You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rm...@apache.org on 2010/06/01 12:35:16 UTC
svn commit: r950008 [3/4] - in /lucene/dev/trunk:
lucene/contrib/benchmark/src/test/org/apache/lucene/benchmark/byTask/
lucene/contrib/highlighter/src/java/org/apache/lucene/search/highlight/
lucene/contrib/highlighter/src/test/org/apache/lucene/search...
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilter.java Tue Jun 1 10:35:13 2010
@@ -19,7 +19,7 @@ package org.apache.lucene.analysis.rever
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.util.Version;
import java.io.IOException;
@@ -42,7 +42,7 @@ import java.io.IOException;
*/
public final class ReverseStringFilter extends TokenFilter {
- private TermAttribute termAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private final char marker;
private final Version matchVersion;
private static final char NOMARKER = '\uFFFF';
@@ -131,20 +131,19 @@ public final class ReverseStringFilter e
super(in);
this.matchVersion = matchVersion;
this.marker = marker;
- termAtt = addAttribute(TermAttribute.class);
}
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- int len = termAtt.termLength();
+ int len = termAtt.length();
if (marker != NOMARKER) {
len++;
- termAtt.resizeTermBuffer(len);
- termAtt.termBuffer()[len - 1] = marker;
+ termAtt.resizeBuffer(len);
+ termAtt.buffer()[len - 1] = marker;
}
- reverse( matchVersion, termAtt.termBuffer(), 0, len );
- termAtt.setTermLength(len);
+ reverse( matchVersion, termAtt.buffer(), 0, len );
+ termAtt.setLength(len);
return true;
} else {
return false;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianLowerCaseFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianLowerCaseFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianLowerCaseFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianLowerCaseFilter.java Tue Jun 1 10:35:13 2010
@@ -22,7 +22,7 @@ import java.io.IOException;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.LowerCaseFilter;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
/**
* Normalizes token text to lower case.
@@ -32,20 +32,19 @@ import org.apache.lucene.analysis.tokena
@Deprecated
public final class RussianLowerCaseFilter extends TokenFilter
{
- private TermAttribute termAtt;
+ private CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
public RussianLowerCaseFilter(TokenStream in)
{
super(in);
- termAtt = addAttribute(TermAttribute.class);
}
@Override
public final boolean incrementToken() throws IOException
{
if (input.incrementToken()) {
- char[] chArray = termAtt.termBuffer();
- int chLen = termAtt.termLength();
+ char[] chArray = termAtt.buffer();
+ int chLen = termAtt.length();
for (int i = 0; i < chLen; i++)
{
chArray[i] = Character.toLowerCase(chArray[i]);
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianStemFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianStemFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianStemFilter.java Tue Jun 1 10:35:13 2010
@@ -22,7 +22,7 @@ import org.apache.lucene.analysis.miscel
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.ru.RussianStemmer;//javadoc @link
import org.apache.lucene.analysis.snowball.SnowballFilter; // javadoc @link
@@ -51,17 +51,14 @@ public final class RussianStemFilter ext
/**
* The actual token in the input stream.
*/
- private RussianStemmer stemmer = null;
+ private RussianStemmer stemmer = new RussianStemmer();
- private final TermAttribute termAtt;
- private final KeywordAttribute keywordAttr;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
public RussianStemFilter(TokenStream in)
{
super(in);
- stemmer = new RussianStemmer();
- termAtt = addAttribute(TermAttribute.class);
- keywordAttr = addAttribute(KeywordAttribute.class);
}
/**
* Returns the next token in the stream, or null at EOS
@@ -71,10 +68,10 @@ public final class RussianStemFilter ext
{
if (input.incrementToken()) {
if(!keywordAttr.isKeyword()) {
- final String term = termAtt.term();
+ final String term = termAtt.toString();
final String s = stemmer.stem(term);
if (s != null && !s.equals(term))
- termAtt.setTermBuffer(s);
+ termAtt.setEmpty().append(s);
}
return true;
} else {
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleFilter.java Tue Jun 1 10:35:13 2010
@@ -137,10 +137,10 @@ public final class ShingleFilter extends
*/
private boolean isOutputHere = false;
- private final CharTermAttribute termAtt;
- private final OffsetAttribute offsetAtt;
- private final PositionIncrementAttribute posIncrAtt;
- private final TypeAttribute typeAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
+ private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
/**
@@ -155,10 +155,6 @@ public final class ShingleFilter extends
super(input);
setMaxShingleSize(maxShingleSize);
setMinShingleSize(minShingleSize);
- this.termAtt = addAttribute(CharTermAttribute.class);
- this.offsetAtt = addAttribute(OffsetAttribute.class);
- this.posIncrAtt = addAttribute(PositionIncrementAttribute.class);
- this.typeAtt = addAttribute(TypeAttribute.class);
}
/**
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleMatrixFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleMatrixFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleMatrixFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleMatrixFilter.java Tue Jun 1 10:35:13 2010
@@ -31,11 +31,11 @@ import org.apache.lucene.analysis.TokenS
import org.apache.lucene.analysis.miscellaneous.EmptyTokenStream;
import org.apache.lucene.analysis.payloads.PayloadHelper;
import org.apache.lucene.analysis.shingle.ShingleMatrixFilter.Matrix.Column.Row;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
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.index.Payload;
@@ -193,14 +193,14 @@ public final class ShingleMatrixFilter e
private TokenStream input;
- private TermAttribute termAtt;
+ private CharTermAttribute termAtt;
private PositionIncrementAttribute posIncrAtt;
private PayloadAttribute payloadAtt;
private OffsetAttribute offsetAtt;
private TypeAttribute typeAtt;
private FlagsAttribute flagsAtt;
- private TermAttribute in_termAtt;
+ private CharTermAttribute in_termAtt;
private PositionIncrementAttribute in_posIncrAtt;
private PayloadAttribute in_payloadAtt;
private OffsetAttribute in_offsetAtt;
@@ -229,7 +229,7 @@ public final class ShingleMatrixFilter e
this.ignoringSinglePrefixOrSuffixShingle = ignoringSinglePrefixOrSuffixShingle;
this.settingsCodec = settingsCodec;
- termAtt = addAttribute(TermAttribute.class);
+ termAtt = addAttribute(CharTermAttribute.class);
posIncrAtt = addAttribute(PositionIncrementAttribute.class);
payloadAtt = addAttribute(PayloadAttribute.class);
offsetAtt = addAttribute(OffsetAttribute.class);
@@ -239,7 +239,7 @@ public final class ShingleMatrixFilter e
// set the input to be an empty token stream, we already have the data.
