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 [2/4] - 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/lucene/contrib/queryparser/src/test/org/apache/lucene/queryParser/standard/TestQueryParserWrapper.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/queryparser/src/test/org/apache/lucene/queryParser/standard/TestQueryParserWrapper.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/queryparser/src/test/org/apache/lucene/queryParser/standard/TestQueryParserWrapper.java (original)
+++ lucene/dev/trunk/lucene/contrib/queryparser/src/test/org/apache/lucene/queryParser/standard/TestQueryParserWrapper.java Tue Jun 1 10:35:13 2010
@@ -36,7 +36,7 @@ import org.apache.lucene.analysis.MockTo
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.document.DateField;
import org.apache.lucene.document.DateTools;
import org.apache.lucene.document.Document;
@@ -93,8 +93,8 @@ public class TestQueryParserWrapper exte
public static Analyzer qpAnalyzer = new QPTestAnalyzer();
public static final class QPTestFilter extends TokenFilter {
- TermAttribute termAtt;
- OffsetAttribute offsetAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
/**
* Filter which discards the token 'stop' and which expands the token
@@ -102,8 +102,6 @@ public class TestQueryParserWrapper exte
*/
public QPTestFilter(TokenStream in) {
super(in);
- termAtt = addAttribute(TermAttribute.class);
- offsetAtt = addAttribute(OffsetAttribute.class);
}
boolean inPhrase = false;
@@ -114,19 +112,19 @@ public class TestQueryParserWrapper exte
if (inPhrase) {
inPhrase = false;
clearAttributes();
- termAtt.setTermBuffer("phrase2");
+ termAtt.setEmpty().append("phrase2");
offsetAtt.setOffset(savedStart, savedEnd);
return true;
} else
while (input.incrementToken()) {
- if (termAtt.term().equals("phrase")) {
+ if (termAtt.toString().equals("phrase")) {
inPhrase = true;
savedStart = offsetAtt.startOffset();
savedEnd = offsetAtt.endOffset();
- termAtt.setTermBuffer("phrase1");
+ termAtt.setEmpty().append("phrase1");
offsetAtt.setOffset(savedStart, savedEnd);
return true;
- } else if (!termAtt.term().equals("stop"))
+ } else if (!termAtt.toString().equals("stop"))
return true;
}
return false;
Modified: lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynExpand.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynExpand.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynExpand.java (original)
+++ lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynExpand.java Tue Jun 1 10:35:13 2010
@@ -29,7 +29,7 @@ import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
@@ -117,10 +117,10 @@ public final class SynExpand {
// [1] Parse query into separate words so that when we expand we can avoid dups
TokenStream ts = a.tokenStream( field, new StringReader( query));
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
while (ts.incrementToken()) {
- String word = termAtt.term();
+ String word = termAtt.toString();
if ( already.add( word))
top.add( word);
}
Modified: lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynLookup.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynLookup.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynLookup.java (original)
+++ lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynLookup.java Tue Jun 1 10:35:13 2010
@@ -28,7 +28,7 @@ import java.util.Set;
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.document.Document;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
@@ -125,10 +125,10 @@ public class SynLookup {
// [1] Parse query into separate words so that when we expand we can avoid dups
TokenStream ts = a.tokenStream( field, new StringReader( query));
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
while (ts.incrementToken()) {
- String word = termAtt.term();
+ String word = termAtt.toString();
if ( already.add( word))
top.add( word);
}
Modified: lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynonymTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynonymTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynonymTokenFilter.java (original)
+++ lucene/dev/trunk/lucene/contrib/wordnet/src/java/org/apache/lucene/wordnet/SynonymTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -21,8 +21,8 @@ import java.io.IOException;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
+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.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.util.AttributeSource;
@@ -45,9 +45,9 @@ public class SynonymTokenFilter extends
private AttributeSource.State current = null;
private int todo = 0;
- private TermAttribute termAtt;
- private TypeAttribute typeAtt;
- private PositionIncrementAttribute posIncrAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
+ private final PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
/**
* Creates an instance for the given underlying stream and synonym table.
@@ -71,10 +71,6 @@ public class SynonymTokenFilter extends
this.synonyms = synonyms;
this.maxSynonyms = maxSynonyms;
-
- this.termAtt = addAttribute(TermAttribute.class);
- this.typeAtt = addAttribute(TypeAttribute.class);
- this.posIncrAtt = addAttribute(PositionIncrementAttribute.class);
}
/** Returns the next token in the stream, or null at EOS. */
@@ -89,7 +85,7 @@ public class SynonymTokenFilter extends
if (!input.incrementToken()) return false; // EOS; iterator exhausted
- stack = synonyms.getSynonyms(termAtt.term()); // push onto stack
+ stack = synonyms.getSynonyms(termAtt.toString()); // push onto stack
if (stack.length > maxSynonyms) randomize(stack);
index = 0;
current = captureState();
@@ -110,7 +106,7 @@ public class SynonymTokenFilter extends
*/
protected boolean createToken(String synonym, AttributeSource.State current) {
restoreState(current);
- termAtt.setTermBuffer(synonym);
+ termAtt.setEmpty().append(synonym);
typeAtt.setType(SYNONYM_TOKEN_TYPE);
posIncrAtt.setPositionIncrement(0);
return true;
Modified: lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/LikeThisQueryBuilder.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/LikeThisQueryBuilder.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/LikeThisQueryBuilder.java (original)
+++ lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/LikeThisQueryBuilder.java Tue Jun 1 10:35:13 2010
@@ -10,7 +10,7 @@ import java.util.Set;
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.search.similar.MoreLikeThisQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.xmlparser.DOMUtils;
@@ -77,11 +77,11 @@ public class LikeThisQueryBuilder implem
for (int i = 0; i < fields.length; i++)
{
TokenStream ts = analyzer.tokenStream(fields[i],new StringReader(stopWords));
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
try
{
while(ts.incrementToken()) {
- stopWordsSet.add(termAtt.term());
+ stopWordsSet.add(termAtt.toString());
}
}
catch(IOException ioe)
Modified: lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanOrTermsBuilder.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanOrTermsBuilder.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanOrTermsBuilder.java (original)
+++ lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanOrTermsBuilder.java Tue Jun 1 10:35:13 2010
@@ -6,7 +6,7 @@ import java.util.ArrayList;
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.index.Term;
