Created
February 29, 2012 02:15
-
-
Save mike-neck/1937011 to your computer and use it in GitHub Desktop.
KuromojiというJavaでできた形態素解析器を使ってみた。
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| @GrabResolver ( | |
| name='ATILIKA dependencies', | |
| root='http://www.atilika.org/nexus/content/repositories/atilika') | |
| @Grab ('org.atilika.kuromoji:kuromoji:0.7.6') | |
| import org.atilika.kuromoji.Token | |
| import org.atilika.kuromoji.Tokenizer | |
| import org.atilika.kuromoji.Tokenizer.Mode | |
| def tokenizer = Tokenizer.builder().build() | |
| def tokens = tokenizer.tokenize('すもももももももものうち。') | |
| tokens.each { | |
| println "======================${it}========================" | |
| println "allFeatures : ${it.allFeatures}" | |
| println "partOfSpeech : ${it.partOfSpeech}" | |
| println "position : ${it.position}" | |
| println "reading : ${it.reading}" | |
| println "surfaceFrom : ${it.surfaceForm}" | |
| println "allFeaturesArray : ${it.allFeaturesArray.join(', ')}" | |
| println "known : ${it.known}" | |
| println "unknown : ${it.unknown}" | |
| println "user defined : ${it.user}" | |
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ======================org.atilika.kuromoji.Token@b317ad9======================== | |
| allFeatures : 名詞,一般,*,*,*,*,すもも,スモモ,スモモ | |
| partOfSpeech : 名詞,一般,*,* | |
| position : 0 | |
| reading : スモモ | |
| surfaceFrom : すもも | |
| allFeaturesArray : 名詞, 一般, *, *, *, *, すもも, スモモ, スモモ | |
| known : true | |
| unknown : false | |
| user defined : false | |
| ======================org.atilika.kuromoji.Token@5d78424c======================== | |
| allFeatures : 助詞,係助詞,*,*,*,*,も,モ,モ | |
| partOfSpeech : 助詞,係助詞,*,* | |
| position : 3 | |
| reading : モ | |
| surfaceFrom : も | |
| allFeaturesArray : 助詞, 係助詞, *, *, *, *, も, モ, モ | |
| known : true | |
| unknown : false | |
| user defined : false | |
| ======================org.atilika.kuromoji.Token@248bb85======================== | |
| allFeatures : 名詞,一般,*,*,*,*,もも,モモ,モモ | |
| partOfSpeech : 名詞,一般,*,* | |
| position : 4 | |
| reading : モモ | |
| surfaceFrom : もも | |
| allFeaturesArray : 名詞, 一般, *, *, *, *, もも, モモ, モモ | |
| known : true | |
| unknown : false | |
| user defined : false | |
| ======================org.atilika.kuromoji.Token@750f19ee======================== | |
| allFeatures : 助詞,係助詞,*,*,*,*,も,モ,モ | |
| partOfSpeech : 助詞,係助詞,*,* | |
| position : 6 | |
| reading : モ | |
| surfaceFrom : も | |
| allFeaturesArray : 助詞, 係助詞, *, *, *, *, も, モ, モ | |
| known : true | |
| unknown : false | |
| user defined : false | |
| ======================org.atilika.kuromoji.Token@326f944c======================== | |
| allFeatures : 名詞,一般,*,*,*,*,もも,モモ,モモ | |
| partOfSpeech : 名詞,一般,*,* | |
| position : 7 | |
| reading : モモ | |
| surfaceFrom : もも | |
| allFeaturesArray : 名詞, 一般, *, *, *, *, もも, モモ, モモ | |
| known : true | |
| unknown : false | |
| user defined : false | |
| ======================org.atilika.kuromoji.Token@3b712372======================== | |
| allFeatures : 助詞,連体化,*,*,*,*,の,ノ,ノ | |
| partOfSpeech : 助詞,連体化,*,* | |
| position : 9 | |
| reading : ノ | |
| surfaceFrom : の | |
| allFeaturesArray : 助詞, 連体化, *, *, *, *, の, ノ, ノ | |
| known : true | |
| unknown : false | |
| user defined : false | |
| ======================org.atilika.kuromoji.Token@ce2fdb======================== | |
| allFeatures : 名詞,非自立,副詞可能,*,*,*,うち,ウチ,ウチ | |
| partOfSpeech : 名詞,非自立,副詞可能,* | |
| position : 10 | |
| reading : ウチ | |
| surfaceFrom : うち | |
| allFeaturesArray : 名詞, 非自立, 副詞可能, *, *, *, うち, ウチ, ウチ | |
| known : true | |
| unknown : false | |
| user defined : false | |
| ======================org.atilika.kuromoji.Token@60a7d346======================== | |
| allFeatures : 記号,句点,*,*,*,*,。,。,。 | |
| partOfSpeech : 記号,句点,*,* | |
| position : 12 | |
| reading : 。 | |
| surfaceFrom : 。 | |
| allFeaturesArray : 記号, 句点, *, *, *, *, 。, 。, 。 | |
| known : true | |
| unknown : false | |
| user defined : false |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment