Expert: change the value of this field. This can - * be used during indexing to re-use a single Field - * instance to improve indexing speed by avoiding GC cost - * of new'ing and reclaiming Field instances. Typically - * a single {@link Document} instance is re-used as - * well. This helps most on small documents.
- * - *Each Field instance should only be used once - * within a single {@link Document} instance. See ImproveIndexingSpeed - * for details.
*/ - public void setValue(String value) { - if (isBinary) { - throw new IllegalArgumentException("cannot set a String value on a binary field"); - } - fieldsData = value; - } - - /** Expert: change the value of this field. See setValue(String). */ - public void setValue(Reader value) { - if (isBinary) { - throw new IllegalArgumentException("cannot set a Reader value on a binary field"); - } - if (isStored) { - throw new IllegalArgumentException("cannot set a Reader value on a stored field"); - } - fieldsData = value; - } - - /** Expert: change the value of this field. See setValue(String). */ - public void setValue(byte[] value) { - if (!isBinary) { - throw new IllegalArgumentException("cannot set a byte[] value on a non-binary field"); - } - fieldsData = value; - binaryLength = value.length; - binaryOffset = 0; - } - - /** Expert: change the value of this field. See setValue(String). */ - public void setValue(byte[] value, int offset, int length) { - if (!isBinary) { - throw new IllegalArgumentException("cannot set a byte[] value on a non-binary field"); - } - fieldsData = value; - binaryLength = length; - binaryOffset = offset; - } - - /** Expert: sets the token stream to be used for indexing and causes isIndexed() and isTokenized() to return true. - * May be combined with stored values from stringValue() or getBinaryValue() */ - public void setTokenStream(TokenStream tokenStream) { - this.isIndexed = true; - this.isTokenized = true; - this.tokenStream = tokenStream; - } - /** * Create a field by specifying its name, value and how it will * be saved in the index. Term vectors will not be stored in the index. - * + * * @param name The name of the field * @param value The string to process * @param store Whethervalue should be stored in the index
* @param index Whether the field should be indexed, and if so, if it should
- * be tokenized before indexing
+ * be tokenized before indexing
* @throws NullPointerException if name or value is null
- * @throws IllegalArgumentException if the field is neither stored nor indexed
+ * @throws IllegalArgumentException if the field is neither stored nor indexed
*/
public Field(String name, String value, Store store, Index index) {
this(name, value, store, index, TermVector.NO);
}
-
+
/**
* Create a field by specifying its name, value and how it will
* be saved in the index.
- *
+ *
* @param name The name of the field
* @param value The string to process
* @param store Whether value should be stored in the index
* @param index Whether the field should be indexed, and if so, if it should
- * be tokenized before indexing
+ * be tokenized before indexing
* @param termVector Whether term vector should be stored
* @throws NullPointerException if name or value is null
* @throws IllegalArgumentException in any of the following situations:
- * TermVector.YESvalue should be stored in the index
* @param index Whether the field should be indexed, and if so, if it should
- * be tokenized before indexing
+ * be tokenized before indexing
* @param termVector Whether term vector should be stored
* @throws NullPointerException if name or value is null
* @throws IllegalArgumentException in any of the following situations:
- * TermVector.YESnull
@@ -439,32 +472,32 @@
}
/**
- * Create a tokenized and indexed field that is not stored, optionally with
+ * Create a tokenized and indexed field that is not stored, optionally with
* storing term vectors. The Reader is read only when the Document is added to the index,
* i.e. you may not close the Reader until {@link IndexWriter#addDocument(Document)}
* has been called.
- *
+ *
* @param name The name of the field
* @param reader The reader with the content
* @param termVector Whether term vector should be stored
* @throws NullPointerException if name or reader is null
- */
+ */
public Field(String name, Reader reader, TermVector termVector) {
- if (name == null)
+ if (name == null) {
throw new NullPointerException("name cannot be null");
- if (reader == null)
+ }
+ if (reader == null) {
throw new NullPointerException("reader cannot be null");
+ }
-
+
- this.name = StringHelper.intern(name); // field names are interned
+ this.name = StringHelper.intern(name); // field names are interned
this.fieldsData = reader;
-
+
this.isStored = false;
-
this.isIndexed = true;
this.isTokenized = true;
-
this.isBinary = false;
-
+
setStoreTermVector(termVector);
}
@@ -474,55 +507,55 @@
* The TokenStream is read only when the Document is added to the index,
* i.e. you may not close the TokenStream until {@link IndexWriter#addDocument(Document)}
* has been called.
- *
+ *
* @param name The name of the field
* @param tokenStream The TokenStream with the content
* @throws NullPointerException if name or tokenStream is null
- */
+ */
public Field(String name, TokenStream tokenStream) {
this(name, tokenStream, TermVector.NO);
}
-
+
/**
- * Create a tokenized and indexed field that is not stored, optionally with
+ * Create a tokenized and indexed field that is not stored, optionally with
* storing term vectors. This is useful for pre-analyzed fields.
* The TokenStream is read only when the Document is added to the index,
* i.e. you may not close the TokenStream until {@link IndexWriter#addDocument(Document)}
* has been called.
- *
+ *
* @param name The name of the field
* @param tokenStream The TokenStream with the content
* @param termVector Whether term vector should be stored
* @throws NullPointerException if name or tokenStream is null
- */
+ */
public Field(String name, TokenStream tokenStream, TermVector termVector) {
- if (name == null)
+ if (name == null) {
throw new NullPointerException("name cannot be null");
- if (tokenStream == null)
+ }
+ if (tokenStream == null) {
throw new NullPointerException("tokenStream cannot be null");
+ }
-
+
- this.name = StringHelper.intern(name); // field names are interned
+ this.name = StringHelper.intern(name); // field names are interned
this.fieldsData = null;
this.tokenStream = tokenStream;
this.isStored = false;
-
this.isIndexed = true;
this.isTokenized = true;
-
this.isBinary = false;
-
+
setStoreTermVector(termVector);
}
-
+
/**
* Create a stored field with binary value. Optionally the value may be compressed.
- *
+ *
* @param name The name of the field
* @param value The binary value
* @param store Must be Store.YES
- * @throws IllegalArgumentException if store is Store.NO
+ * @throws IllegalArgumentException if store is Store.NO
* @deprecated Use {@link #Field(String, byte[]) instead}
*/
@Deprecated
@@ -536,7 +569,7 @@
/**
* Create a stored field with binary value. Optionally the value may be compressed.
- *
+ *
* @param name The name of the field
* @param value The binary value
*/
@@ -546,13 +579,13 @@
/**
* Create a stored field with binary value. Optionally the value may be compressed.
- *
+ *
* @param name The name of the field
* @param value The binary value
* @param offset Starting offset in value where this Field's bytes are
* @param length Number of bytes to use for this Field, starting at offset
* @param store How value should be stored (compressed or not)
- * @throws IllegalArgumentException if store is Store.NO
+ * @throws IllegalArgumentException if store is Store.NO
* @deprecated Use {@link #Field(String, byte[], int, int) instead}
*/
@Deprecated
@@ -566,32 +599,349 @@
/**
* Create a stored field with binary value. Optionally the value may be compressed.
- *
+ *
* @param name The name of the field
* @param value The binary value
* @param offset Starting offset in value where this Field's bytes are
* @param length Number of bytes to use for this Field, starting at offset
*/
public Field(String name, byte[] value, int offset, int length) {
-
- if (name == null)
+ if (name == null) {
throw new IllegalArgumentException("name cannot be null");
- if (value == null)
- throw new IllegalArgumentException("value cannot be null");
+ }
-
+
- this.name = StringHelper.intern(name); // field names are interned
+ this.name = StringHelper.intern(name); // field names are interned
+ this.fieldsData = value;
+
+ this.isStored = true;
+ this.isIndexed = false;
+ this.isTokenized = false;
+ this.omitTermFreqAndPositions = false;
+ this.omitNorms = true;
+
+ this.isBinary = true;
+ this.binaryLength = length;
+ this.binaryOffset = offset;
+
+ setStoreTermVector(TermVector.NO);
+ }
+
+ /**
+ * The value of the field as a String, or null. If null, the Reader value or
+ * binary value is used. Exactly one of stringValue(),
+ * readerValue(), and getBinaryValue() must be set.
+ */
+ public String stringValue() {
+ return fieldsData instanceof String ? (String)fieldsData : null;
+ }
+
+ /**
+ * The value of the field as a Reader, or null. If null, the String value or
+ * binary value is used. Exactly one of stringValue(),
+ * readerValue(), and getBinaryValue() must be set.
+ */
+ public Reader readerValue() {
+ return fieldsData instanceof Reader ? (Reader)fieldsData : null;
+ }
+
+ /**
+ * The TokesStream for this field to be used when indexing, or null. If null, the Reader value
+ * or String value is analyzed to produce the indexed tokens.
