├── .gitignore ├── .travis.yml ├── CONTRIBUTING.md ├── LICENSE ├── README.md ├── docs ├── contribution-guide.md ├── imgs │ ├── img2-1.png │ ├── img2-2.png │ └── img2-3.png └── sbt.md ├── examples ├── pom.xml └── src │ └── main │ ├── java │ └── JavaTwitterKoreanTextExample.java │ └── scala │ └── ScalaTwitterKoreanTextExample.scala ├── pom.xml ├── settings.xml └── src ├── main ├── java │ └── com │ │ └── twitter │ │ └── penguin │ │ └── korean │ │ ├── KoreanPosJava.java │ │ ├── KoreanTokenJava.java │ │ ├── TwitterKoreanProcessorJava.java │ │ └── util │ │ ├── CharArrayMap.java │ │ ├── CharArraySet.java │ │ └── CharacterUtils.java ├── resources │ └── com │ │ └── twitter │ │ └── penguin │ │ └── korean │ │ └── util │ │ ├── adjective │ │ └── adjective.txt │ │ ├── adverb │ │ └── adverb.txt │ │ ├── auxiliary │ │ ├── conjunctions.txt │ │ ├── determiner.txt │ │ └── exclamation.txt │ │ ├── example_chunks.txt │ │ ├── example_tweets.txt │ │ ├── freq │ │ └── entity-freq.txt.gz │ │ ├── josa │ │ └── josa.txt │ │ ├── noun │ │ ├── bible.txt │ │ ├── company_names.txt │ │ ├── congress.txt │ │ ├── entities.txt │ │ ├── foreign.txt │ │ ├── geolocations.txt │ │ ├── kpop.txt │ │ ├── lol.txt │ │ ├── names.txt │ │ ├── nouns.txt │ │ ├── pokemon.txt │ │ ├── profane.txt │ │ ├── slangs.txt │ │ ├── spam.txt │ │ ├── twitter.txt │ │ └── wikipedia_title_nouns.txt │ │ ├── substantives │ │ ├── family_names.txt │ │ ├── given_names.txt │ │ ├── noun_prefix.txt │ │ └── suffix.txt │ │ ├── typos │ │ └── typos.txt │ │ └── verb │ │ ├── eomi.txt │ │ ├── pre_eomi.txt │ │ ├── verb.txt │ │ └── verb_prefix.txt └── scala │ └── com │ └── twitter │ └── penguin │ └── korean │ ├── TwitterKoreanProcessor.scala │ ├── normalizer │ └── KoreanNormalizer.scala │ ├── phrase_extractor │ └── KoreanPhraseExtractor.scala │ ├── qa │ ├── BatchGetUnknownNouns.scala │ ├── BatchTokenizeTweets.scala │ └── KoreanProcessorSandbox.scala │ ├── stemmer │ └── KoreanStemmer.scala │ ├── tokenizer │ ├── KoreanChunker.scala │ ├── KoreanDetokenizer.scala │ ├── KoreanSentenceSplitter.scala │ ├── KoreanTokenizer.scala │ ├── ParsedChunk.scala │ └── TokenizerProfile.scala │ ├── tools │ ├── CreateConjugationExamples.scala │ ├── CreateParsingExamples.scala │ ├── CreatePhraseExtractionExamples.scala │ ├── DeduplicateAndSortDictionaries.scala │ ├── Runnable.scala │ └── UpdateAllTheExamples.scala │ └── util │ ├── Hangul.scala │ ├── KoreanConjugation.scala │ ├── KoreanDictionaryProvider.scala │ ├── KoreanPos.scala │ └── KoreanSubstantive.scala └── test ├── java └── com │ └── twitter │ └── penguin │ └── korean │ └── TwitterKoreanProcessorJavaTest.java ├── resources └── com │ └── twitter │ └── penguin │ └── korean │ └── util │ ├── adj_conjugate.txt │ ├── current_parsing.txt │ ├── current_phrases.txt │ └── verb_conjugate.txt └── scala └── com └── twitter └── penguin └── korean ├── TestBase.scala ├── TwitterKoreanProcessorTest.scala ├── normalizer └── KoreanNormalizerTest.scala ├── phrase_extractor └── KoreanPhraseExtractorTest.scala ├── stemmer └── KoreanStemmerTest.scala ├── tokenizer ├── KoreanChunkerTest.scala ├── KoreanDetokenizerTest.scala ├── KoreanSentenceSplitterTest.scala └── KoreanTokenizerTest.scala └── util ├── HangulTest.scala ├── KoreanConjugationTest.scala ├── KoreanDictionaryProviderTest.scala ├── KoreanPosTest.scala └── KoreanSubstantiveTest.scala /.gitignore: -------------------------------------------------------------------------------- 1 | *.iml 2 | *.swp 3 | .DS_Store 4 | .idea 5 | target -------------------------------------------------------------------------------- /.travis.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/.travis.yml -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/README.md -------------------------------------------------------------------------------- /docs/contribution-guide.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/docs/contribution-guide.md -------------------------------------------------------------------------------- /docs/imgs/img2-1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/docs/imgs/img2-1.png -------------------------------------------------------------------------------- /docs/imgs/img2-2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/docs/imgs/img2-2.png -------------------------------------------------------------------------------- /docs/imgs/img2-3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/docs/imgs/img2-3.png -------------------------------------------------------------------------------- /docs/sbt.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/docs/sbt.md -------------------------------------------------------------------------------- /examples/pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/examples/pom.xml -------------------------------------------------------------------------------- /examples/src/main/java/JavaTwitterKoreanTextExample.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/examples/src/main/java/JavaTwitterKoreanTextExample.java -------------------------------------------------------------------------------- /examples/src/main/scala/ScalaTwitterKoreanTextExample.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/examples/src/main/scala/ScalaTwitterKoreanTextExample.scala -------------------------------------------------------------------------------- /pom.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/pom.xml -------------------------------------------------------------------------------- /settings.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/settings.xml -------------------------------------------------------------------------------- /src/main/java/com/twitter/penguin/korean/KoreanPosJava.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/java/com/twitter/penguin/korean/KoreanPosJava.java -------------------------------------------------------------------------------- /src/main/java/com/twitter/penguin/korean/KoreanTokenJava.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/java/com/twitter/penguin/korean/KoreanTokenJava.java -------------------------------------------------------------------------------- /src/main/java/com/twitter/penguin/korean/TwitterKoreanProcessorJava.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/java/com/twitter/penguin/korean/TwitterKoreanProcessorJava.java -------------------------------------------------------------------------------- /src/main/java/com/twitter/penguin/korean/util/CharArrayMap.