You are viewing a plain text version of this content. The canonical link for it is here.
Posted to java-commits@lucene.apache.org by yo...@apache.org on 2008/11/11 03:35:52 UTC
svn commit: r712922 [1/9] - in /lucene/java/trunk:
contrib/analyzers/src/java/org/apache/lucene/analysis/el/
contrib/analyzers/src/java/org/apache/lucene/analysis/fr/
contrib/analyzers/src/java/org/apache/lucene/analysis/miscellaneous/
contrib/analyzer...
Author: yonik
Date: Mon Nov 10 18:35:46 2008
New Revision: 712922
URL: http://svn.apache.org/viewvc?rev=712922&view=rev
Log:
set svn:eol-style to native on java files
Modified:
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java (contents, props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekCharsets.java (contents, props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekLowerCaseFilter.java (contents, props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/miscellaneous/EmptyTokenStream.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/miscellaneous/PrefixAndSuffixAwareTokenFilter.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/miscellaneous/PrefixAwareTokenFilter.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/miscellaneous/SingleTokenTokenStream.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/payloads/PayloadHelper.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/shingle/ShingleMatrixFilter.java (props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java (contents, props changed)
lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java (contents, props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/cn/TestChineseTokenizer.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/el/GreekAnalyzerTest.java (contents, props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/fr/TestElision.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/miscellaneous/TestEmptyTokenStream.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/miscellaneous/TestPrefixAndSuffixAwareTokenFilter.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/miscellaneous/TestPrefixAwareTokenFilter.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/miscellaneous/TestSingleTokenTokenFilter.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/shingle/TestShingleMatrixFilter.java (props changed)
lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/th/TestThaiAnalyzer.java (props changed)
lucene/java/trunk/contrib/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/SearchTravRetHighlightTask.java (props changed)
lucene/java/trunk/contrib/benchmark/src/test/org/apache/lucene/benchmark/byTask/tasks/CountingHighlighterTestTask.java (props changed)
lucene/java/trunk/contrib/db/bdb-je/src/java/org/apache/lucene/store/je/Block.java (props changed)
lucene/java/trunk/contrib/db/bdb-je/src/java/org/apache/lucene/store/je/File.java (props changed)
lucene/java/trunk/contrib/db/bdb-je/src/java/org/apache/lucene/store/je/JEDirectory.java (props changed)
lucene/java/trunk/contrib/db/bdb-je/src/java/org/apache/lucene/store/je/JEIndexInput.java (props changed)
lucene/java/trunk/contrib/db/bdb-je/src/java/org/apache/lucene/store/je/JEIndexOutput.java (props changed)
lucene/java/trunk/contrib/db/bdb-je/src/java/org/apache/lucene/store/je/JELock.java (props changed)
lucene/java/trunk/contrib/db/bdb-je/src/test/org/apache/lucene/store/je/JEStoreTest.java (props changed)
lucene/java/trunk/contrib/db/bdb/src/java/org/apache/lucene/store/db/DbIndexInput.java (props changed)
lucene/java/trunk/contrib/db/bdb/src/java/org/apache/lucene/store/db/DbIndexOutput.java (props changed)
lucene/java/trunk/contrib/db/bdb/src/test/org/apache/lucene/store/db/DbStoreTest.java (props changed)
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/DefaultEncoder.java (contents, props changed)
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/Encoder.java (contents, props changed)
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/NullFragmenter.java (props changed)
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/SimpleHTMLEncoder.java (contents, props changed)
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/SimpleSpanFragmenter.java (contents, props changed)
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/SpanScorer.java (contents, props changed)
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTerm.java (contents, props changed)
lucene/java/trunk/contrib/highlighter/src/java/org/apache/lucene/search/highlight/WeightedSpanTermExtractor.java (props changed)
lucene/java/trunk/contrib/instantiated/src/java/org/apache/lucene/store/instantiated/FieldSetting.java (props changed)
lucene/java/trunk/contrib/instantiated/src/java/org/apache/lucene/store/instantiated/FieldSettings.java (props changed)
lucene/java/trunk/contrib/instantiated/src/test/org/apache/lucene/store/instantiated/TestEmptyIndex.java (props changed)
lucene/java/trunk/contrib/instantiated/src/test/org/apache/lucene/store/instantiated/TestRealTime.java (props changed)
lucene/java/trunk/contrib/memory/src/java/org/apache/lucene/index/memory/AnalyzerUtil.java (props changed)
lucene/java/trunk/contrib/memory/src/java/org/apache/lucene/index/memory/MemoryIndex.java (props changed)
lucene/java/trunk/contrib/memory/src/java/org/apache/lucene/index/memory/PatternAnalyzer.java (props changed)
lucene/java/trunk/contrib/memory/src/java/org/apache/lucene/index/memory/SynonymMap.java (props changed)
lucene/java/trunk/contrib/memory/src/java/org/apache/lucene/index/memory/SynonymTokenFilter.java (props changed)
lucene/java/trunk/contrib/memory/src/test/org/apache/lucene/index/memory/MemoryIndexTest.java (props changed)
lucene/java/trunk/contrib/memory/src/test/org/apache/lucene/index/memory/PatternAnalyzerTest.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/index/FieldNormModifier.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/index/TermVectorAccessor.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/misc/IndexMergeTool.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/misc/LengthNormModifier.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/misc/SweetSpotSimilarity.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/queryParser/analyzing/AnalyzingQueryParser.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/queryParser/precedence/CharStream.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/queryParser/precedence/FastCharStream.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/queryParser/precedence/ParseException.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/queryParser/precedence/PrecedenceQueryParser.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/queryParser/precedence/PrecedenceQueryParserConstants.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/queryParser/precedence/PrecedenceQueryParserTokenManager.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/queryParser/precedence/Token.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/java/org/apache/lucene/queryParser/precedence/TokenMgrError.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/test/org/apache/lucene/index/TestFieldNormModifier.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/test/org/apache/lucene/index/TestTermVectorAccessor.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/test/org/apache/lucene/misc/SweetSpotSimilarityTest.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/test/org/apache/lucene/misc/TestLengthNormModifier.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/test/org/apache/lucene/queryParser/analyzing/TestAnalyzingQueryParser.java (props changed)
lucene/java/trunk/contrib/miscellaneous/src/test/org/apache/lucene/queryParser/precedence/TestPrecedenceQueryParser.java (props changed)
lucene/java/trunk/contrib/queries/src/java/org/apache/lucene/search/BooleanFilter.java (contents, props changed)
lucene/java/trunk/contrib/queries/src/java/org/apache/lucene/search/BoostingQuery.java (contents, props changed)
lucene/java/trunk/contrib/queries/src/java/org/apache/lucene/search/DuplicateFilter.java (contents, props changed)
lucene/java/trunk/contrib/queries/src/java/org/apache/lucene/search/FilterClause.java (contents, props changed)
lucene/java/trunk/contrib/queries/src/java/org/apache/lucene/search/FuzzyLikeThisQuery.java (contents, props changed)
lucene/java/trunk/contrib/queries/src/java/org/apache/lucene/search/TermsFilter.java (contents, props changed)
lucene/java/trunk/contrib/queries/src/java/org/apache/lucene/search/similar/MoreLikeThis.java (contents, props changed)
lucene/java/trunk/contrib/queries/src/java/org/apache/lucene/search/similar/MoreLikeThisQuery.java (contents, props changed)
lucene/java/trunk/contrib/queries/src/java/org/apache/lucene/search/similar/SimilarityQueries.java (contents, props changed)
lucene/java/trunk/contrib/queries/src/test/org/apache/lucene/search/FuzzyLikeThisQueryTest.java (contents, props changed)
lucene/java/trunk/contrib/regex/src/java/org/apache/lucene/search/regex/JakartaRegexpCapabilities.java (props changed)
lucene/java/trunk/contrib/regex/src/java/org/apache/lucene/search/regex/JavaUtilRegexCapabilities.java (props changed)
lucene/java/trunk/contrib/regex/src/java/org/apache/lucene/search/regex/RegexCapabilities.java (props changed)
lucene/java/trunk/contrib/regex/src/java/org/apache/lucene/search/regex/RegexQuery.java (props changed)
lucene/java/trunk/contrib/regex/src/java/org/apache/lucene/search/regex/RegexQueryCapable.java (props changed)
lucene/java/trunk/contrib/regex/src/java/org/apache/lucene/search/regex/RegexTermEnum.java (props changed)
lucene/java/trunk/contrib/regex/src/java/org/apache/lucene/search/regex/SpanRegexQuery.java (props changed)
lucene/java/trunk/contrib/regex/src/java/org/apache/regexp/RegexpTunnel.java (props changed)
lucene/java/trunk/contrib/regex/src/test/org/apache/lucene/search/regex/TestRegexQuery.java (props changed)