import org.apache.lucene.search.spans.SpanOrQuery;
import org.apache.lucene.search.spans.SpanQuery;
@@ -56,10 +56,10 @@ public class SpanOrTermsBuilder extends
{
ArrayList<SpanQuery> clausesList=new ArrayList<SpanQuery>();
TokenStream ts=analyzer.tokenStream(fieldName,new StringReader(value));
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
while (ts.incrementToken()) {
- SpanTermQuery stq=new SpanTermQuery(new Term(fieldName, termAtt.term()));
+ SpanTermQuery stq=new SpanTermQuery(new Term(fieldName, termAtt.toString()));
clausesList.add(stq);
}
SpanOrQuery soq=new SpanOrQuery(clausesList.toArray(new SpanQuery[clausesList.size()]));
Modified: lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermsFilterBuilder.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermsFilterBuilder.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermsFilterBuilder.java (original)
+++ lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermsFilterBuilder.java Tue Jun 1 10:35:13 2010
@@ -5,7 +5,7 @@ import java.io.StringReader;
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.index.Term;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.TermsFilter;
@@ -57,7 +57,7 @@ public class TermsFilterBuilder implemen
String text = DOMUtils.getNonBlankTextOrFail(e);
String fieldName = DOMUtils.getAttributeWithInheritanceOrFail(e, "fieldName");
TokenStream ts = analyzer.tokenStream(fieldName, new StringReader(text));
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
try
{
@@ -65,11 +65,11 @@ public class TermsFilterBuilder implemen
while (ts.incrementToken()) {
if (term == null)
{
- term = new Term(fieldName, termAtt.term());
+ term = new Term(fieldName, termAtt.toString());
} else
{
// create from previous to save fieldName.intern overhead
- term = term.createTerm(termAtt.term());
+ term = term.createTerm(termAtt.toString());
}
tf.addTerm(term);
}
Modified: lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermsQueryBuilder.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermsQueryBuilder.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermsQueryBuilder.java (original)
+++ lucene/dev/trunk/lucene/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermsQueryBuilder.java Tue Jun 1 10:35:13 2010
@@ -5,7 +5,7 @@ import java.io.StringReader;
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.index.Term;
import org.apache.lucene.search.BooleanClause;
import org.apache.lucene.search.BooleanQuery;
@@ -57,16 +57,16 @@ public class TermsQueryBuilder implement
TokenStream ts = analyzer.tokenStream(fieldName, new StringReader(text));
try
{
- TermAttribute termAtt = ts.addAttribute(TermAttribute.class);
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
Term term = null;
while (ts.incrementToken()) {
if (term == null)
{
- term = new Term(fieldName, termAtt.term());
+ term = new Term(fieldName, termAtt.toString());
} else
{
// create from previous to save fieldName.intern overhead
- term = term.createTerm(termAtt.term());
+ term = term.createTerm(termAtt.toString());
}
bq.add(new BooleanClause(new TermQuery(term),BooleanClause.Occur.SHOULD));
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicNormalizationFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicNormalizationFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicNormalizationFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicNormalizationFilter.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;
/**
* A {@link TokenFilter} that applies {@link ArabicNormalizer} to normalize the orthography.
@@ -29,21 +29,18 @@ import org.apache.lucene.analysis.tokena
*/
public final class ArabicNormalizationFilter extends TokenFilter {
-
- private final ArabicNormalizer normalizer;
- private final TermAttribute termAtt;
+ private final ArabicNormalizer normalizer = new ArabicNormalizer();
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
public ArabicNormalizationFilter(TokenStream input) {
super(input);
- normalizer = new ArabicNormalizer();
- termAtt = addAttribute(TermAttribute.class);
}
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- int newlen = normalizer.normalize(termAtt.termBuffer(), termAtt.termLength());
- termAtt.setTermLength(newlen);
+ int newlen = normalizer.normalize(termAtt.buffer(), termAtt.length());
+ termAtt.setLength(newlen);
return true;
}
return false;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicStemFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicStemFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicStemFilter.java Tue Jun 1 10:35:13 2010
@@ -23,7 +23,7 @@ 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;
/**
* A {@link TokenFilter} that applies {@link ArabicStemmer} to stem Arabic words..
@@ -35,24 +35,20 @@ import org.apache.lucene.analysis.tokena
* @see KeywordMarkerFilter */
public final class ArabicStemFilter extends TokenFilter {
-
- private final ArabicStemmer stemmer;
- private final TermAttribute termAtt;
- private final KeywordAttribute keywordAttr;
+ private final ArabicStemmer stemmer = new ArabicStemmer();
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
public ArabicStemFilter(TokenStream input) {
super(input);
- stemmer = new ArabicStemmer();
- termAtt = addAttribute(TermAttribute.class);
- keywordAttr = addAttribute(KeywordAttribute.class);
}
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
if(!keywordAttr.isKeyword()) {
- final int newlen = stemmer.stem(termAtt.termBuffer(), termAtt.termLength());
- termAtt.setTermLength(newlen);
+ final int newlen = stemmer.stem(termAtt.buffer(), termAtt.length());
+ termAtt.setLength(newlen);
}
return true;
} else {
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianStemFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianStemFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianStemFilter.java Tue Jun 1 10:35:13 2010
@@ -23,7 +23,7 @@ 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;
/**
* A {@link TokenFilter} that applies {@link BulgarianStemmer} to stem Bulgarian
@@ -35,23 +35,20 @@ import org.apache.lucene.analysis.tokena
* </p>
*/
public final class BulgarianStemFilter extends TokenFilter {
- private final BulgarianStemmer stemmer;
- private final TermAttribute termAtt;
- private final KeywordAttribute keywordAttr;
+ private final BulgarianStemmer stemmer = new BulgarianStemmer();
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
public BulgarianStemFilter(final TokenStream input) {
super(input);
- stemmer = new BulgarianStemmer();
- termAtt = addAttribute(TermAttribute.class);
- keywordAttr = addAttribute(KeywordAttribute.class);
}
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
if(!keywordAttr.isKeyword()) {
- final int newlen = stemmer.stem(termAtt.termBuffer(), termAtt.termLength());
- termAtt.setTermLength(newlen);
+ final int newlen = stemmer.stem(termAtt.buffer(), termAtt.length());
+ termAtt.setLength(newlen);
}
return true;
} else {
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianStemFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianStemFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianStemFilter.java Tue Jun 1 10:35:13 2010
@@ -24,7 +24,7 @@ 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;
/**
* A {@link TokenFilter} that applies {@link BrazilianStemmer}.