this.input = new EmptyTokenStream();
- in_termAtt = input.addAttribute(TermAttribute.class);
+ in_termAtt = input.addAttribute(CharTermAttribute.class);
in_posIncrAtt = input.addAttribute(PositionIncrementAttribute.class);
in_payloadAtt = input.addAttribute(PayloadAttribute.class);
in_offsetAtt = input.addAttribute(OffsetAttribute.class);
@@ -311,14 +311,14 @@ public final class ShingleMatrixFilter e
this.spacerCharacter = spacerCharacter;
this.ignoringSinglePrefixOrSuffixShingle = ignoringSinglePrefixOrSuffixShingle;
this.settingsCodec = settingsCodec;
- termAtt = addAttribute(TermAttribute.class);
+ termAtt = addAttribute(CharTermAttribute.class);
posIncrAtt = addAttribute(PositionIncrementAttribute.class);
payloadAtt = addAttribute(PayloadAttribute.class);
offsetAtt = addAttribute(OffsetAttribute.class);
typeAtt = addAttribute(TypeAttribute.class);
flagsAtt = addAttribute(FlagsAttribute.class);
- in_termAtt = input.addAttribute(TermAttribute.class);
+ in_termAtt = input.addAttribute(CharTermAttribute.class);
in_posIncrAtt = input.addAttribute(PositionIncrementAttribute.class);
in_payloadAtt = input.addAttribute(PayloadAttribute.class);
in_offsetAtt = input.addAttribute(OffsetAttribute.class);
@@ -377,7 +377,7 @@ public final class ShingleMatrixFilter e
if (token == null) return false;
clearAttributes();
- termAtt.setTermBuffer(token.termBuffer(), 0, token.termLength());
+ termAtt.copyBuffer(token.buffer(), 0, token.length());
posIncrAtt.setPositionIncrement(token.getPositionIncrement());
flagsAtt.setFlags(token.getFlags());
offsetAtt.setOffset(token.startOffset(), token.endOffset());
@@ -388,7 +388,7 @@ public final class ShingleMatrixFilter e
private Token getNextInputToken(Token token) throws IOException {
if (!input.incrementToken()) return null;
- token.setTermBuffer(in_termAtt.termBuffer(), 0, in_termAtt.termLength());
+ token.copyBuffer(in_termAtt.buffer(), 0, in_termAtt.length());
token.setPositionIncrement(in_posIncrAtt.getPositionIncrement());
token.setFlags(in_flagsAtt.getFlags());
token.setOffset(in_offsetAtt.startOffset(), in_offsetAtt.endOffset());
@@ -399,7 +399,7 @@ public final class ShingleMatrixFilter e
private Token getNextToken(Token token) throws IOException {
if (!this.incrementToken()) return null;
- token.setTermBuffer(termAtt.termBuffer(), 0, termAtt.termLength());
+ token.copyBuffer(termAtt.buffer(), 0, termAtt.length());
token.setPositionIncrement(posIncrAtt.getPositionIncrement());
token.setFlags(flagsAtt.getFlags());
token.setOffset(offsetAtt.startOffset(), offsetAtt.endOffset());
@@ -441,7 +441,7 @@ public final class ShingleMatrixFilter e
for (int i = 0; i < currentShingleLength; i++) {
Token shingleToken = currentPermuationTokens.get(i + currentPermutationTokensStartOffset);
- termLength += shingleToken.termLength();
+ termLength += shingleToken.length();
shingle.add(shingleToken);
}
if (spacerCharacter != null) {
@@ -459,9 +459,9 @@ public final class ShingleMatrixFilter e
if (spacerCharacter != null && sb.length() > 0) {
sb.append(spacerCharacter);
}
- sb.append(shingleToken.termBuffer(), 0, shingleToken.termLength());
+ sb.append(shingleToken.buffer(), 0, shingleToken.length());
}
- reusableToken.setTermBuffer(sb.toString());
+ reusableToken.setEmpty().append(sb);
updateToken(reusableToken, shingle, currentPermutationTokensStartOffset, currentPermutationRows, currentPermuationTokens);
return reusableToken;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/sinks/DateRecognizerSinkFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/sinks/DateRecognizerSinkFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/sinks/DateRecognizerSinkFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/sinks/DateRecognizerSinkFilter.java Tue Jun 1 10:35:13 2010
@@ -21,7 +21,7 @@ import java.text.DateFormat;
import java.text.ParseException;
import java.util.Date;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.util.AttributeSource;
/**
@@ -34,7 +34,7 @@ public class DateRecognizerSinkFilter ex
public static final String DATE_TYPE = "date";
protected DateFormat dateFormat;
- protected TermAttribute termAtt;
+ protected CharTermAttribute termAtt;
/**
* Uses {@link java.text.SimpleDateFormat#getDateInstance()} as the {@link java.text.DateFormat} object.
@@ -50,10 +50,10 @@ public class DateRecognizerSinkFilter ex
@Override
public boolean accept(AttributeSource source) {
if (termAtt == null) {
- termAtt = source.addAttribute(TermAttribute.class);
+ termAtt = source.addAttribute(CharTermAttribute.class);
}
try {
- Date date = dateFormat.parse(termAtt.term());//We don't care about the date, just that we can parse it as a date
+ Date date = dateFormat.parse(termAtt.toString());//We don't care about the date, just that we can parse it as a date
if (date != null) {
return true;
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/snowball/SnowballFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/snowball/SnowballFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/snowball/SnowballFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/snowball/SnowballFilter.java Tue Jun 1 10:35:13 2010
@@ -23,7 +23,7 @@ import org.apache.lucene.analysis.TokenF
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.LowerCaseFilter;
import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tr.TurkishLowerCaseFilter; // javadoc @link
import org.tartarus.snowball.SnowballProgram;
@@ -42,7 +42,7 @@ public final class SnowballFilter extend
private final SnowballProgram stemmer;
- private final TermAttribute termAtt = addAttribute(TermAttribute.class);
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
public SnowballFilter(TokenStream input, SnowballProgram stemmer) {
@@ -76,16 +76,16 @@ public final class SnowballFilter extend
public final boolean incrementToken() throws IOException {
if (input.incrementToken()) {
if (!keywordAttr.isKeyword()) {
- char termBuffer[] = termAtt.termBuffer();
- final int length = termAtt.termLength();
+ char termBuffer[] = termAtt.buffer();
+ final int length = termAtt.length();
stemmer.setCurrent(termBuffer, length);
stemmer.stem();
final char finalTerm[] = stemmer.getCurrentBuffer();
final int newLength = stemmer.getCurrentBufferLength();
if (finalTerm != termBuffer)
- termAtt.setTermBuffer(finalTerm, 0, newLength);
+ termAtt.copyBuffer(finalTerm, 0, newLength);
else
- termAtt.setTermLength(newLength);
+ termAtt.setLength(newLength);
}
return true;
} else {
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymFilter.java Tue Jun 1 10:35:13 2010
@@ -133,7 +133,7 @@ public final class SynonymFilter extends
OffsetAttribute lastOffsetAtt = lastTok.addAttribute(OffsetAttribute.class);
newOffsetAtt.setOffset(newOffsetAtt.startOffset(), lastOffsetAtt.endOffset());
- newTermAtt.copyBuffer(repTok.termBuffer(), 0, repTok.termLength());
+ newTermAtt.copyBuffer(repTok.buffer(), 0, repTok.length());
repPos += repTok.getPositionIncrement();
if (i==0) repPos=origPos; // make position of first token equal to original
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymMap.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymMap.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymMap.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymMap.java Tue Jun 1 10:35:13 2010
@@ -103,8 +103,7 @@ public class SynonymMap {
List<Token> ret = new ArrayList<Token>(strings.size());
for (String str : strings) {
//Token newTok = new Token(str,0,0,"SYNONYM");
- Token newTok = new Token(0,0,"SYNONYM");
- newTok.setTermBuffer(str.toCharArray(), 0, str.length());
+ Token newTok = new Token(str, 0,0,"SYNONYM");
ret.add(newTok);
}
return ret;
@@ -137,7 +136,7 @@ public class SynonymMap {
while(tok1!=null || tok2!=null) {
while (tok1 != null && (pos1 <= pos2 || tok2==null)) {
Token tok = new Token(tok1.startOffset(), tok1.endOffset(), tok1.type());
- tok.setTermBuffer(tok1.termBuffer(), 0, tok1.termLength());
+ tok.copyBuffer(tok1.buffer(), 0, tok1.length());
tok.setPositionIncrement(pos1-pos);
result.add(tok);
pos=pos1;
@@ -146,7 +145,7 @@ public class SynonymMap {
}
while (tok2 != null && (pos2 <= pos1 || tok1==null)) {
Token tok = new Token(tok2.startOffset(), tok2.endOffset(), tok2.type());
- tok.setTermBuffer(tok2.termBuffer(), 0, tok2.termLength());
+ tok.copyBuffer(tok2.buffer(), 0, tok2.length());
tok.setPositionIncrement(pos2-pos);
result.add(tok);
pos=pos2;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishLowerCaseFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishLowerCaseFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishLowerCaseFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishLowerCaseFilter.java Tue Jun 1 10:35:13 2010
@@ -21,7 +21,7 @@ import java.io.IOException;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
/**
* Normalizes Turkish token text to lower case.
@@ -37,7 +37,7 @@ public final class TurkishLowerCaseFilte
private static final int LATIN_SMALL_LETTER_I = '\u0069';
private static final int LATIN_SMALL_LETTER_DOTLESS_I = '\u0131';
private static final int COMBINING_DOT_ABOVE = '\u0307';
- private final TermAttribute termAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
/**
* Create a new TurkishLowerCaseFilter, that normalizes Turkish token text
@@ -47,7 +47,6 @@ public final class TurkishLowerCaseFilte
*/
public TurkishLowerCaseFilter(TokenStream in) {
super(in);
- termAtt = addAttribute(TermAttribute.class);
}
@Override
@@ -55,8 +54,8 @@ public final class TurkishLowerCaseFilte
boolean iOrAfter = false;
if (input.incrementToken()) {
- final char[] buffer = termAtt.termBuffer();
- int length = termAtt.termLength();
+ final char[] buffer = termAtt.buffer();
+ int length = termAtt.length();
for (int i = 0; i < length;) {
final int ch = Character.codePointAt(buffer, i);
@@ -88,7 +87,7 @@ public final class TurkishLowerCaseFilte
i += Character.toChars(Character.toLowerCase(ch), buffer, i);
}
- termAtt.setTermLength(length);
+ termAtt.setLength(length);
return true;
} else
return false;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizer.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizer.java Tue Jun 1 10:35:13 2010
@@ -18,10 +18,10 @@
package org.apache.lucene.analysis.wikipedia;
import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.FlagsAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.util.AttributeSource;
@@ -116,11 +116,11 @@ public final class WikipediaTokenizer ex
private Set<String> untokenizedTypes = Collections.emptySet();
private Iterator<AttributeSource.State> tokens = null;
- private OffsetAttribute offsetAtt;
- private TypeAttribute typeAtt;
- private PositionIncrementAttribute posIncrAtt;
- private TermAttribute termAtt;
- private FlagsAttribute flagsAtt;
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
+ private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final FlagsAttribute flagsAtt = addAttribute(FlagsAttribute.class);
/**
* Creates a new instance of the {@link WikipediaTokenizer}. Attaches the
@@ -176,12 +176,7 @@ public final class WikipediaTokenizer ex
private void init(int tokenOutput, Set<String> untokenizedTypes) {
this.tokenOutput = tokenOutput;
- this.untokenizedTypes = untokenizedTypes;
- this.offsetAtt = addAttribute(OffsetAttribute.class);
- this.typeAtt = addAttribute(TypeAttribute.class);
- this.posIncrAtt = addAttribute(PositionIncrementAttribute.class);
- this.termAtt = addAttribute(TermAttribute.class);
- this.flagsAtt = addAttribute(FlagsAttribute.class);
+ this.untokenizedTypes = untokenizedTypes;
}
/*
@@ -245,8 +240,9 @@ public final class WikipediaTokenizer ex
lastPos = currPos + numAdded;
}
//trim the buffer
+ // TODO: this is inefficient
String s = buffer.toString().trim();
- termAtt.setTermBuffer(s.toCharArray(), 0, s.length());
+ termAtt.setEmpty().append(s);
offsetAtt.setOffset(correctOffset(theStart), correctOffset(theStart + s.length()));
flagsAtt.setFlags(UNTOKENIZED_TOKEN_FLAG);
//The way the loop is written, we will have proceeded to the next token. We need to pushback the scanner to lastPos
@@ -283,8 +279,9 @@ public final class WikipediaTokenizer ex
lastPos = currPos + numAdded;
}
//trim the buffer
+ // TODO: this is inefficient
String s = buffer.toString().trim();
- termAtt.setTermBuffer(s.toCharArray(), 0, s.length());
+ termAtt.setEmpty().append(s);
offsetAtt.setOffset(correctOffset(theStart), correctOffset(theStart + s.length()));
flagsAtt.setFlags(UNTOKENIZED_TOKEN_FLAG);
//The way the loop is written, we will have proceeded to the next token. We need to pushback the scanner to lastPos
@@ -298,7 +295,7 @@ public final class WikipediaTokenizer ex
private void setupToken() {
scanner.getText(termAtt);
final int start = scanner.yychar();
- offsetAtt.setOffset(correctOffset(start), correctOffset(start + termAtt.termLength()));
+ offsetAtt.setOffset(correctOffset(start), correctOffset(start + termAtt.length()));
}
/*
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.java Tue Jun 1 10:35:13 2010
@@ -1,4 +1,4 @@
-/* The following code was generated by JFlex 1.5.0-SNAPSHOT on 17.05.10 14:51 */
+/* The following code was generated by JFlex 1.5.0-SNAPSHOT on 5/31/10 3:11 PM */
package org.apache.lucene.analysis.wikipedia;
@@ -19,14 +19,14 @@ package org.apache.lucene.analysis.wikip
* limitations under the License.
*/
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
/**
* This class is a scanner generated by
* <a href="http://www.jflex.de/">JFlex</a> 1.5.0-SNAPSHOT
- * on 17.05.10 14:51 from the specification file
- * <tt>C:/Users/Uwe Schindler/Projects/lucene/newtrunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.jflex</tt>
+ * on 5/31/10 3:11 PM from the specification file
+ * <tt>C:/Users/rmuir/workspace/solrcene/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.jflex</tt>
*/
class WikipediaTokenizerImpl {
@@ -37,16 +37,16 @@ class WikipediaTokenizerImpl {
private static final int ZZ_BUFFERSIZE = 16384;
/** lexical states */
- public static final int CATEGORY_STATE = 2;
- public static final int DOUBLE_EQUALS_STATE = 14;
+ public static final int THREE_SINGLE_QUOTES_STATE = 10;
public static final int EXTERNAL_LINK_STATE = 6;
+ public static final int DOUBLE_EQUALS_STATE = 14;
public static final int INTERNAL_LINK_STATE = 4;
public static final int DOUBLE_BRACE_STATE = 16;
- public static final int FIVE_SINGLE_QUOTES_STATE = 12;
+ public static final int CATEGORY_STATE = 2;
+ public static final int YYINITIAL = 0;
public static final int STRING = 18;
+ public static final int FIVE_SINGLE_QUOTES_STATE = 12;
public static final int TWO_SINGLE_QUOTES_STATE = 8;
- public static final int YYINITIAL = 0;
- public static final int THREE_SINGLE_QUOTES_STATE = 10;
/**
* ZZ_LEXSTATE[l] is the state in the DFA for the lexical state l
@@ -487,8 +487,8 @@ public final int getPositionIncrement(){
/**
* Fills Lucene token with the current token text.
