You are viewing a plain text version of this content. The canonical link for it is here.
Posted to java-commits@lucene.apache.org by bu...@apache.org on 2009/07/24 23:45:50 UTC
svn commit: r797665 [2/3] - in /lucene/java/trunk: ./
src/java/org/apache/lucene/analysis/
src/java/org/apache/lucene/analysis/standard/
src/java/org/apache/lucene/analysis/tokenattributes/
src/java/org/apache/lucene/index/ src/java/org/apache/lucene/q...
Modified: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/OffsetAttribute.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/OffsetAttribute.java?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/OffsetAttribute.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/OffsetAttribute.java Fri Jul 24 21:45:48 2009
@@ -17,8 +17,6 @@
* limitations under the License.
*/
-import java.io.Serializable;
-
import org.apache.lucene.util.Attribute;
/**
@@ -29,67 +27,23 @@
* The APIs introduced in these classes with Lucene 2.9 might change in the future.
* We will make our best efforts to keep the APIs backwards-compatible.</font>
*/
-public class OffsetAttribute extends Attribute implements Cloneable, Serializable {
- private int startOffset;
- private int endOffset;
-
+public interface OffsetAttribute extends Attribute {
/** Returns this Token's starting offset, the position of the first character
corresponding to this token in the source text.
Note that the difference between endOffset() and startOffset() may not be
equal to termText.length(), as the term text may have been altered by a
stemmer or some other filter. */
- public int startOffset() {
- return startOffset;
- }
+ public int startOffset();
/** Set the starting and ending offset.
@see #startOffset() and #endOffset()*/
- public void setOffset(int startOffset, int endOffset) {
- this.startOffset = startOffset;
- this.endOffset = endOffset;
- }
+ public void setOffset(int startOffset, int endOffset);
/** Returns this Token's ending offset, one greater than the position of the
last character corresponding to this token in the source text. The length
of the token in the source text is (endOffset - startOffset). */
- public int endOffset() {
- return endOffset;
- }
-
-
- public void clear() {
- startOffset = 0;
- endOffset = 0;
- }
-
- public String toString() {
- return "start=" + startOffset + ",end=" + endOffset;
- }
-
- public boolean equals(Object other) {
- if (other == this) {
- return true;
- }
-
- if (other instanceof OffsetAttribute) {
- OffsetAttribute o = (OffsetAttribute) other;
- return o.startOffset == startOffset && o.endOffset == endOffset;
- }
-
- return false;
- }
-
- public int hashCode() {
- int code = startOffset;
- code = code * 31 + endOffset;
- return code;
- }
-
- public void copyTo(Attribute target) {
- OffsetAttribute t = (OffsetAttribute) target;
- t.setOffset(startOffset, endOffset);
- }
+ public int endOffset();
}
Added: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/OffsetAttributeImpl.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/OffsetAttributeImpl.java?rev=797665&view=auto
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/OffsetAttributeImpl.java (added)
+++ lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/OffsetAttributeImpl.java Fri Jul 24 21:45:48 2009
@@ -0,0 +1,91 @@
+package org.apache.lucene.analysis.tokenattributes;
+
+/**
+ * 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 org.apache.lucene.util.AttributeImpl;
+
+/**
+ * The start and end character offset of a Token.
+ *
+ * <p><font color="#FF0000">
+ * WARNING: The status of the new TokenStream, AttributeSource and Attributes is experimental.
+ * The APIs introduced in these classes with Lucene 2.9 might change in the future.
+ * We will make our best efforts to keep the APIs backwards-compatible.</font>
+ */
+public class OffsetAttributeImpl extends AttributeImpl implements OffsetAttribute, Cloneable, Serializable {
+ private int startOffset;
+ private int endOffset;
+
+ /** Returns this Token's starting offset, the position of the first character
+ corresponding to this token in the source text.
+
+ Note that the difference between endOffset() and startOffset() may not be
+ equal to termText.length(), as the term text may have been altered by a
+ stemmer or some other filter. */
+ public int startOffset() {
+ return startOffset;
+ }
+
+
+ /** Set the starting and ending offset.
+ @see #startOffset() and #endOffset()*/
+ public void setOffset(int startOffset, int endOffset) {
+ this.startOffset = startOffset;
+ this.endOffset = endOffset;
+ }
+
+
+ /** Returns this Token's ending offset, one greater than the position of the
+ last character corresponding to this token in the source text. The length
+ of the token in the source text is (endOffset - startOffset). */
+ public int endOffset() {
+ return endOffset;
+ }
+
+
+ public void clear() {
+ startOffset = 0;
+ endOffset = 0;
+ }
+
+ public boolean equals(Object other) {
+ if (other == this) {
+ return true;
+ }
+
+ if (other instanceof OffsetAttributeImpl) {
+ OffsetAttributeImpl o = (OffsetAttributeImpl) other;
+ return o.startOffset == startOffset && o.endOffset == endOffset;
+ }
+
+ return false;
+ }
+
+ public int hashCode() {
+ int code = startOffset;
+ code = code * 31 + endOffset;
+ return code;
+ }
+
+ public void copyTo(AttributeImpl target) {
+ OffsetAttribute t = (OffsetAttribute) target;
+ t.setOffset(startOffset, endOffset);
+ }
+}
Propchange: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/OffsetAttributeImpl.java
------------------------------------------------------------------------------
svn:eol-style = native
Modified: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PayloadAttribute.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PayloadAttribute.java?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PayloadAttribute.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PayloadAttribute.java Fri Jul 24 21:45:48 2009
@@ -17,8 +17,6 @@
* limitations under the License.
*/
-import java.io.Serializable;
-
import org.apache.lucene.index.Payload;
import org.apache.lucene.util.Attribute;
@@ -30,80 +28,14 @@
* The APIs introduced in these classes with Lucene 2.9 might change in the future.
* We will make our best efforts to keep the APIs backwards-compatible.</font>
*/
-public class PayloadAttribute extends Attribute implements Cloneable, Serializable {
- private Payload payload;
-
- /**
- * Initialize this attribute with no payload.
- */
- public PayloadAttribute() {}
-
- /**
- * Initialize this attribute with the given payload.
- */
- public PayloadAttribute(Payload payload) {
- this.payload = payload;
- }
-
+public interface PayloadAttribute extends Attribute {
/**
* Returns this Token's payload.
*/
- public Payload getPayload() {
- return this.payload;
- }
+ public Payload getPayload();
/**
* Sets this Token's payload.