@@ -41,10 +41,10 @@ public final class BrazilianStemFilter e
/**
* {@link BrazilianStemmer} in use by this filter.
*/
- private BrazilianStemmer stemmer = null;
+ private BrazilianStemmer stemmer = new BrazilianStemmer();
private Set<?> exclusions = null;
- private final TermAttribute termAtt;
- private final KeywordAttribute keywordAttr;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
/**
* Creates a new BrazilianStemFilter
@@ -53,9 +53,6 @@ public final class BrazilianStemFilter e
*/
public BrazilianStemFilter(TokenStream in) {
super(in);
- stemmer = new BrazilianStemmer();
- termAtt = addAttribute(TermAttribute.class);
- keywordAttr = addAttribute(KeywordAttribute.class);
}
/**
@@ -74,13 +71,13 @@ public final class BrazilianStemFilter e
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- final String term = termAtt.term();
+ final String term = termAtt.toString();
// Check the exclusion table.
if (!keywordAttr.isKeyword() && (exclusions == null || !exclusions.contains(term))) {
final String s = stemmer.stem(term);
// If not stemmed, don't waste the time adjusting the token.
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/cjk/CJKTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKTokenizer.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKTokenizer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKTokenizer.java Tue Jun 1 10:35:13 2010
@@ -22,7 +22,7 @@ import java.io.Reader;
import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.util.AttributeSource;
@@ -98,9 +98,9 @@ public final class CJKTokenizer extends
*/
private boolean preIsTokened = false;
- private TermAttribute termAtt;
- private OffsetAttribute offsetAtt;
- private TypeAttribute typeAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
//~ Constructors -----------------------------------------------------------
@@ -111,23 +111,14 @@ public final class CJKTokenizer extends
*/
public CJKTokenizer(Reader in) {
super(in);
- init();
}
public CJKTokenizer(AttributeSource source, Reader in) {
super(source, in);
- init();
}
public CJKTokenizer(AttributeFactory factory, Reader in) {
super(factory, in);
- init();
- }
-
- private void init() {
- termAtt = addAttribute(TermAttribute.class);
- offsetAtt = addAttribute(OffsetAttribute.class);
- typeAtt = addAttribute(TypeAttribute.class);
}
//~ Methods ----------------------------------------------------------------
@@ -287,7 +278,7 @@ public final class CJKTokenizer extends
}
if (length > 0) {
- termAtt.setTermBuffer(buffer, 0, length);
+ termAtt.copyBuffer(buffer, 0, length);
offsetAtt.setOffset(correctOffset(start), correctOffset(start+length));
typeAtt.setType(TOKEN_TYPE_NAMES[tokenType]);
return true;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cn/ChineseFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cn/ChineseFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cn/ChineseFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cn/ChineseFilter.java Tue Jun 1 10:35:13 2010
@@ -23,7 +23,7 @@ import java.util.Arrays;
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.StopFilter;
-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;
@@ -61,21 +61,20 @@ public final class ChineseFilter extends
private CharArraySet stopTable;
- private TermAttribute termAtt;
+ private CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
public ChineseFilter(TokenStream in) {
super(in);
stopTable = new CharArraySet(Version.LUCENE_CURRENT, Arrays.asList(STOP_WORDS), false);
- termAtt = addAttribute(TermAttribute.class);
}
@Override
public boolean incrementToken() throws IOException {
while (input.incrementToken()) {
- char text[] = termAtt.termBuffer();
- int termLength = termAtt.termLength();
+ char text[] = termAtt.buffer();
+ int termLength = termAtt.length();
// why not key off token type here assuming ChineseTokenizer comes first?
if (!stopTable.contains(text, 0, termLength)) {
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cn/ChineseTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cn/ChineseTokenizer.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cn/ChineseTokenizer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cn/ChineseTokenizer.java Tue Jun 1 10:35:13 2010
@@ -23,8 +23,8 @@ import java.io.Reader;
import org.apache.lucene.analysis.standard.StandardTokenizer;
import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.util.AttributeSource;
@@ -62,24 +62,16 @@ public final class ChineseTokenizer exte
public ChineseTokenizer(Reader in) {
super(in);
- init();
}
public ChineseTokenizer(AttributeSource source, Reader in) {
super(source, in);
- init();
}
public ChineseTokenizer(AttributeFactory factory, Reader in) {
super(factory, in);
- init();
}
-
- private void init() {
- termAtt = addAttribute(TermAttribute.class);
- offsetAtt = addAttribute(OffsetAttribute.class);
- }
-
+
private int offset = 0, bufferIndex=0, dataLen=0;
private final static int MAX_WORD_LEN = 255;
private final static int IO_BUFFER_SIZE = 1024;
@@ -90,8 +82,8 @@ public final class ChineseTokenizer exte
private int length;
private int start;
- private TermAttribute termAtt;
- private OffsetAttribute offsetAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
private final void push(char c) {
@@ -105,7 +97,7 @@ public final class ChineseTokenizer exte
if (length>0) {
//System.out.println(new String(buffer, 0,
//length));
- termAtt.setTermBuffer(buffer, 0, length);
+ termAtt.copyBuffer(buffer, 0, length);
offsetAtt.setOffset(correctOffset(start), correctOffset(start+length));
return true;
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java Tue Jun 1 10:35:13 2010
@@ -30,7 +30,7 @@ import org.apache.lucene.analysis.tokena
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.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.Version;
@@ -69,12 +69,12 @@ public abstract class CompoundWordTokenF
protected final int maxSubwordSize;
protected final boolean onlyLongestMatch;
- private TermAttribute termAtt;
- private OffsetAttribute offsetAtt;
- private FlagsAttribute flagsAtt;
- private PositionIncrementAttribute posIncAtt;
- private TypeAttribute typeAtt;
- private PayloadAttribute payloadAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
+ private final FlagsAttribute flagsAtt = addAttribute(FlagsAttribute.class);
+ private final PositionIncrementAttribute posIncAtt = addAttribute(PositionIncrementAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