*/
-final void getText(TermAttribute t) {
- t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
+final void getText(CharTermAttribute t) {
+ t.copyBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
}
final int setText(StringBuilder buffer){
@@ -803,184 +803,184 @@ final int setText(StringBuilder buffer){
zzMarkedPos = zzMarkedPosL;
switch (zzAction < 0 ? zzAction : ZZ_ACTION[zzAction]) {
- case 25:
- { numWikiTokensSeen = 0; positionInc = 1; currentTokType = CITATION; yybegin(DOUBLE_BRACE_STATE);
+ case 16:
+ { currentTokType = HEADING; yybegin(DOUBLE_EQUALS_STATE); numWikiTokensSeen++; return currentTokType;
}
case 46: break;
- case 30:
- { numBalanced = 0;currentTokType = ALPHANUM; yybegin(YYINITIAL);/*end italics*/
+ case 39:
+ { positionInc = 1; return ACRONYM;
}
case 47: break;
- case 41:
- { numBalanced = 0;currentTokType = ALPHANUM; yybegin(YYINITIAL);/*end bold italics*/
+ case 8:
+ { /* ignore */
}
case 48: break;
- case 14:
- { yybegin(STRING); numWikiTokensSeen++; return currentTokType;
+ case 20:
+ { numBalanced = 0; numWikiTokensSeen = 0; currentTokType = EXTERNAL_LINK;yybegin(EXTERNAL_LINK_STATE);
}
case 49: break;
- case 23:
- { numWikiTokensSeen = 0; positionInc = 1; yybegin(DOUBLE_EQUALS_STATE);
+ case 35:
+ { positionInc = 1; return COMPANY;
}
case 50: break;
- case 34:
- { positionInc = 1; return NUM;
+ case 4:
+ { numWikiTokensSeen = 0; positionInc = 1; currentTokType = EXTERNAL_LINK_URL; yybegin(EXTERNAL_LINK_STATE);
}
case 51: break;
- case 18:
- { /* ignore STRING */
+ case 25:
+ { numWikiTokensSeen = 0; positionInc = 1; currentTokType = CITATION; yybegin(DOUBLE_BRACE_STATE);
}
case 52: break;
- case 12:
- { currentTokType = ITALICS; numWikiTokensSeen++; yybegin(STRING); return currentTokType;/*italics*/
+ case 43:
+ { numWikiTokensSeen = 0; positionInc = 1; currentTokType = CATEGORY; yybegin(CATEGORY_STATE);
}
case 53: break;
- case 37:
- { numBalanced = 0;currentTokType = ALPHANUM;yybegin(YYINITIAL);/*end bold*/
+ case 22:
+ { numWikiTokensSeen = 0; positionInc = 1; if (numBalanced == 0){numBalanced++;yybegin(TWO_SINGLE_QUOTES_STATE);} else{numBalanced = 0;}
}
case 54: break;
- case 31:
- { numBalanced = 0; numWikiTokensSeen = 0; currentTokType = INTERNAL_LINK;yybegin(INTERNAL_LINK_STATE);
+ case 34:
+ { positionInc = 1; return NUM;
}
case 55: break;
- case 10:
- { numLinkToks = 0; positionInc = 0; yybegin(YYINITIAL);
+ case 32:
+ { positionInc = 1; return APOSTROPHE;
}
case 56: break;
- case 38:
- { numBalanced = 0;currentTokType = ALPHANUM; yybegin(YYINITIAL);/*end sub header*/
+ case 23:
+ { numWikiTokensSeen = 0; positionInc = 1; yybegin(DOUBLE_EQUALS_STATE);
}
case 57: break;
- case 19:
- { yybegin(STRING); numWikiTokensSeen++; return currentTokType;/* STRING ALPHANUM*/
+ case 21:
+ { yybegin(STRING); return currentTokType;/*pipe*/
}
case 58: break;
- case 11:
- { currentTokType = BOLD; yybegin(THREE_SINGLE_QUOTES_STATE);
+ case 2:
+ { positionInc = 1; return ALPHANUM;
}
case 59: break;
- case 1:
- { numWikiTokensSeen = 0; positionInc = 1;
+ case 29:
+ { currentTokType = INTERNAL_LINK; numWikiTokensSeen = 0; yybegin(INTERNAL_LINK_STATE);
}
case 60: break;
- case 33:
- { positionInc = 1; return HOST;
+ case 17:
+ { yybegin(DOUBLE_BRACE_STATE); numWikiTokensSeen = 0; return currentTokType;
}
case 61: break;
- case 3:
- { positionInc = 1; return CJ;
+ case 44:
+ { currentTokType = CATEGORY; numWikiTokensSeen = 0; yybegin(CATEGORY_STATE);
}
case 62: break;
- case 17:
- { yybegin(DOUBLE_BRACE_STATE); numWikiTokensSeen = 0; return currentTokType;
+ case 26:
+ { yybegin(YYINITIAL);
}
case 63: break;
- case 32:
- { positionInc = 1; return APOSTROPHE;
+ case 3:
+ { positionInc = 1; return CJ;
}
case 64: break;
- case 8:
- { /* ignore */
+ case 38:
+ { numBalanced = 0;currentTokType = ALPHANUM; yybegin(YYINITIAL);/*end sub header*/
}
case 65: break;
- case 4:
- { numWikiTokensSeen = 0; positionInc = 1; currentTokType = EXTERNAL_LINK_URL; yybegin(EXTERNAL_LINK_STATE);
+ case 15:
+ { currentTokType = SUB_HEADING; numWikiTokensSeen = 0; yybegin(STRING);
}
case 66: break;
- case 2:
- { positionInc = 1; return ALPHANUM;
+ case 30:
+ { numBalanced = 0;currentTokType = ALPHANUM; yybegin(YYINITIAL);/*end italics*/
}
case 67: break;
- case 26:
- { yybegin(YYINITIAL);
+ case 6:
+ { yybegin(CATEGORY_STATE); numWikiTokensSeen++; return currentTokType;
}
case 68: break;
- case 43:
- { numWikiTokensSeen = 0; positionInc = 1; currentTokType = CATEGORY; yybegin(CATEGORY_STATE);
+ case 5:
+ { positionInc = 1;
}
case 69: break;
- case 36:
- { currentTokType = BOLD_ITALICS; yybegin(FIVE_SINGLE_QUOTES_STATE);
+ case 19:
+ { yybegin(STRING); numWikiTokensSeen++; return currentTokType;/* STRING ALPHANUM*/
}
case 70: break;
- case 13:
- { currentTokType = EXTERNAL_LINK; numWikiTokensSeen = 0; yybegin(EXTERNAL_LINK_STATE);
+ case 42:
+ { positionInc = 1; numWikiTokensSeen++; yybegin(EXTERNAL_LINK_STATE); return currentTokType;
}
case 71: break;
- case 24:
- { numWikiTokensSeen = 0; positionInc = 1; currentTokType = INTERNAL_LINK; yybegin(INTERNAL_LINK_STATE);
- }
- case 72: break;
case 27:
{ numLinkToks = 0; yybegin(YYINITIAL);
}
+ case 72: break;
+ case 11:
+ { currentTokType = BOLD; yybegin(THREE_SINGLE_QUOTES_STATE);
+ }
case 73: break;
- case 15:
- { currentTokType = SUB_HEADING; numWikiTokensSeen = 0; yybegin(STRING);
+ case 13:
+ { currentTokType = EXTERNAL_LINK; numWikiTokensSeen = 0; yybegin(EXTERNAL_LINK_STATE);
}
case 74: break;
- case 28:
- { currentTokType = INTERNAL_LINK; numWikiTokensSeen = 0; yybegin(INTERNAL_LINK_STATE);
+ case 14:
+ { yybegin(STRING); numWikiTokensSeen++; return currentTokType;
}
case 75: break;
- case 39:
- { positionInc = 1; return ACRONYM;
+ case 45:
+ { numBalanced = 0; numWikiTokensSeen = 0; currentTokType = CATEGORY;yybegin(CATEGORY_STATE);
}
case 76: break;
- case 29:
- { currentTokType = INTERNAL_LINK; numWikiTokensSeen = 0; yybegin(INTERNAL_LINK_STATE);
+ case 28:
+ { currentTokType = INTERNAL_LINK; numWikiTokensSeen = 0; yybegin(INTERNAL_LINK_STATE);
}
case 77: break;
- case 7:
- { yybegin(INTERNAL_LINK_STATE); numWikiTokensSeen++; return currentTokType;
+ case 37:
+ { numBalanced = 0;currentTokType = ALPHANUM;yybegin(YYINITIAL);/*end bold*/
}
case 78: break;
- case 16:
- { currentTokType = HEADING; yybegin(DOUBLE_EQUALS_STATE); numWikiTokensSeen++; return currentTokType;
+ case 9:
+ { if (numLinkToks == 0){positionInc = 0;} else{positionInc = 1;} numWikiTokensSeen++; currentTokType = EXTERNAL_LINK; yybegin(EXTERNAL_LINK_STATE); numLinkToks++; return currentTokType;
}
case 79: break;
- case 20:
- { numBalanced = 0; numWikiTokensSeen = 0; currentTokType = EXTERNAL_LINK;yybegin(EXTERNAL_LINK_STATE);
+ case 7:
+ { yybegin(INTERNAL_LINK_STATE); numWikiTokensSeen++; return currentTokType;
}
case 80: break;
- case 35:
- { positionInc = 1; return COMPANY;
+ case 24:
+ { numWikiTokensSeen = 0; positionInc = 1; currentTokType = INTERNAL_LINK; yybegin(INTERNAL_LINK_STATE);
}
case 81: break;
case 40:
{ positionInc = 1; return EMAIL;
}
case 82: break;
- case 42:
- { positionInc = 1; numWikiTokensSeen++; yybegin(EXTERNAL_LINK_STATE); return currentTokType;
+ case 1:
+ { numWikiTokensSeen = 0; positionInc = 1;
}
case 83: break;
- case 6:
- { yybegin(CATEGORY_STATE); numWikiTokensSeen++; return currentTokType;
+ case 18:
+ { /* ignore STRING */
}
case 84: break;
- case 44:
- { currentTokType = CATEGORY; numWikiTokensSeen = 0; yybegin(CATEGORY_STATE);
+ case 36:
+ { currentTokType = BOLD_ITALICS; yybegin(FIVE_SINGLE_QUOTES_STATE);
}
case 85: break;
- case 5:
- { positionInc = 1;
+ case 33:
+ { positionInc = 1; return HOST;
}
case 86: break;
- case 9:
- { if (numLinkToks == 0){positionInc = 0;} else{positionInc = 1;} numWikiTokensSeen++; currentTokType = EXTERNAL_LINK; yybegin(EXTERNAL_LINK_STATE); numLinkToks++; return currentTokType;
+ case 31:
+ { numBalanced = 0; numWikiTokensSeen = 0; currentTokType = INTERNAL_LINK;yybegin(INTERNAL_LINK_STATE);
}
case 87: break;
- case 45:
- { numBalanced = 0; numWikiTokensSeen = 0; currentTokType = CATEGORY;yybegin(CATEGORY_STATE);
+ case 41:
+ { numBalanced = 0;currentTokType = ALPHANUM; yybegin(YYINITIAL);/*end bold italics*/
}
case 88: break;
- case 22:
- { numWikiTokensSeen = 0; positionInc = 1; if (numBalanced == 0){numBalanced++;yybegin(TWO_SINGLE_QUOTES_STATE);} else{numBalanced = 0;}
+ case 12:
+ { currentTokType = ITALICS; numWikiTokensSeen++; yybegin(STRING); return currentTokType;/*italics*/
}
case 89: break;
- case 21:
- { yybegin(STRING); return currentTokType;/*pipe*/
+ case 10:
+ { numLinkToks = 0; positionInc = 0; yybegin(YYINITIAL);
}
case 90: break;
default:
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.jflex
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.jflex?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.jflex (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/wikipedia/WikipediaTokenizerImpl.jflex Tue Jun 1 10:35:13 2010
@@ -17,7 +17,7 @@ package org.apache.lucene.analysis.wikip
* limitations under the License.
