You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by rj...@apache.org on 2014/08/21 05:12:58 UTC
svn commit: r1619283 [1/11] - in /lucene/dev/branches/branch_4x: ./ lucene/
lucene/analysis/
lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/
lucene/analysis/common/src/java/org/apache/lucene/analysis/bg/
lucene/analysis/common/src/java/o...
Author: rjernst
Date: Thu Aug 21 03:12:52 2014
New Revision: 1619283
URL: http://svn.apache.org/r1619283
Log:
LUCENE-5859: Add Analyzer constructors without Version parameter and deprecate those taking Version
Added:
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/Lucene43CompoundWordTokenFilterBase.java
- copied unchanged from r1616901, lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/Lucene43CompoundWordTokenFilterBase.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/Lucene43DictionaryCompoundWordTokenFilter.java
- copied unchanged from r1616901, lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/Lucene43DictionaryCompoundWordTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/Lucene43HyphenationCompoundWordTokenFilter.java
- copied unchanged from r1616901, lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/Lucene43HyphenationCompoundWordTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/Lucene43EdgeNGramTokenFilter.java
- copied unchanged from r1616901, lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/Lucene43EdgeNGramTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/Lucene43NGramTokenFilter.java
- copied unchanged from r1616901, lucene/dev/trunk/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/Lucene43NGramTokenFilter.java
Modified:
lucene/dev/branches/branch_4x/ (props changed)
lucene/dev/branches/branch_4x/lucene/ (props changed)
lucene/dev/branches/branch_4x/lucene/analysis/ (props changed)
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.jflex
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ckb/SoraniAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/KeywordTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/LetterTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/LetterTokenizerFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/LowerCaseFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/LowerCaseFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/LowerCaseTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/LowerCaseTokenizerFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/SimpleAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/StopAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/StopFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/StopFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/TypeTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/TypeTokenFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/UpperCaseFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/UpperCaseFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/WhitespaceAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/WhitespaceTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/WhitespaceTokenizerFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/cz/CzechAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/da/DanishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/de/GermanAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/el/GreekAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/el/GreekLowerCaseFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/el/GreekLowerCaseFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/el/GreekStemmer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishPossessiveFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/en/EnglishPossessiveFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/en/KStemmer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/es/SpanishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/eu/BasqueAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/fa/PersianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/fi/FinnishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/fr/FrenchAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ga/IrishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/gl/GalicianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/hi/HindiAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/hu/HungarianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/hunspell/Stemmer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/hy/ArmenianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/id/IndonesianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/it/ItalianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/lv/LatvianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/CapitalizationFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/CodepointCountFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/CodepointCountFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/KeepWordFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/KeepWordFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/LengthFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/LengthFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/RemoveDuplicatesTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/TrimFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/TrimFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/miscellaneous/WordDelimiterFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/Lucene43EdgeNGramTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/Lucene43NGramTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ngram/NGramTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/nl/DutchAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/no/NorwegianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/PortugueseAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/pt/RSLPStemmerBase.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/reverse/ReverseStringFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ro/RomanianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ru/RussianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/shingle/ShingleAnalyzerWrapper.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/ClassicTokenizerFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/StandardTokenizerFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/standard/UAX29URLEmailTokenizerFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/sv/SwedishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/synonym/SynonymFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiWordFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/th/ThaiWordFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/tr/TurkishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharArrayMap.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharArraySet.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/CharacterUtils.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/FilteringTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/StopwordAnalyzerBase.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/util/WordlistLoader.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/collation/CollationKeyAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ar/TestArabicStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/bg/TestBulgarianStemmer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/br/TestBrazilianStemmer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ca/TestCatalanAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cjk/TestCJKBigramFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ckb/TestSoraniStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/commongrams/CommonGramsFilterTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/compound/TestCompoundWordTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestAnalyzers.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestBugInSomething.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestClassicAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestDuelingAnalyzers.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestKeywordAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestRandomChains.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStandardAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestStopFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestTypeTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestTypeTokenFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestUAX29URLEmailAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/core/TestUAX29URLEmailTokenizer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cz/TestCzechAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/cz/TestCzechStemmer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/da/TestDanishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanLightStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanMinimalStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/de/TestGermanStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/el/GreekAnalyzerTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/el/TestGreekStemmer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestEnglishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/en/TestPorterStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/es/TestSpanishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/eu/TestBasqueAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fa/TestPersianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fi/TestFinnishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fi/TestFinnishLightStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchLightStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/fr/TestFrenchMinimalStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ga/TestIrishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/gl/TestGalicianMinimalStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hi/TestHindiAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hu/TestHungarianLightStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hunspell/TestHunspellStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/hy/TestArmenianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/id/TestIndonesianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/it/TestItalianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/lv/TestLatvianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCapitalizationFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestCodepointCountFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeepWordFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestKeywordMarkerFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLengthFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestLucene47WordDelimiterFilter.java (contents, props changed)
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestPerFieldAnalyzerWrapper.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestStemmerOverrideFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestTrimFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/miscellaneous/TestWordDelimiterFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenFilterTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/EdgeNGramTokenizerTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenFilterTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ngram/NGramTokenizerTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/nl/TestDutchStemmer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/no/TestNorwegianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/no/TestNorwegianLightStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/no/TestNorwegianMinimalStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseLightStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseMinimalStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/pt/TestPortugueseStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/query/QueryAutoStopWordAnalyzerTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/reverse/TestReverseStringFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ro/TestRomanianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ru/TestRussianAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/ru/TestRussianLightStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/shingle/ShingleAnalyzerWrapperTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/shingle/ShingleFilterTest.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/sinks/TestTeeSinkTokenFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/sv/TestSwedishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/sv/TestSwedishLightStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/synonym/TestSolrSynonymParser.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/th/TestThaiAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/tr/TestTurkishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestCharArrayMap.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestCharArraySet.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestCharTokenizers.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestCharacterUtils.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestElision.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestFilesystemResourceLoader.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/analysis/util/TestWordlistLoader.java
lucene/dev/branches/branch_4x/lucene/analysis/common/src/test/org/apache/lucene/collation/TestCollationKeyAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/TestICUNormalizer2CharFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/icu/src/test/org/apache/lucene/analysis/icu/segmentation/TestWithCJKBigramFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/JapaneseAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/JapanesePartOfSpeechStopFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/java/org/apache/lucene/analysis/ja/JapanesePartOfSpeechStopFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseBaseFormFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/kuromoji/src/test/org/apache/lucene/analysis/ja/TestJapaneseKatakanaStemFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/morfologik/src/java/org/apache/lucene/analysis/morfologik/MorfologikFilterFactory.java
lucene/dev/branches/branch_4x/lucene/analysis/morfologik/src/test/org/apache/lucene/analysis/morfologik/TestMorfologikAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/phonetic/src/test/org/apache/lucene/analysis/phonetic/TestPhoneticFilter.java
lucene/dev/branches/branch_4x/lucene/analysis/smartcn/src/java/org/apache/lucene/analysis/cn/smart/SmartChineseAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/smartcn/src/test/org/apache/lucene/analysis/cn/smart/TestSmartChineseAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/stempel/src/java/org/apache/lucene/analysis/pl/PolishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/analysis/stempel/src/test/org/apache/lucene/analysis/pl/TestPolishAnalyzer.java
lucene/dev/branches/branch_4x/lucene/benchmark/ (props changed)
lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/EnwikiQueryMaker.java
lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/FileBasedQueryMaker.java
lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/LongToEnglishQueryMaker.java
lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ReutersQueryMaker.java
lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/SimpleQueryMaker.java
lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/byTask/tasks/NewCollationAnalyzerTask.java
lucene/dev/branches/branch_4x/lucene/benchmark/src/java/org/apache/lucene/benchmark/quality/utils/SimpleQQParser.java
lucene/dev/branches/branch_4x/lucene/benchmark/src/test/org/apache/lucene/benchmark/byTask/TestPerfTasksLogic.java
lucene/dev/branches/branch_4x/lucene/classification/ (props changed)
lucene/dev/branches/branch_4x/lucene/classification/src/ (props changed)
lucene/dev/branches/branch_4x/lucene/classification/src/test/org/apache/lucene/classification/SimpleNaiveBayesClassifierTest.java
lucene/dev/branches/branch_4x/lucene/core/ (props changed)
lucene/dev/branches/branch_4x/lucene/core/src/java/org/apache/lucene/analysis/Analyzer.java
lucene/dev/branches/branch_4x/lucene/demo/ (props changed)
lucene/dev/branches/branch_4x/lucene/demo/src/java/org/apache/lucene/demo/facet/AssociationsFacetsExample.java
lucene/dev/branches/branch_4x/lucene/demo/src/java/org/apache/lucene/demo/facet/DistanceFacetsExample.java
lucene/dev/branches/branch_4x/lucene/demo/src/java/org/apache/lucene/demo/facet/ExpressionAggregationFacetsExample.java
lucene/dev/branches/branch_4x/lucene/demo/src/java/org/apache/lucene/demo/facet/MultiCategoryListsFacetsExample.java
lucene/dev/branches/branch_4x/lucene/demo/src/java/org/apache/lucene/demo/facet/RangeFacetsExample.java
lucene/dev/branches/branch_4x/lucene/demo/src/java/org/apache/lucene/demo/facet/SimpleFacetsExample.java
lucene/dev/branches/branch_4x/lucene/demo/src/java/org/apache/lucene/demo/facet/SimpleSortedSetFacetsExample.java
lucene/dev/branches/branch_4x/lucene/demo/src/java/org/apache/lucene/demo/xmlparser/FormBasedXmlQueryDemo.java
lucene/dev/branches/branch_4x/lucene/memory/ (props changed)
lucene/dev/branches/branch_4x/lucene/memory/src/test/org/apache/lucene/index/memory/MemoryIndexTest.java
lucene/dev/branches/branch_4x/lucene/queryparser/ (props changed)
lucene/dev/branches/branch_4x/lucene/queryparser/src/java/org/apache/lucene/queryparser/analyzing/AnalyzingQueryParser.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/java/org/apache/lucene/queryparser/classic/MultiFieldQueryParser.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/java/org/apache/lucene/queryparser/classic/QueryParser.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/java/org/apache/lucene/queryparser/classic/QueryParser.jj
