field as a single byte and returns an array
* of size reader.maxDoc() of the value each document
* has in the given field.
@@ -97,9 +266,15 @@
* @return The values in the given field for each document.
* @throws IOException If any error occurs.
*/
- public byte[] getBytes (IndexReader reader, String field)
- throws IOException;
+ public byte[] getBytes(IndexReader reader, String field) throws IOException {
+ return getBytes(reader, field, BYTE_PARSER);
+ }
+
+
+
+
+
/** Checks the internal cache for an appropriate entry, and if none is found,
* reads the terms in field as bytes and returns an array of
* size reader.maxDoc() of the value each document has in the
@@ -110,9 +285,39 @@
* @return The values in the given field for each document.
* @throws IOException If any error occurs.
*/
- public byte[] getBytes (IndexReader reader, String field, ByteParser parser)
- throws IOException;
+ public byte[] getBytes(IndexReader reader, String field, ByteParser parser)
+ throws IOException {
+ return (byte[]) bytesCache.get(reader, new Entry(field, parser));
+ }
+ Cache bytesCache = new Cache() {
+
+ protected Object createValue(IndexReader reader, Object entryKey)
+ throws IOException {
+ Entry entry = (Entry) entryKey;
+ String field = entry.field;
+ ByteParser parser = (ByteParser) entry.custom;
+ final byte[] retArray = new byte[reader.maxDoc()];
+ TermDocs termDocs = reader.termDocs();
+ TermEnum termEnum = reader.terms(new Term(field, ""));
+ try {
+ do {
+ Term term = termEnum.term();
+ if (term == null || term.field() != field) break;
+ byte termval = parser.parseByte(term.text());
+ termDocs.seek(termEnum);
+ while (termDocs.next()) {
+ retArray[termDocs.doc()] = termval;
+ }
+ } while (termEnum.next());
+ } finally {
+ termDocs.close();
+ termEnum.close();
+ }
+ return retArray;
+ }
+ };
+
/** Checks the internal cache for an appropriate entry, and if none is
* found, reads the terms in field as shorts and returns an array
* of size reader.maxDoc() of the value each document
@@ -122,8 +327,9 @@
* @return The values in the given field for each document.
* @throws IOException If any error occurs.
*/
- public short[] getShorts (IndexReader reader, String field)
- throws IOException;
+ public short[] getShorts(IndexReader reader, String field) throws IOException {
+ return getShorts(reader, field, SHORT_PARSER);
+ }
/** Checks the internal cache for an appropriate entry, and if none is found,
* reads the terms in field as shorts and returns an array of
@@ -135,9 +341,39 @@
* @return The values in the given field for each document.
* @throws IOException If any error occurs.
*/
- public short[] getShorts (IndexReader reader, String field, ShortParser parser)
- throws IOException;
+ public short[] getShorts(IndexReader reader, String field, ShortParser parser)
+ throws IOException {
+ return (short[]) shortsCache.get(reader, new Entry(field, parser));
+ }
+ Cache shortsCache = new Cache() {
+
+ protected Object createValue(IndexReader reader, Object entryKey)
+ throws IOException {
+ Entry entry = (Entry) entryKey;
+ String field = entry.field;
+ ShortParser parser = (ShortParser) entry.custom;
+ final short[] retArray = new short[reader.maxDoc()];
+ TermDocs termDocs = reader.termDocs();
+ TermEnum termEnum = reader.terms(new Term(field, ""));
+ try {
+ do {
+ Term term = termEnum.term();
+ if (term == null || term.field() != field) break;
+ short termval = parser.parseShort(term.text());
+ termDocs.seek(termEnum);
+ while (termDocs.next()) {
+ retArray[termDocs.doc()] = termval;
+ }
+ } while (termEnum.next());
+ } finally {
+ termDocs.close();
+ termEnum.close();
+ }
+ return retArray;
+ }
+ };
+
/** Checks the internal cache for an appropriate entry, and if none is
* found, reads the terms in field as integers and returns an array
* of size reader.maxDoc() of the value each document
@@ -147,8 +383,9 @@
* @return The values in the given field for each document.
* @throws IOException If any error occurs.
*/
- public int[] getInts (IndexReader reader, String field)
- throws IOException;
+ public int[] getInts(IndexReader reader, String field) throws IOException {
+ return getInts(reader, field, INT_PARSER);
+ }
/** Checks the internal cache for an appropriate entry, and if none is found,
* reads the terms in field as integers and returns an array of
@@ -160,9 +397,40 @@
* @return The values in the given field for each document.
* @throws IOException If any error occurs.
*/
- public int[] getInts (IndexReader reader, String field, IntParser parser)
- throws IOException;
+ public int[] getInts(IndexReader reader, String field, IntParser parser)
+ throws IOException {
+ return (int[]) intsCache.get(reader, new Entry(field, parser));
+ }
+ Cache intsCache = new Cache() {
+
+ protected Object createValue(IndexReader reader, Object entryKey)
+ throws IOException {
+ Entry entry = (Entry) entryKey;
+ String field = entry.field;
+ IntParser parser = (IntParser) entry.custom;
+ final int[] retArray = new int[reader.maxDoc()];
+ TermDocs termDocs = reader.termDocs();
+ TermEnum termEnum = reader.terms(new Term(field, ""));
+ try {
+ do {
+ Term term = termEnum.term();
+ if (term == null || term.field() != field) break;
+ int termval = parser.parseInt(term.text());
+ termDocs.seek(termEnum);
+ while (termDocs.next()) {
+ retArray[termDocs.doc()] = termval;
+ }
+ } while (termEnum.next());
+ } finally {
+ termDocs.close();
+ termEnum.close();
+ }
+ return retArray;
+ }
+ };
+
+
/** Checks the internal cache for an appropriate entry, and if
* none is found, reads the terms in field as floats and returns an array
* of size reader.maxDoc() of the value each document
@@ -172,8 +440,10 @@
* @return The values in the given field for each document.