lucene/java/trunk/contrib/regex/src/test/org/apache/lucene/search/regex/TestSpanRegexQuery.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/Among.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/SnowballProgram.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/TestApp.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/DanishStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/DutchStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/EnglishStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/FinnishStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/FrenchStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/German2Stemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/GermanStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/HungarianStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/ItalianStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/KpStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/LovinsStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/NorwegianStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/PorterStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/PortugueseStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/RomanianStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/RussianStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/SpanishStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/SwedishStemmer.java (props changed)
lucene/java/trunk/contrib/snowball/src/java/org/tartarus/snowball/ext/TurkishStemmer.java (props changed)
lucene/java/trunk/contrib/spellchecker/src/java/org/apache/lucene/search/spell/JaroWinklerDistance.java (props changed)
lucene/java/trunk/contrib/spellchecker/src/java/org/apache/lucene/search/spell/StringDistance.java (props changed)
lucene/java/trunk/contrib/spellchecker/src/test/org/apache/lucene/search/spell/TestJaroWinklerDistance.java (props changed)
lucene/java/trunk/contrib/spellchecker/src/test/org/apache/lucene/search/spell/TestLevenshteinDistance.java (props changed)
lucene/java/trunk/contrib/spellchecker/src/test/org/apache/lucene/search/spell/TestLuceneDictionary.java (props changed)
lucene/java/trunk/contrib/spellchecker/src/test/org/apache/lucene/search/spell/TestPlainTextDictionary.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/parser/CharStream.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/parser/FastCharStream.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/parser/ParseException.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/parser/QueryParser.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/parser/QueryParserConstants.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/parser/QueryParserTokenManager.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/parser/Token.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/parser/TokenMgrError.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/AndQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/BasicQueryFactory.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/ComposedQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/DistanceQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/DistanceSubQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/FieldsQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/NotQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/OrQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/SimpleTerm.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/SpanNearClauseFactory.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/SrndBooleanQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/SrndPrefixQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/SrndQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/SrndTermQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/SrndTruncQuery.java (props changed)
lucene/java/trunk/contrib/surround/src/java/org/apache/lucene/queryParser/surround/query/TooManyBasicQueries.java (props changed)
lucene/java/trunk/contrib/surround/src/test/org/apache/lucene/queryParser/surround/query/BooleanQueryTst.java (props changed)
lucene/java/trunk/contrib/surround/src/test/org/apache/lucene/queryParser/surround/query/ExceptionQueryTst.java (props changed)
lucene/java/trunk/contrib/surround/src/test/org/apache/lucene/queryParser/surround/query/SingleFieldTestDb.java (props changed)
lucene/java/trunk/contrib/surround/src/test/org/apache/lucene/queryParser/surround/query/Test01Exceptions.java (props changed)
lucene/java/trunk/contrib/surround/src/test/org/apache/lucene/queryParser/surround/query/Test02Boolean.java (props changed)
lucene/java/trunk/contrib/surround/src/test/org/apache/lucene/queryParser/surround/query/Test03Distance.java (props changed)
lucene/java/trunk/contrib/swing/src/java/org/apache/lucene/swing/models/ListSearcher.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/java/org/apache/lucene/swing/models/TableSearcher.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/BaseListModel.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/BaseTableModel.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/DataStore.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/ListSearcherSimulator.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/RestaurantInfo.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/TableSearcherSimulator.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/TestBasicList.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/TestBasicTable.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/TestSearchingList.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/TestSearchingTable.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/TestUpdatingList.java (contents, props changed)
lucene/java/trunk/contrib/swing/src/test/org/apache/lucene/swing/models/TestUpdatingTable.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/demo/java/org/apache/lucene/xmlparser/webdemo/FormBasedXmlQueryDemo.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/CoreParser.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/CorePlusExtensionsParser.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/DOMUtils.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/FilterBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/FilterBuilderFactory.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/ParserException.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/QueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/QueryBuilderFactory.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/QueryTemplateManager.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/BooleanFilterBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/BooleanQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/BoostingQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/CachedFilterBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/ConstantScoreQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/DuplicateFilterBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/FilteredQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/FuzzyLikeThisQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/LikeThisQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/MatchAllDocsQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/RangeFilterBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanBuilderBase.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanFirstBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanNearBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanNotBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanOrBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanOrTermsBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanQueryBuilderFactory.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/SpanTermBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermsFilterBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/TermsQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/java/org/apache/lucene/xmlparser/builders/UserInputQueryBuilder.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/test/org/apache/lucene/xmlparser/TestParser.java (contents, props changed)
lucene/java/trunk/contrib/xml-query-parser/src/test/org/apache/lucene/xmlparser/TestQueryTemplateManager.java (contents, props changed)
lucene/java/trunk/src/java/org/apache/lucene/util/ArrayUtil.java (props changed)
lucene/java/trunk/src/java/org/apache/lucene/util/cache/Cache.java (contents, props changed)
lucene/java/trunk/src/java/org/apache/lucene/util/cache/SimpleLRUCache.java (contents, props changed)
lucene/java/trunk/src/java/org/apache/lucene/util/cache/SimpleMapCache.java (contents, props changed)
lucene/java/trunk/src/test/org/apache/lucene/store/MockRAMDirectory.java (props changed)
lucene/java/trunk/src/test/org/apache/lucene/store/MockRAMOutputStream.java (props changed)
lucene/java/trunk/src/test/org/apache/lucene/store/TestLock.java (props changed)
lucene/java/trunk/src/test/org/apache/lucene/store/TestWindowsMMap.java (props changed)
lucene/java/trunk/src/test/org/apache/lucene/util/TestSmallFloat.java (contents, props changed)
lucene/java/trunk/src/test/org/apache/lucene/util/TestStringHelper.java (props changed)
lucene/java/trunk/src/test/org/apache/lucene/util/_TestUtil.java (props changed)
lucene/java/trunk/src/test/org/apache/lucene/util/cache/TestSimpleLRUCache.java (contents, props changed)
Modified: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java?rev=712922&r1=712921&r2=712922&view=diff
==============================================================================
--- lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java (original)
+++ lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java Mon Nov 10 18:35:46 2008
@@ -1,222 +1,222 @@
-package org.apache.lucene.analysis.el;
-
-/**
- * Copyright 2005 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-
-import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.analysis.StopFilter;
-import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.standard.StandardTokenizer;
-
-import java.io.Reader;
-import java.util.HashSet;
-import java.util.Map;
-import java.util.Set;
-
-/**
- * Analyzer for the Greek language. Supports an external list of stopwords (words
- * that will not be indexed at all).