*/
- public void setPayload(Payload payload) {
- this.payload = payload;
- }
-
- public void clear() {
- payload = null;
- }
-
- public String toString() {
- if (payload == null) {
- return "payload=null";
- }
-
- return "payload=" + payload.toString();
- }
-
- public Object clone() {
- PayloadAttribute clone = (PayloadAttribute) super.clone();
- if (payload != null) {
- clone.payload = (Payload) payload.clone();
- }
- return clone;
- }
-
- public boolean equals(Object other) {
- if (other == this) {
- return true;
- }
-
- if (other instanceof PayloadAttribute) {
- PayloadAttribute o = (PayloadAttribute) other;
- if (o.payload == null || payload == null) {
- return o.payload == null && payload == null;
- }
-
- return o.payload.equals(payload);
- }
-
- return false;
- }
-
- public int hashCode() {
- return (payload == null) ? 0 : payload.hashCode();
- }
-
- public void copyTo(Attribute target) {
- PayloadAttribute t = (PayloadAttribute) target;
- t.setPayload((payload == null) ? null : (Payload) payload.clone());
- }
-
-
+ public void setPayload(Payload payload);
}
Added: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PayloadAttributeImpl.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PayloadAttributeImpl.java?rev=797665&view=auto
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PayloadAttributeImpl.java (added)
+++ lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PayloadAttributeImpl.java Fri Jul 24 21:45:48 2009
@@ -0,0 +1,101 @@
+package org.apache.lucene.analysis.tokenattributes;
+
+/**
+ * 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 org.apache.lucene.index.Payload;
+import org.apache.lucene.util.AttributeImpl;
+
+/**
+ * The payload of a Token. See also {@link Payload}.
+ *
+ * <p><font color="#FF0000">
+ * WARNING: The status of the new TokenStream, AttributeSource and Attributes is experimental.
+ * The APIs introduced in these classes with Lucene 2.9 might change in the future.
+ * We will make our best efforts to keep the APIs backwards-compatible.</font>
+ */
+public class PayloadAttributeImpl extends AttributeImpl implements PayloadAttribute, Cloneable, Serializable {
+ private Payload payload;
+
+ /**
+ * Initialize this attribute with no payload.
+ */
+ public PayloadAttributeImpl() {}
+
+ /**
+ * Initialize this attribute with the given payload.
+ */
+ public PayloadAttributeImpl(Payload payload) {
+ this.payload = payload;
+ }
+
+ /**
+ * Returns this Token's payload.
+ */
+ public Payload getPayload() {
+ return this.payload;
+ }
+
+ /**
+ * Sets this Token's payload.
+ */
+ public void setPayload(Payload payload) {
+ this.payload = payload;
+ }
+
+ public void clear() {
+ payload = null;
+ }
+
+ public Object clone() {
+ PayloadAttributeImpl clone = (PayloadAttributeImpl) super.clone();
+ if (payload != null) {
+ clone.payload = (Payload) payload.clone();
+ }
+ return clone;
+ }
+
+ public boolean equals(Object other) {
+ if (other == this) {
+ return true;
+ }
+
+ if (other instanceof PayloadAttribute) {
+ PayloadAttributeImpl o = (PayloadAttributeImpl) other;
+ if (o.payload == null || payload == null) {
+ return o.payload == null && payload == null;
+ }
+
+ return o.payload.equals(payload);
+ }
+
+ return false;
+ }
+
+ public int hashCode() {
+ return (payload == null) ? 0 : payload.hashCode();
+ }
+
+ public void copyTo(AttributeImpl target) {
+ PayloadAttribute t = (PayloadAttribute) target;
+ t.setPayload((payload == null) ? null : (Payload) payload.clone());
+ }
+
+
+}
Propchange: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PayloadAttributeImpl.java
------------------------------------------------------------------------------
svn:eol-style = native
Modified: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PositionIncrementAttribute.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PositionIncrementAttribute.java?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PositionIncrementAttribute.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PositionIncrementAttribute.java Fri Jul 24 21:45:48 2009
@@ -17,13 +17,10 @@
* limitations under the License.
*/
-import java.io.Serializable;
-
-import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.util.Attribute;
/** The positionIncrement determines the position of this token
- * relative to the previous Token in a {@link TokenStream}, used in phrase
+ * relative to the previous Token in a TokenStream, used in phrase
* searching.
*
* <p>The default value is one.
@@ -53,54 +50,15 @@
*
* @see org.apache.lucene.index.TermPositions
*/
-public class PositionIncrementAttribute extends Attribute implements Cloneable, Serializable {
- private int positionIncrement = 1;
-
+public interface PositionIncrementAttribute extends Attribute {
/** Set the position increment. The default value is one.
*
* @param positionIncrement the distance from the prior term
*/
- public void setPositionIncrement(int positionIncrement) {
- if (positionIncrement < 0)
- throw new IllegalArgumentException
- ("Increment must be zero or greater: " + positionIncrement);
- this.positionIncrement = positionIncrement;
- }
+ public void setPositionIncrement(int positionIncrement);
/** Returns the position increment of this Token.
* @see #setPositionIncrement
*/
- public int getPositionIncrement() {
- return positionIncrement;
- }
-
- public void clear() {
- this.positionIncrement = 1;
- }
-
- public String toString() {
- return "positionIncrement=" + positionIncrement;
- }
-
- public boolean equals(Object other) {
- if (other == this) {
- return true;
- }
-
- if (other instanceof PositionIncrementAttribute) {
- return positionIncrement == ((PositionIncrementAttribute) other).positionIncrement;
- }
-
- return false;
- }
-
- public int hashCode() {
- return positionIncrement;
- }
-
- public void copyTo(Attribute target) {
- PositionIncrementAttribute t = (PositionIncrementAttribute) target;
- t.setPositionIncrement(positionIncrement);
- }
-
+ public int getPositionIncrement();
}
Added: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PositionIncrementAttributeImpl.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PositionIncrementAttributeImpl.java?rev=797665&view=auto
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PositionIncrementAttributeImpl.java (added)
+++ lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PositionIncrementAttributeImpl.java Fri Jul 24 21:45:48 2009
@@ -0,0 +1,102 @@
+package org.apache.lucene.analysis.tokenattributes;
+
+/**
+ * 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 org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.util.AttributeImpl;
+
+/** The positionIncrement determines the position of this token
+ * relative to the previous Token in a {@link TokenStream}, used in phrase
+ * searching.
+ *
+ * <p>The default value is one.
+ *
+ * <p>Some common uses for this are:<ul>
+ *
+ * <li>Set it to zero to put multiple terms in the same position. This is
+ * useful if, e.g., a word has multiple stems. Searches for phrases
+ * including either stem will match. In this case, all but the first stem's
+ * increment should be set to zero: the increment of the first instance
+ * should be one. Repeating a token with an increment of zero can also be
+ * used to boost the scores of matches on that token.
+ *
+ * <li>Set it to values greater than one to inhibit exact phrase matches.
+ * If, for example, one does not want phrases to match across removed stop
+ * words, then one could build a stop word filter that removes stop words and
+ * also sets the increment to the number of stop words removed before each
+ * non-stop word. Then exact phrase queries will only match when the terms
+ * occur with no intervening stop words.
+ *
+ * </ul>
+ *
+ * <p><font color="#FF0000">
+ * WARNING: The status of the new TokenStream, AttributeSource and Attributes is experimental.
+ * The APIs introduced in these classes with Lucene 2.9 might change in the future.
+ * We will make our best efforts to keep the APIs backwards-compatible.</font>
+ *
+ * @see org.apache.lucene.index.TermPositions
+ */
+public class PositionIncrementAttributeImpl extends AttributeImpl implements PositionIncrementAttribute, Cloneable, Serializable {
+ private int positionIncrement = 1;
+
+ /** Set the position increment. The default value is one.
+ *
+ * @param positionIncrement the distance from the prior term
+ */
+ public void setPositionIncrement(int positionIncrement) {
+ if (positionIncrement < 0)
+ throw new IllegalArgumentException
+ ("Increment must be zero or greater: " + positionIncrement);
+ this.positionIncrement = positionIncrement;
+ }
+
+ /** Returns the position increment of this Token.
+ * @see #setPositionIncrement
+ */
+ public int getPositionIncrement() {
+ return positionIncrement;
+ }
+
+ public void clear() {
+ this.positionIncrement = 1;
+ }
+
+ public boolean equals(Object other) {
+ if (other == this) {
+ return true;
+ }
+
+ if (other instanceof PositionIncrementAttributeImpl) {
+ return positionIncrement == ((PositionIncrementAttributeImpl) other).positionIncrement;
+ }
+
+ return false;
+ }
+
+ public int hashCode() {
+ return positionIncrement;
+ }
+
+ public void copyTo(AttributeImpl target) {
+ PositionIncrementAttribute t = (PositionIncrementAttribute) target;
+ t.setPositionIncrement(positionIncrement);
+ }
+
+}
Propchange: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/PositionIncrementAttributeImpl.java
------------------------------------------------------------------------------
svn:eol-style = native
Modified: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TermAttribute.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TermAttribute.java?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TermAttribute.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TermAttribute.java Fri Jul 24 21:45:48 2009
@@ -17,9 +17,6 @@
* limitations under the License.
*/
-import java.io.Serializable;
-
-import org.apache.lucene.util.ArrayUtil;
import org.apache.lucene.util.Attribute;
/**
@@ -30,12 +27,7 @@
* The APIs introduced in these classes with Lucene 2.9 might change in the future.
* We will make our best efforts to keep the APIs backwards-compatible.</font>
*/
-public class TermAttribute extends Attribute implements Cloneable, Serializable {
- private static int MIN_BUFFER_SIZE = 10;
-
- private char[] termBuffer;
- private int termLength;
-
+public interface TermAttribute extends Attribute {
/** Returns the Token's term text.
*
* This method has a performance penalty
@@ -45,38 +37,20 @@
* String, use this method, which is nothing more than
* a convenience call to <b>new String(token.termBuffer(), 0, token.termLength())</b>
*/
- public String term() {
- initTermBuffer();
- return new String(termBuffer, 0, termLength);
- }
-
+ public String term();
+
/** Copies the contents of buffer, starting at offset for
* length characters, into the termBuffer array.
* @param buffer the buffer to copy
* @param offset the index in the buffer of the first character to copy
* @param length the number of characters to copy
*/
- public void setTermBuffer(char[] buffer, int offset, int length) {
- char[] newCharBuffer = growTermBuffer(length);
- if (newCharBuffer != null) {
- termBuffer = newCharBuffer;
- }
- System.arraycopy(buffer, offset, termBuffer, 0, length);
- termLength = length;
- }
+ public void setTermBuffer(char[] buffer, int offset, int length);
/** Copies the contents of buffer into the termBuffer array.
* @param buffer the buffer to copy
*/
- public void setTermBuffer(String buffer) {
- int length = buffer.length();
- char[] newCharBuffer = growTermBuffer(length);
- if (newCharBuffer != null) {
- termBuffer = newCharBuffer;
- }
- buffer.getChars(0, length, termBuffer, 0);
- termLength = length;
- }
+ public void setTermBuffer(String buffer);
/** Copies the contents of buffer, starting at offset and continuing
* for length characters, into the termBuffer array.
@@ -84,17 +58,8 @@
* @param offset the index in the buffer of the first character to copy
* @param length the number of characters to copy
*/
- public void setTermBuffer(String buffer, int offset, int length) {
- assert offset <= buffer.length();
- assert offset + length <= buffer.length();
- char[] newCharBuffer = growTermBuffer(length);
- if (newCharBuffer != null) {
- termBuffer = newCharBuffer;
- }
- buffer.getChars(offset, offset + length, termBuffer, 0);
- termLength = length;
- }
-
+ public void setTermBuffer(String buffer, int offset, int length);
+
/** Returns the internal termBuffer character array which
* you can then directly alter. If the array is too
* small for your token, use {@link
@@ -102,10 +67,7 @@
* altering the buffer be sure to call {@link
* #setTermLength} to record the number of valid
* characters that were placed into the termBuffer. */
- public char[] termBuffer() {
- initTermBuffer();
- return termBuffer;
- }
+ public char[] termBuffer();
/** Grows the termBuffer to at least size newSize, preserving the
* existing content. Note: If the next operation is to change
@@ -117,63 +79,12 @@
* @param newSize minimum size of the new termBuffer
* @return newly created termBuffer with length >= newSize
*/
- public char[] resizeTermBuffer(int newSize) {
- char[] newCharBuffer = growTermBuffer(newSize);
- if (termBuffer == null) {
- // If there were termText, then preserve it.