* @throws IOException If any error occurs.
*/
- public float[] getFloats (IndexReader reader, String field)
- throws IOException;
+ public float[] getFloats(IndexReader reader, String field)
+ throws IOException {
+ return getFloats(reader, field, FLOAT_PARSER);
+ }
/** Checks the internal cache for an appropriate entry, and if
* none is found, reads the terms in field as floats and returns an array
@@ -185,9 +455,39 @@
* @return The values in the given field for each document.
* @throws IOException If any error occurs.
*/
- public float[] getFloats (IndexReader reader, String field,
- FloatParser parser) throws IOException;
+ public float[] getFloats(IndexReader reader, String field, FloatParser parser)
+ throws IOException {
+ return (float[]) floatsCache.get(reader, new Entry(field, parser));
+ }
+ Cache floatsCache = new Cache() {
+
+ protected Object createValue(IndexReader reader, Object entryKey)
+ throws IOException {
+ Entry entry = (Entry) entryKey;
+ String field = entry.field;
+ FloatParser parser = (FloatParser) entry.custom;
+ final float[] retArray = new float[reader.maxDoc()];
+ TermDocs termDocs = reader.termDocs();
+ TermEnum termEnum = reader.terms(new Term(field, ""));
+ try {
+ do {
+ Term term = termEnum.term();
+ if (term == null || term.field() != field) break;
+ float termval = parser.parseFloat(term.text());
+ termDocs.seek(termEnum);
+ while (termDocs.next()) {
+ retArray[termDocs.doc()] = termval;
+ }
+ } while (termEnum.next());
+ } finally {
+ termDocs.close();
+ termEnum.close();
+ }
+ return retArray;
+ }
+ };
+
/** Checks the internal cache for an appropriate entry, and if none
* is found, reads the term values in field and returns an array
* of size reader.maxDoc() containing the value each document
@@ -197,9 +497,37 @@
* @return The values in the given field for each document.
* @throws IOException If any error occurs.
*/
- public String[] getStrings (IndexReader reader, String field)
- throws IOException;
+ public String[] getStrings(IndexReader reader, String field)
+ throws IOException {
+ return (String[]) stringsCache.get(reader, field);
+ }
+ Cache stringsCache = new Cache() {
+
+ protected Object createValue(IndexReader reader, Object fieldKey)
+ throws IOException {
+ String field = ((String) fieldKey).intern();
+ final String[] retArray = new String[reader.maxDoc()];
+ TermDocs termDocs = reader.termDocs();
+ TermEnum termEnum = reader.terms(new Term(field, ""));
+ try {
+ do {
+ Term term = termEnum.term();
+ if (term == null || term.field() != field) break;
+ String termval = term.text();
+ termDocs.seek(termEnum);
+ while (termDocs.next()) {
+ retArray[termDocs.doc()] = termval;
+ }
+ } while (termEnum.next());
+ } finally {
+ termDocs.close();
+ termEnum.close();
+ }
+ return retArray;
+ }
+ };
+
/** Checks the internal cache for an appropriate entry, and if none
* is found reads the term values in field and returns
* an array of them in natural order, along with an array telling
@@ -209,9 +537,80 @@
* @return Array of terms and index into the array for each document.
* @throws IOException If any error occurs.
*/
- public StringIndex getStringIndex (IndexReader reader, String field)
- throws IOException;
+ public StringIndex getStringIndex(IndexReader reader, String field)
+ throws IOException {
+ return (StringIndex) stringsIndexCache.get(reader, field);
+ }
+ Cache stringsIndexCache = new Cache() {
+
+ protected Object createValue(IndexReader reader, Object fieldKey)
+ throws IOException {
+ String field = ((String) fieldKey).intern();
+ final int[] retArray = new int[reader.maxDoc()];
+ String[] mterms = new String[reader.maxDoc() + 1];
+ TermDocs termDocs = reader.termDocs();
+ TermEnum termEnum = reader.terms(new Term(field, ""));
+ int t = 0; // current term number
+
+ // an entry for documents that have no terms in this field
+ // should a document with no terms be at top or bottom?
+ // this puts them at the top - if it is changed, FieldDocSortedHitQueue
+ // needs to change as well.
+ mterms[t++] = null;
+
+ try {
+ do {
+ Term term = termEnum.term();
+ if (term == null || term.field() != field) break;
+
+ // store term text
+ // we expect that there is at most one term per document
+ if (t >= mterms.length) throw new RuntimeException("there are more terms than " +
+ "documents in field \"" + field + "\", but it's impossible to sort on " +
+ "tokenized fields");
+ mterms[t] = term.text();
+
+ termDocs.seek(termEnum);
+ while (termDocs.next()) {
+ retArray[termDocs.doc()] = t;
+ }
+
+ t++;
+ } while (termEnum.next());
+ } finally {
+ termDocs.close();
+ termEnum.close();
+ }
+
+ if (t == 0) {
+ // if there are no terms, make the term array
+ // have a single null entry
+ mterms = new String[1];
+ } else if (t < mterms.length) {
+ // if there are less terms than documents,
+ // trim off the dead array space
+ String[] terms = new String[t];
+ System.arraycopy(mterms, 0, terms, 0, t);
+ mterms = terms;
+ }
+
+ StringIndex value = new StringIndex(retArray, mterms);
+ return value;
+ }
+ };
+
+ /** The pattern used to detect integer values in a field */
+ /** removed for java 1.3 compatibility
+ protected static final Pattern pIntegers = Pattern.compile ("[0-9\\-]+");
+ **/
+
+ /** The pattern used to detect float values in a field */
+ /**
+ * removed for java 1.3 compatibility
+ * protected static final Object pFloats = Pattern.compile ("[0-9+\\-\\.eEfFdD]+");
+ */
+
/** Checks the internal cache for an appropriate entry, and if
* none is found reads field to see if it contains integers, floats
* or strings, and then calls one of the other methods in this class to get the
@@ -223,9 +622,63 @@
* @return int[], float[] or StringIndex.
