnalyzerQueryNodeProcessor()); + addProcessor(new PhraseSlopQueryNodeProcessor()); + addProcessor(new GroupQueryNodeProcessor()); + addProcessor(new NoChildOptimizationQueryNodeProcessor()); + addProcessor(new RemoveDeletedQueryNodesProcessor()); + addProcessor(new RemoveEmptyNonLeafQueryNodeProcessor()); + addProcessor(new BooleanSingleChildOptimizationQueryNodeProcessor()); + addProcessor(new DefaultPhraseSlopQueryNodeProcessor()); + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/MatchAllDocsQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/MatchAllDocsQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/MatchAllDocsQueryNodeProcessor.java (revision 0) @@ -0,0 +1,76 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.MatchAllDocsQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.WildcardQueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; +import org.apache.lucene.search.MatchAllDocsQuery; + + +/** + * This processor converts every {@link WildcardQueryNode} that is "*:*" to + * {@link MatchAllDocsQueryNode}. + * + * @see MatchAllDocsQueryNode + * @see MatchAllDocsQuery + */ +public class MatchAllDocsQueryNodeProcessor extends QueryNodeProcessorImpl { + + public MatchAllDocsQueryNodeProcessor() { + // empty constructor + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof WildcardQueryNode) { + WildcardQueryNode wildcardNode = (WildcardQueryNode) node; + + if (wildcardNode.getField().toString().equals("*") && + wildcardNode.getText().toString().equals("*")) { + + return new MatchAllDocsQueryNode(); + + } + + } + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/MultiFieldQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/MultiFieldQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/MultiFieldQueryNodeProcessor.java (revision 0) @@ -0,0 +1,168 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.LinkedList; +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.FieldConfig; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.MultiFieldQueryParserWrapper; +import org.apache.lucene.queryParser.lucene2.config.BoostAttribute; +import org.apache.lucene.queryParser.lucene2.config.MultiFieldAttribute; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.BoostQueryNode; +import org.apache.lucene.queryParser.nodes.FieldableNode; +import org.apache.lucene.queryParser.nodes.GroupQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + + +/** + * This processor is used to expand terms so the query looks for + * the same term in different fields. It also boosts a query based + * on its field. + *

+ * This processor looks for every {@link FieldableNode} contained in the query node tree. + * If a {@link FieldableNode} is found, it checks if there is a {@link MultiFieldAttribute} + * defined in the {@link QueryConfigHandler}. If there is, the {@link FieldableNode} is + * cloned N times and the clones are added to a {@link BooleanQueryNode} together with the original node. + * N is defined by the number of fields that it will be expanded to. The {@link BooleanQueryNode} is returned. + *

+ * This processor also looks a {@link BoostAttribute} for each field in the {@link QueryConfigHandler}. + * If there is a {@link BoostAttribute} in a specific field, this boost is applied to the {@link FieldableNode}. + *
+ * @see BoostAttribute + * @see MultiFieldAttribute + * @see MultiFieldQueryParser + * @see MultiFieldQueryParserWrapper + */ +public class MultiFieldQueryNodeProcessor extends QueryNodeProcessorImpl { + + private boolean processChildren = true; + + public MultiFieldQueryNodeProcessor() { + // empty constructor + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + private QueryNode addBoost(FieldableNode node) throws QueryNodeException { + FieldConfig fieldConfig = getQueryConfigHandler().getFieldConfig( + node.getField()); + + if (fieldConfig != null) { + + if (fieldConfig.hasAttribute(BoostAttribute.class)) { + float boost = ((BoostAttribute) fieldConfig.getAttribute(BoostAttribute.class)).getBoost(); + + return new BoostQueryNode(node, boost); + + } + + } + + return node; + + } + + protected void processChildren(QueryNode queryTree) + throws QueryNodeException { + + if (this.processChildren) { + super.processChildren(queryTree); + + } else { + this.processChildren = true; + } + + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof FieldableNode) { + this.processChildren = false; + FieldableNode fieldNode = (FieldableNode) node; + + if (fieldNode.getField() == null) { + + if (!getQueryConfigHandler().hasAttribute( + MultiFieldAttribute.class)) { + throw new IllegalArgumentException( + "MultiFieldAttribute should be set on the QueryConfigHandler"); + } + + CharSequence[] fields = ((MultiFieldAttribute) getQueryConfigHandler().getAttribute( + MultiFieldAttribute.class)).getFields(); + + if (fields != null && fields.length > 0) { + fieldNode.setField(fields[0]); + QueryNode boostedNode = addBoost(fieldNode); + + if (fields.length == 1) { + return boostedNode; + + } else { + LinkedList children = new LinkedList(); + children.add(boostedNode); + + for (int i = 1; i < fields.length; i++) { + try { + fieldNode = (FieldableNode) fieldNode.cloneTree(); + fieldNode.setField(fields[i]); + boostedNode = addBoost(fieldNode); + + children.add(boostedNode); + + } catch (CloneNotSupportedException e) { + // should never happen + } + + } + + return new GroupQueryNode( + new BooleanQueryNode(children)); + + } + + } + + } + + } + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/lucene2/processors/ParametricRangeQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/ParametricRangeQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/ParametricRangeQueryNodeProcessor.java (revision 0) @@ -0,0 +1,178 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.text.Collator; +import java.text.DateFormat; +import java.util.Calendar; +import java.util.Date; +import java.util.List; +import java.util.Locale; + +import org.apache.lucene.document.DateField; +import org.apache.lucene.document.DateTools; +import org.apache.lucene.document.DateTools.Resolution; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.FieldConfig; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.config.ConstantScoreRewriteAttribute; +import org.apache.lucene.queryParser.lucene2.config.DateResolutionAttribute; +import org.apache.lucene.queryParser.lucene2.config.LocaleAttribute; +import org.apache.lucene.queryParser.lucene2.config.RangeCollatorAttribute; +import org.apache.lucene.queryParser.lucene2.nodes.RangeQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricQueryNode; +import org.apache.lucene.queryParser.nodes.ParametricRangeQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.ParametricQueryNode.CompareOperator; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + + +/** + * This processor converts {@link ParametricRangeQueryNode} objects to + * {@link RangeQueryNode} objects. It reads the lower and upper bounds value + * from the {@link ParametricRangeQueryNode} object and try to parse their values + * using a {@link DateFormat}. If the values cannot be parsed to a date value, + * it will only create the {@link RangeQueryNode} using the non-parsed values. + *

+ * If a {@link LocaleAttribute} is defined in the {@link QueryConfigHandler} it will + * be used to parse the date, otherwise {@link Locale#getDefault()} will be used. + *

+ * If a {@link DateResolutionAttribute} is defined and the {@link Resolution} is not null + * it will also be used to parse the date value. + *

+ * This processor will also try to retrieve a {@link RangeCollatorAttribute} from the {@link QueryConfigHandler}. + * If a {@link RangeCollatorAttribute} is found and the {@link Collator} is not null, it's + * set on the {@link RangeQueryNode}. + *
+ * @see RangeCollatorAttribute + * @see DateResolutionAttribute + * @see LocaleAttribute + * @see RangeQueryNode + * @see ParametricRangeQueryNode + */ +public class ParametricRangeQueryNodeProcessor extends QueryNodeProcessorImpl { + + public ParametricRangeQueryNodeProcessor() { + // empty constructor + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof ParametricRangeQueryNode) { + ParametricRangeQueryNode parametricRangeNode = (ParametricRangeQueryNode) node; + ParametricQueryNode upper = parametricRangeNode.getUpperBound(); + ParametricQueryNode lower = parametricRangeNode.getLowerBound(); + Locale locale = Locale.getDefault(); + Collator collator = null; + DateTools.Resolution dateRes = null; + boolean inclusive = false; + + if (!getQueryConfigHandler().hasAttribute(ConstantScoreRewriteAttribute.class)) { + throw new IllegalArgumentException("ConstantScoreRewriteAttribute should be set on the QueryConfigHandler"); + } + + boolean constantScoreRewrite = ((ConstantScoreRewriteAttribute) getQueryConfigHandler().getAttribute(ConstantScoreRewriteAttribute.class)).isConstantScoreRewrite(); + + if (getQueryConfigHandler().hasAttribute(RangeCollatorAttribute.class)) { + collator = ((RangeCollatorAttribute) getQueryConfigHandler().getAttribute(RangeCollatorAttribute.class)).getRangeCollator(); + } + + if (getQueryConfigHandler().hasAttribute(LocaleAttribute.class)) { + locale = ((LocaleAttribute) getQueryConfigHandler().getAttribute(LocaleAttribute.class)).getLocale(); + } + + FieldConfig fieldConfig = getQueryConfigHandler().getFieldConfig(parametricRangeNode.getField()); + + if (fieldConfig != null) { + + if (fieldConfig.hasAttribute(DateResolutionAttribute.class)) { + dateRes = ((DateResolutionAttribute) fieldConfig.getAttribute(DateResolutionAttribute.class)).getDateResolution(); + } + + } + + if (upper.getOperator() == CompareOperator.LE) { + inclusive = true; + + } else if (lower.getOperator() == CompareOperator.GE) { + inclusive = true; + } + + String part1 = lower.getTextAsString(); + String part2 = upper.getTextAsString(); + + try { + DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT, Locale.getDefault()); + df.setLenient(true); + Date d1 = df.parse(part1); + Date d2 = df.parse(part2); + if (inclusive) { + // The user can only specify the date, not the time, so make sure + // the time is set to the latest possible time of that date to really + // include all documents: + Calendar cal = Calendar.getInstance(locale); + cal.setTime(d2); + cal.set(Calendar.HOUR_OF_DAY, 23); + cal.set(Calendar.MINUTE, 59); + cal.set(Calendar.SECOND, 59); + cal.set(Calendar.MILLISECOND, 999); + d2 = cal.getTime(); + } + + if (dateRes == null) { + // no default or field specific date resolution has been set, + // use deprecated DateField to maintain compatibilty with + // pre-1.9 Lucene versions. + part1 = DateField.dateToString(d1); + part2 = DateField.dateToString(d2); + } else { + part1 = DateTools.dateToString(d1, dateRes); + part2 = DateTools.dateToString(d2, dateRes); + } + } + catch (Exception e) { + // do nothing + } + + lower.setText(part1); + upper.setText(part2); + + return new RangeQueryNode(lower, upper, collator, constantScoreRewrite); + + } + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/PhraseSlopQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/PhraseSlopQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/PhraseSlopQueryNodeProcessor.java (revision 0) @@ -0,0 +1,74 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.lucene2.nodes.MultiPhraseQueryNode; +import org.apache.lucene.queryParser.nodes.SlopQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.TokenizedPhraseQueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + + +/** + * This processor removes invalid {@link SlopQueryNode} objects in the query node tree. + * A {@link SlopQueryNode} is invalid if its child is neither a {@link TokenizedPhraseQueryNode} + * nor a {@link MultiPhraseQueryNode}. + *
+ * @see SlopQueryNode + */ +public class PhraseSlopQueryNodeProcessor extends QueryNodeProcessorImpl { + + public PhraseSlopQueryNodeProcessor() { + // empty constructor + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof SlopQueryNode) { + SlopQueryNode phraseSlopNode = (SlopQueryNode) node; + + if (!(phraseSlopNode.getChild() instanceof TokenizedPhraseQueryNode) && + !(phraseSlopNode.getChild() instanceof MultiPhraseQueryNode)) { + return phraseSlopNode.getChild(); + } + + } + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/PrefixWildcardQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/PrefixWildcardQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/PrefixWildcardQueryNodeProcessor.java (revision 0) @@ -0,0 +1,74 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.lucene2.parser.QueryParser; +import org.apache.lucene.queryParser.nodes.PrefixWildcardQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; +import org.apache.lucene.search.PrefixQuery; + + +/** + * The {@link QueryParser} creates {@link PrefixWildcardQueryNode} nodes which + * have values containing the prefixed wildcard. However, Lucene {@link PrefixQuery} + * cannot contain the prefixed wildcard. So, this processor basically removed the + * prefixed wildcard from the {@link PrefixWildcardQueryNode} value. + *
+ * @see PrefixQuery + * @see PrefixWildcardQueryNode + */ +public class PrefixWildcardQueryNodeProcessor extends QueryNodeProcessorImpl { + + public PrefixWildcardQueryNodeProcessor() { + // empty constructor + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof PrefixWildcardQueryNode) { + PrefixWildcardQueryNode prefixWildcardNode = (PrefixWildcardQueryNode) node; + CharSequence text = prefixWildcardNode.getText(); + + prefixWildcardNode.setText(text.subSequence(0, text.length() - 1)); + + } + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/RemoveEmptyNonLeafQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/RemoveEmptyNonLeafQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/RemoveEmptyNonLeafQueryNodeProcessor.java (revision 0) @@ -0,0 +1,113 @@ +package org.apache.lucene.queryParser.lucene2.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.LinkedList; +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.GroupQueryNode; +import org.apache.lucene.queryParser.nodes.MatchNoDocsQueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + + +/** + * This processor removes every {@link QueryNode} that is not a leaf and has not children. + * If after processing the entire tree the root node is not a leaf and has no children, + * a {@link MatchNoDocsQueryNode} object is returned. + *

+ * This processor is used at the end of a pipeline to avoid invalid query node tree structures + * like a {@link GroupQueryNode} or {@link ModifierQueryNode} with no children. + *
+ * @see QueryNode + * @see MatchNoDocsQueryNode + */ +public class RemoveEmptyNonLeafQueryNodeProcessor extends QueryNodeProcessorImpl { + + private LinkedList childrenBuffer = new LinkedList(); + + public RemoveEmptyNonLeafQueryNodeProcessor() { + // empty constructor + } + + public QueryNode process(QueryNode queryTree) throws QueryNodeException { + queryTree = super.process(queryTree); + + if (!queryTree.isLeaf()) { + + List children = queryTree.getChildren(); + + if (children == null || children.size() == 0) { + return new MatchNoDocsQueryNode(); + } + + } + + return queryTree; + + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + try { + + for (QueryNode child : children) { + + if (!child.isLeaf()) { + + List grandChildren = child.getChildren(); + + if (grandChildren != null && grandChildren.size() > 0) { + this.childrenBuffer.add(child); + } + + } else { + this.childrenBuffer.add(child); + } + + } + + children.clear(); + children.addAll(this.childrenBuffer); + + } finally { + this.childrenBuffer.clear(); + } + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/lucene2/processors/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/lucene2/processors/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/lucene2/processors/package.html (revision 0) @@ -0,0 +1,33 @@ + + + + + + + + +

Lucene 2 Query Node Processors

+

+The package org.apache.lucene.queryParser.lucene2.processors contains every processor needed to assembly a pipeline +that modifies the query node tree according to the actual Lucene queries. +

+

+This processors are already assembled correctly in the LuceneQueryNodeProcessorPipeline. +

+ + Index: src/java/org/apache/lucene/queryParser/builders/QueryBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/builders/QueryBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/builders/QueryBuilder.java (revision 0) @@ -0,0 +1,41 @@ +package org.apache.lucene.queryParser.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.QueryNode; + +/** + * This interface is used by implementors classes that builds some kind of object from a query tree. + * + * @see QueryTreeBuilder + */ +public interface QueryBuilder { + + /** + * Builds some kind of object from a query tree. + * + * @param queryNode the query tree root node + * + * @return some object generated from the query tree + * + * @throws QueryNodeException + */ + Object build(QueryNode queryNode) throws QueryNodeException; + +} Index: src/java/org/apache/lucene/queryParser/builders/QueryTreeBuilder.java =================================================================== --- src/java/org/apache/lucene/queryParser/builders/QueryTreeBuilder.java (revision 0) +++ src/java/org/apache/lucene/queryParser/builders/QueryTreeBuilder.java (revision 0) @@ -0,0 +1,194 @@ +package org.apache.lucene.queryParser.builders; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.HashMap; +import java.util.List; + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.nodes.FieldableNode; +import org.apache.lucene.queryParser.nodes.QueryNode; + + +/** + * This class should be used when there is a builder for each type of node. + * + * The type of node may be defined in 2 different ways: + * - by the field name, when the node implements the {@link FieldableNode} interface + * - by its class, it keeps checking the class and all the interface and classes + * this class implements until it finds a builder for that class/interface + * + * This class always check if there is a builder for the field name before it checks for + * the node class. So, field name builders have precedence over class builders. + * + * When a builder is found for a node, it's called and the node is passed to the builder. + * If the returned built object is not null, it's tagged on the node using the tag {@link QueryTreeBuilder#QUERY_TREE_BUILDER_TAGID}. + * + * @see QueryBuilder + */ +public class QueryTreeBuilder implements QueryBuilder { + + /** + * This tag is used to tag the nodes in a query tree with the built objects produced from their own associated builder. + */ + public static final String QUERY_TREE_BUILDER_TAGID = QueryTreeBuilder.class.getName(); + + private HashMap, QueryBuilder> queryNodeBuilders; + + private HashMap fieldNameBuilders; + + /** + * {@link QueryTreeBuilder} constructor. + */ + public QueryTreeBuilder() { + // empty constructor + } + + /** + * Associates a field name with a builder. + * + * @param fieldName the field name + * @param builder the builder to be associated + */ + public void setBuilder(CharSequence fieldName, QueryBuilder builder) { + + if (this.fieldNameBuilders == null) { + this.fieldNameBuilders = new HashMap(); + } + + this.fieldNameBuilders.put(fieldName, builder); + + } + + /** + * Associates a class with a builder + * + * @param queryNodeClass the class + * @param builder the builder to be associated + */ + public void setBuilder(Class queryNodeClass, QueryBuilder builder) { + + if (this.queryNodeBuilders == null) { + this.queryNodeBuilders = new HashMap, QueryBuilder>(); + } + + this.queryNodeBuilders.put(queryNodeClass, builder); + + } + + private void process(QueryNode node) + throws QueryNodeException { + + if (node != null) { + + List children = node.getChildren(); + + if (children != null) { + + for (QueryNode child : children) { + process(child); + } + + } + + processNode(node); + + } + + } + + private void processNode(QueryNode node) throws QueryNodeException { + QueryBuilder builder = null; + + if (this.fieldNameBuilders != null && + node instanceof FieldableNode) { + + builder = this.fieldNameBuilders.get(((FieldableNode) node).getField()); + + } + + if (builder == null && this.queryNodeBuilders != null) { + + Class clazz = node.getClass(); + + do { + builder = getQueryBuilder(clazz); + + if (builder == null) { + Class[] classes = node.getClass().getInterfaces(); + + for (Class actualClass : classes) { + builder = getQueryBuilder(actualClass); + + if (builder != null) { + break; + } + + } + + } + + } while (builder == null && (clazz = clazz.getSuperclass()) != null); + + } + + if (builder == null) { + // TODO: node should be converted to a readable query instead of just invoking node.toString() + throw new QueryNodeException(new MessageImpl(QueryParserMessages.LUCENE_QUERY_CONVERSION_ERROR, node.toString(), node.getClass().getName())); + + } + + Object obj = builder.build(node); + + if (obj != null) { + node.setTag(QUERY_TREE_BUILDER_TAGID, obj); + } + + } + + private QueryBuilder getQueryBuilder(Class clazz) { + + if (QueryNode.class.isAssignableFrom(clazz)) { + return this.queryNodeBuilders.get(clazz); + } + + return null; + + } + + /** + * Builds some kind of object from a query tree. Each node in the query + * tree is built using an specific builder associated to it. + * + * @param queryNode the query tree root node + * + * @return the built object + * + * @throws QueryNodeException if some node builder throws a {@link QueryNodeException} + * or if there is a node which had no builder associated to it + */ + public Object build(QueryNode queryNode) throws QueryNodeException { + process(queryNode); + + return queryNode.getTag(QUERY_TREE_BUILDER_TAGID); + + } + +} Index: src/java/org/apache/lucene/queryParser/builders/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/builders/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/builders/package.html (revision 0) @@ -0,0 +1,36 @@ + + + + + + + + +

Query Parser Builders

+

+The package org.apache.lucene.queryParser.builders contains the interface that +builders must implement, it also contain a utility QueryTreeBuilder walks the tree +and call the Builder for each node in the tree. + +These builders expect that the query node tree was already processed by a processor pipeline. + +