- // note that if termBuffer is null then newCharBuffer cannot be null
- assert newCharBuffer != null;
- termBuffer = newCharBuffer;
- } else if (newCharBuffer != null) {
- // Note: if newCharBuffer != null then termBuffer needs to grow.
- // If there were a termBuffer, then preserve it
- System.arraycopy(termBuffer, 0, newCharBuffer, 0, termBuffer.length);
- termBuffer = newCharBuffer;
- }
- return termBuffer;
- }
-
- /** Allocates a buffer char[] of at least newSize
- * @param newSize minimum size of the buffer
- * @return newly created buffer with length >= newSize or null if the current termBuffer is big enough
- */
- private char[] growTermBuffer(int newSize) {
- if (termBuffer != null) {
- if (termBuffer.length >= newSize)
- // Already big enough
- return null;
- else
- // Not big enough; create a new array with slight
- // over allocation:
- return new char[ArrayUtil.getNextSize(newSize)];
- } else {
-
- // determine the best size
- // The buffer is always at least MIN_BUFFER_SIZE
- if (newSize < MIN_BUFFER_SIZE) {
- newSize = MIN_BUFFER_SIZE;
- }
-
- return new char[newSize];
- }
- }
-
- // TODO: once we remove the deprecated termText() method
- // and switch entirely to char[] termBuffer we don't need
- // to use this method anymore
- private void initTermBuffer() {
- if (termBuffer == null) {
- termBuffer = new char[MIN_BUFFER_SIZE];
- termLength = 0;
- }
- }
+ public char[] resizeTermBuffer(int newSize);
/** Return number of valid characters (length of the term)
* in the termBuffer array. */
- public int termLength() {
- return termLength;
- }
-
+ public int termLength();
+
/** Set number of valid characters (length of the term) in
* the termBuffer array. Use this to truncate the termBuffer
* or to synchronize with external manipulation of the termBuffer.
@@ -181,61 +92,5 @@
* use {@link #resizeTermBuffer(int)} first.
* @param length the truncated length
*/
- public void setTermLength(int length) {
- initTermBuffer();
- if (length > termBuffer.length)
- throw new IllegalArgumentException("length " + length + " exceeds the size of the termBuffer (" + termBuffer.length + ")");
- termLength = length;
- }
-
- public int hashCode() {
- initTermBuffer();
- int code = termLength;
- code = code * 31 + ArrayUtil.hashCode(termBuffer, 0, termLength);
- return code;
- }
-
- public void clear() {
- termLength = 0;
- }
-
- public Object clone() {
- TermAttribute t = (TermAttribute)super.clone();
- // Do a deep clone
- if (termBuffer != null) {
- t.termBuffer = (char[]) termBuffer.clone();
- }
- return t;
- }
-
- public boolean equals(Object other) {
- if (other == this) {
- return true;
- }
-
- if (other instanceof TermAttribute) {
- initTermBuffer();
- TermAttribute o = ((TermAttribute) other);
- o.initTermBuffer();
-
- for(int i=0;i<termLength;i++) {
- if (termBuffer[i] != o.termBuffer[i]) {
- return false;
- }
- }
- return true;
- }
-
- return false;
- }
-
- public String toString() {
- initTermBuffer();
- return "term=" + new String(termBuffer, 0, termLength);
- }
-
- public void copyTo(Attribute target) {
- TermAttribute t = (TermAttribute) target;
- t.setTermBuffer(termBuffer, 0, termLength);
- }
+ public void setTermLength(int length);
}
Added: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TermAttributeImpl.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TermAttributeImpl.java?rev=797665&view=auto
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TermAttributeImpl.java (added)
+++ lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TermAttributeImpl.java Fri Jul 24 21:45:48 2009
@@ -0,0 +1,241 @@
+package org.apache.lucene.analysis.tokenattributes;
+
+/**
+ * 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 org.apache.lucene.util.ArrayUtil;
+import org.apache.lucene.util.AttributeImpl;
+
+/**
+ * The term text of a Token.
+ *
+ * <p><font color="#FF0000">
+ * WARNING: The status of the new TokenStream, AttributeSource and Attributes is experimental.
+ * The APIs introduced in these classes with Lucene 2.9 might change in the future.
+ * We will make our best efforts to keep the APIs backwards-compatible.</font>
+ */
+public class TermAttributeImpl extends AttributeImpl implements TermAttribute, Cloneable, Serializable {
+ private static int MIN_BUFFER_SIZE = 10;
+
+ private char[] termBuffer;
+ private int termLength;
+
+ /** Returns the Token's term text.
+ *
+ * This method has a performance penalty
+ * because the text is stored internally in a char[]. If
+ * possible, use {@link #termBuffer()} and {@link
+ * #termLength()} directly instead. If you really need a
+ * String, use this method, which is nothing more than
+ * a convenience call to <b>new String(token.termBuffer(), 0, token.termLength())</b>
+ */
+ public String term() {
+ initTermBuffer();
+ return new String(termBuffer, 0, termLength);
+ }
+
+ /** Copies the contents of buffer, starting at offset for
+ * length characters, into the termBuffer array.
+ * @param buffer the buffer to copy
+ * @param offset the index in the buffer of the first character to copy
+ * @param length the number of characters to copy
+ */
+ public void setTermBuffer(char[] buffer, int offset, int length) {
+ char[] newCharBuffer = growTermBuffer(length);
+ if (newCharBuffer != null) {
+ termBuffer = newCharBuffer;
+ }
+ System.arraycopy(buffer, offset, termBuffer, 0, length);
+ termLength = length;
+ }
+
+ /** Copies the contents of buffer into the termBuffer array.
+ * @param buffer the buffer to copy
+ */
+ public void setTermBuffer(String buffer) {
+ int length = buffer.length();
+ char[] newCharBuffer = growTermBuffer(length);
+ if (newCharBuffer != null) {
+ termBuffer = newCharBuffer;
+ }
+ buffer.getChars(0, length, termBuffer, 0);
+ termLength = length;
+ }
+
+ /** Copies the contents of buffer, starting at offset and continuing
+ * for length characters, into the termBuffer array.