- * A default set of stopwords is used unless an alternative list is specified.
- *
- */
-public final class GreekAnalyzer extends Analyzer
-{
- // the letters are indexes to the charset array (see GreekCharsets.java)
- private static char A = 6;
- private static char B = 7;
- private static char G = 8;
- private static char D = 9;
- private static char E = 10;
- private static char Z = 11;
- private static char H = 12;
- private static char TH = 13;
- private static char I = 14;
- private static char K = 15;
- private static char L = 16;
- private static char M = 17;
- private static char N = 18;
- private static char KS = 19;
- private static char O = 20;
- private static char P = 21;
- private static char R = 22;
- private static char S = 24; // skip final sigma
- private static char T = 25;
- private static char Y = 26;
- private static char F = 27;
- private static char X = 28;
- private static char PS = 29;
- private static char W = 30;
-
- /**
- * List of typical Greek stopwords.
- */
- private static char[][] GREEK_STOP_WORDS = {
- {O},
- {H},
- {T, O},
- {O, I},
- {T, A},
- {T, O, Y},
- {T, H, S},
- {T, W, N},
- {T, O, N},
- {T, H, N},
- {K, A, I},
- {K, I},
- {K},
- {E, I, M, A, I},
- {E, I, S, A, I},
- {E, I, N, A, I},
- {E, I, M, A, S, T, E},
- {E, I, S, T, E},
- {S, T, O},
- {S, T, O, N},
- {S, T, H},
- {S, T, H, N},
- {M, A},
- {A, L, L, A},
- {A, P, O},
- {G, I, A},
- {P, R, O, S},
- {M, E},
- {S, E},
- {W, S},
- {P, A, R, A},
- {A, N, T, I},
- {K, A, T, A},
- {M, E, T, A},
- {TH, A},
- {N, A},
- {D, E},
- {D, E, N},
- {M, H},
- {M, H, N},
- {E, P, I},
- {E, N, W},
- {E, A, N},
- {A, N},
- {T, O, T, E},
- {P, O, Y},
- {P, W, S},
- {P, O, I, O, S},
- {P, O, I, A},
- {P, O, I, O},
- {P, O, I, O, I},
- {P, O, I, E, S},
- {P, O, I, W, N},
- {P, O, I, O, Y, S},
- {A, Y, T, O, S},
- {A, Y, T, H},
- {A, Y, T, O},
- {A, Y, T, O, I},
- {A, Y, T, W, N},
- {A, Y, T, O, Y, S},
- {A, Y, T, E, S},
- {A, Y, T, A},
- {E, K, E, I, N, O, S},
- {E, K, E, I, N, H},
- {E, K, E, I, N, O},
- {E, K, E, I, N, O, I},
- {E, K, E, I, N, E, S},
- {E, K, E, I, N, A},
- {E, K, E, I, N, W, N},
- {E, K, E, I, N, O, Y, S},
- {O, P, W, S},
- {O, M, W, S},
- {I, S, W, S},
- {O, S, O},
- {O, T, I}
- };
-
- /**
- * Contains the stopwords used with the StopFilter.
- */
- private Set stopSet = new HashSet();
-
- /**
- * Charset for Greek letters.
- * Represents encoding for 24 lowercase Greek letters.
- * Predefined charsets can be taken from GreekCharSets class
- */
- private char[] charset;
-
- public GreekAnalyzer() {
- charset = GreekCharsets.UnicodeGreek;
- stopSet = StopFilter.makeStopSet(
- makeStopWords(GreekCharsets.UnicodeGreek));
- }
-
- /**
- * Builds an analyzer.
- */
- public GreekAnalyzer(char[] charset)
- {
- this.charset = charset;
- stopSet = StopFilter.makeStopSet(makeStopWords(charset));
- }
-
- /**
- * Builds an analyzer with the given stop words.
- */
- public GreekAnalyzer(char[] charset, String[] stopwords)
- {
- this.charset = charset;
- stopSet = StopFilter.makeStopSet(stopwords);
- }
-
- // Takes greek stop words and translates them to a String array, using
- // the given charset
- private static String[] makeStopWords(char[] charset)
- {
- String[] res = new String[GREEK_STOP_WORDS.length];
- for (int i = 0; i < res.length; i++)
- {
- char[] theStopWord = GREEK_STOP_WORDS[i];
- // translate the word,using the charset
- StringBuffer theWord = new StringBuffer();
- for (int j = 0; j < theStopWord.length; j++)
- {
- theWord.append(charset[theStopWord[j]]);
- }
- res[i] = theWord.toString();
- }
- return res;
- }
-
- /**
- * Builds an analyzer with the given stop words.
- */
- public GreekAnalyzer(char[] charset, Map stopwords)
- {
- this.charset = charset;
- stopSet = new HashSet(stopwords.keySet());
- }
-
- /**
- * Creates a TokenStream which tokenizes all the text in the provided Reader.
- *
- * @return A TokenStream build from a StandardTokenizer filtered with
- * GreekLowerCaseFilter and StopFilter
- */
- public TokenStream tokenStream(String fieldName, Reader reader)
- {
- TokenStream result = new StandardTokenizer(reader);
- result = new GreekLowerCaseFilter(result, charset);
- result = new StopFilter(result, stopSet);
- return result;
- }
-}
+package org.apache.lucene.analysis.el;
+
+/**
+ * Copyright 2005 The Apache Software Foundation
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.StopFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.standard.StandardTokenizer;
+
+import java.io.Reader;
+import java.util.HashSet;
+import java.util.Map;
+import java.util.Set;
+
+/**
+ * Analyzer for the Greek language. Supports an external list of stopwords (words
+ * that will not be indexed at all).
+ * A default set of stopwords is used unless an alternative list is specified.
+ *
+ */
+public final class GreekAnalyzer extends Analyzer
+{
+ // the letters are indexes to the charset array (see GreekCharsets.java)
+ private static char A = 6;
+ private static char B = 7;
+ private static char G = 8;
+ private static char D = 9;
+ private static char E = 10;
+ private static char Z = 11;
+ private static char H = 12;
+ private static char TH = 13;
+ private static char I = 14;
+ private static char K = 15;
+ private static char L = 16;
+ private static char M = 17;
+ private static char N = 18;
+ private static char KS = 19;
+ private static char O = 20;
+ private static char P = 21;
+ private static char R = 22;
+ private static char S = 24; // skip final sigma
+ private static char T = 25;
+ private static char Y = 26;
+ private static char F = 27;
+ private static char X = 28;
+ private static char PS = 29;
+ private static char W = 30;
+
+ /**
+ * List of typical Greek stopwords.
+ */
+ private static char[][] GREEK_STOP_WORDS = {
+ {O},
+ {H},
+ {T, O},
+ {O, I},
+ {T, A},
+ {T, O, Y},
+ {T, H, S},
+ {T, W, N},
+ {T, O, N},
+ {T, H, N},
+ {K, A, I},
+ {K, I},
+ {K},
+ {E, I, M, A, I},
+ {E, I, S, A, I},
+ {E, I, N, A, I},
+ {E, I, M, A, S, T, E},
+ {E, I, S, T, E},
+ {S, T, O},
+ {S, T, O, N},
+ {S, T, H},
+ {S, T, H, N},
+ {M, A},
+ {A, L, L, A},
+ {A, P, O},
+ {G, I, A},
+ {P, R, O, S},
+ {M, E},
+ {S, E},
+ {W, S},
+ {P, A, R, A},
+ {A, N, T, I},
+ {K, A, T, A},
+ {M, E, T, A},
+ {TH, A},
+ {N, A},
+ {D, E},
+ {D, E, N},
+ {M, H},
+ {M, H, N},
+ {E, P, I},
+ {E, N, W},
+ {E, A, N},
+ {A, N},
+ {T, O, T, E},
+ {P, O, Y},
+ {P, W, S},
+ {P, O, I, O, S},
+ {P, O, I, A},
+ {P, O, I, O},
+ {P, O, I, O, I},
+ {P, O, I, E, S},
+ {P, O, I, W, N},
+ {P, O, I, O, Y, S},
+ {A, Y, T, O, S},
+ {A, Y, T, H},
+ {A, Y, T, O},
+ {A, Y, T, O, I},
+ {A, Y, T, W, N},
+ {A, Y, T, O, Y, S},
+ {A, Y, T, E, S},
+ {A, Y, T, A},
+ {E, K, E, I, N, O, S},
+ {E, K, E, I, N, H},
+ {E, K, E, I, N, O},
+ {E, K, E, I, N, O, I},
+ {E, K, E, I, N, E, S},
+ {E, K, E, I, N, A},
+ {E, K, E, I, N, W, N},
+ {E, K, E, I, N, O, Y, S},
+ {O, P, W, S},
+ {O, M, W, S},
+ {I, S, W, S},
+ {O, S, O},
+ {O, T, I}
+ };
+
+ /**
+ * Contains the stopwords used with the StopFilter.
+ */
+ private Set stopSet = new HashSet();
+
+ /**
+ * Charset for Greek letters.
+ * Represents encoding for 24 lowercase Greek letters.
+ * Predefined charsets can be taken from GreekCharSets class
+ */
+ private char[] charset;
+
+ public GreekAnalyzer() {
+ charset = GreekCharsets.UnicodeGreek;
+ stopSet = StopFilter.makeStopSet(
+ makeStopWords(GreekCharsets.UnicodeGreek));
+ }
+
+ /**
+ * Builds an analyzer.
+ */
+ public GreekAnalyzer(char[] charset)
+ {
+ this.charset = charset;
+ stopSet = StopFilter.makeStopSet(makeStopWords(charset));
+ }
+
+ /**
+ * Builds an analyzer with the given stop words.
+ */
+ public GreekAnalyzer(char[] charset, String[] stopwords)
+ {
+ this.charset = charset;
+ stopSet = StopFilter.makeStopSet(stopwords);
+ }
+
+ // Takes greek stop words and translates them to a String array, using
+ // the given charset
+ private static String[] makeStopWords(char[] charset)
+ {
+ String[] res = new String[GREEK_STOP_WORDS.length];
+ for (int i = 0; i < res.length; i++)
+ {
+ char[] theStopWord = GREEK_STOP_WORDS[i];
+ // translate the word,using the charset
+ StringBuffer theWord = new StringBuffer();
+ for (int j = 0; j < theStopWord.length; j++)
+ {
+ theWord.append(charset[theStopWord[j]]);
+ }
+ res[i] = theWord.toString();
+ }
+ return res;
+ }
+
+ /**
+ * Builds an analyzer with the given stop words.
+ */
+ public GreekAnalyzer(char[] charset, Map stopwords)
+ {
+ this.charset = charset;
+ stopSet = new HashSet(stopwords.keySet());
+ }
+
+ /**
+ * Creates a TokenStream which tokenizes all the text in the provided Reader.
+ *
+ * @return A TokenStream build from a StandardTokenizer filtered with
+ * GreekLowerCaseFilter and StopFilter
+ */
+ public TokenStream tokenStream(String fieldName, Reader reader)
+ {
+ TokenStream result = new StandardTokenizer(reader);
+ result = new GreekLowerCaseFilter(result, charset);
+ result = new StopFilter(result, stopSet);
+ return result;
+ }
+}
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java
------------------------------------------------------------------------------
svn:eol-style = native
Modified: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekCharsets.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekCharsets.java?rev=712922&r1=712921&r2=712922&view=diff
==============================================================================
--- lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekCharsets.java (original)
+++ lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekCharsets.java Mon Nov 10 18:35:46 2008
@@ -1,480 +1,480 @@
-package org.apache.lucene.analysis.el;
-
-/**
- * Copyright 2005 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-/**
- * GreekCharsets class contains encodings schemes (charsets) and toLowerCase() method implementation
- * for greek characters in Unicode, ISO-8859-7 and Microsoft Windows CP1253.
- * Each encoding scheme contains lowercase (positions 0-35) and uppercase (position 36-68) characters,
- * including accented ones. One should be able to add other encoding schemes (see RFC 1947) by adding
- * the definition of a new charset as well as the required logic in the toLowerCase() method.
- *
- */
-public class GreekCharsets
-{
- // Unicode Greek charset
- public static char[] UnicodeGreek = {
- // lower case
- '\u0390',
- '\u03AC',
- '\u03AD',
- '\u03AE',
- '\u03AF',
- '\u03B0',
- '\u03B1',
- '\u03B2',
- '\u03B3',
- '\u03B4',
- '\u03B5',
- '\u03B6',
- '\u03B7',
- '\u03B8',
- '\u03B9',
- '\u03BA',
- '\u03BB',
- '\u03BC',
- '\u03BD',
- '\u03BE',
- '\u03BF',
- '\u03C0',
- '\u03C1',
- '\u03C2',
- '\u03C3',
- '\u03C4',
- '\u03C5',
- '\u03C6',
- '\u03C7',
- '\u03C8',
- '\u03C9',
- '\u03CA',
- '\u03CB',
- '\u03CC',
- '\u03CD',
- '\u03CE',
- // upper case
- '\u0386',
- '\u0388',
- '\u0389',
- '\u038A',
- '\u038C',
- '\u038E',
- '\u038F',
- '\u0391',
- '\u0392',
- '\u0393',
- '\u0394',
- '\u0395',
- '\u0396',
- '\u0397',
- '\u0398',
- '\u0399',
- '\u039A',
- '\u039B',
- '\u039C',
- '\u039D',
- '\u039E',
- '\u039F',
- '\u03A0',
- '\u03A1',
- '\u03A3',
- '\u03A4',
- '\u03A5',
- '\u03A6',
- '\u03A7',
- '\u03A8',
- '\u03A9',
- '\u03AA',
- '\u03AB'
- };
-
- // ISO-8859-7 charset (ELOT-928)
- public static char[] ISO = {
- // lower case
- 0xc0,
- 0xdc,
- 0xdd,
- 0xde,
- 0xdf,
- 0xe0,
- 0xe1,
- 0xe2,
- 0xe3,
- 0xe4,
- 0xe5,
- 0xe6,
- 0xe7,
- 0xe8,
- 0xe9,
- 0xea,
- 0xeb,
- 0xec,
- 0xed,
- 0xee,
- 0xef,
- 0xf0,
- 0xf1,
- 0xf2,
- 0xf3,
- 0xf4,
- 0xf5,
- 0xf6,
- 0xf7,
- 0xf8,
- 0xf9,
- 0xfa,
- 0xfb,
- 0xfc,
- 0xfd,
- 0xfe,
- // upper case
- 0xb6,
- 0xb8,
- 0xb9,
- 0xba,
- 0xbc,
- 0xbe,
- 0xbf,
- 0xc1,
- 0xc2,
- 0xc3,
- 0xc4,
- 0xc5,
- 0xc6,
- 0xc7,
- 0xc8,
- 0xc9,
- 0xca,
- 0xcb,
- 0xcc,
- 0xcd,
- 0xce,
- 0xcf,
- 0xd0,
- 0xd1,
- 0xd3,
- 0xd4,
- 0xd5,
- 0xd6,
- 0xd7,
- 0xd8,
- 0xd9,
- 0xda,
- 0xdb
- };
-
- // CP1253 charset
- public static char[] CP1253 = {
- // lower case
- 0xc0,
- 0xdc,
- 0xdd,
- 0xde,
- 0xdf,
- 0xe0,
- 0xe1,