+

+

+ + Index: src/java/org/apache/lucene/queryParser/ParseException.java =================================================================== --- src/java/org/apache/lucene/queryParser/ParseException.java (revision 757685) +++ src/java/org/apache/lucene/queryParser/ParseException.java (working copy) @@ -1,198 +0,0 @@ -/* Generated By:JavaCC: Do not edit this line. ParseException.java Version 4.1 */ -/* JavaCCOptions:KEEP_LINE_COL=null */ -package org.apache.lucene.queryParser; - -/** - * This exception is thrown when parse errors are encountered. - * You can explicitly create objects of this exception type by - * calling the method generateParseException in the generated - * parser. - * - * You can modify this class to customize your error reporting - * mechanisms so long as you retain the public fields. - */ -public class ParseException extends Exception { - - /** - * This constructor is used by the method "generateParseException" - * in the generated parser. Calling this constructor generates - * a new object of this type with the fields "currentToken", - * "expectedTokenSequences", and "tokenImage" set. The boolean - * flag "specialConstructor" is also set to true to indicate that - * this constructor was used to create this object. - * This constructor calls its super class with the empty string - * to force the "toString" method of parent class "Throwable" to - * print the error message in the form: - * ParseException: - */ - public ParseException(Token currentTokenVal, - int[][] expectedTokenSequencesVal, - String[] tokenImageVal - ) - { - super(""); - specialConstructor = true; - currentToken = currentTokenVal; - expectedTokenSequences = expectedTokenSequencesVal; - tokenImage = tokenImageVal; - } - - /** - * The following constructors are for use by you for whatever - * purpose you can think of. Constructing the exception in this - * manner makes the exception behave in the normal way - i.e., as - * documented in the class "Throwable". The fields "errorToken", - * "expectedTokenSequences", and "tokenImage" do not contain - * relevant information. The JavaCC generated code does not use - * these constructors. - */ - - public ParseException() { - super(); - specialConstructor = false; - } - - /** Constructor with message. */ - public ParseException(String message) { - super(message); - specialConstructor = false; - } - - /** - * This variable determines which constructor was used to create - * this object and thereby affects the semantics of the - * "getMessage" method (see below). - */ - protected boolean specialConstructor; - - /** - * This is the last token that has been consumed successfully. If - * this object has been created due to a parse error, the token - * followng this token will (therefore) be the first error token. - */ - public Token currentToken; - - /** - * Each entry in this array is an array of integers. Each array - * of integers represents a sequence of tokens (by their ordinal - * values) that is expected at this point of the parse. - */ - public int[][] expectedTokenSequences; - - /** - * This is a reference to the "tokenImage" array of the generated - * parser within which the parse error occurred. This array is - * defined in the generated ...Constants interface. - */ - public String[] tokenImage; - - /** - * This method has the standard behavior when this object has been - * created using the standard constructors. Otherwise, it uses - * "currentToken" and "expectedTokenSequences" to generate a parse - * error message and returns it. If this object has been created - * due to a parse error, and you do not catch it (it gets thrown - * from the parser), then this method is called during the printing - * of the final stack trace, and hence the correct error message - * gets displayed. - */ - public String getMessage() { - if (!specialConstructor) { - return super.getMessage(); - } - StringBuffer expected = new StringBuffer(); - int maxSize = 0; - for (int i = 0; i < expectedTokenSequences.length; i++) { - if (maxSize < expectedTokenSequences[i].length) { - maxSize = expectedTokenSequences[i].length; - } - for (int j = 0; j < expectedTokenSequences[i].length; j++) { - expected.append(tokenImage[expectedTokenSequences[i][j]]).append(' '); - } - if (expectedTokenSequences[i][expectedTokenSequences[i].length - 1] != 0) { - expected.append("..."); - } - expected.append(eol).append(" "); - } - String retval = "Encountered \""; - Token tok = currentToken.next; - for (int i = 0; i < maxSize; i++) { - if (i != 0) retval += " "; - if (tok.kind == 0) { - retval += tokenImage[0]; - break; - } - retval += " " + tokenImage[tok.kind]; - retval += " \""; - retval += add_escapes(tok.image); - retval += " \""; - tok = tok.next; - } - retval += "\" at line " + currentToken.next.beginLine + ", column " + currentToken.next.beginColumn; - retval += "." + eol; - if (expectedTokenSequences.length == 1) { - retval += "Was expecting:" + eol + " "; - } else { - retval += "Was expecting one of:" + eol + " "; - } - retval += expected.toString(); - return retval; - } - - /** - * The end of line string for this machine. - */ - protected String eol = System.getProperty("line.separator", "\n"); - - /** - * Used to convert raw characters to their escaped version - * when these raw version cannot be used as part of an ASCII - * string literal. - */ - protected String add_escapes(String str) { - StringBuffer retval = new StringBuffer(); - char ch; - for (int i = 0; i < str.length(); i++) { - switch (str.charAt(i)) - { - case 0 : - continue; - case '\b': - retval.append("\\b"); - continue; - case '\t': - retval.append("\\t"); - continue; - case '\n': - retval.append("\\n"); - continue; - case '\f': - retval.append("\\f"); - continue; - case '\r': - retval.append("\\r"); - continue; - case '\"': - retval.append("\\\""); - continue; - case '\'': - retval.append("\\\'"); - continue; - case '\\': - retval.append("\\\\"); - continue; - default: - if ((ch = str.charAt(i)) < 0x20 || ch > 0x7e) { - String s = "0000" + Integer.toString(ch, 16); - retval.append("\\u" + s.substring(s.length() - 4, s.length())); - } else { - retval.append(ch); - } - continue; - } - } - return retval.toString(); - } - -} -/* JavaCC - OriginalChecksum=c63b396885c4ff44d7aa48d3feae60cd (do not edit this line) */ Index: src/java/org/apache/lucene/queryParser/QueryParserConstants.java =================================================================== --- src/java/org/apache/lucene/queryParser/QueryParserConstants.java (revision 757685) +++ src/java/org/apache/lucene/queryParser/QueryParserConstants.java (working copy) @@ -1,125 +0,0 @@ -/* Generated By:JavaCC: Do not edit this line. QueryParserConstants.java */ -package org.apache.lucene.queryParser; - - -/** - * Token literal values and constants. - * Generated by org.javacc.parser.OtherFilesGen#start() - */ -public interface QueryParserConstants { - - /** End of File. */ - int EOF = 0; - /** RegularExpression Id. */ - int _NUM_CHAR = 1; - /** RegularExpression Id. */ - int _ESCAPED_CHAR = 2; - /** RegularExpression Id. */ - int _TERM_START_CHAR = 3; - /** RegularExpression Id. */ - int _TERM_CHAR = 4; - /** RegularExpression Id. */ - int _WHITESPACE = 5; - /** RegularExpression Id. */ - int _QUOTED_CHAR = 6; - /** RegularExpression Id. */ - int AND = 8; - /** RegularExpression Id. */ - int OR = 9; - /** RegularExpression Id. */ - int NOT = 10; - /** RegularExpression Id. */ - int PLUS = 11; - /** RegularExpression Id. */ - int MINUS = 12; - /** RegularExpression Id. */ - int LPAREN = 13; - /** RegularExpression Id. */ - int RPAREN = 14; - /** RegularExpression Id. */ - int COLON = 15; - /** RegularExpression Id. */ - int STAR = 16; - /** RegularExpression Id. */ - int CARAT = 17; - /** RegularExpression Id. */ - int QUOTED = 18; - /** RegularExpression Id. */ - int TERM = 19; - /** RegularExpression Id. */ - int FUZZY_SLOP = 20; - /** RegularExpression Id. */ - int PREFIXTERM = 21; - /** RegularExpression Id. */ - int WILDTERM = 22; - /** RegularExpression Id. */ - int RANGEIN_START = 23; - /** RegularExpression Id. */ - int RANGEEX_START = 24; - /** RegularExpression Id. */ - int NUMBER = 25; - /** RegularExpression Id. */ - int RANGEIN_TO = 26; - /** RegularExpression Id. */ - int RANGEIN_END = 27; - /** RegularExpression Id. */ - int RANGEIN_QUOTED = 28; - /** RegularExpression Id. */ - int RANGEIN_GOOP = 29; - /** RegularExpression Id. */ - int RANGEEX_TO = 30; - /** RegularExpression Id. */ - int RANGEEX_END = 31; - /** RegularExpression Id. */ - int RANGEEX_QUOTED = 32; - /** RegularExpression Id. */ - int RANGEEX_GOOP = 33; - - /** Lexical state. */ - int Boost = 0; - /** Lexical state. */ - int RangeEx = 1; - /** Lexical state. */ - int RangeIn = 2; - /** Lexical state. */ - int DEFAULT = 3; - - /** Literal token values. */ - String[] tokenImage = { - "", - "<_NUM_CHAR>", - "<_ESCAPED_CHAR>", - "<_TERM_START_CHAR>", - "<_TERM_CHAR>", - "<_WHITESPACE>", - "<_QUOTED_CHAR>", - "", - "", - "", - "", - "\"+\"", - "\"-\"", - "\"(\"", - "\")\"", - "\":\"", - "\"*\"", - "\"^\"", - "", - "", - "", - "", - "", - "\"[\"", - "\"{\"", - "", - "\"TO\"", - "\"]\"", - "", - "", - "\"TO\"", - "\"}\"", - "", - "", - }; - -} Index: src/java/org/apache/lucene/queryParser/processors/NoChildOptimizationQueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/processors/NoChildOptimizationQueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/processors/NoChildOptimizationQueryNodeProcessor.java (revision 0) @@ -0,0 +1,90 @@ +package org.apache.lucene.queryParser.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.BoostQueryNode; +import org.apache.lucene.queryParser.nodes.DeletedQueryNode; +import org.apache.lucene.queryParser.nodes.MatchNoDocsQueryNode; +import org.apache.lucene.queryParser.nodes.ModifierQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.TokenizedPhraseQueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + + +/** + * A {@link NoChildOptimizationQueryNodeProcessor} removes every BooleanQueryNode, + * BoostQueryNode, TokenizedPhraseQueryNode or ModifierQueryNode that do not have + * a valid children + * Example: When the children of these nodes are removed for any reason then the + * nodes may become invalid. + */ +public class NoChildOptimizationQueryNodeProcessor extends QueryNodeProcessorImpl { + + public NoChildOptimizationQueryNodeProcessor() { + // empty constructor + } + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof BooleanQueryNode || + node instanceof BoostQueryNode || + node instanceof TokenizedPhraseQueryNode || + node instanceof ModifierQueryNode) { + + List children = node.getChildren(); + + if (children != null && children.size() > 0) { + + for (QueryNode child : children) { + + if (!(child instanceof DeletedQueryNode)) { + return node; + } + + } + + } + + return new MatchNoDocsQueryNode(); + + } + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/java/org/apache/lucene/queryParser/processors/QueryNodeProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/processors/QueryNodeProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/processors/QueryNodeProcessor.java (revision 0) @@ -0,0 +1,72 @@ +package org.apache.lucene.queryParser.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.nodes.QueryNode; + +/** + * A {@link QueryNodeProcessor} is a interface for classes that process a + * query node tree. + * + * The implementor of this class should perform some operation on a query node tree + * and return the same or another query node tree. + * + * It also may carry a {@link QueryConfigHandler} object that contains configuration + * about the query represented by the query tree or the collection/index where + * it's intended to be executed. + * + * In case there is any {@link QueryConfigHandler} associated to the query tree + * to be processed, it should be set using {@link QueryNodeProcessor#setQueryConfigHandler(QueryConfigHandler)} + * before {@link QueryNodeProcessor#process(QueryNode)} is invoked. + * + */ +public interface QueryNodeProcessor { + + /** + * Processes a query node tree. It may return the same or another query tree. + * I should never return null. + * + * @param query tree root node + * + * @return the processed query tree + * + * @throws QueryNodeException + * + * @throws CloneNotSupportedException + */ + public QueryNode process(QueryNode queryTree) throws QueryNodeException; + + /** + * Sets the {@link QueryConfigHandler} associated to the query tree. + * + * @param queryConfigHandler + */ + public void setQueryConfigHandler(QueryConfigHandler queryConfigHandler); + + /** + * Returns the {@link QueryConfigHandler} associated to the query tree if any, + * otherwise it returns null + * + * @return the {@link QueryConfigHandler} associated to the query tree if any, + * otherwise it returns null + */ + public QueryConfigHandler getQueryConfigHandler(); + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/processors/QueryNodeProcessorImpl.java =================================================================== --- src/java/org/apache/lucene/queryParser/processors/QueryNodeProcessorImpl.java (revision 0) +++ src/java/org/apache/lucene/queryParser/processors/QueryNodeProcessorImpl.java (revision 0) @@ -0,0 +1,148 @@ +package org.apache.lucene.queryParser.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.ArrayList; +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.nodes.QueryNode; + + +/** + * @see org.apache.lucene.queryParser.processors.QueryNodeProcessor + */ +public abstract class QueryNodeProcessorImpl implements QueryNodeProcessor { + + private ArrayList childrenListPool = new ArrayList(); + + private QueryConfigHandler queryConfig; + + public QueryNodeProcessorImpl() { + // empty constructor + } + + public QueryNodeProcessorImpl(QueryConfigHandler queryConfigHandler) { + this.queryConfig = queryConfigHandler; + } + + public QueryNode process(QueryNode queryTree) throws QueryNodeException { + return processIteration(queryTree); + } + + private QueryNode processIteration(QueryNode queryTree) throws QueryNodeException { + queryTree = preProcessNode(queryTree); + + processChildren(queryTree); + + queryTree = postProcessNode(queryTree); + + return queryTree; + + } + + protected void processChildren(QueryNode queryTree) + throws QueryNodeException { + + List children = queryTree.getChildren(); + ChildrenList newChildren; + + if (children != null && children.size() > 0) { + + newChildren = allocateChildrenList(); + + try { + + for (QueryNode child : children) { + child = processIteration(child); + + if (child == null) { + throw new NullPointerException(); + + } + + newChildren.add(child); + + } + + List orderedChildrenList = setChildrenOrder(newChildren); + + queryTree.set(orderedChildrenList); + + } finally { + newChildren.beingUsed = false; + } + + } + + } + + private ChildrenList allocateChildrenList() { + ChildrenList list = null; + + for (ChildrenList auxList : this.childrenListPool) { + + if (!auxList.beingUsed) { + list = auxList; + list.clear(); + + break; + + } + + } + + if (list == null) { + list = new ChildrenList(); + this.childrenListPool.add(list); + + } + + list.beingUsed = true; + + return list; + + } + + public void setQueryConfigHandler(QueryConfigHandler queryConfigHandler) { + this.queryConfig = queryConfigHandler; + } + + public QueryConfigHandler getQueryConfigHandler() { + return this.queryConfig; + } + + abstract protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException; + + abstract protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException; + + abstract protected List setChildrenOrder(List children) + throws QueryNodeException; + + private static class ChildrenList extends ArrayList { + + private static final long serialVersionUID = -2613518456949297135L; + + boolean beingUsed; + + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/processors/QueryNodeProcessorPipeline.java =================================================================== --- src/java/org/apache/lucene/queryParser/processors/QueryNodeProcessorPipeline.java (revision 0) +++ src/java/org/apache/lucene/queryParser/processors/QueryNodeProcessorPipeline.java (revision 0) @@ -0,0 +1,99 @@ +package org.apache.lucene.queryParser.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.LinkedList; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.nodes.QueryNode; + + +/** + * A {@link QueryNodeProcessorPipeline} class should be used to build + * a query node processor pipeline. + * + * When a query node tree is processed using this class, it passes + * the query node tree to each processor on the pipeline and the + * result from each processor is passed to the next one, always following + * the order the processors were on the pipeline. + * + * When a {@link QueryConfigHandler} object is set on a {@link QueryNodeProcessorPipeline}, + * it takes care of also setting this {@link QueryConfigHandler} on all processor on + * pipeline. + * + */ +public class QueryNodeProcessorPipeline implements QueryNodeProcessor { + + private LinkedList processors = new LinkedList(); + + private QueryConfigHandler queryConfig; + + /** + * Constructs an empty query node processor pipeline. + */ + public QueryNodeProcessorPipeline() { + // empty constructor + } + + /** + * Constructs with a {@link QueryConfigHandler} object. + */ + public QueryNodeProcessorPipeline(QueryConfigHandler queryConfigHandler) { + this.queryConfig = queryConfigHandler; + } + + public QueryConfigHandler getQueryConfigHandler() { + return this.queryConfig; + } + + public QueryNode process(QueryNode queryTree) throws QueryNodeException { + + for (QueryNodeProcessor processor : this.processors) { + queryTree = processor.process(queryTree); + } + + return queryTree; + + } + + /** + * Adds a processor to the pipeline, it's always added to the end + * of the pipeline. + * + * @param processor the processor to be added + */ + public void addProcessor(QueryNodeProcessor processor) { + this.processors.add(processor); + + processor.setQueryConfigHandler(this.queryConfig); + + } + + public void setQueryConfigHandler(QueryConfigHandler queryConfigHandler) { + this.queryConfig = queryConfigHandler; + + for (QueryNodeProcessor processor : this.processors) { + processor.setQueryConfigHandler(this.queryConfig); + } + + } + +} + + Index: src/java/org/apache/lucene/queryParser/processors/RemoveDeletedQueryNodesProcessor.java =================================================================== --- src/java/org/apache/lucene/queryParser/processors/RemoveDeletedQueryNodesProcessor.java (revision 0) +++ src/java/org/apache/lucene/queryParser/processors/RemoveDeletedQueryNodesProcessor.java (revision 0) @@ -0,0 +1,114 @@ +package org.apache.lucene.queryParser.processors; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Iterator; +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.DeletedQueryNode; +import org.apache.lucene.queryParser.nodes.MatchNoDocsQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; + + +/** + * A {@link QueryNodeProcessorPipeline} class removes every instance + * of {@link DeletedQueryNode} from a query node tree. + * If the resulting root node is a {@link DeletedQueryNode}, + * {@link MatchNoDocsQueryNode} is returned. + * + */ +public class RemoveDeletedQueryNodesProcessor extends + QueryNodeProcessorImpl { + + public RemoveDeletedQueryNodesProcessor() { + // empty constructor + } + + public QueryNode process(QueryNode queryTree) throws QueryNodeException { + queryTree = super.process(queryTree); + + if (queryTree instanceof DeletedQueryNode && + !(queryTree instanceof MatchNoDocsQueryNode)) { + + return new MatchNoDocsQueryNode(); + + } + + return queryTree; + + } + + protected QueryNode postProcessNode(QueryNode node) throws QueryNodeException { + + if (node instanceof BooleanQueryNode) { + List children = node.getChildren(); + boolean removeBoolean = false; + + if (children == null || children.size() == 0) { + removeBoolean = true; + + } else { + removeBoolean = true; + + for (Iterator it = children.iterator() ; it.hasNext() ; ) { + + if (!(it.next() instanceof DeletedQueryNode)) { + removeBoolean = false; + break; + + } + + } + + } + + if (removeBoolean) { + return new DeletedQueryNode(); + } + + } + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + for (int i = 0; i < children.size(); i++) { + + if (children.get(i) instanceof DeletedQueryNode) { + children.remove(i--); + } + + } + + return children; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/AndQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/AndQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/AndQueryNode.java (revision 0) @@ -0,0 +1,75 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link AndQueryNode} represents an AND boolean operation performed + * on a list of nodes. + */ +public class AndQueryNode extends BooleanQueryNode { + + private static final long serialVersionUID = 118496077529151825L; + + /** + * @param clauses - the query nodes to be and'ed + */ + public AndQueryNode(List clauses) { + super(clauses); + if ((clauses == null) || (clauses.size() == 0)) { + throw new IllegalArgumentException("AND query must have at least one clause"); + } + } + + public String toString() { + if (getChildren() == null || getChildren().size() == 0) + return ""; + StringBuilder sb = new StringBuilder(); + sb.append(""); + for (QueryNode child : getChildren()) { + sb.append("\n"); + sb.append(child.toString()); + + } + sb.append("\n"); + return sb.toString(); + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + if (getChildren() == null || getChildren().size() == 0) + return ""; + + StringBuilder sb = new StringBuilder(); + String filler = ""; + for (QueryNode child : getChildren()) { + sb.append(filler).append(child.toQueryString(escapeSyntaxParser)); + filler = " AND "; + } + + // in case is root or the parent is a group node avoid parenthesis + if ((getParent() != null && getParent() instanceof GroupQueryNode ) || isRoot()) + return sb.toString(); + else + return "( " + sb.toString() + " )"; + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/AnyQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/AnyQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/AnyQueryNode.java (revision 0) @@ -0,0 +1,114 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link AnyQueryNode} represents an ANY operator performed on a list + * of nodes. + */ +public class AnyQueryNode extends AndQueryNode { + private static final long serialVersionUID = 1000791433562954187L; + + private CharSequence field = null; + private int matchingElements = 0; + + /** + * @param clauses - the query nodes to be or'ed + */ + public AnyQueryNode(List clauses, CharSequence field, int matchingElements) { + super(clauses); + this.field = field; + this.matchingElements = matchingElements; + } + + /** + * returns null if the field was not specified + * @return the field + */ + public CharSequence getField() { + return this.field; + } + + /** + * returns - null if the field was not specified + * @return the field as a String + */ + public String getFieldAsString() { + if (this.field == null) + return null; + else + return this.field.toString(); + } + + /** + * @param field - the field to set + */ + public void setField(CharSequence field) { + this.field = field; + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + AnyQueryNode clone=(AnyQueryNode)super.cloneTree(); + + clone.field = this.field; + clone.matchingElements = this.matchingElements; + + return clone; + } + + public String toString() { + if (getChildren() == null || getChildren().size() == 0) + return ""; + StringBuilder sb = new StringBuilder(); + sb.append(""); + for (QueryNode clause : getChildren()) { + sb.append("\n"); + sb.append(clause.toString()); + } + sb.append("\n"); + return sb.toString(); + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + String anySTR = " ANY " + this.matchingElements; + + StringBuilder sb = new StringBuilder(); + if (getChildren() == null ||getChildren().size() == 0) + { + // no childs case + } else { + String filler = ""; + for (QueryNode clause : getChildren()) { + sb.append(filler).append(clause.toQueryString(escapeSyntaxParser)); + filler = " "; + } + } + + if (isDefaultField(this.field)) { + return "( " + sb.toString() + " ) " + anySTR; + } else { + return this.field + ":(( " + sb.toString() + " ) " + anySTR + ")"; + } + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/BooleanQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/BooleanQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/BooleanQueryNode.java (revision 0) @@ -0,0 +1,84 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.*; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link BooleanQueryNode} represents a list of elements which do + * not have an explicit boolean operator defined between them. It can + * be used to express a boolean query that intends to use the default + * boolean operator. + */ +public class BooleanQueryNode extends QueryNodeImpl { + + private static final long serialVersionUID = -2206623652088638072L; + + /** + * @param clauses - the query nodes to be and'ed + */ + public BooleanQueryNode (List clauses) { + setLeaf(false); + allocate(); + set(clauses); + } + + + + public String toString() { + if (getChildren() == null || getChildren().size() == 0) + return ""; + StringBuilder sb = new StringBuilder(); + sb.append(""); + for (QueryNode child : getChildren()) { + sb.append("\n"); + sb.append(child.toString()); + } + sb.append("\n"); + return sb.toString(); + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + if (getChildren() == null || getChildren().size() == 0) + return ""; + + StringBuilder sb = new StringBuilder(); + String filler = ""; + for (QueryNode child : getChildren()) { + sb.append(filler).append(child.toQueryString(escapeSyntaxParser)); + filler = " "; + } + + // in case is root or the parent is a group node avoid parenthesis + if ((getParent() != null && getParent() instanceof GroupQueryNode ) || isRoot()) + return sb.toString(); + else + return "( " + sb.toString() + " )"; + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + BooleanQueryNode clone=(BooleanQueryNode)super.cloneTree(); + + // nothing to do here + + return clone; + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/BoostQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/BoostQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/BoostQueryNode.java (revision 0) @@ -0,0 +1,119 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeError; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link BoostQueryNode} boosts the QueryNode tree which is under + * this node. So, it must only and always have one child. + * + * The boost value may vary from 0.0 to 1.0. + * + */ +public class BoostQueryNode extends QueryNodeImpl { + + private static final long serialVersionUID = -3929082630855807593L; + + private float value = 0; + + /** + * Constructs a boost node + * + * @param query the query to be boosted + * @param value the boost value, it may vary from 0.0 to 1.0 + * + * @throws QueryNodeException + */ + public BoostQueryNode(QueryNode query, float value) throws QueryNodeException { + if (query == null) { + throw new QueryNodeError(new MessageImpl(QueryParserMessages.NODE_ACTION_NOT_SUPPORTED, "query", "null")); + } + + this.value = value; + setLeaf(false); + allocate(); + add(query); + } + + /** + * Returns the single child which this node boosts. + * + * @return the single child which this node boosts + */ + public QueryNode getChild() { + List children = getChildren(); + + if (children == null || children.size() == 0) { + return null; + } + + return children.get(0); + + } + + /** + * Returns the boost value. It may vary from 0.0 to 1.0. + * + * @return the boost value + */ + public float getValue() { + return this.value; + } + + /** + * Returns the boost value parsed to a string. + * + * @return the parsed value + */ + private CharSequence getValueString(){ + Float f = new Float(this.value); + if ( f == f.longValue()) + return "" + f.longValue(); + else + return "" + f; + + } + + public String toString() { + return "" + + "\n" + getChild().toString() + + "\n"; + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + if (getChild() == null) return ""; + return getChild().toQueryString(escapeSyntaxParser) + "^" + getValueString(); + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + BoostQueryNode clone=(BoostQueryNode)super.cloneTree(); + + clone.value = this.value; + + return clone; + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/DeletedQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/DeletedQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/DeletedQueryNode.java (revision 0) @@ -0,0 +1,51 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; +import org.apache.lucene.queryParser.processors.RemoveDeletedQueryNodesProcessor; + +/** + * A {@link DeletedQueryNode} represents a node that was deleted from + * the query node tree. It can be removed from the tree using the + * {@link RemoveDeletedQueryNodesProcessor} processor. + */ +public class DeletedQueryNode extends QueryNodeImpl { + + private static final long serialVersionUID = -9151675506000425293L; + + public DeletedQueryNode() { + // empty constructor + } + + public CharSequence toQueryString(EscapeQuerySyntax escaper) { + return "[DELETEDCHILD]"; + } + + public String toString() { + return ""; + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + DeletedQueryNode clone = (DeletedQueryNode) super.cloneTree(); + + return clone; + + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/FieldQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/FieldQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/FieldQueryNode.java (revision 0) @@ -0,0 +1,163 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Locale; + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax.Type; + + +/** + * A {@link FieldQueryNode} represents a element that contains field/text tuple + */ +public class FieldQueryNode extends QueryNodeImpl implements FieldableNode { + + private static final long serialVersionUID = 3634521145130758265L; + + /** + * The term's field + */ + protected CharSequence field; + + /** + * The term's text. + */ + protected CharSequence text; + + /** + * The term's begin position. + */ + protected int begin; + + /** + * The term's end position. + */ + protected int end; + + /** + * The term's position increment. + */ + protected int positionIncrement; + + /** + * @param field - field name + * @param text - value + * @param begin - position in the query string + * @param end - position in the query string + */ + public FieldQueryNode(CharSequence field, CharSequence text, int begin, int end) { + this.field = field; + this.text = text; + this.begin = begin; + this.end = end; + this.setLeaf(true); + + } + + CharSequence getTermEscaped(EscapeQuerySyntax escaper){ + return escaper.escape(this.text, Locale.getDefault(), Type.NORMAL); + } + + CharSequence getTermEscapeQuoted(EscapeQuerySyntax escaper){ + return escaper.escape(this.text, Locale.getDefault(), Type.STRING); + } + + public CharSequence toQueryString(EscapeQuerySyntax escaper) { + if (isDefaultField(this.field)) { + return getTermEscaped(escaper); + } else { + return this.field + ":" + getTermEscaped(escaper); + } + } + + public String toString() { + return ""; + } + + /** + * @return the term + */ + public String getTextAsString() { + if (this.text == null) + return null; + else + return this.text.toString(); + } + + /** + * returns null if the field was not specified in the query string + * @return the field + */ + public String getFieldAsString() { + if (this.field == null) + return null; + else + return this.field.toString(); + } + + public int getBegin() { + return this.begin; + } + + public void setBegin(int begin) { + this.begin = begin; + } + + public int getEnd() { + return this.end; + } + + public void setEnd(int end) { + this.end = end; + } + + /** + * Returns the term. + * @return The "original" form of the term. + */ + public CharSequence getText() { + return this.text; + } + + public CharSequence getField() { + return this.field; + } + + /** + * @param text the text to set + */ + public void setText(CharSequence text) { + this.text = text; + } + + public void setField(CharSequence field) { + this.field = field; + } + + public int getPositionIncrement() { + return this.positionIncrement; + } + + public void setPositionIncrement(int pi) { + this.positionIncrement = pi; + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/FieldableNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/FieldableNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/FieldableNode.java (revision 0) @@ -0,0 +1,44 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * A query node implements {@link FieldableNode} interface to indicate that its children and itself + * are associated to a specific field. + * + * If it has any children which also implements this interface, it must ensure the children are + * associated to the same field. + * + */ +public interface FieldableNode extends QueryNode { + + /** + * Returns the field associated to the node and every node under it. + * + * @return the field name + */ + CharSequence getField(); + + /** + * Associates the node to a field. + * + * @param fieldName the field name + */ + void setField(CharSequence fieldName); + +} Index: src/java/org/apache/lucene/queryParser/nodes/FuzzyQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/FuzzyQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/FuzzyQueryNode.java (revision 0) @@ -0,0 +1,77 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + +/** + * A {@link FuzzyQueryNode} represents a element that contains + * field/text/similarity tuple + */ +public class FuzzyQueryNode extends FieldQueryNode { + + private static final long serialVersionUID = -1794537213032589441L; + + private float similarity; + + /** + * @param field Name of the field query will use. + * @param termStr Term token to use for building term for the query + */ + /** + * @param field - Field name + * @param term - Value + * @param minSimilarity - similarity value + * @param begin - position in the query string + * @param end - position in the query string + */ + public FuzzyQueryNode(CharSequence field, CharSequence term, float minSimilarity, int begin, int end) + { + super(field, term, begin, end); + this.similarity = minSimilarity; + setLeaf(true); + } + + public CharSequence toQueryString(EscapeQuerySyntax escaper) { + if (isDefaultField(this.field)) { + return getTermEscaped(escaper) + "~" + this.similarity; + } else { + return this.field + ":" + getTermEscaped(escaper) + "~" + this.similarity; + } + } + + public String toString() { + return ""; + } + + public FuzzyQueryNode cloneTree() throws CloneNotSupportedException { + FuzzyQueryNode clone=(FuzzyQueryNode)super.cloneTree(); + + clone.similarity = this.similarity; + + return clone; + } + + /** + * @return the similarity + */ + public float getSimilarity() { + return this.similarity; + } +} Index: src/java/org/apache/lucene/queryParser/nodes/GroupQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/GroupQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/GroupQueryNode.java (revision 0) @@ -0,0 +1,86 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.ArrayList; +import java.util.List; + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeError; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link GroupQueryNode} represents a location where the original + * user typed real parenthesis on the query string. + * This class is useful for queries like: + * a) a AND b OR c + * b) ( a AND b) OR c + * + * Parenthesis might be used to define the boolean operation precedence. + */ +public class GroupQueryNode extends QueryNodeImpl { + + private static final long serialVersionUID = -9204673493869114999L; + + /** + * This QueryNode is used to identify parenthesis on the original query string + */ + public GroupQueryNode(QueryNode query) { + if (query == null) { + throw new QueryNodeError(new MessageImpl(QueryParserMessages.PARAMETER_VALUE_NOT_SUPPORTED, "query", "null")); + } + + allocate(); + setLeaf(false); + add(query); + } + + public QueryNode getChild() { + return getChildren().get(0); + } + + public String toString() { + return "" + + "\n" + getChild().toString() + + "\n"; + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + if (getChild() == null) return ""; + + return "( " + getChild().toQueryString(escapeSyntaxParser) + " )"; + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + GroupQueryNode clone=(GroupQueryNode)super.cloneTree(); + + return clone; + } + + /** + * @param child + */ + public void setChild(QueryNode child) { + List list = new ArrayList(); + list.add(child); + this.set(list); + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/MatchAllDocsQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/MatchAllDocsQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/MatchAllDocsQueryNode.java (revision 0) @@ -0,0 +1,49 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + +/** + * A {@link MatchAllDocsQueryNode} indicates that a query node tree or subtree + * will match all documents if executed in the index. + */ +public class MatchAllDocsQueryNode extends QueryNodeImpl { + + private static final long serialVersionUID = -7050381275423477809L; + + public MatchAllDocsQueryNode() { + // empty constructor + } + + public String toString() { + return ""; + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + return "*:*"; + } + + public MatchAllDocsQueryNode cloneTree() throws CloneNotSupportedException { + MatchAllDocsQueryNode clone=(MatchAllDocsQueryNode)super.cloneTree(); + + //nothing to clone + + return clone; + } +} Index: src/java/org/apache/lucene/queryParser/nodes/MatchNoDocsQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/MatchNoDocsQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/MatchNoDocsQueryNode.java (revision 0) @@ -0,0 +1,37 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * A {@link MatchNoDocsQueryNode} indicates that a query node tree or subtree + * will not match any documents if executed in the index. + * + */ +public class MatchNoDocsQueryNode extends DeletedQueryNode { + + private static final long serialVersionUID = 8081805751679581497L; + + public MatchNoDocsQueryNode() { + // empty constructor + } + + public String toString() { + return ""; + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/ModifierQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/ModifierQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/ModifierQueryNode.java (revision 0) @@ -0,0 +1,152 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.ArrayList; +import java.util.List; + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeError; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link ModifierQueryNode} indicates the modifier value (+,-,?,NONE) + * for each term on the query string + * for example "+t1 -t2 t3" will have a tree of + * + * + * + * + * + * + * + * + * + * + */ +public class ModifierQueryNode extends QueryNodeImpl { + + private static final long serialVersionUID = -391209837953928169L; + + public enum Modifier { + MOD_NONE, MOD_NOT, MOD_REQ; + + public String toString() { + switch (this) { + case MOD_NONE: + return "MOD_NONE"; + case MOD_NOT: + return "MOD_NOT"; + case MOD_REQ: + return "MOD_REQ"; + } + // this code is never executed + return "MOD_DEFAULT"; + } + + public String toDigitString(){ + switch(this){ + case MOD_NONE: return ""; + case MOD_NOT: return "-"; + case MOD_REQ: return "+"; + } + // this code is never executed + return ""; + } + + public String toLargeString() { + switch(this){ + case MOD_NONE: return ""; + case MOD_NOT: return "NOT "; + case MOD_REQ: return "+"; + } + // this code is never executed + return ""; + } + } + + private Modifier modifier = Modifier.MOD_NONE; + + /** + * Used to store the modifier value on the original query string + * @param query - QueryNode subtree + * @param mod - Modifier Value + */ + public ModifierQueryNode(QueryNode query, Modifier mod) { + if (query == null) { + throw new QueryNodeError(new MessageImpl(QueryParserMessages.PARAMETER_VALUE_NOT_SUPPORTED, "query", "null")); + } + + allocate(); + setLeaf(false); + add(query); + this.modifier = mod; + } + + public QueryNode getChild() { + return getChildren().get(0); + } + + public Modifier getModifier() { + return this.modifier; + } + + public String toString() { + return "" + + "\n" + getChild().toString() + + "\n"; + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + if (getChild() == null) return ""; + + String leftParenthensis = ""; + String rightParenthensis = ""; + + if (getChild() != null && getChild() instanceof ModifierQueryNode){ + leftParenthensis = "("; + rightParenthensis = ")"; + } + + if (getChild() instanceof BooleanQueryNode){ + return this.modifier.toLargeString() + leftParenthensis + getChild().toQueryString(escapeSyntaxParser) + rightParenthensis; + } else { + return this.modifier.toDigitString() + leftParenthensis + getChild().toQueryString(escapeSyntaxParser) + rightParenthensis; + } + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + ModifierQueryNode clone=(ModifierQueryNode)super.cloneTree(); + + clone.modifier = this.modifier; + + return clone; + } + + /** + * @param child + */ + public void setChild(QueryNode child) { + List list = new ArrayList(); + list.add(child); + this.set(list); + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/MultiLevelFieldQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/MultiLevelFieldQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/MultiLevelFieldQueryNode.java (revision 0) @@ -0,0 +1,154 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.ArrayList; +import java.util.List; +import java.util.Locale; + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax.Type; + + +/** + * A {@link MultiLevelFieldQueryNode} is used for to store queries like + * /company/USA/California + * /product/shoes/brown + * QueryText are objects that contain the text, begin position and + * end position in the query. + * + * Example how the text parser creates these objects: + * + * List values = ArrayList(); + * values.add(new MultiLevelFieldQueryNode.QueryText("company", 1, 7)); + * values.add(new MultiLevelFieldQueryNode.QueryText("USA", 9, 12)); + * values.add(new MultiLevelFieldQueryNode.QueryText("California", 14, 23)); + * QueryNode q = new MultiLevelFieldQueryNode(values); + * + */ +public class MultiLevelFieldQueryNode extends QueryNodeImpl implements FieldableNode { + + private static final long serialVersionUID = -8325921322405804789L; + + public static class QueryText { + CharSequence value = null; + /** + * The term's begin position. + */ + int begin; + + /** + * The term's end position. + */ + int end; + + /** + * @param value - text value + * @param begin - position in the query string + * @param end - position in the query string + */ + public QueryText(CharSequence value, int begin, int end) { + super(); + this.value = value; + this.begin = begin; + this.end = end; + } + + public QueryText clone() throws CloneNotSupportedException { + QueryText clone=(QueryText)super.clone(); + clone.value = this.value; + clone.begin = this.begin; + clone.end = this.end; + return clone; + } + } + + private List values = null; + /** + * @param values - List of QueryText objects + */ + public MultiLevelFieldQueryNode(List pValues) { + this.values = pValues; + } + + public CharSequence getField() { + //first value contains the field name + return this.values.get(0).value; + } + + public CharSequence getText() { + //second value contains the text value + return this.values.get(1).value; + } + + CharSequence getTermEscaped(EscapeQuerySyntax escaper){ + return escaper.escape(this.values.get(1).value, Locale.getDefault(), Type.NORMAL); + } + + CharSequence getTermEscapeQuoted(EscapeQuerySyntax escaper){ + return escaper.escape(this.values.get(1).value, Locale.getDefault(), Type.STRING); + } + + public void setField(CharSequence fieldName) { + List children = getChildren(); + + if (children != null) { + + for (QueryNode child : children) { + + if (child instanceof FieldableNode) { + ((FieldableNode) child).setField(fieldName); + } + + } + + } + + } + + public CharSequence toQueryString(EscapeQuerySyntax escaper) { + if (isDefaultField(this.values.get(0).value)) { + return "/DEFAULT/" + getTermEscaped(escaper); + } else { + return "/" + this.values.get(0).value + "/\"" + getTermEscaped(escaper) + "\""; + } + } + + public String toString() { + QueryText text = this.values.get(0); + + return ""; + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + MultiLevelFieldQueryNode clone=(MultiLevelFieldQueryNode)super.cloneTree(); + + // copy children + if (this.values != null) { + List localValues = new ArrayList(); + for (QueryText value : this.values) { + localValues.add(value.clone()); + } + clone.values = localValues; + } + + return clone; + } +} Index: src/java/org/apache/lucene/queryParser/nodes/NoTokenFoundQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/NoTokenFoundQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/NoTokenFoundQueryNode.java (revision 0) @@ -0,0 +1,49 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + +/** + * A {@link NoTokenFoundQueryNode} is used if a term is convert into + * no tokens by the tokenizer/lemmatizer/analyzer (null). + */ +public class NoTokenFoundQueryNode extends DeletedQueryNode { + + private static final long serialVersionUID = 7332975497586993833L; + + public NoTokenFoundQueryNode() { + super(); + } + + public CharSequence toQueryString(EscapeQuerySyntax escaper) { + return "[NTF]"; + } + + public String toString() { + return ""; + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + NoTokenFoundQueryNode clone=(NoTokenFoundQueryNode)super.cloneTree(); + + // nothing to do here + + return clone; + } +} Index: src/java/org/apache/lucene/queryParser/nodes/OpaqueQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/OpaqueQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/OpaqueQueryNode.java (revision 0) @@ -0,0 +1,80 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + +/** + * A {@link OpaqueQueryNode} is used for specify values that are + * not supposed to be parsed by the parser. + * For example: and XPATH query in the middle of a query string + * a b @xpath:'/bookstore/book[1]/title' c d + */ +public class OpaqueQueryNode extends QueryNodeImpl { + + private static final long serialVersionUID = 0L; + + private CharSequence schema = null; + + private CharSequence value = null; + + /** + * @param schema - schema identifier + * @param value - value that was not parsed + */ + public OpaqueQueryNode(CharSequence schema, CharSequence value) { + this.setLeaf(true); + + this.schema = schema; + this.value = value; + + } + + public String toString() { + return ""; + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + return "@" + this.schema + ":'" + this.value + "'"; + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + OpaqueQueryNode clone=(OpaqueQueryNode)super.cloneTree(); + + clone.schema = this.schema; + clone.value = this.value; + + return clone; + } + + /** + * @return the schema + */ + public CharSequence getSchema() { + return this.schema; + } + + /** + * @return the value + */ + public CharSequence getValue() { + return this.value; + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/OrQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/OrQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/OrQueryNode.java (revision 0) @@ -0,0 +1,77 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Iterator; +import java.util.List; + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link OrQueryNode} represents an OR boolean operation performed + * on a list of nodes. + * + */ +public class OrQueryNode extends BooleanQueryNode { + + private static final long serialVersionUID = -3692323307688017852L; + + /** + * @param clauses - the query nodes to be or'ed + */ + public OrQueryNode(List clauses) { + super(clauses); + if ((clauses == null) || (clauses.size() == 0)) { + throw new IllegalArgumentException("OR query must have at least one clause"); + } + } + + public String toString() { + if (getChildren() == null || getChildren().size() == 0) + return ""; + StringBuilder sb = new StringBuilder(); + sb.append(""); + for (QueryNode child : getChildren()) { + sb.append("\n"); + sb.append(child.toString()); + + } + sb.append("\n"); + return sb.toString(); + } + + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + if (getChildren() == null || getChildren().size() == 0) + return ""; + + StringBuilder sb = new StringBuilder(); + String filler = ""; + for (Iterator it = getChildren().iterator() ; it.hasNext() ; ) { + sb.append(filler).append(it.next().toQueryString(escapeSyntaxParser)); + filler = " OR "; + } + + // in case is root or the parent is a group node avoid parenthesis + if ((getParent() != null && getParent() instanceof GroupQueryNode ) || isRoot()) + return sb.toString(); + else + return "( " + sb.toString() + " )"; + } +} Index: src/java/org/apache/lucene/queryParser/nodes/ParametricQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/ParametricQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/ParametricQueryNode.java (revision 0) @@ -0,0 +1,95 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + +/** + * A {@link ParametricQueryNode} represents LE, LT, GE, GT, EQ, NE + * query. + * Example: date >= "2009-10-10" OR price = 200 + */ +public class ParametricQueryNode extends FieldQueryNode { + + private static final long serialVersionUID = -5770038129741218116L; + + private CompareOperator operator; + + public enum CompareOperator { + LE, LT, GE, GT, EQ, NE; + + public String toString() { + if ( LE.equals(this)) { + return "<="; + } else if (LT.equals(this)) { + return "<"; + } else if (GE.equals(this)) { + return ">="; + } else if (GT.equals(this)) { + return ">"; + } else if (EQ.equals(this)) { + return "="; + } else if (NE.equals(this)) { + return "!="; + } else { + throw new IllegalArgumentException("Unknown operator"); + } + } + } + + /** + * @param field - field name + * @param comp - CompareOperator + * @param value - text value + * @param begin - position in the query string + * @param end - position in the query string + */ + public ParametricQueryNode(CharSequence field, CompareOperator comp, CharSequence text, int begin, int end) { + super(field, text, begin, end); + this.operator = comp; + setLeaf(true); + } + + public CharSequence getOperand() { + return getText(); + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + return this.field + "" + this.operator.toString() + "\"" + this.text + "\""; + } + + public String toString() { + return ""; + } + + public ParametricQueryNode cloneTree() throws CloneNotSupportedException { + ParametricQueryNode clone=(ParametricQueryNode)super.cloneTree(); + + clone.operator = this.operator; + + return clone; + } + + /** + * @return the operator + */ + public CompareOperator getOperator() { + return this.operator; + } +} Index: src/java/org/apache/lucene/queryParser/nodes/ParametricRangeQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/ParametricRangeQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/ParametricRangeQueryNode.java (revision 0) @@ -0,0 +1,112 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.nodes.ParametricQueryNode.CompareOperator; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link ParametricRangeQueryNode} represents LE, LT, GE, GT, EQ, NE + * query. + * Example: date >= "2009-10-10" OR price = 200 + */ +public class ParametricRangeQueryNode extends QueryNodeImpl implements FieldableNode { + + private static final long serialVersionUID = 7120958816535573935L; + + public ParametricRangeQueryNode(ParametricQueryNode lowerBound, ParametricQueryNode upperBound) { + + if (upperBound.getOperator() != CompareOperator.LE && upperBound.getOperator() != CompareOperator.LT) { + throw new IllegalArgumentException("upper bound should have " + CompareOperator.LE + " or " + CompareOperator.LT); + } + + if (lowerBound.getOperator() != CompareOperator.GE && lowerBound.getOperator() != CompareOperator.GT) { + throw new IllegalArgumentException("lower bound should have " + CompareOperator.GE + " or " + CompareOperator.GT); + } + + if (upperBound.getField() != lowerBound.getField() || + (upperBound.getField() != null && !upperBound.getField().equals(lowerBound.getField()))) { + + throw new IllegalArgumentException("lower and upper bounds should have the same field name!"); + + } + + allocate(); + setLeaf(false); + + add(lowerBound); + add(upperBound); + + } + + public ParametricQueryNode getUpperBound() { + return (ParametricQueryNode) getChildren().get(1); + } + + public ParametricQueryNode getLowerBound() { + return (ParametricQueryNode) getChildren().get(0); + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + return getLowerBound().toQueryString(escapeSyntaxParser) + " AND " + getUpperBound().toQueryString(escapeSyntaxParser); + } + + public CharSequence getField() { + return getLowerBound().getField(); + } + + @Override + public String toString() { + StringBuilder sb = new StringBuilder("\n\t"); + sb.append(getUpperBound()).append("\n\t"); + sb.append(getLowerBound()).append("\n"); + sb.append("\n"); + + return sb.toString(); + + } + + public ParametricRangeQueryNode cloneTree() throws CloneNotSupportedException { + ParametricRangeQueryNode clone=(ParametricRangeQueryNode)super.cloneTree(); + + // nothing to do here + + return clone; + } + + public void setField(CharSequence fieldName) { + List children = getChildren(); + + if (children != null) { + + for (QueryNode child : getChildren()) { + + if (child instanceof FieldableNode) { + ((FieldableNode) child).setField(fieldName); + } + + } + + } + + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/nodes/PrefixWildcardQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/PrefixWildcardQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/PrefixWildcardQueryNode.java (revision 0) @@ -0,0 +1,55 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + + +/** + * A {@link PrefixWildcardQueryNode} represents wildcardquery that + * matches abc* or *. + * This does not apply to phrases, this is a special case on the original + * lucene parser. + * TODO: refactor the code to remove this special case from the parser. + * and probably do it on a Processor + */ +public class PrefixWildcardQueryNode extends WildcardQueryNode { + + private static final long serialVersionUID = 6851557641826407515L; + + /** + * @param field - field name + * @param term - value including the wildcard + * @param begin - position in the query string + * @param end - position in the query string + */ + public PrefixWildcardQueryNode(CharSequence field, CharSequence text, int begin, int end) + { + super(field, text, begin, end); + } + + public String toString() { + return ""; + } + + public PrefixWildcardQueryNode cloneTree() throws CloneNotSupportedException { + PrefixWildcardQueryNode clone=(PrefixWildcardQueryNode)super.cloneTree(); + + // nothing to do here + + return clone; + } +} Index: src/java/org/apache/lucene/queryParser/nodes/ProximityQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/ProximityQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/ProximityQueryNode.java (revision 0) @@ -0,0 +1,232 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeError; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link ProximityQueryNode} represents a query where the terms + * should meet specific distance conditions. + * (a b c) WITHIN [SENTENCE|PARAGRAPH|NUMBER] [INORDER] + * ("a" "b" "c") WITHIN [SENTENCE|PARAGRAPH|NUMBER] [INORDER] + * + * TODO: Add this to the future lucene2 parser/processor/builder + */ +public class ProximityQueryNode extends BooleanQueryNode { + + private static final long serialVersionUID = 9018220596680832916L; + + public enum Type { + PARAGRAPH, SENTENCE, NUMBER; + + CharSequence toQueryString() { + switch (this) { + case PARAGRAPH: + return "WITHIN PARAGRAPH"; + case SENTENCE: + return "WITHIN SENTENCE"; + case NUMBER: + return "WITHIN"; + default: + return "WITHIN SENTENCE"; + } + } + + + public String toString() { + switch (this) { + case PARAGRAPH: + return "PARAGRAPH"; + case SENTENCE: + return "SENTENCE"; + case NUMBER: + return "NUMBER"; + default: + return "NUMBER"; + } + } + } + + // utility class + static public class ProximityType { + int pDistance = 0; + + Type pType = null; + + public ProximityType(Type type) { + this(type, 0); + } + + public ProximityType(Type type, int distance) { + this.pType = type; + this.pDistance = distance; + } + } + + private Type proximityType = Type.SENTENCE; + private int distance = -1; + private boolean inorder = false; + private CharSequence field = null; + + /** + * @param clauses - QueryNode children + * @param field - field name + * @param type - type of proximity query + * @param distance - positive integer that specifies the distance + * @param inorder - true, if the tokens should be matched in the order of the clauses + */ + public ProximityQueryNode(List clauses, CharSequence field, Type type, int distance, boolean inorder) { + super(clauses); + setLeaf(false); + this.proximityType = type; + this.inorder = inorder; + this.field = field; + if (type == Type.NUMBER){ + if (distance <= 0) { + throw new QueryNodeError(new MessageImpl(QueryParserMessages.PARAMETER_VALUE_NOT_SUPPORTED, "distance", distance)); + + } else { + this.distance = distance; + } + + } + clearFields(clauses, field); + } + + /** + * @param clauses - QueryNode children + * @param field - field name + * @param type - type of proximity query + * @param inorder - true, if the tokens should be matched in the order of the clauses + */ + public ProximityQueryNode(List clauses, CharSequence field, Type type, boolean inorder) { + this(clauses, field, type, -1, inorder); + } + + static private void clearFields(List nodes, CharSequence field){ + if (nodes == null || nodes.size() == 0) + return; + + for (QueryNode clause : nodes) { + + if (clause instanceof FieldQueryNode){ + ((FieldQueryNode)clause).toQueryStringIgnoreFields = true; + ((FieldQueryNode)clause).setField(field); + } + } + } + + public Type getProximityType() { + return this.proximityType; + } + + public String toString() { + String distanceSTR = ( (this.distance == -1) ? ("") : ( " distance='" + this.distance) + "'" ); + + if (getChildren() == null || getChildren().size() == 0) + return ""; + StringBuilder sb = new StringBuilder(); + sb.append(""); + for (QueryNode child : getChildren()) { + sb.append("\n"); + sb.append(child.toString()); + } + sb.append("\n"); + return sb.toString(); + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + String withinSTR = this.proximityType.toQueryString() + ( (this.distance == -1) ? ("") : ( " " + this.distance) ) + + ((this.inorder)?(" INORDER"):("")); + + StringBuilder sb = new StringBuilder(); + if (getChildren() == null ||getChildren().size() == 0) + { + // no children case + } else { + String filler = ""; + for (QueryNode child : getChildren()) { + sb.append(filler).append(child.toQueryString(escapeSyntaxParser)); + filler = " "; + } + } + + if (isDefaultField(this.field)) { + return "( " + sb.toString() + " ) " + withinSTR; + } else { + return this.field + ":(( " + sb.toString() + " ) " + withinSTR + ")"; + } + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + ProximityQueryNode clone=(ProximityQueryNode)super.cloneTree(); + + clone.proximityType = this.proximityType; + clone.distance = this.distance; + clone.field = this.field; + + return clone; + } + + /** + * @return the distance + */ + public int getDistance() { + return this.distance; + } + + /** + * returns null if the field was not specified in the query string + * @return the field + */ + public CharSequence getField() { + return this.field; + } + + /** + * returns null if the field was not specified in the query string + * @return the field + */ + public String getFieldAsString() { + if (this.field == null) + return null; + else + return this.field.toString(); + } + + /** + * @param field the field to set + */ + public void setField(CharSequence field) { + this.field = field; + } + + /** + * @return terms must be matched in the specified order + */ + public boolean isInOrder() { + return this.inorder; + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/QueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/QueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/QueryNode.java (revision 0) @@ -0,0 +1,96 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.Serializable; +import java.util.List; + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link QueryNode} is a interface implemented by all nodes on a + * QueryNode tree. + */ +public interface QueryNode extends Serializable +{ + + /** convert to a query string understood by the query parser */ + // TODO: this interface might be changed in the future + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser); + + /** for printing */ + public String toString(); + + /** get Children nodes */ + public List getChildren(); + + + /** verify if a node is a Leaf node */ + public boolean isLeaf(); + + /** verify if a node contains a tag */ + public boolean containsTag(CharSequence tagName); + + /** + * @param tagName + * @return of stored on under that tag name + */ + public Object getTag(CharSequence tagName); + + public QueryNode getParent(); + + /** + * Recursive clone the QueryNode tree + * The tags are not copied to the new tree when you call the cloneTree() method + * @return the cloned tree + * @throws CloneNotSupportedException + */ + public QueryNode cloneTree() throws CloneNotSupportedException; + + // Below are the methods that can change state of a QueryNode + // Write Operations (not Thread Safe) + + // add a new child to a non Leaf node + public void add(QueryNode child); + public void add(List children); + + // reset the children of a node + public void set(List children); + + /** + * Associate the specified value with the specified tagName. + * If the tagName already exists, the old value is replaced. + * The tagName and value cannot be null. + * tagName will be converted to lowercase. + * + * @param tagName + * @param value + */ + public void setTag(CharSequence tagName, Object value); + + /** + * Unset a tag. + * tagName will be converted to lowercase. + * + * @param tagName + * @param value + */ + public void unsetTag(CharSequence tagName); + +} Index: src/java/org/apache/lucene/queryParser/nodes/QueryNodeImpl.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/QueryNodeImpl.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/QueryNodeImpl.java (revision 0) @@ -0,0 +1,216 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.ArrayList; +import java.util.Hashtable; +import java.util.List; +import java.util.Map; +import java.util.ResourceBundle; + +import org.apache.lucene.messages.NLS; +import org.apache.lucene.queryParser.messages.QueryParserMessages; + +/** + * A {@link QueryNodeImpl} is the default implementation of the interface + * {@link QueryNode} + */ +public abstract class QueryNodeImpl implements QueryNode, Cloneable { + + private static final long serialVersionUID = 5569870883474845989L; + + /* index default field */ + //TODO remove PLAINTEXT_FIELD_NAME replacing it with configuration APIs + public static final String PLAINTEXT_FIELD_NAME = "_plain"; + + private boolean isLeaf = true; + + private Hashtable tags = new Hashtable (); + + private List clauses = null; + + protected void allocate(){ + + if (this.clauses == null) { + this.clauses = new ArrayList(); + + } else { + this.clauses.clear(); + } + + } + + public final void add(QueryNode child) { + + if (isLeaf() || this.clauses == null || child == null){ + throw new IllegalArgumentException(NLS.getLocalizedMessage(QueryParserMessages.NODE_ACTION_NOT_SUPPORTED)); + } + + this.clauses.add(child); + ((QueryNodeImpl)child).setParent(this); + + } + + public final void add(List children) { + + if (isLeaf() || this.clauses == null){ + throw new IllegalArgumentException(NLS.getLocalizedMessage(QueryParserMessages.NODE_ACTION_NOT_SUPPORTED)); + } + + for (QueryNode child : getChildren()) { + add(child); + } + + } + + public boolean isLeaf() { + return this.isLeaf; + } + + public final void set(List children) { + + if (isLeaf() || this.clauses == null) { + ResourceBundle bundle = ResourceBundle.getBundle("org.apache.lucene.queryParser.messages.QueryParserMessages"); + String message = bundle.getObject("Q0008E.NODE_ACTION_NOT_SUPPORTED").toString(); + + throw new IllegalArgumentException(message); + + } + + // reset parent value + for (QueryNode child : children) { + + ((QueryNodeImpl) child).setParent(null); + + } + + // allocate new children list + allocate(); + + // add new childs and set parent + for (QueryNode child : children) { + add(child); + } + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + QueryNodeImpl clone=(QueryNodeImpl)super.clone(); + clone.isLeaf = this.isLeaf; + + // Reset all tags + clone.tags = new Hashtable(); + + // copy children + if (this.clauses != null) { + List localClauses = new ArrayList(); + for (QueryNode clause : this.clauses) { + localClauses.add(clause.cloneTree()); + } + clone.clauses = localClauses; + } + + return clone; + } + + public Object clone() throws CloneNotSupportedException{ + return cloneTree(); + } + + protected void setLeaf(boolean isLeaf) { + this.isLeaf = isLeaf; + } + + /** + * @return a List for QueryNode object. Returns null, for nodes that do + * not contain children. All leaf Nodes return null. + */ + public final List getChildren() { + if (isLeaf() || this.clauses == null){ + return null; + } + return this.clauses; + } + + public void setTag(CharSequence tagName, Object value) { + this.tags.put(tagName.toString().toLowerCase(), value); + } + + public void unsetTag(CharSequence tagName) { + this.tags.remove(tagName.toString().toLowerCase()); + } + + public boolean containsTag(CharSequence tagName){ + return this.tags.containsKey(tagName.toString().toLowerCase()); + } + + public Object getTag(CharSequence tagName){ + return this.tags.get(tagName.toString().toLowerCase()); + } + + private QueryNode parent = null; + private void setParent(QueryNode parent){ + this.parent = parent; + } + + public QueryNode getParent(){ + return this.parent; + } + + protected boolean isRoot() { + return getParent() == null; + } + + /** + * If set to true the the method toQueryString will not write field names + */ + protected boolean toQueryStringIgnoreFields = false; + + /** + * This method is use toQueryString to detect if fld is the default field + * @param fld - field name + * @return true if fld is the default field + */ + protected boolean isDefaultField(CharSequence fld){ + if (this.toQueryStringIgnoreFields) return true; + if (fld == null) return true; + if (QueryNodeImpl.PLAINTEXT_FIELD_NAME.equals(fld.toString())) return true; + return false; + } + + /** + * Every implementation of this class should return pseudo xml like this: + * + * For FieldQueryNode: + * + * + * @see org.apache.lucene.queryParser.QueryNode.toString() + */ + public String toString() { + return super.toString(); + } + + /** + * @see org.apache.lucene.queryParser.QueryNode.getTags() + * @return + */ + @SuppressWarnings("unchecked") + public Map getTags() { + return (Map) this.tags.clone(); + } + +} // end class QueryNodeImpl Index: src/java/org/apache/lucene/queryParser/nodes/QuotedFieldQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/QuotedFieldQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/QuotedFieldQueryNode.java (revision 0) @@ -0,0 +1,60 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + +/** + * A {@link QuotedFieldQueryNode} represents phrase query. + * Example: "life is great" + */ +public class QuotedFieldQueryNode extends FieldQueryNode { + + private static final long serialVersionUID = -6675157780051428987L; + + /** + * @param field - field name + * @param text - value + * @param begin - position in the query string + * @param end - position in the query string + */ + public QuotedFieldQueryNode(CharSequence field, CharSequence text, int begin, int end) { + super(field, text, begin, end); + } + + public CharSequence toQueryString(EscapeQuerySyntax escaper) { + if (isDefaultField(this.field)) { + return "\"" + getTermEscapeQuoted(escaper) + "\""; + } else { + return this.field + ":" + "\"" + getTermEscapeQuoted(escaper) + "\""; + } + } + + public String toString() { + return ""; + } + + public QuotedFieldQueryNode cloneTree() throws CloneNotSupportedException { + QuotedFieldQueryNode clone=(QuotedFieldQueryNode)super.cloneTree(); + // nothing to do here + return clone; + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/SlopQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/SlopQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/SlopQueryNode.java (revision 0) @@ -0,0 +1,113 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeError; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + +/** + * A {@link SlopQueryNode} represents phrase query with a slop. + * + * From Lucene FAQ: + * Is there a way to use a proximity operator (like near or within) with Lucene? + * There is a variable called slop that allows you to perform NEAR/WITHIN-like queries. + * By default, slop is set to 0 so that only exact phrases will match. + * When using QueryParser you can use this syntax to specify the slop: + * "doug cutting"~2 will find documents that contain + * "doug cutting" as well as ones that contain "cutting doug". + */ +public class SlopQueryNode extends QueryNodeImpl implements FieldableNode { + + private static final long serialVersionUID = 0L; + + private int value = 0; + + /** + * @param query - QueryNode Tree with the phrase + * @param value - slop value + */ + public SlopQueryNode(QueryNode query, int value) { + if (query == null) { + throw new QueryNodeError(new MessageImpl(QueryParserMessages.NODE_ACTION_NOT_SUPPORTED, "query", "null")); + } + + this.value = value; + setLeaf(false); + allocate(); + add(query); + } + + public QueryNode getChild() { + return getChildren().get(0); + } + + public int getValue() { + return this.value; + } + + private CharSequence getValueString(){ + Float f = new Float(this.value); + if ( f == f.longValue()) + return "" + f.longValue(); + else + return "" + f; + + } + + public String toString() { + return "" + + "\n" + getChild().toString() + + "\n"; + } + + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + if (getChild() == null) return ""; + return getChild().toQueryString(escapeSyntaxParser) + "~" + getValueString(); + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + SlopQueryNode clone=(SlopQueryNode)super.cloneTree(); + + clone.value = this.value; + + return clone; + } + + public CharSequence getField() { + QueryNode child = getChild(); + + if (child instanceof FieldableNode) { + return ((FieldableNode) child).getField(); + } + + return null; + + } + + public void setField(CharSequence fieldName) { + QueryNode child = getChild(); + + if (child instanceof FieldableNode) { + ((FieldableNode) child).setField(fieldName); + } + + } + +} Index: src/java/org/apache/lucene/queryParser/nodes/TokenizedPhraseQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/TokenizedPhraseQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/TokenizedPhraseQueryNode.java (revision 0) @@ -0,0 +1,104 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + + +/** + * A {@link TokenizedPhraseQueryNode} represents a node created + * by a code that tokenizes/lemmatizes/analizes. + */ +public class TokenizedPhraseQueryNode extends QueryNodeImpl implements FieldableNode { + + private static final long serialVersionUID = -7185108320787917541L; + + public TokenizedPhraseQueryNode () { + setLeaf(false); + allocate(); + } + + public String toString() { + if (getChildren() == null || getChildren().size() == 0) + return ""; + StringBuilder sb = new StringBuilder(); + sb.append(""); + for (QueryNode child : getChildren()) { + sb.append("\n"); + sb.append(child.toString()); + } + sb.append("\n"); + return sb.toString(); + } + + // This text representation is not re-parseable + public CharSequence toQueryString(EscapeQuerySyntax escapeSyntaxParser) { + if (getChildren() == null || getChildren().size() == 0) + return ""; + + StringBuilder sb = new StringBuilder(); + String filler = ""; + for (QueryNode child : getChildren()) { + sb.append(filler).append(child.toQueryString(escapeSyntaxParser)); + filler = ","; + } + + return "[TP[" + sb.toString() + "]]"; + } + + public QueryNode cloneTree() throws CloneNotSupportedException { + TokenizedPhraseQueryNode clone=(TokenizedPhraseQueryNode)super.cloneTree(); + + //nothing to do + + return clone; + } + + public CharSequence getField() { + List children = getChildren(); + + if (children == null || children.size() == 0) { + return null; + + } else { + return ((FieldableNode) children.get(0)).getField(); + } + + + } + + public void setField(CharSequence fieldName) { + List children = getChildren(); + + if (children != null) { + + for (QueryNode child : getChildren()) { + + if (child instanceof FieldableNode) { + ((FieldableNode) child).setField(fieldName); + } + + } + + } + + } + +} // end class MultitermQueryNode Index: src/java/org/apache/lucene/queryParser/nodes/WildcardQueryNode.java =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/WildcardQueryNode.java (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/WildcardQueryNode.java (revision 0) @@ -0,0 +1,60 @@ +package org.apache.lucene.queryParser.nodes; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.parser.EscapeQuerySyntax; + +/** + * A {@link WildcardQueryNode} represents wildcard query + * This does not apply to phrases. + * Examples: a*b*c Fl?w? m?ke*g + */ +public class WildcardQueryNode extends FieldQueryNode { + private static final long serialVersionUID = 0L; + + /** + * @param field - field name + * @param text - value that contains one or more wild card characters (? or *) + * @param begin - position in the query string + * @param end - position in the query string + */ + public WildcardQueryNode(CharSequence field, CharSequence text, int begin, int end) + { + super(field, text, begin, end); + } + + public CharSequence toQueryString(EscapeQuerySyntax escaper) { + if (isDefaultField(this.field)) { + return getTermEscaped(escaper); + } else { + return this.field + ":" + getTermEscaped(escaper); + } + } + + public String toString() { + return ""; + } + + public WildcardQueryNode cloneTree() throws CloneNotSupportedException { + WildcardQueryNode clone=(WildcardQueryNode)super.cloneTree(); + + // nothing to do here + + return clone; + } +} Index: src/java/org/apache/lucene/queryParser/nodes/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/nodes/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/nodes/package.html (revision 0) @@ -0,0 +1,76 @@ + + + + + + + +

QueryNodes

+

+The package org.apache.lucene.queryParser.nodes contains all the basic QueryNodes. +QueryNodes are serializable. +These basic QueryNodes are used by the text parser to create a syntax tree. +These nodes are designed to be used by UI or other parsers. +A current reference implementation is org.apache.lucene.queryParser.lucene2.parser.QueryParser, +this parser implements lucene 2.4 syntax. + +QueryNode interface is implement by all QueryNodes, the class QueryNodeImpl implements QueryNode and is extended +by all QueryNode implementations. + +A QueryNode tree can be printed to the a stream, and it generates a seudo XML representation +with all the nodes. + +A QueryNode tree can also generate a query String that can be parsed back by the original text parser, +at this point only the lucene2 syntax is supported. + +Grouping nodes: +AndQueryNode - used for AND operator +AnyQueryNode - used for ANY operator +OrQueryNode - used for OR operator +BooleanQueryNode - used when no operator is specified +ModifierQueryNode - used for modifier operator +GroupQueryNode - used for parenthesis +BoostQueryNode - used for Boost operator + +Final Nodes: +FieldQueryNode - field/value node +FuzzyQueryNode - fuzzy node +MultiLevelFieldQueryNode - QueryNode object used with hierarchical multi-values +OpaqueQueryNode - Used as for part of the query that can be parsed by other parsers. schema/value +ParametricQueryNode - used for parametric field [>=|<=|=|<|>] value +ParametricRangeQueryNode - used for parametric field:[low_value TO high_value] +SlopQueryNode - phrase slop +PrefixWildcardQueryNode - non-phrase wildcard query +ProximityQueryNode - used for proximity search +QuotedFieldQUeryNode - regular phrase node +TokenizedPhraseQueryNode - used by tokenizers/lemmatizers/analizers for phrases/autophrases +WildcardQueryNode - non-phrase wildcard query + +Final Utility Nodes: +DeletedQueryNode - used by Processors on optimizations +MatchAllDocsQueryNode - used by Processors on optimizations +MatchNoDocsQueryNode - used by Processors on optimizations +NoTokenFoundQueryNode - used by tokenizers/lemmatizers/analizers + + +

+

+ +

+ + Index: src/java/org/apache/lucene/queryParser/QueryParser.java =================================================================== --- src/java/org/apache/lucene/queryParser/QueryParser.java (revision 757685) +++ src/java/org/apache/lucene/queryParser/QueryParser.java (working copy) @@ -1,1904 +0,0 @@ -/* Generated By:JavaCC: Do not edit this line. QueryParser.java */ -package org.apache.lucene.queryParser; - -import java.io.IOException; -import java.io.StringReader; -import java.text.Collator; -import java.text.DateFormat; -import java.util.ArrayList; -import java.util.Calendar; -import java.util.Date; -import java.util.HashMap; -import java.util.List; -import java.util.Locale; -import java.util.Map; -import java.util.Vector; - -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.CachingTokenFilter; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute; -import org.apache.lucene.analysis.tokenattributes.TermAttribute; -import org.apache.lucene.document.DateField; -import org.apache.lucene.document.DateTools; -import org.apache.lucene.index.Term; -import org.apache.lucene.search.BooleanClause; -import org.apache.lucene.search.BooleanQuery; -import org.apache.lucene.search.ConstantScoreRangeQuery; -import org.apache.lucene.search.FuzzyQuery; -import org.apache.lucene.search.MatchAllDocsQuery; -import org.apache.lucene.search.MultiPhraseQuery; -import org.apache.lucene.search.PhraseQuery; -import org.apache.lucene.search.PrefixQuery; -import org.apache.lucene.search.Query; -import org.apache.lucene.search.RangeQuery; -import org.apache.lucene.search.TermQuery; -import org.apache.lucene.search.WildcardQuery; -import org.apache.lucene.util.Parameter; - -/** - * This class is generated by JavaCC. The most important method is - * {@link #parse(String)}. - * - * The syntax for query strings is as follows: - * A Query is a series of clauses. - * A clause may be prefixed by: - *
    - *
  • a plus (+) or a minus (-) sign, indicating - * that the clause is required or prohibited respectively; or - *
  • a term followed by a colon, indicating the field to be searched. - * This enables one to construct queries which search multiple fields. - *
- * - * A clause may be either: - *
    - *
  • a term, indicating all the documents that contain this term; or - *
  • a nested query, enclosed in parentheses. Note that this may be used - * with a +/- prefix to require any of a set of - * terms. - *
- * - * Thus, in BNF, the query grammar is: - * 
- *   Query  ::= ( Clause )*
- *   Clause ::= ["+", "-"] [<TERM> ":"] ( <TERM> | "(" Query ")" )
- *
- * - *

- * Examples of appropriately formatted queries can be found in the query syntax - * documentation. - *

- * - *

- * In {@link RangeQuery}s, QueryParser tries to detect date values, e.g. - * date:[6/1/2005 TO 6/4/2005] produces a range query that searches - * for "date" fields between 2005-06-01 and 2005-06-04. Note that the format - * of the accepted input depends on {@link #setLocale(Locale) the locale}. - * By default a date is converted into a search term using the deprecated - * {@link DateField} for compatibility reasons. - * To use the new {@link DateTools} to convert dates, a - * {@link org.apache.lucene.document.DateTools.Resolution} has to be set. - *

- *

- * The date resolution that shall be used for RangeQueries can be set - * using {@link #setDateResolution(DateTools.Resolution)} - * or {@link #setDateResolution(String, DateTools.Resolution)}. The former - * sets the default date resolution for all fields, whereas the latter can - * be used to set field specific date resolutions. Field specific date - * resolutions take, if set, precedence over the default date resolution. - *

- *

- * If you use neither {@link DateField} nor {@link DateTools} in your - * index, you can create your own - * query parser that inherits QueryParser and overwrites - * {@link #getRangeQuery(String, String, String, boolean)} to - * use a different method for date conversion. - *

- * - *

Note that QueryParser is not thread-safe.