*/
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
%%
@@ -81,8 +81,8 @@ public final int getPositionIncrement(){
/**
* Fills Lucene token with the current token text.
*/
-final void getText(TermAttribute t) {
- t.setTermBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
+final void getText(CharTermAttribute t) {
+ t.copyBuffer(zzBuffer, zzStartRead, zzMarkedPos-zzStartRead);
}
final int setText(StringBuilder buffer){
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -17,8 +17,6 @@ package org.apache.lucene.analysis.compo
* limitations under the License.
*/
-import java.io.File;
-import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.io.StringReader;
@@ -27,7 +25,7 @@ import org.apache.lucene.analysis.BaseTo
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.compound.hyphenation.HyphenationTree;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
public class TestCompoundWordTokenFilter extends BaseTokenStreamTestCase {
public void testHyphenationCompoundWordsDA() throws Exception {
@@ -176,15 +174,15 @@ public class TestCompoundWordTokenFilter
CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE,
CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE, false);
- TermAttribute termAtt = tf.getAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = tf.getAttribute(CharTermAttribute.class);
assertTrue(tf.incrementToken());
- assertEquals("Rindfleischüberwachungsgesetz", termAtt.term());
+ assertEquals("Rindfleischüberwachungsgesetz", termAtt.toString());
assertTrue(tf.incrementToken());
- assertEquals("Rind", termAtt.term());
+ assertEquals("Rind", termAtt.toString());
wsTokenizer.reset(new StringReader("Rindfleischüberwachungsgesetz"));
tf.reset();
assertTrue(tf.incrementToken());
- assertEquals("Rindfleischüberwachungsgesetz", termAtt.term());
+ assertEquals("Rindfleischüberwachungsgesetz", termAtt.toString());
}
private Reader getHyphenationReader() throws Exception {
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElision.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElision.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElision.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/fr/TestElision.java Tue Jun 1 10:35:13 2010
@@ -28,6 +28,7 @@ import org.apache.lucene.analysis.BaseTo
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.standard.StandardTokenizer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.TermAttribute;
/**
@@ -50,9 +51,9 @@ public class TestElision extends BaseTok
private List<String> filter(TokenFilter filter) throws IOException {
List<String> tas = new ArrayList<String>();
- TermAttribute termAtt = filter.getAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
while (filter.incrementToken()) {
- tas.add(termAtt.term());
+ tas.add(termAtt.toString());
}
return tas;
}
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestPrefixAndSuffixAwareTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestPrefixAndSuffixAwareTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestPrefixAndSuffixAwareTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestPrefixAndSuffixAwareTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -41,8 +41,6 @@ public class TestPrefixAndSuffixAwareTok
private static Token createToken(String term, int start, int offset)
{
- Token token = new Token(start, offset);
- token.setTermBuffer(term);
- return token;
+ return new Token(term, start, offset);
}
}
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestPrefixAwareTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestPrefixAwareTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestPrefixAwareTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestPrefixAwareTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -52,8 +52,6 @@ public class TestPrefixAwareTokenFilter
private static Token createToken(String term, int start, int offset)
{
- Token token = new Token(start, offset);
- token.setTermBuffer(term);
- return token;
+ return new Token(term, start, offset);
}
}
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestRemoveDuplicatesTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestRemoveDuplicatesTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestRemoveDuplicatesTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestRemoveDuplicatesTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -51,7 +51,7 @@ public class TestRemoveDuplicatesTokenFi
if (toks.hasNext()) {
clearAttributes();
Token tok = toks.next();
- termAtt.setEmpty().append(tok.term());
+ termAtt.setEmpty().append(tok);
offsetAtt.setOffset(tok.startOffset(), tok.endOffset());
posIncAtt.setPositionIncrement(tok.getPositionIncrement());
return true;
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestSingleTokenTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestSingleTokenTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestSingleTokenTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestSingleTokenTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -22,14 +22,14 @@ import java.io.IOException;
import org.apache.lucene.util.LuceneTestCase;
import org.apache.lucene.util.AttributeImpl;
import org.apache.lucene.analysis.Token;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
public class TestSingleTokenTokenFilter extends LuceneTestCase {
public void test() throws IOException {
Token token = new Token();
SingleTokenTokenStream ts = new SingleTokenTokenStream(token);
- AttributeImpl tokenAtt = (AttributeImpl) ts.addAttribute(TermAttribute.class);
+ AttributeImpl tokenAtt = (AttributeImpl) ts.addAttribute(CharTermAttribute.class);
assertTrue(tokenAtt instanceof Token);
ts.reset();
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestTrimFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestTrimFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestTrimFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestTrimFilter.java Tue Jun 1 10:35:13 2010
@@ -97,7 +97,7 @@ public class TestTrimFilter extends Base
else {
clearAttributes();
Token token = tokens[index++];
- termAtt.setEmpty().append(token.term());
+ termAtt.setEmpty().append(token);
offsetAtt.setOffset(token.startOffset(), token.endOffset());
posIncAtt.setPositionIncrement(token.getPositionIncrement());
flagsAtt.setFlags(token.getFlags());
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/DelimitedPayloadTokenFilterTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/DelimitedPayloadTokenFilterTest.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/DelimitedPayloadTokenFilterTest.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/DelimitedPayloadTokenFilterTest.java Tue Jun 1 10:35:13 2010
@@ -18,8 +18,8 @@ package org.apache.lucene.analysis.paylo
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.index.Payload;
import org.apache.lucene.util.LuceneTestCase;
@@ -32,7 +32,7 @@ public class DelimitedPayloadTokenFilter
DelimitedPayloadTokenFilter filter = new DelimitedPayloadTokenFilter
(new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(test)),
DelimitedPayloadTokenFilter.DEFAULT_DELIMITER, new IdentityEncoder());
- TermAttribute termAtt = filter.getAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
PayloadAttribute payAtt = filter.getAttribute(PayloadAttribute.class);
assertTermEquals("The", filter, termAtt, payAtt, null);
assertTermEquals("quick", filter, termAtt, payAtt, "JJ".getBytes("UTF-8"));
@@ -70,7 +70,7 @@ public class DelimitedPayloadTokenFilter
public void testFloatEncoding() throws Exception {
String test = "The quick|1.0 red|2.0 fox|3.5 jumped|0.5 over the lazy|5 brown|99.3 dogs|83.7";
DelimitedPayloadTokenFilter filter = new DelimitedPayloadTokenFilter(new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(test)), '|', new FloatEncoder());
- TermAttribute termAtt = filter.getAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
PayloadAttribute payAtt = filter.getAttribute(PayloadAttribute.class);
assertTermEquals("The", filter, termAtt, payAtt, null);
assertTermEquals("quick", filter, termAtt, payAtt, PayloadHelper.encodeFloat(1.0f));
