Index: solr/core/src/java/org/apache/solr/analysis/StopFilterFactory.java =================================================================== --- solr/core/src/java/org/apache/solr/analysis/StopFilterFactory.java (revision 1242044) +++ solr/core/src/java/org/apache/solr/analysis/StopFilterFactory.java (working copy) @@ -87,7 +87,7 @@ @Override public TokenStream create(TokenStream input) { - StopFilter stopFilter = new StopFilter(luceneMatchVersion,input,stopWords,ignoreCase); + StopFilter stopFilter = new StopFilter(luceneMatchVersion,input,stopWords); stopFilter.setEnablePositionIncrements(enablePositionIncrements); return stopFilter; } Index: solr/core/src/java/org/apache/solr/analysis/CommonGramsFilterFactory.java =================================================================== --- solr/core/src/java/org/apache/solr/analysis/CommonGramsFilterFactory.java (revision 1242044) +++ solr/core/src/java/org/apache/solr/analysis/CommonGramsFilterFactory.java (working copy) @@ -76,7 +76,7 @@ } public CommonGramsFilter create(TokenStream input) { - CommonGramsFilter commonGrams = new CommonGramsFilter(luceneMatchVersion, input, commonWords, ignoreCase); + CommonGramsFilter commonGrams = new CommonGramsFilter(luceneMatchVersion, input, commonWords); return commonGrams; } } Index: solr/core/src/java/org/apache/solr/analysis/CommonGramsQueryFilterFactory.java =================================================================== --- solr/core/src/java/org/apache/solr/analysis/CommonGramsQueryFilterFactory.java (revision 1242044) +++ solr/core/src/java/org/apache/solr/analysis/CommonGramsQueryFilterFactory.java (working copy) @@ -88,8 +88,7 @@ * Create a CommonGramsFilter and wrap it with a CommonGramsQueryFilter */ public CommonGramsQueryFilter create(TokenStream input) { - CommonGramsFilter commonGrams = new CommonGramsFilter(luceneMatchVersion, input, commonWords, - ignoreCase); + CommonGramsFilter commonGrams = new CommonGramsFilter(luceneMatchVersion, input, commonWords); CommonGramsQueryFilter commonGramsQuery = new CommonGramsQueryFilter( commonGrams); return commonGramsQuery; Index: modules/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilter.java =================================================================== --- modules/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilter.java (revision 1242044) +++ modules/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilter.java (working copy) @@ -37,17 +37,10 @@ public void testExactCase() throws IOException { StringReader reader = new StringReader("Now is The Time"); Set stopWords = asSet("is", "the", "Time"); - TokenStream stream = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopWords, false); + TokenStream stream = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopWords); assertTokenStreamContents(stream, new String[] { "Now", "The" }); } - public void testIgnoreCase() throws IOException { - StringReader reader = new StringReader("Now is The Time"); - Set stopWords = asSet( "is", "the", "Time" ); - TokenStream stream = new StopFilter(TEST_VERSION_CURRENT, new MockTokenizer(reader, MockTokenizer.WHITESPACE, false), stopWords, true); - assertTokenStreamContents(stream, new String[] { "Now" }); - } - public void testStopFilt() throws IOException { StringReader reader = new StringReader("Now is The Time"); String[] stopWords = new String[] { "is", "the", "Time" }; Index: modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java =================================================================== --- modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java (revision 1242044) +++ modules/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java (working copy) @@ -67,35 +67,16 @@ * in a potential bigram are in the set of common words . * * @param input TokenStream input in filter chain - * @param commonWords The set of common words. + * @param commonWords The set of common words. If it is a {@link CharArraySet} it + * will be used directly (please build the set with the appropriate + * case-sensitivity options). */ public CommonGramsFilter(Version matchVersion, TokenStream input, Set commonWords) { - this(matchVersion, input, commonWords, false); - } - - /** - * Construct a token stream filtering the given input using a Set of common - * words to create bigrams, case-sensitive if ignoreCase is false (unless Set - * is CharArraySet). If commonWords is an instance of - * {@link CharArraySet} (true if makeCommonSet() was used to - * construct the set) it will be directly used and ignoreCase - * will be ignored since CharArraySet directly controls case - * sensitivity. - *

- * If commonWords is not an instance of {@link CharArraySet}, a - * new CharArraySet will be constructed and ignoreCase will be - * used to specify the case sensitivity of that set. - * - * @param input TokenStream input in filter chain. - * @param commonWords The set of common words. - * @param ignoreCase -Ignore case when constructing bigrams for common words. - */ - public CommonGramsFilter(Version matchVersion, TokenStream input, Set commonWords, boolean ignoreCase) { super(input); if (commonWords instanceof CharArraySet) { this.commonWords = (CharArraySet) commonWords; } else { - this.commonWords = new CharArraySet(matchVersion, commonWords.size(), ignoreCase); + this.commonWords = new CharArraySet(matchVersion, commonWords.size(), false); this.commonWords.addAll(commonWords); } } Index: modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopFilter.java =================================================================== --- modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopFilter.java (revision 1242044) +++ modules/analysis/common/src/java/org/apache/lucene/analysis/core/StopFilter.java (working copy) @@ -44,34 +44,6 @@ private final CharArraySet stopWords; private final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class); - - /** - * Construct a token stream filtering the given input. If - * stopWords is an instance of {@link CharArraySet} (true if - * makeStopSet() was used to construct the set) it will be - * directly used and ignoreCase will be ignored since - * CharArraySet directly controls case sensitivity. - *

- * If stopWords is not an instance of {@link CharArraySet}, a new - * CharArraySet will be constructed and ignoreCase will be used - * to specify the case sensitivity of that set. - * - * @param matchVersion - * Lucene version to enable correct Unicode 4.0 behavior in the stop - * set if Version > 3.0. See above for details. - * @param input - * Input TokenStream - * @param stopWords - * A Set of Strings or char[] or any other toString()-able set - * representing the stopwords - * @param ignoreCase - * if true, all words are lower cased first - */ - public StopFilter(Version matchVersion, TokenStream input, Set stopWords, boolean ignoreCase) - { - super(true, input); - this.stopWords = stopWords instanceof CharArraySet ? (CharArraySet) stopWords : new CharArraySet(matchVersion, stopWords, ignoreCase); - } /** * Constructs a filter which removes words from the input TokenStream that are @@ -84,11 +56,14 @@ * Input stream * @param stopWords * A Set of Strings or char[] or any other toString()-able set - * representing the stopwords + * representing the stopwords. If it is a {@link CharArraySet} it + * will be used directly (please build the set with the appropriate + * case-sensitivity options). * @see #makeStopSet(Version, java.lang.String...) */ public StopFilter(Version matchVersion, TokenStream in, Set stopWords) { - this(matchVersion, in, stopWords, false); + super(true, in); + this.stopWords = stopWords instanceof CharArraySet ? (CharArraySet) stopWords : new CharArraySet(matchVersion, stopWords, false); } /** Index: modules/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.java =================================================================== --- modules/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.java (revision 1242044) +++ modules/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.java (working copy) @@ -147,7 +147,7 @@ // The porter stemming is too strict, this is not a bug, this is a feature:) result = new PorterStemFilter(result); if (!stopWords.isEmpty()) { - result = new StopFilter(matchVersion, result, stopWords, false); + result = new StopFilter(matchVersion, result, stopWords); } return new TokenStreamComponents(tokenizer, result); }