+ */
+ public TokenStream tokenStreamValue() {
+ return tokenStream;
+ }
+
+ /**
+ * Expert: change the value of this field. This can + * be used during indexing to re-use a single Field + * instance to improve indexing speed by avoiding GC cost + * of new'ing and reclaiming Field instances. Typically + * a single {@link Document} instance is re-used as + * well. This helps most on small documents.
+ * + *Each Field instance should only be used once + * within a single {@link Document} instance. See ImproveIndexingSpeed + * for details.
+ * + * @param value New value for the Field + */ + public void setValue(String value) { + if (isBinary) { + throw new IllegalArgumentException("cannot set a String value on a binary field"); + } fieldsData = value; + } - + - isStored = true; - isIndexed = false; - isTokenized = false; - omitTermFreqAndPositions = false; - omitNorms = true; + /** + * Expert: change the value of this field. See setValue(String). + * + * @param value New Reader value for the Field + */ + public void setValue(Reader value) { + if (isBinary) { + throw new IllegalArgumentException("cannot set a Reader value on a binary field"); + } + if (isStored) { + throw new IllegalArgumentException("cannot set a Reader value on a stored field"); + } + fieldsData = value; + } - + - isBinary = true; + /** + * Expert: change the value of this field. See setValue(String). + * + * @param value New value for the field + */ + public void setValue(byte[] value) { + if (!isBinary) { + throw new IllegalArgumentException("cannot set a byte[] value on a non-binary field"); + } + fieldsData = value; + binaryLength = value.length; + binaryOffset = 0; + } + + /** + * Expert: change the value of this field. See setValue(String). + * + * @param value byte array to take the new value from + * @param offset Offset in the array that the new value begins at + * @param length Length in the array that the new value is + */ + public void setValue(byte[] value, int offset, int length) { + if (!isBinary) { + throw new IllegalArgumentException("cannot set a byte[] value on a non-binary field"); + } + fieldsData = value; binaryLength = length; binaryOffset = offset; + } - + - setStoreTermVector(TermVector.NO); + /** + * Expert: sets the token stream to be used for indexing and causes isIndexed() and isTokenized() to return true. + * May be combined with stored values from stringValue() or getBinaryValue() + * + * @param tokenStream New TokenStream for the field + */ + public void setTokenStream(TokenStream tokenStream) { + this.isIndexed = true; + this.isTokenized = true; + this.tokenStream = tokenStream; } + + /** + * Sets the term vector related properties to the values defined in the given TermVector + * + * @param termVector TermVector representation of term vector configuration + */ + protected void setStoreTermVector(Field.TermVector termVector) { + this.storeTermVector = termVector.isStored(); + this.storePositionWithTermVector = termVector.withPositions(); + this.storeOffsetWithTermVector = termVector.withOffsets(); -} + } + + /** + * {@inheritDoc} + */ + public void setBoost(float boost) { + this.boost = boost; + } + + /** + * {@inheritDoc} + */ + public float getBoost() { + return boost; + } + + /** + * {@inheritDoc} + */ + public String name() { + return name; + } + + /** + * {@inheritDoc} + */ + public final boolean isStored() { + return isStored; + } + + /** + * {@inheritDoc} + */ + public final boolean isIndexed() { + return isIndexed; + } + + /** + * {@inheritDoc} + */ + public final boolean isTokenized() { + return isTokenized; + } + + /** + * {@inheritDoc} + */ + public final boolean isTermVectorStored() { + return storeTermVector; + } + + /** + * {@inheritDoc} + */ + public boolean isStoreOffsetWithTermVector() { + return storeOffsetWithTermVector; + } + + /** + * {@inheritDoc} + */ + public boolean isStorePositionWithTermVector() { + return storePositionWithTermVector; + } + + /** + * {@inheritDoc} + */ + public boolean isBinary() { + return isBinary; + } + + /** + * {@inheritDoc} + */ + public boolean getOmitNorms() { + return omitNorms; + } + + /** + * {@inheritDoc} + */ + public void setOmitNorms(boolean omitNorms) { + this.omitNorms = omitNorms; + } + + /** + * {@inheritDoc} + */ + public boolean isLazy() { + return lazy; + } + + /** + * {@inheritDoc} + */ + public int getBinaryOffset() { + return binaryOffset; + } + + /** + * {@inheritDoc} + */ + public int getBinaryLength() { + if (isBinary) { + return binaryLength; + } + if (fieldsData instanceof byte[]) { + return ((byte[]) fieldsData).length; + } + return 0; + } + + /** + * {@inheritDoc} + */ + public byte[] getBinaryValue() { + return getBinaryValue(null); + } + + /** + * {@inheritDoc} + */ + public byte[] getBinaryValue(byte[] result) { + return isBinary || fieldsData instanceof byte[] ? (byte[]) fieldsData : null; + } + + /** + * {@inheritDoc} + */ + public boolean getOmitTermFreqAndPositions() { + return omitTermFreqAndPositions; + } + + /** + * {@inheritDoc} + */ + public void setOmitTermFreqAndPositions(boolean omitTermFreqAndPositions) { + this.omitTermFreqAndPositions = omitTermFreqAndPositions; + } + + /** + * Prints a Field for human consumption. + */ + @Override + public final String toString() { + StringBuilder result = new StringBuilder(); + if (isStored) { + result.append("stored"); + } + if (isIndexed) { + if (result.length() > 0) { + result.append(","); + } + result.append("indexed"); + } + if (isTokenized) { + if (result.length() > 0) { + result.append(","); + } + result.append("tokenized"); + } + if (storeTermVector) { + if (result.length() > 0) { + result.append(","); + } + result.append("termVector"); + } + if (storeOffsetWithTermVector) { + if (result.length() > 0) { + result.append(","); + } + result.append("termVectorOffsets"); + } + if (storePositionWithTermVector) { + if (result.length() > 0) { + result.append(","); + } + result.append("termVectorPosition"); + } + if (isBinary) { + if (result.length() > 0) { + result.append(","); + } + result.append("binary"); + } + if (omitNorms) { + result.append(",omitNorms"); + } + if (omitTermFreqAndPositions) { + result.append(",omitTermFreqAndPositions"); + } + if (lazy) { + result.append(",lazy"); + } + result.append('<').append(name).append(':'); + + if (fieldsData != null && !lazy) { + result.append(fieldsData); + } + + result.append('>'); + return result.toString(); + } +} Index: src/java/org/apache/lucene/index/CheckIndex.java =================================================================== --- src/java/org/apache/lucene/index/CheckIndex.java (revision 917019) +++ src/java/org/apache/lucene/index/CheckIndex.java Sat Mar 13 20:32:42 CET 2010 @@ -20,7 +20,7 @@ import org.apache.lucene.store.FSDirectory; import org.apache.lucene.store.Directory; import org.apache.lucene.store.IndexInput; -import org.apache.lucene.document.AbstractField; // for javadocs +import org.apache.lucene.document.Field; // for javadocs import org.apache.lucene.document.Document; import java.text.NumberFormat; @@ -166,7 +166,7 @@ /** True if at least one of the fields in this segment * does not omitTermFreqAndPositions. - * @see AbstractField#setOmitTermFreqAndPositions */ + * @see Field#setOmitTermFreqAndPositions */ public boolean hasProx; /** Map that includes certain Index: src/java/org/apache/lucene/document/NumericField.java =================================================================== --- src/java/org/apache/lucene/document/NumericField.java (revision 917019) +++ src/java/org/apache/lucene/document/NumericField.java Sat Mar 13 20:01:01 CET 2010 @@ -138,10 +138,8 @@ * * @since 2.9 */ -public final class NumericField extends AbstractField { +public final class NumericField extends Field { - private final NumericTokenStream numericTS; - /** * Creates a field for numeric values using the defaultprecisionStep
* {@link NumericUtils#PRECISION_STEP_DEFAULT} (4). The instance is not yet initialized with
@@ -193,16 +191,11 @@
* @param index if the field should be indexed using {@link NumericTokenStream}
*/
public NumericField(String name, int precisionStep, Field.Store store, boolean index) {
- super(name, store, index ? Field.Index.ANALYZED_NO_NORMS : Field.Index.NO, Field.TermVector.NO);
+ super(name, null, store, index ? Field.Index.ANALYZED_NO_NORMS : Field.Index.NO, Field.TermVector.NO);
setOmitTermFreqAndPositions(true);
- numericTS = new NumericTokenStream(precisionStep);
+ tokenStream = new NumericTokenStream(precisionStep);
}
-
+
- /** Returns a {@link NumericTokenStream} for indexing the numeric value. */
- public TokenStream tokenStreamValue() {
- return isIndexed() ? numericTS : null;
- }
-
/** Returns always null for numeric fields */
@Override
public byte[] getBinaryValue(byte[] result){
@@ -231,7 +224,7 @@
* document.add(new NumericField(name, precisionStep).setLongValue(value))