@@ -88,7 +88,7 @@ public class DelimitedPayloadTokenFilter
public void testIntEncoding() throws Exception {
String test = "The quick|1 red|2 fox|3 jumped over the lazy|5 brown|99 dogs|83";
DelimitedPayloadTokenFilter filter = new DelimitedPayloadTokenFilter(new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(test)), '|', new IntegerEncoder());
- TermAttribute termAtt = filter.getAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
PayloadAttribute payAtt = filter.getAttribute(PayloadAttribute.class);
assertTermEquals("The", filter, termAtt, payAtt, null);
assertTermEquals("quick", filter, termAtt, payAtt, PayloadHelper.encodeInt(1));
@@ -104,10 +104,10 @@ public class DelimitedPayloadTokenFilter
}
void assertTermEquals(String expected, TokenStream stream, byte[] expectPay) throws Exception {
- TermAttribute termAtt = stream.getAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = stream.getAttribute(CharTermAttribute.class);
PayloadAttribute payloadAtt = stream.getAttribute(PayloadAttribute.class);
assertTrue(stream.incrementToken());
- assertEquals(expected, termAtt.term());
+ assertEquals(expected, termAtt.toString());
Payload payload = payloadAtt.getPayload();
if (payload != null) {
assertTrue(payload.length() + " does not equal: " + expectPay.length, payload.length() == expectPay.length);
@@ -121,9 +121,9 @@ public class DelimitedPayloadTokenFilter
}
- void assertTermEquals(String expected, TokenStream stream, TermAttribute termAtt, PayloadAttribute payAtt, byte[] expectPay) throws Exception {
+ void assertTermEquals(String expected, TokenStream stream, CharTermAttribute termAtt, PayloadAttribute payAtt, byte[] expectPay) throws Exception {
assertTrue(stream.incrementToken());
- assertEquals(expected, termAtt.term());
+ assertEquals(expected, termAtt.toString());
Payload payload = payAtt.getPayload();
if (payload != null) {
assertTrue(payload.length() + " does not equal: " + expectPay.length, payload.length() == expectPay.length);
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/NumericPayloadTokenFilterTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/NumericPayloadTokenFilterTest.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/NumericPayloadTokenFilterTest.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/NumericPayloadTokenFilterTest.java Tue Jun 1 10:35:13 2010
@@ -20,8 +20,8 @@ import org.apache.lucene.analysis.BaseTo
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import java.io.IOException;
@@ -39,11 +39,11 @@ public class NumericPayloadTokenFilterTe
NumericPayloadTokenFilter nptf = new NumericPayloadTokenFilter(new WordTokenFilter(new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(test))), 3, "D");
boolean seenDogs = false;
- TermAttribute termAtt = nptf.getAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = nptf.getAttribute(CharTermAttribute.class);
TypeAttribute typeAtt = nptf.getAttribute(TypeAttribute.class);
PayloadAttribute payloadAtt = nptf.getAttribute(PayloadAttribute.class);
while (nptf.incrementToken()) {
- if (termAtt.term().equals("dogs")) {
+ if (termAtt.toString().equals("dogs")) {
seenDogs = true;
assertTrue(typeAtt.type() + " is not equal to " + "D", typeAtt.type().equals("D") == true);
assertTrue("payloadAtt.getPayload() is null and it shouldn't be", payloadAtt.getPayload() != null);
@@ -60,19 +60,17 @@ public class NumericPayloadTokenFilterTe
}
private final class WordTokenFilter extends TokenFilter {
- private TermAttribute termAtt;
- private TypeAttribute typeAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
private WordTokenFilter(TokenStream input) {
super(input);
- termAtt = addAttribute(TermAttribute.class);
- typeAtt = addAttribute(TypeAttribute.class);
}
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- if (termAtt.term().equals("dogs"))
+ if (termAtt.toString().equals("dogs"))
typeAtt.setType("D");
return true;
} else {
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/TypeAsPayloadTokenFilterTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/TypeAsPayloadTokenFilterTest.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/TypeAsPayloadTokenFilterTest.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/payloads/TypeAsPayloadTokenFilterTest.java Tue Jun 1 10:35:13 2010
@@ -21,7 +21,7 @@ import org.apache.lucene.analysis.TokenF
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import java.io.IOException;
@@ -39,12 +39,12 @@ public class TypeAsPayloadTokenFilterTes
TypeAsPayloadTokenFilter nptf = new TypeAsPayloadTokenFilter(new WordTokenFilter(new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(test))));
int count = 0;
- TermAttribute termAtt = nptf.getAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = nptf.getAttribute(CharTermAttribute.class);
TypeAttribute typeAtt = nptf.getAttribute(TypeAttribute.class);
PayloadAttribute payloadAtt = nptf.getAttribute(PayloadAttribute.class);
while (nptf.incrementToken()) {
- assertTrue(typeAtt.type() + " is not null and it should be", typeAtt.type().equals(String.valueOf(Character.toUpperCase(termAtt.termBuffer()[0]))));
+ assertTrue(typeAtt.type() + " is not null and it should be", typeAtt.type().equals(String.valueOf(Character.toUpperCase(termAtt.buffer()[0]))));
assertTrue("nextToken.getPayload() is null and it shouldn't be", payloadAtt.getPayload() != null);
String type = new String(payloadAtt.getPayload().getData(), "UTF-8");
assertTrue(type + " is not equal to " + typeAtt.type(), type.equals(typeAtt.type()) == true);
@@ -55,19 +55,17 @@ public class TypeAsPayloadTokenFilterTes
}
private final class WordTokenFilter extends TokenFilter {
- private TermAttribute termAtt;
- private TypeAttribute typeAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
private WordTokenFilter(TokenStream input) {
super(input);
- termAtt = addAttribute(TermAttribute.class);
- typeAtt = addAttribute(TypeAttribute.class);
}
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- typeAtt.setType(String.valueOf(Character.toUpperCase(termAtt.termBuffer()[0])));
+ typeAtt.setType(String.valueOf(Character.toUpperCase(termAtt.buffer()[0])));
return true;
} else {
return false;
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/position/PositionFilterTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/position/PositionFilterTest.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/position/PositionFilterTest.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/position/PositionFilterTest.java Tue Jun 1 10:35:13 2010
@@ -22,7 +22,7 @@ import java.io.IOException;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.shingle.ShingleFilter;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
public class PositionFilterTest extends BaseTokenStreamTestCase {
@@ -30,19 +30,18 @@ public class PositionFilterTest extends
protected int index = 0;
protected String[] testToken;
- protected TermAttribute termAtt;
+ protected final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
public TestTokenStream(String[] testToken) {
super();
this.testToken = testToken;
- termAtt = addAttribute(TermAttribute.class);
}
@Override
public final boolean incrementToken() throws IOException {
clearAttributes();
if (index < testToken.length) {
- termAtt.setTermBuffer(testToken[index++]);
+ termAtt.setEmpty().append(testToken[index++]);
return true;
} else {
return false;
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzerTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzerTest.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzerTest.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzerTest.java Tue Jun 1 10:35:13 2010
@@ -26,7 +26,6 @@ import org.apache.lucene.analysis.TokenS
import org.apache.lucene.analysis.core.LetterTokenizer;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
@@ -176,9 +175,6 @@ public class QueryAutoStopWordAnalyzerTe
QueryAutoStopWordAnalyzer a = new QueryAutoStopWordAnalyzer(TEST_VERSION_CURRENT, new WhitespaceAnalyzer(TEST_VERSION_CURRENT));
a.addStopWords(reader, 10);
TokenStream ts = a.tokenStream("repetitiveField", new StringReader("this boring"));