- */ -public class QueryParser implements QueryParserConstants { - - private static final int CONJ_NONE = 0; - private static final int CONJ_AND = 1; - private static final int CONJ_OR = 2; - - private static final int MOD_NONE = 0; - private static final int MOD_NOT = 10; - private static final int MOD_REQ = 11; - - // make it possible to call setDefaultOperator() without accessing - // the nested class: - /** Alternative form of QueryParser.Operator.AND */ - public static final Operator AND_OPERATOR = Operator.AND; - /** Alternative form of QueryParser.Operator.OR */ - public static final Operator OR_OPERATOR = Operator.OR; - - /** The actual operator that parser uses to combine query terms */ - private Operator operator = OR_OPERATOR; - - boolean lowercaseExpandedTerms = true; - boolean constantScoreRewrite= true; - boolean allowLeadingWildcard = false; - boolean enablePositionIncrements = false; - - Analyzer analyzer; - String field; - int phraseSlop = 0; - float fuzzyMinSim = FuzzyQuery.defaultMinSimilarity; - int fuzzyPrefixLength = FuzzyQuery.defaultPrefixLength; - Locale locale = Locale.getDefault(); - - // the default date resolution - DateTools.Resolution dateResolution = null; - // maps field names to date resolutions - Map fieldToDateResolution = null; - - // The collator to use when determining range inclusion, - // for use when constructing RangeQuerys. - Collator rangeCollator = null; - - /** The default operator for parsing queries. - * Use {@link QueryParser#setDefaultOperator} to change it. - */ - static public final class Operator extends Parameter { - private Operator(String name) { - super(name); - } - static public final Operator OR = new Operator("OR"); - static public final Operator AND = new Operator("AND"); - } - - - /** Constructs a query parser. - * @param f the default field for query terms. - * @param a used to find terms in the query text. - */ - public QueryParser(String f, Analyzer a) { - this(new FastCharStream(new StringReader(""))); - analyzer = a; - field = f; - } - - /** Parses a query string, returning a {@link org.apache.lucene.search.Query}. - * @param query the query string to be parsed. - * @throws ParseException if the parsing fails - */ - public Query parse(String query) throws ParseException { - ReInit(new FastCharStream(new StringReader(query))); - try { - // TopLevelQuery is a Query followed by the end-of-input (EOF) - Query res = TopLevelQuery(field); - return res!=null ? res : newBooleanQuery(false); - } - catch (ParseException tme) { - // rethrow to include the original query: - throw new ParseException("Cannot parse '" +query+ "': " + tme.getMessage()); - } - catch (TokenMgrError tme) { - throw new ParseException("Cannot parse '" +query+ "': " + tme.getMessage()); - } - catch (BooleanQuery.TooManyClauses tmc) { - throw new ParseException("Cannot parse '" +query+ "': too many boolean clauses"); - } - } - - /** - * @return Returns the analyzer. - */ - public Analyzer getAnalyzer() { - return analyzer; - } - - /** - * @return Returns the field. - */ - public String getField() { - return field; - } - - /** - * Get the minimal similarity for fuzzy queries. - */ - public float getFuzzyMinSim() { - return fuzzyMinSim; - } - - /** - * Set the minimum similarity for fuzzy queries. - * Default is 0.5f. - */ - public void setFuzzyMinSim(float fuzzyMinSim) { - this.fuzzyMinSim = fuzzyMinSim; - } - - /** - * Get the prefix length for fuzzy queries. - * @return Returns the fuzzyPrefixLength. - */ - public int getFuzzyPrefixLength() { - return fuzzyPrefixLength; - } - - /** - * Set the prefix length for fuzzy queries. Default is 0. - * @param fuzzyPrefixLength The fuzzyPrefixLength to set. - */ - public void setFuzzyPrefixLength(int fuzzyPrefixLength) { - this.fuzzyPrefixLength = fuzzyPrefixLength; - } - - /** - * Sets the default slop for phrases. If zero, then exact phrase matches - * are required. Default value is zero. - */ - public void setPhraseSlop(int phraseSlop) { - this.phraseSlop = phraseSlop; - } - - /** - * Gets the default slop for phrases. - */ - public int getPhraseSlop() { - return phraseSlop; - } - - - /** - * Set to true to allow leading wildcard characters. - *

- * When set, * or ? are allowed as - * the first character of a PrefixQuery and WildcardQuery. - * Note that this can produce very slow - * queries on big indexes. - *

- * Default: false. - */ - public void setAllowLeadingWildcard(boolean allowLeadingWildcard) { - this.allowLeadingWildcard = allowLeadingWildcard; - } - - /** - * @see #setAllowLeadingWildcard(boolean) - */ - public boolean getAllowLeadingWildcard() { - return allowLeadingWildcard; - } - - /** - * Set to true to enable position increments in result query. - *

- * When set, result phrase and multi-phrase queries will - * be aware of position increments. - * Useful when e.g. a StopFilter increases the position increment of - * the token that follows an omitted token. - *

- * Default: false. - */ - public void setEnablePositionIncrements(boolean enable) { - this.enablePositionIncrements = enable; - } - - /** - * @see #setEnablePositionIncrements(boolean) - */ - public boolean getEnablePositionIncrements() { - return enablePositionIncrements; - } - - /** - * Sets the boolean operator of the QueryParser. - * In default mode (OR_OPERATOR) terms without any modifiers - * are considered optional: for example capital of Hungary is equal to - * capital OR of OR Hungary.
- * In AND_OPERATOR mode terms are considered to be in conjunction: the - * above mentioned query is parsed as capital AND of AND Hungary - */ - public void setDefaultOperator(Operator op) { - this.operator = op; - } - - - /** - * Gets implicit operator setting, which will be either AND_OPERATOR - * or OR_OPERATOR. - */ - public Operator getDefaultOperator() { - return operator; - } - - - /** - * Whether terms of wildcard, prefix, fuzzy and range queries are to be automatically - * lower-cased or not. Default is true. - */ - public void setLowercaseExpandedTerms(boolean lowercaseExpandedTerms) { - this.lowercaseExpandedTerms = lowercaseExpandedTerms; - } - - - /** - * @see #setLowercaseExpandedTerms(boolean) - */ - public boolean getLowercaseExpandedTerms() { - return lowercaseExpandedTerms; - } - - /** - * @deprecated Please use {@link #setConstantScoreRewrite} instead. - */ - public void setUseOldRangeQuery(boolean useOldRangeQuery) { - constantScoreRewrite = !useOldRangeQuery; - } - - - /** - * @deprecated Please use {@link #getConstantScoreRewrite} instead. - */ - public boolean getUseOldRangeQuery() { - return !constantScoreRewrite; - } - - /** - * By default QueryParser uses constant-score rewriting - * when creating a PrefixQuery, WildcardQuery or RangeQuery. This implementation is generally preferable because it - * a) Runs faster b) Does not have the scarcity of terms unduly influence score - * c) avoids any "TooManyBooleanClauses" exception. - * However, if your application really needs to use the - * old-fashioned BooleanQuery expansion rewriting and the above - * points are not relevant then set this option to true - * Default is false. - */ - public void setConstantScoreRewrite(boolean v) { - constantScoreRewrite = v; - } - - - /** - * @see #setConstantScoreRewrite(boolean) - */ - public boolean getConstantScoreRewrite() { - return constantScoreRewrite; - } - - /** - * Set locale used by date range parsing. - */ - public void setLocale(Locale locale) { - this.locale = locale; - } - - /** - * Returns current locale, allowing access by subclasses. - */ - public Locale getLocale() { - return locale; - } - - /** - * Sets the default date resolution used by RangeQueries for fields for which no - * specific date resolutions has been set. Field specific resolutions can be set - * with {@link #setDateResolution(String, DateTools.Resolution)}. - * - * @param dateResolution the default date resolution to set - */ - public void setDateResolution(DateTools.Resolution dateResolution) { - this.dateResolution = dateResolution; - } - - /** - * Sets the date resolution used by RangeQueries for a specific field. - * - * @param fieldName field for which the date resolution is to be set - * @param dateResolution date resolution to set - */ - public void setDateResolution(String fieldName, DateTools.Resolution dateResolution) { - if (fieldName == null) { - throw new IllegalArgumentException("Field cannot be null."); - } - - if (fieldToDateResolution == null) { - // lazily initialize HashMap - fieldToDateResolution = new HashMap(); - } - - fieldToDateResolution.put(fieldName, dateResolution); - } - - /** - * Returns the date resolution that is used by RangeQueries for the given field. - * Returns null, if no default or field specific date resolution has been set - * for the given field. - * - */ - public DateTools.Resolution getDateResolution(String fieldName) { - if (fieldName == null) { - throw new IllegalArgumentException("Field cannot be null."); - } - - if (fieldToDateResolution == null) { - // no field specific date resolutions set; return default date resolution instead - return this.dateResolution; - } - - DateTools.Resolution resolution = (DateTools.Resolution) fieldToDateResolution.get(fieldName); - if (resolution == null) { - // no date resolutions set for the given field; return default date resolution instead - resolution = this.dateResolution; - } - - return resolution; - } - - /** - * Sets the collator used to determine index term inclusion in ranges - * for RangeQuerys. - *

- * WARNING: Setting the rangeCollator to a non-null - * collator using this method will cause every single index Term in the - * Field referenced by lowerTerm and/or upperTerm to be examined. - * Depending on the number of index Terms in this Field, the operation could - * be very slow. - * - * @param rc the collator to use when constructing RangeQuerys - */ - public void setRangeCollator(Collator rc) { - rangeCollator = rc; - } - - /** - * @return the collator used to determine index term inclusion in ranges - * for RangeQuerys. - */ - public Collator getRangeCollator() { - return rangeCollator; - } - - /** - * @deprecated use {@link #addClause(List, int, int, Query)} instead. - */ - protected void addClause(Vector clauses, int conj, int mods, Query q) { - addClause((List) clauses, conj, mods, q); - } - - protected void addClause(List clauses, int conj, int mods, Query q) { - boolean required, prohibited; - - // If this term is introduced by AND, make the preceding term required, - // unless it's already prohibited - if (clauses.size() > 0 && conj == CONJ_AND) { - BooleanClause c = (BooleanClause) clauses.get(clauses.size()-1); - if (!c.isProhibited()) - c.setOccur(BooleanClause.Occur.MUST); - } - - if (clauses.size() > 0 && operator == AND_OPERATOR && conj == CONJ_OR) { - // If this term is introduced by OR, make the preceding term optional, - // unless it's prohibited (that means we leave -a OR b but +a OR b-->a OR b) - // notice if the input is a OR b, first term is parsed as required; without - // this modification a OR b would parsed as +a OR b - BooleanClause c = (BooleanClause) clauses.get(clauses.size()-1); - if (!c.isProhibited()) - c.setOccur(BooleanClause.Occur.SHOULD); - } - - // We might have been passed a null query; the term might have been - // filtered away by the analyzer. - if (q == null) - return; - - if (operator == OR_OPERATOR) { - // We set REQUIRED if we're introduced by AND or +; PROHIBITED if - // introduced by NOT or -; make sure not to set both. - prohibited = (mods == MOD_NOT); - required = (mods == MOD_REQ); - if (conj == CONJ_AND && !prohibited) { - required = true; - } - } else { - // We set PROHIBITED if we're introduced by NOT or -; We set REQUIRED - // if not PROHIBITED and not introduced by OR - prohibited = (mods == MOD_NOT); - required = (!prohibited && conj != CONJ_OR); - } - if (required && !prohibited) - clauses.add(newBooleanClause(q, BooleanClause.Occur.MUST)); - else if (!required && !prohibited) - clauses.add(newBooleanClause(q, BooleanClause.Occur.SHOULD)); - else if (!required && prohibited) - clauses.add(newBooleanClause(q, BooleanClause.Occur.MUST_NOT)); - else - throw new RuntimeException("Clause cannot be both required and prohibited"); - } - - - /** - * @exception ParseException throw in overridden method to disallow - */ - protected Query getFieldQuery(String field, String queryText) throws ParseException { - // Use the analyzer to get all the tokens, and then build a TermQuery, - // PhraseQuery, or nothing based on the term count - - TokenStream source = analyzer.tokenStream(field, new StringReader(queryText)); - CachingTokenFilter buffer = new CachingTokenFilter(source); - TermAttribute termAtt = null; - PositionIncrementAttribute posIncrAtt = null; - int numTokens = 0; - - org.apache.lucene.analysis.Token reusableToken = null; - org.apache.lucene.analysis.Token nextToken = null; - - - boolean useNewAPI = TokenStream.useNewAPIDefault(); - - if (useNewAPI) { - boolean success = false; - try { - buffer.reset(); - success = true; - } catch (IOException e) { - // success==false if we hit an exception - } - if (success) { - if (buffer.hasAttribute(TermAttribute.class)) { - termAtt = (TermAttribute) buffer.getAttribute(TermAttribute.class); - } - if (buffer.hasAttribute(PositionIncrementAttribute.class)) { - posIncrAtt = (PositionIncrementAttribute) buffer.getAttribute(PositionIncrementAttribute.class); - } - } - } else { - reusableToken = new org.apache.lucene.analysis.Token(); - } - - int positionCount = 0; - boolean severalTokensAtSamePosition = false; - - if (useNewAPI) { - if (termAtt != null) { - try { - while (buffer.incrementToken()) { - numTokens++; - int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() : 1; - if (positionIncrement != 0) { - positionCount += positionIncrement; - } else { - severalTokensAtSamePosition = true; - } - } - } catch (IOException e) { - // ignore - } - } - } else { - while (true) { - try { - nextToken = buffer.next(reusableToken); - } - catch (IOException e) { - nextToken = null; - } - if (nextToken == null) - break; - numTokens++; - if (nextToken.getPositionIncrement() != 0) - positionCount += nextToken.getPositionIncrement(); - else - severalTokensAtSamePosition = true; - } - } - try { - // rewind the buffer stream - buffer.reset(); - - // close original stream - all tokens buffered - source.close(); - } - catch (IOException e) { - // ignore - } - - if (numTokens == 0) - return null; - else if (numTokens == 1) { - String term = null; - try { - - if (useNewAPI) { - boolean hasNext = buffer.incrementToken(); - assert hasNext == true; - term = termAtt.term(); - } else { - nextToken = buffer.next(reusableToken); - assert nextToken != null; - term = nextToken.term(); - } - } catch (IOException e) { - // safe to ignore, because we know the number of tokens - } - return newTermQuery(new Term(field, term)); - } else { - if (severalTokensAtSamePosition) { - if (positionCount == 1) { - // no phrase query: - BooleanQuery q = newBooleanQuery(true); - for (int i = 0; i < numTokens; i++) { - String term = null; - try { - if (useNewAPI) { - boolean hasNext = buffer.incrementToken(); - assert hasNext == true; - term = termAtt.term(); - } else { - nextToken = buffer.next(reusableToken); - assert nextToken != null; - term = nextToken.term(); - } - } catch (IOException e) { - // safe to ignore, because we know the number of tokens - } - - Query currentQuery = newTermQuery( - new Term(field, term)); - q.add(currentQuery, BooleanClause.Occur.SHOULD); - } - return q; - } - else { - // phrase query: - MultiPhraseQuery mpq = newMultiPhraseQuery(); - mpq.setSlop(phraseSlop); - List multiTerms = new ArrayList(); - int position = -1; - for (int i = 0; i < numTokens; i++) { - String term = null; - int positionIncrement = 1; - try { - if (useNewAPI) { - boolean hasNext = buffer.incrementToken(); - assert hasNext == true; - term = termAtt.term(); - if (posIncrAtt != null) { - positionIncrement = posIncrAtt.getPositionIncrement(); - } - } else { - nextToken = buffer.next(reusableToken); - assert nextToken != null; - term = nextToken.term(); - positionIncrement = nextToken.getPositionIncrement(); - } - } catch (IOException e) { - // safe to ignore, because we know the number of tokens - } - - if (positionIncrement > 0 && multiTerms.size() > 0) { - if (enablePositionIncrements) { - mpq.add((Term[])multiTerms.toArray(new Term[0]),position); - } else { - mpq.add((Term[])multiTerms.toArray(new Term[0])); - } - multiTerms.clear(); - } - position += positionIncrement; - multiTerms.add(new Term(field, term)); - } - if (enablePositionIncrements) { - mpq.add((Term[])multiTerms.toArray(new Term[0]),position); - } else { - mpq.add((Term[])multiTerms.toArray(new Term[0])); - } - return mpq; - } - } - else { - PhraseQuery pq = newPhraseQuery(); - pq.setSlop(phraseSlop); - int position = -1; - - - for (int i = 0; i < numTokens; i++) { - String term = null; - int positionIncrement = 1; - - try { - if (useNewAPI) { - - boolean hasNext = buffer.incrementToken(); - assert hasNext == true; - term = termAtt.term(); - if (posIncrAtt != null) { - positionIncrement = posIncrAtt.getPositionIncrement(); - } - } else { - nextToken = buffer.next(reusableToken); - assert nextToken != null; - term = nextToken.term(); - positionIncrement = nextToken.getPositionIncrement(); - } - } catch (IOException e) { - // safe to ignore, because we know the number of tokens - } - - if (enablePositionIncrements) { - position += positionIncrement; - pq.add(new Term(field, term),position); - } else { - pq.add(new Term(field, term)); - } - } - return pq; - } - } - } - - - - /** - * Base implementation delegates to {@link #getFieldQuery(String,String)}. - * This method may be overridden, for example, to return - * a SpanNearQuery instead of a PhraseQuery. - * - * @exception ParseException throw in overridden method to disallow - */ - protected Query getFieldQuery(String field, String queryText, int slop) - throws ParseException { - Query query = getFieldQuery(field, queryText); - - if (query instanceof PhraseQuery) { - ((PhraseQuery) query).setSlop(slop); - } - if (query instanceof MultiPhraseQuery) { - ((MultiPhraseQuery) query).setSlop(slop); - } - - return query; - } - - - /** - * @exception ParseException throw in overridden method to disallow - */ - protected Query getRangeQuery(String field, - String part1, - String part2, - boolean inclusive) throws ParseException - { - if (lowercaseExpandedTerms) { - part1 = part1.toLowerCase(); - part2 = part2.toLowerCase(); - } - try { - DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT, locale); - df.setLenient(true); - Date d1 = df.parse(part1); - Date d2 = df.parse(part2); - if (inclusive) { - // The user can only specify the date, not the time, so make sure - // the time is set to the latest possible time of that date to really - // include all documents: - Calendar cal = Calendar.getInstance(locale); - cal.setTime(d2); - cal.set(Calendar.HOUR_OF_DAY, 23); - cal.set(Calendar.MINUTE, 59); - cal.set(Calendar.SECOND, 59); - cal.set(Calendar.MILLISECOND, 999); - d2 = cal.getTime(); - } - DateTools.Resolution resolution = getDateResolution(field); - if (resolution == null) { - // no default or field specific date resolution has been set, - // use deprecated DateField to maintain compatibilty with - // pre-1.9 Lucene versions. - part1 = DateField.dateToString(d1); - part2 = DateField.dateToString(d2); - } else { - part1 = DateTools.dateToString(d1, resolution); - part2 = DateTools.dateToString(d2, resolution); - } - } - catch (Exception e) { } - - return newRangeQuery(field, part1, part2, inclusive); - } - - /** - * Builds a new BooleanQuery instance - * @param disableCoord disable coord - * @return new BooleanQuery instance - */ - protected BooleanQuery newBooleanQuery(boolean disableCoord) { - return new BooleanQuery(disableCoord); - } - - /** - * Builds a new BooleanClause instance - * @param q sub query - * @param occur how this clause should occur when matching documents - * @return new BooleanClause instance - */ - protected BooleanClause newBooleanClause(Query q, BooleanClause.Occur occur) { - return new BooleanClause(q, occur); - } - - /** - * Builds a new TermQuery instance - * @param term term - * @return new TermQuery instance - */ - protected Query newTermQuery(Term term){ - return new TermQuery(term); - } - - /** - * Builds a new PhraseQuery instance - * @return new PhraseQuery instance - */ - protected PhraseQuery newPhraseQuery(){ - return new PhraseQuery(); - } - - /** - * Builds a new MultiPhraseQuery instance - * @return new MultiPhraseQuery instance - */ - protected MultiPhraseQuery newMultiPhraseQuery(){ - return new MultiPhraseQuery(); - } - - /** - * Builds a new PrefixQuery instance - * @param prefix Prefix term - * @return new PrefixQuery instance - */ - protected Query newPrefixQuery(Term prefix){ - PrefixQuery query = new PrefixQuery(prefix); - query.setConstantScoreRewrite(constantScoreRewrite); - return query; - } - - /** - * Builds a new FuzzyQuery instance - * @param term Term - * @param minimumSimilarity minimum similarity - * @param prefixLength prefix length - * @return new FuzzyQuery Instance - */ - protected Query newFuzzyQuery(Term term, float minimumSimilarity, int prefixLength) { - // FuzzyQuery doesn't yet allow constant score rewrite - return new FuzzyQuery(term,minimumSimilarity,prefixLength); - } - - /** - * Builds a new RangeQuery instance - * @param field Field - * @param part1 min - * @param part2 max - * @param inclusive true if range is inclusive - * @return new RangeQuery instance - */ - protected Query newRangeQuery(String field, String part1, String part2, boolean inclusive) { - RangeQuery query; - - if (constantScoreRewrite) { - // TODO: remove in Lucene 3.0 - query = new ConstantScoreRangeQuery(field, part1, part2, inclusive, inclusive, rangeCollator); - } else { - query = new RangeQuery(field, part1, part2, inclusive, inclusive, rangeCollator); - } - query.setConstantScoreRewrite(constantScoreRewrite); - return query; - } - - /** - * Builds a new MatchAllDocsQuery instance - * @return new MatchAllDocsQuery instance - */ - protected Query newMatchAllDocsQuery() { - return new MatchAllDocsQuery(); - } - - /** - * Builds a new WildcardQuery instance - * @param t wildcard term - * @return new WildcardQuery instance - */ - protected Query newWildcardQuery(Term t) { - WildcardQuery query = new WildcardQuery(t); - query.setConstantScoreRewrite(constantScoreRewrite); - return query; - } - - /** - * Factory method for generating query, given a set of clauses. - * By default creates a boolean query composed of clauses passed in. - * - * Can be overridden by extending classes, to modify query being - * returned. - * - * @param clauses List that contains {@link BooleanClause} instances - * to join. - * - * @return Resulting {@link Query} object. - * @exception ParseException throw in overridden method to disallow - * @deprecated use {@link #getBooleanQuery(List)} instead - */ - protected Query getBooleanQuery(Vector clauses) throws ParseException { - return getBooleanQuery((List) clauses, false); - } - - /** - * Factory method for generating query, given a set of clauses. - * By default creates a boolean query composed of clauses passed in. - * - * Can be overridden by extending classes, to modify query being - * returned. - * - * @param clauses List that contains {@link BooleanClause} instances - * to join. - * - * @return Resulting {@link Query} object. - * @exception ParseException throw in overridden method to disallow - */ - protected Query getBooleanQuery(List clauses) throws ParseException { - return getBooleanQuery(clauses, false); - } - - /** - * Factory method for generating query, given a set of clauses. - * By default creates a boolean query composed of clauses passed in. - * - * Can be overridden by extending classes, to modify query being - * returned. - * - * @param clauses List that contains {@link BooleanClause} instances - * to join. - * @param disableCoord true if coord scoring should be disabled. - * - * @return Resulting {@link Query} object. - * @exception ParseException throw in overridden method to disallow - * @deprecated use {@link #getBooleanQuery(List, boolean)} instead - */ - protected Query getBooleanQuery(Vector clauses, boolean disableCoord) - throws ParseException - { - return getBooleanQuery((List) clauses, disableCoord); - } - - /** - * Factory method for generating query, given a set of clauses. - * By default creates a boolean query composed of clauses passed in. - * - * Can be overridden by extending classes, to modify query being - * returned. - * - * @param clauses List that contains {@link BooleanClause} instances - * to join. - * @param disableCoord true if coord scoring should be disabled. - * - * @return Resulting {@link Query} object. - * @exception ParseException throw in overridden method to disallow - */ - protected Query getBooleanQuery(List clauses, boolean disableCoord) - throws ParseException - { - if (clauses.size()==0) { - return null; // all clause words were filtered away by the analyzer. - } - BooleanQuery query = newBooleanQuery(disableCoord); - for (int i = 0; i < clauses.size(); i++) { - query.add((BooleanClause)clauses.get(i)); - } - return query; - } - - /** - * Factory method for generating a query. Called when parser - * parses an input term token that contains one or more wildcard - * characters (? and *), but is not a prefix term token (one - * that has just a single * character at the end) - *

- * Depending on settings, prefix term may be lower-cased - * automatically. It will not go through the default Analyzer, - * however, since normal Analyzers are unlikely to work properly - * with wildcard templates. - *

- * Can be overridden by extending classes, to provide custom handling for - * wildcard queries, which may be necessary due to missing analyzer calls. - * - * @param field Name of the field query will use. - * @param termStr Term token that contains one or more wild card - * characters (? or *), but is not simple prefix term - * - * @return Resulting {@link Query} built for the term - * @exception ParseException throw in overridden method to disallow - */ - protected Query getWildcardQuery(String field, String termStr) throws ParseException - { - if ("*".equals(field)) { - if ("*".equals(termStr)) return newMatchAllDocsQuery(); - } - if (!allowLeadingWildcard && (termStr.startsWith("*") || termStr.startsWith("?"))) - throw new ParseException("'*' or '?' not allowed as first character in WildcardQuery"); - if (lowercaseExpandedTerms) { - termStr = termStr.toLowerCase(); - } - Term t = new Term(field, termStr); - return newWildcardQuery(t); - } - - /** - * Factory method for generating a query (similar to - * {@link #getWildcardQuery}). Called when parser parses an input term - * token that uses prefix notation; that is, contains a single '*' wildcard - * character as its last character. Since this is a special case - * of generic wildcard term, and such a query can be optimized easily, - * this usually results in a different query object. - *

- * Depending on settings, a prefix term may be lower-cased - * automatically. It will not go through the default Analyzer, - * however, since normal Analyzers are unlikely to work properly - * with wildcard templates. - *