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/java/com/twitter/penguin/korean/util/CharArrayMap.java -------------------------------------------------------------------------------- /src/main/java/com/twitter/penguin/korean/util/CharArraySet.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/java/com/twitter/penguin/korean/util/CharArraySet.java -------------------------------------------------------------------------------- /src/main/java/com/twitter/penguin/korean/util/CharacterUtils.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/java/com/twitter/penguin/korean/util/CharacterUtils.java -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/adjective/adjective.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/adjective/adjective.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/adverb/adverb.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/adverb/adverb.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/auxiliary/conjunctions.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/auxiliary/conjunctions.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/auxiliary/determiner.txt: -------------------------------------------------------------------------------- 1 | 그 2 | 내 3 | 네 4 | 다섯 5 | 두 6 | 아홉 7 | 여덟 8 | 여섯 9 | 이 10 | 일곱 11 | 저 12 | 한 13 | -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/auxiliary/exclamation.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/auxiliary/exclamation.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/example_chunks.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/example_chunks.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/example_tweets.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/example_tweets.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/freq/entity-freq.txt.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/freq/entity-freq.txt.gz -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/josa/josa.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/josa/josa.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/bible.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/bible.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/company_names.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/company_names.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/congress.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/congress.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/entities.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/entities.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/foreign.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/foreign.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/geolocations.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/geolocations.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/kpop.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/kpop.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/lol.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/lol.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/names.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/names.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/nouns.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/nouns.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/pokemon.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/pokemon.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/profane.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/profane.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/slangs.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/slangs.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/spam.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/spam.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/twitter.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/twitter.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/noun/wikipedia_title_nouns.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/noun/wikipedia_title_nouns.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/substantives/family_names.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/substantives/family_names.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/substantives/given_names.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/substantives/given_names.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/substantives/noun_prefix.txt: -------------------------------------------------------------------------------- 1 | 극 2 | 느티 3 | 두세 4 | 몇 5 | 뭔 6 | 아랫 7 | 올 8 | 재한 9 | -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/substantives/suffix.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/substantives/suffix.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/typos/typos.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/typos/typos.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/verb/eomi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/verb/eomi.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/verb/pre_eomi.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/verb/pre_eomi.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/verb/verb.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/resources/com/twitter/penguin/korean/util/verb/verb.txt -------------------------------------------------------------------------------- /src/main/resources/com/twitter/penguin/korean/util/verb/verb_prefix.txt: -------------------------------------------------------------------------------- 1 | 내 2 | 딱 3 | 못 4 | 발가 5 | 싸 6 | 안 7 | 엇 8 | 잘 9 | 짓 10 | 쵸 11 | -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/TwitterKoreanProcessor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/TwitterKoreanProcessor.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/normalizer/KoreanNormalizer.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/normalizer/KoreanNormalizer.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/phrase_extractor/KoreanPhraseExtractor.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/phrase_extractor/KoreanPhraseExtractor.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/qa/BatchGetUnknownNouns.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/qa/BatchGetUnknownNouns.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/qa/BatchTokenizeTweets.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/qa/BatchTokenizeTweets.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/qa/KoreanProcessorSandbox.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/qa/KoreanProcessorSandbox.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/stemmer/KoreanStemmer.