+ private final PayloadAttribute payloadAtt = addAttribute(PayloadAttribute.class);
private final Token wrapper = new Token();
/**
@@ -160,13 +160,6 @@ public abstract class CompoundWordTokenF
this.dictionary = new CharArraySet(matchVersion, dictionary.size(), false);
addAllLowerCase(this.dictionary, dictionary);
}
-
- termAtt = addAttribute(TermAttribute.class);
- offsetAtt = addAttribute(OffsetAttribute.class);
- flagsAtt = addAttribute(FlagsAttribute.class);
- posIncAtt = addAttribute(PositionIncrementAttribute.class);
- typeAtt = addAttribute(TypeAttribute.class);
- payloadAtt = addAttribute(PayloadAttribute.class);
}
/**
@@ -192,7 +185,7 @@ public abstract class CompoundWordTokenF
private final void setToken(final Token token) throws IOException {
clearAttributes();
- termAtt.setTermBuffer(token.termBuffer(), 0, token.termLength());
+ termAtt.copyBuffer(token.buffer(), 0, token.length());
flagsAtt.setFlags(token.getFlags());
typeAtt.setType(token.type());
offsetAtt.setOffset(token.startOffset(), token.endOffset());
@@ -210,7 +203,7 @@ public abstract class CompoundWordTokenF
if (!input.incrementToken())
return false;
- wrapper.setTermBuffer(termAtt.termBuffer(), 0, termAtt.termLength());
+ wrapper.copyBuffer(termAtt.buffer(), 0, termAtt.length());
wrapper.setStartOffset(offsetAtt.startOffset());
wrapper.setEndOffset(offsetAtt.endOffset());
wrapper.setFlags(flagsAtt.getFlags());
@@ -248,7 +241,7 @@ public abstract class CompoundWordTokenF
protected final Token createToken(final int offset, final int length,
final Token prototype) {
int newStart = prototype.startOffset() + offset;
- Token t = prototype.clone(prototype.termBuffer(), offset, length, newStart, newStart+length);
+ Token t = prototype.clone(prototype.buffer(), offset, length, newStart, newStart+length);
t.setPositionIncrement(0);
return t;
}
@@ -258,7 +251,7 @@ public abstract class CompoundWordTokenF
tokens.add((Token) token.clone());
// Only words longer than minWordSize get processed
- if (token.termLength() < this.minWordSize) {
+ if (token.length() < this.minWordSize) {
return;
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -191,22 +191,22 @@ public class DictionaryCompoundWordToken
@Override
protected void decomposeInternal(final Token token) {
// Only words longer than minWordSize get processed
- if (token.termLength() < this.minWordSize) {
+ if (token.length() < this.minWordSize) {
return;
}
- char[] lowerCaseTermBuffer=makeLowerCaseCopy(token.termBuffer());
+ char[] lowerCaseTermBuffer=makeLowerCaseCopy(token.buffer());
- for (int i=0;i<token.termLength()-this.minSubwordSize;++i) {
+ for (int i=0;i<token.length()-this.minSubwordSize;++i) {
Token longestMatchToken=null;
for (int j=this.minSubwordSize-1;j<this.maxSubwordSize;++j) {
- if(i+j>token.termLength()) {
+ if(i+j>token.length()) {
break;
}
if(dictionary.contains(lowerCaseTermBuffer, i, j)) {
if (this.onlyLongestMatch) {
if (longestMatchToken!=null) {
- if (longestMatchToken.termLength()<j) {
+ if (longestMatchToken.length()<j) {
longestMatchToken=createToken(i,j,token);
}
} else {
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -302,15 +302,15 @@ public class HyphenationCompoundWordToke
@Override
protected void decomposeInternal(final Token token) {
// get the hyphenation points
- Hyphenation hyphens = hyphenator.hyphenate(token.termBuffer(), 0, token
- .termLength(), 1, 1);
+ Hyphenation hyphens = hyphenator.hyphenate(token.buffer(), 0, token
+ .length(), 1, 1);
// No hyphen points found -> exit
if (hyphens == null) {
return;
}
final int[] hyp = hyphens.getHyphenationPoints();
- char[] lowerCaseTermBuffer=makeLowerCaseCopy(token.termBuffer());
+ char[] lowerCaseTermBuffer=makeLowerCaseCopy(token.buffer());
for (int i = 0; i < hyp.length; ++i) {
int remaining = hyp.length - i;
@@ -335,7 +335,7 @@ public class HyphenationCompoundWordToke
if (dictionary == null || dictionary.contains(lowerCaseTermBuffer, start, partLength)) {
if (this.onlyLongestMatch) {
if (longestMatchToken != null) {
- if (longestMatchToken.termLength() < partLength) {
+ if (longestMatchToken.length() < partLength) {
longestMatchToken = createToken(start, partLength, token);
}
} else {
@@ -352,7 +352,7 @@ public class HyphenationCompoundWordToke
// characters
if (this.onlyLongestMatch) {
if (longestMatchToken != null) {
- if (longestMatchToken.termLength() < partLength - 1) {
+ if (longestMatchToken.length() < partLength - 1) {
longestMatchToken = createToken(start, partLength - 1, token);
}
} else {
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechStemFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechStemFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechStemFilter.java Tue Jun 1 10:35:13 2010
@@ -6,7 +6,7 @@ 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;
/**
* Licensed to the Apache Software Foundation (ASF) under one or more
@@ -37,23 +37,20 @@ import org.apache.lucene.analysis.tokena
* @see KeywordMarkerFilter
*/
public final class CzechStemFilter extends TokenFilter {
- private final CzechStemmer stemmer;
- private final TermAttribute termAtt;
- private final KeywordAttribute keywordAttr;
+ private final CzechStemmer stemmer = new CzechStemmer();
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
public CzechStemFilter(TokenStream input) {
super(input);
- stemmer = new CzechStemmer();
- termAtt = addAttribute(TermAttribute.class);
- keywordAttr = addAttribute(KeywordAttribute.class);
}
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
if(!keywordAttr.isKeyword()) {
- final int newlen = stemmer.stem(termAtt.termBuffer(), termAtt.termLength());
- termAtt.setTermLength(newlen);
+ final int newlen = stemmer.stem(termAtt.buffer(), termAtt.length());
+ termAtt.setLength(newlen);
}
return true;
} else {
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/de/GermanStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/de/GermanStemFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/de/GermanStemFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/de/GermanStemFilter.java Tue Jun 1 10:35:13 2010
@@ -24,7 +24,7 @@ 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;
/**
* A {@link TokenFilter} that stems German words.
@@ -45,11 +45,11 @@ public final class GermanStemFilter exte
/**
* The actual token in the input stream.