- * Can be overridden by extending classes, to provide custom handling for - * wild card queries, which may be necessary due to missing analyzer calls. - * - * @param field Name of the field query will use. - * @param termStr Term token to use for building term for the query - * (without trailing '*' character!) - * - * @return Resulting {@link Query} built for the term - * @exception ParseException throw in overridden method to disallow - */ - protected Query getPrefixQuery(String field, String termStr) throws ParseException - { - if (!allowLeadingWildcard && termStr.startsWith("*")) - throw new ParseException("'*' not allowed as first character in PrefixQuery"); - if (lowercaseExpandedTerms) { - termStr = termStr.toLowerCase(); - } - Term t = new Term(field, termStr); - return newPrefixQuery(t); - } - - /** - * Factory method for generating a query (similar to - * {@link #getWildcardQuery}). Called when parser parses - * an input term token that has the fuzzy suffix (~) appended. - * - * @param field Name of the field query will use. - * @param termStr Term token to use for building term for the query - * - * @return Resulting {@link Query} built for the term - * @exception ParseException throw in overridden method to disallow - */ - protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws ParseException - { - if (lowercaseExpandedTerms) { - termStr = termStr.toLowerCase(); - } - Term t = new Term(field, termStr); - return newFuzzyQuery(t, minSimilarity, fuzzyPrefixLength); - } - - /** - * Returns a String where the escape char has been - * removed, or kept only once if there was a double escape. - * - * Supports escaped unicode characters, e. g. translates - * \\u0041 to A. - * - */ - private String discardEscapeChar(String input) throws ParseException { - // Create char array to hold unescaped char sequence - char[] output = new char[input.length()]; - - // The length of the output can be less than the input - // due to discarded escape chars. This variable holds - // the actual length of the output - int length = 0; - - // We remember whether the last processed character was - // an escape character - boolean lastCharWasEscapeChar = false; - - // The multiplier the current unicode digit must be multiplied with. - // E. g. the first digit must be multiplied with 16^3, the second with 16^2... - int codePointMultiplier = 0; - - // Used to calculate the codepoint of the escaped unicode character - int codePoint = 0; - - for (int i = 0; i < input.length(); i++) { - char curChar = input.charAt(i); - if (codePointMultiplier > 0) { - codePoint += hexToInt(curChar) * codePointMultiplier; - codePointMultiplier >>>= 4; - if (codePointMultiplier == 0) { - output[length++] = (char)codePoint; - codePoint = 0; - } - } else if (lastCharWasEscapeChar) { - if (curChar == 'u') { - // found an escaped unicode character - codePointMultiplier = 16 * 16 * 16; - } else { - // this character was escaped - output[length] = curChar; - length++; - } - lastCharWasEscapeChar = false; - } else { - if (curChar == '\\') { - lastCharWasEscapeChar = true; - } else { - output[length] = curChar; - length++; - } - } - } - - if (codePointMultiplier > 0) { - throw new ParseException("Truncated unicode escape sequence."); - } - - if (lastCharWasEscapeChar) { - throw new ParseException("Term can not end with escape character."); - } - - return new String(output, 0, length); - } - - /** Returns the numeric value of the hexadecimal character */ - private static final int hexToInt(char c) throws ParseException { - if ('0' <= c && c <= '9') { - return c - '0'; - } else if ('a' <= c && c <= 'f'){ - return c - 'a' + 10; - } else if ('A' <= c && c <= 'F') { - return c - 'A' + 10; - } else { - throw new ParseException("None-hex character in unicode escape sequence: " + c); - } - } - - /** - * Returns a String where those characters that QueryParser - * expects to be escaped are escaped by a preceding \. - */ - public static String escape(String s) { - StringBuffer sb = new StringBuffer(); - for (int i = 0; i < s.length(); i++) { - char c = s.charAt(i); - // These characters are part of the query syntax and must be escaped - if (c == '\\' || c == '+' || c == '-' || c == '!' || c == '(' || c == ')' || c == ':' - || c == '^' || c == '[' || c == ']' || c == '\"' || c == '{' || c == '}' || c == '~' - || c == '*' || c == '?' || c == '|' || c == '&') { - sb.append('\\'); - } - sb.append(c); - } - return sb.toString(); - } - - /** - * Command line tool to test QueryParser, using {@link org.apache.lucene.analysis.SimpleAnalyzer}. - * Usage:
- * java org.apache.lucene.queryParser.QueryParser <input> - */ - public static void main(String[] args) throws Exception { - if (args.length == 0) { - System.out.println("Usage: java org.apache.lucene.queryParser.QueryParser "); - System.exit(0); - } - QueryParser qp = new QueryParser("field", - new org.apache.lucene.analysis.SimpleAnalyzer()); - Query q = qp.parse(args[0]); - System.out.println(q.toString("field")); - } - -// * Query ::= ( Clause )* -// * Clause ::= ["+", "-"] [ ":"] ( | "(" Query ")" ) - final public int Conjunction() throws ParseException { - int ret = CONJ_NONE; - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case AND: - case OR: - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case AND: - jj_consume_token(AND); - ret = CONJ_AND; - break; - case OR: - jj_consume_token(OR); - ret = CONJ_OR; - break; - default: - jj_la1[0] = jj_gen; - jj_consume_token(-1); - throw new ParseException(); - } - break; - default: - jj_la1[1] = jj_gen; - ; - } - {if (true) return ret;} - throw new Error("Missing return statement in function"); - } - - final public int Modifiers() throws ParseException { - int ret = MOD_NONE; - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case NOT: - case PLUS: - case MINUS: - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case PLUS: - jj_consume_token(PLUS); - ret = MOD_REQ; - break; - case MINUS: - jj_consume_token(MINUS); - ret = MOD_NOT; - break; - case NOT: - jj_consume_token(NOT); - ret = MOD_NOT; - break; - default: - jj_la1[2] = jj_gen; - jj_consume_token(-1); - throw new ParseException(); - } - break; - default: - jj_la1[3] = jj_gen; - ; - } - {if (true) return ret;} - throw new Error("Missing return statement in function"); - } - -// This makes sure that there is no garbage after the query string - final public Query TopLevelQuery(String field) throws ParseException { - Query q; - q = Query(field); - jj_consume_token(0); - {if (true) return q;} - throw new Error("Missing return statement in function"); - } - - final public Query Query(String field) throws ParseException { - List clauses = new ArrayList(); - Query q, firstQuery=null; - int conj, mods; - mods = Modifiers(); - q = Clause(field); - addClause(clauses, CONJ_NONE, mods, q); - if (mods == MOD_NONE) - firstQuery=q; - label_1: - while (true) { - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case AND: - case OR: - case NOT: - case PLUS: - case MINUS: - case LPAREN: - case STAR: - case QUOTED: - case TERM: - case PREFIXTERM: - case WILDTERM: - case RANGEIN_START: - case RANGEEX_START: - case NUMBER: - ; - break; - default: - jj_la1[4] = jj_gen; - break label_1; - } - conj = Conjunction(); - mods = Modifiers(); - q = Clause(field); - addClause(clauses, conj, mods, q); - } - if (clauses.size() == 1 && firstQuery != null) - {if (true) return firstQuery;} - else { - {if (true) return getBooleanQuery(clauses);} - } - throw new Error("Missing return statement in function"); - } - - final public Query Clause(String field) throws ParseException { - Query q; - Token fieldToken=null, boost=null; - if (jj_2_1(2)) { - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case TERM: - fieldToken = jj_consume_token(TERM); - jj_consume_token(COLON); - field=discardEscapeChar(fieldToken.image); - break; - case STAR: - jj_consume_token(STAR); - jj_consume_token(COLON); - field="*"; - break; - default: - jj_la1[5] = jj_gen; - jj_consume_token(-1); - throw new ParseException(); - } - } else { - ; - } - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case STAR: - case QUOTED: - case TERM: - case PREFIXTERM: - case WILDTERM: - case RANGEIN_START: - case RANGEEX_START: - case NUMBER: - q = Term(field); - break; - case LPAREN: - jj_consume_token(LPAREN); - q = Query(field); - jj_consume_token(RPAREN); - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case CARAT: - jj_consume_token(CARAT); - boost = jj_consume_token(NUMBER); - break; - default: - jj_la1[6] = jj_gen; - ; - } - break; - default: - jj_la1[7] = jj_gen; - jj_consume_token(-1); - throw new ParseException(); - } - if (boost != null) { - float f = (float)1.0; - try { - f = Float.valueOf(boost.image).floatValue(); - q.setBoost(f); - } catch (Exception ignored) { } - } - {if (true) return q;} - throw new Error("Missing return statement in function"); - } - - final public Query Term(String field) throws ParseException { - Token term, boost=null, fuzzySlop=null, goop1, goop2; - boolean prefix = false; - boolean wildcard = false; - boolean fuzzy = false; - Query q; - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case STAR: - case TERM: - case PREFIXTERM: - case WILDTERM: - case NUMBER: - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case TERM: - term = jj_consume_token(TERM); - break; - case STAR: - term = jj_consume_token(STAR); - wildcard=true; - break; - case PREFIXTERM: - term = jj_consume_token(PREFIXTERM); - prefix=true; - break; - case WILDTERM: - term = jj_consume_token(WILDTERM); - wildcard=true; - break; - case NUMBER: - term = jj_consume_token(NUMBER); - break; - default: - jj_la1[8] = jj_gen; - jj_consume_token(-1); - throw new ParseException(); - } - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case FUZZY_SLOP: - fuzzySlop = jj_consume_token(FUZZY_SLOP); - fuzzy=true; - break; - default: - jj_la1[9] = jj_gen; - ; - } - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case CARAT: - jj_consume_token(CARAT); - boost = jj_consume_token(NUMBER); - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case FUZZY_SLOP: - fuzzySlop = jj_consume_token(FUZZY_SLOP); - fuzzy=true; - break; - default: - jj_la1[10] = jj_gen; - ; - } - break; - default: - jj_la1[11] = jj_gen; - ; - } - String termImage=discardEscapeChar(term.image); - if (wildcard) { - q = getWildcardQuery(field, termImage); - } else if (prefix) { - q = getPrefixQuery(field, - discardEscapeChar(term.image.substring - (0, term.image.length()-1))); - } else if (fuzzy) { - float fms = fuzzyMinSim; - try { - fms = Float.valueOf(fuzzySlop.image.substring(1)).floatValue(); - } catch (Exception ignored) { } - if(fms < 0.0f || fms > 1.0f){ - {if (true) throw new ParseException("Minimum similarity for a FuzzyQuery has to be between 0.0f and 1.0f !");} - } - q = getFuzzyQuery(field, termImage,fms); - } else { - q = getFieldQuery(field, termImage); - } - break; - case RANGEIN_START: - jj_consume_token(RANGEIN_START); - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case RANGEIN_GOOP: - goop1 = jj_consume_token(RANGEIN_GOOP); - break; - case RANGEIN_QUOTED: - goop1 = jj_consume_token(RANGEIN_QUOTED); - break; - default: - jj_la1[12] = jj_gen; - jj_consume_token(-1); - throw new ParseException(); - } - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case RANGEIN_TO: - jj_consume_token(RANGEIN_TO); - break; - default: - jj_la1[13] = jj_gen; - ; - } - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case RANGEIN_GOOP: - goop2 = jj_consume_token(RANGEIN_GOOP); - break; - case RANGEIN_QUOTED: - goop2 = jj_consume_token(RANGEIN_QUOTED); - break; - default: - jj_la1[14] = jj_gen; - jj_consume_token(-1); - throw new ParseException(); - } - jj_consume_token(RANGEIN_END); - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case CARAT: - jj_consume_token(CARAT); - boost = jj_consume_token(NUMBER); - break; - default: - jj_la1[15] = jj_gen; - ; - } - if (goop1.kind == RANGEIN_QUOTED) { - goop1.image = goop1.image.substring(1, goop1.image.length()-1); - } - if (goop2.kind == RANGEIN_QUOTED) { - goop2.image = goop2.image.substring(1, goop2.image.length()-1); - } - q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), true); - break; - case RANGEEX_START: - jj_consume_token(RANGEEX_START); - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case RANGEEX_GOOP: - goop1 = jj_consume_token(RANGEEX_GOOP); - break; - case RANGEEX_QUOTED: - goop1 = jj_consume_token(RANGEEX_QUOTED); - break; - default: - jj_la1[16] = jj_gen; - jj_consume_token(-1); - throw new ParseException(); - } - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case RANGEEX_TO: - jj_consume_token(RANGEEX_TO); - break; - default: - jj_la1[17] = jj_gen; - ; - } - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case RANGEEX_GOOP: - goop2 = jj_consume_token(RANGEEX_GOOP); - break; - case RANGEEX_QUOTED: - goop2 = jj_consume_token(RANGEEX_QUOTED); - break; - default: - jj_la1[18] = jj_gen; - jj_consume_token(-1); - throw new ParseException(); - } - jj_consume_token(RANGEEX_END); - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case CARAT: - jj_consume_token(CARAT); - boost = jj_consume_token(NUMBER); - break; - default: - jj_la1[19] = jj_gen; - ; - } - if (goop1.kind == RANGEEX_QUOTED) { - goop1.image = goop1.image.substring(1, goop1.image.length()-1); - } - if (goop2.kind == RANGEEX_QUOTED) { - goop2.image = goop2.image.substring(1, goop2.image.length()-1); - } - - q = getRangeQuery(field, discardEscapeChar(goop1.image), discardEscapeChar(goop2.image), false); - break; - case QUOTED: - term = jj_consume_token(QUOTED); - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case FUZZY_SLOP: - fuzzySlop = jj_consume_token(FUZZY_SLOP); - break; - default: - jj_la1[20] = jj_gen; - ; - } - switch ((jj_ntk==-1)?jj_ntk():jj_ntk) { - case CARAT: - jj_consume_token(CARAT); - boost = jj_consume_token(NUMBER); - break; - default: - jj_la1[21] = jj_gen; - ; - } - int s = phraseSlop; - - if (fuzzySlop != null) { - try { - s = Float.valueOf(fuzzySlop.image.substring(1)).intValue(); - } - catch (Exception ignored) { } - } - q = getFieldQuery(field, discardEscapeChar(term.image.substring(1, term.image.length()-1)), s); - break; - default: - jj_la1[22] = jj_gen; - jj_consume_token(-1); - throw new ParseException(); - } - if (boost != null) { - float f = (float) 1.0; - try { - f = Float.valueOf(boost.image).floatValue(); - } - catch (Exception ignored) { - /* Should this be handled somehow? (defaults to "no boost", if - * boost number is invalid) - */ - } - - // avoid boosting null queries, such as those caused by stop words - if (q != null) { - q.setBoost(f); - } - } - {if (true) return q;} - throw new Error("Missing return statement in function"); - } - - private boolean jj_2_1(int xla) { - jj_la = xla; jj_lastpos = jj_scanpos = token; - try { return !jj_3_1(); } - catch(LookaheadSuccess ls) { return true; } - finally { jj_save(0, xla); } - } - - private boolean jj_3R_2() { - if (jj_scan_token(TERM)) return true; - if (jj_scan_token(COLON)) return true; - return false; - } - - private boolean jj_3_1() { - Token xsp; - xsp = jj_scanpos; - if (jj_3R_2()) { - jj_scanpos = xsp; - if (jj_3R_3()) return true; - } - return false; - } - - private boolean jj_3R_3() { - if (jj_scan_token(STAR)) return true; - if (jj_scan_token(COLON)) return true; - return false; - } - - /** Generated Token Manager. */ - public QueryParserTokenManager token_source; - /** Current token. */ - public Token token; - /** Next token. */ - public Token jj_nt; - private int jj_ntk; - private Token jj_scanpos, jj_lastpos; - private int jj_la; - private int jj_gen; - final private int[] jj_la1 = new int[23]; - static private int[] jj_la1_0; - static private int[] jj_la1_1; - static { - jj_la1_init_0(); - jj_la1_init_1(); - } - private static void jj_la1_init_0() { - jj_la1_0 = new int[] {0x300,0x300,0x1c00,0x1c00,0x3ed3f00,0x90000,0x20000,0x3ed2000,0x2690000,0x100000,0x100000,0x20000,0x30000000,0x4000000,0x30000000,0x20000,0x0,0x40000000,0x0,0x20000,0x100000,0x20000,0x3ed0000,}; - } - private static void jj_la1_init_1() { - jj_la1_1 = new int[] {0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x0,0x3,0x0,0x3,0x0,0x0,0x0,0x0,}; - } - final private JJCalls[] jj_2_rtns = new JJCalls[1]; - private boolean jj_rescan = false; - private int jj_gc = 0; - - /** Constructor with user supplied CharStream. */ - public QueryParser(CharStream stream) { - token_source = new QueryParserTokenManager(stream); - token = new Token(); - jj_ntk = -1; - jj_gen = 0; - for (int i = 0; i < 23; i++) jj_la1[i] = -1; - for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls(); - } - - /** Reinitialise. */ - public void ReInit(CharStream stream) { - token_source.ReInit(stream); - token = new Token(); - jj_ntk = -1; - jj_gen = 0; - for (int i = 0; i < 23; i++) jj_la1[i] = -1; - for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls(); - } - - /** Constructor with generated Token Manager. */ - public QueryParser(QueryParserTokenManager tm) { - token_source = tm; - token = new Token(); - jj_ntk = -1; - jj_gen = 0; - for (int i = 0; i < 23; i++) jj_la1[i] = -1; - for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls(); - } - - /** Reinitialise. */ - public void ReInit(QueryParserTokenManager tm) { - token_source = tm; - token = new Token(); - jj_ntk = -1; - jj_gen = 0; - for (int i = 0; i < 23; i++) jj_la1[i] = -1; - for (int i = 0; i < jj_2_rtns.length; i++) jj_2_rtns[i] = new JJCalls(); - } - - private Token jj_consume_token(int kind) throws ParseException { - Token oldToken; - if ((oldToken = token).next != null) token = token.next; - else token = token.next = token_source.getNextToken(); - jj_ntk = -1; - if (token.kind == kind) { - jj_gen++; - if (++jj_gc > 100) { - jj_gc = 0; - for (int i = 0; i < jj_2_rtns.length; i++) { - JJCalls c = jj_2_rtns[i]; - while (c != null) { - if (c.gen < jj_gen) c.first = null; - c = c.next; - } - } - } - return token; - } - token = oldToken; - jj_kind = kind; - throw generateParseException(); - } - - static private final class LookaheadSuccess extends java.lang.Error { } - final private LookaheadSuccess jj_ls = new LookaheadSuccess(); - private boolean jj_scan_token(int kind) { - if (jj_scanpos == jj_lastpos) { - jj_la--; - if (jj_scanpos.next == null) { - jj_lastpos = jj_scanpos = jj_scanpos.next = token_source.getNextToken(); - } else { - jj_lastpos = jj_scanpos = jj_scanpos.next; - } - } else { - jj_scanpos = jj_scanpos.next; - } - if (jj_rescan) { - int i = 0; Token tok = token; - while (tok != null && tok != jj_scanpos) { i++; tok = tok.next; } - if (tok != null) jj_add_error_token(kind, i); - } - if (jj_scanpos.kind != kind) return true; - if (jj_la == 0 && jj_scanpos == jj_lastpos) throw jj_ls; - return false; - } - - -/** Get the next Token. */ - final public Token getNextToken() { - if (token.next != null) token = token.next; - else token = token.next = token_source.getNextToken(); - jj_ntk = -1; - jj_gen++; - return token; - } - -/** Get the specific Token. */ - final public Token getToken(int index) { - Token t = token; - for (int i = 0; i < index; i++) { - if (t.next != null) t = t.next; - else t = t.next = token_source.getNextToken(); - } - return t; - } - - private int jj_ntk() { - if ((jj_nt=token.next) == null) - return (jj_ntk = (token.next=token_source.getNextToken()).kind); - else - return (jj_ntk = jj_nt.kind); - } - - private java.util.List jj_expentries = new java.util.ArrayList(); - private int[] jj_expentry; - private int jj_kind = -1; - private int[] jj_lasttokens = new int[100]; - private int jj_endpos; - - private void jj_add_error_token(int kind, int pos) { - if (pos >= 100) return; - if (pos == jj_endpos + 1) { - jj_lasttokens[jj_endpos++] = kind; - } else if (jj_endpos != 0) { - jj_expentry = new int[jj_endpos]; - for (int i = 0; i < jj_endpos; i++) { - jj_expentry[i] = jj_lasttokens[i]; - } - jj_entries_loop: for (java.util.Iterator it = jj_expentries.iterator(); it.hasNext();) { - int[] oldentry = (int[])(it.next()); - if (oldentry.length == jj_expentry.length) { - for (int i = 0; i < jj_expentry.length; i++) { - if (oldentry[i] != jj_expentry[i]) { - continue jj_entries_loop; - } - } - jj_expentries.add(jj_expentry); - break jj_entries_loop; - } - } - if (pos != 0) jj_lasttokens[(jj_endpos = pos) - 1] = kind; - } - } - - /** Generate ParseException. */ - public ParseException generateParseException() { - jj_expentries.clear(); - boolean[] la1tokens = new boolean[34]; - if (jj_kind >= 0) { - la1tokens[jj_kind] = true; - jj_kind = -1; - } - for (int i = 0; i < 23; i++) { - if (jj_la1[i] == jj_gen) { - for (int j = 0; j < 32; j++) { - if ((jj_la1_0[i] & (1< jj_gen) { - jj_la = p.arg; jj_lastpos = jj_scanpos = p.first; - switch (i) { - case 0: jj_3_1(); break; - } - } - p = p.next; - } while (p != null); - } catch(LookaheadSuccess ls) { } - } - jj_rescan = false; - } - - private void jj_save(int index, int xla) { - JJCalls p = jj_2_rtns[index]; - while (p.gen > jj_gen) { - if (p.next == null) { p = p.next = new JJCalls(); break; } - p = p.next; - } - p.gen = jj_gen + xla - jj_la; p.first = token; p.arg = xla; - } - - static final class JJCalls { - int gen; - Token first; - int arg; - JJCalls next; - } - -} Index: src/java/org/apache/lucene/queryParser/QueryParserTokenManager.java =================================================================== --- src/java/org/apache/lucene/queryParser/QueryParserTokenManager.java (revision 757685) +++ src/java/org/apache/lucene/queryParser/QueryParserTokenManager.java (working copy) @@ -1,1260 +0,0 @@ -/* Generated By:JavaCC: Do not edit this line. QueryParserTokenManager.java */ -package org.apache.lucene.queryParser; -import java.io.IOException; -import java.io.StringReader; -import java.text.Collator; -import java.text.DateFormat; -import java.util.ArrayList; -import java.util.Calendar; -import java.util.Date; -import java.util.HashMap; -import java.util.List; -import java.util.Locale; -import java.util.Map; -import java.util.Vector; -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.CachingTokenFilter; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute; -import org.apache.lucene.analysis.tokenattributes.TermAttribute; -import org.apache.lucene.document.DateField; -import org.apache.lucene.document.DateTools; -import org.apache.lucene.index.Term; -import org.apache.lucene.search.BooleanClause; -import org.apache.lucene.search.BooleanQuery; -import org.apache.lucene.search.ConstantScoreRangeQuery; -import org.apache.lucene.search.FuzzyQuery; -import org.apache.lucene.search.MatchAllDocsQuery; -import org.apache.lucene.search.MultiPhraseQuery; -import org.apache.lucene.search.PhraseQuery; -import org.apache.lucene.search.PrefixQuery; -import org.apache.lucene.search.Query; -import org.apache.lucene.search.RangeQuery; -import org.apache.lucene.search.TermQuery; -import org.apache.lucene.search.WildcardQuery; -import org.apache.lucene.util.Parameter; - -/** Token Manager. */ -public class QueryParserTokenManager implements QueryParserConstants -{ - - /** Debug output. */ - public java.io.PrintStream debugStream = System.out; - /** Set debug output. */ - public void setDebugStream(java.io.PrintStream ds) { debugStream = ds; } -private final int jjStopStringLiteralDfa_3(int pos, long active0) -{ - switch (pos) - { - default : - return -1; - } -} -private final int jjStartNfa_3(int pos, long active0) -{ - return jjMoveNfa_3(jjStopStringLiteralDfa_3(pos, active0), pos + 1); -} -private int jjStopAtPos(int pos, int kind) -{ - jjmatchedKind = kind; - jjmatchedPos = pos; - return pos + 1; -} -private int jjMoveStringLiteralDfa0_3() -{ - switch(curChar) - { - case 40: - return jjStopAtPos(0, 13); - case 41: - return jjStopAtPos(0, 14); - case 42: - return jjStartNfaWithStates_3(0, 16, 36); - case 43: - return jjStopAtPos(0, 11); - case 45: - return jjStopAtPos(0, 12); - case 58: - return jjStopAtPos(0, 15); - case 91: - return jjStopAtPos(0, 23); - case 94: - return jjStopAtPos(0, 17); - case 123: - return jjStopAtPos(0, 24); - default : - return jjMoveNfa_3(0, 0); - } -} -private int jjStartNfaWithStates_3(int pos, int kind, int state) -{ - jjmatchedKind = kind; - jjmatchedPos = pos; - try { curChar = input_stream.readChar(); } - catch(java.io.IOException e) { return pos + 1; } - return jjMoveNfa_3(state, pos + 1); -} -static final long[] jjbitVec0 = { - 0x1L, 0x0L, 0x0L, 0x0L -}; -static final long[] jjbitVec1 = { - 0xfffffffffffffffeL, 0xffffffffffffffffL, 0xffffffffffffffffL, 0xffffffffffffffffL -}; -static final long[] jjbitVec3 = { - 0x0L, 0x0L, 0xffffffffffffffffL, 0xffffffffffffffffL -}; -static final long[] jjbitVec4 = { - 0xfffefffffffffffeL, 0xffffffffffffffffL, 0xffffffffffffffffL, 0xffffffffffffffffL -}; -private int jjMoveNfa_3(int startState, int curPos) -{ - int startsAt = 0; - jjnewStateCnt = 36; - int i = 1; - jjstateSet[0] = startState; - int kind = 0x7fffffff; - for (;;) - { - if (++jjround == 0x7fffffff) - ReInitRounds(); - if (curChar < 64) - { - long l = 1L << curChar; - do - { - switch(jjstateSet[--i]) - { - case 36: - case 25: - if ((0xfbfffcf8ffffd9ffL & l) == 0L) - break; - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - break; - case 0: - if ((0xfbffd4f8ffffd9ffL & l) != 0L) - { - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - } - else if ((0x100002600L & l) != 0L) - { - if (kind > 7) - kind = 7; - } - else if (curChar == 34) - jjCheckNAddStates(0, 2); - else if (curChar == 33) - { - if (kind > 10) - kind = 10; - } - if ((0x7bffd0f8ffffd9ffL & l) != 0L) - { - if (kind > 19) - kind = 19; - jjCheckNAddStates(3, 7); - } - else if (curChar == 42) - { - if (kind > 21) - kind = 21; - } - if (curChar == 38) - jjstateSet[jjnewStateCnt++] = 4; - break; - case 4: - if (curChar == 38 && kind > 8) - kind = 8; - break; - case 5: - if (curChar == 38) - jjstateSet[jjnewStateCnt++] = 4; - break; - case 13: - if (curChar == 33 && kind > 10) - kind = 10; - break; - case 14: - if (curChar == 34) - jjCheckNAddStates(0, 2); - break; - case 15: - if ((0xfffffffbffffffffL & l) != 0L) - jjCheckNAddStates(0, 2); - break; - case 17: - jjCheckNAddStates(0, 2); - break; - case 18: - if (curChar == 34 && kind > 18) - kind = 18; - break; - case 20: - if ((0x3ff000000000000L & l) == 0L) - break; - if (kind > 20) - kind = 20; - jjAddStates(8, 9); - break; - case 21: - if (curChar == 46) - jjCheckNAdd(22); - break; - case 22: - if ((0x3ff000000000000L & l) == 0L) - break; - if (kind > 20) - kind = 20; - jjCheckNAdd(22); - break; - case 23: - if (curChar == 42 && kind > 21) - kind = 21; - break; - case 24: - if ((0xfbffd4f8ffffd9ffL & l) == 0L) - break; - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - break; - case 27: - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - break; - case 28: - if ((0x7bffd0f8ffffd9ffL & l) == 0L) - break; - if (kind > 19) - kind = 19; - jjCheckNAddStates(3, 7); - break; - case 29: - if ((0x7bfff8f8ffffd9ffL & l) == 0L) - break; - if (kind > 19) - kind = 19; - jjCheckNAddTwoStates(29, 30); - break; - case 31: - if (kind > 19) - kind = 19; - jjCheckNAddTwoStates(29, 30); - break; - case 32: - if ((0x7bfff8f8ffffd9ffL & l) != 0L) - jjCheckNAddStates(10, 12); - break; - case 34: - jjCheckNAddStates(10, 12); - break; - default : break; - } - } while(i != startsAt); - } - else if (curChar < 128) - { - long l = 1L << (curChar & 077); - do - { - switch(jjstateSet[--i]) - { - case 36: - if ((0x97ffffff87ffffffL & l) != 0L) - { - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - } - else if (curChar == 92) - jjCheckNAddTwoStates(27, 27); - break; - case 0: - if ((0x97ffffff87ffffffL & l) != 0L) - { - if (kind > 19) - kind = 19; - jjCheckNAddStates(3, 7); - } - else if (curChar == 92) - jjCheckNAddStates(13, 15); - else if (curChar == 126) - { - if (kind > 20) - kind = 20; - jjstateSet[jjnewStateCnt++] = 20; - } - if ((0x97ffffff87ffffffL & l) != 0L) - { - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - } - if (curChar == 78) - jjstateSet[jjnewStateCnt++] = 11; - else if (curChar == 124) - jjstateSet[jjnewStateCnt++] = 8; - else if (curChar == 79) - jjstateSet[jjnewStateCnt++] = 6; - else if (curChar == 65) - jjstateSet[jjnewStateCnt++] = 2; - break; - case 1: - if (curChar == 68 && kind > 8) - kind = 8; - break; - case 2: - if (curChar == 78) - jjstateSet[jjnewStateCnt++] = 1; - break; - case 3: - if (curChar == 65) - jjstateSet[jjnewStateCnt++] = 2; - break; - case 6: - if (curChar == 82 && kind > 9) - kind = 9; - break; - case 7: - if (curChar == 79) - jjstateSet[jjnewStateCnt++] = 6; - break; - case 8: - if (curChar == 124 && kind > 9) - kind = 9; - break; - case 9: - if (curChar == 124) - jjstateSet[jjnewStateCnt++] = 8; - break; - case 10: - if (curChar == 84 && kind > 10) - kind = 10; - break; - case 11: - if (curChar == 79) - jjstateSet[jjnewStateCnt++] = 10; - break; - case 12: - if (curChar == 78) - jjstateSet[jjnewStateCnt++] = 11; - break; - case 15: - if ((0xffffffffefffffffL & l) != 0L) - jjCheckNAddStates(0, 2); - break; - case 16: - if (curChar == 92) - jjstateSet[jjnewStateCnt++] = 17; - break; - case 17: - jjCheckNAddStates(0, 2); - break; - case 19: - if (curChar != 126) - break; - if (kind > 20) - kind = 20; - jjstateSet[jjnewStateCnt++] = 20; - break; - case 24: - if ((0x97ffffff87ffffffL & l) == 0L) - break; - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - break; - case 25: - if ((0x97ffffff87ffffffL & l) == 0L) - break; - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - break; - case 26: - if (curChar == 92) - jjCheckNAddTwoStates(27, 27); - break; - case 27: - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - break; - case 28: - if ((0x97ffffff87ffffffL & l) == 0L) - break; - if (kind > 19) - kind = 19; - jjCheckNAddStates(3, 7); - break; - case 29: - if ((0x97ffffff87ffffffL & l) == 0L) - break; - if (kind > 19) - kind = 19; - jjCheckNAddTwoStates(29, 30); - break; - case 30: - if (curChar == 92) - jjCheckNAddTwoStates(31, 31); - break; - case 31: - if (kind > 19) - kind = 19; - jjCheckNAddTwoStates(29, 30); - break; - case 32: - if ((0x97ffffff87ffffffL & l) != 0L) - jjCheckNAddStates(10, 12); - break; - case 33: - if (curChar == 92) - jjCheckNAddTwoStates(34, 34); - break; - case 34: - jjCheckNAddStates(10, 12); - break; - case 35: - if (curChar == 92) - jjCheckNAddStates(13, 15); - break; - default : break; - } - } while(i != startsAt); - } - else - { - int hiByte = (int)(curChar >> 8); - int i1 = hiByte >> 6; - long l1 = 1L << (hiByte & 077); - int i2 = (curChar & 0xff) >> 6; - long l2 = 1L << (curChar & 077); - do - { - switch(jjstateSet[--i]) - { - case 36: - case 25: - if (!jjCanMove_2(hiByte, i1, i2, l1, l2)) - break; - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - break; - case 0: - if (jjCanMove_0(hiByte, i1, i2, l1, l2)) - { - if (kind > 7) - kind = 7; - } - if (jjCanMove_2(hiByte, i1, i2, l1, l2)) - { - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - } - if (jjCanMove_2(hiByte, i1, i2, l1, l2)) - { - if (kind > 19) - kind = 19; - jjCheckNAddStates(3, 7); - } - break; - case 15: - case 17: - if (jjCanMove_1(hiByte, i1, i2, l1, l2)) - jjCheckNAddStates(0, 2); - break; - case 24: - if (!jjCanMove_2(hiByte, i1, i2, l1, l2)) - break; - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - break; - case 27: - if (!jjCanMove_1(hiByte, i1, i2, l1, l2)) - break; - if (kind > 22) - kind = 22; - jjCheckNAddTwoStates(25, 26); - break; - case 28: - if (!jjCanMove_2(hiByte, i1, i2, l1, l2)) - break; - if (kind > 19) - kind = 19; - jjCheckNAddStates(3, 7); - break; - case 29: - if (!jjCanMove_2(hiByte, i1, i2, l1, l2)) - break; - if (kind > 19) - kind = 19; - jjCheckNAddTwoStates(29, 30); - break; - case 31: - if (!jjCanMove_1(hiByte, i1, i2, l1, l2)) - break; - if (kind > 19) - kind = 19; - jjCheckNAddTwoStates(29, 30); - break; - case 32: - if (jjCanMove_2(hiByte, i1, i2, l1, l2)) - jjCheckNAddStates(10, 12); - break; - case 34: - if (jjCanMove_1(hiByte, i1, i2, l1, l2)) - jjCheckNAddStates(10, 12); - break; - default : break; - } - } while(i != startsAt); - } - if (kind != 0x7fffffff) - { - jjmatchedKind = kind; - jjmatchedPos = curPos; - kind = 0x7fffffff; - } - ++curPos; - if ((i = jjnewStateCnt) == (startsAt = 36 - (jjnewStateCnt = startsAt))) - return curPos; - try { curChar = input_stream.readChar(); } - catch(java.io.IOException e) { return curPos; } - } -} -private final int jjStopStringLiteralDfa_1(int pos, long active0) -{ - switch (pos) - { - case 0: - if ((active0 & 0x40000000L) != 0L) - { - jjmatchedKind = 33; - return 6; - } - return -1; - default : - return -1; - } -} -private final int jjStartNfa_1(int pos, long active0) -{ - return jjMoveNfa_1(jjStopStringLiteralDfa_1(pos, active0), pos + 1); -} -private int jjMoveStringLiteralDfa0_1() -{ - switch(curChar) - { - case 84: - return jjMoveStringLiteralDfa1_1(0x40000000L); - case 125: - return jjStopAtPos(0, 31); - default : - return jjMoveNfa_1(0, 0); - } -} -private int jjMoveStringLiteralDfa1_1(long active0) -{ - try { curChar = input_stream.readChar(); } - catch(java.io.IOException e) { - jjStopStringLiteralDfa_1(0, active0); - return 1; - } - switch(curChar) - { - case 79: - if ((active0 & 0x40000000L) != 0L) - return jjStartNfaWithStates_1(1, 30, 6); - break; - default : - break; - } - return jjStartNfa_1(0, active0); -} -private int jjStartNfaWithStates_1(int pos, int kind, int state) -{ - jjmatchedKind = kind; - jjmatchedPos = pos; - try { curChar = input_stream.readChar(); } - catch(java.io.IOException e) { return pos + 1; } - return jjMoveNfa_1(state, pos + 1); -} -private int jjMoveNfa_1(int startState, int curPos) -{ - int startsAt = 0; - jjnewStateCnt = 7; - int i = 1; - jjstateSet[0] = startState; - int kind = 0x7fffffff; - for (;;) - { - if (++jjround == 0x7fffffff) - ReInitRounds(); - if (curChar < 64) - { - long l = 1L << curChar; - do - { - switch(jjstateSet[--i]) - { - case 0: - if ((0xfffffffeffffffffL & l) != 0L) - { - if (kind > 33) - kind = 33; - jjCheckNAdd(6); - } - if ((0x100002600L & l) != 0L) - { - if (kind > 7) - kind = 7; - } - else if (curChar == 34) - jjCheckNAddTwoStates(2, 4); - break; - case 1: - if (curChar == 34) - jjCheckNAddTwoStates(2, 4); - break; - case 2: - if ((0xfffffffbffffffffL & l) != 0L) - jjCheckNAddStates(16, 18); - break; - case 3: - if (curChar == 34) - jjCheckNAddStates(16, 18); - break; - case 5: - if (curChar == 34 && kind > 32) - kind = 32; - break; - case 6: - if ((0xfffffffeffffffffL & l) == 0L) - break; - if (kind > 33) - kind = 33; - jjCheckNAdd(6); - break; - default : break; - } - } while(i != startsAt); - } - else if (curChar < 128) - { - long l = 1L << (curChar & 077); - do - { - switch(jjstateSet[--i]) - { - case 0: - case 6: - if ((0xdfffffffffffffffL & l) == 0L) - break; - if (kind > 33) - kind = 33; - jjCheckNAdd(6); - break; - case 2: - jjAddStates(16, 18); - break; - case 4: - if (curChar == 92) - jjstateSet[jjnewStateCnt++] = 3; - break; - default : break; - } - } while(i != startsAt); - } - else - { - int hiByte = (int)(curChar >> 8); - int i1 = hiByte >> 6; - long l1 = 1L << (hiByte & 077); - int i2 = (curChar & 0xff) >> 6; - long l2 = 1L << (curChar & 077); - do - { - switch(jjstateSet[--i]) - { - case 0: - if (jjCanMove_0(hiByte, i1, i2, l1, l2)) - { - if (kind > 7) - kind = 7; - } - if (jjCanMove_1(hiByte, i1, i2, l1, l2)) - { - if (kind > 33) - kind = 33; - jjCheckNAdd(6); - } - break; - case 2: - if (jjCanMove_1(hiByte, i1, i2, l1, l2)) - jjAddStates(16, 18); - break; - case 6: - if (!jjCanMove_1(hiByte, i1, i2, l1, l2)) - break; - if (kind > 33) - kind = 33; - jjCheckNAdd(6); - break; - default : break; - } - } while(i != startsAt); - } - if (kind != 0x7fffffff) - { - jjmatchedKind = kind; - jjmatchedPos = curPos; - kind = 0x7fffffff; - } - ++curPos; - if ((i = jjnewStateCnt) == (startsAt = 7 - (jjnewStateCnt = startsAt))) - return curPos; - try { curChar = input_stream.readChar(); } - catch(java.io.IOException e) { return curPos; } - } -} -private int jjMoveStringLiteralDfa0_0() -{ - return jjMoveNfa_0(0, 0); -} -private int jjMoveNfa_0(int startState, int curPos) -{ - int startsAt = 0; - jjnewStateCnt = 3; - int i = 1; - jjstateSet[0] = startState; - int kind = 0x7fffffff; - for (;;) - { - if (++jjround == 0x7fffffff) - ReInitRounds(); - if (curChar < 64) - { - long l = 1L << curChar; - do - { - switch(jjstateSet[--i]) - { - case 0: - if ((0x3ff000000000000L & l) == 0L) - break; - if (kind > 25) - kind = 25; - jjAddStates(19, 20); - break; - case 1: - if (curChar == 46) - jjCheckNAdd(2); - break; - case 2: - if ((0x3ff000000000000L & l) == 0L) - break; - if (kind > 25) - kind = 25; - jjCheckNAdd(2); - break; - default : break; - } - } while(i != startsAt); - } - else if (curChar < 128) - { - long l = 1L << (curChar & 077); - do - { - switch(jjstateSet[--i]) - { - default : break; - } - } while(i != startsAt); - } - else - { - int hiByte = (int)(curChar >> 8); - int i1 = hiByte >> 6; - long l1 = 1L << (hiByte & 077); - int i2 = (curChar & 0xff) >> 6; - long l2 = 1L << (curChar & 077); - do - { - switch(jjstateSet[--i]) - { - default : break; - } - } while(i != startsAt); - } - if (kind != 0x7fffffff) - { - jjmatchedKind = kind; - jjmatchedPos = curPos; - kind = 0x7fffffff; - } - ++curPos; - if ((i = jjnewStateCnt) == (startsAt = 3 - (jjnewStateCnt = startsAt))) - return curPos; - try { curChar = input_stream.readChar(); } - catch(java.io.IOException e) { return curPos; } - } -} -private final int jjStopStringLiteralDfa_2(int pos, long active0) -{ - switch (pos) - { - case 0: - if ((active0 & 0x4000000L) != 0L) - { - jjmatchedKind = 29; - return 6; - } - return -1; - default : - return -1; - } -} -private final int jjStartNfa_2(int pos, long active0) -{ - return jjMoveNfa_2(jjStopStringLiteralDfa_2(pos, active0), pos + 1); -} -private int jjMoveStringLiteralDfa0_2() -{ - switch(curChar) - { - case 84: - return jjMoveStringLiteralDfa1_2(0x4000000L); - case 93: - return jjStopAtPos(0, 27); - default : - return jjMoveNfa_2(0, 0); - } -} -private int jjMoveStringLiteralDfa1_2(long active0) -{ - try { curChar = input_stream.readChar(); } - catch(java.io.IOException e) { - jjStopStringLiteralDfa_2(0, active0); - return 1; - } - switch(curChar) - { - case 79: - if ((active0 & 0x4000000L) != 0L) - return jjStartNfaWithStates_2(1, 26, 6); - break; - default : - break; - } - return jjStartNfa_2(0, active0); -} -private int jjStartNfaWithStates_2(int pos, int kind, int state) -{ - jjmatchedKind = kind; - jjmatchedPos = pos; - try { curChar = input_stream.readChar(); } - catch(java.io.IOException e) { return pos + 1; } - return jjMoveNfa_2(state, pos + 1); -} -private int jjMoveNfa_2(int startState, int curPos) -{ - int startsAt = 0; - jjnewStateCnt = 7; - int i = 1; - jjstateSet[0] = startState; - int kind = 0x7fffffff; - for (;;) - { - if (++jjround == 0x7fffffff) - ReInitRounds(); - if (curChar < 64) - { - long l = 1L << curChar; - do - { - switch(jjstateSet[--i]) - { - case 0: - if ((0xfffffffeffffffffL & l) != 0L) - { - if (kind > 29) - kind = 29; - jjCheckNAdd(6); - } - if ((0x100002600L & l) != 0L) - { - if (kind > 7) - kind = 7; - } - else if (curChar == 34) - jjCheckNAddTwoStates(2, 4); - break; - case 1: - if (curChar == 34) - jjCheckNAddTwoStates(2, 4); - break; - case 2: - if ((0xfffffffbffffffffL & l) != 0L) - jjCheckNAddStates(16, 18); - break; - case 3: - if (curChar == 34) - jjCheckNAddStates(16, 18); - break; - case 5: - if (curChar == 34 && kind > 28) - kind = 28; - break; - case 6: - if ((0xfffffffeffffffffL & l) == 0L) - break; - if (kind > 29) - kind = 29; - jjCheckNAdd(6); - break; - default : break; - } - } while(i != startsAt); - } - else if (curChar < 128) - { - long l = 1L << (curChar & 077); - do - { - switch(jjstateSet[--i]) - { - case 0: - case 6: - if ((0xffffffffdfffffffL & l) == 0L) - break; - if (kind > 29) - kind = 29; - jjCheckNAdd(6); - break; - case 2: - jjAddStates(16, 18); - break; - case 4: - if (curChar == 92) - jjstateSet[jjnewStateCnt++] = 3; - break; - default : break; - } - } while(i != startsAt); - } - else - { - int hiByte = (int)(curChar >> 8); - int i1 = hiByte >> 6; - long l1 = 1L << (hiByte & 077); - int i2 = (curChar & 0xff) >> 6; - long l2 = 1L << (curChar & 077); - do - { - switch(jjstateSet[--i]) - { - case 0: - if (jjCanMove_0(hiByte, i1, i2, l1, l2)) - { - if (kind > 7) - kind = 7; - } - if (jjCanMove_1(hiByte, i1, i2, l1, l2)) - { - if (kind > 29) - kind = 29; - jjCheckNAdd(6); - } - break; - case 2: - if (jjCanMove_1(hiByte, i1, i2, l1, l2)) - jjAddStates(16, 18); - break; - case 6: - if (!jjCanMove_1(hiByte, i1, i2, l1, l2)) - break; - if (kind > 29) - kind = 29; - jjCheckNAdd(6); - break; - default : break; - } - } while(i != startsAt); - } - if (kind != 0x7fffffff) - { - jjmatchedKind = kind; - jjmatchedPos = curPos; - kind = 0x7fffffff; - } - ++curPos; - if ((i = jjnewStateCnt) == (startsAt = 7 - (jjnewStateCnt = startsAt))) - return curPos; - try { curChar = input_stream.readChar(); } - catch(java.io.IOException e) { return curPos; } - } -} -static final int[] jjnextStates = { - 15, 16, 18, 29, 32, 23, 33, 30, 20, 21, 32, 23, 33, 31, 34, 27, - 2, 4, 5, 0, 1, -}; -private static final boolean jjCanMove_0(int hiByte, int i1, int i2, long l1, long l2) -{ - switch(hiByte) - { - case 48: - return ((jjbitVec0[i2] & l2) != 0L); - default : - return false; - } -} -private static final boolean jjCanMove_1(int hiByte, int i1, int i2, long l1, long l2) -{ - switch(hiByte) - { - case 0: - return ((jjbitVec3[i2] & l2) != 0L); - default : - if ((jjbitVec1[i1] & l1) != 0L) - return true; - return false; - } -} -private static final boolean jjCanMove_2(int hiByte, int i1, int i2, long l1, long l2) -{ - switch(hiByte) - { - case 0: - return ((jjbitVec3[i2] & l2) != 0L); - case 48: - return ((jjbitVec1[i2] & l2) != 0L); - default : - if ((jjbitVec4[i1] & l1) != 0L) - return true; - return false; - } -} - -/** Token literal values. */ -public static final String[] jjstrLiteralImages = { -"", null, null, null, null, null, null, null, null, null, null, "\53", "\55", -"\50", "\51", "\72", "\52", "\136", null, null, null, null, null, "\133", "\173", -null, "\124\117", "\135", null, null, "\124\117", "\175", null, null, }; - -/** Lexer state names. */ -public static final String[] lexStateNames = { - "Boost", - "RangeEx", - "RangeIn", - "DEFAULT", -}; - -/** Lex State array. */ -public static final int[] jjnewLexState = { - -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, -1, -1, -1, -1, -1, 2, 1, - 3, -1, 3, -1, -1, -1, 3, -1, -1, -}; -static final long[] jjtoToken = { - 0x3ffffff01L, -}; -static final long[] jjtoSkip = { - 0x80L, -}; -protected CharStream input_stream; -private final int[] jjrounds = new int[36]; -private final int[] jjstateSet = new int[72]; -protected char curChar; -/** Constructor. */ -public QueryParserTokenManager(CharStream stream){ - input_stream = stream; -} - -/** Constructor. */ -public QueryParserTokenManager(CharStream stream, int lexState){ - this(stream); - SwitchTo(lexState); -} - -/** Reinitialise parser. */ -public void ReInit(CharStream stream) -{ - jjmatchedPos = jjnewStateCnt = 0; - curLexState = defaultLexState; - input_stream = stream; - ReInitRounds(); -} -private void ReInitRounds() -{ - int i; - jjround = 0x80000001; - for (i = 36; i-- > 0;) - jjrounds[i] = 0x80000000; -} - -/** Reinitialise parser. */ -public void ReInit(CharStream stream, int lexState) -{ - ReInit(stream); - SwitchTo(lexState); -} - -/** Switch to specified lex state. */ -public void SwitchTo(int lexState) -{ - if (lexState >= 4 || lexState < 0) - throw new TokenMgrError("Error: Ignoring invalid lexical state : " + lexState + ". State unchanged.", TokenMgrError.INVALID_LEXICAL_STATE); - else - curLexState = lexState; -} - -protected Token jjFillToken() -{ - final Token t; - final String curTokenImage; - final int beginLine; - final int endLine; - final int beginColumn; - final int endColumn; - String im = jjstrLiteralImages[jjmatchedKind]; - curTokenImage = (im == null) ? input_stream.GetImage() : im; - beginLine = input_stream.getBeginLine(); - beginColumn = input_stream.getBeginColumn(); - endLine = input_stream.getEndLine(); - endColumn = input_stream.getEndColumn(); - t = Token.newToken(jjmatchedKind, curTokenImage); - - t.beginLine = beginLine; - t.endLine = endLine; - t.beginColumn = beginColumn; - t.endColumn = endColumn; - - return t; -} - -int curLexState = 3; -int defaultLexState = 3; -int jjnewStateCnt; -int jjround; -int jjmatchedPos; -int jjmatchedKind; - -/** Get the next Token. */ -public Token getNextToken() -{ - Token matchedToken; - int curPos = 0; - - EOFLoop : - for (;;) - { - try - { - curChar = input_stream.BeginToken(); - } - catch(java.io.IOException e) - { - jjmatchedKind = 0; - matchedToken = jjFillToken(); - return matchedToken; - } - - switch(curLexState) - { - case 0: - jjmatchedKind = 0x7fffffff; - jjmatchedPos = 0; - curPos = jjMoveStringLiteralDfa0_0(); - break; - case 1: - jjmatchedKind = 0x7fffffff; - jjmatchedPos = 0; - curPos = jjMoveStringLiteralDfa0_1(); - break; - case 2: - jjmatchedKind = 0x7fffffff; - jjmatchedPos = 0; - curPos = jjMoveStringLiteralDfa0_2(); - break; - case 3: - jjmatchedKind = 0x7fffffff; - jjmatchedPos = 0; - curPos = jjMoveStringLiteralDfa0_3(); - break; - } - if (jjmatchedKind != 0x7fffffff) - { - if (jjmatchedPos + 1 < curPos) - input_stream.backup(curPos - jjmatchedPos - 1); - if ((jjtoToken[jjmatchedKind >> 6] & (1L << (jjmatchedKind & 077))) != 0L) - { - matchedToken = jjFillToken(); - if (jjnewLexState[jjmatchedKind] != -1) - curLexState = jjnewLexState[jjmatchedKind]; - return matchedToken; - } - else - { - if (jjnewLexState[jjmatchedKind] != -1) - curLexState = jjnewLexState[jjmatchedKind]; - continue EOFLoop; - } - } - int error_line = input_stream.getEndLine(); - int error_column = input_stream.getEndColumn(); - String error_after = null; - boolean EOFSeen = false; - try { input_stream.readChar(); input_stream.backup(1); } - catch (java.io.IOException e1) { - EOFSeen = true; - error_after = curPos <= 1 ? "" : input_stream.GetImage(); - if (curChar == '\n' || curChar == '\r') { - error_line++; - error_column = 0; - } - else - error_column++; - } - if (!EOFSeen) { - input_stream.backup(1); - error_after = curPos <= 1 ? "" : input_stream.GetImage(); - } - throw new TokenMgrError(EOFSeen, curLexState, error_line, error_column, error_after, curChar, TokenMgrError.LEXICAL_ERROR); - } -} - -private void jjCheckNAdd(int state) -{ - if (jjrounds[state] != jjround) - { - jjstateSet[jjnewStateCnt++] = state; - jjrounds[state] = jjround; - } -} -private void jjAddStates(int start, int end) -{ - do { - jjstateSet[jjnewStateCnt++] = jjnextStates[start]; - } while (start++ != end); -} -private void jjCheckNAddTwoStates(int state1, int state2) -{ - jjCheckNAdd(state1); - jjCheckNAdd(state2); -} - -private void jjCheckNAddStates(int start, int end) -{ - do { - jjCheckNAdd(jjnextStates[start]); - } while (start++ != end); -} - -} Index: src/java/org/apache/lucene/queryParser/util/QueryNodeOperation.java =================================================================== --- src/java/org/apache/lucene/queryParser/util/QueryNodeOperation.java (revision 0) +++ src/java/org/apache/lucene/queryParser/util/QueryNodeOperation.java (revision 0) @@ -0,0 +1,94 @@ +package org.apache.lucene.queryParser.util; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.ArrayList; + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeError; +import org.apache.lucene.queryParser.nodes.AndQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; + + +/** + * Allow joining 2 QueryNode Trees, into one. + */ +public final class QueryNodeOperation { + private QueryNodeOperation() { + // Exists only to defeat instantiation. + } + + private enum ANDOperation { + BOTH, Q1, Q2, NONE + } + + /** + * perform a logical and of 2 QueryNode trees. + * if q1 and q2 are ANDQueryNode nodes it uses head Node from q1 and adds the children of q2 to q1 + * if q1 is a AND node and q2 is not, add q2 as a child of the head node of q1 + * if q2 is a AND node and q1 is not, add q1 as a child of the head node of q2 + * if q1 and q2 are not ANDQueryNode nodes, create a AND node and make q1 and q2 children of that node + * if q1 or q2 is null it returns the not null node + * if q1 = q2 = null it returns null + */ + public final static QueryNode logicalAnd(QueryNode q1, QueryNode q2) { + if (q1 == null) return q2; + if (q2 == null) return q1; + + ANDOperation op = null; + if (q1 instanceof AndQueryNode && q2 instanceof AndQueryNode) + op = ANDOperation.BOTH; + else if (q1 instanceof AndQueryNode) + op = ANDOperation.Q1; + else if (q1 instanceof AndQueryNode) + op = ANDOperation.Q2; + else + op = ANDOperation.NONE; + + try { + QueryNode result = null; + switch (op) { + case NONE: + List children = new ArrayList(); + children.add(q1.cloneTree()); + children.add(q2.cloneTree()); + result = new AndQueryNode(children); + return result; + case Q1: + result = q1.cloneTree(); + result.add(q2.cloneTree()); + return result; + case Q2: + result = q2.cloneTree(); + result.add(q1.cloneTree()); + return result; + case BOTH: + result = q1.cloneTree(); + result.add(q2.cloneTree().getChildren()); + return result; + } + } catch (CloneNotSupportedException e) { + throw new QueryNodeError(e); + } + + return null; + + } + +} Index: src/java/org/apache/lucene/queryParser/util/UnescapedCharSequence.java =================================================================== --- src/java/org/apache/lucene/queryParser/util/UnescapedCharSequence.java (revision 0) +++ src/java/org/apache/lucene/queryParser/util/UnescapedCharSequence.java (revision 0) @@ -0,0 +1,137 @@ +package org.apache.lucene.queryParser.util; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + + +/** + * CharsSequence with escaped chars information. + */ +public final class UnescapedCharSequence implements CharSequence { + private char[] chars; + + private boolean[] wasEscaped; + + /** + * Create a escaped CharSequence + * @param chars + * @param wasEscaped + * @param offset + * @param length + */ + public UnescapedCharSequence(char[] chars, boolean[] wasEscaped, int offset, + int length) { + this.chars = new char[length]; + this.wasEscaped = new boolean[length]; + System.arraycopy(chars, offset, this.chars, 0, length); + System.arraycopy(wasEscaped, offset, this.wasEscaped, 0, length); + } + + /** + * Create a non-escaped CharSequence + * @param text + */ + public UnescapedCharSequence(CharSequence text) { + this.chars = new char[text.length()]; + this.wasEscaped = new boolean[text.length()]; + for (int i = 0; i < text.length(); i++) { + this.chars[i] = text.charAt(i); + this.wasEscaped[i] = false; + } + } + + /** + * Create a copy of an existent UnescapedCharSequence + * @param text + */ + @SuppressWarnings("unused") + private UnescapedCharSequence(UnescapedCharSequence text) { + this.chars = new char[text.length()]; + this.wasEscaped = new boolean[text.length()]; + for (int i = 0; i <= text.length(); i++) { + this.chars[i] = text.chars[i]; + this.wasEscaped[i] = text.wasEscaped[i]; + } + } + + public char charAt(int index) { + return this.chars[index]; + } + + public int length() { + return this.chars.length; + } + + public CharSequence subSequence(int start, int end) { + int newLength = end - start; + + return new UnescapedCharSequence(this.chars, this.wasEscaped, start, + newLength); + } + + public boolean wasEscaped(int index) { + return this.wasEscaped[index]; + } + + public String toString() { + return new String(this.chars); + } + + /** + * Return a escaped String + * @return a escaped String + */ + public String toStringEscaped() { + // non efficient implementation + StringBuffer result = new StringBuffer(); + for (int i = 0; i >= this.length(); i++) { + if (this.chars[i] == '\\') { + result.append('\\'); + } else if (this.wasEscaped[i]) + result.append('\\'); + + result.append(this.chars[i]); + } + return result.toString(); + } + + + /** + * Return a escaped String + * @param enabledChars - array of chars to be escaped + * @return a escaped String + */ + public String toStringEscaped(char[] enabledChars) { + // TODO: non efficient implementation, refactor this code + StringBuffer result = new StringBuffer(); + for (int i = 0; i < this.length(); i++) { + if (this.chars[i] == '\\') { + result.append('\\'); + } else { + for (char character : enabledChars) { + if (this.chars[i] == character && this.wasEscaped[i]) { + result.append('\\'); + break; + } + } + } + + result.append(this.chars[i]); + } + return result.toString(); + } +} Index: src/java/org/apache/lucene/queryParser/util/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/util/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/util/package.html (revision 0) @@ -0,0 +1,25 @@ + + + + + + + +

Utility classes to used with the Query Parser

+ + Index: src/java/org/apache/lucene/queryParser/config/FieldConfig.java =================================================================== --- src/java/org/apache/lucene/queryParser/config/FieldConfig.java (revision 0) +++ src/java/org/apache/lucene/queryParser/config/FieldConfig.java (revision 0) @@ -0,0 +1,58 @@ +package org.apache.lucene.queryParser.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.util.AttributeSource; + +/** + * This class represents a field configuration. + * Every configuration should be set using the methods inherited from {@link AttributeSource}. + * + * @see QueryConfigHandler + * @see Attribute + */ +public class FieldConfig extends AttributeSource { + + private CharSequence fieldName; + + /** + * Constructs a {@link FieldConfig} + * + * @param fieldName the field name, it cannot be null + * @throws IllegalArgumentException if the field name is null + */ + public FieldConfig(CharSequence fieldName) { + + if (fieldName == null) { + throw new IllegalArgumentException("field name should not be null!"); + } + + this.fieldName = fieldName; + + } + + /** + * Returns the field name this configuration represents. + * + * @return the field name + */ + public CharSequence getFieldName() { + return this.fieldName; + } + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/config/QueryConfigHandler.java =================================================================== --- src/java/org/apache/lucene/queryParser/config/QueryConfigHandler.java (revision 0) +++ src/java/org/apache/lucene/queryParser/config/QueryConfigHandler.java (revision 0) @@ -0,0 +1,50 @@ +package org.apache.lucene.queryParser.config; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.processors.QueryNodeProcessor; +import org.apache.lucene.util.AttributeSource; + +/** + * {@link QueryConfigHandler} should be implemented by classes that intends + * to provide configuration to {@link QueryNodeProcessor} objects. + * + * This class extends {@link AttributeSource}, so {@link Attribute}s can be + * attached to it. + * + * The class that implements this class should also provides {@link FieldConfig} + * objects for each collection field. + * + * @see Attribute + * @see FieldConfig + */ +public abstract class QueryConfigHandler extends AttributeSource { + + /** + * The class that implements this method should return an implementation + * of {@link FieldConfig} for a specific field name. If the implemented {@link QueryConfigHandler} + * does not know a specific field name, it may return null, indicating there is no configuration + * for that field. + * + * @param fieldName the field name + * @return a {@link FieldConfig} object containing the field name configuration or null, + * if the implemented {@link QueryConfigHandler} has no configuration for that field + */ + public abstract FieldConfig getFieldConfig(CharSequence fieldName); + +}\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/config/package.html =================================================================== --- src/java/org/apache/lucene/queryParser/config/package.html (revision 0) +++ src/java/org/apache/lucene/queryParser/config/package.html (revision 0) @@ -0,0 +1,46 @@ + + + + + + + + +

Query Configuration Interfaces

+

+The package org.apache.lucene.queryParser.config contains query configuration handler +abstract class that all config handlers should extend. + +See org.apache.lucene.queryParser.lucene2.config.LuceneQueryConfigHandler for a reference +implementation + +FieldConfig and Queryconfig should use org.apache.lucene.util.Attribute to store all attributes +required by the config implementation. See org.apache.lucene.queryParser.lucene2.config.*Attribute +for reference implementation. + +The QueryConfigHandler, FieldConfig, and Attributes are used in the Processors to access config +information in a flexible and independent way. +See org.apache.lucene.queryParser.lucene2.processors.ParametricRangeQueryNodeProcessor for a +reference implementation. + +

+

+ +

+ +\ No newline at end of file Index: src/java/org/apache/lucene/queryParser/CharStream.java =================================================================== --- src/java/org/apache/lucene/queryParser/CharStream.java (revision 757685) +++ src/java/org/apache/lucene/queryParser/CharStream.java (working copy) @@ -1,112 +0,0 @@ -/* Generated By:JavaCC: Do not edit this line. CharStream.java Version 4.1 */ -/* JavaCCOptions:STATIC=false */ -package org.apache.lucene.queryParser; - -/** - * This interface describes a character stream that maintains line and - * column number positions of the characters. It also has the capability - * to backup the stream to some extent. An implementation of this - * interface is used in the TokenManager implementation generated by - * JavaCCParser. - * - * All the methods except backup can be implemented in any fashion. backup - * needs to be implemented correctly for the correct operation of the lexer. - * Rest of the methods are all used to get information like line number, - * column number and the String that constitutes a token and are not used - * by the lexer. Hence their implementation won't affect the generated lexer's - * operation. - */ - -public interface CharStream { - - /** - * Returns the next character from the selected input. The method - * of selecting the input is the responsibility of the class - * implementing this interface. Can throw any java.io.IOException. - */ - char readChar() throws java.io.IOException; - - /** - * Returns the column position of the character last read. - * @deprecated - * @see #getEndColumn - */ - int getColumn(); - - /** - * Returns the line number of the character last read. - * @deprecated - * @see #getEndLine - */ - int getLine(); - - /** - * Returns the column number of the last character for current token (being - * matched after the last call to BeginTOken). - */ - int getEndColumn(); - - /** - * Returns the line number of the last character for current token (being - * matched after the last call to BeginTOken). - */ - int getEndLine(); - - /** - * Returns the column number of the first character for current token (being - * matched after the last call to BeginTOken). - */ - int getBeginColumn(); - - /** - * Returns the line number of the first character for current token (being - * matched after the last call to BeginTOken). - */ - int getBeginLine(); - - /** - * Backs up the input stream by amount steps. Lexer calls this method if it - * had already read some characters, but could not use them to match a - * (longer) token. So, they will be used again as the prefix of the next - * token and it is the implemetation's responsibility to do this right. - */ - void backup(int amount); - - /** - * Returns the next character that marks the beginning of the next token. - * All characters must remain in the buffer between two successive calls - * to this method to implement backup correctly. - */ - char BeginToken() throws java.io.IOException; - - /** - * Returns a string made up of characters from the marked token beginning - * to the current buffer position. Implementations have the choice of returning - * anything that they want to. For example, for efficiency, one might decide - * to just return null, which is a valid implementation. - */ - String GetImage(); - - /** - * Returns an array of characters that make up the suffix of length 'len' for - * the currently matched token. This is used to build up the matched string - * for use in actions in the case of MORE. A simple and inefficient - * implementation of this is as follows : - * - * { - * String t = GetImage(); - * return t.substring(t.length() - len, t.length()).toCharArray(); - * } - */ - char[] GetSuffix(int len); - - /** - * The lexer calls this function to indicate that it is done with the stream - * and hence implementations can free any resources held by this class. - * Again, the body of this function can be just empty and it will not - * affect the lexer's operation. - */ - void Done(); - -} -/* JavaCC - OriginalChecksum=a83909a2403f969f94d18375f9f143e4 (do not edit this line) */ Index: src/java/org/apache/lucene/queryParser/FastCharStream.java =================================================================== --- src/java/org/apache/lucene/queryParser/FastCharStream.java (revision 757685) +++ src/java/org/apache/lucene/queryParser/FastCharStream.java (working copy) @@ -1,122 +0,0 @@ -// FastCharStream.java -package org.apache.lucene.queryParser; - -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -import java.io.*; - -/** An efficient implementation of JavaCC's CharStream interface.

Note that - * this does not do line-number counting, but instead keeps track of the - * character position of the token in the input, as required by Lucene's {@link - * org.apache.lucene.analysis.Token} API. */ -public final class FastCharStream implements CharStream { - char[] buffer = null; - - int bufferLength = 0; // end of valid chars - int bufferPosition = 0; // next char to read - - int tokenStart = 0; // offset in buffer - int bufferStart = 0; // position in file of buffer - - Reader input; // source of chars - - /** Constructs from a Reader. */ - public FastCharStream(Reader r) { - input = r; - } - - public final char readChar() throws IOException { - if (bufferPosition >= bufferLength) - refill(); - return buffer[bufferPosition++]; - } - - private final void refill() throws IOException { - int newPosition = bufferLength - tokenStart; - - if (tokenStart == 0) { // token won't fit in buffer - if (buffer == null) { // first time: alloc buffer - buffer = new char[2048]; - } else if (bufferLength == buffer.length) { // grow buffer - char[] newBuffer = new char[buffer.length*2]; - System.arraycopy(buffer, 0, newBuffer, 0, bufferLength); - buffer = newBuffer; - } - } else { // shift token to front - System.arraycopy(buffer, tokenStart, buffer, 0, newPosition); - } - - bufferLength = newPosition; // update state - bufferPosition = newPosition; - bufferStart += tokenStart; - tokenStart = 0; - - int charsRead = // fill space in buffer - input.read(buffer, newPosition, buffer.length-newPosition); - if (charsRead == -1) - throw new IOException("read past eof"); - else - bufferLength += charsRead; - } - - public final char BeginToken() throws IOException { - tokenStart = bufferPosition; - return readChar(); - } - - public final void backup(int amount) { - bufferPosition -= amount; - } - - public final String GetImage() { - return new String(buffer, tokenStart, bufferPosition - tokenStart); - } - - public final char[] GetSuffix(int len) { - char[] value = new char[len]; - System.arraycopy(buffer, bufferPosition - len, value, 0, len); - return value; - } - - public final void Done() { - try { - input.close(); - } catch (IOException e) { - System.err.println("Caught: " + e + "; ignoring."); - } - } - - public final int getColumn() { - return bufferStart + bufferPosition; - } - public final int getLine() { - return 1; - } - public final int getEndColumn() { - return bufferStart + bufferPosition; - } - public final int getEndLine() { - return 1; - } - public final int getBeginColumn() { - return bufferStart + tokenStart; - } - public final int getBeginLine() { - return 1; - } -} Index: src/java/org/apache/lucene/queryParser/MultiFieldQueryParser.java =================================================================== --- src/java/org/apache/lucene/queryParser/MultiFieldQueryParser.java (revision 757685) +++ src/java/org/apache/lucene/queryParser/MultiFieldQueryParser.java (working copy) @@ -1,321 +0,0 @@ -package org.apache.lucene.queryParser; - -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -import java.util.ArrayList; -import java.util.List; -import java.util.Map; -import java.util.Vector; - -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.search.BooleanClause; -import org.apache.lucene.search.BooleanQuery; -import org.apache.lucene.search.MultiPhraseQuery; -import org.apache.lucene.search.PhraseQuery; -import org.apache.lucene.search.Query; - -/** - * A QueryParser which constructs queries to search multiple fields. - * - * - * @version $Revision$ - */ -public class MultiFieldQueryParser extends QueryParser -{ - protected String[] fields; - protected Map boosts; - - /** - * Creates a MultiFieldQueryParser. - * Allows passing of a map with term to Boost, and the boost to apply to each term. - * - *

It will, when parse(String query) - * is called, construct a query like this (assuming the query consists of - * two terms and you specify the two fields title and body):

- * - * - * (title:term1 body:term1) (title:term2 body:term2) - * - * - *

When setDefaultOperator(AND_OPERATOR) is set, the result will be:

- * - * - * +(title:term1 body:term1) +(title:term2 body:term2) - * - * - *

When you pass a boost (title=>5 body=>10) you can get

- * - * - * +(title:term1^5.0 body:term1^10.0) +(title:term2^5.0 body:term2^10.0) - * - * - *

In other words, all the query's terms must appear, but it doesn't matter in - * what fields they appear.