* @throws IOException If any error occurs.
*/
- public Object getAuto (IndexReader reader, String field)
- throws IOException;
+ public Object getAuto(IndexReader reader, String field) throws IOException {
+ return autoCache.get(reader, field);
+ }
+
+ Cache autoCache = new Cache() {
+
+ protected Object createValue(IndexReader reader, Object fieldKey)
+ throws IOException {
+ String field = ((String)fieldKey).intern();
+ TermEnum enumerator = reader.terms (new Term (field, ""));
+ try {
+ Term term = enumerator.term();
+ if (term == null) {
+ throw new RuntimeException ("no terms in field " + field + " - cannot determine sort type");
+ }
+ Object ret = null;
+ if (term.field() == field) {
+ String termtext = term.text().trim();
+
+ /**
+ * Java 1.4 level code:
+
+ if (pIntegers.matcher(termtext).matches())
+ return IntegerSortedHitQueue.comparator (reader, enumerator, field);
+
+ else if (pFloats.matcher(termtext).matches())
+ return FloatSortedHitQueue.comparator (reader, enumerator, field);
+ */
+
+ // Java 1.3 level code:
+ try {
+ Integer.parseInt (termtext);
+ ret = getInts (reader, field);
+ } catch (NumberFormatException nfe1) {
+ try {
+ Long.parseLong(termtext);
+ ret = getLongs (reader, field);
+ } catch (NumberFormatException nfe2) {
+ try {
+ Float.parseFloat (termtext);
+ ret = getFloats (reader, field);
+ } catch (NumberFormatException nfe3) {
+ ret = getStringIndex (reader, field);
+ }
+ }
+ }
+ } else {
+ throw new RuntimeException ("field \"" + field + "\" does not appear to be indexed");
+ }
+ return ret;
+ } finally {
+ enumerator.close();
+ }
+ }
+ };
+
/** Checks the internal cache for an appropriate entry, and if none
* is found reads the terms out of field and calls the given SortComparator
* to get the sort values. A hit in the cache will happen if reader,
@@ -237,7 +690,159 @@
* @return Array of sort objects, one for each document.
* @throws IOException If any error occurs.
*/
- public Comparable[] getCustom (IndexReader reader, String field, SortComparator comparator)
- throws IOException;
+ public Comparable[] getCustom(IndexReader reader, String field,
+ SortComparator comparator) throws IOException {
+ return (Comparable[]) customCache.get(reader, new Entry(field, comparator));
+ }
+
+ Cache customCache = new Cache() {
+
+ protected Object createValue(IndexReader reader, Object entryKey)
+ throws IOException {
+ Entry entry = (Entry) entryKey;
+ String field = entry.field;
+ SortComparator comparator = (SortComparator) entry.custom;
+ final Comparable[] retArray = new Comparable[reader.maxDoc()];
+ TermDocs termDocs = reader.termDocs();
+ TermEnum termEnum = reader.terms(new Term(field, ""));
+ try {
+ do {
+ Term term = termEnum.term();
+ if (term == null || term.field() != field) break;
+ Comparable termval = comparator.getComparable(term.text());
+ termDocs.seek(termEnum);
+ while (termDocs.next()) {
+ retArray[termDocs.doc()] = termval;
+ }
+ } while (termEnum.next());
+ } finally {
+ termDocs.close();
+ termEnum.close();
+ }
+ return retArray;
+ }
+ };
+
+ /**
+ * Checks the internal cache for an appropriate entry, and if none is
+ * found, reads the terms in field as longs and returns an array
+ * of size reader.maxDoc() of the value each document
+ * has in the given field.
+ *
+ * @param reader Used to get field values.
+ * @param field Which field contains the longs.
+ * @return The values in the given field for each document.
+ * @throws java.io.IOException If any error occurs.
+ */
+ public long[] getLongs(IndexReader reader, String field) throws IOException {
+ return getLongs(reader, field, LONG_PARSER);
+ }
+
+ /**
+ * Checks the internal cache for an appropriate entry, and if none is found,
+ * reads the terms in field as longs and returns an array of
+ * size reader.maxDoc() of the value each document has in the
+ * given field.
+ *
+ * @param reader Used to get field values.
+ * @param field Which field contains the longs.
+ * @param parser Computes integer for string values.
+ * @return The values in the given field for each document.
+ * @throws IOException If any error occurs.
+ */
+ public long[] getLongs(IndexReader reader, String field, FieldCache.LongParser parser)
+ throws IOException {
+ return (long[]) longsCache.get(reader, new Entry(field, parser));
+ }
+
+ Cache longsCache = new Cache() {
+
+ protected Object createValue(IndexReader reader, Object entryKey)
+ throws IOException {
+ Entry entry = (Entry) entryKey;
+ String field = entry.field;
+ FieldCache.LongParser parser = (FieldCache.LongParser) entry.custom;
+ final long[] retArray = new long[reader.maxDoc()];
+ TermDocs termDocs = reader.termDocs();
+ TermEnum termEnum = reader.terms(new Term(field, ""));
+ try {
+ do {
+ Term term = termEnum.term();
+ if (term == null || term.field() != field) break;
+ long termval = parser.parseLong(term.text());
+ termDocs.seek(termEnum);
+ while (termDocs.next()) {
+ retArray[termDocs.doc()] = termval;
+ }
+ } while (termEnum.next());
+ } finally {
+ termDocs.close();
+ termEnum.close();
+ }
+ return retArray;
+ }
+ };
+
+ /**
+ * Checks the internal cache for an appropriate entry, and if none is
+ * found, reads the terms in field as integers and returns an array
+ * of size reader.maxDoc() of the value each document
+ * has in the given field.
+ *
+ * @param reader Used to get field values.
+ * @param field Which field contains the doubles.
+ * @return The values in the given field for each document.
+ * @throws IOException If any error occurs.
+ */
+ public double[] getDoubles(IndexReader reader, String field)
+ throws IOException {
+ return getDoubles(reader, field, DOUBLE_PARSER);
+ }
+
+ /**
+ * Checks the internal cache for an appropriate entry, and if none is found,
+ * reads the terms in field as doubles and returns an array of
+ * size reader.maxDoc() of the value each document has in the
+ * given field.
+ *
+ * @param reader Used to get field values.
+ * @param field Which field contains the doubles.
+ * @param parser Computes integer for string values.
+ * @return The values in the given field for each document.
+ * @throws IOException If any error occurs.
+ */
+ public double[] getDoubles(IndexReader reader, String field, FieldCache.DoubleParser parser)
+ throws IOException {
+ return (double[]) doublesCache.get(reader, new Entry(field, parser));
+ }
+
+ Cache doublesCache = new Cache() {
+
+ protected Object createValue(IndexReader reader, Object entryKey)
+ throws IOException {
+ Entry entry = (Entry) entryKey;
+ String field = entry.field;
+ FieldCache.DoubleParser parser = (FieldCache.DoubleParser) entry.custom;
+ final double[] retArray = new double[reader.maxDoc()];
+ TermDocs termDocs = reader.termDocs();
+ TermEnum termEnum = reader.terms(new Term(field, ""));
+ try {
+ do {
+ Term term = termEnum.term();
+ if (term == null || term.field() != field) break;
+ double termval = parser.parseDouble(term.text());
+ termDocs.seek(termEnum);
+ while (termDocs.next()) {
+ retArray[termDocs.doc()] = termval;
+ }
+ } while (termEnum.next());
+ } finally {
+ termDocs.close();
+ termEnum.close();
+ }
+ return retArray;
+ }
+ };
+
}
Index: src/java/org/apache/lucene/search/ExtendedFieldCacheImpl.java
===================================================================
--- src/java/org/apache/lucene/search/ExtendedFieldCacheImpl.java (revision 600585)
+++ src/java/org/apache/lucene/search/ExtendedFieldCacheImpl.java (working copy)
@@ -1,117 +0,0 @@
-package org.apache.lucene.search;
-
-import org.apache.lucene.index.IndexReader;
-import org.apache.lucene.index.Term;
-import org.apache.lucene.index.TermDocs;
-import org.apache.lucene.index.TermEnum;
-
-import java.io.IOException;
-
-
-/**
- *
- *
- **/
-class ExtendedFieldCacheImpl extends FieldCacheImpl implements ExtendedFieldCache {
- private static final LongParser LONG_PARSER = new LongParser() {
- public long parseLong(String value) {
- return Long.parseLong(value);
- }
- };
-
- private static final DoubleParser DOUBLE_PARSER = new DoubleParser() {
- public double parseDouble(String value) {
- return Double.parseDouble(value);
- }
- };
-
- private static final ByteParser BYTE_PARSER = new ByteParser() {
- public byte parseByte(String string) {
- return Byte.parseByte(string);
- }
- };
-
- private static final ShortParser SHORT_PARSER = new ShortParser() {
- public short parseShort(String string) {
- return Short.parseShort(string);
- }
- };
-
- public long[] getLongs(IndexReader reader, String field) throws IOException {
- return getLongs(reader, field, LONG_PARSER);
- }
-
- // inherit javadocs
- public long[] getLongs(IndexReader reader, String field, LongParser parser)
- throws IOException {
- return (long[]) longsCache.get(reader, new Entry(field, parser));
- }
-
- Cache longsCache = new Cache() {
-
- protected Object createValue(IndexReader reader, Object entryKey)
- throws IOException {
- Entry entry = (Entry) entryKey;
- String field = entry.field;
- LongParser parser = (LongParser) entry.custom;
- final long[] retArray = new long[reader.maxDoc()];
- TermDocs termDocs = reader.termDocs();
- TermEnum termEnum = reader.terms (new Term(field, ""));
- try {
- do {
- Term term = termEnum.term();
- if (term==null || term.field() != field) break;
- long termval = parser.parseLong(term.text());
- termDocs.seek (termEnum);
- while (termDocs.next()) {
- retArray[termDocs.doc()] = termval;
- }
- } while (termEnum.next());
- } finally {
- termDocs.close();
- termEnum.close();
- }
- return retArray;
- }
- };
-
- // inherit javadocs
- public double[] getDoubles(IndexReader reader, String field)
- throws IOException {
- return getDoubles(reader, field, DOUBLE_PARSER);
- }
-
- // inherit javadocs
- public double[] getDoubles(IndexReader reader, String field, DoubleParser parser)
- throws IOException {
- return (double[]) doublesCache.get(reader, new Entry(field, parser));
- }
-
- Cache doublesCache = new Cache() {
-
- protected Object createValue(IndexReader reader, Object entryKey)
- throws IOException {
- Entry entry = (Entry) entryKey;
- String field = entry.field;
- DoubleParser parser = (DoubleParser) entry.custom;
- final double[] retArray = new double[reader.maxDoc()];
- TermDocs termDocs = reader.termDocs();
- TermEnum termEnum = reader.terms (new Term (field, ""));
- try {
- do {
- Term term = termEnum.term();
- if (term==null || term.field() != field) break;
- double termval = parser.parseDouble(term.text());
- termDocs.seek (termEnum);
- while (termDocs.next()) {
- retArray[termDocs.doc()] = termval;
- }
- } while (termEnum.next());
- } finally {
- termDocs.close();
- termEnum.close();
- }
- return retArray;
- }
- };
-}
Index: src/java/org/apache/lucene/search/FieldSortedHitQueue.java
===================================================================
--- src/java/org/apache/lucene/search/FieldSortedHitQueue.java (revision 600585)
+++ src/java/org/apache/lucene/search/FieldSortedHitQueue.java (working copy)
@@ -149,19 +149,19 @@
throws IOException {
if (type == SortField.DOC) return ScoreDocComparator.INDEXORDER;
if (type == SortField.SCORE) return ScoreDocComparator.RELEVANCE;
- FieldCacheImpl.Entry entry = (factory != null)
- ? new FieldCacheImpl.Entry (field, factory)
- : new FieldCacheImpl.Entry (field, type, locale);
+ FieldCache.Entry entry = (factory != null)
+ ? new FieldCache.Entry (field, factory)
+ : new FieldCache.Entry (field, type, locale);
return (ScoreDocComparator)Comparators.get(reader, entry);
}
/** Internal cache of comparators. Similar to FieldCache, only
* caches comparators instead of term values. */
- static final FieldCacheImpl.Cache Comparators = new FieldCacheImpl.Cache() {
+ static final FieldCache.Cache Comparators = new FieldCache.Cache() {
protected Object createValue(IndexReader reader, Object entryKey)
throws IOException {
- FieldCacheImpl.Entry entry = (FieldCacheImpl.Entry) entryKey;
+ FieldCache.Entry entry = (FieldCache.Entry) entryKey;
String fieldname = entry.field;
int type = entry.type;
Locale locale = entry.locale;
@@ -174,6 +174,12 @@
case SortField.INT:
comparator = comparatorInt (reader, fieldname);
break;
+ case SortField.SHORT:
+ comparator = comparatorShort(reader, fieldname);
+ break;
+ case SortField.BYTE:
+ comparator = comparatorByte(reader, fieldname);
+ break;
case SortField.FLOAT:
comparator = comparatorFloat (reader, fieldname);
break;
@@ -198,6 +204,68 @@
};
/**
+ * Returns a comparator for sorting hits according to a field containing bytes.