*/
- private GermanStemmer stemmer = null;
+ private GermanStemmer stemmer = new GermanStemmer();
private Set<?> exclusionSet = null;
- private final TermAttribute termAtt;
- private final KeywordAttribute keywordAttr;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
/**
* Creates a {@link GermanStemFilter} instance
@@ -58,9 +58,6 @@ public final class GermanStemFilter exte
public GermanStemFilter( TokenStream in )
{
super(in);
- stemmer = new GermanStemmer();
- termAtt = addAttribute(TermAttribute.class);
- keywordAttr = addAttribute(KeywordAttribute.class);
}
/**
@@ -80,13 +77,13 @@ public final class GermanStemFilter exte
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- String term = termAtt.term();
+ String term = termAtt.toString();
// Check the exclusion table.
if (!keywordAttr.isKeyword() && (exclusionSet == null || !exclusionSet.contains(term))) {
String s = stemmer.stem(term);
// If not stemmed, don't waste the time adjusting the token.
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/fa/PersianNormalizationFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianNormalizationFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianNormalizationFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianNormalizationFilter.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;
/**
* A {@link TokenFilter} that applies {@link PersianNormalizer} to normalize the
@@ -30,22 +30,19 @@ import org.apache.lucene.analysis.tokena
*/
public final class PersianNormalizationFilter extends TokenFilter {
-
- private final PersianNormalizer normalizer;
- private final TermAttribute termAtt;
+ private final PersianNormalizer normalizer = new PersianNormalizer();
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
public PersianNormalizationFilter(TokenStream input) {
super(input);
- normalizer = new PersianNormalizer();
- termAtt = addAttribute(TermAttribute.class);
}
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- final int newlen = normalizer.normalize(termAtt.termBuffer(), termAtt
- .termLength());
- termAtt.setTermLength(newlen);
+ final int newlen = normalizer.normalize(termAtt.buffer(),
+ termAtt.length());
+ termAtt.setLength(newlen);
return true;
}
return false;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java Tue Jun 1 10:35:13 2010
@@ -23,7 +23,7 @@ import java.util.Arrays;
import org.apache.lucene.analysis.standard.StandardTokenizer; // for javadocs
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.TokenFilter;
-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;
@@ -37,7 +37,7 @@ import org.apache.lucene.util.Version;
*/
public final class ElisionFilter extends TokenFilter {
private CharArraySet articles = CharArraySet.EMPTY_SET;
- private final TermAttribute termAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private static final CharArraySet DEFAULT_ARTICLES = CharArraySet.unmodifiableSet(
new CharArraySet(Version.LUCENE_CURRENT, Arrays.asList(
"l", "m", "t", "qu", "n", "s", "j"), true));
@@ -100,7 +100,6 @@ public final class ElisionFilter extends
super(input);
this.articles = CharArraySet.unmodifiableSet(
new CharArraySet(matchVersion, articles, true));
- termAtt = addAttribute(TermAttribute.class);
}
/**
@@ -115,13 +114,13 @@ public final class ElisionFilter extends
}
/**
- * Increments the {@link TokenStream} with a {@link TermAttribute} without elisioned start
+ * Increments the {@link TokenStream} with a {@link CharTermAttribute} without elisioned start
*/
@Override
public final boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- char[] termBuffer = termAtt.termBuffer();
- int termLength = termAtt.termLength();
+ char[] termBuffer = termAtt.buffer();
+ int termLength = termAtt.length();
int minPoz = Integer.MAX_VALUE;
for (int i = 0; i < apostrophes.length; i++) {
@@ -137,8 +136,8 @@ public final class ElisionFilter extends
// An apostrophe has been found. If the prefix is an article strip it off.
if (minPoz != Integer.MAX_VALUE
- && articles.contains(termAtt.termBuffer(), 0, minPoz)) {
- termAtt.setTermBuffer(termAtt.termBuffer(), minPoz + 1, termAtt.termLength() - (minPoz + 1));
+ && articles.contains(termAtt.buffer(), 0, minPoz)) {
+ termAtt.copyBuffer(termAtt.buffer(), minPoz + 1, termAtt.length() - (minPoz + 1));
}
return true;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchStemFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchStemFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchStemFilter.java Tue Jun 1 10:35:13 2010
@@ -22,7 +22,7 @@ import org.apache.lucene.analysis.TokenF
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.snowball.SnowballFilter;
import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import java.io.IOException;
import java.util.HashSet;
@@ -51,17 +51,14 @@ public final class FrenchStemFilter exte
/**
* The actual token in the input stream.
*/
- private FrenchStemmer stemmer = null;
+ private FrenchStemmer stemmer = new FrenchStemmer();
private Set<?> exclusions = null;
- private final TermAttribute termAtt;
- private final KeywordAttribute keywordAttr;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
public FrenchStemFilter( TokenStream in ) {
- super(in);
- stemmer = new FrenchStemmer();
- termAtt = addAttribute(TermAttribute.class);
- keywordAttr = addAttribute(KeywordAttribute.class);
+ super(in);
}
/**
@@ -82,14 +79,14 @@ public final class FrenchStemFilter exte
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- String term = termAtt.term();
+ String term = termAtt.toString();
// Check the exclusion table
if ( !keywordAttr.isKeyword() && (exclusions == null || !exclusions.contains( term )) ) {
String s = stemmer.stem( term );
// If not stemmed, don't waste the time adjusting the token.
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/hi/HindiNormalizationFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiNormalizationFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiNormalizationFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiNormalizationFilter.java Tue Jun 1 10:35:13 2010
@@ -23,7 +23,7 @@ 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;
/**
* A {@link TokenFilter} that applies {@link HindiNormalizer} to normalize the
@@ -39,7 +39,7 @@ import org.apache.lucene.analysis.tokena
public final class HindiNormalizationFilter extends TokenFilter {
private final HindiNormalizer normalizer = new HindiNormalizer();
- private final TermAttribute termAtt = addAttribute(TermAttribute.class);
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private final KeywordAttribute keywordAtt = addAttribute(KeywordAttribute.class);
public HindiNormalizationFilter(TokenStream input) {
@@ -50,8 +50,8 @@ public final class HindiNormalizationFil
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
if (!keywordAtt.isKeyword())
- termAtt.setTermLength(normalizer.normalize(termAtt.termBuffer(),
- termAtt.termLength()));
+ termAtt.setLength(normalizer.normalize(termAtt.buffer(),
+ termAtt.length()));
return true;
}
return false;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiStemFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiStemFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiStemFilter.java Tue Jun 1 10:35:13 2010
@@ -22,13 +22,13 @@ import java.io.IOException;
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;
/**
* A {@link TokenFilter} that applies {@link HindiStemmer} to stem Hindi words.
