├── .classpath ├── .gitignore ├── .project ├── Data ├── BIG2GBK.map ├── BIG5.pdat ├── BIG5.wordlist ├── BiWord.big ├── Configure.xml ├── CoreDict.pdat ├── CoreDict.pos ├── CoreDict.unig ├── FieldDict.pdat ├── FieldDict.pos ├── GBK.pdat ├── GBK.wordlist ├── GBK2BIG.map ├── GBK2GBKC.map ├── GBK2UTF.map ├── GBKA.pdat ├── GBKA.wordlist ├── GBKA2UTF.map ├── GBKC.pdat ├── GBKC.wordlist ├── GBKC2GBK.map ├── GranDict.pdat ├── GranDict.pos ├── ICTPOS.map ├── NLPIR.ctx ├── NLPIR.user ├── NLPIR_First.map ├── NewWord.lst ├── PKU.map ├── PKU_First.map ├── UTF2GBK.map ├── UTF2GBKA.map ├── UTF8.pdat ├── UTF8.wordlist ├── UserDict.pdat ├── charset.type ├── nr.ctx ├── nr.fsa └── nr.role ├── NLPIR.dll ├── NLPIR.h ├── NLPIR.lib ├── NLPIR_JNI.dll ├── README.md ├── docs ├── ICTCLAS-汉语词性标注集 ├── References └── 文本分类算法中词语权重计算方法的改进.pdf ├── lib ├── commons-logging-1.1.2.jar ├── hamcrest-core-1.3.jar ├── junit-4.11.jar ├── log4j-1.2.16.jar ├── lucene-core-4.0.0.jar ├── mmseg4j-analysis-1.9.1.jar ├── mmseg4j-core-1.9.1.jar └── slf4j-api-1.6.2.jar └── src ├── ictclas └── java │ └── kevin │ └── zhang │ └── NLPIR.java ├── main ├── java │ └── org │ │ └── shirdrn │ │ └── document │ │ └── processor │ │ ├── AbstractDocumentProcessorDriver.java │ │ ├── TestDocumentProcessorDriver.java │ │ ├── TrainDocumentProcessorDriver.java │ │ ├── analyzer │ │ ├── AbstractDocumentAnalyzer.java │ │ ├── IctclasAnalyzer.java │ │ └── MMSeg4jAnalyzer.java │ │ ├── common │ │ ├── AbstractComponent.java │ │ ├── Component.java │ │ ├── Context.java │ │ ├── DocumentAnalyzer.java │ │ ├── FDMetadata.java │ │ ├── LexicalCategory.java │ │ ├── ProcessorType.java │ │ ├── Term.java │ │ ├── TermFilter.java │ │ └── VectorMetadata.java │ │ ├── component │ │ ├── AbstractOutputtingQuantizedData.java │ │ ├── BasicInformationCollector.java │ │ ├── DocumentTFIDFComputation.java │ │ ├── DocumentWordsCollector.java │ │ ├── test │ │ │ ├── LoadFeatureTermVector.java │ │ │ └── OutputtingQuantizedTestData.java │ │ └── train │ │ │ ├── FeatureTermVectorSelector.java │ │ │ └── OutputtingQuantizedTrainData.java │ │ ├── config │ │ ├── Configuration.java │ │ ├── ContextReadable.java │ │ └── ContextWriteable.java │ │ ├── filter │ │ ├── AggregatedTermFilter.java │ │ ├── LexicalCategoryFilter.java │ │ ├── SingleWordTermFilter.java │ │ └── StopwordsTermFilter.java │ │ └── utils │ │ ├── CheckUtils.java │ │ ├── MetricUtils.java │ │ ├── ReflectionUtils.java │ │ ├── SortUtils.java │ │ └── UTF8Encoding.java └── resources │ ├── config-test.properties │ ├── config-train.properties │ ├── log4j.properties │ └── stopwords │ └── 中文停用词表.txt └── test ├── java └── org │ └── shirdrn │ └── document │ └── processor │ └── analyzer │ └── TestIctclasAnalyzer.java └── resources ├── config-test.properties └── config-train.properties /.classpath: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/.classpath -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/.gitignore -------------------------------------------------------------------------------- /.project: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/.project -------------------------------------------------------------------------------- /Data/BIG2GBK.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/BIG2GBK.map -------------------------------------------------------------------------------- /Data/BIG5.pdat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/BIG5.pdat -------------------------------------------------------------------------------- /Data/BIG5.wordlist: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/BIG5.wordlist -------------------------------------------------------------------------------- /Data/BiWord.big: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/BiWord.big -------------------------------------------------------------------------------- /Data/Configure.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/Configure.xml -------------------------------------------------------------------------------- /Data/CoreDict.pdat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/CoreDict.pdat -------------------------------------------------------------------------------- /Data/CoreDict.pos: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/CoreDict.pos -------------------------------------------------------------------------------- /Data/CoreDict.unig: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/CoreDict.unig -------------------------------------------------------------------------------- /Data/FieldDict.pdat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/FieldDict.pdat -------------------------------------------------------------------------------- /Data/FieldDict.pos: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/FieldDict.pos -------------------------------------------------------------------------------- /Data/GBK.pdat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBK.pdat -------------------------------------------------------------------------------- /Data/GBK.wordlist: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBK.wordlist -------------------------------------------------------------------------------- /Data/GBK2BIG.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBK2BIG.map -------------------------------------------------------------------------------- /Data/GBK2GBKC.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBK2GBKC.map -------------------------------------------------------------------------------- /Data/GBK2UTF.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBK2UTF.map -------------------------------------------------------------------------------- /Data/GBKA.pdat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBKA.pdat -------------------------------------------------------------------------------- /Data/GBKA.wordlist: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBKA.wordlist -------------------------------------------------------------------------------- /Data/GBKA2UTF.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBKA2UTF.map -------------------------------------------------------------------------------- /Data/GBKC.pdat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBKC.pdat -------------------------------------------------------------------------------- /Data/GBKC.wordlist: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBKC.wordlist -------------------------------------------------------------------------------- /Data/GBKC2GBK.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GBKC2GBK.map -------------------------------------------------------------------------------- /Data/GranDict.pdat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GranDict.pdat -------------------------------------------------------------------------------- /Data/GranDict.pos: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/GranDict.pos -------------------------------------------------------------------------------- /Data/ICTPOS.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/ICTPOS.map -------------------------------------------------------------------------------- /Data/NLPIR.ctx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/NLPIR.ctx -------------------------------------------------------------------------------- /Data/NLPIR.user: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/NLPIR.user -------------------------------------------------------------------------------- /Data/NLPIR_First.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/NLPIR_First.map -------------------------------------------------------------------------------- /Data/NewWord.lst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/NewWord.lst -------------------------------------------------------------------------------- /Data/PKU.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/PKU.map -------------------------------------------------------------------------------- /Data/PKU_First.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/PKU_First.map -------------------------------------------------------------------------------- /Data/UTF2GBK.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/UTF2GBK.map -------------------------------------------------------------------------------- /Data/UTF2GBKA.map: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/UTF2GBKA.map -------------------------------------------------------------------------------- /Data/UTF8.pdat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/UTF8.pdat -------------------------------------------------------------------------------- /Data/UTF8.wordlist: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/UTF8.wordlist -------------------------------------------------------------------------------- /Data/UserDict.pdat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/UserDict.pdat -------------------------------------------------------------------------------- /Data/charset.type: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/charset.type -------------------------------------------------------------------------------- /Data/nr.ctx: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/nr.ctx -------------------------------------------------------------------------------- /Data/nr.fsa: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/nr.fsa -------------------------------------------------------------------------------- /Data/nr.role: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/Data/nr.role -------------------------------------------------------------------------------- /NLPIR.dll: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/NLPIR.dll -------------------------------------------------------------------------------- /NLPIR.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/NLPIR.h -------------------------------------------------------------------------------- /NLPIR.lib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/NLPIR.lib -------------------------------------------------------------------------------- /NLPIR_JNI.dll: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/NLPIR_JNI.dll -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/README.md -------------------------------------------------------------------------------- /docs/ICTCLAS-汉语词性标注集: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/docs/ICTCLAS-汉语词性标注集 -------------------------------------------------------------------------------- /docs/References: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/docs/References -------------------------------------------------------------------------------- /docs/文本分类算法中词语权重计算方法的改进.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/docs/文本分类算法中词语权重计算方法的改进.pdf -------------------------------------------------------------------------------- /lib/commons-logging-1.1.2.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/lib/commons-logging-1.1.2.jar -------------------------------------------------------------------------------- /lib/hamcrest-core-1.3.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/lib/hamcrest-core-1.3.jar -------------------------------------------------------------------------------- /lib/junit-4.11.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/lib/junit-4.11.jar -------------------------------------------------------------------------------- /lib/log4j-1.2.16.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/lib/log4j-1.2.16.jar -------------------------------------------------------------------------------- /lib/lucene-core-4.0.0.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/lib/lucene-core-4.0.0.jar -------------------------------------------------------------------------------- /lib/mmseg4j-analysis-1.9.1.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/lib/mmseg4j-analysis-1.9.1.jar -------------------------------------------------------------------------------- /lib/mmseg4j-core-1.9.1.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/lib/mmseg4j-core-1.9.1.jar -------------------------------------------------------------------------------- /lib/slf4j-api-1.6.2.jar: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/lib/slf4j-api-1.6.2.jar -------------------------------------------------------------------------------- /src/ictclas/java/kevin/zhang/NLPIR.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/ictclas/java/kevin/zhang/NLPIR.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/AbstractDocumentProcessorDriver.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/AbstractDocumentProcessorDriver.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/TestDocumentProcessorDriver.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/TestDocumentProcessorDriver.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/TrainDocumentProcessorDriver.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/TrainDocumentProcessorDriver.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/analyzer/AbstractDocumentAnalyzer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/analyzer/AbstractDocumentAnalyzer.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/analyzer/IctclasAnalyzer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/analyzer/IctclasAnalyzer.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/analyzer/MMSeg4jAnalyzer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/analyzer/MMSeg4jAnalyzer.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/common/AbstractComponent.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/common/AbstractComponent.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/common/Component.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/common/Component.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/common/Context.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/common/Context.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/common/DocumentAnalyzer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/common/DocumentAnalyzer.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/common/FDMetadata.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/common/FDMetadata.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/common/LexicalCategory.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/common/LexicalCategory.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/common/ProcessorType.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/common/ProcessorType.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/common/Term.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/common/Term.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/common/TermFilter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/common/TermFilter.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/common/VectorMetadata.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/common/VectorMetadata.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/component/AbstractOutputtingQuantizedData.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/component/AbstractOutputtingQuantizedData.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/component/BasicInformationCollector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/component/BasicInformationCollector.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/component/DocumentTFIDFComputation.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/component/DocumentTFIDFComputation.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/component/DocumentWordsCollector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/component/DocumentWordsCollector.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/component/test/LoadFeatureTermVector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/component/test/LoadFeatureTermVector.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/component/test/OutputtingQuantizedTestData.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/component/test/OutputtingQuantizedTestData.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/component/train/FeatureTermVectorSelector.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/component/train/FeatureTermVectorSelector.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/component/train/OutputtingQuantizedTrainData.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/component/train/OutputtingQuantizedTrainData.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/config/Configuration.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/config/Configuration.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/config/ContextReadable.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/config/ContextReadable.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/config/ContextWriteable.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/config/ContextWriteable.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/filter/AggregatedTermFilter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/filter/AggregatedTermFilter.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/filter/LexicalCategoryFilter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/filter/LexicalCategoryFilter.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/filter/SingleWordTermFilter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/filter/SingleWordTermFilter.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/filter/StopwordsTermFilter.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/filter/StopwordsTermFilter.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/utils/CheckUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/utils/CheckUtils.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/utils/MetricUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/utils/MetricUtils.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/utils/ReflectionUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/utils/ReflectionUtils.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/utils/SortUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/utils/SortUtils.java -------------------------------------------------------------------------------- /src/main/java/org/shirdrn/document/processor/utils/UTF8Encoding.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/java/org/shirdrn/document/processor/utils/UTF8Encoding.java -------------------------------------------------------------------------------- /src/main/resources/config-test.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/resources/config-test.properties -------------------------------------------------------------------------------- /src/main/resources/config-train.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/resources/config-train.properties -------------------------------------------------------------------------------- /src/main/resources/log4j.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/resources/log4j.properties -------------------------------------------------------------------------------- /src/main/resources/stopwords/中文停用词表.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/main/resources/stopwords/中文停用词表.txt -------------------------------------------------------------------------------- /src/test/java/org/shirdrn/document/processor/analyzer/TestIctclasAnalyzer.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/test/java/org/shirdrn/document/processor/analyzer/TestIctclasAnalyzer.java -------------------------------------------------------------------------------- /src/test/resources/config-test.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/test/resources/config-test.properties -------------------------------------------------------------------------------- /src/test/resources/config-train.properties: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shirdrn/document-processor/HEAD/src/test/resources/config-train.properties --------------------------------------------------------------------------------