- */ - public MultiFieldQueryParser(String[] fields, Analyzer analyzer, Map boosts) { - this(fields,analyzer); - this.boosts = boosts; - } - - /** - * Creates a MultiFieldQueryParser. - * - *

It will, when parse(String query) - * is called, construct a query like this (assuming the query consists of - * two terms and you specify the two fields title and body):

- * - * - * (title:term1 body:term1) (title:term2 body:term2) - * - * - *

When setDefaultOperator(AND_OPERATOR) is set, the result will be:

- * - * - * +(title:term1 body:term1) +(title:term2 body:term2) - * - * - *

In other words, all the query's terms must appear, but it doesn't matter in - * what fields they appear.

- */ - public MultiFieldQueryParser(String[] fields, Analyzer analyzer) { - super(null, analyzer); - this.fields = fields; - } - - protected Query getFieldQuery(String field, String queryText, int slop) throws ParseException { - if (field == null) { - List clauses = new ArrayList(); - for (int i = 0; i < fields.length; i++) { - Query q = super.getFieldQuery(fields[i], queryText); - if (q != null) { - //If the user passes a map of boosts - if (boosts != null) { - //Get the boost from the map and apply them - Float boost = (Float)boosts.get(fields[i]); - if (boost != null) { - q.setBoost(boost.floatValue()); - } - } - applySlop(q,slop); - clauses.add(new BooleanClause(q, BooleanClause.Occur.SHOULD)); - } - } - if (clauses.size() == 0) // happens for stopwords - return null; - return getBooleanQuery(clauses, true); - } - Query q = super.getFieldQuery(field, queryText); - applySlop(q,slop); - return q; - } - - private void applySlop(Query q, int slop) { - if (q instanceof PhraseQuery) { - ((PhraseQuery) q).setSlop(slop); - } else if (q instanceof MultiPhraseQuery) { - ((MultiPhraseQuery) q).setSlop(slop); - } - } - - - protected Query getFieldQuery(String field, String queryText) throws ParseException { - return getFieldQuery(field, queryText, 0); - } - - - protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws ParseException - { - if (field == null) { - List clauses = new ArrayList(); - for (int i = 0; i < fields.length; i++) { - clauses.add(new BooleanClause(getFuzzyQuery(fields[i], termStr, minSimilarity), - BooleanClause.Occur.SHOULD)); - } - return getBooleanQuery(clauses, true); - } - return super.getFuzzyQuery(field, termStr, minSimilarity); - } - - protected Query getPrefixQuery(String field, String termStr) throws ParseException - { - if (field == null) { - List clauses = new ArrayList(); - for (int i = 0; i < fields.length; i++) { - clauses.add(new BooleanClause(getPrefixQuery(fields[i], termStr), - BooleanClause.Occur.SHOULD)); - } - return getBooleanQuery(clauses, true); - } - return super.getPrefixQuery(field, termStr); - } - - protected Query getWildcardQuery(String field, String termStr) throws ParseException { - if (field == null) { - List clauses = new ArrayList(); - for (int i = 0; i < fields.length; i++) { - clauses.add(new BooleanClause(getWildcardQuery(fields[i], termStr), - BooleanClause.Occur.SHOULD)); - } - return getBooleanQuery(clauses, true); - } - return super.getWildcardQuery(field, termStr); - } - - - protected Query getRangeQuery(String field, String part1, String part2, boolean inclusive) throws ParseException { - if (field == null) { - List clauses = new ArrayList(); - for (int i = 0; i < fields.length; i++) { - clauses.add(new BooleanClause(getRangeQuery(fields[i], part1, part2, inclusive), - BooleanClause.Occur.SHOULD)); - } - return getBooleanQuery(clauses, true); - } - return super.getRangeQuery(field, part1, part2, inclusive); - } - - /** - * Parses a query which searches on the fields specified. - *

- * If x fields are specified, this effectively constructs: - * 

-   * 
-   * (field1:query1) (field2:query2) (field3:query3)...(fieldx:queryx)
-   * 
-   *
- * @param queries Queries strings to parse - * @param fields Fields to search on - * @param analyzer Analyzer to use - * @throws ParseException if query parsing fails - * @throws IllegalArgumentException if the length of the queries array differs - * from the length of the fields array - */ - public static Query parse(String[] queries, String[] fields, - Analyzer analyzer) throws ParseException - { - if (queries.length != fields.length) - throw new IllegalArgumentException("queries.length != fields.length"); - BooleanQuery bQuery = new BooleanQuery(); - for (int i = 0; i < fields.length; i++) - { - QueryParser qp = new QueryParser(fields[i], analyzer); - Query q = qp.parse(queries[i]); - if (q!=null && // q never null, just being defensive - (!(q instanceof BooleanQuery) || ((BooleanQuery)q).getClauses().length>0)) { - bQuery.add(q, BooleanClause.Occur.SHOULD); - } - } - return bQuery; - } - - /** - * Parses a query, searching on the fields specified. - * Use this if you need to specify certain fields as required, - * and others as prohibited. - * 

-   * Usage:
-   * 
-   * String[] fields = {"filename", "contents", "description"};
-   * BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD,
-   *                BooleanClause.Occur.MUST,
-   *                BooleanClause.Occur.MUST_NOT};
-   * MultiFieldQueryParser.parse("query", fields, flags, analyzer);
-   * 
-   *
- *

- * The code above would construct a query: - * 

-   * 
-   * (filename:query) +(contents:query) -(description:query)
-   * 
-   *
- * - * @param query Query string to parse - * @param fields Fields to search on - * @param flags Flags describing the fields - * @param analyzer Analyzer to use - * @throws ParseException if query parsing fails - * @throws IllegalArgumentException if the length of the fields array differs - * from the length of the flags array - */ - public static Query parse(String query, String[] fields, - BooleanClause.Occur[] flags, Analyzer analyzer) throws ParseException { - if (fields.length != flags.length) - throw new IllegalArgumentException("fields.length != flags.length"); - BooleanQuery bQuery = new BooleanQuery(); - for (int i = 0; i < fields.length; i++) { - QueryParser qp = new QueryParser(fields[i], analyzer); - Query q = qp.parse(query); - if (q!=null && // q never null, just being defensive - (!(q instanceof BooleanQuery) || ((BooleanQuery)q).getClauses().length>0)) { - bQuery.add(q, flags[i]); - } - } - return bQuery; - } - - /** - * Parses a query, searching on the fields specified. - * Use this if you need to specify certain fields as required, - * and others as prohibited. - * 

-   * Usage:
-   * 
-   * String[] query = {"query1", "query2", "query3"};
-   * String[] fields = {"filename", "contents", "description"};
-   * BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD,
-   *                BooleanClause.Occur.MUST,
-   *                BooleanClause.Occur.MUST_NOT};
-   * MultiFieldQueryParser.parse(query, fields, flags, analyzer);
-   * 
-   *
- *

- * The code above would construct a query: - * 

-   * 
-   * (filename:query1) +(contents:query2) -(description:query3)
-   * 
-   *
- * - * @param queries Queries string to parse - * @param fields Fields to search on - * @param flags Flags describing the fields - * @param analyzer Analyzer to use - * @throws ParseException if query parsing fails - * @throws IllegalArgumentException if the length of the queries, fields, - * and flags array differ - */ - public static Query parse(String[] queries, String[] fields, BooleanClause.Occur[] flags, - Analyzer analyzer) throws ParseException - { - if (!(queries.length == fields.length && queries.length == flags.length)) - throw new IllegalArgumentException("queries, fields, and flags array have have different length"); - BooleanQuery bQuery = new BooleanQuery(); - for (int i = 0; i < fields.length; i++) - { - QueryParser qp = new QueryParser(fields[i], analyzer); - Query q = qp.parse(queries[i]); - if (q!=null && // q never null, just being defensive - (!(q instanceof BooleanQuery) || ((BooleanQuery)q).getClauses().length>0)) { - bQuery.add(q, flags[i]); - } - } - return bQuery; - } - -} Index: src/java/org/apache/lucene/queryParser/QueryNodeError.java =================================================================== --- src/java/org/apache/lucene/queryParser/QueryNodeError.java (revision 0) +++ src/java/org/apache/lucene/queryParser/QueryNodeError.java (revision 0) @@ -0,0 +1,69 @@ +package org.apache.lucene.queryParser; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.messages.Message; +import org.apache.lucene.messages.NLSException; + +/** + * Error class with NLS support + * @see org.apache.lucene.messages.NLS + * @see org.apache.lucene.messages.Message + */ +public class QueryNodeError extends Error implements NLSException { + + private static final long serialVersionUID = 1804855832182710327L; + private Message message; + + /** + * @param message - NLS Message Object + */ + public QueryNodeError(Message message) { + super(message.getKey()); + + this.message = message; + + } + + /** + * @param throwable - @see java.lang.Error + */ + public QueryNodeError(Throwable throwable) { + super(throwable); + } + + /** + * @param message - NLS Message Object + * @param throwable - @see java.lang.Error + */ + public QueryNodeError(Message message, Throwable throwable) { + super(message.getKey(), throwable); + + this.message = message; + + } + + + /* (non-Javadoc) + * @see org.apache.lucene.messages.NLSException#getMessageObject() + */ + public Message getMessageObject() { + return this.message; + } + +} Index: src/java/org/apache/lucene/queryParser/QueryNodeParseException.java =================================================================== --- src/java/org/apache/lucene/queryParser/QueryNodeParseException.java (revision 0) +++ src/java/org/apache/lucene/queryParser/QueryNodeParseException.java (revision 0) @@ -0,0 +1,106 @@ +package org.apache.lucene.queryParser; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.messages.Message; +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.messages.QueryParserMessages; + +/** + * TODO: document this class + */ +public class QueryNodeParseException extends QueryNodeException { + + private static final long serialVersionUID = 8197535103538766773L; + + private CharSequence query; + + private int beginColumn = -1; + + private int beginLine = -1; + + private String errorToken = ""; + + public QueryNodeParseException(Message message) { + super(message); + } + + public QueryNodeParseException(Throwable throwable) { + super(throwable); + } + + public QueryNodeParseException(Message message, Throwable throwable) { + super(message, throwable); + } + + public void setQuery(CharSequence query) { + this.query = query; + this.message = new MessageImpl(QueryParserMessages.INVALID_SYNTAX_CANNOT_PARSE, query, ""); + } + + public CharSequence getQuery() { + return this.query; + } + + /** + * @param errorToken the errorToken in the query + */ + protected void setErrorToken(String errorToken) { + this.errorToken = errorToken; + } + + public String getErrorToken() { + return this.errorToken ; + } + + public void setNonLocalizedMessage(Message message) { + this.message = message; + } + + /** + * For EndOfLine and EndOfFile ("") parsing problems the last char in the string is returned + * For the case where the parser is not able to figure out the line and column number -1 will be returned + * @return line where the problem was found + */ + public int getBeginLine() { + return this.beginLine ; + } + + /** + * For EndOfLine and EndOfFile ("") parsing problems the last char in the string is returned + * For the case where the parser is not able to figure out the line and column number -1 will be returned + * @return column of the first char where the problem was found + */ + public int getBeginColumn() { + return this.beginColumn; + } + + /** + * @param beginLine the beginLine to set + */ + protected void setBeginLine(int beginLine) { + this.beginLine = beginLine; + } + + /** + * @param beginColumn the beginColumn to set + */ + protected void setBeginColumn(int beginColumn) { + this.beginColumn = beginColumn; + } +} Index: src/java/org/apache/lucene/messages/Message.java =================================================================== --- src/java/org/apache/lucene/messages/Message.java (revision 0) +++ src/java/org/apache/lucene/messages/Message.java (revision 0) @@ -0,0 +1,36 @@ +package org.apache.lucene.messages; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.Serializable; +import java.util.Locale; + +/** + * For Native Language Support (NLS), system of software internationalization. + */ +public interface Message extends Serializable { + + public String getKey(); + + public Object[] getArguments(); + + public String getLocalizedMessage(); + + public String getLocalizedMessage(Locale locale); + +} Index: src/java/org/apache/lucene/messages/MessageImpl.java =================================================================== --- src/java/org/apache/lucene/messages/MessageImpl.java (revision 0) +++ src/java/org/apache/lucene/messages/MessageImpl.java (revision 0) @@ -0,0 +1,71 @@ +package org.apache.lucene.messages; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Locale; + +/** + * For Native Language Support (NLS), system of software internationalization. + */ +public class MessageImpl implements Message { + + private static final long serialVersionUID = -3077643314630884523L; + + private String key; + + private Object[] arguments = new Object[0]; + + public MessageImpl(String key) { + this.key = key; + + } + + public MessageImpl(String key, Object... args) { + this(key); + this.arguments = args; + } + + + public Object[] getArguments() { + return this.arguments; + } + + public String getKey() { + return this.key; + } + + public String getLocalizedMessage() { + return getLocalizedMessage(Locale.getDefault()); + } + + public String getLocalizedMessage(Locale locale) { + return NLS.getLocalizedMessage(getKey(), locale, getArguments()); + } + + public String toString(){ + Object[] args = getArguments(); + String argsString = ""; + if ( args != null){ + for (int i=0; i < args.length; i++){ + argsString += args[i] + (i> bundles = new HashMap>(0); + + protected NLS() { + // Do not instantiate + } + + public static String getLocalizedMessage(String key) { + return getLocalizedMessage(key, Locale.getDefault()); + } + + public static String getLocalizedMessage(String key, Locale locale) { + Object message = getResourceBundleObject(key, locale); + if (message == null) { + return "Message with key:" + key + " and locale: " + locale + + " not found."; + } + return message.toString(); + } + + public static String getLocalizedMessage(String key, Locale locale, Object... args) { + String str = getLocalizedMessage(key, locale); + + if (args.length > 0) { + str = MessageFormat.format(str, args); + } + + return str; + } + + public static String getLocalizedMessage(String key, Object... args) { + return getLocalizedMessage(key, Locale.getDefault(), args); + } + + /** + * Initialize a given class with the message bundle Keys + * Should be called from a class that extends NLS in a static block + * at class load time. + * + * @param bundleName Property file with that contains the message bundle + * @param clazz where constants will reside + */ + @SuppressWarnings("unchecked") + protected static void initializeMessages(String bundleName, Class clazz) { + try { + load(clazz); + if (!bundles.containsKey(bundleName)) + bundles.put(bundleName, clazz); + } catch (Throwable e){ + // ignore all errors and exceptions + // because this function is supposed to be called at class load time. + } + } + + private static Object getResourceBundleObject(String messageKey, + Locale locale) { + + // slow resource checking + // need to loop thru all registered resource bundles + for ( Iterator it = bundles.keySet().iterator() ; it.hasNext() ; ) { + Class clazz = bundles.get(it.next()); + ResourceBundle resourceBundle = ResourceBundle.getBundle( + clazz.getName(), locale); + if (resourceBundle != null) { + try { + Object obj = resourceBundle.getObject(messageKey); + if (obj != null) + return obj; + } catch(MissingResourceException e){ + // just continue it might be on the next resource bundle + } + } + } + // if resource is not found + return null; + } + + /** + * @param bundleName + * @param clazz + */ + private static void load(Class clazz) { + final Field[] fieldArray = clazz.getDeclaredFields(); + + boolean isFieldAccessible = (clazz.getModifiers() & Modifier.PUBLIC) != 0; + + // build a map of field names to Field objects + final int len = fieldArray.length; + Map fields = new HashMap(len * 2); + for (int i = 0; i < len; i++) { + fields.put(fieldArray[i].getName(), fieldArray[i]); + loadfieldValue(fieldArray[i], isFieldAccessible, clazz); + } + } + + /** + * @param field + * @param isFieldAccessible + */ + private static void loadfieldValue(Field field, boolean isFieldAccessible, Class clazz) { + int MOD_EXPECTED = Modifier.PUBLIC | Modifier.STATIC; + int MOD_MASK = MOD_EXPECTED | Modifier.FINAL; + if ((field.getModifiers() & MOD_MASK) != MOD_EXPECTED) + return; + + // Set a value for this empty field. + if (!isFieldAccessible) + makeAccessible(field); + try { + field.set(null, field.getName()); + validateMessage(field.getName(), clazz); + } catch (IllegalArgumentException e) { + // should not happen + } catch (IllegalAccessException e) { + // should not happen + } + } + + + /** + * @param key - Message Key + */ + private static void validateMessage(String key, Class clazz) { + // Test if the message is present in the resource bundle + try { + ResourceBundle resourceBundle = ResourceBundle.getBundle(clazz.getName(), Locale.getDefault()); + if (resourceBundle != null) { + Object obj = resourceBundle.getObject(key); + if (obj == null) + System.err.println("WARN: Message with key:" + key + " and locale: " + Locale.getDefault() + " not found."); + } + } catch(MissingResourceException e){ + System.err.println("WARN: Message with key:" + key + " and locale: " + Locale.getDefault() + " not found."); + } catch (Throwable e) { + // ignore all other errors and exceptions + // since this code is just a test to see if the message is present on the system + } + } + + /* + * Make a class field accessible + */ + @SuppressWarnings("unchecked") + private static void makeAccessible(final Field field) { + if (System.getSecurityManager() == null) { + field.setAccessible(true); + } else { + AccessController.doPrivileged(new PrivilegedAction() { + public Object run() { + field.setAccessible(true); + return null; + } + }); + } + } +} Index: src/java/org/apache/lucene/messages/NLSException.java =================================================================== --- src/java/org/apache/lucene/messages/NLSException.java (revision 0) +++ src/java/org/apache/lucene/messages/NLSException.java (revision 0) @@ -0,0 +1,30 @@ +package org.apache.lucene.messages; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + * For Native Language Support (NLS), system of software internationalization. + * This Interface should be implemented by all exceptions that require translation + * + */ +public interface NLSException { + /** + * @return a instance of a class that implements the Message interface + */ + public Message getMessageObject(); +} Index: src/test/org/apache/lucene/messages/MessagesTest.java =================================================================== --- src/test/org/apache/lucene/messages/MessagesTest.java (revision 0) +++ src/test/org/apache/lucene/messages/MessagesTest.java (revision 0) @@ -0,0 +1,41 @@ +package org.apache.lucene.messages; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +/** + */ +public class MessagesTest extends NLS { + + private static final String BUNDLE_NAME= MessagesTest.class.getName(); + + private MessagesTest() { + // should never be instantiated + } + + static { + // register all string ids with NLS class and initialize static string values + NLS.initializeMessages(BUNDLE_NAME, MessagesTest.class); + } + + // static string must match the strings in the property files. + public static String Q0001E_INVALID_SYNTAX; + public static String Q0004E_INVALID_SYNTAX_ESCAPE_UNICODE_TRUNCATION; + + //this message is missing from the properties file + public static String Q0005E_MESSAGE_NOT_IN_BUNDLE; +} Index: src/test/org/apache/lucene/messages/MessagesTest.properties =================================================================== --- src/test/org/apache/lucene/messages/MessagesTest.properties (revision 0) +++ src/test/org/apache/lucene/messages/MessagesTest.properties (revision 0) @@ -0,0 +1,3 @@ +Q0001E_INVALID_SYNTAX = Syntax Error: {0} + +Q0004E_INVALID_SYNTAX_ESCAPE_UNICODE_TRUNCATION = Truncated unicode escape sequence. Index: src/test/org/apache/lucene/messages/MessagesTest_ja.properties =================================================================== --- src/test/org/apache/lucene/messages/MessagesTest_ja.properties (revision 0) +++ src/test/org/apache/lucene/messages/MessagesTest_ja.properties (revision 0) @@ -0,0 +1,3 @@ +Q0001E_INVALID_SYNTAX = \u69cb\u6587\u30a8\u30e9\u30fc: {0} + +Q0004E_INVALID_SYNTAX_ESCAPE_UNICODE_TRUNCATION = \u5207\u308a\u6368\u3066\u3089\u308c\u305f\u30e6\u30cb\u30b3\u30fc\u30c9\u30fb\u30a8\u30b9\u30b1\u30fc\u30d7\u30fb\u30b7\u30fc\u30b1\u30f3\u30b9\u3002 Index: src/test/org/apache/lucene/messages/TestNLS.java =================================================================== --- src/test/org/apache/lucene/messages/TestNLS.java (revision 0) +++ src/test/org/apache/lucene/messages/TestNLS.java (revision 0) @@ -0,0 +1,67 @@ +package org.apache.lucene.messages; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.Locale; +import junit.framework.TestCase; + +/** + */ +public class TestNLS extends TestCase { + public void testMessageLoading() { + Message invalidSyntax = new MessageImpl(MessagesTest.Q0001E_INVALID_SYNTAX, "XXX"); + assertEquals("Syntax Error: XXX", invalidSyntax.getLocalizedMessage()); + } + + public void testMessageLoading_ja() { + Message invalidSyntax = new MessageImpl(MessagesTest.Q0001E_INVALID_SYNTAX, "XXX"); + assertEquals("構文エラー: XXX", invalidSyntax.getLocalizedMessage(Locale.JAPANESE)); + } + + public void testNLSLoading() { + String message = NLS.getLocalizedMessage(MessagesTest.Q0004E_INVALID_SYNTAX_ESCAPE_UNICODE_TRUNCATION); + assertEquals("Truncated unicode escape sequence.", message); + + message = NLS.getLocalizedMessage(MessagesTest.Q0001E_INVALID_SYNTAX, "XXX"); + assertEquals("Syntax Error: XXX", message); + } + + public void testNLSLoading_ja() { + String message = NLS.getLocalizedMessage(MessagesTest.Q0004E_INVALID_SYNTAX_ESCAPE_UNICODE_TRUNCATION, Locale.JAPANESE); + assertEquals("切り捨てられたユニコード・エスケープ・シーケンス。", message); + + message = NLS.getLocalizedMessage(MessagesTest.Q0001E_INVALID_SYNTAX, Locale.JAPANESE, "XXX"); + assertEquals("構文エラー: XXX", message); + } + + public void testNLSLoading_xx_XX() { + Locale locale = new Locale("xx","XX",""); + String message = NLS.getLocalizedMessage(MessagesTest.Q0004E_INVALID_SYNTAX_ESCAPE_UNICODE_TRUNCATION, locale); + assertEquals("Truncated unicode escape sequence.", message); + + message = NLS.getLocalizedMessage(MessagesTest.Q0001E_INVALID_SYNTAX, locale, "XXX"); + assertEquals("Syntax Error: XXX", message); + } + + public void testMissingMessage() { + Locale locale = Locale.ENGLISH; + String message = NLS.getLocalizedMessage(MessagesTest.Q0005E_MESSAGE_NOT_IN_BUNDLE, locale); + + assertEquals("Message with key:Q0005E_MESSAGE_NOT_IN_BUNDLE and locale: " + locale.toString() + " not found.", message); + } +} Index: src/test/org/apache/lucene/queryParser/spans/SpanOrQueryNodeBuilder.java =================================================================== --- src/test/org/apache/lucene/queryParser/spans/SpanOrQueryNodeBuilder.java (revision 0) +++ src/test/org/apache/lucene/queryParser/spans/SpanOrQueryNodeBuilder.java (revision 0) @@ -0,0 +1,54 @@ +package org.apache.lucene.queryParser.spans; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.lucene2.builders.LuceneQueryBuilder; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.spans.SpanOrQuery; +import org.apache.lucene.search.spans.SpanQuery; + +/** + * This builder creates {@link SpanOrQuery}s from a {@link BooleanQueryNode}.

+ * + * It assumes that the {@link BooleanQueryNode} instance has at least one child. + */ +public class SpanOrQueryNodeBuilder implements LuceneQueryBuilder { + + public SpanOrQuery build(QueryNode node) throws QueryNodeException { + + // validates node + BooleanQueryNode booleanNode = (BooleanQueryNode) node; + + List children = booleanNode.getChildren(); + SpanQuery[] spanQueries = new SpanQuery[children.size()]; + + int i = 0; + for (QueryNode child : children) { + spanQueries[i++] = (SpanQuery) child.getTag(QueryTreeBuilder.QUERY_TREE_BUILDER_TAGID); + } + + return new SpanOrQuery(spanQueries); + + } + +} Index: src/test/org/apache/lucene/queryParser/spans/SpanTermQueryNodeBuilder.java =================================================================== --- src/test/org/apache/lucene/queryParser/spans/SpanTermQueryNodeBuilder.java (revision 0) +++ src/test/org/apache/lucene/queryParser/spans/SpanTermQueryNodeBuilder.java (revision 0) @@ -0,0 +1,39 @@ +package org.apache.lucene.queryParser.spans; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.index.Term; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.lucene2.builders.LuceneQueryBuilder; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.spans.SpanTermQuery; + +/** + * This builder creates {@link SpanTermQuery}s from a {@link FieldQueryNode} object. + */ +public class SpanTermQueryNodeBuilder implements LuceneQueryBuilder { + + public SpanTermQuery build(QueryNode node) throws QueryNodeException { + FieldQueryNode fieldQueryNode = (FieldQueryNode) node; + + return new SpanTermQuery(new Term(fieldQueryNode.getFieldAsString(), fieldQueryNode.getTextAsString())); + + } + +} Index: src/test/org/apache/lucene/queryParser/spans/SpansQueryConfigHandler.java =================================================================== --- src/test/org/apache/lucene/queryParser/spans/SpansQueryConfigHandler.java (revision 0) +++ src/test/org/apache/lucene/queryParser/spans/SpansQueryConfigHandler.java (revision 0) @@ -0,0 +1,43 @@ +package org.apache.lucene.queryParser.spans; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.config.FieldConfig; +import org.apache.lucene.queryParser.config.QueryConfigHandler; + +/** + * This query config handler only adds the {@link UniqueFieldAttribute} to + * it.

+ * + * It does not return any configuration for a field in specific. + */ +public class SpansQueryConfigHandler extends QueryConfigHandler { + + public SpansQueryConfigHandler() { + addAttribute(UniqueFieldAttribute.class); + } + + @Override + public FieldConfig getFieldConfig(CharSequence fieldName) { + + // there is no field configuration, always return null + return null; + + } + +} Index: src/test/org/apache/lucene/queryParser/spans/SpansQueryTreeBuilder.java =================================================================== --- src/test/org/apache/lucene/queryParser/spans/SpansQueryTreeBuilder.java (revision 0) +++ src/test/org/apache/lucene/queryParser/spans/SpansQueryTreeBuilder.java (revision 0) @@ -0,0 +1,48 @@ +package org.apache.lucene.queryParser.spans; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.builders.QueryTreeBuilder; +import org.apache.lucene.queryParser.lucene2.builders.LuceneQueryBuilder; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.search.spans.SpanQuery; + +/** + * Sets up a query tree builder to build a span query tree from a query node tree.

+ * + * The defined map is:
+ * - every BooleanQueryNode instance is delegated to the SpanOrQueryNodeBuilder
+ * - every FieldQueryNode instance is delegated to the SpanTermQueryNodeBuilder
+ * + */ +public class SpansQueryTreeBuilder extends QueryTreeBuilder implements LuceneQueryBuilder { + + public SpansQueryTreeBuilder() { + setBuilder(BooleanQueryNode.class, new SpanOrQueryNodeBuilder()); + setBuilder(FieldQueryNode.class, new SpanTermQueryNodeBuilder()); + + } + + public SpanQuery build(QueryNode queryTree) throws QueryNodeException { + return (SpanQuery) super.build(queryTree); + } + +} Index: src/test/org/apache/lucene/queryParser/spans/SpansValidatorQueryNodeProcessor.java =================================================================== --- src/test/org/apache/lucene/queryParser/spans/SpansValidatorQueryNodeProcessor.java (revision 0) +++ src/test/org/apache/lucene/queryParser/spans/SpansValidatorQueryNodeProcessor.java (revision 0) @@ -0,0 +1,70 @@ +package org.apache.lucene.queryParser.spans; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.nodes.AndQueryNode; +import org.apache.lucene.queryParser.nodes.BooleanQueryNode; +import org.apache.lucene.queryParser.nodes.FieldQueryNode; +import org.apache.lucene.queryParser.nodes.OrQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + +/** + * Validates every query node in a query node tree. This processor + * will pass fine if the query nodes are only {@link BooleanQueryNode}s, + * {@link OrQueryNode}s or {@link FieldQueryNode}s, otherwise an exception will be thrown.

+ * + * If they are {@link AndQueryNode} or an instance of anything else that implements + * {@link FieldQueryNode} the exception will also be thrown. + */ +public class SpansValidatorQueryNodeProcessor extends QueryNodeProcessorImpl { + + @Override + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + @Override + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + if (!((node instanceof BooleanQueryNode && !(node instanceof AndQueryNode)) || node.getClass() == FieldQueryNode.class)) { + throw new QueryNodeException(new MessageImpl(QueryParserMessages.NODE_ACTION_NOT_SUPPORTED)); + } + + return node; + + } + + @Override + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParser.java =================================================================== --- src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParser.java (revision 0) +++ src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParser.java (revision 0) @@ -0,0 +1,213 @@ +package org.apache.lucene.queryParser.spans; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import javax.management.Query; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.lucene2.parser.QueryParser; +import org.apache.lucene.queryParser.nodes.OrQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorPipeline; +import org.apache.lucene.search.spans.SpanOrQuery; +import org.apache.lucene.search.spans.SpanQuery; +import org.apache.lucene.search.spans.SpanTermQuery; +import org.apache.lucene.util.LuceneTestCase; + +/** + * This test case demonstrates how the new query parser can be used.

+ * + * It tests queries likes "term", "field:term" "term1 term2" "term1 OR term2", + * which are all already supported by the current syntax parser ({@link QueryParser}).

+ * + * The goals is to create a new query parser that supports only the pair + * "field:term" or a list of pairs separated or not by an OR operator, and from + * this query generate {@link SpanQuery} objects instead of the regular + * {@link Query} objects. Basically, every pair will be converted to a + * {@link SpanTermQuery} object and if there are more than one + * pair they will be grouped by an {@link OrQueryNode}.

+ * + * Another functionality that will be added is the ability to convert every + * field defined in the query to an unique specific field.

+ * + * The query generation is divided in three different steps: parsing (syntax), + * processing (semantic) and building.

+ * + * The parsing phase, as already mentioned will be performed by the current + * query parser: {@link QueryParser}.

+ * + * The processing phase will be performed by a processor pipeline which is + * compound by 2 processors: {@link SpansValidatorQueryNodeProcessor} and + * {@link UniqueFieldQueryNodeProcessor}.
+ * 
+ *   {@link SpansValidatorQueryNodeProcessor}: as it's going to use the current 
+ *   query parser to parse the syntax, it will support more features than we want,
+ *   this processor basically validates the query node tree generated by the parser
+ *   and just let got through the elements we want, all the other elements as 
+ *   wildcards, range queries, etc...if found, an exception is thrown.
+ *   
+ *   {@link UniqueFieldQueryNodeProcessor}: this processor will take care of reading
+ *   what is the "unique field" from the configuration and convert every field defined
+ *   in every pair to this "unique field". For that, a {@link SpansQueryConfigHandler} is
+ *   used, which has the {@link UniqueFieldAttribute} defined in it.
+ * + * The building phase is performed by the {@link SpansQueryTreeBuilder}, which basically + * contains a map that defines which builder will be used to generate + * {@link SpanQuery} objects from {@link QueryNode} objects.

+ * + * @see SpansQueryConfigHandler + * @see SpansQueryTreeBuilder + * @see SpansValidatorQueryNodeProcessor + * @see SpanOrQueryNodeBuilder + * @see SpanTermQueryNodeBuilder + * @see QueryParser + * @see UniqueFieldQueryNodeProcessor + * @see UniqueFieldAttribute + * + */ +public class TestSpanQueryParser extends LuceneTestCase { + + private QueryNodeProcessorPipeline spanProcessorPipeline; + + private SpansQueryConfigHandler spanQueryConfigHandler; + + private SpansQueryTreeBuilder spansQueryTreeBuilder; + + private QueryParser queryParser = new QueryParser(); + + public TestSpanQueryParser() { + // empty constructor + } + + @Override + protected void setUp() throws Exception { + super.setUp(); + + this.spanProcessorPipeline = new QueryNodeProcessorPipeline(); + this.spanQueryConfigHandler = new SpansQueryConfigHandler(); + this.spansQueryTreeBuilder = new SpansQueryTreeBuilder(); + + // set up the processor pipeline + this.spanProcessorPipeline.setQueryConfigHandler(this.spanQueryConfigHandler); + + this.spanProcessorPipeline.addProcessor(new SpansValidatorQueryNodeProcessor()); + this.spanProcessorPipeline.addProcessor(new UniqueFieldQueryNodeProcessor()); + + } + + public SpanQuery getSpanQuery(CharSequence query) throws QueryNodeException { + return getSpanQuery("", query); + } + + public SpanQuery getSpanQuery(CharSequence uniqueField, CharSequence query) throws QueryNodeException { + UniqueFieldAttribute uniqueFieldAtt = (UniqueFieldAttribute) this.spanQueryConfigHandler.getAttribute(UniqueFieldAttribute.class); + uniqueFieldAtt.setUniqueField(uniqueField); + + QueryNode queryTree = this.queryParser.parse(query, "defaultField"); + queryTree = this.spanProcessorPipeline.process(queryTree); + + return this.spansQueryTreeBuilder.build(queryTree); + + } + + public void testTermSpans() throws Exception { + assertEquals(getSpanQuery("field:term").toString(), "term"); + assertEquals(getSpanQuery("term").toString(), "term"); + + assertTrue(getSpanQuery("field:term") instanceof SpanTermQuery); + assertTrue(getSpanQuery("term") instanceof SpanTermQuery); + + } + + public void testUniqueField() throws Exception { + assertEquals(getSpanQuery("field", "term").toString(), "field:term"); + assertEquals(getSpanQuery("field", "field:term").toString(), "field:term"); + assertEquals(getSpanQuery("field", "anotherField:term").toString(), "field:term"); + + } + + public void testOrSpans() throws Exception { + assertEquals(getSpanQuery("term1 term2").toString(), "spanOr([term1, term2])"); + assertEquals(getSpanQuery("term1 OR term2").toString(), "spanOr([term1, term2])"); + + assertTrue(getSpanQuery("term1 term2") instanceof SpanOrQuery); + assertTrue(getSpanQuery("term1 term2") instanceof SpanOrQuery); + + } + + public void testQueryValidator() throws QueryNodeException { + + try { + getSpanQuery("term*"); + fail("QueryNodeException was expected, wildcard queries should not be supported"); + + } catch (QueryNodeException ex) { + // expected exception + } + + try { + getSpanQuery("[a TO z]"); + fail("QueryNodeException was expected, range queries should not be supported"); + + } catch (QueryNodeException ex) { + // expected exception + } + + try { + getSpanQuery("a~0.5"); + fail("QueryNodeException was expected, boost queries should not be supported"); + + } catch (QueryNodeException ex) { + // expected exception + } + + try { + getSpanQuery("a^0.5"); + fail("QueryNodeException was expected, fuzzy queries should not be supported"); + + } catch (QueryNodeException ex) { + // expected exception + } + + try { + getSpanQuery("\"a b\""); + fail("QueryNodeException was expected, quoted queries should not be supported"); + + } catch (QueryNodeException ex) { + // expected exception + } + + try { + getSpanQuery("(a b)"); + fail("QueryNodeException was expected, parenthesized queries should not be supported"); + + } catch (QueryNodeException ex) { + // expected exception + } + + try { + getSpanQuery("a AND b"); + fail("QueryNodeException was expected, and queries should not be supported"); + + } catch (QueryNodeException ex) { + // expected exception + } + + } + +} Index: src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParserSimpleSample.java =================================================================== --- src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParserSimpleSample.java (revision 0) +++ src/test/org/apache/lucene/queryParser/spans/TestSpanQueryParserSimpleSample.java (revision 0) @@ -0,0 +1,130 @@ +package org.apache.lucene.queryParser.spans; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import javax.management.Query; + +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.lucene2.parser.QueryParser; +import org.apache.lucene.queryParser.nodes.OrQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.parser.Parser; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorPipeline; +import org.apache.lucene.search.spans.SpanQuery; +import org.apache.lucene.search.spans.SpanTermQuery; +import org.apache.lucene.util.LuceneTestCase; + +/** + * This test case demonstrates how the new query parser can be used.

+ * + * It tests queries likes "term", "field:term" "term1 term2" "term1 OR term2", + * which are all already supported by the current syntax parser ({@link QueryParser}).

+ * + * The goals is to create a new query parser that supports only the pair + * "field:term" or a list of pairs separated or not by an OR operator, and from + * this query generate {@link SpanQuery} objects instead of the regular + * {@link Query} objects. Basically, every pair will be converted to a + * {@link SpanTermQuery} object and if there are more than one + * pair they will be grouped by an {@link OrQueryNode}.

+ * + * Another functionality that will be added is the ability to convert every + * field defined in the query to an unique specific field.

+ * + * The query generation is divided in three different steps: parsing (syntax), + * processing (semantic) and building.

+ * + * The parsing phase, as already mentioned will be performed by the current + * query parser: {@link QueryParser}.

+ * + * The processing phase will be performed by a processor pipeline which is + * compound by 2 processors: {@link SpansValidatorQueryNodeProcessor} and + * {@link UniqueFieldQueryNodeProcessor}.
+ * 
+ *   {@link SpansValidatorQueryNodeProcessor}: as it's going to use the current 
+ *   query parser to parse the syntax, it will support more features than we want,
+ *   this processor basically validates the query node tree generated by the parser
+ *   and just let got through the elements we want, all the other elements as 
+ *   wildcards, range queries, etc...if found, an exception is thrown.
+ *   
+ *   {@link UniqueFieldQueryNodeProcessor}: this processor will take care of reading
+ *   what is the "unique field" from the configuration and convert every field defined
+ *   in every pair to this "unique field". For that, a {@link SpansQueryConfigHandler} is
+ *   used, which has the {@link UniqueFieldAttribute} defined in it.
+ * + * The building phase is performed by the {@link SpansQueryTreeBuilder}, which basically + * contains a map that defines which builder will be used to generate + * {@link SpanQuery} objects from {@link QueryNode} objects.

+ * + * @see TestSpanQueryParser for a more advanced example + * + * @see SpansQueryConfigHandler + * @see SpansQueryTreeBuilder + * @see SpansValidatorQueryNodeProcessor + * @see SpanOrQueryNodeBuilder + * @see SpanTermQueryNodeBuilder + * @see QueryParser + * @see UniqueFieldQueryNodeProcessor + * @see UniqueFieldAttribute + * + */ +public class TestSpanQueryParserSimpleSample extends LuceneTestCase { + + public TestSpanQueryParserSimpleSample() { + // empty constructor + } + + public void testBasicDemo() throws Exception { + Parser queryParser = new QueryParser(); + + // convert the CharSequence into a QueryNode tree + QueryNode queryTree = queryParser.parse("body:text", null); + + // create a config handler with a attribute used in UniqueFieldQueryNodeProcessor + QueryConfigHandler spanQueryConfigHandler = new SpansQueryConfigHandler(); + UniqueFieldAttribute uniqueFieldAtt = (UniqueFieldAttribute) spanQueryConfigHandler.getAttribute(UniqueFieldAttribute.class); + uniqueFieldAtt.setUniqueField("index"); + + // set up the processor pipeline with the ConfigHandler + // and create the pipeline for this simple demo + QueryNodeProcessorPipeline spanProcessorPipeline = new QueryNodeProcessorPipeline(spanQueryConfigHandler); + // @see SpansValidatorQueryNodeProcessor + spanProcessorPipeline.addProcessor(new SpansValidatorQueryNodeProcessor()); + // @see UniqueFieldQueryNodeProcessor + spanProcessorPipeline.addProcessor(new UniqueFieldQueryNodeProcessor()); + + // print to show out the QueryTree before being processed + System.out.println(queryTree); + + // Process the QueryTree using our new Processors + queryTree = spanProcessorPipeline.process(queryTree); + + // print to show out the QueryTree after being processed + System.out.println(queryTree); + + // create a instance off the Builder + SpansQueryTreeBuilder spansQueryTreeBuilder = new SpansQueryTreeBuilder(); + + // convert QueryNode tree to span query Objects + SpanQuery spanquery = spansQueryTreeBuilder.build(queryTree); + + assertTrue(spanquery instanceof SpanTermQuery); + assertEquals(spanquery.toString(), "index:text"); + + } + +} Index: src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttribute.java =================================================================== --- src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttribute.java (revision 0) +++ src/test/org/apache/lucene/queryParser/spans/UniqueFieldAttribute.java (revision 0) @@ -0,0 +1,88 @@ +package org.apache.lucene.queryParser.spans; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import org.apache.lucene.queryParser.nodes.FieldableNode; +import org.apache.lucene.util.Attribute; + +/** + * This attribute is used by the {@link UniqueFieldQueryNodeProcessor} + * processor. It holds a value that defines which is the unique field name + * that should be set in every {@link FieldableNode}.

+ * + * @see UniqueFieldQueryNodeProcessor + */ +public class UniqueFieldAttribute extends Attribute { + + private static final long serialVersionUID = 8553318595851064232L; + + private CharSequence uniqueField; + + public UniqueFieldAttribute() { + clear(); + } + + @Override + public void clear() { + this.uniqueField = ""; + } + + public void setUniqueField(CharSequence uniqueField) { + this.uniqueField = uniqueField; + } + + public CharSequence getUniqueField() { + return this.uniqueField; + } + + @Override + public void copyTo(Attribute target) { + + if (!(target instanceof UniqueFieldAttribute)) { + throw new IllegalArgumentException("cannot copy the values from attribute UniqueFieldAttribute to an instance of " + target.getClass().getName()); + } + + UniqueFieldAttribute uniqueFieldAttr = (UniqueFieldAttribute) target; + uniqueFieldAttr.uniqueField = uniqueField.toString(); + + } + + @Override + public boolean equals(Object other) { + + if (other instanceof UniqueFieldAttribute) { + + return ((UniqueFieldAttribute) other).uniqueField.equals(this.uniqueField); + + } + + return false; + + } + + @Override + public int hashCode() { + return this.uniqueField.hashCode(); + } + + @Override + public String toString() { + return ""; + } + +} Index: src/test/org/apache/lucene/queryParser/spans/UniqueFieldQueryNodeProcessor.java =================================================================== --- src/test/org/apache/lucene/queryParser/spans/UniqueFieldQueryNodeProcessor.java (revision 0) +++ src/test/org/apache/lucene/queryParser/spans/UniqueFieldQueryNodeProcessor.java (revision 0) @@ -0,0 +1,81 @@ +package org.apache.lucene.queryParser.spans; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.util.List; + +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.config.QueryConfigHandler; +import org.apache.lucene.queryParser.nodes.FieldableNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; + +/** + * This processor changes every field name of each {@link FieldableNode} query node + * contained in the query tree to the field name defined in the {@link UniqueFieldAttribute}. + * So, the {@link UniqueFieldAttribute} must be defined in the {@link QueryConfigHandler} object + * set in this processor, otherwise it throws an exception.