+ * @param buffer the buffer to copy
+ * @param offset the index in the buffer of the first character to copy
+ * @param length the number of characters to copy
+ */
+ public void setTermBuffer(String buffer, int offset, int length) {
+ assert offset <= buffer.length();
+ assert offset + length <= buffer.length();
+ char[] newCharBuffer = growTermBuffer(length);
+ if (newCharBuffer != null) {
+ termBuffer = newCharBuffer;
+ }
+ buffer.getChars(offset, offset + length, termBuffer, 0);
+ termLength = length;
+ }
+
+ /** Returns the internal termBuffer character array which
+ * you can then directly alter. If the array is too
+ * small for your token, use {@link
+ * #resizeTermBuffer(int)} to increase it. After
+ * altering the buffer be sure to call {@link
+ * #setTermLength} to record the number of valid
+ * characters that were placed into the termBuffer. */
+ public char[] termBuffer() {
+ initTermBuffer();
+ return termBuffer;
+ }
+
+ /** Grows the termBuffer to at least size newSize, preserving the
+ * existing content. Note: If the next operation is to change
+ * the contents of the term buffer use
+ * {@link #setTermBuffer(char[], int, int)},
+ * {@link #setTermBuffer(String)}, or
+ * {@link #setTermBuffer(String, int, int)}
+ * to optimally combine the resize with the setting of the termBuffer.
+ * @param newSize minimum size of the new termBuffer
+ * @return newly created termBuffer with length >= newSize
+ */
+ public char[] resizeTermBuffer(int newSize) {
+ char[] newCharBuffer = growTermBuffer(newSize);
+ if (termBuffer == null) {
+ // If there were termText, then preserve it.
+ // note that if termBuffer is null then newCharBuffer cannot be null
+ assert newCharBuffer != null;
+ termBuffer = newCharBuffer;
+ } else if (newCharBuffer != null) {
+ // Note: if newCharBuffer != null then termBuffer needs to grow.
+ // If there were a termBuffer, then preserve it
+ System.arraycopy(termBuffer, 0, newCharBuffer, 0, termBuffer.length);
+ termBuffer = newCharBuffer;
+ }
+ return termBuffer;
+ }
+
+ /** Allocates a buffer char[] of at least newSize
+ * @param newSize minimum size of the buffer
+ * @return newly created buffer with length >= newSize or null if the current termBuffer is big enough
+ */
+ private char[] growTermBuffer(int newSize) {
+ if (termBuffer != null) {
+ if (termBuffer.length >= newSize)
+ // Already big enough
+ return null;
+ else
+ // Not big enough; create a new array with slight
+ // over allocation:
+ return new char[ArrayUtil.getNextSize(newSize)];
+ } else {
+
+ // determine the best size
+ // The buffer is always at least MIN_BUFFER_SIZE
+ if (newSize < MIN_BUFFER_SIZE) {
+ newSize = MIN_BUFFER_SIZE;
+ }
+
+ return new char[newSize];
+ }
+ }
+
+ // TODO: once we remove the deprecated termText() method
+ // and switch entirely to char[] termBuffer we don't need
+ // to use this method anymore
+ private void initTermBuffer() {
+ if (termBuffer == null) {
+ termBuffer = new char[MIN_BUFFER_SIZE];
+ termLength = 0;
+ }
+ }
+
+ /** Return number of valid characters (length of the term)
+ * in the termBuffer array. */
+ public int termLength() {
+ return termLength;
+ }
+
+ /** Set number of valid characters (length of the term) in
+ * the termBuffer array. Use this to truncate the termBuffer
+ * or to synchronize with external manipulation of the termBuffer.
+ * Note: to grow the size of the array,
+ * use {@link #resizeTermBuffer(int)} first.
+ * @param length the truncated length
+ */
+ public void setTermLength(int length) {
+ initTermBuffer();
+ if (length > termBuffer.length)
+ throw new IllegalArgumentException("length " + length + " exceeds the size of the termBuffer (" + termBuffer.length + ")");
+ termLength = length;
+ }
+
+ public int hashCode() {
+ initTermBuffer();
+ int code = termLength;
+ code = code * 31 + ArrayUtil.hashCode(termBuffer, 0, termLength);
+ return code;
+ }
+
+ public void clear() {
+ termLength = 0;
+ }
+
+ public Object clone() {
+ TermAttributeImpl t = (TermAttributeImpl)super.clone();
+ // Do a deep clone
+ if (termBuffer != null) {
+ t.termBuffer = (char[]) termBuffer.clone();
+ }
+ return t;
+ }
+
+ public boolean equals(Object other) {
+ if (other == this) {
+ return true;
+ }
+
+ if (other instanceof TermAttribute) {
+ initTermBuffer();
+ TermAttributeImpl o = ((TermAttributeImpl) other);
+ o.initTermBuffer();
+
+ for(int i=0;i<termLength;i++) {
+ if (termBuffer[i] != o.termBuffer[i]) {
+ return false;
+ }
+ }
+ return true;
+ }
+
+ return false;
+ }
+
+ public String toString() {
+ initTermBuffer();
+ return "term=" + new String(termBuffer, 0, termLength);
+ }
+
+ public void copyTo(AttributeImpl target) {
+ TermAttribute t = (TermAttribute) target;
+ t.setTermBuffer(termBuffer, 0, termLength);
+ }
+}
Propchange: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TermAttributeImpl.java
------------------------------------------------------------------------------
svn:eol-style = native
Modified: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TypeAttribute.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TypeAttribute.java?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TypeAttribute.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TypeAttribute.java Fri Jul 24 21:45:48 2009
@@ -17,8 +17,6 @@
* limitations under the License.
*/
-import java.io.Serializable;
-
import org.apache.lucene.util.Attribute;
/**
@@ -29,55 +27,11 @@
* The APIs introduced in these classes with Lucene 2.9 might change in the future.
* We will make our best efforts to keep the APIs backwards-compatible.</font>
*/
-public class TypeAttribute extends Attribute implements Cloneable, Serializable {
- private String type;
- public static final String DEFAULT_TYPE = "word";
-
- public TypeAttribute() {
- this(DEFAULT_TYPE);
- }
-
- public TypeAttribute(String type) {
- this.type = type;
- }
-
+public interface TypeAttribute extends Attribute {
/** Returns this Token's lexical type. Defaults to "word". */
- public String type() {
- return type;
- }
+ public String type();
/** Set the lexical type.