- 0xe2,
- 0xe3,
- 0xe4,
- 0xe5,
- 0xe6,
- 0xe7,
- 0xe8,
- 0xe9,
- 0xea,
- 0xeb,
- 0xec,
- 0xed,
- 0xee,
- 0xef,
- 0xf0,
- 0xf1,
- 0xf2,
- 0xf3,
- 0xf4,
- 0xf5,
- 0xf6,
- 0xf7,
- 0xf8,
- 0xf9,
- 0xfa,
- 0xfb,
- 0xfc,
- 0xfd,
- 0xfe,
- // upper case
- 0xa2,
- 0xb8,
- 0xb9,
- 0xba,
- 0xbc,
- 0xbe,
- 0xbf,
- 0xc1,
- 0xc2,
- 0xc3,
- 0xc4,
- 0xc5,
- 0xc6,
- 0xc7,
- 0xc8,
- 0xc9,
- 0xca,
- 0xcb,
- 0xcc,
- 0xcd,
- 0xce,
- 0xcf,
- 0xd0,
- 0xd1,
- 0xd3,
- 0xd4,
- 0xd5,
- 0xd6,
- 0xd7,
- 0xd8,
- 0xd9,
- 0xda,
- 0xdb
- };
-
- public static char toLowerCase(char letter, char[] charset)
- {
- if (charset == UnicodeGreek) {
- // First deal with lower case, not accented letters
- if (letter >= '\u03B1' && letter <= '\u03C9')
- {
- // Special case 'small final sigma', where we return 'small sigma'
- if (letter == '\u03C2') {
- return '\u03C3';
- } else {
- return letter;
- }
- }
- // Then deal with lower case, accented letters
- // alpha with acute
- if (letter == '\u03AC') {
- return '\u03B1';
- }
- // epsilon with acute
- if (letter == '\u03AD') {
- return '\u03B5';
- }
- // eta with acute
- if (letter == '\u03AE') {
- return '\u03B7';
- }
- // iota with acute, iota with diaeresis, iota with acute and diaeresis
- if (letter == '\u03AF' || letter == '\u03CA' || letter == '\u0390') {
- return '\u03B9';
- }
- // upsilon with acute, upsilon with diaeresis, upsilon with acute and diaeresis
- if (letter == '\u03CD' || letter == '\u03CB' || letter == '\u03B0') {
- return '\u03C5';
- }
- // omicron with acute
- if (letter == '\u03CC') {
- return '\u03BF';
- }
- // omega with acute
- if (letter == '\u03CE') {
- return '\u03C9';
- }
- // After that, deal with upper case, not accented letters
- if (letter >= '\u0391' && letter <= '\u03A9')
- {
- return (char) (letter + 32);
- }
- // Finally deal with upper case, accented letters
- // alpha with acute
- if (letter == '\u0386') {
- return '\u03B1';
- }
- // epsilon with acute
- if (letter == '\u0388') {
- return '\u03B5';
- }
- // eta with acute
- if (letter == '\u0389') {
- return '\u03B7';
- }
- // iota with acute, iota with diaeresis
- if (letter == '\u038A' || letter == '\u03AA') {
- return '\u03B9';
- }
- // upsilon with acute, upsilon with diaeresis
- if (letter == '\u038E' || letter == '\u03AB') {
- return '\u03C5';
- }
- // omicron with acute
- if (letter == '\u038C') {
- return '\u03BF';
- }
- // omega with acute
- if (letter == '\u038F') {
- return '\u03C9';
- }
- } else if (charset == ISO) {
- // First deal with lower case, not accented letters
- if (letter >= 0xe1 && letter <= 0xf9)
- {
- // Special case 'small final sigma', where we return 'small sigma'
- if (letter == 0xf2) {
- return 0xf3;
- } else {
- return letter;
- }
- }
- // Then deal with lower case, accented letters
- // alpha with acute
- if (letter == 0xdc) {
- return 0xe1;
- }
- // epsilon with acute
- if (letter == 0xdd) {
- return 0xe5;
- }
- // eta with acute
- if (letter == 0xde) {
- return 0xe7;
- }
- // iota with acute, iota with diaeresis, iota with acute and diaeresis
- if (letter == 0xdf || letter == 0xfa || letter == 0xc0) {
- return '\u03B9';
- }
- // upsilon with acute, upsilon with diaeresis, upsilon with acute and diaeresis
- if (letter == 0xfd || letter == 0xfb || letter == 0xe0) {
- return 0xf5;
- }
- // omicron with acute
- if (letter == 0xfc) {
- return 0xef;
- }
- // omega with acute
- if (letter == 0xfe) {
- return 0xf9;
- }
- // After that, deal with upper case, not accented letters
- if (letter >= 0xc1 && letter <= 0xd9) {
- return (char) (letter + 32);
- }
- // Finally deal with upper case, accented letters
- // alpha with acute
- if (letter == 0xb6) {
- return 0xe1;
- }
- // epsilon with acute
- if (letter == 0xb8) {
- return 0xe5;
- }
- // eta with acute
- if (letter == 0xb9) {
- return 0xe7;
- }
- // iota with acute, iota with diaeresis
- if (letter == 0xba || letter == 0xda) {
- return 0xe9;
- }
- // upsilon with acute, upsilon with diaeresis
- if (letter == 0xbe || letter == 0xdb) {
- return 0xf5;
- }
- // omicron with acute
- if (letter == 0xbc) {
- return 0xef;
- }
- // omega with acute
- if (letter == 0xbf) {
- return 0xf9;
- }
- } else if (charset == CP1253) {
- // First deal with lower case, not accented letters
- if (letter >= 0xe1 && letter <= 0xf9)
- {
- // Special case 'small final sigma', where we return 'small sigma'
- if (letter == 0xf2) {
- return 0xf3;
- } else {
- return letter;
- }
- }
- // Then deal with lower case, accented letters
- // alpha with acute
- if (letter == 0xdc) {
- return 0xe1;
- }
- // epsilon with acute
- if (letter == 0xdd) {
- return 0xe5;
- }
- // eta with acute
- if (letter == 0xde) {
- return 0xe7;
- }
- // iota with acute, iota with diaeresis, iota with acute and diaeresis
- if (letter == 0xdf || letter == 0xfa || letter == 0xc0) {
- return '\u03B9';
- }
- // upsilon with acute, upsilon with diaeresis, upsilon with acute and diaeresis
- if (letter == 0xfd || letter == 0xfb || letter == 0xe0) {
- return 0xf5;
- }
- // omicron with acute
- if (letter == 0xfc) {
- return 0xef;
- }
- // omega with acute
- if (letter == 0xfe) {
- return 0xf9;
- }
- // After that, deal with upper case, not accented letters
- if (letter >= 0xc1 && letter <= 0xd9) {
- return (char) (letter + 32);
- }
- // Finally deal with upper case, accented letters
- // alpha with acute
- if (letter == 0xa2) {
- return 0xe1;
- }
- // epsilon with acute
- if (letter == 0xb8) {
- return 0xe5;
- }
- // eta with acute
- if (letter == 0xb9) {
- return 0xe7;
- }
- // iota with acute, iota with diaeresis
- if (letter == 0xba || letter == 0xda) {
- return 0xe9;
- }
- // upsilon with acute, upsilon with diaeresis
- if (letter == 0xbe || letter == 0xdb) {
- return 0xf5;
- }
- // omicron with acute
- if (letter == 0xbc) {
- return 0xef;
- }
- // omega with acute
- if (letter == 0xbf) {
- return 0xf9;
- }
- }
-
- return Character.toLowerCase(letter);
- }
-}
+package org.apache.lucene.analysis.el;
+
+/**
+ * Copyright 2005 The Apache Software Foundation
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+/**
+ * GreekCharsets class contains encodings schemes (charsets) and toLowerCase() method implementation
+ * for greek characters in Unicode, ISO-8859-7 and Microsoft Windows CP1253.
