├── .gitignore ├── COPYING ├── COPYING.LESSER ├── README ├── pom.xml └── src ├── main ├── java │ └── org │ │ └── wltea │ │ └── analyzer │ │ ├── Context.java │ │ ├── IKSegmentation.java │ │ ├── Lexeme.java │ │ ├── cfg │ │ └── Configuration.java │ │ ├── dic │ │ ├── DictSegment.java │ │ ├── Dictionary.java │ │ └── Hit.java │ │ ├── help │ │ └── CharacterHelper.java │ │ ├── lucene │ │ ├── IKAnalyzer.java │ │ ├── IKQueryParser.java │ │ ├── IKSimilarity.java │ │ └── IKTokenizer.java │ │ ├── sample │ │ └── IKAnalyzerDemo.java │ │ ├── seg │ │ ├── CJKSegmenter.java │ │ ├── ISegmenter.java │ │ ├── LetterSegmenter.java │ │ └── QuantifierSegmenter.java │ │ └── solr │ │ └── IKTokenizerFactory.java └── resources │ ├── IKAnalyzer.cfg.xml │ ├── ext_stopword.dic │ └── org │ └── wltea │ └── analyzer │ └── dic │ ├── main.dic │ ├── preposition.dic │ ├── quantifier.dic │ ├── stopword.dic │ ├── suffix.dic │ └── surname.dic └── test ├── java └── org │ └── wltea │ └── analyzer │ ├── cube │ └── HCube.java │ └── test │ ├── CfgTester.java │ ├── CharacterTest.java │ ├── DictionaryTester.java │ ├── IKTokenerTest.java │ ├── NumberSegmenter.java │ ├── SegmentorTester.java │ ├── SimpleQuantifierSegmenter.java │ └── StandardAnalyzerTest.java └── resources ├── CH_stopword.dic └── mydict.dic /.gitignore: -------------------------------------------------------------------------------- 1 | target 2 | .settings 3 | .classpath 4 | .project 5 | -------------------------------------------------------------------------------- /COPYING: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/COPYING -------------------------------------------------------------------------------- /COPYING.LESSER: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/COPYING.LESSER -------------------------------------------------------------------------------- /README: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/README -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/pom.xml -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/Context.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/Context.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/IKSegmentation.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/IKSegmentation.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/Lexeme.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/Lexeme.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/cfg/Configuration.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/cfg/Configuration.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/dic/DictSegment.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/dic/DictSegment.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/dic/Dictionary.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/dic/Dictionary.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/dic/Hit.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/dic/Hit.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/help/CharacterHelper.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/help/CharacterHelper.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/lucene/IKAnalyzer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/lucene/IKAnalyzer.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/lucene/IKQueryParser.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/lucene/IKQueryParser.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/lucene/IKSimilarity.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/lucene/IKSimilarity.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/lucene/IKTokenizer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/lucene/IKTokenizer.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/sample/IKAnalyzerDemo.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/sample/IKAnalyzerDemo.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/seg/CJKSegmenter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/seg/CJKSegmenter.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/seg/ISegmenter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/seg/ISegmenter.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/seg/LetterSegmenter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/seg/LetterSegmenter.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/seg/QuantifierSegmenter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/seg/QuantifierSegmenter.java -------------------------------------------------------------------------------- /src/main/java/org/wltea/analyzer/solr/IKTokenizerFactory.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/java/org/wltea/analyzer/solr/IKTokenizerFactory.java -------------------------------------------------------------------------------- /src/main/resources/IKAnalyzer.cfg.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/resources/IKAnalyzer.cfg.xml -------------------------------------------------------------------------------- /src/main/resources/ext_stopword.dic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/resources/ext_stopword.dic -------------------------------------------------------------------------------- /src/main/resources/org/wltea/analyzer/dic/main.dic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/resources/org/wltea/analyzer/dic/main.dic -------------------------------------------------------------------------------- /src/main/resources/org/wltea/analyzer/dic/preposition.dic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/resources/org/wltea/analyzer/dic/preposition.dic -------------------------------------------------------------------------------- /src/main/resources/org/wltea/analyzer/dic/quantifier.dic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/resources/org/wltea/analyzer/dic/quantifier.dic -------------------------------------------------------------------------------- /src/main/resources/org/wltea/analyzer/dic/stopword.dic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/resources/org/wltea/analyzer/dic/stopword.dic -------------------------------------------------------------------------------- /src/main/resources/org/wltea/analyzer/dic/suffix.dic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/resources/org/wltea/analyzer/dic/suffix.dic -------------------------------------------------------------------------------- /src/main/resources/org/wltea/analyzer/dic/surname.dic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/main/resources/org/wltea/analyzer/dic/surname.dic -------------------------------------------------------------------------------- /src/test/java/org/wltea/analyzer/cube/HCube.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/test/java/org/wltea/analyzer/cube/HCube.java -------------------------------------------------------------------------------- /src/test/java/org/wltea/analyzer/test/CfgTester.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/test/java/org/wltea/analyzer/test/CfgTester.java -------------------------------------------------------------------------------- /src/test/java/org/wltea/analyzer/test/CharacterTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/test/java/org/wltea/analyzer/test/CharacterTest.java -------------------------------------------------------------------------------- /src/test/java/org/wltea/analyzer/test/DictionaryTester.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/test/java/org/wltea/analyzer/test/DictionaryTester.java -------------------------------------------------------------------------------- /src/test/java/org/wltea/analyzer/test/IKTokenerTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/test/java/org/wltea/analyzer/test/IKTokenerTest.java -------------------------------------------------------------------------------- /src/test/java/org/wltea/analyzer/test/NumberSegmenter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/test/java/org/wltea/analyzer/test/NumberSegmenter.java -------------------------------------------------------------------------------- /src/test/java/org/wltea/analyzer/test/SegmentorTester.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/test/java/org/wltea/analyzer/test/SegmentorTester.java -------------------------------------------------------------------------------- /src/test/java/org/wltea/analyzer/test/SimpleQuantifierSegmenter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/test/java/org/wltea/analyzer/test/SimpleQuantifierSegmenter.java -------------------------------------------------------------------------------- /src/test/java/org/wltea/analyzer/test/StandardAnalyzerTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/test/java/org/wltea/analyzer/test/StandardAnalyzerTest.java -------------------------------------------------------------------------------- /src/test/resources/CH_stopword.dic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wks/ik-analyzer/HEAD/src/test/resources/CH_stopword.dic -------------------------------------------------------------------------------- /src/test/resources/mydict.dic: -------------------------------------------------------------------------------- 1 | 房 --------------------------------------------------------------------------------