*/
public final class HindiStemFilter extends TokenFilter {
- private final TermAttribute termAtt = addAttribute(TermAttribute.class);
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private final KeywordAttribute keywordAtt = addAttribute(KeywordAttribute.class);
private final HindiStemmer stemmer = new HindiStemmer();
@@ -40,7 +40,7 @@ public final class HindiStemFilter exten
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
if (!keywordAtt.isKeyword())
- termAtt.setTermLength(stemmer.stem(termAtt.termBuffer(), termAtt.termLength()));
+ termAtt.setLength(stemmer.stem(termAtt.buffer(), termAtt.length()));
return true;
} else {
return false;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/in/IndicNormalizationFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/in/IndicNormalizationFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/in/IndicNormalizationFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/in/IndicNormalizationFilter.java Tue Jun 1 10:35:13 2010
@@ -21,14 +21,14 @@ 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;
/**
* A {@link TokenFilter} that applies {@link IndicNormalizer} to normalize text
* in Indian Languages.
*/
public final class IndicNormalizationFilter extends TokenFilter {
- private final TermAttribute termAtt = addAttribute(TermAttribute.class);
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private final IndicNormalizer normalizer = new IndicNormalizer();
public IndicNormalizationFilter(TokenStream input) {
@@ -38,7 +38,7 @@ public final class IndicNormalizationFil
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- termAtt.setTermLength(normalizer.normalize(termAtt.termBuffer(), termAtt.termLength()));
+ termAtt.setLength(normalizer.normalize(termAtt.buffer(), termAtt.length()));
return true;
} else {
return false;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/PatternAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/PatternAnalyzer.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/PatternAnalyzer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/PatternAnalyzer.java Tue Jun 1 10:35:13 2010
@@ -30,8 +30,8 @@ import org.apache.lucene.analysis.Analyz
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.core.StopAnalyzer;
import org.apache.lucene.analysis.core.StopFilter;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.Version;
@@ -332,8 +332,8 @@ public final class PatternAnalyzer exten
private Matcher matcher;
private int pos = 0;
private static final Locale locale = Locale.getDefault();
- private TermAttribute termAtt = addAttribute(TermAttribute.class);
- private OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
public PatternTokenizer(String str, Pattern pattern, boolean toLowerCase) {
this.str = str;
@@ -360,7 +360,7 @@ public final class PatternAnalyzer exten
if (start != end) { // non-empty match (header/trailer)
String text = str.substring(start, end);
if (toLowerCase) text = text.toLowerCase(locale);
- termAtt.setTermBuffer(text);
+ termAtt.setEmpty().append(text);
offsetAtt.setOffset(start, end);
return true;
}
@@ -392,8 +392,8 @@ public final class PatternAnalyzer exten
private final boolean toLowerCase;
private final Set<?> stopWords;
private static final Locale locale = Locale.getDefault();
- private TermAttribute termAtt = addAttribute(TermAttribute.class);
- private OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
public FastStringTokenizer(String str, boolean isLetter, boolean toLowerCase, Set<?> stopWords) {
this.str = str;
@@ -446,7 +446,7 @@ public final class PatternAnalyzer exten
{
return false;
}
- termAtt.setTermBuffer(text);
+ termAtt.setEmpty().append(text);
offsetAtt.setOffset(start, i);
return true;
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/PrefixAwareTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/PrefixAwareTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/PrefixAwareTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/PrefixAwareTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -23,7 +23,7 @@ import org.apache.lucene.analysis.tokena
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.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.apache.lucene.index.Payload;
@@ -44,14 +44,14 @@ public class PrefixAwareTokenFilter exte
private TokenStream prefix;
private TokenStream suffix;
- private TermAttribute termAtt;
+ private CharTermAttribute termAtt;
private PositionIncrementAttribute posIncrAtt;
private PayloadAttribute payloadAtt;
private OffsetAttribute offsetAtt;
private TypeAttribute typeAtt;
private FlagsAttribute flagsAtt;
- private TermAttribute p_termAtt;
+ private CharTermAttribute p_termAtt;
private PositionIncrementAttribute p_posIncrAtt;
private PayloadAttribute p_payloadAtt;
private OffsetAttribute p_offsetAtt;
@@ -64,14 +64,14 @@ public class PrefixAwareTokenFilter exte
this.prefix = prefix;
prefixExhausted = false;
- 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);
- p_termAtt = prefix.addAttribute(TermAttribute.class);
+ p_termAtt = prefix.addAttribute(CharTermAttribute.class);
p_posIncrAtt = prefix.addAttribute(PositionIncrementAttribute.class);
p_payloadAtt = prefix.addAttribute(PayloadAttribute.class);
p_offsetAtt = prefix.addAttribute(OffsetAttribute.class);
@@ -115,7 +115,7 @@ public class PrefixAwareTokenFilter exte
private void setCurrentToken(Token token) {
if (token == null) return;
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());
@@ -125,7 +125,7 @@ public class PrefixAwareTokenFilter exte
private Token getNextPrefixInputToken(Token token) throws IOException {
if (!prefix.incrementToken()) return null;
- token.setTermBuffer(p_termAtt.termBuffer(), 0, p_termAtt.termLength());
+ token.copyBuffer(p_termAtt.buffer(), 0, p_termAtt.length());
token.setPositionIncrement(p_posIncrAtt.getPositionIncrement());
token.setFlags(p_flagsAtt.getFlags());
token.setOffset(p_offsetAtt.startOffset(), p_offsetAtt.endOffset());
@@ -136,7 +136,7 @@ public class PrefixAwareTokenFilter exte
private Token getNextSuffixInputToken(Token token) throws IOException {
if (!suffix.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());
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/SingleTokenTokenStream.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/SingleTokenTokenStream.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/SingleTokenTokenStream.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/SingleTokenTokenStream.java Tue Jun 1 10:35:13 2010
@@ -22,7 +22,7 @@ import java.io.IOException;
import org.apache.lucene.util.AttributeImpl;
import org.apache.lucene.analysis.Token;
import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
/**
* A {@link TokenStream} containing a single token.
@@ -41,7 +41,7 @@ public final class SingleTokenTokenStrea
assert token != null;
this.singleToken = (Token) token.clone();
- tokenAtt = (AttributeImpl) addAttribute(TermAttribute.class);
+ tokenAtt = (AttributeImpl) addAttribute(CharTermAttribute.class);
assert (tokenAtt instanceof Token);
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/StemmerOverrideFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/StemmerOverrideFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/StemmerOverrideFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/StemmerOverrideFilter.java Tue Jun 1 10:35:13 2010
@@ -23,7 +23,7 @@ import java.util.Map;
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.util.CharArrayMap;
import org.apache.lucene.util.Version;
@@ -34,7 +34,7 @@ import org.apache.lucene.util.Version;
public final class StemmerOverrideFilter extends TokenFilter {
private final CharArrayMap<String> dictionary;
- private final TermAttribute termAtt = addAttribute(TermAttribute.class);
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
private final KeywordAttribute keywordAtt = addAttribute(KeywordAttribute.class);
/**
@@ -56,9 +56,9 @@ public final class StemmerOverrideFilter
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
if (!keywordAtt.isKeyword()) { // don't muck with already-keyworded terms
- String stem = dictionary.get(termAtt.termBuffer(), 0, termAtt.termLength());
+ String stem = dictionary.get(termAtt.buffer(), 0, termAtt.length());
if (stem != null) {
- termAtt.setTermBuffer(stem);
+ termAtt.setEmpty().append(stem);
keywordAtt.setKeyword(true);
}
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -20,7 +20,7 @@ package org.apache.lucene.analysis.ngram
import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import java.io.IOException;
@@ -72,8 +72,8 @@ public final class EdgeNGramTokenFilter
private int curGramSize;
private int tokStart;
- private final TermAttribute termAtt;
- private final OffsetAttribute offsetAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
/**
* Creates EdgeNGramTokenFilter that can generate n-grams in the sizes of the given range
@@ -101,8 +101,6 @@ public final class EdgeNGramTokenFilter
this.minGram = minGram;
this.maxGram = maxGram;
this.side = side;
- this.termAtt = addAttribute(TermAttribute.class);
- this.offsetAtt = addAttribute(OffsetAttribute.class);
}
/**
@@ -124,8 +122,8 @@ public final class EdgeNGramTokenFilter
if (!input.incrementToken()) {
return false;
} else {
- curTermBuffer = termAtt.termBuffer().clone();
- curTermLength = termAtt.termLength();
+ curTermBuffer = termAtt.buffer().clone();
+ curTermLength = termAtt.length();
curGramSize = minGram;
tokStart = offsetAtt.startOffset();
}
@@ -138,7 +136,7 @@ public final class EdgeNGramTokenFilter
int end = start + curGramSize;
clearAttributes();
offsetAtt.setOffset(tokStart + start, tokStart + end);
- termAtt.setTermBuffer(curTermBuffer, start, curGramSize);
+ termAtt.copyBuffer(curTermBuffer, start, curGramSize);
curGramSize++;
return true;
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java Tue Jun 1 10:35:13 2010
@@ -18,8 +18,8 @@ package org.apache.lucene.analysis.ngram
*/
import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.util.AttributeSource;
import java.io.IOException;
@@ -37,8 +37,8 @@ public final class EdgeNGramTokenizer ex
public static final int DEFAULT_MAX_GRAM_SIZE = 1;
public static final int DEFAULT_MIN_GRAM_SIZE = 1;
- private TermAttribute termAtt;
- private OffsetAttribute offsetAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
/** Specifies which side of the input the n-gram should be generated from */
public static enum Side {
@@ -173,10 +173,6 @@ public final class EdgeNGramTokenizer ex
this.minGram = minGram;
this.maxGram = maxGram;
this.side = side;
-
- this.termAtt = addAttribute(TermAttribute.class);
- this.offsetAtt = addAttribute(OffsetAttribute.class);
-
}
/** Returns the next token in the stream, or null at EOS. */
@@ -206,7 +202,7 @@ public final class EdgeNGramTokenizer ex
// grab gramSize chars from front or back
int start = side == Side.FRONT ? 0 : inLen - gramSize;
int end = start + gramSize;
- termAtt.setTermBuffer(inStr, start, gramSize);
+ termAtt.setEmpty().append(inStr, start, end);
offsetAtt.setOffset(correctOffset(start), correctOffset(end));
gramSize++;
return true;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.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.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
/**
* Tokenizes the input into n-grams of the given size(s).
@@ -39,8 +39,8 @@ public final class NGramTokenFilter exte
private int curPos;
private int tokStart;
- private TermAttribute termAtt;
- private OffsetAttribute offsetAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
/**
* Creates NGramTokenFilter with given min and max n-grams.
@@ -58,9 +58,6 @@ public final class NGramTokenFilter exte
}
this.minGram = minGram;
this.maxGram = maxGram;
-
- this.termAtt = addAttribute(TermAttribute.class);
- this.offsetAtt = addAttribute(OffsetAttribute.class);
}
/**
@@ -79,8 +76,8 @@ public final class NGramTokenFilter exte
if (!input.incrementToken()) {
return false;
} else {
- curTermBuffer = termAtt.termBuffer().clone();
- curTermLength = termAtt.termLength();
+ curTermBuffer = termAtt.buffer().clone();
+ curTermLength = termAtt.length();
curGramSize = minGram;
curPos = 0;
tokStart = offsetAtt.startOffset();
@@ -89,7 +86,7 @@ public final class NGramTokenFilter exte
while (curGramSize <= maxGram) {
while (curPos+curGramSize <= curTermLength) { // while there is input
clearAttributes();
- termAtt.setTermBuffer(curTermBuffer, curPos, curGramSize);
+ termAtt.copyBuffer(curTermBuffer, curPos, curGramSize);
offsetAtt.setOffset(tokStart + curPos, tokStart + curPos + curGramSize);
curPos++;
return true;
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java Tue Jun 1 10:35:13 2010
@@ -18,8 +18,8 @@ package org.apache.lucene.analysis.ngram
*/
import org.apache.lucene.analysis.Tokenizer;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
import org.apache.lucene.util.AttributeSource;
import java.io.IOException;
@@ -39,8 +39,8 @@ public final class NGramTokenizer extend
private String inStr;
private boolean started = false;
- private TermAttribute termAtt;
- private OffsetAttribute offsetAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
/**
* Creates NGramTokenizer with given min and max n-grams.
@@ -94,9 +94,6 @@ public final class NGramTokenizer extend
}
this.minGram = minGram;
this.maxGram = maxGram;
-
- this.termAtt = addAttribute(TermAttribute.class);
- this.offsetAtt = addAttribute(OffsetAttribute.class);
}
/** Returns the next token in the stream, or null at EOS. */
@@ -123,7 +120,7 @@ public final class NGramTokenizer extend
int oldPos = pos;
pos++;
- termAtt.setTermBuffer(inStr, oldPos, gramSize);
+ termAtt.setEmpty().append(inStr, oldPos, oldPos+gramSize);
offsetAtt.setOffset(correctOffset(oldPos), correctOffset(oldPos+gramSize));
return true;
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchStemFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchStemFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchStemFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchStemFilter.java Tue Jun 1 10:35:13 2010
@@ -28,7 +28,7 @@ import org.apache.lucene.analysis.TokenF
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.snowball.SnowballFilter;
import org.apache.lucene.analysis.tokenattributes.KeywordAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
/**
* A {@link TokenFilter} that stems Dutch words.
@@ -52,17 +52,14 @@ public final class DutchStemFilter exten
/**
* The actual token in the input stream.
*/
- private DutchStemmer stemmer = null;
+ private DutchStemmer stemmer = new DutchStemmer();
private Set<?> exclusions = null;
- private final TermAttribute termAtt;
- private final KeywordAttribute keywordAttr;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final KeywordAttribute keywordAttr = addAttribute(KeywordAttribute.class);
public DutchStemFilter(TokenStream _in) {
super(_in);
- stemmer = new DutchStemmer();
- termAtt = addAttribute(TermAttribute.class);
- keywordAttr = addAttribute(KeywordAttribute.class);
}
/**
@@ -99,14 +96,14 @@ public final class DutchStemFilter exten
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- final String term = termAtt.term();
+ final String term = termAtt.toString();
// Check the exclusion table.
if (!keywordAttr.isKeyword() && (exclusions == null || !exclusions.contains(term))) {
final String s = stemmer.stem(term);
// If not stemmed, don't waste the time adjusting the token.
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/payloads/DelimitedPayloadTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/DelimitedPayloadTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/DelimitedPayloadTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/DelimitedPayloadTokenFilter.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.PayloadAttribute;
-import org.apache.lucene.analysis.tokenattributes.TermAttribute;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
/**
@@ -39,15 +39,13 @@ import org.apache.lucene.analysis.tokena
public final class DelimitedPayloadTokenFilter extends TokenFilter {
public static final char DEFAULT_DELIMITER = '|';
private final char delimiter;
- private final TermAttribute termAtt;
- private final PayloadAttribute payAtt;
+ private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
+ private final PayloadAttribute payAtt = addAttribute(PayloadAttribute.class);
private final PayloadEncoder encoder;
public DelimitedPayloadTokenFilter(TokenStream input, char delimiter, PayloadEncoder encoder) {
super(input);
- termAtt = addAttribute(TermAttribute.class);
- payAtt = addAttribute(PayloadAttribute.class);
this.delimiter = delimiter;
this.encoder = encoder;
}
@@ -55,12 +53,12 @@ public final class DelimitedPayloadToken
@Override
public boolean incrementToken() throws IOException {
if (input.incrementToken()) {
- final char[] buffer = termAtt.termBuffer();
- final int length = termAtt.termLength();
+ final char[] buffer = termAtt.buffer();
+ final int length = termAtt.length();
for (int i = 0; i < length; i++) {
if (buffer[i] == delimiter) {
payAtt.setPayload(encoder.encode(buffer, i + 1, (length - (i + 1))));
- termAtt.setTermLength(i); // simply set a new length
+ termAtt.setLength(i); // simply set a new length
return true;
}
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/NumericPayloadTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/NumericPayloadTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/NumericPayloadTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/NumericPayloadTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -35,16 +35,14 @@ public class NumericPayloadTokenFilter e
private String typeMatch;
private Payload thePayload;
- private PayloadAttribute payloadAtt;
- private TypeAttribute typeAtt;
+ private final PayloadAttribute payloadAtt = addAttribute(PayloadAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
public NumericPayloadTokenFilter(TokenStream input, float payload, String typeMatch) {
super(input);
//Need to encode the payload
thePayload = new Payload(PayloadHelper.encodeFloat(payload));
this.typeMatch = typeMatch;
- payloadAtt = addAttribute(PayloadAttribute.class);
- typeAtt = addAttribute(TypeAttribute.class);
}
@Override
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/TokenOffsetPayloadTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/TokenOffsetPayloadTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/TokenOffsetPayloadTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/TokenOffsetPayloadTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -33,13 +33,11 @@ import org.apache.lucene.index.Payload;
*
**/
public class TokenOffsetPayloadTokenFilter extends TokenFilter {
- protected OffsetAttribute offsetAtt;
- protected PayloadAttribute payAtt;
+ private final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
+ private final PayloadAttribute payAtt = addAttribute(PayloadAttribute.class);
public TokenOffsetPayloadTokenFilter(TokenStream input) {
super(input);
- offsetAtt = addAttribute(OffsetAttribute.class);
- payAtt = addAttribute(PayloadAttribute.class);
}
@Override
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/TypeAsPayloadTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/TypeAsPayloadTokenFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/TypeAsPayloadTokenFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/payloads/TypeAsPayloadTokenFilter.java Tue Jun 1 10:35:13 2010
@@ -33,13 +33,11 @@ import java.io.IOException;
*
**/
public class TypeAsPayloadTokenFilter extends TokenFilter {
- private PayloadAttribute payloadAtt;
- private TypeAttribute typeAtt;
+ private final PayloadAttribute payloadAtt = addAttribute(PayloadAttribute.class);
+ private final TypeAttribute typeAtt = addAttribute(TypeAttribute.class);
public TypeAsPayloadTokenFilter(TokenStream input) {
super(input);
- payloadAtt = addAttribute(PayloadAttribute.class);
- typeAtt = addAttribute(TypeAttribute.class);
}
Modified: lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/position/PositionFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/position/PositionFilter.java?rev=950008&r1=950007&r2=950008&view=diff
==============================================================================
--- lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/position/PositionFilter.java (original)
+++ lucene/dev/trunk/modules/analysis/common/src/java/org/apache/lucene/analysis/position/PositionFilter.java Tue Jun 1 10:35:13 2010
@@ -35,7 +35,7 @@ public final class PositionFilter extend
/** The first token must have non-zero positionIncrement **/
private boolean firstTokenPositioned = false;
- private PositionIncrementAttribute posIncrAtt;
+ private PositionIncrementAttribute posIncrAtt = addAttribute(PositionIncrementAttribute.class);
/**
* Constructs a PositionFilter that assigns a position increment of zero to
@@ -45,7 +45,6 @@ public final class PositionFilter extend
*/
public PositionFilter(final TokenStream input) {
super(input);
- posIncrAtt = addAttribute(PositionIncrementAttribute.class);
}
/**