*/
public NumericField setLongValue(final long value) {
- numericTS.setLongValue(value);
+ ((NumericTokenStream) tokenStream).setLongValue(value);
fieldsData = Long.valueOf(value);
return this;
}
@@ -243,7 +236,7 @@
* document.add(new NumericField(name, precisionStep).setIntValue(value))
*/
public NumericField setIntValue(final int value) {
- numericTS.setIntValue(value);
+ ((NumericTokenStream) tokenStream).setIntValue(value);
fieldsData = Integer.valueOf(value);
return this;
}
@@ -255,7 +248,7 @@
* document.add(new NumericField(name, precisionStep).setDoubleValue(value))
*/
public NumericField setDoubleValue(final double value) {
- numericTS.setDoubleValue(value);
+ ((NumericTokenStream) tokenStream).setDoubleValue(value);
fieldsData = Double.valueOf(value);
return this;
}
@@ -267,9 +260,48 @@
* document.add(new NumericField(name, precisionStep).setFloatValue(value))
*/
public NumericField setFloatValue(final float value) {
- numericTS.setFloatValue(value);
+ ((NumericTokenStream) tokenStream).setFloatValue(value);
fieldsData = Float.valueOf(value);
return this;
}
+ /**
+ * An unsupported operation for NumericFields
+ */
+ @Override
+ public void setTokenStream(TokenStream tokenStream) {
+ throw new UnsupportedOperationException("Cannot set new TokenStreams in NumericFields");
-}
+ }
+
+ /**
+ * An unsupported operation for NumericFields
+ */
+ @Override
+ public void setValue(String value) {
+ throw new UnsupportedOperationException("Cannot set String values in NumericFields");
+ }
+
+ /**
+ * An unsupported operation for NumericFields
+ */
+ @Override
+ public void setValue(Reader value) {
+ throw new UnsupportedOperationException("Cannot set value through Readers in NumericFields");
+ }
+
+ /**
+ * An unsupported operation for NumericFields
+ */
+ @Override
+ public void setValue(byte[] value) {
+ throw new UnsupportedOperationException("Cannot set byte[] values in NumericFields");
+ }
+
+ /**
+ * An unsupported operation for NumericFields
+ */
+ @Override
+ public void setValue(byte[] value, int offset, int length) {
+ throw new UnsupportedOperationException("Cannot set byte[] values in NumericFields");
+ }
+}
Index: src/java/org/apache/lucene/document/AbstractField.java
===================================================================
--- src/java/org/apache/lucene/document/AbstractField.java (revision 917019)
+++ src/java/org/apache/lucene/document/AbstractField.java Sat Mar 13 20:27:07 CET 2010
@@ -24,8 +24,11 @@
/**
*
- *
+ * @deprecated The functionality of this class has been moved to {@link Field}
+ * therefore subclasses should extend {@link Field}. This class
+ * will be removed in a future version.
**/
+@Deprecated
public abstract class AbstractField implements Fieldable {
protected String name = "body";
@@ -122,16 +125,16 @@
/** True iff the value of the field is to be stored in the index for return
with search hits. It is an error for this to be true if a field is
Reader-valued. */
- public final boolean isStored() { return isStored; }
+ public boolean isStored() { return isStored; }
/** True iff the value of the field is to be indexed, so that it may be
searched on. */
- public final boolean isIndexed() { return isIndexed; }
+ public boolean isIndexed() { return isIndexed; }
/** True iff the value of the field should be tokenized as text prior to
indexing. Un-tokenized fields are indexed as a single word and may not be
Reader-valued. */
- public final boolean isTokenized() { return isTokenized; }
+ public boolean isTokenized() { return isTokenized; }
/** True iff the term or terms used to index this field are stored as a term
* vector, available from {@link org.apache.lucene.index.IndexReader#getTermFreqVector(int,String)}.
@@ -141,7 +144,7 @@
*
* @see org.apache.lucene.index.IndexReader#getTermFreqVector(int, String)
*/
- public final boolean isTermVectorStored() { return storeTermVector; }
+ public boolean isTermVectorStored() { return storeTermVector; }
/**
* True iff terms are stored as term vector together with their offsets
@@ -159,7 +162,7 @@
}
/** True iff the value of the filed is stored as binary */
- public final boolean isBinary() {
+ public boolean isBinary() {
return isBinary;
}
@@ -237,7 +240,7 @@
/** Prints a Field for human consumption. */
@Override
- public final String toString() {
+ public String toString() {
StringBuilder result = new StringBuilder();
if (isStored) {
result.append("stored");