+ * + * @see UniqueFieldAttribute + */ +public class UniqueFieldQueryNodeProcessor extends QueryNodeProcessorImpl { + + @Override + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + @Override + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof FieldableNode) { + FieldableNode fieldNode = (FieldableNode) node; + + QueryConfigHandler queryConfig = getQueryConfigHandler(); + + if (queryConfig == null) { + throw new IllegalArgumentException("A config handler is expected by the processor UniqueFieldQueryNodeProcessor!"); + } + + if (!queryConfig.hasAttribute(UniqueFieldAttribute.class)) { + throw new IllegalArgumentException("UniqueFieldAttribute should be defined in the config handler!"); + } + + CharSequence uniqueField = ((UniqueFieldAttribute) queryConfig.getAttribute(UniqueFieldAttribute.class)).getUniqueField(); + + fieldNode.setField(uniqueField); + + } + + return node; + + } + + @Override + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + +} Index: src/test/org/apache/lucene/queryParser/TestQueryParser.java =================================================================== --- src/test/org/apache/lucene/queryParser/TestQueryParser.java (revision 757685) +++ src/test/org/apache/lucene/queryParser/TestQueryParser.java (working copy) @@ -1,996 +0,0 @@ -package org.apache.lucene.queryParser; - -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -import java.io.IOException; -import java.io.Reader; -import java.text.Collator; -import java.text.DateFormat; -import java.util.Calendar; -import java.util.Date; -import java.util.Locale; - -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.KeywordAnalyzer; -import org.apache.lucene.analysis.LowerCaseTokenizer; -import org.apache.lucene.analysis.SimpleAnalyzer; -import org.apache.lucene.analysis.StopAnalyzer; -import org.apache.lucene.analysis.StopFilter; -import org.apache.lucene.analysis.TokenFilter; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.WhitespaceAnalyzer; -import org.apache.lucene.analysis.standard.StandardAnalyzer; -import org.apache.lucene.analysis.tokenattributes.OffsetAttribute; -import org.apache.lucene.analysis.tokenattributes.TermAttribute; -import org.apache.lucene.document.DateField; -import org.apache.lucene.document.DateTools; -import org.apache.lucene.document.Document; -import org.apache.lucene.document.Field; -import org.apache.lucene.index.IndexWriter; -import org.apache.lucene.index.Term; -import org.apache.lucene.search.BooleanQuery; -import org.apache.lucene.search.FuzzyQuery; -import org.apache.lucene.search.IndexSearcher; -import org.apache.lucene.search.MatchAllDocsQuery; -import org.apache.lucene.search.PhraseQuery; -import org.apache.lucene.search.PrefixQuery; -import org.apache.lucene.search.Query; -import org.apache.lucene.search.RangeQuery; -import org.apache.lucene.search.ScoreDoc; -import org.apache.lucene.search.TermQuery; -import org.apache.lucene.search.WildcardQuery; -import org.apache.lucene.store.RAMDirectory; -import org.apache.lucene.util.LuceneTestCase; - -/** - * Tests QueryParser. - */ -public class TestQueryParser extends LuceneTestCase { - - public static Analyzer qpAnalyzer = new QPTestAnalyzer(); - - public static class QPTestFilter extends TokenFilter { - TermAttribute termAtt; - OffsetAttribute offsetAtt; - - /** - * Filter which discards the token 'stop' and which expands the - * token 'phrase' into 'phrase1 phrase2' - */ - public QPTestFilter(TokenStream in) { - super(in); - termAtt = (TermAttribute) addAttribute(TermAttribute.class); - offsetAtt = (OffsetAttribute) addAttribute(OffsetAttribute.class); - } - - boolean inPhrase = false; - int savedStart = 0, savedEnd = 0; - - public boolean incrementToken() throws IOException { - if (inPhrase) { - inPhrase = false; - termAtt.setTermBuffer("phrase2"); - offsetAtt.setStartOffset(savedStart); - offsetAtt.setEndOffset(savedEnd); - return true; - } else - while (input.incrementToken()) { - if (termAtt.term().equals("phrase")) { - inPhrase = true; - savedStart = offsetAtt.startOffset(); - savedEnd = offsetAtt.endOffset(); - termAtt.setTermBuffer("phrase1"); - offsetAtt.setStartOffset(savedStart); - offsetAtt.setEndOffset(savedEnd); - return true; - } else if (!termAtt.term().equals("stop")) - return true; - } - return false; - } - } - - - public static class QPTestAnalyzer extends Analyzer { - - /** Filters LowerCaseTokenizer with StopFilter. */ - public final TokenStream tokenStream(String fieldName, Reader reader) { - return new QPTestFilter(new LowerCaseTokenizer(reader)); - } - } - - public static class QPTestParser extends QueryParser { - public QPTestParser(String f, Analyzer a) { - super(f, a); - } - - protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws ParseException { - throw new ParseException("Fuzzy queries not allowed"); - } - - protected Query getWildcardQuery(String field, String termStr) throws ParseException { - throw new ParseException("Wildcard queries not allowed"); - } - } - - private int originalMaxClauses; - - public void setUp() throws Exception { - super.setUp(); - originalMaxClauses = BooleanQuery.getMaxClauseCount(); - } - - public QueryParser getParser(Analyzer a) throws Exception { - if (a == null) - a = new SimpleAnalyzer(); - QueryParser qp = new QueryParser("field", a); - qp.setDefaultOperator(QueryParser.OR_OPERATOR); - return qp; - } - - public Query getQuery(String query, Analyzer a) throws Exception { - return getParser(a).parse(query); - } - - public void assertQueryEquals(String query, Analyzer a, String result) - throws Exception { - Query q = getQuery(query, a); - String s = q.toString("field"); - if (!s.equals(result)) { - fail("Query /" + query + "/ yielded /" + s - + "/, expecting /" + result + "/"); - } - } - - public void assertQueryEquals(QueryParser qp, String field, String query, String result) - throws Exception { - Query q = qp.parse(query); - String s = q.toString(field); - if (!s.equals(result)) { - fail("Query /" + query + "/ yielded /" + s - + "/, expecting /" + result + "/"); - } - } - - public void assertEscapedQueryEquals(String query, Analyzer a, String result) - throws Exception { - String escapedQuery = QueryParser.escape(query); - if (!escapedQuery.equals(result)) { - fail("Query /" + query + "/ yielded /" + escapedQuery - + "/, expecting /" + result + "/"); - } - } - - public void assertWildcardQueryEquals(String query, boolean lowercase, String result, boolean allowLeadingWildcard) - throws Exception { - QueryParser qp = getParser(null); - qp.setLowercaseExpandedTerms(lowercase); - qp.setAllowLeadingWildcard(allowLeadingWildcard); - Query q = qp.parse(query); - String s = q.toString("field"); - if (!s.equals(result)) { - fail("WildcardQuery /" + query + "/ yielded /" + s - + "/, expecting /" + result + "/"); - } - } - - public void assertWildcardQueryEquals(String query, boolean lowercase, String result) - throws Exception { - assertWildcardQueryEquals(query, lowercase, result, false); - } - - public void assertWildcardQueryEquals(String query, String result) throws Exception { - QueryParser qp = getParser(null); - Query q = qp.parse(query); - String s = q.toString("field"); - if (!s.equals(result)) { - fail("WildcardQuery /" + query + "/ yielded /" + s + "/, expecting /" - + result + "/"); - } - } - - public Query getQueryDOA(String query, Analyzer a) - throws Exception { - if (a == null) - a = new SimpleAnalyzer(); - QueryParser qp = new QueryParser("field", a); - qp.setDefaultOperator(QueryParser.AND_OPERATOR); - return qp.parse(query); - } - - public void assertQueryEqualsDOA(String query, Analyzer a, String result) - throws Exception { - Query q = getQueryDOA(query, a); - String s = q.toString("field"); - if (!s.equals(result)) { - fail("Query /" + query + "/ yielded /" + s - + "/, expecting /" + result + "/"); - } - } - - public void testCJK() throws Exception { - // Test Ideographic Space - As wide as a CJK character cell (fullwidth) - // used google to translate the word "term" to japanese -> 用語 - assertQueryEquals("term\u3000term\u3000term", null, "term\u0020term\u0020term"); - assertQueryEquals("用語\u3000用語\u3000用語", null, "用語\u0020用語\u0020用語"); - } - - public void testSimple() throws Exception { - assertQueryEquals("term term term", null, "term term term"); - assertQueryEquals("türm term term", new WhitespaceAnalyzer(), "türm term term"); - assertQueryEquals("ümlaut", new WhitespaceAnalyzer(), "ümlaut"); - - assertQueryEquals("\"\"", new KeywordAnalyzer(), ""); - assertQueryEquals("foo:\"\"", new KeywordAnalyzer(), "foo:"); - - assertQueryEquals("a AND b", null, "+a +b"); - assertQueryEquals("(a AND b)", null, "+a +b"); - assertQueryEquals("c OR (a AND b)", null, "c (+a +b)"); - assertQueryEquals("a AND NOT b", null, "+a -b"); - assertQueryEquals("a AND -b", null, "+a -b"); - assertQueryEquals("a AND !b", null, "+a -b"); - assertQueryEquals("a && b", null, "+a +b"); - assertQueryEquals("a && ! b", null, "+a -b"); - - assertQueryEquals("a OR b", null, "a b"); - assertQueryEquals("a || b", null, "a b"); - assertQueryEquals("a OR !b", null, "a -b"); - assertQueryEquals("a OR ! b", null, "a -b"); - assertQueryEquals("a OR -b", null, "a -b"); - - assertQueryEquals("+term -term term", null, "+term -term term"); - assertQueryEquals("foo:term AND field:anotherTerm", null, - "+foo:term +anotherterm"); - assertQueryEquals("term AND \"phrase phrase\"", null, - "+term +\"phrase phrase\""); - assertQueryEquals("\"hello there\"", null, "\"hello there\""); - assertTrue(getQuery("a AND b", null) instanceof BooleanQuery); - assertTrue(getQuery("hello", null) instanceof TermQuery); - assertTrue(getQuery("\"hello there\"", null) instanceof PhraseQuery); - - assertQueryEquals("germ term^2.0", null, "germ term^2.0"); - assertQueryEquals("(term)^2.0", null, "term^2.0"); - assertQueryEquals("(germ term)^2.0", null, "(germ term)^2.0"); - assertQueryEquals("term^2.0", null, "term^2.0"); - assertQueryEquals("term^2", null, "term^2.0"); - assertQueryEquals("\"germ term\"^2.0", null, "\"germ term\"^2.0"); - assertQueryEquals("\"term germ\"^2", null, "\"term germ\"^2.0"); - - assertQueryEquals("(foo OR bar) AND (baz OR boo)", null, - "+(foo bar) +(baz boo)"); - assertQueryEquals("((a OR b) AND NOT c) OR d", null, - "(+(a b) -c) d"); - assertQueryEquals("+(apple \"steve jobs\") -(foo bar baz)", null, - "+(apple \"steve jobs\") -(foo bar baz)"); - assertQueryEquals("+title:(dog OR cat) -author:\"bob dole\"", null, - "+(title:dog title:cat) -author:\"bob dole\""); - - QueryParser qp = new QueryParser("field", new StandardAnalyzer()); - // make sure OR is the default: - assertEquals(QueryParser.OR_OPERATOR, qp.getDefaultOperator()); - qp.setDefaultOperator(QueryParser.AND_OPERATOR); - assertEquals(QueryParser.AND_OPERATOR, qp.getDefaultOperator()); - qp.setDefaultOperator(QueryParser.OR_OPERATOR); - assertEquals(QueryParser.OR_OPERATOR, qp.getDefaultOperator()); - } - - public void testPunct() throws Exception { - Analyzer a = new WhitespaceAnalyzer(); - assertQueryEquals("a&b", a, "a&b"); - assertQueryEquals("a&&b", a, "a&&b"); - assertQueryEquals(".NET", a, ".NET"); - } - - public void testSlop() throws Exception { - assertQueryEquals("\"term germ\"~2", null, "\"term germ\"~2"); - assertQueryEquals("\"term germ\"~2 flork", null, "\"term germ\"~2 flork"); - assertQueryEquals("\"term\"~2", null, "term"); - assertQueryEquals("\" \"~2 germ", null, "germ"); - assertQueryEquals("\"term germ\"~2^2", null, "\"term germ\"~2^2.0"); - } - - public void testNumber() throws Exception { -// The numbers go away because SimpleAnalzyer ignores them - assertQueryEquals("3", null, ""); - assertQueryEquals("term 1.0 1 2", null, "term"); - assertQueryEquals("term term1 term2", null, "term term term"); - - Analyzer a = new StandardAnalyzer(); - assertQueryEquals("3", a, "3"); - assertQueryEquals("term 1.0 1 2", a, "term 1.0 1 2"); - assertQueryEquals("term term1 term2", a, "term term1 term2"); - } - - public void testWildcard() throws Exception { - assertQueryEquals("term*", null, "term*"); - assertQueryEquals("term*^2", null, "term*^2.0"); - assertQueryEquals("term~", null, "term~0.5"); - assertQueryEquals("term~0.7", null, "term~0.7"); - assertQueryEquals("term~^2", null, "term~0.5^2.0"); - assertQueryEquals("term^2~", null, "term~0.5^2.0"); - assertQueryEquals("term*germ", null, "term*germ"); - assertQueryEquals("term*germ^3", null, "term*germ^3.0"); - - assertTrue(getQuery("term*", null) instanceof PrefixQuery); - assertTrue(getQuery("term*^2", null) instanceof PrefixQuery); - assertTrue(getQuery("term~", null) instanceof FuzzyQuery); - assertTrue(getQuery("term~0.7", null) instanceof FuzzyQuery); - FuzzyQuery fq = (FuzzyQuery)getQuery("term~0.7", null); - assertEquals(0.7f, fq.getMinSimilarity(), 0.1f); - assertEquals(FuzzyQuery.defaultPrefixLength, fq.getPrefixLength()); - fq = (FuzzyQuery)getQuery("term~", null); - assertEquals(0.5f, fq.getMinSimilarity(), 0.1f); - assertEquals(FuzzyQuery.defaultPrefixLength, fq.getPrefixLength()); - - assertParseException("term~1.1"); // value > 1, throws exception - - assertTrue(getQuery("term*germ", null) instanceof WildcardQuery); - -/* Tests to see that wild card terms are (or are not) properly - * lower-cased with propery parser configuration - */ -// First prefix queries: - // by default, convert to lowercase: - assertWildcardQueryEquals("Term*", true, "term*"); - // explicitly set lowercase: - assertWildcardQueryEquals("term*", true, "term*"); - assertWildcardQueryEquals("Term*", true, "term*"); - assertWildcardQueryEquals("TERM*", true, "term*"); - // explicitly disable lowercase conversion: - assertWildcardQueryEquals("term*", false, "term*"); - assertWildcardQueryEquals("Term*", false, "Term*"); - assertWildcardQueryEquals("TERM*", false, "TERM*"); -// Then 'full' wildcard queries: - // by default, convert to lowercase: - assertWildcardQueryEquals("Te?m", "te?m"); - // explicitly set lowercase: - assertWildcardQueryEquals("te?m", true, "te?m"); - assertWildcardQueryEquals("Te?m", true, "te?m"); - assertWildcardQueryEquals("TE?M", true, "te?m"); - assertWildcardQueryEquals("Te?m*gerM", true, "te?m*germ"); - // explicitly disable lowercase conversion: - assertWildcardQueryEquals("te?m", false, "te?m"); - assertWildcardQueryEquals("Te?m", false, "Te?m"); - assertWildcardQueryEquals("TE?M", false, "TE?M"); - assertWildcardQueryEquals("Te?m*gerM", false, "Te?m*gerM"); -// Fuzzy queries: - assertWildcardQueryEquals("Term~", "term~0.5"); - assertWildcardQueryEquals("Term~", true, "term~0.5"); - assertWildcardQueryEquals("Term~", false, "Term~0.5"); -// Range queries: - assertWildcardQueryEquals("[A TO C]", "[a TO c]"); - assertWildcardQueryEquals("[A TO C]", true, "[a TO c]"); - assertWildcardQueryEquals("[A TO C]", false, "[A TO C]"); - // Test suffix queries: first disallow - try { - assertWildcardQueryEquals("*Term", true, "*term"); - fail(); - } catch(ParseException pe) { - // expected exception - } - try { - assertWildcardQueryEquals("?Term", true, "?term"); - fail(); - } catch(ParseException pe) { - // expected exception - } - // Test suffix queries: then allow - assertWildcardQueryEquals("*Term", true, "*term", true); - assertWildcardQueryEquals("?Term", true, "?term", true); - } - - public void testLeadingWildcardType() throws Exception { - QueryParser qp = getParser(null); - qp.setAllowLeadingWildcard(true); - assertEquals(WildcardQuery.class, qp.parse("t*erm*").getClass()); - assertEquals(WildcardQuery.class, qp.parse("?term*").getClass()); - assertEquals(WildcardQuery.class, qp.parse("*term*").getClass()); - } - - public void testQPA() throws Exception { - assertQueryEquals("term term^3.0 term", qpAnalyzer, "term term^3.0 term"); - assertQueryEquals("term stop^3.0 term", qpAnalyzer, "term term"); - - assertQueryEquals("term term term", qpAnalyzer, "term term term"); - assertQueryEquals("term +stop term", qpAnalyzer, "term term"); - assertQueryEquals("term -stop term", qpAnalyzer, "term term"); - - assertQueryEquals("drop AND (stop) AND roll", qpAnalyzer, "+drop +roll"); - assertQueryEquals("term +(stop) term", qpAnalyzer, "term term"); - assertQueryEquals("term -(stop) term", qpAnalyzer, "term term"); - - assertQueryEquals("drop AND stop AND roll", qpAnalyzer, "+drop +roll"); - assertQueryEquals("term phrase term", qpAnalyzer, - "term \"phrase1 phrase2\" term"); - assertQueryEquals("term AND NOT phrase term", qpAnalyzer, - "+term -\"phrase1 phrase2\" term"); - assertQueryEquals("stop^3", qpAnalyzer, ""); - assertQueryEquals("stop", qpAnalyzer, ""); - assertQueryEquals("(stop)^3", qpAnalyzer, ""); - assertQueryEquals("((stop))^3", qpAnalyzer, ""); - assertQueryEquals("(stop^3)", qpAnalyzer, ""); - assertQueryEquals("((stop)^3)", qpAnalyzer, ""); - assertQueryEquals("(stop)", qpAnalyzer, ""); - assertQueryEquals("((stop))", qpAnalyzer, ""); - assertTrue(getQuery("term term term", qpAnalyzer) instanceof BooleanQuery); - assertTrue(getQuery("term +stop", qpAnalyzer) instanceof TermQuery); - } - - public void testRange() throws Exception { - assertQueryEquals("[ a TO z]", null, "[a TO z]"); - assertTrue(((RangeQuery)getQuery("[ a TO z]", null)).getConstantScoreRewrite()); - - QueryParser qp = new QueryParser("field", new SimpleAnalyzer()); - qp.setConstantScoreRewrite(false); - assertFalse(((RangeQuery)qp.parse("[ a TO z]")).getConstantScoreRewrite()); - - assertQueryEquals("[ a TO z ]", null, "[a TO z]"); - assertQueryEquals("{ a TO z}", null, "{a TO z}"); - assertQueryEquals("{ a TO z }", null, "{a TO z}"); - assertQueryEquals("{ a TO z }^2.0", null, "{a TO z}^2.0"); - assertQueryEquals("[ a TO z] OR bar", null, "[a TO z] bar"); - assertQueryEquals("[ a TO z] AND bar", null, "+[a TO z] +bar"); - assertQueryEquals("( bar blar { a TO z}) ", null, "bar blar {a TO z}"); - assertQueryEquals("gack ( bar blar { a TO z}) ", null, "gack (bar blar {a TO z})"); - } - - public void testFarsiRangeCollating() throws Exception { - - RAMDirectory ramDir = new RAMDirectory(); - IndexWriter iw = new IndexWriter(ramDir, new WhitespaceAnalyzer(), true, - IndexWriter.MaxFieldLength.LIMITED); - Document doc = new Document(); - doc.add(new Field("content","\u0633\u0627\u0628", - Field.Store.YES, Field.Index.UN_TOKENIZED)); - iw.addDocument(doc); - iw.close(); - IndexSearcher is = new IndexSearcher(ramDir); - - QueryParser qp = new QueryParser("content", new WhitespaceAnalyzer()); - - // Neither Java 1.4.2 nor 1.5.0 has Farsi Locale collation available in - // RuleBasedCollator. However, the Arabic Locale seems to order the Farsi - // characters properly. - Collator c = Collator.getInstance(new Locale("ar")); - qp.setRangeCollator(c); - - // Unicode order would include U+0633 in [ U+062F - U+0698 ], but Farsi - // orders the U+0698 character before the U+0633 character, so the single - // index Term below should NOT be returned by a ConstantScoreRangeQuery - // with a Farsi Collator (or an Arabic one for the case when Farsi is not - // supported). - - // Test ConstantScoreRangeQuery - qp.setConstantScoreRewrite(true); - ScoreDoc[] result = is.search(qp.parse("[ \u062F TO \u0698 ]"), null, 1000).scoreDocs; - assertEquals("The index Term should not be included.", 0, result.length); - - result = is.search(qp.parse("[ \u0633 TO \u0638 ]"), null, 1000).scoreDocs; - assertEquals("The index Term should be included.", 1, result.length); - - // Test RangeQuery - qp.setConstantScoreRewrite(false); - result = is.search(qp.parse("[ \u062F TO \u0698 ]"), null, 1000).scoreDocs; - assertEquals("The index Term should not be included.", 0, result.length); - - result = is.search(qp.parse("[ \u0633 TO \u0638 ]"), null, 1000).scoreDocs; - assertEquals("The index Term should be included.", 1, result.length); - - is.close(); - } - - /** for testing legacy DateField support */ - private String getLegacyDate(String s) throws Exception { - DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT); - return DateField.dateToString(df.parse(s)); - } - - /** for testing DateTools support */ - private String getDate(String s, DateTools.Resolution resolution) throws Exception { - DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT); - return getDate(df.parse(s), resolution); - } - - /** for testing DateTools support */ - private String getDate(Date d, DateTools.Resolution resolution) throws Exception { - if (resolution == null) { - return DateField.dateToString(d); - } else { - return DateTools.dateToString(d, resolution); - } - } - - private String getLocalizedDate(int year, int month, int day, boolean extendLastDate) { - DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT); - Calendar calendar = Calendar.getInstance(); - calendar.set(year, month, day); - if (extendLastDate) { - calendar.set(Calendar.HOUR_OF_DAY, 23); - calendar.set(Calendar.MINUTE, 59); - calendar.set(Calendar.SECOND, 59); - calendar.set(Calendar.MILLISECOND, 999); - } - return df.format(calendar.getTime()); - } - - /** for testing legacy DateField support */ - public void testLegacyDateRange() throws Exception { - String startDate = getLocalizedDate(2002, 1, 1, false); - String endDate = getLocalizedDate(2002, 1, 4, false); - Calendar endDateExpected = Calendar.getInstance(); - endDateExpected.set(2002, 1, 4, 23, 59, 59); - endDateExpected.set(Calendar.MILLISECOND, 999); - assertQueryEquals("[ " + startDate + " TO " + endDate + "]", null, - "[" + getLegacyDate(startDate) + " TO " + DateField.dateToString(endDateExpected.getTime()) + "]"); - assertQueryEquals("{ " + startDate + " " + endDate + " }", null, - "{" + getLegacyDate(startDate) + " TO " + getLegacyDate(endDate) + "}"); - } - - public void testDateRange() throws Exception { - String startDate = getLocalizedDate(2002, 1, 1, false); - String endDate = getLocalizedDate(2002, 1, 4, false); - Calendar endDateExpected = Calendar.getInstance(); - endDateExpected.set(2002, 1, 4, 23, 59, 59); - endDateExpected.set(Calendar.MILLISECOND, 999); - final String defaultField = "default"; - final String monthField = "month"; - final String hourField = "hour"; - QueryParser qp = new QueryParser("field", new SimpleAnalyzer()); - - // Don't set any date resolution and verify if DateField is used - assertDateRangeQueryEquals(qp, defaultField, startDate, endDate, - endDateExpected.getTime(), null); - - // set a field specific date resolution - qp.setDateResolution(monthField, DateTools.Resolution.MONTH); - - // DateField should still be used for defaultField - assertDateRangeQueryEquals(qp, defaultField, startDate, endDate, - endDateExpected.getTime(), null); - - // set default date resolution to MILLISECOND - qp.setDateResolution(DateTools.Resolution.MILLISECOND); - - // set second field specific date resolution - qp.setDateResolution(hourField, DateTools.Resolution.HOUR); - - // for this field no field specific date resolution has been set, - // so verify if the default resolution is used - assertDateRangeQueryEquals(qp, defaultField, startDate, endDate, - endDateExpected.getTime(), DateTools.Resolution.MILLISECOND); - - // verify if field specific date resolutions are used for these two fields - assertDateRangeQueryEquals(qp, monthField, startDate, endDate, - endDateExpected.getTime(), DateTools.Resolution.MONTH); - - assertDateRangeQueryEquals(qp, hourField, startDate, endDate, - endDateExpected.getTime(), DateTools.Resolution.HOUR); - } - - public void assertDateRangeQueryEquals(QueryParser qp, String field, String startDate, String endDate, - Date endDateInclusive, DateTools.Resolution resolution) throws Exception { - assertQueryEquals(qp, field, field + ":[" + startDate + " TO " + endDate + "]", - "[" + getDate(startDate, resolution) + " TO " + getDate(endDateInclusive, resolution) + "]"); - assertQueryEquals(qp, field, field + ":{" + startDate + " TO " + endDate + "}", - "{" + getDate(startDate, resolution) + " TO " + getDate(endDate, resolution) + "}"); - } - - public void testEscaped() throws Exception { - Analyzer a = new WhitespaceAnalyzer(); - - /*assertQueryEquals("\\[brackets", a, "\\[brackets"); - assertQueryEquals("\\[brackets", null, "brackets"); - assertQueryEquals("\\\\", a, "\\\\"); - assertQueryEquals("\\+blah", a, "\\+blah"); - assertQueryEquals("\\(blah", a, "\\(blah"); - - assertQueryEquals("\\-blah", a, "\\-blah"); - assertQueryEquals("\\!blah", a, "\\!blah"); - assertQueryEquals("\\{blah", a, "\\{blah"); - assertQueryEquals("\\}blah", a, "\\}blah"); - assertQueryEquals("\\:blah", a, "\\:blah"); - assertQueryEquals("\\^blah", a, "\\^blah"); - assertQueryEquals("\\[blah", a, "\\[blah"); - assertQueryEquals("\\]blah", a, "\\]blah"); - assertQueryEquals("\\\"blah", a, "\\\"blah"); - assertQueryEquals("\\(blah", a, "\\(blah"); - assertQueryEquals("\\)blah", a, "\\)blah"); - assertQueryEquals("\\~blah", a, "\\~blah"); - assertQueryEquals("\\*blah", a, "\\*blah"); - assertQueryEquals("\\?blah", a, "\\?blah"); - //assertQueryEquals("foo \\&\\& bar", a, "foo \\&\\& bar"); - //assertQueryEquals("foo \\|| bar", a, "foo \\|| bar"); - //assertQueryEquals("foo \\AND bar", a, "foo \\AND bar");*/ - - assertQueryEquals("\\a", a, "a"); - - assertQueryEquals("a\\-b:c", a, "a-b:c"); - assertQueryEquals("a\\+b:c", a, "a+b:c"); - assertQueryEquals("a\\:b:c", a, "a:b:c"); - assertQueryEquals("a\\\\b:c", a, "a\\b:c"); - - assertQueryEquals("a:b\\-c", a, "a:b-c"); - assertQueryEquals("a:b\\+c", a, "a:b+c"); - assertQueryEquals("a:b\\:c", a, "a:b:c"); - assertQueryEquals("a:b\\\\c", a, "a:b\\c"); - - assertQueryEquals("a:b\\-c*", a, "a:b-c*"); - assertQueryEquals("a:b\\+c*", a, "a:b+c*"); - assertQueryEquals("a:b\\:c*", a, "a:b:c*"); - - assertQueryEquals("a:b\\\\c*", a, "a:b\\c*"); - - assertQueryEquals("a:b\\-?c", a, "a:b-?c"); - assertQueryEquals("a:b\\+?c", a, "a:b+?c"); - assertQueryEquals("a:b\\:?c", a, "a:b:?c"); - - assertQueryEquals("a:b\\\\?c", a, "a:b\\?c"); - - assertQueryEquals("a:b\\-c~", a, "a:b-c~0.5"); - assertQueryEquals("a:b\\+c~", a, "a:b+c~0.5"); - assertQueryEquals("a:b\\:c~", a, "a:b:c~0.5"); - assertQueryEquals("a:b\\\\c~", a, "a:b\\c~0.5"); - - assertQueryEquals("[ a\\- TO a\\+ ]", null, "[a- TO a+]"); - assertQueryEquals("[ a\\: TO a\\~ ]", null, "[a: TO a~]"); - assertQueryEquals("[ a\\\\ TO a\\* ]", null, "[a\\ TO a*]"); - - assertQueryEquals("[\"c\\:\\\\temp\\\\\\~foo0.txt\" TO \"c\\:\\\\temp\\\\\\~foo9.txt\"]", a, - "[c:\\temp\\~foo0.txt TO c:\\temp\\~foo9.txt]"); - - assertQueryEquals("a\\\\\\+b", a, "a\\+b"); - - assertQueryEquals("a \\\"b c\\\" d", a, "a \"b c\" d"); - assertQueryEquals("\"a \\\"b c\\\" d\"", a, "\"a \"b c\" d\""); - assertQueryEquals("\"a \\+b c d\"", a, "\"a +b c d\""); - - assertQueryEquals("c\\:\\\\temp\\\\\\~foo.txt", a, "c:\\temp\\~foo.txt"); - - assertParseException("XY\\"); // there must be a character after the escape char - - // test unicode escaping - assertQueryEquals("a\\u0062c", a, "abc"); - assertQueryEquals("XY\\u005a", a, "XYZ"); - assertQueryEquals("XY\\u005A", a, "XYZ"); - assertQueryEquals("\"a \\\\\\u0028\\u0062\\\" c\"", a, "\"a \\(b\" c\""); - - assertParseException("XY\\u005G"); // test non-hex character in escaped unicode sequence - assertParseException("XY\\u005"); // test incomplete escaped unicode sequence - - // Tests bug LUCENE-800 - assertQueryEquals("(item:\\\\ item:ABCD\\\\)", a, "item:\\ item:ABCD\\"); - assertParseException("(item:\\\\ item:ABCD\\\\))"); // unmatched closing paranthesis - assertQueryEquals("\\*", a, "*"); - assertQueryEquals("\\\\", a, "\\"); // escaped backslash - - assertParseException("\\"); // a backslash must always be escaped - - // LUCENE-1189 - assertQueryEquals("(\"a\\\\\") or (\"b\")", a ,"a\\ or b"); - } - - public void testQueryStringEscaping() throws Exception { - Analyzer a = new WhitespaceAnalyzer(); - - assertEscapedQueryEquals("a-b:c", a, "a\\-b\\:c"); - assertEscapedQueryEquals("a+b:c", a, "a\\+b\\:c"); - assertEscapedQueryEquals("a:b:c", a, "a\\:b\\:c"); - assertEscapedQueryEquals("a\\b:c", a, "a\\\\b\\:c"); - - assertEscapedQueryEquals("a:b-c", a, "a\\:b\\-c"); - assertEscapedQueryEquals("a:b+c", a, "a\\:b\\+c"); - assertEscapedQueryEquals("a:b:c", a, "a\\:b\\:c"); - assertEscapedQueryEquals("a:b\\c", a, "a\\:b\\\\c"); - - assertEscapedQueryEquals("a:b-c*", a, "a\\:b\\-c\\*"); - assertEscapedQueryEquals("a:b+c*", a, "a\\:b\\+c\\*"); - assertEscapedQueryEquals("a:b:c*", a, "a\\:b\\:c\\*"); - - assertEscapedQueryEquals("a:b\\\\c*", a, "a\\:b\\\\\\\\c\\*"); - - assertEscapedQueryEquals("a:b-?c", a, "a\\:b\\-\\?c"); - assertEscapedQueryEquals("a:b+?c", a, "a\\:b\\+\\?c"); - assertEscapedQueryEquals("a:b:?c", a, "a\\:b\\:\\?c"); - - assertEscapedQueryEquals("a:b?c", a, "a\\:b\\?c"); - - assertEscapedQueryEquals("a:b-c~", a, "a\\:b\\-c\\~"); - assertEscapedQueryEquals("a:b+c~", a, "a\\:b\\+c\\~"); - assertEscapedQueryEquals("a:b:c~", a, "a\\:b\\:c\\~"); - assertEscapedQueryEquals("a:b\\c~", a, "a\\:b\\\\c\\~"); - - assertEscapedQueryEquals("[ a - TO a+ ]", null, "\\[ a \\- TO a\\+ \\]"); - assertEscapedQueryEquals("[ a : TO a~ ]", null, "\\[ a \\: TO a\\~ \\]"); - assertEscapedQueryEquals("[ a\\ TO a* ]", null, "\\[ a\\\\ TO a\\* \\]"); - - // LUCENE-881 - assertEscapedQueryEquals("|| abc ||", a, "\\|\\| abc \\|\\|"); - assertEscapedQueryEquals("&& abc &&", a, "\\&\\& abc \\&\\&"); - } - - public void testTabNewlineCarriageReturn() - throws Exception { - assertQueryEqualsDOA("+weltbank +worlbank", null, - "+weltbank +worlbank"); - - assertQueryEqualsDOA("+weltbank\n+worlbank", null, - "+weltbank +worlbank"); - assertQueryEqualsDOA("weltbank \n+worlbank", null, - "+weltbank +worlbank"); - assertQueryEqualsDOA("weltbank \n +worlbank", null, - "+weltbank +worlbank"); - - assertQueryEqualsDOA("+weltbank\r+worlbank", null, - "+weltbank +worlbank"); - assertQueryEqualsDOA("weltbank \r+worlbank", null, - "+weltbank +worlbank"); - assertQueryEqualsDOA("weltbank \r +worlbank", null, - "+weltbank +worlbank"); - - assertQueryEqualsDOA("+weltbank\r\n+worlbank", null, - "+weltbank +worlbank"); - assertQueryEqualsDOA("weltbank \r\n+worlbank", null, - "+weltbank +worlbank"); - assertQueryEqualsDOA("weltbank \r\n +worlbank", null, - "+weltbank +worlbank"); - assertQueryEqualsDOA("weltbank \r \n +worlbank", null, - "+weltbank +worlbank"); - - assertQueryEqualsDOA("+weltbank\t+worlbank", null, - "+weltbank +worlbank"); - assertQueryEqualsDOA("weltbank \t+worlbank", null, - "+weltbank +worlbank"); - assertQueryEqualsDOA("weltbank \t +worlbank", null, - "+weltbank +worlbank"); - } - - public void testSimpleDAO() - throws Exception { - assertQueryEqualsDOA("term term term", null, "+term +term +term"); - assertQueryEqualsDOA("term +term term", null, "+term +term +term"); - assertQueryEqualsDOA("term term +term", null, "+term +term +term"); - assertQueryEqualsDOA("term +term +term", null, "+term +term +term"); - assertQueryEqualsDOA("-term term term", null, "-term +term +term"); - } - - public void testBoost() - throws Exception { - StandardAnalyzer oneStopAnalyzer = new StandardAnalyzer(new String[]{"on"}); - QueryParser qp = new QueryParser("field", oneStopAnalyzer); - Query q = qp.parse("on^1.0"); - assertNotNull(q); - q = qp.parse("\"hello\"^2.0"); - assertNotNull(q); - assertEquals(q.getBoost(), (float) 2.0, (float) 0.5); - q = qp.parse("hello^2.0"); - assertNotNull(q); - assertEquals(q.getBoost(), (float) 2.0, (float) 0.5); - q = qp.parse("\"on\"^1.0"); - assertNotNull(q); - - QueryParser qp2 = new QueryParser("field", new StandardAnalyzer()); - q = qp2.parse("the^3"); - // "the" is a stop word so the result is an empty query: - assertNotNull(q); - assertEquals("", q.toString()); - assertEquals(1.0f, q.getBoost(), 0.01f); - } - - public void assertParseException(String queryString) throws Exception { - try { - getQuery(queryString, null); - } catch (ParseException expected) { - return; - } - fail("ParseException expected, not thrown"); - } - - public void testException() throws Exception { - assertParseException("\"some phrase"); - assertParseException("(foo bar"); - assertParseException("foo bar))"); - assertParseException("field:term:with:colon some more terms"); - assertParseException("(sub query)^5.0^2.0 plus more"); - assertParseException("secret AND illegal) AND access:confidential"); - } - - - public void testCustomQueryParserWildcard() { - try { - new QPTestParser("contents", new WhitespaceAnalyzer()).parse("a?t"); - fail("Wildcard queries should not be allowed"); - } catch (ParseException expected) { - // expected exception - } - } - - public void testCustomQueryParserFuzzy() throws Exception { - try { - new QPTestParser("contents", new WhitespaceAnalyzer()).parse("xunit~"); - fail("Fuzzy queries should not be allowed"); - } catch (ParseException expected) { - // expected exception - } - } - - public void testBooleanQuery() throws Exception { - BooleanQuery.setMaxClauseCount(2); - try { - QueryParser qp = new QueryParser("field", new WhitespaceAnalyzer()); - qp.parse("one two three"); - fail("ParseException expected due to too many boolean clauses"); - } catch (ParseException expected) { - // too many boolean clauses, so ParseException is expected - } - } - - /** - * This test differs from TestPrecedenceQueryParser - */ - public void testPrecedence() throws Exception { - QueryParser qp = new QueryParser("field", new WhitespaceAnalyzer()); - Query query1 = qp.parse("A AND B OR C AND D"); - Query query2 = qp.parse("+A +B +C +D"); - assertEquals(query1, query2); - } - - public void testLocalDateFormat() throws IOException, ParseException { - RAMDirectory ramDir = new RAMDirectory(); - IndexWriter iw = new IndexWriter(ramDir, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED); - addDateDoc("a", 2005, 12, 2, 10, 15, 33, iw); - addDateDoc("b", 2005, 12, 4, 22, 15, 00, iw); - iw.close(); - IndexSearcher is = new IndexSearcher(ramDir); - assertHits(1, "[12/1/2005 TO 12/3/2005]", is); - assertHits(2, "[12/1/2005 TO 12/4/2005]", is); - assertHits(1, "[12/3/2005 TO 12/4/2005]", is); - assertHits(1, "{12/1/2005 TO 12/3/2005}", is); - assertHits(1, "{12/1/2005 TO 12/4/2005}", is); - assertHits(0, "{12/3/2005 TO 12/4/2005}", is); - is.close(); - } - - public void testStarParsing() throws Exception { - final int[] type = new int[1]; - QueryParser qp = new QueryParser("field", new WhitespaceAnalyzer()) { - protected Query getWildcardQuery(String field, String termStr) throws ParseException { - // override error checking of superclass - type[0]=1; - return new TermQuery(new Term(field,termStr)); - } - protected Query getPrefixQuery(String field, String termStr) throws ParseException { - // override error checking of superclass - type[0]=2; - return new TermQuery(new Term(field,termStr)); - } - - protected Query getFieldQuery(String field, String queryText) throws ParseException { - type[0]=3; - return super.getFieldQuery(field, queryText); - } - }; - - TermQuery tq; - - tq = (TermQuery)qp.parse("foo:zoo*"); - assertEquals("zoo",tq.getTerm().text()); - assertEquals(2,type[0]); - - tq = (TermQuery)qp.parse("foo:zoo*^2"); - assertEquals("zoo",tq.getTerm().text()); - assertEquals(2,type[0]); - assertEquals(tq.getBoost(),2,0); - - tq = (TermQuery)qp.parse("foo:*"); - assertEquals("*",tq.getTerm().text()); - assertEquals(1,type[0]); // could be a valid prefix query in the future too - - tq = (TermQuery)qp.parse("foo:*^2"); - assertEquals("*",tq.getTerm().text()); - assertEquals(1,type[0]); - assertEquals(tq.getBoost(),2,0); - - tq = (TermQuery)qp.parse("*:foo"); - assertEquals("*",tq.getTerm().field()); - assertEquals("foo",tq.getTerm().text()); - assertEquals(3,type[0]); - - tq = (TermQuery)qp.parse("*:*"); - assertEquals("*",tq.getTerm().field()); - assertEquals("*",tq.getTerm().text()); - assertEquals(1,type[0]); // could be handled as a prefix query in the future - - tq = (TermQuery)qp.parse("(*:*)"); - assertEquals("*",tq.getTerm().field()); - assertEquals("*",tq.getTerm().text()); - assertEquals(1,type[0]); - - } - - public void testStopwords() throws Exception { - QueryParser qp = new QueryParser("a", new StopAnalyzer(new String[]{"the", "foo"})); - Query result = qp.parse("a:the OR a:foo"); - assertNotNull("result is null and it shouldn't be", result); - assertTrue("result is not a BooleanQuery", result instanceof BooleanQuery); - assertTrue(((BooleanQuery) result).clauses().size() + " does not equal: " + 0, ((BooleanQuery) result).clauses().size() == 0); - result = qp.parse("a:woo OR a:the"); - assertNotNull("result is null and it shouldn't be", result); - assertTrue("result is not a TermQuery", result instanceof TermQuery); - result = qp.parse("(fieldX:xxxxx OR fieldy:xxxxxxxx)^2 AND (fieldx:the OR fieldy:foo)"); - assertNotNull("result is null and it shouldn't be", result); - assertTrue("result is not a BooleanQuery", result instanceof BooleanQuery); - System.out.println("Result: " + result); - assertTrue(((BooleanQuery) result).clauses().size() + " does not equal: " + 2, ((BooleanQuery) result).clauses().size() == 2); - } - - public void testPositionIncrement() throws Exception { - boolean dflt = StopFilter.getEnablePositionIncrementsDefault(); - StopFilter.setEnablePositionIncrementsDefault(true); - try { - QueryParser qp = new QueryParser("a", new StopAnalyzer(new String[]{"the", "in", "are", "this"})); - qp.setEnablePositionIncrements(true); - String qtxt = "\"the words in poisitions pos02578 are stopped in this phrasequery\""; - // 0 2 5 7 8 - int expectedPositions[] = {1,3,4,6,9}; - PhraseQuery pq = (PhraseQuery) qp.parse(qtxt); - //System.out.println("Query text: "+qtxt); - //System.out.println("Result: "+pq); - Term t[] = pq.getTerms(); - int pos[] = pq.getPositions(); - for (int i = 0; i < t.length; i++) { - //System.out.println(i+". "+t[i]+" pos: "+pos[i]); - assertEquals("term "+i+" = "+t[i]+" has wrong term-position!",expectedPositions[i],pos[i]); - } - } finally { - StopFilter.setEnablePositionIncrementsDefault(dflt); - } - } - - public void testMatchAllDocs() throws Exception { - QueryParser qp = new QueryParser("field", new WhitespaceAnalyzer()); - assertEquals(new MatchAllDocsQuery(), qp.parse("*:*")); - assertEquals(new MatchAllDocsQuery(), qp.parse("(*:*)")); - BooleanQuery bq = (BooleanQuery)qp.parse("+*:* -*:*"); - assertTrue(bq.getClauses()[0].getQuery() instanceof MatchAllDocsQuery); - assertTrue(bq.getClauses()[1].getQuery() instanceof MatchAllDocsQuery); - } - - private void assertHits(int expected, String query, IndexSearcher is) throws ParseException, IOException { - QueryParser qp = new QueryParser("date", new WhitespaceAnalyzer()); - qp.setLocale(Locale.ENGLISH); - Query q = qp.parse(query); - ScoreDoc[] hits = is.search(q, null, 1000).scoreDocs; - assertEquals(expected, hits.length); - } - - private static void addDateDoc(String content, int year, int month, - int day, int hour, int minute, int second, IndexWriter iw) throws IOException { - Document d = new Document(); - d.add(new Field("f", content, Field.Store.YES, Field.Index.ANALYZED)); - Calendar cal = Calendar.getInstance(); - cal.set(year, month-1, day, hour, minute, second); - d.add(new Field("date", DateField.dateToString(cal.getTime()), Field.Store.YES, Field.Index.NOT_ANALYZED)); - iw.addDocument(d); - } - - public void tearDown() throws Exception { - super.tearDown(); - BooleanQuery.setMaxClauseCount(originalMaxClauses); - } - -} Index: src/test/org/apache/lucene/queryParser/TestMultiAnalyzer.java =================================================================== --- src/test/org/apache/lucene/queryParser/TestMultiAnalyzer.java (revision 757685) +++ src/test/org/apache/lucene/queryParser/TestMultiAnalyzer.java (working copy) @@ -1,273 +0,0 @@ -package org.apache.lucene.queryParser; - -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -import java.io.IOException; -import java.io.Reader; - -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.LowerCaseFilter; -import org.apache.lucene.analysis.TokenFilter; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.standard.StandardTokenizer; -import org.apache.lucene.analysis.tokenattributes.OffsetAttribute; -import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute; -import org.apache.lucene.analysis.tokenattributes.TermAttribute; -import org.apache.lucene.analysis.tokenattributes.TypeAttribute; -import org.apache.lucene.search.Query; -import org.apache.lucene.util.LuceneTestCase; - -/** - * Test QueryParser's ability to deal with Analyzers that return more - * than one token per position or that return tokens with a position - * increment > 1. - * - */ -public class TestMultiAnalyzer extends LuceneTestCase { - - private static int multiToken = 0; - - public void testMultiAnalyzer() throws ParseException { - - QueryParser qp = new QueryParser("", new MultiAnalyzer()); - - // trivial, no multiple tokens: - assertEquals("foo", qp.parse("foo").toString()); - assertEquals("foo", qp.parse("\"foo\"").toString()); - assertEquals("foo foobar", qp.parse("foo foobar").toString()); - assertEquals("\"foo foobar\"", qp.parse("\"foo foobar\"").toString()); - assertEquals("\"foo foobar blah\"", qp.parse("\"foo foobar blah\"").toString()); - - // two tokens at the same position: - assertEquals("(multi multi2) foo", qp.parse("multi foo").toString()); - assertEquals("foo (multi multi2)", qp.parse("foo multi").toString()); - assertEquals("(multi multi2) (multi multi2)", qp.parse("multi multi").toString()); - assertEquals("+(foo (multi multi2)) +(bar (multi multi2))", - qp.parse("+(foo multi) +(bar multi)").toString()); - assertEquals("+(foo (multi multi2)) field:\"bar (multi multi2)\"", - qp.parse("+(foo multi) field:\"bar multi\"").toString()); - - // phrases: - assertEquals("\"(multi multi2) foo\"", qp.parse("\"multi foo\"").toString()); - assertEquals("\"foo (multi multi2)\"", qp.parse("\"foo multi\"").toString()); - assertEquals("\"foo (multi multi2) foobar (multi multi2)\"", - qp.parse("\"foo multi foobar multi\"").toString()); - - // fields: - assertEquals("(field:multi field:multi2) field:foo", qp.parse("field:multi field:foo").toString()); - assertEquals("field:\"(multi multi2) foo\"", qp.parse("field:\"multi foo\"").toString()); - - // three tokens at one position: - assertEquals("triplemulti multi3 multi2", qp.parse("triplemulti").toString()); - assertEquals("foo (triplemulti multi3 multi2) foobar", - qp.parse("foo triplemulti foobar").toString()); - - // phrase with non-default slop: - assertEquals("\"(multi multi2) foo\"~10", qp.parse("\"multi foo\"~10").toString()); - - // phrase with non-default boost: - assertEquals("\"(multi multi2) foo\"^2.0", qp.parse("\"multi