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/stemmer/KoreanStemmer.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanChunker.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanChunker.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanDetokenizer.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanDetokenizer.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanSentenceSplitter.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanSentenceSplitter.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanTokenizer.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tokenizer/KoreanTokenizer.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tokenizer/ParsedChunk.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tokenizer/ParsedChunk.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tokenizer/TokenizerProfile.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tokenizer/TokenizerProfile.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tools/CreateConjugationExamples.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tools/CreateConjugationExamples.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tools/CreateParsingExamples.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tools/CreateParsingExamples.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tools/CreatePhraseExtractionExamples.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tools/CreatePhraseExtractionExamples.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tools/DeduplicateAndSortDictionaries.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tools/DeduplicateAndSortDictionaries.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tools/Runnable.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tools/Runnable.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/tools/UpdateAllTheExamples.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/tools/UpdateAllTheExamples.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/util/Hangul.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/util/Hangul.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/util/KoreanConjugation.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/util/KoreanConjugation.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/util/KoreanDictionaryProvider.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/util/KoreanDictionaryProvider.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/util/KoreanPos.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/util/KoreanPos.scala -------------------------------------------------------------------------------- /src/main/scala/com/twitter/penguin/korean/util/KoreanSubstantive.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/main/scala/com/twitter/penguin/korean/util/KoreanSubstantive.scala -------------------------------------------------------------------------------- /src/test/java/com/twitter/penguin/korean/TwitterKoreanProcessorJavaTest.java: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/java/com/twitter/penguin/korean/TwitterKoreanProcessorJavaTest.java -------------------------------------------------------------------------------- /src/test/resources/com/twitter/penguin/korean/util/adj_conjugate.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/resources/com/twitter/penguin/korean/util/adj_conjugate.txt -------------------------------------------------------------------------------- /src/test/resources/com/twitter/penguin/korean/util/current_parsing.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/resources/com/twitter/penguin/korean/util/current_parsing.txt -------------------------------------------------------------------------------- /src/test/resources/com/twitter/penguin/korean/util/current_phrases.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/resources/com/twitter/penguin/korean/util/current_phrases.txt -------------------------------------------------------------------------------- /src/test/resources/com/twitter/penguin/korean/util/verb_conjugate.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/resources/com/twitter/penguin/korean/util/verb_conjugate.txt -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/TestBase.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/TestBase.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/TwitterKoreanProcessorTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/TwitterKoreanProcessorTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/normalizer/KoreanNormalizerTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/normalizer/KoreanNormalizerTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/phrase_extractor/KoreanPhraseExtractorTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/phrase_extractor/KoreanPhraseExtractorTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/stemmer/KoreanStemmerTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/stemmer/KoreanStemmerTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/tokenizer/KoreanChunkerTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/tokenizer/KoreanChunkerTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/tokenizer/KoreanDetokenizerTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/tokenizer/KoreanDetokenizerTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/tokenizer/KoreanSentenceSplitterTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/tokenizer/KoreanSentenceSplitterTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/tokenizer/KoreanTokenizerTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/tokenizer/KoreanTokenizerTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/util/HangulTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/util/HangulTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/util/KoreanConjugationTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/util/KoreanConjugationTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/util/KoreanDictionaryProviderTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/util/KoreanDictionaryProviderTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/util/KoreanPosTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/util/KoreanPosTest.scala -------------------------------------------------------------------------------- /src/test/scala/com/twitter/penguin/korean/util/KoreanSubstantiveTest.scala: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/twitter/twitter-korean-text/HEAD/src/test/scala/com/twitter/penguin/korean/util/KoreanSubstantiveTest.scala --------------------------------------------------------------------------------