@see #type() */
- public void setType(String type) {
- this.type = type;
- }
-
- public void clear() {
- type = DEFAULT_TYPE;
- }
-
- public String toString() {
- return "type=" + type;
- }
-
- public boolean equals(Object other) {
- if (other == this) {
- return true;
- }
-
- if (other instanceof TypeAttribute) {
- return type.equals(((TypeAttribute) other).type);
- }
-
- return false;
- }
-
- public int hashCode() {
- return type.hashCode();
- }
-
- public void copyTo(Attribute target) {
- TypeAttribute t = (TypeAttribute) target;
- t.setType(new String(type));
- }
+ public void setType(String type);
}
Added: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TypeAttributeImpl.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TypeAttributeImpl.java?rev=797665&view=auto
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TypeAttributeImpl.java (added)
+++ lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TypeAttributeImpl.java Fri Jul 24 21:45:48 2009
@@ -0,0 +1,79 @@
+package org.apache.lucene.analysis.tokenattributes;
+
+/**
+ * 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 org.apache.lucene.util.AttributeImpl;
+
+/**
+ * A Token's lexical type. The Default value is "word".
+ *
+ * <p><font color="#FF0000">
+ * WARNING: The status of the new TokenStream, AttributeSource and Attributes is experimental.
+ * The APIs introduced in these classes with Lucene 2.9 might change in the future.
+ * We will make our best efforts to keep the APIs backwards-compatible.</font>
+ */
+public class TypeAttributeImpl extends AttributeImpl implements TypeAttribute, Cloneable, Serializable {
+ private String type;
+ public static final String DEFAULT_TYPE = "word";
+
+ public TypeAttributeImpl() {
+ this(DEFAULT_TYPE);
+ }
+
+ public TypeAttributeImpl(String type) {
+ this.type = type;
+ }
+
+ /** Returns this Token's lexical type. Defaults to "word". */
+ public String type() {
+ return type;
+ }
+
+ /** Set the lexical type.
+ @see #type() */
+ public void setType(String type) {
+ this.type = type;
+ }
+
+ public void clear() {
+ type = DEFAULT_TYPE;
+ }
+
+ public boolean equals(Object other) {
+ if (other == this) {
+ return true;
+ }
+
+ if (other instanceof TypeAttributeImpl) {
+ return type.equals(((TypeAttributeImpl) other).type);
+ }
+
+ return false;
+ }
+
+ public int hashCode() {
+ return type.hashCode();
+ }
+
+ public void copyTo(AttributeImpl target) {
+ TypeAttribute t = (TypeAttribute) target;
+ t.setType(new String(type));
+ }
+}
Propchange: lucene/java/trunk/src/java/org/apache/lucene/analysis/tokenattributes/TypeAttributeImpl.java
------------------------------------------------------------------------------
svn:eol-style = native
Modified: lucene/java/trunk/src/java/org/apache/lucene/index/DocInverterPerField.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/index/DocInverterPerField.java?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/index/DocInverterPerField.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/index/DocInverterPerField.java Fri Jul 24 21:45:48 2009
@@ -20,7 +20,6 @@
import java.io.IOException;
import java.io.Reader;
import org.apache.lucene.document.Fieldable;
-import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
@@ -83,7 +82,6 @@
final int valueLength = stringValue.length();
perThread.singleTokenTokenStream.reinit(stringValue, 0, valueLength);
fieldState.attributeSource = perThread.singleTokenTokenStream;
- perThread.localTokenStream.reset();
consumer.start(field);
boolean success = false;
@@ -132,21 +130,15 @@
try {
int offsetEnd = fieldState.offset-1;
- boolean useNewTokenStreamAPI = stream.useNewAPI();
- Token localToken = null;
-
- if (useNewTokenStreamAPI) {
- fieldState.attributeSource = stream;
- } else {
- fieldState.attributeSource = perThread.localTokenStream;
- localToken = perThread.localToken;
- }
-
- consumer.start(field);
+ boolean hasMoreTokens = stream.incrementToken();
+
+ fieldState.attributeSource = stream;
OffsetAttribute offsetAttribute = (OffsetAttribute) fieldState.attributeSource.addAttribute(OffsetAttribute.class);
PositionIncrementAttribute posIncrAttribute = (PositionIncrementAttribute) fieldState.attributeSource.addAttribute(PositionIncrementAttribute.class);
+ consumer.start(field);
+
for(;;) {
// If we hit an exception in stream.next below
@@ -155,14 +147,8 @@
// non-aborting and (above) this one document
// will be marked as deleted, but still
// consume a docID
- Token token = null;
- if (useNewTokenStreamAPI) {
- if (!stream.incrementToken()) break;
- } else {
- token = stream.next(localToken);
- if (token == null) break;
- perThread.localTokenStream.set(token);
- }
+
+ if (!hasMoreTokens) break;
final int posIncr = posIncrAttribute.getPositionIncrement();
fieldState.position += posIncr;
@@ -194,6 +180,8 @@
docState.infoStream.println("maxFieldLength " +maxFieldLength+ " reached for field " + fieldInfo.name + ", ignoring following tokens");
break;
}
+
+ hasMoreTokens = stream.incrementToken();
}
fieldState.offset = offsetEnd+1;
} finally {
Modified: lucene/java/trunk/src/java/org/apache/lucene/index/DocInverterPerThread.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/index/DocInverterPerThread.java?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/index/DocInverterPerThread.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/index/DocInverterPerThread.java Fri Jul 24 21:45:48 2009
@@ -19,15 +19,9 @@
import java.io.IOException;
-import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.tokenattributes.FlagsAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
-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.util.Attribute;
/** This is a DocFieldConsumer that inverts each field,
* separately, from a Document, and accepts a
@@ -37,10 +31,8 @@
final DocInverter docInverter;
final InvertedDocConsumerPerThread consumer;
final InvertedDocEndConsumerPerThread endConsumer;
- final Token localToken = new Token();
//TODO: change to SingleTokenTokenStream after Token was removed
final SingleTokenTokenStream singleTokenTokenStream = new SingleTokenTokenStream();
- final BackwardsCompatibilityStream localTokenStream = new BackwardsCompatibilityStream();
static class SingleTokenTokenStream extends TokenStream {
TermAttribute termAttribute;
@@ -55,75 +47,12 @@
termAttribute.setTermBuffer(stringValue);
offsetAttribute.setOffset(startOffset, endOffset);
}
- }
-
- /** This stream wrapper is only used to maintain backwards compatibility with the
- * old TokenStream API and can be removed in Lucene 3.0
- * @deprecated
- */
- static class BackwardsCompatibilityStream extends TokenStream {
- private Token token;
-
- TermAttribute termAttribute = new TermAttribute() {
- public String term() {
- return token.term();
- }
-
- public char[] termBuffer() {
- return token.termBuffer();
- }
-
- public int termLength() {
- return token.termLength();
- }
- };
- OffsetAttribute offsetAttribute = new OffsetAttribute() {
- public int startOffset() {
- return token.startOffset();
- }
-
- public int endOffset() {
- return token.endOffset();
- }
- };
-
- PositionIncrementAttribute positionIncrementAttribute = new PositionIncrementAttribute() {
- public int getPositionIncrement() {
- return token.getPositionIncrement();
- }
- };
-
- FlagsAttribute flagsAttribute = new FlagsAttribute() {