+ * @param reader Index to use.
+ * @param fieldname Fieldable containg integer values.
+ * @return Comparator for sorting hits.
+ * @throws IOException If an error occurs reading the index.
+ */
+ static ScoreDocComparator comparatorByte(final IndexReader reader, final String fieldname)
+ throws IOException {
+ final String field = fieldname.intern();
+ final byte[] fieldOrder = FieldCache.DEFAULT.getBytes(reader, field);
+ return new ScoreDocComparator() {
+
+ public final int compare (final ScoreDoc i, final ScoreDoc j) {
+ final int fi = fieldOrder[i.doc];
+ final int fj = fieldOrder[j.doc];
+ if (fi < fj) return -1;
+ if (fi > fj) return 1;
+ return 0;
+ }
+
+ public Comparable sortValue (final ScoreDoc i) {
+ return new Byte(fieldOrder[i.doc]);
+ }
+
+ public int sortType() {
+ return SortField.INT;
+ }
+ };
+ }
+
+ /**
+ * Returns a comparator for sorting hits according to a field containing shorts.
+ * @param reader Index to use.
+ * @param fieldname Fieldable containg integer values.
+ * @return Comparator for sorting hits.
+ * @throws IOException If an error occurs reading the index.
+ */
+ static ScoreDocComparator comparatorShort(final IndexReader reader, final String fieldname)
+ throws IOException {
+ final String field = fieldname.intern();
+ final short[] fieldOrder = FieldCache.DEFAULT.getShorts(reader, field);
+ return new ScoreDocComparator() {
+
+ public final int compare (final ScoreDoc i, final ScoreDoc j) {
+ final int fi = fieldOrder[i.doc];
+ final int fj = fieldOrder[j.doc];
+ if (fi < fj) return -1;
+ if (fi > fj) return 1;
+ return 0;
+ }
+
+ public Comparable sortValue (final ScoreDoc i) {
+ return new Short(fieldOrder[i.doc]);
+ }
+
+ public int sortType() {
+ return SortField.SHORT;
+ }
+ };
+ }
+
+ /**
* Returns a comparator for sorting hits according to a field containing integers.
* @param reader Index to use.
* @param fieldname Fieldable containg integer values.
@@ -238,7 +306,7 @@
static ScoreDocComparator comparatorLong (final IndexReader reader, final String fieldname)
throws IOException {
final String field = fieldname.intern();
- final long[] fieldOrder = ExtendedFieldCache.EXT_DEFAULT.getLongs (reader, field);
+ final long[] fieldOrder = FieldCache.DEFAULT.getLongs (reader, field);
return new ScoreDocComparator() {
public final int compare (final ScoreDoc i, final ScoreDoc j) {
@@ -301,7 +369,7 @@
static ScoreDocComparator comparatorDouble(final IndexReader reader, final String fieldname)
throws IOException {
final String field = fieldname.intern();
- final double[] fieldOrder = ExtendedFieldCache.EXT_DEFAULT.getDoubles (reader, field);
+ final double[] fieldOrder = FieldCache.DEFAULT.getDoubles (reader, field);
return new ScoreDocComparator () {
public final int compare (final ScoreDoc i, final ScoreDoc j) {
Index: src/java/org/apache/lucene/search/ExtendedFieldCache.java
===================================================================
--- src/java/org/apache/lucene/search/ExtendedFieldCache.java (revision 600585)
+++ src/java/org/apache/lucene/search/ExtendedFieldCache.java (working copy)
@@ -1,87 +0,0 @@
-package org.apache.lucene.search;
-
-import org.apache.lucene.index.IndexReader;
-
-import java.io.IOException;
-
-
-/**
- *
- *
- **/
-public interface ExtendedFieldCache extends FieldCache {
- public interface LongParser {
- /**
- * Return an long representation of this field's value.
- */
- public long parseLong(String string);
- }
-
- public interface DoubleParser {
- /**
- * Return an long representation of this field's value.
- */
- public double parseDouble(String string);
- }
-
- public static ExtendedFieldCache EXT_DEFAULT = new ExtendedFieldCacheImpl();
-
- /**
- * Checks the internal cache for an appropriate entry, and if none is
- * found, reads the terms in field as longs and returns an array
- * of size reader.maxDoc() of the value each document
- * has in the given field.
- *
- * @param reader Used to get field values.
- * @param field Which field contains the longs.