- TermAttribute termAtt = ts.getAttribute(TermAttribute.class);
- assertTrue(ts.incrementToken());
- assertEquals("this", termAtt.term());
- assertFalse(ts.incrementToken());
+ assertTokenStreamContents(ts, new String[] { "this" });
}
}
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/reverse/TestReverseStringFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/reverse/TestReverseStringFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/reverse/TestReverseStringFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/reverse/TestReverseStringFilter.java Tue Jun 1 10:35:13 2010
@@ -21,46 +21,22 @@ import java.io.StringReader;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
-import org.apache.lucene.util.Version;
public class TestReverseStringFilter extends BaseTokenStreamTestCase {
public void testFilter() throws Exception {
TokenStream stream = new WhitespaceTokenizer(TEST_VERSION_CURRENT,
new StringReader("Do have a nice day")); // 1-4 length string
ReverseStringFilter filter = new ReverseStringFilter(TEST_VERSION_CURRENT, stream);
- TermAttribute text = filter.getAttribute(TermAttribute.class);
- assertTrue(filter.incrementToken());
- assertEquals("oD", text.term());
- assertTrue(filter.incrementToken());
- assertEquals("evah", text.term());
- assertTrue(filter.incrementToken());
- assertEquals("a", text.term());
- assertTrue(filter.incrementToken());
- assertEquals("ecin", text.term());
- assertTrue(filter.incrementToken());
- assertEquals("yad", text.term());
- assertFalse(filter.incrementToken());
+ assertTokenStreamContents(filter, new String[] { "oD", "evah", "a", "ecin", "yad" });
}
public void testFilterWithMark() throws Exception {
TokenStream stream = new WhitespaceTokenizer(TEST_VERSION_CURRENT, new StringReader(
"Do have a nice day")); // 1-4 length string
ReverseStringFilter filter = new ReverseStringFilter(TEST_VERSION_CURRENT, stream, '\u0001');
- TermAttribute text = filter
- .getAttribute(TermAttribute.class);
- assertTrue(filter.incrementToken());
- assertEquals("\u0001oD", text.term());
- assertTrue(filter.incrementToken());
- assertEquals("\u0001evah", text.term());
- assertTrue(filter.incrementToken());
- assertEquals("\u0001a", text.term());
- assertTrue(filter.incrementToken());
- assertEquals("\u0001ecin", text.term());
- assertTrue(filter.incrementToken());
- assertEquals("\u0001yad", text.term());
- assertFalse(filter.incrementToken());
+ assertTokenStreamContents(filter,
+ new String[] { "\u0001oD", "\u0001evah", "\u0001a", "\u0001ecin", "\u0001yad" });
}
public void testReverseString() throws Exception {
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/ru/TestRussianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/ru/TestRussianAnalyzer.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/ru/TestRussianAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/ru/TestRussianAnalyzer.java Tue Jun 1 10:35:13 2010
@@ -17,17 +17,13 @@ package org.apache.lucene.analysis.ru;
* limitations under the License.
*/
-import java.io.File;
-import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
-import java.io.Reader;
-import java.io.StringReader;
import org.apache.lucene.analysis.BaseTokenStreamTestCase;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.Version;
@@ -65,8 +61,8 @@ public class TestRussianAnalyzer extends
new RussianLetterTokenizer(TEST_VERSION_CURRENT,
sampleUnicode);
- TermAttribute text = in.getAttribute(TermAttribute.class);
- TermAttribute sampleText = sample.getAttribute(TermAttribute.class);
+ CharTermAttribute text = in.getAttribute(CharTermAttribute.class);
+ CharTermAttribute sampleText = sample.getAttribute(CharTermAttribute.class);
for (;;)
{
@@ -76,34 +72,21 @@ public class TestRussianAnalyzer extends
boolean nextSampleToken = sample.incrementToken();
assertEquals(
"Unicode",
- text.term(),
+ text.toString(),
nextSampleToken == false
? null
- : sampleText.term());
+ : sampleText.toString());
}
inWords.close();
sampleUnicode.close();
}
- public void testDigitsInRussianCharset()
+ /** Check that RussianAnalyzer doesnt discard any numbers */
+ public void testDigitsInRussianCharset() throws IOException
{
- Reader reader = new StringReader("text 1000");
- RussianAnalyzer ra = new RussianAnalyzer(TEST_VERSION_CURRENT);
- TokenStream stream = ra.tokenStream("", reader);
-
- TermAttribute termText = stream.getAttribute(TermAttribute.class);
- try {
- assertTrue(stream.incrementToken());
- assertEquals("text", termText.term());
- assertTrue(stream.incrementToken());
- assertEquals("RussianAnalyzer's tokenizer skips numbers from input text", "1000", termText.term());
- assertFalse(stream.incrementToken());
- }
- catch (IOException e)
- {
- fail("unexpected IOException");
- }
+ RussianAnalyzer ra = new RussianAnalyzer(TEST_VERSION_CURRENT);
+ assertAnalyzesTo(ra, "text 1000", new String[] { "text", "1000" });
}
/** @deprecated remove this test in Lucene 4.0: stopwords changed */
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/shingle/ShingleAnalyzerWrapperTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/shingle/ShingleAnalyzerWrapperTest.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/shingle/ShingleAnalyzerWrapperTest.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/shingle/ShingleAnalyzerWrapperTest.java Tue Jun 1 10:35:13 2010
@@ -26,8 +26,8 @@ import org.apache.lucene.analysis.TokenS
import org.apache.lucene.analysis.core.LetterTokenizer;
import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
@@ -159,11 +159,11 @@ public class ShingleAnalyzerWrapperTest
int j = -1;
PositionIncrementAttribute posIncrAtt = ts.addAttribute(PositionIncrementAttribute.class);
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
while (ts.incrementToken()) {
j += posIncrAtt.getPositionIncrement();
- String termText = termAtt.term();
+ String termText = termAtt.toString();
q.add(new Term("content", termText), j);
}
@@ -186,10 +186,10 @@ public class ShingleAnalyzerWrapperTest
TokenStream ts = analyzer.tokenStream("content",
new StringReader("test sentence"));
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
while (ts.incrementToken()) {
- String termText = termAtt.term();
+ String termText = termAtt.toString();
q.add(new TermQuery(new Term("content", termText)),
BooleanClause.Occur.SHOULD);
}
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/shingle/TestShingleMatrixFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/shingle/TestShingleMatrixFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/shingle/TestShingleMatrixFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/shingle/TestShingleMatrixFilter.java Tue Jun 1 10:35:13 2010
@@ -31,7 +31,12 @@ import org.apache.lucene.analysis.miscel
import org.apache.lucene.analysis.payloads.PayloadHelper;
import org.apache.lucene.analysis.shingle.ShingleMatrixFilter.Matrix;
import org.apache.lucene.analysis.shingle.ShingleMatrixFilter.Matrix.Column;
-import org.apache.lucene.analysis.tokenattributes.*;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+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.TypeAttribute;
public class TestShingleMatrixFilter extends BaseTokenStreamTestCase {
@@ -415,7 +420,7 @@ public class TestShingleMatrixFilter ext
private Token tokenFactory(String text, int posIncr, int startOffset, int endOffset) {
Token token = new Token(startOffset, endOffset);
- token.setTermBuffer(text);
+ token.setEmpty().append(text);
token.setPositionIncrement(posIncr);
return token;
}
@@ -427,7 +432,7 @@ public class TestShingleMatrixFilter ext
private Token tokenFactory(String text, int posIncr, float weight, int startOffset, int endOffset) {
Token token = new Token(startOffset, endOffset);
- token.setTermBuffer(text);
+ token.setEmpty().append(text);
token.setPositionIncrement(posIncr);
ShingleMatrixFilter.defaultSettingsCodec.setWeight(token, weight);
return token;
@@ -435,7 +440,7 @@ public class TestShingleMatrixFilter ext
private Token tokenFactory(String text, int posIncr, float weight, int startOffset, int endOffset, ShingleMatrixFilter.TokenPositioner positioner) {