lucene/dev/branches/branch_4x/lucene/queryparser/src/java/org/apache/lucene/queryparser/classic/QueryParserBase.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/java/org/apache/lucene/queryparser/complexPhrase/ComplexPhraseQueryParser.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/java/org/apache/lucene/queryparser/ext/ExtendableQueryParser.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/java/org/apache/lucene/queryparser/xml/builders/UserInputQueryBuilder.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/test/org/apache/lucene/queryparser/analyzing/TestAnalyzingQueryParser.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/test/org/apache/lucene/queryparser/classic/TestMultiAnalyzer.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/test/org/apache/lucene/queryparser/classic/TestMultiFieldQueryParser.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/test/org/apache/lucene/queryparser/classic/TestMultiPhraseQueryParsing.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/test/org/apache/lucene/queryparser/classic/TestQueryParser.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/test/org/apache/lucene/queryparser/complexPhrase/TestComplexPhraseQuery.java
lucene/dev/branches/branch_4x/lucene/queryparser/src/test/org/apache/lucene/queryparser/ext/TestExtendableQueryParser.java
lucene/dev/branches/branch_4x/lucene/suggest/ (props changed)
lucene/dev/branches/branch_4x/lucene/suggest/src/java/org/apache/lucene/search/suggest/analyzing/AnalyzingInfixSuggester.java
lucene/dev/branches/branch_4x/lucene/suggest/src/test/org/apache/lucene/search/suggest/analyzing/AnalyzingInfixSuggesterTest.java
lucene/dev/branches/branch_4x/lucene/suggest/src/test/org/apache/lucene/search/suggest/analyzing/BlendedInfixSuggesterTest.java
lucene/dev/branches/branch_4x/lucene/suggest/src/test/org/apache/lucene/search/suggest/analyzing/TestFreeTextSuggester.java
lucene/dev/branches/branch_4x/lucene/suggest/src/test/org/apache/lucene/search/suggest/analyzing/TestSuggestStopFilter.java
lucene/dev/branches/branch_4x/solr/ (props changed)
lucene/dev/branches/branch_4x/solr/core/ (props changed)
lucene/dev/branches/branch_4x/solr/core/src/java/org/apache/solr/handler/component/SpellCheckComponent.java
lucene/dev/branches/branch_4x/solr/core/src/java/org/apache/solr/rest/schema/analysis/ManagedStopFilterFactory.java
lucene/dev/branches/branch_4x/solr/core/src/java/org/apache/solr/schema/CollationField.java
lucene/dev/branches/branch_4x/solr/core/src/java/org/apache/solr/schema/FieldTypePluginLoader.java
lucene/dev/branches/branch_4x/solr/core/src/java/org/apache/solr/search/ComplexPhraseQParserPlugin.java
lucene/dev/branches/branch_4x/solr/core/src/java/org/apache/solr/spelling/SolrSpellChecker.java
lucene/dev/branches/branch_4x/solr/core/src/test-files/solr/collection1/conf/schema-luceneMatchVersion.xml
lucene/dev/branches/branch_4x/solr/core/src/test/org/apache/solr/analysis/TestLuceneMatchVersion.java
lucene/dev/branches/branch_4x/solr/core/src/test/org/apache/solr/core/TestArbitraryIndexDir.java
lucene/dev/branches/branch_4x/solr/core/src/test/org/apache/solr/highlight/HighlighterTest.java
lucene/dev/branches/branch_4x/solr/core/src/test/org/apache/solr/search/TestSort.java
lucene/dev/branches/branch_4x/solr/core/src/test/org/apache/solr/spelling/IndexBasedSpellCheckerTest.java
lucene/dev/branches/branch_4x/solr/core/src/test/org/apache/solr/spelling/SimpleQueryConverter.java
lucene/dev/branches/branch_4x/solr/core/src/test/org/apache/solr/spelling/SpellingQueryConverterTest.java
lucene/dev/branches/branch_4x/solr/core/src/test/org/apache/solr/spelling/TestSuggestSpellingConverter.java
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ar/ArabicAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -89,6 +89,14 @@ public final class ArabicAnalyzer extend
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
*/
+ public ArabicAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
+ }
+
+ /**
+ * @deprecated Use {@link #ArabicAnalyzer()}
+ */
+ @Deprecated
public ArabicAnalyzer(Version matchVersion) {
this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
}
@@ -96,11 +104,17 @@ public final class ArabicAnalyzer extend
/**
* Builds an analyzer with the given stop words
*
- * @param matchVersion
- * lucene compatibility version
* @param stopwords
* a stopword set
*/
+ public ArabicAnalyzer(CharArraySet stopwords){
+ this(stopwords, CharArraySet.EMPTY_SET);
+ }
+
+ /**
+ * @deprecated Use {@link #ArabicAnalyzer(CharArraySet)}
+ */
+ @Deprecated
public ArabicAnalyzer(Version matchVersion, CharArraySet stopwords){
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -110,13 +124,20 @@ public final class ArabicAnalyzer extend
* provided this analyzer will add a {@link SetKeywordMarkerFilter} before
* {@link ArabicStemFilter}.
*
- * @param matchVersion
- * lucene compatibility version
* @param stopwords
* a stopword set
* @param stemExclusionSet
* a set of terms not to be stemmed
*/
+ public ArabicAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet){
+ super(stopwords);
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
+ }
+
+ /**
+ * @deprecated Use {@link #ArabicAnalyzer(CharArraySet,CharArraySet)}
+ */
+ @Deprecated
public ArabicAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet){
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
@@ -137,11 +158,11 @@ public final class ArabicAnalyzer extend
@Override
protected TokenStreamComponents createComponents(String fieldName,
Reader reader) {
- final Tokenizer source = matchVersion.onOrAfter(Version.LUCENE_3_1) ?
- new StandardTokenizer(matchVersion, reader) : new ArabicLetterTokenizer(matchVersion, reader);
- TokenStream result = new LowerCaseFilter(matchVersion, source);
+ final Tokenizer source = getVersion().onOrAfter(Version.LUCENE_3_1_0) ?
+ new StandardTokenizer(getVersion(), reader) : new ArabicLetterTokenizer(getVersion(), reader);
+ TokenStream result = new LowerCaseFilter(getVersion(), source);
// the order here is important: the stopword list is not normalized!
- result = new StopFilter( matchVersion, result, stopwords);
+ result = new StopFilter(getVersion(), result, stopwords);
// TODO maybe we should make ArabicNormalization filter also KeywordAttribute aware?!
result = new ArabicNormalizationFilter(result);
if(!stemExclusionSet.isEmpty()) {
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/bg/BulgarianAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -19,7 +19,6 @@ package org.apache.lucene.analysis.bg;
import java.io.IOException;
import java.io.Reader;
-import java.util.Set;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.core.LowerCaseFilter;
@@ -42,6 +41,7 @@ import org.apache.lucene.util.Version;
* <p>
*/
public final class BulgarianAnalyzer extends StopwordAnalyzerBase {
+
/**
* File containing default Bulgarian stopwords.
*
@@ -84,6 +84,14 @@ public final class BulgarianAnalyzer ext
* Builds an analyzer with the default stop words:
* {@link #DEFAULT_STOPWORD_FILE}.
*/
+ public BulgarianAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
+ }
+
+ /**
+ * @deprecated Use {@link #BulgarianAnalyzer()}
+ */
+ @Deprecated
public BulgarianAnalyzer(Version matchVersion) {
this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
}
@@ -91,6 +99,14 @@ public final class BulgarianAnalyzer ext
/**
* Builds an analyzer with the given stop words.
*/
+ public BulgarianAnalyzer(CharArraySet stopwords) {
+ this(stopwords, CharArraySet.EMPTY_SET);
+ }
+
+ /**
+ * @deprecated Use {@link #BulgarianAnalyzer(CharArraySet)}
+ */
+ @Deprecated
public BulgarianAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -100,10 +116,20 @@ public final class BulgarianAnalyzer ext
* If a stem exclusion set is provided this analyzer will add a {@link SetKeywordMarkerFilter}
* before {@link BulgarianStemFilter}.
*/
+ public BulgarianAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
+ super(stopwords);
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
+ }
+
+ /**
+ * @deprecated Use {@link #BulgarianAnalyzer(CharArraySet,CharArraySet)}
+ */
+ @Deprecated
public BulgarianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
- matchVersion, stemExclusionSet)); }
+ matchVersion, stemExclusionSet));
+ }
/**
* Creates a
@@ -119,10 +145,10 @@ public final class BulgarianAnalyzer ext
*/
@Override
public TokenStreamComponents createComponents(String fieldName, Reader reader) {
- final Tokenizer source = new StandardTokenizer(matchVersion, reader);
- TokenStream result = new StandardFilter(matchVersion, source);
- result = new LowerCaseFilter(matchVersion, result);
- result = new StopFilter(matchVersion, result, stopwords);
+ final Tokenizer source = new StandardTokenizer(getVersion(), reader);
+ TokenStream result = new StandardFilter(getVersion(), source);
+ result = new LowerCaseFilter(getVersion(), result);
+ result = new StopFilter(getVersion(), result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new BulgarianStemFilter(result);
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/br/BrazilianAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -65,7 +65,7 @@ public final class BrazilianAnalyzer ext
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getWordSet(IOUtils.getDecodingReader(BrazilianAnalyzer.class,
- DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), "#", Version.LUCENE_CURRENT);
+ DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), "#");
} catch (IOException ex) {
// default set should always be present as it is part of the
// distribution (JAR)
@@ -83,6 +83,14 @@ public final class BrazilianAnalyzer ext
/**
* Builds an analyzer with the default stop words ({@link #getDefaultStopSet()}).
*/
+ public BrazilianAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
+ }
+
+ /**
+ * @deprecated Use {@link #BrazilianAnalyzer()}
+ */
+ @Deprecated
public BrazilianAnalyzer(Version matchVersion) {
this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
}
@@ -90,28 +98,39 @@ public final class BrazilianAnalyzer ext
/**
* Builds an analyzer with the given stop words
*
- * @param matchVersion
- * lucene compatibility version
* @param stopwords
* a stopword set
*/
+ public BrazilianAnalyzer(CharArraySet stopwords) {
+ super(stopwords);
+ }
+
+ /**
+ * @deprecated Use {@link #BrazilianAnalyzer(CharArraySet)}
+ */
+ @Deprecated
public BrazilianAnalyzer(Version matchVersion, CharArraySet stopwords) {
- super(matchVersion, stopwords);
+ super(matchVersion, stopwords);
}
/**
* Builds an analyzer with the given stop words and stemming exclusion words
*
- * @param matchVersion
- * lucene compatibility version
* @param stopwords
* a stopword set
*/
- public BrazilianAnalyzer(Version matchVersion, CharArraySet stopwords,
- CharArraySet stemExclusionSet) {
+ public BrazilianAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
+ this(stopwords);
+ excltable = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
+ }
+
+ /**
+ * @deprecated Use {@link #BrazilianAnalyzer(CharArraySet,CharArraySet)}
+ */
+ @Deprecated
+ public BrazilianAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
this(matchVersion, stopwords);
- excltable = CharArraySet.unmodifiableSet(CharArraySet
- .copy(matchVersion, stemExclusionSet));
+ excltable = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionSet));
}
/**
@@ -127,10 +146,10 @@ public final class BrazilianAnalyzer ext
@Override
protected TokenStreamComponents createComponents(String fieldName,
Reader reader) {
- Tokenizer source = new StandardTokenizer(matchVersion, reader);
- TokenStream result = new LowerCaseFilter(matchVersion, source);
- result = new StandardFilter(matchVersion, result);
- result = new StopFilter(matchVersion, result, stopwords);
+ Tokenizer source = new StandardTokenizer(getVersion(), reader);
+ TokenStream result = new LowerCaseFilter(getVersion(), source);
+ result = new StandardFilter(getVersion(), result);
+ result = new StopFilter(getVersion(), result, stopwords);
if(excltable != null && !excltable.isEmpty())
result = new SetKeywordMarkerFilter(result, excltable);
return new TokenStreamComponents(source, new BrazilianStemFilter(result));
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ca/CatalanAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -54,7 +54,7 @@ public final class CatalanAnalyzer exten
public final static String DEFAULT_STOPWORD_FILE = "stopwords.txt";
private static final CharArraySet DEFAULT_ARTICLES = CharArraySet.unmodifiableSet(
- new CharArraySet(Version.LUCENE_CURRENT,
+ new CharArraySet(
Arrays.asList(
"d", "l", "m", "n", "s", "t"
), true));
@@ -89,6 +89,14 @@ public final class CatalanAnalyzer exten
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
*/
+ public CatalanAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
+ }
+
+ /**
+ * @deprecated Use {@link #CatalanAnalyzer()}
+ */
+ @Deprecated
public CatalanAnalyzer(Version matchVersion) {
this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
}
@@ -96,9 +104,16 @@ public final class CatalanAnalyzer exten
/**
* Builds an analyzer with the given stop words.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
+ public CatalanAnalyzer(CharArraySet stopwords) {
+ this(stopwords, CharArraySet.EMPTY_SET);
+ }
+
+ /**
+ * @deprecated Use {@link #CatalanAnalyzer(CharArraySet)}
+ */
+ @Deprecated
public CatalanAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -108,14 +123,21 @@ public final class CatalanAnalyzer exten
* provided this analyzer will add a {@link SetKeywordMarkerFilter} before
* stemming.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
+ public CatalanAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
+ super(stopwords);
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
+ }
+
+ /**
+ * @deprecated Use {@link #CatalanAnalyzer(CharArraySet, CharArraySet)}
+ */
+ @Deprecated
public CatalanAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
- this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
- matchVersion, stemExclusionSet));
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(matchVersion, stemExclusionSet));
}
/**
@@ -133,13 +155,13 @@ public final class CatalanAnalyzer exten
@Override
protected TokenStreamComponents createComponents(String fieldName,
Reader reader) {
- final Tokenizer source = new StandardTokenizer(matchVersion, reader);
- TokenStream result = new StandardFilter(matchVersion, source);
- if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
+ final Tokenizer source = new StandardTokenizer(getVersion(), reader);
+ TokenStream result = new StandardFilter(getVersion(), source);
+ if (getVersion().onOrAfter(Version.LUCENE_3_6_0)) {
result = new ElisionFilter(result, DEFAULT_ARTICLES);
}
- result = new LowerCaseFilter(matchVersion, result);
- result = new StopFilter(matchVersion, result, stopwords);
+ result = new LowerCaseFilter(getVersion(), result);
+ result = new StopFilter(getVersion(), result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new SnowballFilter(result, new CatalanStemmer());
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.java Thu Aug 21 03:12:52 2014
@@ -26,7 +26,6 @@ import java.util.HashMap;
import java.util.Map;
import java.util.Set;
-import org.apache.lucene.util.Version;
import org.apache.lucene.analysis.util.CharArrayMap;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.OpenStringBuilder;
@@ -29840,7 +29839,7 @@ public final class HTMLStripCharFilter e
upperCaseVariantsAccepted.put("amp", "AMP");
}
private static final CharArrayMap<Character> entityValues
- = new CharArrayMap<>(Version.LUCENE_CURRENT, 253, false);
+ = new CharArrayMap<>(253, false);
static {
String[] entities = {
"AElig", "\u00C6", "Aacute", "\u00C1", "Acirc", "\u00C2",
@@ -29979,7 +29978,7 @@ public final class HTMLStripCharFilter e
escapeSTYLE = true;
} else {
if (null == this.escapedTags) {
- this.escapedTags = new CharArraySet(Version.LUCENE_CURRENT, 16, true);
+ this.escapedTags = new CharArraySet(16, true);
}
this.escapedTags.add(tag);
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.jflex
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.jflex?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.jflex (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/charfilter/HTMLStripCharFilter.jflex Thu Aug 21 03:12:52 2014
@@ -24,7 +24,6 @@ import java.util.HashMap;
import java.util.Map;
import java.util.Set;
-import org.apache.lucene.util.Version;
import org.apache.lucene.analysis.util.CharArrayMap;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.analysis.util.OpenStringBuilder;
@@ -195,7 +194,7 @@ InlineElment = ( [aAbBiIqQsSuU]
escapeSTYLE = true;
} else {
if (null == this.escapedTags) {
- this.escapedTags = new CharArraySet(Version.LUCENE_CURRENT, 16, true);
+ this.escapedTags = new CharArraySet(16, true);
}
this.escapedTags.add(tag);
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/cjk/CJKAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -37,6 +37,7 @@ import org.apache.lucene.util.Version;
* and filters stopwords with {@link StopFilter}
*/
public final class CJKAnalyzer extends StopwordAnalyzerBase {
+
/**
* File containing default CJK stopwords.
* <p/>
@@ -70,6 +71,14 @@ public final class CJKAnalyzer extends S
/**
* Builds an analyzer which removes words in {@link #getDefaultStopSet()}.
*/
+ public CJKAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
+ }
+
+ /**
+ * @deprecated Use {@link #CJKAnalyzer()}
+ */
+ @Deprecated
public CJKAnalyzer(Version matchVersion) {
this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
}
@@ -77,11 +86,17 @@ public final class CJKAnalyzer extends S
/**
* Builds an analyzer with the given stop words
*
- * @param matchVersion
- * lucene compatibility version
* @param stopwords
* a stopword set
*/
+ public CJKAnalyzer(CharArraySet stopwords){
+ super(stopwords);
+ }
+
+ /**
+ * @deprecated Use {@link #CJKAnalyzer(CharArraySet)}
+ */
+ @Deprecated
public CJKAnalyzer(Version matchVersion, CharArraySet stopwords){
super(matchVersion, stopwords);
}
@@ -89,16 +104,16 @@ public final class CJKAnalyzer extends S
@Override
protected TokenStreamComponents createComponents(String fieldName,
Reader reader) {
- if (matchVersion.onOrAfter(Version.LUCENE_3_6)) {
- final Tokenizer source = new StandardTokenizer(matchVersion, reader);
+ if (getVersion().onOrAfter(Version.LUCENE_3_6_0)) {
+ final Tokenizer source = new StandardTokenizer(getVersion(), reader);
// run the widthfilter first before bigramming, it sometimes combines characters.
TokenStream result = new CJKWidthFilter(source);
- result = new LowerCaseFilter(matchVersion, result);
+ result = new LowerCaseFilter(getVersion(), result);
result = new CJKBigramFilter(result);
- return new TokenStreamComponents(source, new StopFilter(matchVersion, result, stopwords));
+ return new TokenStreamComponents(source, new StopFilter(getVersion(), result, stopwords));
} else {
final Tokenizer source = new CJKTokenizer(reader);
- return new TokenStreamComponents(source, new StopFilter(matchVersion, source, stopwords));
+ return new TokenStreamComponents(source, new StopFilter(getVersion(), source, stopwords));
}
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ckb/SoraniAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ckb/SoraniAnalyzer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ckb/SoraniAnalyzer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/ckb/SoraniAnalyzer.java Thu Aug 21 03:12:52 2014
@@ -62,7 +62,7 @@ public final class SoraniAnalyzer extend
static {
try {
DEFAULT_STOP_SET = WordlistLoader.getWordSet(IOUtils.getDecodingReader(SoraniAnalyzer.class,
- DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8), Version.LUCENE_CURRENT);
+ DEFAULT_STOPWORD_FILE, StandardCharsets.UTF_8));
} catch (IOException ex) {
// default set should always be present as it is part of the
// distribution (JAR)
@@ -74,6 +74,14 @@ public final class SoraniAnalyzer extend
/**
* Builds an analyzer with the default stop words: {@link #DEFAULT_STOPWORD_FILE}.
*/
+ public SoraniAnalyzer() {
+ this(DefaultSetHolder.DEFAULT_STOP_SET);
+ }
+
+ /**
+ * @deprecated Use {@link #SoraniAnalyzer()}
+ */
+ @Deprecated
public SoraniAnalyzer(Version matchVersion) {
this(matchVersion, DefaultSetHolder.DEFAULT_STOP_SET);
}
@@ -81,9 +89,16 @@ public final class SoraniAnalyzer extend
/**
* Builds an analyzer with the given stop words.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
*/
+ public SoraniAnalyzer(CharArraySet stopwords) {
+ this(stopwords, CharArraySet.EMPTY_SET);
+ }
+
+ /**
+ * @deprecated Use {@link #SoraniAnalyzer(CharArraySet)}
+ */
+ @Deprecated
public SoraniAnalyzer(Version matchVersion, CharArraySet stopwords) {
this(matchVersion, stopwords, CharArraySet.EMPTY_SET);
}
@@ -93,10 +108,18 @@ public final class SoraniAnalyzer extend
* provided this analyzer will add a {@link SetKeywordMarkerFilter} before
* stemming.
*
- * @param matchVersion lucene compatibility version
* @param stopwords a stopword set
* @param stemExclusionSet a set of terms not to be stemmed
*/
+ public SoraniAnalyzer(CharArraySet stopwords, CharArraySet stemExclusionSet) {
+ super(stopwords);
+ this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(stemExclusionSet));
+ }
+
+ /**
+ * @deprecated Use {@link #SoraniAnalyzer(CharArraySet,CharArraySet)}
+ */
+ @Deprecated
public SoraniAnalyzer(Version matchVersion, CharArraySet stopwords, CharArraySet stemExclusionSet) {
super(matchVersion, stopwords);
this.stemExclusionSet = CharArraySet.unmodifiableSet(CharArraySet.copy(
@@ -118,11 +141,11 @@ public final class SoraniAnalyzer extend
*/
@Override
protected TokenStreamComponents createComponents(String fieldName, Reader reader) {
- final Tokenizer source = new StandardTokenizer(matchVersion, reader);
- TokenStream result = new StandardFilter(matchVersion, source);
+ final Tokenizer source = new StandardTokenizer(getVersion(), reader);
+ TokenStream result = new StandardFilter(getVersion(), source);
result = new SoraniNormalizationFilter(result);
- result = new LowerCaseFilter(matchVersion, result);
- result = new StopFilter(matchVersion, result, stopwords);
+ result = new LowerCaseFilter(getVersion(), result);
+ result = new StopFilter(getVersion(), result, stopwords);
if(!stemExclusionSet.isEmpty())
result = new SetKeywordMarkerFilter(result, stemExclusionSet);
result = new SoraniStemFilter(result);
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/commongrams/CommonGramsFilter.java Thu Aug 21 03:12:52 2014
@@ -78,12 +78,20 @@ public final class CommonGramsFilter ext
* @param input TokenStream input in filter chain
* @param commonWords The set of common words.
*/
- public CommonGramsFilter(Version matchVersion, TokenStream input, CharArraySet commonWords) {
+ public CommonGramsFilter(TokenStream input, CharArraySet commonWords) {
super(input);
this.commonWords = commonWords;
}
/**
+ * @deprecated Use {@link #CommonGramsFilter(TokenStream, CharArraySet)}
+ */
+ @Deprecated
+ public CommonGramsFilter(Version matchVersion, TokenStream input, CharArraySet commonWords) {
+ this(input, commonWords);
+ }
+
+ /**
* Inserts bigrams for common words into a token stream. For each input token,
* output the token. If the token and/or the following token are in the list
* of common words also output a bigram with position increment 0 and
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/CompoundWordTokenFilterBase.java Thu Aug 21 03:12:52 2014
@@ -17,24 +17,23 @@ package org.apache.lucene.analysis.compo
* limitations under the License.
*/
-import java.io.IOException;
-import java.util.LinkedList;
-
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.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
import org.apache.lucene.analysis.util.CharArraySet;
-import org.apache.lucene.util.AttributeSource;
import org.apache.lucene.util.Version;
+import java.io.IOException;
+import java.util.LinkedList;
+
/**
* Base class for decomposition token filters.
* <p>
*
* <a name="version"></a>
- * You must specify the required {@link Version} compatibility when creating
+ * You may specify the {@link Version} compatibility when creating
* CompoundWordTokenFilterBase:
* <ul>
* <li>As of 3.1, CompoundWordTokenFilterBase correctly handles Unicode 4.0
@@ -66,21 +65,36 @@ public abstract class CompoundWordTokenF
protected final int minSubwordSize;
protected final int maxSubwordSize;
protected final boolean onlyLongestMatch;
-
+
protected final CharTermAttribute termAtt = addAttribute(CharTermAttribute.class);
protected final OffsetAttribute offsetAtt = addAttribute(OffsetAttribute.class);
private final PositionIncrementAttribute posIncAtt = addAttribute(PositionIncrementAttribute.class);
-
- private AttributeSource.State current;
+ private State current;
+
+ protected CompoundWordTokenFilterBase(TokenStream input, CharArraySet dictionary, boolean onlyLongestMatch) {
+ this(Version.LATEST, input,dictionary,onlyLongestMatch);
+ }
+
+ @Deprecated
protected CompoundWordTokenFilterBase(Version matchVersion, TokenStream input, CharArraySet dictionary, boolean onlyLongestMatch) {
this(matchVersion, input,dictionary,DEFAULT_MIN_WORD_SIZE,DEFAULT_MIN_SUBWORD_SIZE,DEFAULT_MAX_SUBWORD_SIZE, onlyLongestMatch);
}
+ protected CompoundWordTokenFilterBase(TokenStream input, CharArraySet dictionary) {
+ this(Version.LATEST, input,dictionary);
+ }
+
+ @Deprecated
protected CompoundWordTokenFilterBase(Version matchVersion, TokenStream input, CharArraySet dictionary) {
this(matchVersion, input,dictionary,DEFAULT_MIN_WORD_SIZE,DEFAULT_MIN_SUBWORD_SIZE,DEFAULT_MAX_SUBWORD_SIZE, false);
}
+ protected CompoundWordTokenFilterBase(TokenStream input, CharArraySet dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch) {
+ this(Version.LATEST, input, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
+ }
+
+ @Deprecated
protected CompoundWordTokenFilterBase(Version matchVersion, TokenStream input, CharArraySet dictionary, int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch) {
super(input);
this.matchVersion = matchVersion;
@@ -100,7 +114,7 @@ public abstract class CompoundWordTokenF
this.onlyLongestMatch=onlyLongestMatch;
this.dictionary = dictionary;
}
-
+
@Override
public final boolean incrementToken() throws IOException {
if (!tokens.isEmpty()) {
@@ -141,7 +155,7 @@ public abstract class CompoundWordTokenF
tokens.clear();
current = null;
}
-
+
/**
* Helper class to hold decompounded token information
*/
@@ -156,7 +170,7 @@ public abstract class CompoundWordTokenF
// offsets of the original word
int startOff = CompoundWordTokenFilterBase.this.offsetAtt.startOffset();
int endOff = CompoundWordTokenFilterBase.this.offsetAtt.endOffset();
-
+
if (matchVersion.onOrAfter(Version.LUCENE_4_4) ||
endOff - startOff != CompoundWordTokenFilterBase.this.termAtt.length()) {
// if length by start + end offsets doesn't match the term text then assume
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilter.java Thu Aug 21 03:12:52 2014
@@ -18,21 +18,18 @@ package org.apache.lucene.analysis.compo
*/
-import java.util.Set;
-
-import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.util.CharArraySet;
import org.apache.lucene.util.Version;
/**
- * A {@link TokenFilter} that decomposes compound words found in many Germanic languages.
+ * A {@link org.apache.lucene.analysis.TokenFilter} that decomposes compound words found in many Germanic languages.
* <p>
* "Donaudampfschiff" becomes Donau, dampf, schiff so that you can find
- * "Donaudampfschiff" even when you only enter "schiff".
+ * "Donaudampfschiff" even when you only enter "schiff".
* It uses a brute-force algorithm to achieve this.
* <p>
- * You must specify the required {@link Version} compatibility when creating
+ * You may specify the {@link Version} compatibility when creating
* CompoundWordTokenFilterBase:
* <ul>
* <li>As of 3.1, CompoundWordTokenFilterBase correctly handles Unicode 4.0
@@ -41,37 +38,38 @@ import org.apache.lucene.util.Version;
* </ul>
*/
public class DictionaryCompoundWordTokenFilter extends CompoundWordTokenFilterBase {
-
+
/**
* Creates a new {@link DictionaryCompoundWordTokenFilter}
- *
- * @param matchVersion
- * Lucene version to enable correct Unicode 4.0 behavior in the
- * dictionaries if Version > 3.0. See <a
- * href="CompoundWordTokenFilterBase.html#version"
- * >CompoundWordTokenFilterBase</a> for details.
+ *
* @param input
- * the {@link TokenStream} to process
+ * the {@link org.apache.lucene.analysis.TokenStream} to process
* @param dictionary
* the word dictionary to match against.
*/
+ public DictionaryCompoundWordTokenFilter(TokenStream input, CharArraySet dictionary) {
+ super(input, dictionary);
+ if (dictionary == null) {
+ throw new IllegalArgumentException("dictionary cannot be null");
+ }
+ }
+
+ /**
+ * @deprecated Use {@link #DictionaryCompoundWordTokenFilter(TokenStream,CharArraySet)}
+ */
+ @Deprecated
public DictionaryCompoundWordTokenFilter(Version matchVersion, TokenStream input, CharArraySet dictionary) {
super(matchVersion, input, dictionary);
if (dictionary == null) {
throw new IllegalArgumentException("dictionary cannot be null");
}
}
-
+
/**
* Creates a new {@link DictionaryCompoundWordTokenFilter}
- *
- * @param matchVersion
- * Lucene version to enable correct Unicode 4.0 behavior in the
- * dictionaries if Version > 3.0. See <a
- * href="CompoundWordTokenFilterBase.html#version"
- * >CompoundWordTokenFilterBase</a> for details.
+ *
* @param input
- * the {@link TokenStream} to process
+ * the {@link org.apache.lucene.analysis.TokenStream} to process
* @param dictionary
* the word dictionary to match against.
* @param minWordSize
@@ -83,6 +81,18 @@ public class DictionaryCompoundWordToken
* @param onlyLongestMatch
* Add only the longest matching subword to the stream
*/
+ public DictionaryCompoundWordTokenFilter(TokenStream input, CharArraySet dictionary,
+ int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch) {
+ super(input, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
+ if (dictionary == null) {
+ throw new IllegalArgumentException("dictionary cannot be null");
+ }
+ }
+
+ /**
+ * @deprecated Use {@link #DictionaryCompoundWordTokenFilter(TokenStream,CharArraySet,int,int,int,boolean)}
+ */
+ @Deprecated
public DictionaryCompoundWordTokenFilter(Version matchVersion, TokenStream input, CharArraySet dictionary,
int minWordSize, int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch) {
super(matchVersion, input, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilterFactory.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/DictionaryCompoundWordTokenFilterFactory.java Thu Aug 21 03:12:52 2014
@@ -22,12 +22,13 @@ import org.apache.lucene.analysis.util.C
import org.apache.lucene.analysis.util.ResourceLoader;
import org.apache.lucene.analysis.util.ResourceLoaderAware;
import org.apache.lucene.analysis.util.TokenFilterFactory;
+import org.apache.lucene.util.Version;
import java.util.Map;
import java.io.IOException;
/**
- * Factory for {@link DictionaryCompoundWordTokenFilter}.
+ * Factory for {@link DictionaryCompoundWordTokenFilter}.
* <pre class="prettyprint">
* <fieldType name="text_dictcomp" class="solr.TextField" positionIncrementGap="100">
* <analyzer>
@@ -67,8 +68,13 @@ public class DictionaryCompoundWordToken
@Override
public TokenStream create(TokenStream input) {
// if the dictionary is null, it means it was empty
- return dictionary == null ? input : new DictionaryCompoundWordTokenFilter
- (luceneMatchVersion, input, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
+ if (dictionary == null) {
+ return input;
+ }
+ if (luceneMatchVersion.onOrAfter(Version.LUCENE_4_4_0)) {
+ return new DictionaryCompoundWordTokenFilter(input, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
+ }
+ return new Lucene43DictionaryCompoundWordTokenFilter(input, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilter.java Thu Aug 21 03:12:52 2014
@@ -17,10 +17,6 @@ package org.apache.lucene.analysis.compo
* limitations under the License.
*/
-import java.io.File;
-import java.io.IOException;
-
-import org.apache.lucene.analysis.TokenFilter;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.compound.hyphenation.Hyphenation;
import org.apache.lucene.analysis.compound.hyphenation.HyphenationTree;
@@ -28,14 +24,17 @@ import org.apache.lucene.analysis.util.C
import org.apache.lucene.util.Version;
import org.xml.sax.InputSource;
+import java.io.File;
+import java.io.IOException;
+
/**
- * A {@link TokenFilter} that decomposes compound words found in many Germanic languages.
- * <p>
+ * A {@link org.apache.lucene.analysis.TokenFilter} that decomposes compound words found in many Germanic languages.
+ *
* "Donaudampfschiff" becomes Donau, dampf, schiff so that you can find
* "Donaudampfschiff" even when you only enter "schiff". It uses a hyphenation
* grammar and a word dictionary to achieve this.
* <p>
- * You must specify the required {@link Version} compatibility when creating
+ * You may specify the {@link Version} compatibility when creating
* CompoundWordTokenFilterBase:
* <ul>
* <li>As of 3.1, CompoundWordTokenFilterBase correctly handles Unicode 4.0
@@ -48,13 +47,8 @@ public class HyphenationCompoundWordToke
private HyphenationTree hyphenator;
/**
- * Creates a new {@link HyphenationCompoundWordTokenFilter} instance.
- *
- * @param matchVersion
- * Lucene version to enable correct Unicode 4.0 behavior in the
- * dictionaries if Version > 3.0. See <a
- * href="CompoundWordTokenFilterBase.html#version"
- * >CompoundWordTokenFilterBase</a> for details.
+ * Creates a new {@link HyphenationCompoundWordTokenFilter} instance.
+ *
* @param input
* the {@link TokenStream} to process
* @param hyphenator
@@ -62,6 +56,16 @@ public class HyphenationCompoundWordToke
* @param dictionary
* the word dictionary to match against.
*/
+ public HyphenationCompoundWordTokenFilter(TokenStream input,
+ HyphenationTree hyphenator, CharArraySet dictionary) {
+ this(input, hyphenator, dictionary, DEFAULT_MIN_WORD_SIZE,
+ DEFAULT_MIN_SUBWORD_SIZE, DEFAULT_MAX_SUBWORD_SIZE, false);
+ }
+
+ /**
+ * @deprecated Use {@link #HyphenationCompoundWordTokenFilter(TokenStream,HyphenationTree,CharArraySet)}
+ */
+ @Deprecated
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input,
HyphenationTree hyphenator, CharArraySet dictionary) {
this(matchVersion, input, hyphenator, dictionary, DEFAULT_MIN_WORD_SIZE,
@@ -70,12 +74,7 @@ public class HyphenationCompoundWordToke
/**
* Creates a new {@link HyphenationCompoundWordTokenFilter} instance.
- *
- * @param matchVersion
- * Lucene version to enable correct Unicode 4.0 behavior in the
- * dictionaries if Version > 3.0. See <a
- * href="CompoundWordTokenFilterBase.html#version"
- * >CompoundWordTokenFilterBase</a> for details.
+ *
* @param input
* the {@link TokenStream} to process
* @param hyphenator
@@ -91,6 +90,19 @@ public class HyphenationCompoundWordToke
* @param onlyLongestMatch
* Add only the longest matching subword to the stream
*/
+ public HyphenationCompoundWordTokenFilter(TokenStream input,
+ HyphenationTree hyphenator, CharArraySet dictionary, int minWordSize,
+ int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch) {
+ super(input, dictionary, minWordSize, minSubwordSize, maxSubwordSize,
+ onlyLongestMatch);
+
+ this.hyphenator = hyphenator;
+ }
+
+ /**
+ * @deprecated Use {@link #HyphenationCompoundWordTokenFilter(TokenStream,HyphenationTree,CharArraySet,int,int,int,boolean)}
+ */
+ @Deprecated
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input,
HyphenationTree hyphenator, CharArraySet dictionary, int minWordSize,
int minSubwordSize, int maxSubwordSize, boolean onlyLongestMatch) {
@@ -103,33 +115,54 @@ public class HyphenationCompoundWordToke
/**
* Create a HyphenationCompoundWordTokenFilter with no dictionary.
* <p>
- * Calls {@link #HyphenationCompoundWordTokenFilter(Version, TokenStream, HyphenationTree, CharArraySet, int, int, int, boolean)
+ * Calls {@link #HyphenationCompoundWordTokenFilter(org.apache.lucene.analysis.TokenStream, org.apache.lucene.analysis.compound.hyphenation.HyphenationTree, org.apache.lucene.analysis.util.CharArraySet, int, int, int, boolean)
* HyphenationCompoundWordTokenFilter(matchVersion, input, hyphenator,
* null, minWordSize, minSubwordSize, maxSubwordSize }
*/
+ public HyphenationCompoundWordTokenFilter(TokenStream input,
+ HyphenationTree hyphenator, int minWordSize, int minSubwordSize,
+ int maxSubwordSize) {
+ this(input, hyphenator, null, minWordSize, minSubwordSize,
+ maxSubwordSize, false);
+ }
+
+ /**
+ * @deprecated Use {@link #HyphenationCompoundWordTokenFilter(TokenStream,HyphenationTree,int,int,int)}
+ */
+ @Deprecated
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input,
HyphenationTree hyphenator, int minWordSize, int minSubwordSize,
int maxSubwordSize) {
this(matchVersion, input, hyphenator, null, minWordSize, minSubwordSize,
maxSubwordSize, false);
}
-
+
/**
* Create a HyphenationCompoundWordTokenFilter with no dictionary.
* <p>
- * Calls {@link #HyphenationCompoundWordTokenFilter(Version, TokenStream, HyphenationTree, int, int, int)
- * HyphenationCompoundWordTokenFilter(matchVersion, input, hyphenator,
+ * Calls {@link #HyphenationCompoundWordTokenFilter(org.apache.lucene.analysis.TokenStream, org.apache.lucene.analysis.compound.hyphenation.HyphenationTree, int, int, int)
+ * HyphenationCompoundWordTokenFilter(matchVersion, input, hyphenator,
* DEFAULT_MIN_WORD_SIZE, DEFAULT_MIN_SUBWORD_SIZE, DEFAULT_MAX_SUBWORD_SIZE }
*/
+ public HyphenationCompoundWordTokenFilter(TokenStream input,
+ HyphenationTree hyphenator) {
+ this(input, hyphenator, DEFAULT_MIN_WORD_SIZE, DEFAULT_MIN_SUBWORD_SIZE,
+ DEFAULT_MAX_SUBWORD_SIZE);
+ }
+
+ /**
+ * @deprecated Use {@link #HyphenationCompoundWordTokenFilter(TokenStream,HyphenationTree)}
+ */
+ @Deprecated
public HyphenationCompoundWordTokenFilter(Version matchVersion, TokenStream input,
HyphenationTree hyphenator) {
- this(matchVersion, input, hyphenator, DEFAULT_MIN_WORD_SIZE, DEFAULT_MIN_SUBWORD_SIZE,
+ this(matchVersion, input, hyphenator, DEFAULT_MIN_WORD_SIZE, DEFAULT_MIN_SUBWORD_SIZE,
DEFAULT_MAX_SUBWORD_SIZE);
}
/**
* Create a hyphenator tree
- *
+ *
* @param hyphenationFilename the filename of the XML grammar to load
* @return An object representing the hyphenation patterns
* @throws IOException If there is a low-level I/O error.
@@ -141,7 +174,7 @@ public class HyphenationCompoundWordToke
/**
* Create a hyphenator tree
- *
+ *
* @param hyphenationFile the file of the XML grammar to load
* @return An object representing the hyphenation patterns
* @throws IOException If there is a low-level I/O error.
@@ -153,7 +186,7 @@ public class HyphenationCompoundWordToke
/**
* Create a hyphenator tree
- *
+ *
* @param hyphenationSource the InputSource pointing to the XML grammar
* @return An object representing the hyphenation patterns
* @throws IOException If there is a low-level I/O error.
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilterFactory.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilterFactory.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilterFactory.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/compound/HyphenationCompoundWordTokenFilterFactory.java Thu Aug 21 03:12:52 2014
@@ -29,6 +29,8 @@ import org.apache.lucene.util.IOUtils;
import java.util.Map;
import java.io.IOException;
import java.io.InputStream;
+
+import org.apache.lucene.util.Version;
import org.xml.sax.InputSource;
/**
@@ -97,7 +99,11 @@ public class HyphenationCompoundWordToke
final InputSource is = new InputSource(stream);
is.setEncoding(encoding); // if it's null let xml parser decide
is.setSystemId(hypFile);
- hyphenator = HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
+ if (luceneMatchVersion.onOrAfter(Version.LUCENE_4_4_0)) {
+ hyphenator = HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
+ } else {
+ hyphenator = Lucene43HyphenationCompoundWordTokenFilter.getHyphenationTree(is);
+ }
} finally {
IOUtils.closeWhileHandlingException(stream);
}
@@ -105,6 +111,10 @@ public class HyphenationCompoundWordToke
@Override
public TokenFilter create(TokenStream input) {
- return new HyphenationCompoundWordTokenFilter(luceneMatchVersion, input, hyphenator, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
+ if (luceneMatchVersion.onOrAfter(Version.LUCENE_4_4_0)) {
+ return new HyphenationCompoundWordTokenFilter(input, hyphenator, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
+ }
+ return new Lucene43HyphenationCompoundWordTokenFilter(input, hyphenator, dictionary, minWordSize, minSubwordSize, maxSubwordSize, onlyLongestMatch);
+
}
}
Modified: lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/KeywordTokenizer.java
URL: http://svn.apache.org/viewvc/lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/KeywordTokenizer.java?rev=1619283&r1=1619282&r2=1619283&view=diff
==============================================================================
--- lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/KeywordTokenizer.java (original)
+++ lucene/dev/branches/branch_4x/lucene/analysis/common/src/java/org/apache/lucene/analysis/core/KeywordTokenizer.java Thu Aug 21 03:12:52 2014
@@ -24,7 +24,6 @@ import org.apache.lucene.analysis.Tokeni
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.util.AttributeFactory;
-import org.apache.lucene.util.AttributeSource;
/**
* Emits the entire input as a single token.