- * @return The values in the given field for each document.
- * @throws java.io.IOException If any error occurs.
- */
- public long[] getLongs(IndexReader reader, String field)
- throws IOException;
-
- /**
- * Checks the internal cache for an appropriate entry, and if none is found,
- * reads the terms in field as longs and returns an array of
- * size reader.maxDoc() of the value each document has in the
- * given field.
- *
- * @param reader Used to get field values.
- * @param field Which field contains the longs.
- * @param parser Computes integer for string values.
- * @return The values in the given field for each document.
- * @throws IOException If any error occurs.
- */
- public long[] getLongs(IndexReader reader, String field, LongParser parser)
- throws IOException;
-
-
- /**
- * Checks the internal cache for an appropriate entry, and if none is
- * found, reads the terms in field as integers and returns an array
- * of size reader.maxDoc() of the value each document
- * has in the given field.
- *
- * @param reader Used to get field values.
- * @param field Which field contains the doubles.
- * @return The values in the given field for each document.
- * @throws IOException If any error occurs.
- */
- public double[] getDoubles(IndexReader reader, String field)
- throws IOException;
-
- /**
- * Checks the internal cache for an appropriate entry, and if none is found,
- * reads the terms in field as doubles and returns an array of
- * size reader.maxDoc() of the value each document has in the
- * given field.
- *
- * @param reader Used to get field values.
- * @param field Which field contains the doubles.
- * @param parser Computes integer for string values.
- * @return The values in the given field for each document.
- * @throws IOException If any error occurs.
- */
- public double[] getDoubles(IndexReader reader, String field, DoubleParser parser)
- throws IOException;
-}
Index: src/java/org/apache/lucene/search/SortField.java
===================================================================
--- src/java/org/apache/lucene/search/SortField.java (revision 600585)
+++ src/java/org/apache/lucene/search/SortField.java (working copy)
@@ -68,10 +68,20 @@
* lower values are at the front. */
public static final int DOUBLE = 7;
+ /**
+ * Sort using term values as encoded Shorts. Sort values are shorts and lower values are at the front
+ */
+ public static final int SHORT = 8;
+
/** Sort using a custom Comparator. Sort values are any Comparable and
* sorting is done according to natural order. */
public static final int CUSTOM = 9;
+ /**
+ * Sort using term values as encoded bytes. Sort values are bytes and lower values are at the front
+ */
+ public static final int BYTE = 10;
+
// IMPLEMENTATION NOTE: the FieldCache.STRING_INDEX is in the same "namespace"
// as the above static int values. Any new values must not have the same value
// as FieldCache.STRING_INDEX.
Index: src/java/org/apache/lucene/search/FieldCacheImpl.java
===================================================================
--- src/java/org/apache/lucene/search/FieldCacheImpl.java (revision 600585)
+++ src/java/org/apache/lucene/search/FieldCacheImpl.java (working copy)
@@ -1,560 +0,0 @@
-package org.apache.lucene.search;
-
-/**
- * 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.IndexReader;
-import org.apache.lucene.index.Term;
-import org.apache.lucene.index.TermDocs;
-import org.apache.lucene.index.TermEnum;
-import org.apache.lucene.search.ExtendedFieldCache.LongParser;
-
-import java.io.IOException;
-import java.util.Locale;
-import java.util.Map;
-import java.util.WeakHashMap;
-import java.util.HashMap;
-
-/**
- * Expert: The default cache implementation, storing all values in memory.
- * A WeakHashMap is used for storage.
- *
- * Created: May 19, 2004 4:40:36 PM - * - * @author Tim Jones (Nacimiento Software) - * @since lucene 1.4 - * @version $Id$ - */ -class FieldCacheImpl -implements FieldCache { - - /** Expert: Internal cache. */ - abstract static class Cache { - private final Map readerCache = new WeakHashMap(); - - protected abstract Object createValue(IndexReader reader, Object key) - throws IOException; - - public Object get(IndexReader reader, Object key) throws IOException { - Map innerCache; - Object value; - synchronized (readerCache) { - innerCache = (Map) readerCache.get(reader); - if (innerCache == null) { - innerCache = new HashMap(); - readerCache.put(reader, innerCache); - value = null; - } else { - value = innerCache.get(key); - } - if (value == null) { - value = new CreationPlaceholder(); - innerCache.put(key, value); - } - } - if (value instanceof CreationPlaceholder) { - synchronized (value) { - CreationPlaceholder progress = (CreationPlaceholder) value; - if (progress.value == null) { - progress.value = createValue(reader, key); - synchronized (readerCache) { - innerCache.put(key, progress.value); - } - } - return progress.value; - } - } - return value; - } - } - - static final class CreationPlaceholder { - Object value; - } - - /** Expert: Every composite-key in the internal cache is of this type. */ - static class Entry { - final String field; // which Fieldable - final int type; // which SortField type - final Object custom; // which custom comparator - final Locale locale; // the locale we're sorting (if string) - - /** Creates one of these objects. */ - Entry (String field, int type, Locale locale) { - this.field = field.intern(); - this.type = type; - this.custom = null; - this.locale = locale; - } - - /** Creates one of these objects for a custom comparator. */ - Entry (String field, Object custom) { - this.field = field.intern(); - this.type = SortField.CUSTOM; - this.custom = custom; - this.locale = null; - } - - /** Two of these are equal iff they reference the same field and type. */ - public boolean equals (Object o) { - if (o instanceof Entry) { - Entry other = (Entry) o; - if (other.field == field && other.type == type) { - if (other.locale == null ? locale == null : other.locale.equals(locale)) { - if (other.custom == null) { - if (custom == null) return true; - } else if (other.custom.equals (custom)) { - return true; - } - } - } - } - return false; - } - - /** Composes a hashcode based on the field and type. */ - public int hashCode() { - return field.hashCode() ^ type ^ (custom==null ? 0 : custom.hashCode()) ^ (locale==null ? 0 : locale.hashCode()); - } - } - - private static final ByteParser BYTE_PARSER = new ByteParser() { - public byte parseByte(String value) { - return Byte.parseByte(value); - } - }; - - private static final ShortParser SHORT_PARSER = new ShortParser() { - public short parseShort(String value) { - return Short.parseShort(value); - } - }; - - private static final IntParser INT_PARSER = new IntParser() { - public int parseInt(String value) { - return Integer.parseInt(value); - } - }; - - private static final LongParser LONG_PARSER = new LongParser() { - public long parseLong(String value) { - return Long.parseLong(value); - } - }; - - private static final FloatParser FLOAT_PARSER = new FloatParser() { - public float parseFloat(String value) { - return Float.parseFloat(value); - } - }; - - // inherit javadocs - public byte[] getBytes (IndexReader reader, String field) throws IOException { - return getBytes(reader, field, BYTE_PARSER); - } - - // inherit javadocs - public byte[] getBytes(IndexReader reader, String field, ByteParser parser) - throws IOException { - return (byte[]) bytesCache.get(reader, new Entry(field, parser)); - } - - Cache bytesCache = new Cache() { - - protected Object createValue(IndexReader reader, Object entryKey) - throws IOException { - Entry entry = (Entry) entryKey; - String field = entry.field; - ByteParser parser = (ByteParser) entry.custom; - final byte[] retArray = new byte[reader.maxDoc()]; - TermDocs termDocs = reader.termDocs(); - TermEnum termEnum = reader.terms (new Term (field, "")); - try { - do { - Term term = termEnum.term(); - if (term==null || term.field() != field) break; - byte termval = parser.parseByte(term.text()); - termDocs.seek (termEnum); - while (termDocs.next()) { - retArray[termDocs.doc()] = termval; - } - } while (termEnum.next()); - } finally { - termDocs.close(); - termEnum.close(); - } - return retArray; - } - }; - - // inherit javadocs - public short[] getShorts (IndexReader reader, String field) throws IOException { - return getShorts(reader, field, SHORT_PARSER); - } - - // inherit javadocs - public short[] getShorts(IndexReader reader, String field, ShortParser parser) - throws IOException { - return (short[]) shortsCache.get(reader, new Entry(field, parser)); - } - - Cache shortsCache = new Cache() { - - protected Object createValue(IndexReader reader, Object entryKey) - throws IOException { - Entry entry = (Entry) entryKey; - String field = entry.field; - ShortParser parser = (ShortParser) entry.custom; - final short[] retArray = new short[reader.maxDoc()]; - TermDocs termDocs = reader.termDocs(); - TermEnum termEnum = reader.terms (new Term (field, "")); - try { - do { - Term term = termEnum.term(); - if (term==null || term.field() != field) break; - short termval = parser.parseShort(term.text()); - termDocs.seek (termEnum); - while (termDocs.next()) { - retArray[termDocs.doc()] = termval; - } - } while (termEnum.next()); - } finally { - termDocs.close(); - termEnum.close(); - } - return retArray; - } - }; - - // inherit javadocs - public int[] getInts (IndexReader reader, String field) throws IOException { - return getInts(reader, field, INT_PARSER); - } - - // inherit javadocs - public int[] getInts(IndexReader reader, String field, IntParser parser) - throws IOException { - return (int[]) intsCache.get(reader, new Entry(field, parser)); - } - - Cache intsCache = new Cache() { - - protected Object createValue(IndexReader reader, Object entryKey) - throws IOException { - Entry entry = (Entry) entryKey; - String field = entry.field; - IntParser parser = (IntParser) entry.custom; - final int[] retArray = new int[reader.maxDoc()]; - TermDocs termDocs = reader.termDocs(); - TermEnum termEnum = reader.terms (new Term (field, "")); - try { - do { - Term term = termEnum.term(); - if (term==null || term.field() != field) break; - int termval = parser.parseInt(term.text()); - termDocs.seek (termEnum); - while (termDocs.next()) { - retArray[termDocs.doc()] = termval; - } - } while (termEnum.next()); - } finally { - termDocs.close(); - termEnum.close(); - } - return retArray; - } - }; - - // inherit javadocs - public long[] getLongs (IndexReader reader, String field) throws IOException { - return getLongs(reader, field, LONG_PARSER); - } - - // inherit javadocs - public long[] getLongs(IndexReader reader, String field, LongParser parser) - throws IOException { - return (long[]) longsCache.get(reader, new Entry(field, parser)); - } - - Cache longsCache = new Cache() { - - protected Object createValue(IndexReader reader, Object entryKey) - throws IOException { - Entry entry = (Entry) entryKey; - String field = entry.field; - LongParser parser = (LongParser) entry.custom; - final long[] retArray = new long[reader.maxDoc()]; - TermDocs termDocs = reader.termDocs(); - TermEnum termEnum = reader.terms (new Term (field, "")); - try { - do { - Term term = termEnum.term(); - if (term==null || term.field() != field) break; - long termval = parser.parseLong(term.text()); - termDocs.seek (termEnum); - while (termDocs.next()) { - retArray[termDocs.doc()] = termval; - } - } while (termEnum.next()); - } finally { - termDocs.close(); - termEnum.close(); - } - return retArray; - } - }; - - // inherit javadocs - public float[] getFloats (IndexReader reader, String field) - throws IOException { - return getFloats(reader, field, FLOAT_PARSER); - } - - // inherit javadocs - public float[] getFloats(IndexReader reader, String field, FloatParser parser) - throws IOException { - return (float[]) floatsCache.get(reader, new Entry(field, parser)); - } - - Cache floatsCache = new Cache() { - - protected Object createValue(IndexReader reader, Object entryKey) - throws IOException { - Entry entry = (Entry) entryKey; - String field = entry.field; - FloatParser parser = (FloatParser) entry.custom; - final float[] retArray = new float[reader.maxDoc()]; - TermDocs termDocs = reader.termDocs(); - TermEnum termEnum = reader.terms (new Term (field, "")); - try { - do { - Term term = termEnum.term(); - if (term==null || term.field() != field) break; - float termval = parser.parseFloat(term.text()); - termDocs.seek (termEnum); - while (termDocs.next()) { - retArray[termDocs.doc()] = termval; - } - } while (termEnum.next()); - } finally { - termDocs.close(); - termEnum.close(); - } - return retArray; - } - }; - - // inherit javadocs - public String[] getStrings(IndexReader reader, String field) - throws IOException { - return (String[]) stringsCache.get(reader, field); - } - - Cache stringsCache = new Cache() { - - protected Object createValue(IndexReader reader, Object fieldKey) - throws IOException { - String field = ((String) fieldKey).intern(); - final String[] retArray = new String[reader.maxDoc()]; - TermDocs termDocs = reader.termDocs(); - TermEnum termEnum = reader.terms (new Term (field, "")); - try { - do { - Term term = termEnum.term(); - if (term==null || term.field() != field) break; - String termval = term.text(); - termDocs.seek (termEnum); - while (termDocs.next()) { - retArray[termDocs.doc()] = termval; - } - } while (termEnum.next()); - } finally { - termDocs.close(); - termEnum.close(); - } - return retArray; - } - }; - - // inherit javadocs - public StringIndex getStringIndex(IndexReader reader, String field) - throws IOException { - return (StringIndex) stringsIndexCache.get(reader, field); - } - - Cache stringsIndexCache = new Cache() { - - protected Object createValue(IndexReader reader, Object fieldKey) - throws IOException { - String field = ((String) fieldKey).intern(); - final int[] retArray = new int[reader.maxDoc()]; - String[] mterms = new String[reader.maxDoc()+1]; - TermDocs termDocs = reader.termDocs(); - TermEnum termEnum = reader.terms (new Term (field, "")); - int t = 0; // current term number - - // an entry for documents that have no terms in this field - // should a document with no terms be at top or bottom? - // this puts them at the top - if it is changed, FieldDocSortedHitQueue - // needs to change as well. - mterms[t++] = null; - - try { - do { - Term term = termEnum.term(); - if (term==null || term.field() != field) break; - - // store term text - // we expect that there is at most one term per document - if (t >= mterms.length) throw new RuntimeException ("there are more terms than " + - "documents in field \"" + field + "\", but it's impossible to sort on " + - "tokenized fields"); - mterms[t] = term.text(); - - termDocs.seek (termEnum); - while (termDocs.next()) { - retArray[termDocs.doc()] = t; - } - - t++; - } while (termEnum.next()); - } finally { - termDocs.close(); - termEnum.close(); - } - - if (t == 0) { - // if there are no terms, make the term array - // have a single null entry - mterms = new String[1]; - } else if (t < mterms.length) { - // if there are less terms than documents, - // trim off the dead array space - String[] terms = new String[t]; - System.arraycopy (mterms, 0, terms, 0, t); - mterms = terms; - } - - StringIndex value = new StringIndex (retArray, mterms); - return value; - } - }; - - /** The pattern used to detect integer values in a field */ - /** removed for java 1.3 compatibility - protected static final Pattern pIntegers = Pattern.compile ("[0-9\\-]+"); - **/ - - /** The pattern used to detect float values in a field */ - /** - * removed for java 1.3 compatibility - * protected static final Object pFloats = Pattern.compile ("[0-9+\\-\\.eEfFdD]+"); - */ - - // inherit javadocs - public Object getAuto(IndexReader reader, String field) throws IOException { - return autoCache.get(reader, field); - } - - Cache autoCache = new Cache() { - - protected Object createValue(IndexReader reader, Object fieldKey) - throws IOException { - String field = ((String)fieldKey).intern(); - TermEnum enumerator = reader.terms (new Term (field, "")); - try { - Term term = enumerator.term(); - if (term == null) { - throw new RuntimeException ("no terms in field " + field + " - cannot determine sort type"); - } - Object ret = null; - if (term.field() == field) { - String termtext = term.text().trim(); - - /** - * Java 1.4 level code: - - if (pIntegers.matcher(termtext).matches()) - return IntegerSortedHitQueue.comparator (reader, enumerator, field); - - else if (pFloats.matcher(termtext).matches()) - return FloatSortedHitQueue.comparator (reader, enumerator, field); - */ - - // Java 1.3 level code: - try { - Integer.parseInt (termtext); - ret = getInts (reader, field); - } catch (NumberFormatException nfe1) { - try { - Long.parseLong(termtext); - ret = getLongs (reader, field); - } catch (NumberFormatException nfe2) { - try { - Float.parseFloat (termtext); - ret = getFloats (reader, field); - } catch (NumberFormatException nfe3) { - ret = getStringIndex (reader, field); - } - } - } - } else { - throw new RuntimeException ("field \"" + field + "\" does not appear to be indexed"); - } - return ret; - } finally { - enumerator.close(); - } - } - }; - - // inherit javadocs - public Comparable[] getCustom(IndexReader reader, String field, - SortComparator comparator) throws IOException { - return (Comparable[]) customCache.get(reader, new Entry(field, comparator)); - } - - Cache customCache = new Cache() { - - protected Object createValue(IndexReader reader, Object entryKey) - throws IOException { - Entry entry = (Entry) entryKey; - String field = entry.field; - SortComparator comparator = (SortComparator) entry.custom; - final Comparable[] retArray = new Comparable[reader.maxDoc()]; - TermDocs termDocs = reader.termDocs(); - TermEnum termEnum = reader.terms (new Term (field, "")); - try { - do { - Term term = termEnum.term(); - if (term==null || term.field() != field) break; - Comparable termval = comparator.getComparable (term.text()); - termDocs.seek (termEnum); - while (termDocs.next()) { - retArray[termDocs.doc()] = termval; - } - } while (termEnum.next()); - } finally { - termDocs.close(); - termEnum.close(); - } - return retArray; - } - }; - -} -