Token token = new Token(startOffset, endOffset);
- token.setTermBuffer(text);
+ token.setEmpty().append(text);
token.setPositionIncrement(posIncr);
ShingleMatrixFilter.defaultSettingsCodec.setWeight(token, weight);
ShingleMatrixFilter.defaultSettingsCodec.setTokenPositioner(token, positioner);
@@ -445,20 +450,20 @@ public class TestShingleMatrixFilter ext
// assert-methods start here
private void assertNext(TokenStream ts, String text) throws IOException {
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
assertTrue(ts.incrementToken());
- assertEquals(text, termAtt.term());
+ assertEquals(text, termAtt.toString());
}
private void assertNext(TokenStream ts, String text, int positionIncrement, float boost, int startOffset, int endOffset) throws IOException {
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
PositionIncrementAttribute posIncrAtt = ts.addAttribute(PositionIncrementAttribute.class);
PayloadAttribute payloadAtt = ts.addAttribute(PayloadAttribute.class);
OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
assertTrue(ts.incrementToken());
- assertEquals(text, termAtt.term());
+ assertEquals(text, termAtt.toString());
assertEquals(positionIncrement, posIncrAtt.getPositionIncrement());
assertEquals(boost, payloadAtt.getPayload() == null ? 1f : PayloadHelper.decodeFloat(payloadAtt.getPayload().getData()), 0);
assertEquals(startOffset, offsetAtt.startOffset());
@@ -466,11 +471,11 @@ public class TestShingleMatrixFilter ext
}
private void assertNext(TokenStream ts, String text, int startOffset, int endOffset) throws IOException {
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
assertTrue(ts.incrementToken());
- assertEquals(text, termAtt.term());
+ assertEquals(text, termAtt.toString());
assertEquals(startOffset, offsetAtt.startOffset());
assertEquals(endOffset, offsetAtt.endOffset());
}
@@ -478,7 +483,7 @@ public class TestShingleMatrixFilter ext
private static Token createToken(String term, int start, int offset)
{
Token token = new Token(start, offset);
- token.setTermBuffer(term);
+ token.setEmpty().append(term);
return token;
}
@@ -486,21 +491,15 @@ public class TestShingleMatrixFilter ext
public final static class TokenListStream extends TokenStream {
private Collection<Token> tokens;
- TermAttribute termAtt;
- PositionIncrementAttribute posIncrAtt;
- PayloadAttribute payloadAtt;
- OffsetAttribute offsetAtt;
- TypeAttribute typeAtt;
- FlagsAttribute flagsAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
+ private final PayloadAttribute payloadAtt = addAttribute(PayloadAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
+ private final FlagsAttribute flagsAtt = addAttribute(FlagsAttribute.class);
public TokenListStream(Collection<Token> tokens) {
this.tokens = tokens;
- termAtt = addAttribute(TermAttribute.class);
- posIncrAtt = addAttribute(PositionIncrementAttribute.class);
- payloadAtt = addAttribute(PayloadAttribute.class);
- offsetAtt = addAttribute(OffsetAttribute.class);
- typeAtt = addAttribute(TypeAttribute.class);
- flagsAtt = addAttribute(FlagsAttribute.class);
}
private Iterator<Token> iterator;
@@ -515,7 +514,7 @@ public class TestShingleMatrixFilter ext
}
Token prototype = iterator.next();
clearAttributes();
- termAtt.setTermBuffer(prototype.termBuffer(), 0, prototype.termLength());
+ termAtt.copyBuffer(prototype.buffer(), 0, prototype.length());
posIncrAtt.setPositionIncrement(prototype.getPositionIncrement());
flagsAtt.setFlags(prototype.getFlags());
offsetAtt.setOffset(prototype.startOffset(), prototype.endOffset());
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/sinks/TokenTypeSinkTokenizerTest.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/sinks/TokenTypeSinkTokenizerTest.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/sinks/TokenTypeSinkTokenizerTest.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/sinks/TokenTypeSinkTokenizerTest.java Tue Jun 1 10:35:13 2010
@@ -23,7 +23,7 @@ import org.apache.lucene.analysis.BaseTo
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.WhitespaceTokenizer;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
public class TokenTypeSinkTokenizerTest extends BaseTokenStreamTestCase {
@@ -41,11 +41,11 @@ public class TokenTypeSinkTokenizerTest
boolean seenDogs = false;
- TermAttribute termAtt = ttf.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ttf.addAttribute(CharTermAttribute.class);
TypeAttribute typeAtt = ttf.addAttribute(TypeAttribute.class);
ttf.reset();
while (ttf.incrementToken()) {
- if (termAtt.term().equals("dogs")) {
+ if (termAtt.toString().equals("dogs")) {
seenDogs = true;
assertTrue(typeAtt.type() + " is not equal to " + "D", typeAtt.type().equals("D") == true);
} else {
@@ -64,20 +64,18 @@ public class TokenTypeSinkTokenizerTest
}
private class WordTokenFilter extends TokenFilter {
- private TermAttribute termAtt;
- private TypeAttribute typeAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
private WordTokenFilter(TokenStream input) {
super(input);
- termAtt = addAttribute(TermAttribute.class);
- typeAtt = addAttribute(TypeAttribute.class);
}
@Override
public final boolean incrementToken() throws IOException {
if (!input.incrementToken()) return false;
- if (termAtt.term().equals("dogs")) {
+ if (termAtt.toString().equals("dogs")) {
typeAtt.setType("D");
}
return true;
Modified: lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/snowball/TestSnowball.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/snowball/TestSnowball.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/snowball/TestSnowball.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/test/org/apache/lucene/analysis/snowball/TestSnowball.java Tue Jun 1 10:35:13 2010
@@ -22,11 +22,11 @@ import org.apache.lucene.analysis.Analyz
import org.apache.lucene.index.Payload;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
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.Version;
@@ -93,7 +93,7 @@ public class TestSnowball extends BaseTo
public void testFilterTokens() throws Exception {
SnowballFilter filter = new SnowballFilter(new TestTokenStream(), "English");
- TermAttribute termAtt = filter.getAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = filter.getAttribute(CharTermAttribute.class);
OffsetAttribute offsetAtt = filter.getAttribute(OffsetAttribute.class);
TypeAttribute typeAtt = filter.getAttribute(TypeAttribute.class);
PayloadAttribute payloadAtt = filter.getAttribute(PayloadAttribute.class);
@@ -102,7 +102,7 @@ public class TestSnowball extends BaseTo
filter.incrementToken();
- assertEquals("accent", termAtt.term());
+ assertEquals("accent", termAtt.toString());
assertEquals(2, offsetAtt.startOffset());
assertEquals(7, offsetAtt.endOffset());
assertEquals("wrd", typeAtt.type());
@@ -112,27 +112,21 @@ public class TestSnowball extends BaseTo
}
private final class TestTokenStream extends TokenStream {
- private TermAttribute termAtt;
- private OffsetAttribute offsetAtt;
- private TypeAttribute typeAtt;
- private PayloadAttribute payloadAtt;
- private PositionIncrementAttribute posIncAtt;
- private FlagsAttribute flagsAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
+ private final PayloadAttribute payloadAtt = addAttribute(PayloadAttribute.class);
+ private final PositionIncrementAttribute posIncAtt = addAttribute(PositionIncrementAttribute.class);
+ private final FlagsAttribute flagsAtt = addAttribute(FlagsAttribute.class);
TestTokenStream() {
super();
- termAtt = addAttribute(TermAttribute.class);
- offsetAtt = addAttribute(OffsetAttribute.class);
- typeAtt = addAttribute(TypeAttribute.class);
- payloadAtt = addAttribute(PayloadAttribute.class);
- posIncAtt = addAttribute(PositionIncrementAttribute.class);
- flagsAtt = addAttribute(FlagsAttribute.class);
}
@Override
public boolean incrementToken() {
clearAttributes();
- termAtt.setTermBuffer("accents");
+ termAtt.setEmpty().append("accents");
offsetAtt.setOffset(2, 7);
typeAtt.setType("wrd");
posIncAtt.setPositionIncrement(3);