foo\"^2").toString()); - - // phrase after changing default slop - qp.setPhraseSlop(99); - assertEquals("\"(multi multi2) foo\"~99 bar", - qp.parse("\"multi foo\" bar").toString()); - assertEquals("\"(multi multi2) foo\"~99 \"foo bar\"~2", - qp.parse("\"multi foo\" \"foo bar\"~2").toString()); - qp.setPhraseSlop(0); - - // non-default operator: - qp.setDefaultOperator(QueryParser.AND_OPERATOR); - assertEquals("+(multi multi2) +foo", qp.parse("multi foo").toString()); - - } - - public void testMultiAnalyzerWithSubclassOfQueryParser() throws ParseException { - - DumbQueryParser qp = new DumbQueryParser("", new MultiAnalyzer()); - qp.setPhraseSlop(99); // modified default slop - - // direct call to (super's) getFieldQuery to demonstrate differnce - // between phrase and multiphrase with modified default slop - assertEquals("\"foo bar\"~99", - qp.getSuperFieldQuery("","foo bar").toString()); - assertEquals("\"(multi multi2) bar\"~99", - qp.getSuperFieldQuery("","multi bar").toString()); - - - // ask sublcass to parse phrase with modified default slop - assertEquals("\"(multi multi2) foo\"~99 bar", - qp.parse("\"multi foo\" bar").toString()); - - } - - public void testPosIncrementAnalyzer() throws ParseException { - QueryParser qp = new QueryParser("", new PosIncrementAnalyzer()); - assertEquals("quick brown", qp.parse("the quick brown").toString()); - assertEquals("\"quick brown\"", qp.parse("\"the quick brown\"").toString()); - assertEquals("quick brown fox", qp.parse("the quick brown fox").toString()); - assertEquals("\"quick brown fox\"", qp.parse("\"the quick brown fox\"").toString()); - } - - /** - * Expands "multi" to "multi" and "multi2", both at the same position, - * and expands "triplemulti" to "triplemulti", "multi3", and "multi2". - */ - private class MultiAnalyzer extends Analyzer { - - public MultiAnalyzer() { - } - - public TokenStream tokenStream(String fieldName, Reader reader) { - TokenStream result = new StandardTokenizer(reader); - result = new TestFilter(result); - result = new LowerCaseFilter(result); - return result; - } - } - - private final class TestFilter extends TokenFilter { - - private String prevType; - private int prevStartOffset; - private int prevEndOffset; - - TermAttribute termAtt; - PositionIncrementAttribute posIncrAtt; - OffsetAttribute offsetAtt; - TypeAttribute typeAtt; - - public TestFilter(TokenStream in) { - super(in); - termAtt = (TermAttribute) addAttribute(TermAttribute.class); - posIncrAtt = (PositionIncrementAttribute) addAttribute(PositionIncrementAttribute.class); - offsetAtt = (OffsetAttribute) addAttribute(OffsetAttribute.class); - typeAtt = (TypeAttribute) addAttribute(TypeAttribute.class); - } - - public final boolean incrementToken() throws java.io.IOException { - if (multiToken > 0) { - termAtt.setTermBuffer("multi"+(multiToken+1)); - offsetAtt.setStartOffset(prevStartOffset); - offsetAtt.setEndOffset(prevEndOffset); - typeAtt.setType(prevType); - posIncrAtt.setPositionIncrement(0); - multiToken--; - return true; - } else { - boolean next = input.incrementToken(); - if (next == false) { - return false; - } - prevType = typeAtt.type(); - prevStartOffset = offsetAtt.startOffset(); - prevEndOffset = offsetAtt.endOffset(); - String text = termAtt.term(); - if (text.equals("triplemulti")) { - multiToken = 2; - return true; - } else if (text.equals("multi")) { - multiToken = 1; - return true; - } else { - return true; - } - } - } - } - - /** - * Analyzes "the quick brown" as: quick(incr=2) brown(incr=1). - * Does not work correctly for input other than "the quick brown ...". - */ - private class PosIncrementAnalyzer extends Analyzer { - - public PosIncrementAnalyzer() { - } - - public TokenStream tokenStream(String fieldName, Reader reader) { - TokenStream result = new StandardTokenizer(reader); - result = new TestPosIncrementFilter(result); - result = new LowerCaseFilter(result); - return result; - } - } - - private final class TestPosIncrementFilter extends TokenFilter { - - TermAttribute termAtt; - PositionIncrementAttribute posIncrAtt; - - public TestPosIncrementFilter(TokenStream in) { - super(in); - termAtt = (TermAttribute) addAttribute(TermAttribute.class); - posIncrAtt = (PositionIncrementAttribute) addAttribute(PositionIncrementAttribute.class); - } - - public final boolean incrementToken () throws java.io.IOException { - while(input.incrementToken()) { - if (termAtt.term().equals("the")) { - // stopword, do nothing - } else if (termAtt.term().equals("quick")) { - posIncrAtt.setPositionIncrement(2); - return true; - } else { - posIncrAtt.setPositionIncrement(1); - return true; - } - } - return false; - } - } - - /** a very simple subclass of QueryParser */ - private final static class DumbQueryParser extends QueryParser { - - public DumbQueryParser(String f, Analyzer a) { - super(f, a); - } - - /** expose super's version */ - public Query getSuperFieldQuery(String f, String t) - throws ParseException { - return super.getFieldQuery(f,t); - } - /** wrap super's version */ - protected Query getFieldQuery(String f, String t) - throws ParseException { - return new DumbQueryWrapper(getSuperFieldQuery(f,t)); - } - } - - /** - * A very simple wrapper to prevent instanceof checks but uses - * the toString of the query it wraps. - */ - private final static class DumbQueryWrapper extends Query { - - private Query q; - public DumbQueryWrapper(Query q) { - super(); - this.q = q; - } - public String toString(String f) { - return q.toString(f); - } - } - -} Index: src/test/org/apache/lucene/queryParser/lucene2/LuceneQueryParserTestSuite.java =================================================================== --- src/test/org/apache/lucene/queryParser/lucene2/LuceneQueryParserTestSuite.java (revision 0) +++ src/test/org/apache/lucene/queryParser/lucene2/LuceneQueryParserTestSuite.java (revision 0) @@ -0,0 +1,41 @@ +package org.apache.lucene.queryParser.lucene2; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import junit.framework.Test; +import junit.framework.TestSuite; + +/** + * Test QueryParser's old testcases using the Flexible Query Parser + * wrappers to validate old testcases + * + */ +public class LuceneQueryParserTestSuite { + + public static Test suite() { + TestSuite suite = new TestSuite("Apache Lucene query parser test cases"); + + suite.addTestSuite(org.apache.lucene.queryParser.lucene2.TestMultiAnalyzer.class); + suite.addTestSuite(org.apache.lucene.queryParser.lucene2.TestMultiFieldQueryParser.class); + suite.addTestSuite(org.apache.lucene.queryParser.lucene2.TestQueryParser.class); + + return suite; + + } + +} Index: src/test/org/apache/lucene/queryParser/lucene2/TestMultiAnalyzer.java =================================================================== --- src/test/org/apache/lucene/queryParser/lucene2/TestMultiAnalyzer.java (revision 0) +++ src/test/org/apache/lucene/queryParser/lucene2/TestMultiAnalyzer.java (revision 0) @@ -0,0 +1,305 @@ +package org.apache.lucene.queryParser.lucene2; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.IOException; +import java.io.Reader; + +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.analysis.LowerCaseFilter; +import org.apache.lucene.analysis.Token; +import org.apache.lucene.analysis.TokenFilter; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.analysis.standard.StandardTokenizer; +import org.apache.lucene.analysis.tokenattributes.OffsetAttribute; +import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute; +import org.apache.lucene.analysis.tokenattributes.TermAttribute; +import org.apache.lucene.analysis.tokenattributes.TypeAttribute; +import org.apache.lucene.queryParser.ParseException; +import org.apache.lucene.util.LuceneTestCase; + +/** + * Test QueryParser's ability to deal with Analyzers that return more + * than one token per position or that return tokens with a position + * increment > 1. + * + */ +public class TestMultiAnalyzer extends LuceneTestCase { + + private static int multiToken = 0; + + public void testMultiAnalyzer() throws ParseException { + + QueryParserWrapper qp = new QueryParserWrapper("", new MultiAnalyzer()); + + // trivial, no multiple tokens: + assertEquals("foo", qp.parse("foo").toString()); + assertEquals("foo", qp.parse("\"foo\"").toString()); + assertEquals("foo foobar", qp.parse("foo foobar").toString()); + assertEquals("\"foo foobar\"", qp.parse("\"foo foobar\"").toString()); + assertEquals("\"foo foobar blah\"", qp.parse("\"foo foobar blah\"").toString()); + + // two tokens at the same position: + assertEquals("(multi multi2) foo", qp.parse("multi foo").toString()); + assertEquals("foo (multi multi2)", qp.parse("foo multi").toString()); + assertEquals("(multi multi2) (multi multi2)", qp.parse("multi multi").toString()); + assertEquals("+(foo (multi multi2)) +(bar (multi multi2))", + qp.parse("+(foo multi) +(bar multi)").toString()); + assertEquals("+(foo (multi multi2)) field:\"bar (multi multi2)\"", + qp.parse("+(foo multi) field:\"bar multi\"").toString()); + + // phrases: + assertEquals("\"(multi multi2) foo\"", qp.parse("\"multi foo\"").toString()); + assertEquals("\"foo (multi multi2)\"", qp.parse("\"foo multi\"").toString()); + assertEquals("\"foo (multi multi2) foobar (multi multi2)\"", + qp.parse("\"foo multi foobar multi\"").toString()); + + // fields: + assertEquals("(field:multi field:multi2) field:foo", qp.parse("field:multi field:foo").toString()); + assertEquals("field:\"(multi multi2) foo\"", qp.parse("field:\"multi foo\"").toString()); + + // three tokens at one position: + assertEquals("triplemulti multi3 multi2", qp.parse("triplemulti").toString()); + assertEquals("foo (triplemulti multi3 multi2) foobar", + qp.parse("foo triplemulti foobar").toString()); + + // phrase with non-default slop: + assertEquals("\"(multi multi2) foo\"~10", qp.parse("\"multi foo\"~10").toString()); + + // phrase with non-default boost: + assertEquals("\"(multi multi2) foo\"^2.0", qp.parse("\"multi foo\"^2").toString()); + + // phrase after changing default slop + qp.setPhraseSlop(99); + assertEquals("\"(multi multi2) foo\"~99 bar", + qp.parse("\"multi foo\" bar").toString()); + assertEquals("\"(multi multi2) foo\"~99 \"foo bar\"~2", + qp.parse("\"multi foo\" \"foo bar\"~2").toString()); + qp.setPhraseSlop(0); + + // non-default operator: + qp.setDefaultOperator(QueryParserWrapper.AND_OPERATOR); + assertEquals("+(multi multi2) +foo", qp.parse("multi foo").toString()); + + } + +// public void testMultiAnalyzerWithSubclassOfQueryParser() throws ParseException { +// this test doesn't make sense when using the new QueryParser API +// DumbQueryParser qp = new DumbQueryParser("", new MultiAnalyzer()); +// qp.setPhraseSlop(99); // modified default slop +// +// // direct call to (super's) getFieldQuery to demonstrate differnce +// // between phrase and multiphrase with modified default slop +// assertEquals("\"foo bar\"~99", +// qp.getSuperFieldQuery("","foo bar").toString()); +// assertEquals("\"(multi multi2) bar\"~99", +// qp.getSuperFieldQuery("","multi bar").toString()); +// +// +// // ask sublcass to parse phrase with modified default slop +// assertEquals("\"(multi multi2) foo\"~99 bar", +// qp.parse("\"multi foo\" bar").toString()); +// +// } + + public void testPosIncrementAnalyzer() throws ParseException { + QueryParserWrapper qp = new QueryParserWrapper("", new PosIncrementAnalyzer()); + assertEquals("quick brown", qp.parse("the quick brown").toString()); + assertEquals("\"quick brown\"", qp.parse("\"the quick brown\"").toString()); + assertEquals("quick brown fox", qp.parse("the quick brown fox").toString()); + assertEquals("\"quick brown fox\"", qp.parse("\"the quick brown fox\"").toString()); + } + + /** + * Expands "multi" to "multi" and "multi2", both at the same position, + * and expands "triplemulti" to "triplemulti", "multi3", and "multi2". + */ + private class MultiAnalyzer extends Analyzer { + + public MultiAnalyzer() { + } + + public TokenStream tokenStream(String fieldName, Reader reader) { + TokenStream result = new StandardTokenizer(reader); + result = new TestFilter(result); + result = new LowerCaseFilter(result); + return result; + } + } + + private final class TestFilter extends TokenFilter { + + private String prevType; + private int prevStartOffset; + private int prevEndOffset; + + TermAttribute termAtt; + PositionIncrementAttribute posIncrAtt; + OffsetAttribute offsetAtt; + TypeAttribute typeAtt; + + public TestFilter(TokenStream in) { + super(in); + termAtt = (TermAttribute) addAttribute(TermAttribute.class); + posIncrAtt = (PositionIncrementAttribute) addAttribute(PositionIncrementAttribute.class); + offsetAtt = (OffsetAttribute) addAttribute(OffsetAttribute.class); + typeAtt = (TypeAttribute) addAttribute(TypeAttribute.class); + + } + + /* (non-Javadoc) + * @see org.apache.lucene.analysis.TokenStream#next(org.apache.lucene.analysis.Token) + */ + @Override + public Token next(Token reusableToken) throws IOException { + + if (multiToken > 0) { + reusableToken.setTermBuffer("multi"+(multiToken+1)); + reusableToken.setStartOffset(prevStartOffset); + reusableToken.setEndOffset(prevEndOffset); + reusableToken.setType(prevType); + reusableToken.setPositionIncrement(0); + multiToken--; + return reusableToken; + } else { + boolean next = (reusableToken = input.next(token)) != null; + if (next == false) { + return null; + } + prevType = reusableToken.type(); + prevStartOffset = reusableToken.startOffset(); + prevEndOffset = reusableToken.endOffset(); + String text = reusableToken.term(); + if (text.equals("triplemulti")) { + multiToken = 2; + return reusableToken; + } else if (text.equals("multi")) { + multiToken = 1; + return reusableToken; + } else { + return reusableToken; + } + } + + + } + + private Token token = new Token(); + + public final boolean incrementToken() throws java.io.IOException { + if (multiToken > 0) { + termAtt.setTermBuffer("multi"+(multiToken+1)); + offsetAtt.setStartOffset(prevStartOffset); + offsetAtt.setEndOffset(prevEndOffset); + typeAtt.setType(prevType); + posIncrAtt.setPositionIncrement(0); + multiToken--; + return true; + } else { + boolean next = input.incrementToken(); + if (next == false) { + return false; + } + prevType = typeAtt.type(); + prevStartOffset = offsetAtt.startOffset(); + prevEndOffset = offsetAtt.endOffset(); + String text = termAtt.term(); + if (text.equals("triplemulti")) { + multiToken = 2; + return true; + } else if (text.equals("multi")) { + multiToken = 1; + return true; + } else { + return true; + } + } + } + + + + } + + /** + * Analyzes "the quick brown" as: quick(incr=2) brown(incr=1). + * Does not work correctly for input other than "the quick brown ...". + */ + private class PosIncrementAnalyzer extends Analyzer { + + public PosIncrementAnalyzer() { + } + + public TokenStream tokenStream(String fieldName, Reader reader) { + TokenStream result = new StandardTokenizer(reader); + result = new TestPosIncrementFilter(result); + result = new LowerCaseFilter(result); + return result; + } + } + + private class TestPosIncrementFilter extends TokenFilter { + + TermAttribute termAtt; + PositionIncrementAttribute posIncrAtt; + + public TestPosIncrementFilter(TokenStream in) { + super(in); + termAtt = (TermAttribute) addAttribute(TermAttribute.class); + posIncrAtt = (PositionIncrementAttribute) addAttribute(PositionIncrementAttribute.class); + } + + private Token token = new Token(); + + /* (non-Javadoc) + * @see org.apache.lucene.analysis.TokenStream#next() + */ + @Override + public Token next(Token reusableToken) throws IOException { + while(null != (reusableToken = input.next(token))) { + String term = reusableToken.term(); + if (term.equals("the")) { + // stopword, do nothing + } else if (term.equals("quick")) { + reusableToken.setPositionIncrement(2); + return reusableToken; + } else { + reusableToken.setPositionIncrement(1); + return reusableToken; + } + } + return null; + } + + public final boolean incrementToken () throws java.io.IOException { + while(input.incrementToken()) { + if (termAtt.term().equals("the")) { + // stopword, do nothing + } else if (termAtt.term().equals("quick")) { + posIncrAtt.setPositionIncrement(2); + return true; + } else { + posIncrAtt.setPositionIncrement(1); + return true; + } + } + return false; + } + + } + +} Index: src/test/org/apache/lucene/queryParser/lucene2/TestMultiFieldQueryParser.java =================================================================== --- src/test/org/apache/lucene/queryParser/lucene2/TestMultiFieldQueryParser.java (revision 0) +++ src/test/org/apache/lucene/queryParser/lucene2/TestMultiFieldQueryParser.java (revision 0) @@ -0,0 +1,328 @@ +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package org.apache.lucene.queryParser.lucene2; + +import java.io.Reader; +import java.util.HashMap; +import java.util.Map; + +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.analysis.Token; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.analysis.standard.StandardAnalyzer; +import org.apache.lucene.document.Document; +import org.apache.lucene.document.Field; +import org.apache.lucene.index.IndexWriter; +import org.apache.lucene.queryParser.ParseException; +import org.apache.lucene.search.BooleanClause; +import org.apache.lucene.search.IndexSearcher; +import org.apache.lucene.search.Query; +import org.apache.lucene.search.ScoreDoc; +import org.apache.lucene.search.BooleanClause.Occur; +import org.apache.lucene.store.Directory; +import org.apache.lucene.store.RAMDirectory; +import org.apache.lucene.util.LuceneTestCase; + +/** + * Tests QueryParser. + */ +public class TestMultiFieldQueryParser extends LuceneTestCase { + + /** test stop words arsing for both the non static form, and for the + * corresponding static form (qtxt, fields[]). */ + public void tesStopwordsParsing() throws Exception { + assertStopQueryEquals("one", "b:one t:one"); + assertStopQueryEquals("one stop", "b:one t:one"); + assertStopQueryEquals("one (stop)", "b:one t:one"); + assertStopQueryEquals("one ((stop))", "b:one t:one"); + assertStopQueryEquals("stop", ""); + assertStopQueryEquals("(stop)", ""); + assertStopQueryEquals("((stop))", ""); + } + + // verify parsing of query using a stopping analyzer + private void assertStopQueryEquals (String qtxt, String expectedRes) throws Exception { + String[] fields = {"b", "t"}; + Occur occur[] = {Occur.SHOULD, Occur.SHOULD}; + TestQueryParser.QPTestAnalyzer a = new TestQueryParser.QPTestAnalyzer(); + MultiFieldQueryParserWrapper mfqp = new MultiFieldQueryParserWrapper(fields, a); + + Query q = mfqp.parse(qtxt); + assertEquals(expectedRes, q.toString()); + + q = MultiFieldQueryParserWrapper.parse(qtxt, fields, occur, a); + assertEquals(expectedRes, q.toString()); + } + + public void testSimple() throws Exception { + String[] fields = {"b", "t"}; + MultiFieldQueryParserWrapper mfqp = new MultiFieldQueryParserWrapper(fields, new StandardAnalyzer()); + + Query q = mfqp.parse("one"); + assertEquals("b:one t:one", q.toString()); + + q = mfqp.parse("one two"); + assertEquals("(b:one t:one) (b:two t:two)", q.toString()); + + q = mfqp.parse("+one +two"); + assertEquals("+(b:one t:one) +(b:two t:two)", q.toString()); + + q = mfqp.parse("+one -two -three"); + assertEquals("+(b:one t:one) -(b:two t:two) -(b:three t:three)", q.toString()); + + q = mfqp.parse("one^2 two"); + assertEquals("((b:one t:one)^2.0) (b:two t:two)", q.toString()); + + q = mfqp.parse("one~ two"); + assertEquals("(b:one~0.5 t:one~0.5) (b:two t:two)", q.toString()); + + q = mfqp.parse("one~0.8 two^2"); + assertEquals("(b:one~0.8 t:one~0.8) ((b:two t:two)^2.0)", q.toString()); + + q = mfqp.parse("one* two*"); + assertEquals("(b:one* t:one*) (b:two* t:two*)", q.toString()); + + q = mfqp.parse("[a TO c] two"); + assertEquals("(b:[a TO c] t:[a TO c]) (b:two t:two)", q.toString()); + + q = mfqp.parse("w?ldcard"); + assertEquals("b:w?ldcard t:w?ldcard", q.toString()); + + q = mfqp.parse("\"foo bar\""); + assertEquals("b:\"foo bar\" t:\"foo bar\"", q.toString()); + + q = mfqp.parse("\"aa bb cc\" \"dd ee\""); + assertEquals("(b:\"aa bb cc\" t:\"aa bb cc\") (b:\"dd ee\" t:\"dd ee\")", q.toString()); + + q = mfqp.parse("\"foo bar\"~4"); + assertEquals("b:\"foo bar\"~4 t:\"foo bar\"~4", q.toString()); + + // LUCENE-1213: MultiFieldQueryParserWrapper was ignoring slop when phrase had a field. + q = mfqp.parse("b:\"foo bar\"~4"); + assertEquals("b:\"foo bar\"~4", q.toString()); + + // make sure that terms which have a field are not touched: + q = mfqp.parse("one f:two"); + assertEquals("(b:one t:one) f:two", q.toString()); + + // AND mode: + mfqp.setDefaultOperator(QueryParserWrapper.AND_OPERATOR); + q = mfqp.parse("one two"); + assertEquals("+(b:one t:one) +(b:two t:two)", q.toString()); + q = mfqp.parse("\"aa bb cc\" \"dd ee\""); + assertEquals("+(b:\"aa bb cc\" t:\"aa bb cc\") +(b:\"dd ee\" t:\"dd ee\")", q.toString()); + + } + + public void testBoostsSimple() throws Exception { + Map boosts = new HashMap(); + boosts.put("b", new Float(5)); + boosts.put("t", new Float(10)); + String[] fields = {"b", "t"}; + MultiFieldQueryParserWrapper mfqp = new MultiFieldQueryParserWrapper(fields, new StandardAnalyzer(), boosts); + + + //Check for simple + Query q = mfqp.parse("one"); + assertEquals("b:one^5.0 t:one^10.0", q.toString()); + + //Check for AND + q = mfqp.parse("one AND two"); + assertEquals("+(b:one^5.0 t:one^10.0) +(b:two^5.0 t:two^10.0)", q.toString()); + + //Check for OR + q = mfqp.parse("one OR two"); + assertEquals("(b:one^5.0 t:one^10.0) (b:two^5.0 t:two^10.0)", q.toString()); + + //Check for AND and a field + q = mfqp.parse("one AND two AND foo:test"); + assertEquals("+(b:one^5.0 t:one^10.0) +(b:two^5.0 t:two^10.0) +foo:test", q.toString()); + + q = mfqp.parse("one^3 AND two^4"); + assertEquals("+((b:one^5.0 t:one^10.0)^3.0) +((b:two^5.0 t:two^10.0)^4.0)", q.toString()); + } + + public void testStaticMethod1() throws ParseException { + String[] fields = {"b", "t"}; + String[] queries = {"one", "two"}; + Query q = MultiFieldQueryParserWrapper.parse(queries, fields, new StandardAnalyzer()); + assertEquals("b:one t:two", q.toString()); + + String[] queries2 = {"+one", "+two"}; + q = MultiFieldQueryParserWrapper.parse(queries2, fields, new StandardAnalyzer()); + assertEquals("(+b:one) (+t:two)", q.toString()); + + String[] queries3 = {"one", "+two"}; + q = MultiFieldQueryParserWrapper.parse(queries3, fields, new StandardAnalyzer()); + assertEquals("b:one (+t:two)", q.toString()); + + String[] queries4 = {"one +more", "+two"}; + q = MultiFieldQueryParserWrapper.parse(queries4, fields, new StandardAnalyzer()); + assertEquals("(b:one +b:more) (+t:two)", q.toString()); + + String[] queries5 = {"blah"}; + try { + q = MultiFieldQueryParserWrapper.parse(queries5, fields, new StandardAnalyzer()); + fail(); + } catch(IllegalArgumentException e) { + // expected exception, array length differs + } + + // check also with stop words for this static form (qtxts[], fields[]). + TestQueryParser.QPTestAnalyzer stopA = new TestQueryParser.QPTestAnalyzer(); + + String[] queries6 = {"((+stop))", "+((stop))"}; + q = MultiFieldQueryParserWrapper.parse(queries6, fields, stopA); + assertEquals("", q.toString()); + + String[] queries7 = {"one ((+stop)) +more", "+((stop)) +two"}; + q = MultiFieldQueryParserWrapper.parse(queries7, fields, stopA); + assertEquals("(b:one +b:more) (+t:two)", q.toString()); + + } + + public void testStaticMethod2() throws ParseException { + String[] fields = {"b", "t"}; + BooleanClause.Occur[] flags = {BooleanClause.Occur.MUST, BooleanClause.Occur.MUST_NOT}; + Query q = MultiFieldQueryParserWrapper.parse("one", fields, flags, new StandardAnalyzer()); + assertEquals("+b:one -t:one", q.toString()); + + q = MultiFieldQueryParserWrapper.parse("one two", fields, flags, new StandardAnalyzer()); + assertEquals("+(b:one b:two) -(t:one t:two)", q.toString()); + + try { + BooleanClause.Occur[] flags2 = {BooleanClause.Occur.MUST}; + q = MultiFieldQueryParserWrapper.parse("blah", fields, flags2, new StandardAnalyzer()); + fail(); + } catch(IllegalArgumentException e) { + // expected exception, array length differs + } + } + + public void testStaticMethod2Old() throws ParseException { + String[] fields = {"b", "t"}; + //int[] flags = {MultiFieldQueryParserWrapper.REQUIRED_FIELD, MultiFieldQueryParserWrapper.PROHIBITED_FIELD}; + BooleanClause.Occur[] flags = {BooleanClause.Occur.MUST, BooleanClause.Occur.MUST_NOT}; + MultiFieldQueryParserWrapper parser = new MultiFieldQueryParserWrapper(fields, new StandardAnalyzer()); + + Query q = MultiFieldQueryParserWrapper.parse("one", fields, flags, new StandardAnalyzer());//, fields, flags, new StandardAnalyzer()); + assertEquals("+b:one -t:one", q.toString()); + + q = MultiFieldQueryParserWrapper.parse("one two", fields, flags, new StandardAnalyzer()); + assertEquals("+(b:one b:two) -(t:one t:two)", q.toString()); + + try { + BooleanClause.Occur[] flags2 = {BooleanClause.Occur.MUST}; + q = MultiFieldQueryParserWrapper.parse("blah", fields, flags2, new StandardAnalyzer()); + fail(); + } catch(IllegalArgumentException e) { + // expected exception, array length differs + } + } + + public void testStaticMethod3() throws ParseException { + String[] queries = {"one", "two", "three"}; + String[] fields = {"f1", "f2", "f3"}; + BooleanClause.Occur[] flags = {BooleanClause.Occur.MUST, + BooleanClause.Occur.MUST_NOT, BooleanClause.Occur.SHOULD}; + Query q = MultiFieldQueryParserWrapper.parse(queries, fields, flags, new StandardAnalyzer()); + assertEquals("+f1:one -f2:two f3:three", q.toString()); + + try { + BooleanClause.Occur[] flags2 = {BooleanClause.Occur.MUST}; + q = MultiFieldQueryParserWrapper.parse(queries, fields, flags2, new StandardAnalyzer()); + fail(); + } catch(IllegalArgumentException e) { + // expected exception, array length differs + } + } + + public void testStaticMethod3Old() throws ParseException { + String[] queries = {"one", "two"}; + String[] fields = {"b", "t"}; + BooleanClause.Occur[] flags = {BooleanClause.Occur.MUST, BooleanClause.Occur.MUST_NOT}; + Query q = MultiFieldQueryParserWrapper.parse(queries, fields, flags, new StandardAnalyzer()); + assertEquals("+b:one -t:two", q.toString()); + + try { + BooleanClause.Occur[] flags2 = {BooleanClause.Occur.MUST}; + q = MultiFieldQueryParserWrapper.parse(queries, fields, flags2, new StandardAnalyzer()); + fail(); + } catch(IllegalArgumentException e) { + // expected exception, array length differs + } + } + + public void testAnalyzerReturningNull() throws ParseException { + String[] fields = new String[] { "f1", "f2", "f3" }; + MultiFieldQueryParserWrapper parser = new MultiFieldQueryParserWrapper(fields, new AnalyzerReturningNull()); + Query q = parser.parse("bla AND blo"); + assertEquals("+(f2:bla f3:bla) +(f2:blo f3:blo)", q.toString()); + // the following queries are not affected as their terms are not analyzed anyway: + q = parser.parse("bla*"); + assertEquals("f1:bla* f2:bla* f3:bla*", q.toString()); + q = parser.parse("bla~"); + assertEquals("f1:bla~0.5 f2:bla~0.5 f3:bla~0.5", q.toString()); + q = parser.parse("[a TO c]"); + assertEquals("f1:[a TO c] f2:[a TO c] f3:[a TO c]", q.toString()); + } + + public void testStopWordSearching() throws Exception { + Analyzer analyzer = new StandardAnalyzer(); + Directory ramDir = new RAMDirectory(); + IndexWriter iw = new IndexWriter(ramDir, analyzer, true, IndexWriter.MaxFieldLength.LIMITED); + Document doc = new Document(); + doc.add(new Field("body", "blah the footest blah", Field.Store.NO, Field.Index.ANALYZED)); + iw.addDocument(doc); + iw.close(); + + MultiFieldQueryParserWrapper mfqp = + new MultiFieldQueryParserWrapper(new String[] {"body"}, analyzer); + mfqp.setDefaultOperator(QueryParserWrapper.Operator.AND); + Query q = mfqp.parse("the footest"); + IndexSearcher is = new IndexSearcher(ramDir); + ScoreDoc[] hits = is.search(q, null, 1000).scoreDocs; + assertEquals(1, hits.length); + is.close(); + } + + /** + * Return empty tokens for field "f1". + */ + private static class AnalyzerReturningNull extends Analyzer { + StandardAnalyzer stdAnalyzer = new StandardAnalyzer(); + + public AnalyzerReturningNull() { + } + + public TokenStream tokenStream(String fieldName, Reader reader) { + if ("f1".equals(fieldName)) { + return new EmptyTokenStream(); + } else { + return stdAnalyzer.tokenStream(fieldName, reader); + } + } + + private static class EmptyTokenStream extends TokenStream { + public Token next(final Token reusableToken) { + return null; + } + } + } + +} Index: src/test/org/apache/lucene/queryParser/lucene2/TestQueryParser.java =================================================================== --- src/test/org/apache/lucene/queryParser/lucene2/TestQueryParser.java (revision 0) +++ src/test/org/apache/lucene/queryParser/lucene2/TestQueryParser.java (revision 0) @@ -0,0 +1,1099 @@ +package org.apache.lucene.queryParser.lucene2; + +/** + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +import java.io.IOException; +import java.io.Reader; +import java.text.Collator; +import java.text.DateFormat; +import java.util.Calendar; +import java.util.Date; +import java.util.List; +import java.util.Locale; + +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.analysis.KeywordAnalyzer; +import org.apache.lucene.analysis.LowerCaseTokenizer; +import org.apache.lucene.analysis.SimpleAnalyzer; +import org.apache.lucene.analysis.StopAnalyzer; +import org.apache.lucene.analysis.StopFilter; +import org.apache.lucene.analysis.Token; +import org.apache.lucene.analysis.TokenFilter; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.analysis.WhitespaceAnalyzer; +import org.apache.lucene.analysis.standard.StandardAnalyzer; +import org.apache.lucene.analysis.tokenattributes.OffsetAttribute; +import org.apache.lucene.analysis.tokenattributes.TermAttribute; +import org.apache.lucene.document.DateField; +import org.apache.lucene.document.DateTools; +import org.apache.lucene.document.Document; +import org.apache.lucene.document.Field; +import org.apache.lucene.index.IndexWriter; +import org.apache.lucene.index.Term; +import org.apache.lucene.messages.MessageImpl; +import org.apache.lucene.queryParser.QueryNodeException; +import org.apache.lucene.queryParser.messages.QueryParserMessages; +import org.apache.lucene.queryParser.nodes.FuzzyQueryNode; +import org.apache.lucene.queryParser.nodes.QueryNode; +import org.apache.lucene.queryParser.nodes.WildcardQueryNode; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorImpl; +import org.apache.lucene.queryParser.processors.QueryNodeProcessorPipeline; +import org.apache.lucene.queryParser.ParseException; +import org.apache.lucene.search.BooleanQuery; +import org.apache.lucene.search.FuzzyQuery; +import org.apache.lucene.search.IndexSearcher; +import org.apache.lucene.search.MatchAllDocsQuery; +import org.apache.lucene.search.PhraseQuery; +import org.apache.lucene.search.PrefixQuery; +import org.apache.lucene.search.Query; +import org.apache.lucene.search.RangeQuery; +import org.apache.lucene.search.ScoreDoc; +import org.apache.lucene.search.TermQuery; +import org.apache.lucene.search.WildcardQuery; +import org.apache.lucene.store.RAMDirectory; +import org.apache.lucene.util.LuceneTestCase; + + +/** + * Tests QueryParser. + */ +public class TestQueryParser extends LuceneTestCase { + + public static Analyzer qpAnalyzer = new QPTestAnalyzer(); + + public static class QPTestFilter extends TokenFilter { + TermAttribute termAtt; + OffsetAttribute offsetAtt; + + /** + * Filter which discards the token 'stop' and which expands the + * token 'phrase' into 'phrase1 phrase2' + */ + public QPTestFilter(TokenStream in) { + super(in); + termAtt = (TermAttribute) addAttribute(TermAttribute.class); + offsetAtt = (OffsetAttribute) addAttribute(OffsetAttribute.class); + } + + boolean inPhrase = false; + int savedStart = 0, savedEnd = 0; + + + + public Token next(Token reusableToken) throws IOException { + Token token = reusableToken; + + if (inPhrase) { + inPhrase = false; + token.setTermBuffer("phrase2"); + token.setStartOffset(savedStart); + token.setEndOffset(savedEnd); + return reusableToken; + } else + while ((token = this.input.next(reusableToken)) != null) { + if (token.term().equals("phrase")) { + inPhrase = true; + savedStart = token.startOffset(); + savedEnd = token.endOffset(); + token.setTermBuffer("phrase1"); + token.setStartOffset(savedStart); + token.setEndOffset(savedEnd); + return token; + } else if (!token.term().equals("stop")) + return token; + } + + return null; + + + } + + public boolean incrementToken() throws IOException { + if (inPhrase) { + inPhrase = false; + termAtt.setTermBuffer("phrase2"); + offsetAtt.setStartOffset(savedStart); + offsetAtt.setEndOffset(savedEnd); + return true; + } else + while (input.incrementToken()) { + if (termAtt.term().equals("phrase")) { + inPhrase = true; + savedStart = offsetAtt.startOffset(); + savedEnd = offsetAtt.endOffset(); + termAtt.setTermBuffer("phrase1"); + offsetAtt.setStartOffset(savedStart); + offsetAtt.setEndOffset(savedEnd); + return true; + } else if (!termAtt.term().equals("stop")) + return true; + } + return false; + } + } + + + public static class QPTestAnalyzer extends Analyzer { + + /** Filters LowerCaseTokenizer with StopFilter. */ + public final TokenStream tokenStream(String fieldName, Reader reader) { + return new QPTestFilter(new LowerCaseTokenizer(reader)); + } + } + + public static class QPTestParser extends QueryParserWrapper { + public QPTestParser(String f, Analyzer a) { + super(f, a); + + QueryNodeProcessorPipeline newProcessorPipeline = new QueryNodeProcessorPipeline(getQueryProcessor().getQueryConfigHandler()); + newProcessorPipeline.addProcessor(new QPTestParserQueryNodeProcessor()); + newProcessorPipeline.addProcessor(getQueryProcessor()); + + setQueryProcessor(newProcessorPipeline); + + } + + protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws ParseException { + throw new ParseException("Fuzzy queries not allowed"); + } + + protected Query getWildcardQuery(String field, String termStr) throws ParseException { + throw new ParseException("Wildcard queries not allowed"); + } + + private static class QPTestParserQueryNodeProcessor extends QueryNodeProcessorImpl { + + protected QueryNode postProcessNode(QueryNode node) + throws QueryNodeException { + + return node; + + } + + protected QueryNode preProcessNode(QueryNode node) + throws QueryNodeException { + + if (node instanceof WildcardQueryNode || + node instanceof FuzzyQueryNode) { + + throw new QueryNodeException(new MessageImpl(QueryParserMessages.EMPTY_MESSAGE)); + + } + + return node; + + } + + protected List setChildrenOrder(List children) + throws QueryNodeException { + + return children; + + } + + } + + } + + private int originalMaxClauses; + + public void setUp() throws Exception { + super.setUp(); + originalMaxClauses = BooleanQuery.getMaxClauseCount(); + } + + public QueryParserWrapper getParser(Analyzer a) throws Exception { + if (a == null) + a = new SimpleAnalyzer(); + QueryParserWrapper qp = new QueryParserWrapper("field", a); + qp.setDefaultOperator(QueryParserWrapper.OR_OPERATOR); + return qp; + } + + public Query getQuery(String query, Analyzer a) throws Exception { + return getParser(a).parse(query); + } + + public void assertQueryEquals(String query, Analyzer a, String result) + throws Exception { + Query q = getQuery(query, a); + String s = q.toString("field"); + if (!s.equals(result)) { + fail("Query /" + query + "/ yielded /" + s + + "/, expecting /" + result + "/"); + } + } + + public void assertQueryEquals(QueryParserWrapper qp, String field, String query, String result) + throws Exception { + Query q = qp.parse(query); + String s = q.toString(field); + if (!s.equals(result)) { + fail("Query /" + query + "/ yielded /" + s + + "/, expecting /" + result + "/"); + } + } + + public void assertEscapedQueryEquals(String query, Analyzer a, String result) + throws Exception { + String escapedQuery = QueryParserWrapper.escape(query); + if (!escapedQuery.equals(result)) { + fail("Query /" + query + "/ yielded /" + escapedQuery + + "/, expecting /" + result + "/"); + } + } + + public void assertWildcardQueryEquals(String query, boolean lowercase, String result, boolean allowLeadingWildcard) + throws Exception { + QueryParserWrapper qp = getParser(null); + qp.setLowercaseExpandedTerms(lowercase); + qp.setAllowLeadingWildcard(allowLeadingWildcard); + Query q = qp.parse(query); + String s = q.toString("field"); + if (!s.equals(result)) { + fail("WildcardQuery /" + query + "/ yielded /" + s + + "/, expecting /" + result + "/"); + } + } + + public void assertWildcardQueryEquals(String query, boolean lowercase, String result) + throws Exception { + assertWildcardQueryEquals(query, lowercase, result, false); + } + + public void assertWildcardQueryEquals(String query, String result) throws Exception { + QueryParserWrapper qp = getParser(null); + Query q = qp.parse(query); + String s = q.toString("field"); + if (!s.equals(result)) { + fail("WildcardQuery /" + query + "/ yielded /" + s + "/, expecting /" + + result + "/"); + } + } + + public Query getQueryDOA(String query, Analyzer a) + throws Exception { + if (a == null) + a = new SimpleAnalyzer(); + QueryParserWrapper qp = new QueryParserWrapper("field", a); + qp.setDefaultOperator(QueryParserWrapper.AND_OPERATOR); + return qp.parse(query); + } + + public void assertQueryEqualsDOA(String query, Analyzer a, String result) + throws Exception { + Query q = getQueryDOA(query, a); + String s = q.toString("field"); + if (!s.equals(result)) { + fail("Query /" + query + "/ yielded /" + s + + "/, expecting /" + result + "/"); + } + } + + public void testCJK() throws Exception { + // Test Ideographic Space - As wide as a CJK character cell (fullwidth) + // used google to translate the word "term" to japanese -> 用語 + assertQueryEquals("term\u3000term\u3000term", null, "term\u0020term\u0020term"); + assertQueryEquals("用語\u3000用語\u3000用語", null, "用語\u0020用語\u0020用語"); + } + + public void testSimple() throws Exception { + assertQueryEquals("\"term germ\"~2", null, "\"term germ\"~2"); + assertQueryEquals("term term term", null, "term term term"); + assertQueryEquals("türm term term", new WhitespaceAnalyzer(), "türm term term"); + assertQueryEquals("ümlaut", new WhitespaceAnalyzer(), "ümlaut"); + + assertQueryEquals("\"\"", new KeywordAnalyzer(), ""); + assertQueryEquals("foo:\"\"", new KeywordAnalyzer(), "foo:"); + + assertQueryEquals("a AND b", null, "+a +b"); + assertQueryEquals("(a AND b)", null, "+a +b"); + assertQueryEquals("c OR (a AND b)", null, "c (+a +b)"); + + assertQueryEquals("a AND NOT b", null, "+a -b"); + + assertQueryEquals("a AND -b", null, "+a -b"); + + assertQueryEquals("a AND !b", null, "+a -b"); + + assertQueryEquals("a && b", null, "+a +b"); + + + assertQueryEquals("a && ! b", null, "+a -b"); + + assertQueryEquals("a OR b", null, "a b"); + assertQueryEquals("a || b", null, "a b"); + + assertQueryEquals("a OR !b", null, "a -b"); + + assertQueryEquals("a OR ! b", null, "a -b"); + + assertQueryEquals("a OR -b", null, "a -b"); + + assertQueryEquals("+term -term term", null, "+term -term term"); + assertQueryEquals("foo:term AND field:anotherTerm", null, + "+foo:term +anotherterm"); + assertQueryEquals("term AND \"phrase phrase\"", null, + "+term +\"phrase phrase\""); + assertQueryEquals("\"hello there\"", null, "\"hello there\""); + assertTrue(getQuery("a AND b", null) instanceof BooleanQuery); + assertTrue(getQuery("hello", null) instanceof TermQuery); + assertTrue(getQuery("\"hello there\"", null) instanceof PhraseQuery); + + assertQueryEquals("germ term^2.0", null, "germ term^2.0"); + assertQueryEquals("(term)^2.0", null, "term^2.0"); + assertQueryEquals("(germ term)^2.0", null, "(germ term)^2.0"); + assertQueryEquals("term^2.0", null, "term^2.0"); + assertQueryEquals("term^2", null, "term^2.0"); + assertQueryEquals("\"germ term\"^2.0", null, "\"germ term\"^2.0"); + assertQueryEquals("\"term germ\"^2", null, "\"term germ\"^2.0"); + + assertQueryEquals("(foo OR bar) AND (baz OR boo)", null, + "+(foo bar) +(baz boo)"); + assertQueryEquals("((a OR b) AND NOT c) OR d", null, + "(+(a b) -c) d"); + assertQueryEquals("+(apple \"steve jobs\") -(foo bar baz)", null, + "+(apple \"steve jobs\") -(foo bar baz)"); + assertQueryEquals("+title:(dog OR cat) -author:\"bob dole\"", null, + "+(title:dog title:cat) -author:\"bob dole\""); + + QueryParserWrapper qp = new QueryParserWrapper("field", new StandardAnalyzer()); + // make sure OR is the default: + assertEquals(QueryParserWrapper.OR_OPERATOR, qp.getDefaultOperator()); + qp.setDefaultOperator(QueryParserWrapper.AND_OPERATOR); + assertEquals(QueryParserWrapper.AND_OPERATOR, qp.getDefaultOperator()); + qp.setDefaultOperator(QueryParserWrapper.OR_OPERATOR); + assertEquals(QueryParserWrapper.OR_OPERATOR, qp.getDefaultOperator()); + } + + public void testPunct() throws Exception { + Analyzer a = new WhitespaceAnalyzer(); + assertQueryEquals("a&b", a, "a&b"); + assertQueryEquals("a&&b", a, "a&&b"); + assertQueryEquals(".NET", a, ".NET"); + } + + public void testSlop() throws Exception { + + assertQueryEquals("\"term germ\"~2", null, "\"term germ\"~2"); + assertQueryEquals("\"term germ\"~2 flork", null, "\"term germ\"~2 flork"); + assertQueryEquals("\"term\"~2", null, "term"); + assertQueryEquals("\" \"~2 germ", null, "germ"); + assertQueryEquals("\"term germ\"~2^2", null, "\"term germ\"~2^2.0"); + } + + public void testNumber() throws Exception { +// The numbers go away because SimpleAnalzyer ignores them + assertQueryEquals("3", null, ""); + assertQueryEquals("term 1.0 1 2", null, "term"); + assertQueryEquals("term term1 term2", null, "term term term"); + + Analyzer a = new StandardAnalyzer(); + assertQueryEquals("3", a, "3"); + assertQueryEquals("term 1.0 1 2", a, "term 1.0 1 2"); + assertQueryEquals("term term1 term2", a, "term term1 term2"); + } + + public void testWildcard() throws Exception { + assertQueryEquals("term*", null, "term*"); + assertQueryEquals("term*^2", null, "term*^2.0"); + assertQueryEquals("term~", null, "term~0.5"); + assertQueryEquals("term~0.7", null, "term~0.7"); + + assertQueryEquals("term~^2", null, "term~0.5^2.0"); + + assertQueryEquals("term^2~", null, "term~0.5^2.0"); + assertQueryEquals("term*germ", null, "term*germ"); + assertQueryEquals("term*germ^3", null, "term*germ^3.0"); + + assertTrue(getQuery("term*", null) instanceof PrefixQuery); + assertTrue(getQuery("term*^2", null) instanceof