+ * Each encoding scheme contains lowercase (positions 0-35) and uppercase (position 36-68) characters,
+ * including accented ones. One should be able to add other encoding schemes (see RFC 1947) by adding
+ * the definition of a new charset as well as the required logic in the toLowerCase() method.
+ *
+ */
+public class GreekCharsets
+{
+ // Unicode Greek charset
+ public static char[] UnicodeGreek = {
+ // lower case
+ '\u0390',
+ '\u03AC',
+ '\u03AD',
+ '\u03AE',
+ '\u03AF',
+ '\u03B0',
+ '\u03B1',
+ '\u03B2',
+ '\u03B3',
+ '\u03B4',
+ '\u03B5',
+ '\u03B6',
+ '\u03B7',
+ '\u03B8',
+ '\u03B9',
+ '\u03BA',
+ '\u03BB',
+ '\u03BC',
+ '\u03BD',
+ '\u03BE',
+ '\u03BF',
+ '\u03C0',
+ '\u03C1',
+ '\u03C2',
+ '\u03C3',
+ '\u03C4',
+ '\u03C5',
+ '\u03C6',
+ '\u03C7',
+ '\u03C8',
+ '\u03C9',
+ '\u03CA',
+ '\u03CB',
+ '\u03CC',
+ '\u03CD',
+ '\u03CE',
+ // upper case
+ '\u0386',
+ '\u0388',
+ '\u0389',
+ '\u038A',
+ '\u038C',
+ '\u038E',
+ '\u038F',
+ '\u0391',
+ '\u0392',
+ '\u0393',
+ '\u0394',
+ '\u0395',
+ '\u0396',
+ '\u0397',
+ '\u0398',
+ '\u0399',
+ '\u039A',
+ '\u039B',
+ '\u039C',
+ '\u039D',
+ '\u039E',
+ '\u039F',
+ '\u03A0',
+ '\u03A1',
+ '\u03A3',
+ '\u03A4',
+ '\u03A5',
+ '\u03A6',
+ '\u03A7',
+ '\u03A8',
+ '\u03A9',
+ '\u03AA',
+ '\u03AB'
+ };
+
+ // ISO-8859-7 charset (ELOT-928)
+ public static char[] ISO = {
+ // lower case
+ 0xc0,
+ 0xdc,
+ 0xdd,
+ 0xde,
+ 0xdf,
+ 0xe0,
+ 0xe1,
+ 0xe2,
+ 0xe3,
+ 0xe4,
+ 0xe5,
+ 0xe6,
+ 0xe7,
+ 0xe8,
+ 0xe9,
+ 0xea,
+ 0xeb,
+ 0xec,
+ 0xed,
+ 0xee,
+ 0xef,
+ 0xf0,
+ 0xf1,
+ 0xf2,
+ 0xf3,
+ 0xf4,
+ 0xf5,
+ 0xf6,
+ 0xf7,
+ 0xf8,
+ 0xf9,
+ 0xfa,
+ 0xfb,
+ 0xfc,
+ 0xfd,
+ 0xfe,
+ // upper case
+ 0xb6,
+ 0xb8,
+ 0xb9,
+ 0xba,
+ 0xbc,
+ 0xbe,
+ 0xbf,
+ 0xc1,
+ 0xc2,
+ 0xc3,
+ 0xc4,
+ 0xc5,
+ 0xc6,
+ 0xc7,
+ 0xc8,
+ 0xc9,
+ 0xca,
+ 0xcb,
+ 0xcc,
+ 0xcd,
+ 0xce,
+ 0xcf,
+ 0xd0,
+ 0xd1,
+ 0xd3,
+ 0xd4,
+ 0xd5,
+ 0xd6,
+ 0xd7,
+ 0xd8,
+ 0xd9,
+ 0xda,
+ 0xdb
+ };
+
+ // CP1253 charset
+ public static char[] CP1253 = {
+ // lower case
+ 0xc0,
+ 0xdc,
+ 0xdd,
+ 0xde,
+ 0xdf,
+ 0xe0,
+ 0xe1,
+ 0xe2,
+ 0xe3,
+ 0xe4,
+ 0xe5,
+ 0xe6,
+ 0xe7,
+ 0xe8,
+ 0xe9,
+ 0xea,
+ 0xeb,
+ 0xec,
+ 0xed,
+ 0xee,
+ 0xef,
+ 0xf0,
+ 0xf1,
+ 0xf2,
+ 0xf3,
+ 0xf4,
+ 0xf5,
+ 0xf6,
+ 0xf7,
+ 0xf8,
+ 0xf9,
+ 0xfa,
+ 0xfb,
+ 0xfc,
+ 0xfd,
+ 0xfe,
+ // upper case
+ 0xa2,
+ 0xb8,
+ 0xb9,
+ 0xba,
+ 0xbc,
+ 0xbe,
+ 0xbf,
+ 0xc1,
+ 0xc2,
+ 0xc3,
+ 0xc4,
+ 0xc5,
+ 0xc6,
+ 0xc7,
+ 0xc8,
+ 0xc9,
+ 0xca,
+ 0xcb,
+ 0xcc,
+ 0xcd,
+ 0xce,
+ 0xcf,
+ 0xd0,
+ 0xd1,
+ 0xd3,
+ 0xd4,
+ 0xd5,
+ 0xd6,
+ 0xd7,
+ 0xd8,
+ 0xd9,
+ 0xda,
+ 0xdb
+ };
+
+ public static char toLowerCase(char letter, char[] charset)
+ {
+ if (charset == UnicodeGreek) {
+ // First deal with lower case, not accented letters
+ if (letter >= '\u03B1' && letter <= '\u03C9')
+ {
+ // Special case 'small final sigma', where we return 'small sigma'
+ if (letter == '\u03C2') {
+ return '\u03C3';
+ } else {
+ return letter;
+ }
+ }
+ // Then deal with lower case, accented letters
+ // alpha with acute
+ if (letter == '\u03AC') {
+ return '\u03B1';
+ }
+ // epsilon with acute
+ if (letter == '\u03AD') {
+ return '\u03B5';
+ }
+ // eta with acute
+ if (letter == '\u03AE') {
+ return '\u03B7';
+ }
+ // iota with acute, iota with diaeresis, iota with acute and diaeresis
+ if (letter == '\u03AF' || letter == '\u03CA' || letter == '\u0390') {
+ return '\u03B9';
+ }
+ // upsilon with acute, upsilon with diaeresis, upsilon with acute and diaeresis
+ if (letter == '\u03CD' || letter == '\u03CB' || letter == '\u03B0') {
+ return '\u03C5';
+ }
+ // omicron with acute
+ if (letter == '\u03CC') {
+ return '\u03BF';
+ }
+ // omega with acute
+ if (letter == '\u03CE') {
+ return '\u03C9';
+ }
+ // After that, deal with upper case, not accented letters
+ if (letter >= '\u0391' && letter <= '\u03A9')
+ {
+ return (char) (letter + 32);
+ }
+ // Finally deal with upper case, accented letters
+ // alpha with acute
+ if (letter == '\u0386') {
+ return '\u03B1';
+ }
+ // epsilon with acute
+ if (letter == '\u0388') {
+ return '\u03B5';
+ }
+ // eta with acute
+ if (letter == '\u0389') {
+ return '\u03B7';
+ }
+ // iota with acute, iota with diaeresis
+ if (letter == '\u038A' || letter == '\u03AA') {
+ return '\u03B9';
+ }
+ // upsilon with acute, upsilon with diaeresis
+ if (letter == '\u038E' || letter == '\u03AB') {
+ return '\u03C5';
+ }
+ // omicron with acute
+ if (letter == '\u038C') {
+ return '\u03BF';
+ }
+ // omega with acute
+ if (letter == '\u038F') {
+ return '\u03C9';
+ }
+ } else if (charset == ISO) {
+ // First deal with lower case, not accented letters
+ if (letter >= 0xe1 && letter <= 0xf9)
+ {
+ // Special case 'small final sigma', where we return 'small sigma'
+ if (letter == 0xf2) {
+ return 0xf3;
+ } else {
+ return letter;
+ }
+ }
+ // Then deal with lower case, accented letters
+ // alpha with acute
+ if (letter == 0xdc) {
+ return 0xe1;
+ }
+ // epsilon with acute
+ if (letter == 0xdd) {
+ return 0xe5;
+ }
+ // eta with acute
+ if (letter == 0xde) {
+ return 0xe7;
+ }
+ // iota with acute, iota with diaeresis, iota with acute and diaeresis
+ if (letter == 0xdf || letter == 0xfa || letter == 0xc0) {
+ return '\u03B9';
+ }
+ // upsilon with acute, upsilon with diaeresis, upsilon with acute and diaeresis
+ if (letter == 0xfd || letter == 0xfb || letter == 0xe0) {
+ return 0xf5;
+ }
+ // omicron with acute
+ if (letter == 0xfc) {
+ return 0xef;
+ }
+ // omega with acute
+ if (letter == 0xfe) {
+ return 0xf9;
+ }
+ // After that, deal with upper case, not accented letters
+ if (letter >= 0xc1 && letter <= 0xd9) {
+ return (char) (letter + 32);
+ }
+ // Finally deal with upper case, accented letters
+ // alpha with acute
+ if (letter == 0xb6) {
+ return 0xe1;
+ }
+ // epsilon with acute
+ if (letter == 0xb8) {
+ return 0xe5;
+ }
+ // eta with acute
+ if (letter == 0xb9) {
+ return 0xe7;
+ }
+ // iota with acute, iota with diaeresis
+ if (letter == 0xba || letter == 0xda) {
+ return 0xe9;
+ }
+ // upsilon with acute, upsilon with diaeresis
+ if (letter == 0xbe || letter == 0xdb) {
+ return 0xf5;
+ }
+ // omicron with acute
+ if (letter == 0xbc) {
+ return 0xef;
+ }
+ // omega with acute
+ if (letter == 0xbf) {
+ return 0xf9;
+ }
+ } else if (charset == CP1253) {
+ // First deal with lower case, not accented letters
+ if (letter >= 0xe1 && letter <= 0xf9)
+ {
+ // Special case 'small final sigma', where we return 'small sigma'
+ if (letter == 0xf2) {
+ return 0xf3;
+ } else {
+ return letter;
+ }
+ }
+ // Then deal with lower case, accented letters
+ // alpha with acute
+ if (letter == 0xdc) {
+ return 0xe1;
+ }
+ // epsilon with acute
+ if (letter == 0xdd) {
+ return 0xe5;
+ }
+ // eta with acute
+ if (letter == 0xde) {
+ return 0xe7;
+ }
+ // iota with acute, iota with diaeresis, iota with acute and diaeresis
+ if (letter == 0xdf || letter == 0xfa || letter == 0xc0) {
+ return '\u03B9';
+ }
+ // upsilon with acute, upsilon with diaeresis, upsilon with acute and diaeresis
+ if (letter == 0xfd || letter == 0xfb || letter == 0xe0) {
+ return 0xf5;
+ }
+ // omicron with acute
+ if (letter == 0xfc) {
+ return 0xef;
+ }
+ // omega with acute
+ if (letter == 0xfe) {
+ return 0xf9;
+ }
+ // After that, deal with upper case, not accented letters
+ if (letter >= 0xc1 && letter <= 0xd9) {
+ return (char) (letter + 32);
+ }
+ // Finally deal with upper case, accented letters
+ // alpha with acute
+ if (letter == 0xa2) {
+ return 0xe1;
+ }
+ // epsilon with acute
+ if (letter == 0xb8) {
+ return 0xe5;
+ }
+ // eta with acute
+ if (letter == 0xb9) {
+ return 0xe7;
+ }
+ // iota with acute, iota with diaeresis
+ if (letter == 0xba || letter == 0xda) {
+ return 0xe9;
+ }
+ // upsilon with acute, upsilon with diaeresis
+ if (letter == 0xbe || letter == 0xdb) {
+ return 0xf5;
+ }
+ // omicron with acute
+ if (letter == 0xbc) {
+ return 0xef;
+ }
+ // omega with acute
+ if (letter == 0xbf) {
+ return 0xf9;
+ }
+ }
+
+ return Character.toLowerCase(letter);
+ }
+}
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekCharsets.java
------------------------------------------------------------------------------
svn:eol-style = native
Modified: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekLowerCaseFilter.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekLowerCaseFilter.java?rev=712922&r1=712921&r2=712922&view=diff
==============================================================================
--- lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekLowerCaseFilter.java (original)
+++ lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekLowerCaseFilter.java Mon Nov 10 18:35:46 2008
@@ -1,53 +1,53 @@
-package org.apache.lucene.analysis.el;
-
-/**
- * Copyright 2005 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-import org.apache.lucene.analysis.TokenFilter;
-import org.apache.lucene.analysis.Token;
-import org.apache.lucene.analysis.TokenStream;
-
-/**
- * Normalizes token text to lower case, analyzing given ("greek") charset.
- *
- */
-public final class GreekLowerCaseFilter extends TokenFilter
-{
- char[] charset;
-
- public GreekLowerCaseFilter(TokenStream in, char[] charset)
- {
- super(in);
- this.charset = charset;
- }
-
- public final Token next(final Token reusableToken) throws java.io.IOException
- {
- assert reusableToken != null;
- Token nextToken = input.next(reusableToken);
-
- if (nextToken == null)
- return null;
-
- char[] chArray = nextToken.termBuffer();
- int chLen = nextToken.termLength();
- for (int i = 0; i < chLen; i++)
- {
- chArray[i] = GreekCharsets.toLowerCase(chArray[i], charset);
- }
- return nextToken;
- }
-}
+package org.apache.lucene.analysis.el;
+
+/**
+ * Copyright 2005 The Apache Software Foundation
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.Token;
+import org.apache.lucene.analysis.TokenStream;
+
+/**
+ * Normalizes token text to lower case, analyzing given ("greek") charset.
+ *
+ */
+public final class GreekLowerCaseFilter extends TokenFilter
+{
+ char[] charset;
+
+ public GreekLowerCaseFilter(TokenStream in, char[] charset)
+ {
+ super(in);
+ this.charset = charset;
+ }
+
+ public final Token next(final Token reusableToken) throws java.io.IOException
+ {
+ assert reusableToken != null;
+ Token nextToken = input.next(reusableToken);
+
+ if (nextToken == null)
+ return null;
+
+ char[] chArray = nextToken.termBuffer();
+ int chLen = nextToken.termLength();
+ for (int i = 0; i < chLen; i++)
+ {
+ chArray[i] = GreekCharsets.toLowerCase(chArray[i], charset);
+ }
+ return nextToken;
+ }
+}
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/el/GreekLowerCaseFilter.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/fr/ElisionFilter.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/miscellaneous/EmptyTokenStream.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/miscellaneous/PrefixAndSuffixAwareTokenFilter.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/miscellaneous/PrefixAwareTokenFilter.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/miscellaneous/SingleTokenTokenStream.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/payloads/PayloadHelper.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/shingle/ShingleMatrixFilter.java
------------------------------------------------------------------------------
svn:eol-style = native
Modified: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java?rev=712922&r1=712921&r2=712922&view=diff
==============================================================================
--- lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java (original)
+++ lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java Mon Nov 10 18:35:46 2008
@@ -1,39 +1,39 @@
-package org.apache.lucene.analysis.th;
-
-/**
- * Copyright 2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-import java.io.Reader;
-import org.apache.lucene.analysis.Analyzer;
-import org.apache.lucene.analysis.StopAnalyzer;
-import org.apache.lucene.analysis.StopFilter;
-import org.apache.lucene.analysis.TokenStream;
-import org.apache.lucene.analysis.standard.StandardFilter;
-import org.apache.lucene.analysis.standard.StandardTokenizer;
-
-/**
- * Analyzer for Thai language. It uses java.text.BreakIterator to break words.
- * @version 0.2
- */
-public class ThaiAnalyzer extends Analyzer {
- public TokenStream tokenStream(String fieldName, Reader reader) {
- TokenStream ts = new StandardTokenizer(reader);
- ts = new StandardFilter(ts);
- ts = new ThaiWordFilter(ts);
- ts = new StopFilter(ts, StopAnalyzer.ENGLISH_STOP_WORDS);
- return ts;
- }
-}
+package org.apache.lucene.analysis.th;
+
+/**
+ * Copyright 2006 The Apache Software Foundation
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.Reader;
+import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.StopAnalyzer;
+import org.apache.lucene.analysis.StopFilter;
+import org.apache.lucene.analysis.TokenStream;
+import org.apache.lucene.analysis.standard.StandardFilter;
+import org.apache.lucene.analysis.standard.StandardTokenizer;
+
+/**
+ * Analyzer for Thai language. It uses java.text.BreakIterator to break words.
+ * @version 0.2
+ */
+public class ThaiAnalyzer extends Analyzer {
+ public TokenStream tokenStream(String fieldName, Reader reader) {
+ TokenStream ts = new StandardTokenizer(reader);
+ ts = new StandardFilter(ts);
+ ts = new ThaiWordFilter(ts);
+ ts = new StopFilter(ts, StopAnalyzer.ENGLISH_STOP_WORDS);
+ return ts;
+ }
+}
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java
------------------------------------------------------------------------------
svn:eol-style = native
Modified: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java?rev=712922&r1=712921&r2=712922&view=diff
==============================================================================
--- lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java (original)
+++ lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java Mon Nov 10 18:35:46 2008
@@ -1,77 +1,77 @@
-package org.apache.lucene.analysis.th;
-
-/**
- * Copyright 2006 The Apache Software Foundation
- *
- * Licensed under the Apache License, Version 2.0 (the "License");
- * you may not use this file except in compliance with the License.
- * You may obtain a copy of the License at
- *
- * http://www.apache.org/licenses/LICENSE-2.0
- *
- * Unless required by applicable law or agreed to in writing, software
- * distributed under the License is distributed on an "AS IS" BASIS,
- * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
- * See the License for the specific language governing permissions and
- * limitations under the License.
- */
-
-import java.io.IOException;
-import java.util.Locale;
-import java.lang.Character.UnicodeBlock;
-import org.apache.lucene.analysis.Token;
-import org.apache.lucene.analysis.TokenFilter;
-import org.apache.lucene.analysis.TokenStream;
-import java.text.BreakIterator;
-
-/**
- * TokenFilter that use java.text.BreakIterator to break each
- * Token that is Thai into separate Token(s) for each Thai word.
- * @version 0.2
- */
-public class ThaiWordFilter extends TokenFilter {
-
- private BreakIterator breaker = null;
- private Token thaiToken = null;
-
- public ThaiWordFilter(TokenStream input) {
- super(input);
- breaker = BreakIterator.getWordInstance(new Locale("th"));
- }
-
- public Token next(final Token reusableToken) throws IOException {
- assert reusableToken != null;
- if (thaiToken != null) {
- int start = breaker.current();
- int end = breaker.next();
- if (end != BreakIterator.DONE) {
- reusableToken.reinit(thaiToken, thaiToken.termBuffer(), start, end - start);
- reusableToken.setStartOffset(thaiToken.startOffset()+start);
- reusableToken.setEndOffset(thaiToken.endOffset()+end);
- return reusableToken;
- }
- thaiToken = null;
- }
-
- Token nextToken = input.next(reusableToken);
- if (nextToken == null || nextToken.termLength() == 0) {
- return null;
- }
-
- String text = nextToken.term();
- if (UnicodeBlock.of(text.charAt(0)) != UnicodeBlock.THAI) {
- nextToken.setTermBuffer(text.toLowerCase());
- return nextToken;
- }
-
- thaiToken = (Token) nextToken.clone();
- breaker.setText(text);
- int end = breaker.next();
- if (end != BreakIterator.DONE) {
- nextToken.setTermBuffer(text, 0, end);
- nextToken.setEndOffset(nextToken.startOffset() + end);
- return nextToken;
- }
- return null;
- }
-}
+package org.apache.lucene.analysis.th;
+
+/**
+ * Copyright 2006 The Apache Software Foundation
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+import java.io.IOException;
+import java.util.Locale;
+import java.lang.Character.UnicodeBlock;
+import org.apache.lucene.analysis.Token;
+import org.apache.lucene.analysis.TokenFilter;
+import org.apache.lucene.analysis.TokenStream;
+import java.text.BreakIterator;
+
+/**
+ * TokenFilter that use java.text.BreakIterator to break each
+ * Token that is Thai into separate Token(s) for each Thai word.
+ * @version 0.2
+ */
+public class ThaiWordFilter extends TokenFilter {
+
+ private BreakIterator breaker = null;
+ private Token thaiToken = null;
+
+ public ThaiWordFilter(TokenStream input) {
+ super(input);
+ breaker = BreakIterator.getWordInstance(new Locale("th"));
+ }
+
+ public Token next(final Token reusableToken) throws IOException {
+ assert reusableToken != null;
+ if (thaiToken != null) {
+ int start = breaker.current();
+ int end = breaker.next();
+ if (end != BreakIterator.DONE) {
+ reusableToken.reinit(thaiToken, thaiToken.termBuffer(), start, end - start);
+ reusableToken.setStartOffset(thaiToken.startOffset()+start);
+ reusableToken.setEndOffset(thaiToken.endOffset()+end);
+ return reusableToken;
+ }
+ thaiToken = null;
+ }
+
+ Token nextToken = input.next(reusableToken);
+ if (nextToken == null || nextToken.termLength() == 0) {
+ return null;
+ }
+
+ String text = nextToken.term();
+ if (UnicodeBlock.of(text.charAt(0)) != UnicodeBlock.THAI) {
+ nextToken.setTermBuffer(text.toLowerCase());
+ return nextToken;
+ }
+
+ thaiToken = (Token) nextToken.clone();
+ breaker.setText(text);
+ int end = breaker.next();
+ if (end != BreakIterator.DONE) {
+ nextToken.setTermBuffer(text, 0, end);
+ nextToken.setEndOffset(nextToken.startOffset() + end);
+ return nextToken;
+ }
+ return null;
+ }
+}
Propchange: lucene/java/trunk/contrib/analyzers/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java
------------------------------------------------------------------------------
svn:eol-style = native
Propchange: lucene/java/trunk/contrib/analyzers/src/test/org/apache/lucene/analysis/cn/TestChineseTokenizer.java
------------------------------------------------------------------------------
svn:eol-style = native