- public int getFlags() {
- return token.getFlags();
- }
- };
- PayloadAttribute payloadAttribute = new PayloadAttribute() {
- public Payload getPayload() {
- return token.getPayload();
- }
- };
-
- TypeAttribute typeAttribute = new TypeAttribute() {
- public String type() {
- return token.type();
- }
- };
-
- BackwardsCompatibilityStream() {
- attributes.put(TermAttribute.class, termAttribute);
- attributes.put(OffsetAttribute.class, offsetAttribute);
- attributes.put(PositionIncrementAttribute.class, positionIncrementAttribute);
- attributes.put(FlagsAttribute.class, flagsAttribute);
- attributes.put(PayloadAttribute.class, payloadAttribute);
- attributes.put(TypeAttribute.class, typeAttribute);
+ // this is a dummy, to not throw an UOE because this class does not implement any iteration method
+ public boolean incrementToken() {
+ throw new UnsupportedOperationException();
}
-
- public void set(Token token) {
- this.token = token;
- }
- };
+ }
final DocumentsWriter.DocState docState;
Modified: lucene/java/trunk/src/java/org/apache/lucene/queryParser/QueryParser.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/queryParser/QueryParser.java?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/queryParser/QueryParser.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/queryParser/QueryParser.java Fri Jul 24 21:45:48 2009
@@ -531,66 +531,41 @@
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
+ 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 (success) {
- if (buffer.hasAttribute(TermAttribute.class)) {
- termAtt = (TermAttribute) buffer.getAttribute(TermAttribute.class);
- }
- if (buffer.hasAttribute(PositionIncrementAttribute.class)) {
- posIncrAtt = (PositionIncrementAttribute) buffer.getAttribute(PositionIncrementAttribute.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;
- }
+ boolean hasMoreTokens = false;
+ if (termAtt != null) {
+ try {
+ hasMoreTokens = buffer.incrementToken();
+ while (hasMoreTokens) {
+ numTokens++;
+ int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() : 1;
+ if (positionIncrement != 0) {
+ positionCount += positionIncrement;
+ } else {
+ severalTokensAtSamePosition = true;
}
- } catch (IOException e) {
- // ignore
+ hasMoreTokens = buffer.incrementToken();
}
- }
- } 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;
+ } catch (IOException e) {
+ // ignore
}
}
try {
@@ -609,16 +584,9 @@
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();
- }
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ term = termAtt.term();
} catch (IOException e) {
// safe to ignore, because we know the number of tokens
}
@@ -631,15 +599,9 @@
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();
- }
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ term = termAtt.term();
} catch (IOException e) {
// safe to ignore, because we know the number of tokens
}
@@ -660,18 +622,11 @@
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();
+ 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
@@ -707,19 +662,11 @@
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();
+ 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
@@ -1625,12 +1572,6 @@
finally { jj_save(0, xla); }
}
- private boolean jj_3R_3() {
- if (jj_scan_token(STAR)) return true;
- if (jj_scan_token(COLON)) return true;
- return false;
- }
-
private boolean jj_3R_2() {
if (jj_scan_token(TERM)) return true;
if (jj_scan_token(COLON)) return true;
@@ -1647,6 +1588,12 @@
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. */
Modified: lucene/java/trunk/src/java/org/apache/lucene/queryParser/QueryParser.jj
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/queryParser/QueryParser.jj?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/queryParser/QueryParser.jj (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/queryParser/QueryParser.jj Fri Jul 24 21:45:48 2009
@@ -555,67 +555,42 @@
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
+ 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 (success) {
- if (buffer.hasAttribute(TermAttribute.class)) {
- termAtt = (TermAttribute) buffer.getAttribute(TermAttribute.class);
- }
- if (buffer.hasAttribute(PositionIncrementAttribute.class)) {
- posIncrAtt = (PositionIncrementAttribute) buffer.getAttribute(PositionIncrementAttribute.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;
- }
+ boolean hasMoreTokens = false;
+ if (termAtt != null) {
+ try {
+ hasMoreTokens = buffer.incrementToken();
+ while (hasMoreTokens) {
+ numTokens++;
+ int positionIncrement = (posIncrAtt != null) ? posIncrAtt.getPositionIncrement() : 1;
+ if (positionIncrement != 0) {
+ positionCount += positionIncrement;
+ } else {
+ severalTokensAtSamePosition = true;
}
- } catch (IOException e) {
- // ignore
+ hasMoreTokens = buffer.incrementToken();
}
+ } 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
@@ -627,22 +602,15 @@
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();
- }
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ term = termAtt.term();
} catch (IOException e) {
// safe to ignore, because we know the number of tokens
}
@@ -655,19 +623,13 @@
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();
- }
+ boolean hasNext = buffer.incrementToken();
+ assert hasNext == true;
+ term = termAtt.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);
@@ -684,18 +646,11 @@
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();
+ 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
@@ -724,26 +679,18 @@
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();
+ 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
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/QueryTermVector.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/QueryTermVector.java?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/QueryTermVector.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/QueryTermVector.java Fri Jul 24 21:45:48 2009
@@ -27,7 +27,6 @@
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.tokenattributes.TermAttribute;
import org.apache.lucene.index.TermFreqVector;
@@ -59,17 +58,15 @@
{
List terms = new ArrayList();
try {
- if (stream.useNewAPI()) {
- stream.reset();
- TermAttribute termAtt = (TermAttribute) stream.getAttribute(TermAttribute.class);
- while (stream.incrementToken()) {
- terms.add(termAtt.term());
- }
- } else {
- final Token reusableToken = new Token();
- for (Token nextToken = stream.next(reusableToken); nextToken != null; nextToken = stream.next(reusableToken)) {
- terms.add(nextToken.term());
- }
+ boolean hasMoreTokens = false;
+
+ stream.reset();
+ TermAttribute termAtt = (TermAttribute) stream.getAttribute(TermAttribute.class);
+
+ hasMoreTokens = stream.incrementToken();
+ while (hasMoreTokens) {
+ terms.add(termAtt.term());
+ hasMoreTokens = stream.incrementToken();
}
processTerms((String[])terms.toArray(new String[terms.size()]));
} catch (IOException e) {
Modified: lucene/java/trunk/src/java/org/apache/lucene/util/Attribute.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/util/Attribute.java?rev=797665&r1=797664&r2=797665&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/util/Attribute.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/util/Attribute.java Fri Jul 24 21:45:48 2009
@@ -17,79 +17,14 @@
* limitations under the License.