PrefixQuery); + assertTrue(getQuery("term~", null) instanceof FuzzyQuery); + assertTrue(getQuery("term~0.7", null) instanceof FuzzyQuery); + FuzzyQuery fq = (FuzzyQuery)getQuery("term~0.7", null); + assertEquals(0.7f, fq.getMinSimilarity(), 0.1f); + assertEquals(FuzzyQuery.defaultPrefixLength, fq.getPrefixLength()); + fq = (FuzzyQuery)getQuery("term~", null); + assertEquals(0.5f, fq.getMinSimilarity(), 0.1f); + assertEquals(FuzzyQuery.defaultPrefixLength, fq.getPrefixLength()); + + assertParseException("term~1.1"); // value > 1, throws exception + + assertTrue(getQuery("term*germ", null) instanceof WildcardQuery); + +/* Tests to see that wild card terms are (or are not) properly + * lower-cased with propery parser configuration + */ +// First prefix queries: + // by default, convert to lowercase: + assertWildcardQueryEquals("Term*", true, "term*"); + // explicitly set lowercase: + assertWildcardQueryEquals("term*", true, "term*"); + assertWildcardQueryEquals("Term*", true, "term*"); + assertWildcardQueryEquals("TERM*", true, "term*"); + // explicitly disable lowercase conversion: + assertWildcardQueryEquals("term*", false, "term*"); + assertWildcardQueryEquals("Term*", false, "Term*"); + assertWildcardQueryEquals("TERM*", false, "TERM*"); +// Then 'full' wildcard queries: + // by default, convert to lowercase: + assertWildcardQueryEquals("Te?m", "te?m"); + // explicitly set lowercase: + assertWildcardQueryEquals("te?m", true, "te?m"); + assertWildcardQueryEquals("Te?m", true, "te?m"); + assertWildcardQueryEquals("TE?M", true, "te?m"); + assertWildcardQueryEquals("Te?m*gerM", true, "te?m*germ"); + // explicitly disable lowercase conversion: + assertWildcardQueryEquals("te?m", false, "te?m"); + assertWildcardQueryEquals("Te?m", false, "Te?m"); + assertWildcardQueryEquals("TE?M", false, "TE?M"); + assertWildcardQueryEquals("Te?m*gerM", false, "Te?m*gerM"); +// Fuzzy queries: + assertWildcardQueryEquals("Term~", "term~0.5"); + assertWildcardQueryEquals("Term~", true, "term~0.5"); + assertWildcardQueryEquals("Term~", false, "Term~0.5"); +// Range queries: + + // TODO: implement this on QueryParser + // Q0002E_INVALID_SYNTAX_CANNOT_PARSE: Syntax Error, cannot parse '[A TO C]': Lexical error at line 1, column 1. Encountered: "[" (91), after : "" + assertWildcardQueryEquals("[A TO C]", "[a TO c]"); + assertWildcardQueryEquals("[A TO C]", true, "[a TO c]"); + assertWildcardQueryEquals("[A TO C]", false, "[A TO C]"); + // Test suffix queries: first disallow + try { + assertWildcardQueryEquals("*Term", true, "*term"); + fail(); + } catch(ParseException pe) { + // expected exception + } + try { + assertWildcardQueryEquals("?Term", true, "?term"); + fail(); + } catch(ParseException pe) { + // expected exception + } + // Test suffix queries: then allow + assertWildcardQueryEquals("*Term", true, "*term", true); + assertWildcardQueryEquals("?Term", true, "?term", true); + } + + public void testLeadingWildcardType() throws Exception { + QueryParserWrapper qp = getParser(null); + qp.setAllowLeadingWildcard(true); + assertEquals(WildcardQuery.class, qp.parse("t*erm*").getClass()); + assertEquals(WildcardQuery.class, qp.parse("?term*").getClass()); + assertEquals(WildcardQuery.class, qp.parse("*term*").getClass()); + } + + public void testQPA() throws Exception { + assertQueryEquals("term term^3.0 term", qpAnalyzer, "term term^3.0 term"); + assertQueryEquals("term stop^3.0 term", qpAnalyzer, "term term"); + + assertQueryEquals("term term term", qpAnalyzer, "term term term"); + assertQueryEquals("term +stop term", qpAnalyzer, "term term"); + assertQueryEquals("term -stop term", qpAnalyzer, "term term"); + + assertQueryEquals("drop AND (stop) AND roll", qpAnalyzer, "+drop +roll"); + assertQueryEquals("term +(stop) term", qpAnalyzer, "term term"); + assertQueryEquals("term -(stop) term", qpAnalyzer, "term term"); + + assertQueryEquals("drop AND stop AND roll", qpAnalyzer, "+drop +roll"); + assertQueryEquals("term phrase term", qpAnalyzer, + "term \"phrase1 phrase2\" term"); + + assertQueryEquals("term AND NOT phrase term", qpAnalyzer, + "+term -\"phrase1 phrase2\" term"); + + assertQueryEquals("stop^3", qpAnalyzer, ""); + assertQueryEquals("stop", qpAnalyzer, ""); + assertQueryEquals("(stop)^3", qpAnalyzer, ""); + assertQueryEquals("((stop))^3", qpAnalyzer, ""); + assertQueryEquals("(stop^3)", qpAnalyzer, ""); + assertQueryEquals("((stop)^3)", qpAnalyzer, ""); + assertQueryEquals("(stop)", qpAnalyzer, ""); + assertQueryEquals("((stop))", qpAnalyzer, ""); + assertTrue(getQuery("term term term", qpAnalyzer) instanceof BooleanQuery); + assertTrue(getQuery("term +stop", qpAnalyzer) instanceof TermQuery); + } + + public void testRange() throws Exception { + assertQueryEquals("[ a TO z]", null, "[a TO z]"); + assertTrue(((RangeQuery)getQuery("[ a TO z]", null)).getConstantScoreRewrite()); + + QueryParserWrapper qp = new QueryParserWrapper("field", new SimpleAnalyzer()); + qp.setConstantScoreRewrite(false); + assertFalse(((RangeQuery)qp.parse("[ a TO z]")).getConstantScoreRewrite()); + + assertQueryEquals("[ a TO z ]", null, "[a TO z]"); + assertQueryEquals("{ a TO z}", null, "{a TO z}"); + assertQueryEquals("{ a TO z }", null, "{a TO z}"); + assertQueryEquals("{ a TO z }^2.0", null, "{a TO z}^2.0"); + assertQueryEquals("[ a TO z] OR bar", null, "[a TO z] bar"); + assertQueryEquals("[ a TO z] AND bar", null, "+[a TO z] +bar"); + assertQueryEquals("( bar blar { a TO z}) ", null, "bar blar {a TO z}"); + assertQueryEquals("gack ( bar blar { a TO z}) ", null, "gack (bar blar {a TO z})"); + } + + public void testFarsiRangeCollating() throws Exception { + + RAMDirectory ramDir = new RAMDirectory(); + IndexWriter iw = new IndexWriter(ramDir, new WhitespaceAnalyzer(), true, + IndexWriter.MaxFieldLength.LIMITED); + Document doc = new Document(); + doc.add(new Field("content","\u0633\u0627\u0628", + Field.Store.YES, Field.Index.UN_TOKENIZED)); + iw.addDocument(doc); + iw.close(); + IndexSearcher is = new IndexSearcher(ramDir); + + QueryParserWrapper qp = new QueryParserWrapper("content", new WhitespaceAnalyzer()); + + // Neither Java 1.4.2 nor 1.5.0 has Farsi Locale collation available in + // RuleBasedCollator. However, the Arabic Locale seems to order the Farsi + // characters properly. + Collator c = Collator.getInstance(new Locale("ar")); + qp.setRangeCollator(c); + + // Unicode order would include U+0633 in [ U+062F - U+0698 ], but Farsi + // orders the U+0698 character before the U+0633 character, so the single + // index Term below should NOT be returned by a ConstantScoreRangeQuery + // with a Farsi Collator (or an Arabic one for the case when Farsi is not + // supported). + + // Test ConstantScoreRangeQuery + qp.setConstantScoreRewrite(true); + ScoreDoc[] result = is.search(qp.parse("[ \u062F TO \u0698 ]"), null, 1000).scoreDocs; + assertEquals("The index Term should not be included.", 0, result.length); + + result = is.search(qp.parse("[ \u0633 TO \u0638 ]"), null, 1000).scoreDocs; + assertEquals("The index Term should be included.", 1, result.length); + + // Test RangeQuery + qp.setConstantScoreRewrite(false); + result = is.search(qp.parse("[ \u062F TO \u0698 ]"), null, 1000).scoreDocs; + assertEquals("The index Term should not be included.", 0, result.length); + + result = is.search(qp.parse("[ \u0633 TO \u0638 ]"), null, 1000).scoreDocs; + assertEquals("The index Term should be included.", 1, result.length); + + is.close(); + } + + /** for testing legacy DateField support */ + private String getLegacyDate(String s) throws Exception { + DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT); + return DateField.dateToString(df.parse(s)); + } + + /** for testing DateTools support */ + private String getDate(String s, DateTools.Resolution resolution) throws Exception { + DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT); + return getDate(df.parse(s), resolution); + } + + /** for testing DateTools support */ + private String getDate(Date d, DateTools.Resolution resolution) throws Exception { + if (resolution == null) { + return DateField.dateToString(d); + } else { + return DateTools.dateToString(d, resolution); + } + } + + private String getLocalizedDate(int year, int month, int day, boolean extendLastDate) { + DateFormat df = DateFormat.getDateInstance(DateFormat.SHORT); + Calendar calendar = Calendar.getInstance(); + calendar.set(year, month, day); + if (extendLastDate) { + calendar.set(Calendar.HOUR_OF_DAY, 23); + calendar.set(Calendar.MINUTE, 59); + calendar.set(Calendar.SECOND, 59); + calendar.set(Calendar.MILLISECOND, 999); + } + return df.format(calendar.getTime()); + } + + /** for testing legacy DateField support */ + public void testLegacyDateRange() throws Exception { + String startDate = getLocalizedDate(2002, 1, 1, false); + String endDate = getLocalizedDate(2002, 1, 4, false); + Calendar endDateExpected = Calendar.getInstance(); + endDateExpected.set(2002, 1, 4, 23, 59, 59); + endDateExpected.set(Calendar.MILLISECOND, 999); + assertQueryEquals("[ " + startDate + " TO " + endDate + "]", null, + "[" + getLegacyDate(startDate) + " TO " + DateField.dateToString(endDateExpected.getTime()) + "]"); + assertQueryEquals("{ " + startDate + " " + endDate + " }", null, + "{" + getLegacyDate(startDate) + " TO " + getLegacyDate(endDate) + "}"); + } + + public void testDateRange() throws Exception { + String startDate = getLocalizedDate(2002, 1, 1, false); + String endDate = getLocalizedDate(2002, 1, 4, false); + Calendar endDateExpected = Calendar.getInstance(); + endDateExpected.set(2002, 1, 4, 23, 59, 59); + endDateExpected.set(Calendar.MILLISECOND, 999); + final String defaultField = "default"; + final String monthField = "month"; + final String hourField = "hour"; + QueryParserWrapper qp = new QueryParserWrapper("field", new SimpleAnalyzer()); + + // Don't set any date resolution and verify if DateField is used + assertDateRangeQueryEquals(qp, defaultField, startDate, endDate, + endDateExpected.getTime(), null); + + // set a field specific date resolution + qp.setDateResolution(monthField, DateTools.Resolution.MONTH); + + // DateField should still be used for defaultField + assertDateRangeQueryEquals(qp, defaultField, startDate, endDate, + endDateExpected.getTime(), null); + + // set default date resolution to MILLISECOND + qp.setDateResolution(DateTools.Resolution.MILLISECOND); + + // set second field specific date resolution + qp.setDateResolution(hourField, DateTools.Resolution.HOUR); + + // for this field no field specific date resolution has been set, + // so verify if the default resolution is used + assertDateRangeQueryEquals(qp, defaultField, startDate, endDate, + endDateExpected.getTime(), DateTools.Resolution.MILLISECOND); + + // verify if field specific date resolutions are used for these two fields + assertDateRangeQueryEquals(qp, monthField, startDate, endDate, + endDateExpected.getTime(), DateTools.Resolution.MONTH); + + assertDateRangeQueryEquals(qp, hourField, startDate, endDate, + endDateExpected.getTime(), DateTools.Resolution.HOUR); + } + + public void assertDateRangeQueryEquals(QueryParserWrapper qp, String field, String startDate, String endDate, + Date endDateInclusive, DateTools.Resolution resolution) throws Exception { + assertQueryEquals(qp, field, field + ":[" + startDate + " TO " + endDate + "]", + "[" + getDate(startDate, resolution) + " TO " + getDate(endDateInclusive, resolution) + "]"); + assertQueryEquals(qp, field, field + ":{" + startDate + " TO " + endDate + "}", + "{" + getDate(startDate, resolution) + " TO " + getDate(endDate, resolution) + "}"); + } + + public void testEscaped() throws Exception { + Analyzer a = new WhitespaceAnalyzer(); + + /*assertQueryEquals("\\[brackets", a, "\\[brackets"); + assertQueryEquals("\\[brackets", null, "brackets"); + assertQueryEquals("\\\\", a, "\\\\"); + assertQueryEquals("\\+blah", a, "\\+blah"); + assertQueryEquals("\\(blah", a, "\\(blah"); + + assertQueryEquals("\\-blah", a, "\\-blah"); + assertQueryEquals("\\!blah", a, "\\!blah"); + assertQueryEquals("\\{blah", a, "\\{blah"); + assertQueryEquals("\\}blah", a, "\\}blah"); + assertQueryEquals("\\:blah", a, "\\:blah"); + assertQueryEquals("\\^blah", a, "\\^blah"); + assertQueryEquals("\\[blah", a, "\\[blah"); + assertQueryEquals("\\]blah", a, "\\]blah"); + assertQueryEquals("\\\"blah", a, "\\\"blah"); + assertQueryEquals("\\(blah", a, "\\(blah"); + assertQueryEquals("\\)blah", a, "\\)blah"); + assertQueryEquals("\\~blah", a, "\\~blah"); + assertQueryEquals("\\*blah", a, "\\*blah"); + assertQueryEquals("\\?blah", a, "\\?blah"); + //assertQueryEquals("foo \\&\\& bar", a, "foo \\&\\& bar"); + //assertQueryEquals("foo \\|| bar", a, "foo \\|| bar"); + //assertQueryEquals("foo \\AND bar", a, "foo \\AND bar");*/ + + assertQueryEquals("\\a", a, "a"); + + assertQueryEquals("a\\-b:c", a, "a-b:c"); + assertQueryEquals("a\\+b:c", a, "a+b:c"); + assertQueryEquals("a\\:b:c", a, "a:b:c"); + assertQueryEquals("a\\\\b:c", a, "a\\b:c"); + + assertQueryEquals("a:b\\-c", a, "a:b-c"); + assertQueryEquals("a:b\\+c", a, "a:b+c"); + assertQueryEquals("a:b\\:c", a, "a:b:c"); + assertQueryEquals("a:b\\\\c", a, "a:b\\c"); + + assertQueryEquals("a:b\\-c*", a, "a:b-c*"); + assertQueryEquals("a:b\\+c*", a, "a:b+c*"); + assertQueryEquals("a:b\\:c*", a, "a:b:c*"); + + assertQueryEquals("a:b\\\\c*", a, "a:b\\c*"); + + assertQueryEquals("a:b\\-?c", a, "a:b-?c"); + assertQueryEquals("a:b\\+?c", a, "a:b+?c"); + assertQueryEquals("a:b\\:?c", a, "a:b:?c"); + + assertQueryEquals("a:b\\\\?c", a, "a:b\\?c"); + + assertQueryEquals("a:b\\-c~", a, "a:b-c~0.5"); + assertQueryEquals("a:b\\+c~", a, "a:b+c~0.5"); + assertQueryEquals("a:b\\:c~", a, "a:b:c~0.5"); + assertQueryEquals("a:b\\\\c~", a, "a:b\\c~0.5"); + + //TODO: implement Range queries on QueryParser + assertQueryEquals("[ a\\- TO a\\+ ]", null, "[a- TO a+]"); + assertQueryEquals("[ a\\: TO a\\~ ]", null, "[a: TO a~]"); + assertQueryEquals("[ a\\\\ TO a\\* ]", null, "[a\\ TO a*]"); + + assertQueryEquals("[\"c\\:\\\\temp\\\\\\~foo0.txt\" TO \"c\\:\\\\temp\\\\\\~foo9.txt\"]", a, + "[c:\\temp\\~foo0.txt TO c:\\temp\\~foo9.txt]"); + + assertQueryEquals("a\\\\\\+b", a, "a\\+b"); + + assertQueryEquals("a \\\"b c\\\" d", a, "a \"b c\" d"); + assertQueryEquals("\"a \\\"b c\\\" d\"", a, "\"a \"b c\" d\""); + assertQueryEquals("\"a \\+b c d\"", a, "\"a +b c d\""); + + assertQueryEquals("c\\:\\\\temp\\\\\\~foo.txt", a, "c:\\temp\\~foo.txt"); + + assertParseException("XY\\"); // there must be a character after the escape char + + // test unicode escaping + assertQueryEquals("a\\u0062c", a, "abc"); + assertQueryEquals("XY\\u005a", a, "XYZ"); + assertQueryEquals("XY\\u005A", a, "XYZ"); + assertQueryEquals("\"a \\\\\\u0028\\u0062\\\" c\"", a, "\"a \\(b\" c\""); + + assertParseException("XY\\u005G"); // test non-hex character in escaped unicode sequence + assertParseException("XY\\u005"); // test incomplete escaped unicode sequence + + // Tests bug LUCENE-800 + assertQueryEquals("(item:\\\\ item:ABCD\\\\)", a, "item:\\ item:ABCD\\"); + assertParseException("(item:\\\\ item:ABCD\\\\))"); // unmatched closing paranthesis + assertQueryEquals("\\*", a, "*"); + assertQueryEquals("\\\\", a, "\\"); // escaped backslash + + assertParseException("\\"); // a backslash must always be escaped + + // LUCENE-1189 + assertQueryEquals("(\"a\\\\\") or (\"b\")", a ,"a\\ or b"); + } + + public void testQueryStringEscaping() throws Exception { + Analyzer a = new WhitespaceAnalyzer(); + + assertEscapedQueryEquals("a-b:c", a, "a\\-b\\:c"); + assertEscapedQueryEquals("a+b:c", a, "a\\+b\\:c"); + assertEscapedQueryEquals("a:b:c", a, "a\\:b\\:c"); + assertEscapedQueryEquals("a\\b:c", a, "a\\\\b\\:c"); + + assertEscapedQueryEquals("a:b-c", a, "a\\:b\\-c"); + assertEscapedQueryEquals("a:b+c", a, "a\\:b\\+c"); + assertEscapedQueryEquals("a:b:c", a, "a\\:b\\:c"); + assertEscapedQueryEquals("a:b\\c", a, "a\\:b\\\\c"); + + assertEscapedQueryEquals("a:b-c*", a, "a\\:b\\-c\\*"); + assertEscapedQueryEquals("a:b+c*", a, "a\\:b\\+c\\*"); + assertEscapedQueryEquals("a:b:c*", a, "a\\:b\\:c\\*"); + + assertEscapedQueryEquals("a:b\\\\c*", a, "a\\:b\\\\\\\\c\\*"); + + assertEscapedQueryEquals("a:b-?c", a, "a\\:b\\-\\?c"); + assertEscapedQueryEquals("a:b+?c", a, "a\\:b\\+\\?c"); + assertEscapedQueryEquals("a:b:?c", a, "a\\:b\\:\\?c"); + + assertEscapedQueryEquals("a:b?c", a, "a\\:b\\?c"); + + assertEscapedQueryEquals("a:b-c~", a, "a\\:b\\-c\\~"); + assertEscapedQueryEquals("a:b+c~", a, "a\\:b\\+c\\~"); + assertEscapedQueryEquals("a:b:c~", a, "a\\:b\\:c\\~"); + assertEscapedQueryEquals("a:b\\c~", a, "a\\:b\\\\c\\~"); + + assertEscapedQueryEquals("[ a - TO a+ ]", null, "\\[ a \\- TO a\\+ \\]"); + assertEscapedQueryEquals("[ a : TO a~ ]", null, "\\[ a \\: TO a\\~ \\]"); + assertEscapedQueryEquals("[ a\\ TO a* ]", null, "\\[ a\\\\ TO a\\* \\]"); + + // LUCENE-881 + assertEscapedQueryEquals("|| abc ||", a, "\\|\\| abc \\|\\|"); + assertEscapedQueryEquals("&& abc &&", a, "\\&\\& abc \\&\\&"); + } + + public void testTabNewlineCarriageReturn() + throws Exception { + assertQueryEqualsDOA("+weltbank +worlbank", null, + "+weltbank +worlbank"); + + assertQueryEqualsDOA("+weltbank\n+worlbank", null, + "+weltbank +worlbank"); + assertQueryEqualsDOA("weltbank \n+worlbank", null, + "+weltbank +worlbank"); + assertQueryEqualsDOA("weltbank \n +worlbank", null, + "+weltbank +worlbank"); + + assertQueryEqualsDOA("+weltbank\r+worlbank", null, + "+weltbank +worlbank"); + assertQueryEqualsDOA("weltbank \r+worlbank", null, + "+weltbank +worlbank"); + assertQueryEqualsDOA("weltbank \r +worlbank", null, + "+weltbank +worlbank"); + + assertQueryEqualsDOA("+weltbank\r\n+worlbank", null, + "+weltbank +worlbank"); + assertQueryEqualsDOA("weltbank \r\n+worlbank", null, + "+weltbank +worlbank"); + assertQueryEqualsDOA("weltbank \r\n +worlbank", null, + "+weltbank +worlbank"); + assertQueryEqualsDOA("weltbank \r \n +worlbank", null, + "+weltbank +worlbank"); + + assertQueryEqualsDOA("+weltbank\t+worlbank", null, + "+weltbank +worlbank"); + assertQueryEqualsDOA("weltbank \t+worlbank", null, + "+weltbank +worlbank"); + assertQueryEqualsDOA("weltbank \t +worlbank", null, + "+weltbank +worlbank"); + } + + public void testSimpleDAO() + throws Exception { + assertQueryEqualsDOA("term term term", null, "+term +term +term"); + assertQueryEqualsDOA("term +term term", null, "+term +term +term"); + assertQueryEqualsDOA("term term +term", null, "+term +term +term"); + assertQueryEqualsDOA("term +term +term", null, "+term +term +term"); + assertQueryEqualsDOA("-term term term", null, "-term +term +term"); + } + + public void testBoost() + throws Exception { + StandardAnalyzer oneStopAnalyzer = new StandardAnalyzer(new String[]{"on"}); + QueryParserWrapper qp = new QueryParserWrapper("field", oneStopAnalyzer); + Query q = qp.parse("on^1.0"); + assertNotNull(q); + q = qp.parse("\"hello\"^2.0"); + assertNotNull(q); + assertEquals(q.getBoost(), (float) 2.0, (float) 0.5); + q = qp.parse("hello^2.0"); + assertNotNull(q); + assertEquals(q.getBoost(), (float) 2.0, (float) 0.5); + q = qp.parse("\"on\"^1.0"); + assertNotNull(q); + + QueryParserWrapper qp2 = new QueryParserWrapper("field", new StandardAnalyzer()); + q = qp2.parse("the^3"); + // "the" is a stop word so the result is an empty query: + assertNotNull(q); + assertEquals("", q.toString()); + assertEquals(1.0f, q.getBoost(), 0.01f); + } + + public void assertParseException(String queryString) throws Exception { + try { + getQuery(queryString, null); + } catch (ParseException expected) { + return; + } + fail("ParseException expected, not thrown"); + } + + public void testException() throws Exception { + assertParseException("\"some phrase"); + assertParseException("(foo bar"); + assertParseException("foo bar))"); + assertParseException("field:term:with:colon some more terms"); + assertParseException("(sub query)^5.0^2.0 plus more"); + assertParseException("secret AND illegal) AND access:confidential"); + } + + public void testCustomQueryParserWildcard() { + try { + new QPTestParser("contents", new WhitespaceAnalyzer()).parse("a?t"); + fail("Wildcard queries should not be allowed"); + } catch (ParseException expected) { + // expected exception + } + } + + public void testCustomQueryParserFuzzy() throws Exception { + try { + new QPTestParser("contents", new WhitespaceAnalyzer()).parse("xunit~"); + fail("Fuzzy queries should not be allowed"); + } catch (ParseException expected) { + // expected exception + } + } + + public void testBooleanQuery() throws Exception { + BooleanQuery.setMaxClauseCount(2); + try { + QueryParserWrapper qp = new QueryParserWrapper("field", new WhitespaceAnalyzer()); + qp.parse("one two three"); + fail("ParseException expected due to too many boolean clauses"); + } catch (ParseException expected) { + // too many boolean clauses, so ParseException is expected + } + } + + /** + * This test differs from TestPrecedenceQueryParser + */ + public void testPrecedence() throws Exception { + QueryParserWrapper qp = new QueryParserWrapper("field", new WhitespaceAnalyzer()); + Query query1 = qp.parse("A AND B OR C AND D"); + Query query2 = qp.parse("+A +B +C +D"); + + assertEquals(query1, query2); + } + + public void testLocalDateFormat() throws IOException, ParseException { + + RAMDirectory ramDir = new RAMDirectory(); + IndexWriter iw = new IndexWriter(ramDir, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED); + addDateDoc("a", 2005, 12, 2, 10, 15, 33, iw); + addDateDoc("b", 2005, 12, 4, 22, 15, 00, iw); + iw.close(); + IndexSearcher is = new IndexSearcher(ramDir); + assertHits(1, "[12/1/2005 TO 12/3/2005]", is); + assertHits(2, "[12/1/2005 TO 12/4/2005]", is); + assertHits(1, "[12/3/2005 TO 12/4/2005]", is); + assertHits(1, "{12/1/2005 TO 12/3/2005}", is); + assertHits(1, "{12/1/2005 TO 12/4/2005}", is); + assertHits(0, "{12/3/2005 TO 12/4/2005}", is); + is.close(); + } + + public void testStarParsing() throws Exception { +// final int[] type = new int[1]; +// QueryParser qp = new QueryParserWrapper("field", new WhitespaceAnalyzer()) { +// protected Query getWildcardQuery(String field, String termStr) throws ParseException { +// // override error checking of superclass +// type[0]=1; +// return new TermQuery(new Term(field,termStr)); +// } +// protected Query getPrefixQuery(String field, String termStr) throws ParseException { +// // override error checking of superclass +// type[0]=2; +// return new TermQuery(new Term(field,termStr)); +// } +// +// protected Query getFieldQuery(String field, String queryText) throws ParseException { +// type[0]=3; +// return super.getFieldQuery(field, queryText); +// } +// }; +// +// TermQuery tq; +// +// tq = (TermQuery)qp.parse("foo:zoo*"); +// assertEquals("zoo",tq.getTerm().text()); +// assertEquals(2,type[0]); +// +// tq = (TermQuery)qp.parse("foo:zoo*^2"); +// assertEquals("zoo",tq.getTerm().text()); +// assertEquals(2,type[0]); +// assertEquals(tq.getBoost(),2,0); +// +// tq = (TermQuery)qp.parse("foo:*"); +// assertEquals("*",tq.getTerm().text()); +// assertEquals(1,type[0]); // could be a valid prefix query in the future too +// +// tq = (TermQuery)qp.parse("foo:*^2"); +// assertEquals("*",tq.getTerm().text()); +// assertEquals(1,type[0]); +// assertEquals(tq.getBoost(),2,0); +// +// tq = (TermQuery)qp.parse("*:foo"); +// assertEquals("*",tq.getTerm().field()); +// assertEquals("foo",tq.getTerm().text()); +// assertEquals(3,type[0]); +// +// tq = (TermQuery)qp.parse("*:*"); +// assertEquals("*",tq.getTerm().field()); +// assertEquals("*",tq.getTerm().text()); +// assertEquals(1,type[0]); // could be handled as a prefix query in the future +// +// tq = (TermQuery)qp.parse("(*:*)"); +// assertEquals("*",tq.getTerm().field()); +// assertEquals("*",tq.getTerm().text()); +// assertEquals(1,type[0]); + + } + + public void testStopwords() throws Exception { + QueryParserWrapper qp = new QueryParserWrapper("a", new StopAnalyzer(new String[]{"the", "foo"})); + Query result = qp.parse("a:the OR a:foo"); + assertNotNull("result is null and it shouldn't be", result); + assertTrue("result is not a BooleanQuery", result instanceof BooleanQuery); + assertTrue(((BooleanQuery) result).clauses().size() + " does not equal: " + 0, ((BooleanQuery) result).clauses().size() == 0); + result = qp.parse("a:woo OR a:the"); + assertNotNull("result is null and it shouldn't be", result); + assertTrue("result is not a TermQuery", result instanceof TermQuery); + result = qp.parse("(fieldX:xxxxx OR fieldy:xxxxxxxx)^2 AND (fieldx:the OR fieldy:foo)"); + assertNotNull("result is null and it shouldn't be", result); + assertTrue("result is not a BooleanQuery", result instanceof BooleanQuery); + System.out.println("Result: " + result); + assertTrue(((BooleanQuery) result).clauses().size() + " does not equal: " + 2, ((BooleanQuery) result).clauses().size() == 2); + } + + public void testPositionIncrement() throws Exception { + boolean dflt = StopFilter.getEnablePositionIncrementsDefault(); + StopFilter.setEnablePositionIncrementsDefault(true); + try { + QueryParserWrapper qp = new QueryParserWrapper("a", new StopAnalyzer(new String[]{"the", "in", "are", "this"})); + qp.setEnablePositionIncrements(true); + String qtxt = "\"the words in poisitions pos02578 are stopped in this phrasequery\""; + // 0 2 5 7 8 + int expectedPositions[] = {1,3,4,6,9}; + PhraseQuery pq = (PhraseQuery) qp.parse(qtxt); + //System.out.println("Query text: "+qtxt); + //System.out.println("Result: "+pq); + Term t[] = pq.getTerms(); + int pos[] = pq.getPositions(); + for (int i = 0; i < t.length; i++) { + //System.out.println(i+". "+t[i]+" pos: "+pos[i]); + assertEquals("term "+i+" = "+t[i]+" has wrong term-position!",expectedPositions[i],pos[i]); + } + + } finally { + StopFilter.setEnablePositionIncrementsDefault(dflt); + } + } + + public void testMatchAllDocs() throws Exception { + QueryParserWrapper qp = new QueryParserWrapper("field", new WhitespaceAnalyzer()); + assertEquals(new MatchAllDocsQuery(), qp.parse("*:*")); + assertEquals(new MatchAllDocsQuery(), qp.parse("(*:*)")); + BooleanQuery bq = (BooleanQuery)qp.parse("+*:* -*:*"); + assertTrue(bq.getClauses()[0].getQuery() instanceof MatchAllDocsQuery); + assertTrue(bq.getClauses()[1].getQuery() instanceof MatchAllDocsQuery); + } + + private void assertHits(int expected, String query, IndexSearcher is) throws ParseException, IOException { + QueryParserWrapper qp = new QueryParserWrapper("date", new WhitespaceAnalyzer()); + qp.setLocale(Locale.ENGLISH); + Query q = qp.parse(query); + ScoreDoc[] hits = is.search(q, null, 1000).scoreDocs; + assertEquals(expected, hits.length); + } + + private static void addDateDoc(String content, int year, int month, + int day, int hour, int minute, int second, IndexWriter iw) throws IOException { + Document d = new Document(); + d.add(new Field("f", content, Field.Store.YES, Field.Index.ANALYZED)); + Calendar cal = Calendar.getInstance(); + cal.set(year, month-1, day, hour, minute, second); + d.add(new Field("date", DateField.dateToString(cal.getTime()), Field.Store.YES, Field.Index.NOT_ANALYZED)); + iw.addDocument(d); + } + + public void tearDown() throws Exception { + super.tearDown(); + BooleanQuery.setMaxClauseCount(originalMaxClauses); + } + +} Index: src/test/org/apache/lucene/queryParser/TestMultiFieldQueryParser.java =================================================================== --- src/test/org/apache/lucene/queryParser/TestMultiFieldQueryParser.java (revision 757685) +++ src/test/org/apache/lucene/queryParser/TestMultiFieldQueryParser.java (working copy) @@ -1,326 +0,0 @@ -package org.apache.lucene.queryParser; - -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You under the Apache License, Version 2.0 - * (the "License"); you may not use this file except in compliance with - * the License. You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, software - * distributed under the License is distributed on an "AS IS" BASIS, - * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. - * See the License for the specific language governing permissions and - * limitations under the License. - */ - -import java.io.Reader; -import java.util.HashMap; -import java.util.Map; - -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.standard.StandardAnalyzer; -import org.apache.lucene.document.Document; -import org.apache.lucene.document.Field; -import org.apache.lucene.index.IndexWriter; -import org.apache.lucene.search.BooleanClause; -import org.apache.lucene.search.IndexSearcher; -import org.apache.lucene.search.Query; -import org.apache.lucene.search.ScoreDoc; -import org.apache.lucene.search.BooleanClause.Occur; -import org.apache.lucene.store.Directory; -import org.apache.lucene.store.RAMDirectory; -import org.apache.lucene.util.LuceneTestCase; - -/** - * Tests QueryParser. - */ -public class TestMultiFieldQueryParser extends LuceneTestCase { - - /** test stop words arsing for both the non static form, and for the - * corresponding static form (qtxt, fields[]). */ - public void tesStopwordsParsing() throws Exception { - assertStopQueryEquals("one", "b:one t:one"); - assertStopQueryEquals("one stop", "b:one t:one"); - assertStopQueryEquals("one (stop)", "b:one t:one"); - assertStopQueryEquals("one ((stop))", "b:one t:one"); - assertStopQueryEquals("stop", ""); - assertStopQueryEquals("(stop)", ""); - assertStopQueryEquals("((stop))", ""); - } - - // verify parsing of query using a stopping analyzer - private void assertStopQueryEquals (String qtxt, String expectedRes) throws Exception { - String[] fields = {"b", "t"}; - Occur occur[] = {Occur.SHOULD, Occur.SHOULD}; - TestQueryParser.QPTestAnalyzer a = new TestQueryParser.QPTestAnalyzer(); - MultiFieldQueryParser mfqp = new MultiFieldQueryParser(fields, a); - - Query q = mfqp.parse(qtxt); - assertEquals(expectedRes, q.toString()); - - q = MultiFieldQueryParser.parse(qtxt, fields, occur, a); - assertEquals(expectedRes, q.toString()); - } - - public void testSimple() throws Exception { - String[] fields = {"b", "t"}; - MultiFieldQueryParser mfqp = new MultiFieldQueryParser(fields, new StandardAnalyzer()); - - Query q = mfqp.parse("one"); - assertEquals("b:one t:one", q.toString()); - - q = mfqp.parse("one two"); - assertEquals("(b:one t:one) (b:two t:two)", q.toString()); - - q = mfqp.parse("+one +two"); - assertEquals("+(b:one t:one) +(b:two t:two)", q.toString()); - - q = mfqp.parse("+one -two -three"); - assertEquals("+(b:one t:one) -(b:two t:two) -(b:three t:three)", q.toString()); - - q = mfqp.parse("one^2 two"); - assertEquals("((b:one t:one)^2.0) (b:two t:two)", q.toString()); - - q = mfqp.parse("one~ two"); - assertEquals("(b:one~0.5 t:one~0.5) (b:two t:two)", q.toString()); - - q = mfqp.parse("one~0.8 two^2"); - assertEquals("(b:one~0.8 t:one~0.8) ((b:two t:two)^2.0)", q.toString()); - - q = mfqp.parse("one* two*"); - assertEquals("(b:one* t:one*) (b:two* t:two*)", q.toString()); - - q = mfqp.parse("[a TO c] two"); - assertEquals("(b:[a TO c] t:[a TO c]) (b:two t:two)", q.toString()); - - q = mfqp.parse("w?ldcard"); - assertEquals("b:w?ldcard t:w?ldcard", q.toString()); - - q = mfqp.parse("\"foo bar\""); - assertEquals("b:\"foo bar\" t:\"foo bar\"", q.toString()); - - q = mfqp.parse("\"aa bb cc\" \"dd ee\""); - assertEquals("(b:\"aa bb cc\" t:\"aa bb cc\") (b:\"dd ee\" t:\"dd ee\")", q.toString()); - - q = mfqp.parse("\"foo bar\"~4"); - assertEquals("b:\"foo bar\"~4 t:\"foo bar\"~4", q.toString()); - - // LUCENE-1213: MultiFieldQueryParser was ignoring slop when phrase had a field. - q = mfqp.parse("b:\"foo bar\"~4"); - assertEquals("b:\"foo bar\"~4", q.toString()); - - // make sure that terms which have a field are not touched: - q = mfqp.parse("one f:two"); - assertEquals("(b:one t:one) f:two", q.toString()); - - // AND mode: - mfqp.setDefaultOperator(QueryParser.AND_OPERATOR); - q = mfqp.parse("one two"); - assertEquals("+(b:one t:one) +(b:two t:two)", q.toString()); - q = mfqp.parse("\"aa bb cc\" \"dd ee\""); - assertEquals("+(b:\"aa bb cc\" t:\"aa bb cc\") +(b:\"dd ee\" t:\"dd ee\")", q.toString()); - - } - - public void testBoostsSimple() throws Exception { - Map boosts = new HashMap(); - boosts.put("b", new Float(5)); - boosts.put("t", new Float(10)); - String[] fields = {"b", "t"}; - MultiFieldQueryParser mfqp = new MultiFieldQueryParser(fields, new StandardAnalyzer(), boosts); - - - //Check for simple - Query q = mfqp.parse("one"); - assertEquals("b:one^5.0 t:one^10.0", q.toString()); - - //Check for AND - q = mfqp.parse("one AND two"); - assertEquals("+(b:one^5.0 t:one^10.0) +(b:two^5.0 t:two^10.0)", q.toString()); - - //Check for OR - q = mfqp.parse("one OR two"); - assertEquals("(b:one^5.0 t:one^10.0) (b:two^5.0 t:two^10.0)", q.toString()); - - //Check for AND and a field - q = mfqp.parse("one AND two AND foo:test"); - assertEquals("+(b:one^5.0 t:one^10.0) +(b:two^5.0 t:two^10.0) +foo:test", q.toString()); - - q = mfqp.parse("one^3 AND two^4"); - assertEquals("+((b:one^5.0 t:one^10.0)^3.0) +((b:two^5.0 t:two^10.0)^4.0)", q.toString()); - } - - public void testStaticMethod1() throws ParseException { - String[] fields = {"b", "t"}; - String[] queries = {"one", "two"}; - Query q = MultiFieldQueryParser.parse(queries, fields, new StandardAnalyzer()); - assertEquals("b:one t:two", q.toString()); - - String[] queries2 = {"+one", "+two"}; - q = MultiFieldQueryParser.parse(queries2, fields, new StandardAnalyzer()); - assertEquals("(+b:one) (+t:two)", q.toString()); - - String[] queries3 = {"one", "+two"}; - q = MultiFieldQueryParser.parse(queries3, fields, new StandardAnalyzer()); - assertEquals("b:one (+t:two)", q.toString()); - - String[] queries4 = {"one +more", "+two"}; - q = MultiFieldQueryParser.parse(queries4, fields, new StandardAnalyzer()); - assertEquals("(b:one +b:more) (+t:two)", q.toString()); - - String[] queries5 = {"blah"}; - try { - q = MultiFieldQueryParser.parse(queries5, fields, new StandardAnalyzer()); - fail(); - } catch(IllegalArgumentException e) { - // expected exception, array length differs - } - - // check also with stop words for this static form (qtxts[], fields[]). - TestQueryParser.QPTestAnalyzer stopA = new TestQueryParser.QPTestAnalyzer(); - - String[] queries6 = {"((+stop))", "+((stop))"}; - q = MultiFieldQueryParser.parse(queries6, fields, stopA); - assertEquals("", q.toString()); - - String[] queries7 = {"one ((+stop)) +more", "+((stop)) +two"}; - q = MultiFieldQueryParser.parse(queries7, fields, stopA); - assertEquals("(b:one +b:more) (+t:two)", q.toString()); - - } - - public void testStaticMethod2() throws ParseException { - String[] fields = {"b", "t"}; - BooleanClause.Occur[] flags = {BooleanClause.Occur.MUST, BooleanClause.Occur.MUST_NOT}; - Query q = MultiFieldQueryParser.parse("one", fields, flags, new StandardAnalyzer()); - assertEquals("+b:one -t:one", q.toString()); - - q = MultiFieldQueryParser.parse("one two", fields, flags, new StandardAnalyzer()); - assertEquals("+(b:one b:two) -(t:one t:two)", q.toString()); - - try { - BooleanClause.Occur[] flags2 = {BooleanClause.Occur.MUST}; - q = MultiFieldQueryParser.parse("blah", fields, flags2, new StandardAnalyzer()); - fail(); - } catch(IllegalArgumentException e) { - // expected exception, array length differs - } - } - - public void testStaticMethod2Old() throws ParseException { - String[] fields = {"b", "t"}; - //int[] flags = {MultiFieldQueryParser.REQUIRED_FIELD, MultiFieldQueryParser.PROHIBITED_FIELD}; - BooleanClause.Occur[] flags = {BooleanClause.Occur.MUST, BooleanClause.Occur.MUST_NOT}; - MultiFieldQueryParser parser = new MultiFieldQueryParser(fields, new StandardAnalyzer()); - - Query q = MultiFieldQueryParser.parse("one", fields, flags, new StandardAnalyzer());//, fields, flags, new StandardAnalyzer()); - assertEquals("+b:one -t:one", q.toString()); - - q = MultiFieldQueryParser.parse("one two", fields, flags, new StandardAnalyzer()); - assertEquals("+(b:one b:two) -(t:one t:two)", q.toString()); - - try { - BooleanClause.Occur[] flags2 = {BooleanClause.Occur.MUST}; - q = MultiFieldQueryParser.parse("blah", fields, flags2, new StandardAnalyzer()); - fail(); - } catch(IllegalArgumentException e) { - // expected exception, array length differs - } - } - - public void testStaticMethod3() throws ParseException { - String[] queries = {"one", "two", "three"}; - String[] fields = {"f1", "f2", "f3"}; - BooleanClause.Occur[] flags = {BooleanClause.Occur.MUST, - BooleanClause.Occur.MUST_NOT, BooleanClause.Occur.SHOULD}; - Query q = MultiFieldQueryParser.parse(queries, fields, flags, new StandardAnalyzer()); - assertEquals("+f1:one -f2:two f3:three", q.toString()); - - try { - BooleanClause.Occur[] flags2 = {BooleanClause.Occur.MUST}; - q = MultiFieldQueryParser.parse(queries, fields, flags2, new StandardAnalyzer()); - fail(); - } catch(IllegalArgumentException e) { - // expected exception, array length differs - } - } - - public void testStaticMethod3Old() throws ParseException { - String[] queries = {"one", "two"}; - String[] fields = {"b", "t"}; - BooleanClause.Occur[] flags = {BooleanClause.Occur.MUST, BooleanClause.Occur.MUST_NOT}; - Query q = MultiFieldQueryParser.parse(queries, fields, flags, new StandardAnalyzer()); - assertEquals("+b:one -t:two", q.toString()); - - try { - BooleanClause.Occur[] flags2 = {BooleanClause.Occur.MUST}; - q = MultiFieldQueryParser.parse(queries, fields, flags2, new StandardAnalyzer()); - fail(); - } catch(IllegalArgumentException e) { - // expected exception, array length differs - } - } - - public void testAnalyzerReturningNull() throws ParseException { - String[] fields = new String[] { "f1", "f2", "f3" }; - MultiFieldQueryParser parser = new MultiFieldQueryParser(fields, new AnalyzerReturningNull()); - Query q = parser.parse("bla AND blo"); - assertEquals("+(f2:bla f3:bla) +(f2:blo f3:blo)", q.toString()); - // the following queries are not affected as their terms are not analyzed anyway: - q = parser.parse("bla*"); - assertEquals("f1:bla* f2:bla* f3:bla*", q.toString()); - q = parser.parse("bla~"); - assertEquals("f1:bla~0.5 f2:bla~0.5 f3:bla~0.5", q.toString()); - q = parser.parse("[a TO c]"); - assertEquals("f1:[a TO c] f2:[a TO c] f3:[a TO c]", q.toString()); - } - - public void testStopWordSearching() throws Exception { - Analyzer analyzer = new StandardAnalyzer(); - Directory ramDir = new RAMDirectory(); - IndexWriter iw = new IndexWriter(ramDir, analyzer, true, IndexWriter.MaxFieldLength.LIMITED); - Document doc = new Document(); - doc.add(new Field("body", "blah the footest blah", Field.Store.NO, Field.Index.ANALYZED)); - iw.addDocument(doc); - iw.close(); - - MultiFieldQueryParser mfqp = - new MultiFieldQueryParser(new String[] {"body"}, analyzer); - mfqp.setDefaultOperator(QueryParser.Operator.AND); - Query q = mfqp.parse("the footest"); - IndexSearcher is = new IndexSearcher(ramDir); - ScoreDoc[] hits = is.search(q, null, 1000).scoreDocs; - assertEquals(1, hits.length); - is.close(); - } - - /** - * Return empty tokens for field "f1". - */ - private static class AnalyzerReturningNull extends Analyzer { - StandardAnalyzer stdAnalyzer = new StandardAnalyzer(); - - public AnalyzerReturningNull() { - } - - public TokenStream tokenStream(String fieldName, Reader reader) { - if ("f1".equals(fieldName)) { - return new EmptyTokenStream(); - } else { - return stdAnalyzer.tokenStream(fieldName, reader); - } - } - - private static class EmptyTokenStream extends TokenStream { - public Token next(final Token reusableToken) { - return null; - } - } - } - -} Index: common-build.xml =================================================================== --- common-build.xml (revision 757685) +++ common-build.xml (working copy) @@ -1,588 +0,0 @@ - - - - - - - This file is designed for importing into a main build file, and not intended - for standalone use. - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - One or more of the JavaCC .jj files is newer than its corresponding - .java file. Run the "javacc" target to regenerate the artifacts. - - - - - - - - - - - - - - - - One or more of the JFlex .jflex files is newer than its corresponding - .java file. Run the "jflex" target to regenerate the artifacts. - - - - - - ################################################################## - JavaCC not found. - JavaCC Home: ${javacc.home} - JavaCC JAR: ${javacc.jar} - - Please download and install JavaCC from: - - <http://javacc.dev.java.net> - - Then, create a build.properties file either in your home - directory, or within the Lucene directory and set the javacc.home - property to the path where JavaCC is installed. For example, - if you installed JavaCC in /usr/local/java/javacc-3.2, then set the - javacc.home property to: - - javacc.home=/usr/local/java/javacc-3.2 - - If you get an error like the one below, then you have not installed - things correctly. Please check all your paths and try again. - - java.lang.NoClassDefFoundError: org.javacc.parser.Main - ################################################################## - - - - - - - ################################################################## - JFlex not found. - JFlex Home: ${jflex.home} - - Please download and install JFlex from: - - <http://jflex.de/download.html> - - Then, create a build.properties file either in your home - directory, or within the Lucene directory and set the jflex.home - property to the path where JFlex is installed. For example, - if you installed JFlex in /usr/local/java/jflex-1.4.1, then set the - jflex.home property to: - - jflex.home=/usr/local/java/jflex-1.4.1 - - ################################################################## - - - - - - - - - - - - - - - - - - - - ################################################################## - Maven ant tasks not found. - Please make sure the maven-ant-tasks jar is in ANT_HOME/lib, or made - available to Ant using other mechanisms like -lib or CLASSPATH. - ################################################################## - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - MAYBE - Tests failed! - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Clover not found. Code coverage reports disabled. - - - - - - ################################################################## - Clover not found. - Please make sure clover.jar is in ANT_HOME/lib, or made available - to Ant using other mechanisms like -lib or CLASSPATH. - ################################################################## - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -