├── .gitignore ├── LICENSE ├── Makefile ├── README.md ├── head ├── thucke │ ├── articleSpliter.h │ ├── keyword.h │ └── trie.h └── thulac │ ├── cb_decoder.h │ ├── cb_model.h │ ├── cb_ngram_feature.h │ ├── cb_tagging_decoder.h │ ├── dat.h │ ├── filter.h │ ├── negword.h │ ├── postprocess.h │ ├── preprocess.h │ ├── punctuation.h │ ├── segment_wrapper.h │ ├── thulac_base.h │ ├── thulac_character.h │ ├── thulac_raw.h │ ├── thulac_segment.h │ ├── timeword.h │ └── verbword.h ├── src ├── articleSpliter.cpp ├── keywordExtract.cpp ├── keywordLoad.cpp ├── thucke.cpp ├── thulac_segment.cpp └── trie.cpp ├── test1.txt └── test2.txt /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/LICENSE -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/Makefile -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/README.md -------------------------------------------------------------------------------- /head/thucke/articleSpliter.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thucke/articleSpliter.h -------------------------------------------------------------------------------- /head/thucke/keyword.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thucke/keyword.h -------------------------------------------------------------------------------- /head/thucke/trie.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thucke/trie.h -------------------------------------------------------------------------------- /head/thulac/cb_decoder.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/cb_decoder.h -------------------------------------------------------------------------------- /head/thulac/cb_model.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/cb_model.h -------------------------------------------------------------------------------- /head/thulac/cb_ngram_feature.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/cb_ngram_feature.h -------------------------------------------------------------------------------- /head/thulac/cb_tagging_decoder.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/cb_tagging_decoder.h -------------------------------------------------------------------------------- /head/thulac/dat.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/dat.h -------------------------------------------------------------------------------- /head/thulac/filter.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/filter.h -------------------------------------------------------------------------------- /head/thulac/negword.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/negword.h -------------------------------------------------------------------------------- /head/thulac/postprocess.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/postprocess.h -------------------------------------------------------------------------------- /head/thulac/preprocess.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/preprocess.h -------------------------------------------------------------------------------- /head/thulac/punctuation.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/punctuation.h -------------------------------------------------------------------------------- /head/thulac/segment_wrapper.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/segment_wrapper.h -------------------------------------------------------------------------------- /head/thulac/thulac_base.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/thulac_base.h -------------------------------------------------------------------------------- /head/thulac/thulac_character.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/thulac_character.h -------------------------------------------------------------------------------- /head/thulac/thulac_raw.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/thulac_raw.h -------------------------------------------------------------------------------- /head/thulac/thulac_segment.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/thulac_segment.h -------------------------------------------------------------------------------- /head/thulac/timeword.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/timeword.h -------------------------------------------------------------------------------- /head/thulac/verbword.h: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/head/thulac/verbword.h -------------------------------------------------------------------------------- /src/articleSpliter.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/src/articleSpliter.cpp -------------------------------------------------------------------------------- /src/keywordExtract.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/src/keywordExtract.cpp -------------------------------------------------------------------------------- /src/keywordLoad.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/src/keywordLoad.cpp -------------------------------------------------------------------------------- /src/thucke.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/src/thucke.cpp -------------------------------------------------------------------------------- /src/thulac_segment.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/src/thulac_segment.cpp -------------------------------------------------------------------------------- /src/trie.cpp: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/src/trie.cpp -------------------------------------------------------------------------------- /test1.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/test1.txt -------------------------------------------------------------------------------- /test2.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/thunlp/THUCKE/HEAD/test2.txt --------------------------------------------------------------------------------