*/
-import java.io.Serializable;
-
/**
- * Base class for Attributes that can be added to a
- * {@link org.apache.lucene.util.AttributeSource}.
- * <p>
- * Attributes are used to add data in a dynamic, yet type-safe way to a source
- * of usually streamed objects, e. g. a {@link org.apache.lucene.analysis.TokenStream}.
+ * Base interface for attributes.
+ *
* <p><font color="#FF0000">
* WARNING: The status of the new TokenStream, AttributeSource and Attributes is experimental.
* The APIs introduced in these classes with Lucene 2.9 might change in the future.
* We will make our best efforts to keep the APIs backwards-compatible.</font>
*/
-public abstract class Attribute implements Cloneable, Serializable {
- /**
- * Clears the values in this Attribute and resets it to its
- * default value.
- */
- public abstract void clear();
-
- /**
- * Subclasses must implement this method and should follow a syntax
- * similar to this one:
- *
- * <pre>
- * public String toString() {
- * return "start=" + startOffset + ",end=" + endOffset;
- * }
- * </pre>
- */
- public abstract String toString();
-
- /**
- * Subclasses must implement this method and should compute
- * a hashCode similar to this:
- * <pre>
- * public int hashCode() {
- * int code = startOffset;
- * code = code * 31 + endOffset;
- * return code;
- * }
- * </pre>
- *
- * see also {@link #equals(Object)}
- */
- public abstract int hashCode();
-
- /**
- * All values used for computation of {@link #hashCode()}
- * should be checked here for equality.
- *
- * see also {@link Object#equals(Object)}
- */
- public abstract boolean equals(Object other);
-
- /**
- * Copies the values from this Attribute into the passed-in
- * target attribute. The type of the target must match the type
- * of this attribute.
- */
- public abstract void copyTo(Attribute target);
-
- /**
- * Shallow clone. Subclasses must override this if they
- * need to clone any members deeply,
- */
- public Object clone() {
- Object clone = null;
- try {
- clone = super.clone();
- } catch (CloneNotSupportedException e) {
- throw new RuntimeException(e); // shouldn't happen
- }
- return clone;
- }
+public interface Attribute {
+ public void clear();
}
Added: lucene/java/trunk/src/java/org/apache/lucene/util/AttributeImpl.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/util/AttributeImpl.java?rev=797665&view=auto
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/util/AttributeImpl.java (added)
+++ lucene/java/trunk/src/java/org/apache/lucene/util/AttributeImpl.java Fri Jul 24 21:45:48 2009
@@ -0,0 +1,123 @@
+package org.apache.lucene.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.io.Serializable;
+import java.lang.reflect.Field;
+
+/**
+ * Base class for Attributes that can be added to a
+ * {@link org.apache.lucene.util.AttributeSource}.
+ * <p>
+ * Attributes are used to add data in a dynamic, yet type-safe way to a source
+ * of usually streamed objects, e. g. a {@link org.apache.lucene.analysis.TokenStream}.
+ * <p><font color="#FF0000">
+ * WARNING: The status of the new TokenStream, AttributeSource and Attributes is experimental.
+ * The APIs introduced in these classes with Lucene 2.9 might change in the future.
+ * We will make our best efforts to keep the APIs backwards-compatible.</font>
+ */
+public abstract class AttributeImpl implements Cloneable, Serializable {
+ /**
+ * Clears the values in this Attribute and resets it to its
+ * default value.
+ */
+ public abstract void clear();
+
+ /**
+ * The default implementation of this method accesses all declared
+ * fields of this object and prints the values in the following syntax:
+ *
+ * <pre>
+ * public String toString() {
+ * return "start=" + startOffset + ",end=" + endOffset;
+ * }
+ * </pre>
+ *
+ * This method may be overridden by subclasses.
+ */
+ public String toString() {
+ StringBuffer buffer = new StringBuffer();
+ Class clazz = this.getClass();
+ Field[] fields = clazz.getDeclaredFields();
+ try {
+ for (int i = 0; i < fields.length; i++) {
+ Field f = fields[i];
+ f.setAccessible(true);
+ Object value = f.get(this);
+ if (value == null) {
+ buffer.append(f.getName() + "=null");
+ } else {
+ buffer.append(f.getName() + "=" + value);
+ }
+ if (i < fields.length - 1) {
+ buffer.append(',');
+ }
+ }
+ } catch (IllegalAccessException e) {
+ // this should never happen, because we're just accessing fields
+ // from 'this'
+ throw new RuntimeException(e);
+ }
+
+ return buffer.toString();
+ }
+
+ /**
+ * Subclasses must implement this method and should compute
+ * a hashCode similar to this:
+ * <pre>
+ * public int hashCode() {
+ * int code = startOffset;
+ * code = code * 31 + endOffset;
+ * return code;
+ * }
+ * </pre>
+ *
+ * see also {@link #equals(Object)}
+ */
+ public abstract int hashCode();
+
+ /**
+ * All values used for computation of {@link #hashCode()}
+ * should be checked here for equality.
+ *
+ * see also {@link Object#equals(Object)}
+ */
+ public abstract boolean equals(Object other);
+
+ /**
+ * Copies the values from this Attribute into the passed-in
+ * target attribute. The type of the target must match the type
+ * of this attribute.
+ */
+ public abstract void copyTo(AttributeImpl target);
+
+ /**
+ * Shallow clone. Subclasses must override this if they
+ * need to clone any members deeply,
+ */
+ public Object clone() {
+ Object clone = null;
+ try {
+ clone = super.clone();
+ } catch (CloneNotSupportedException e) {
+ throw new RuntimeException(e); // shouldn't happen
+ }
+ return clone;
+ }
+}
Propchange: lucene/java/trunk/src/java/org/apache/lucene/util/AttributeImpl.java
------------------------------------------------------------------------------
svn:eol-style = native