Created
March 5, 2012 17:44
-
-
Save hideaki-t/1979749 to your computer and use it in GitHub Desktop.
Kuromoji(will be included in lucene 3.6) test w/java7
This file contains 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
import org.apache.lucene.analysis.TokenStream; | |
import org.apache.lucene.analysis.ja.JapaneseAnalyzer; | |
import org.apache.lucene.analysis.ja.tokenattributes.BaseFormAttribute; | |
import org.apache.lucene.analysis.ja.tokenattributes.InflectionAttribute; | |
import org.apache.lucene.analysis.ja.tokenattributes.PartOfSpeechAttribute; | |
import org.apache.lucene.analysis.ja.tokenattributes.ReadingAttribute; | |
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; | |
import org.apache.lucene.util.Version; | |
import java.io.IOException; | |
import java.io.StringReader; | |
public class Test { | |
public static void main(String[] args) { | |
try (JapaneseAnalyzer t = new JapaneseAnalyzer(Version.LUCENE_36); | |
TokenStream ts = t.reusableTokenStream("txt", new StringReader("今日はカレーを食べました"))) { | |
while (ts.incrementToken()) { | |
CharTermAttribute term = ts.getAttribute(CharTermAttribute.class); | |
BaseFormAttribute base = ts.getAttribute(BaseFormAttribute.class); | |
PartOfSpeechAttribute pos = ts.getAttribute(PartOfSpeechAttribute.class); | |
ReadingAttribute read = ts.getAttribute(ReadingAttribute.class); | |
InflectionAttribute inflect = ts.getAttribute(InflectionAttribute.class); | |
System.out.println(term); | |
System.out.println(base); | |
System.out.println(pos); | |
System.out.println(read); | |
System.out.println(inflect); | |
} | |
} catch (IOException ioe) { | |
ioe.printStackTrace(); | |
} | |
} | |
} |
This file contains 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
import org.apache.lucene.analysis.ja.JapaneseTokenizer; | |
import org.apache.lucene.analysis.ja.tokenattributes.BaseFormAttribute; | |
import org.apache.lucene.analysis.ja.tokenattributes.InflectionAttribute; | |
import org.apache.lucene.analysis.ja.tokenattributes.PartOfSpeechAttribute; | |
import org.apache.lucene.analysis.ja.tokenattributes.ReadingAttribute; | |
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; | |
import java.io.IOException; | |
import java.io.StringReader; | |
public class TestTokenizer { | |
public static void main(String[] args) { | |
try (JapaneseTokenizer ts = new JapaneseTokenizer( | |
new StringReader("今日はカレーを食べました"), | |
null, false, JapaneseTokenizer.Mode.NORMAL)) { | |
while (ts.incrementToken()) { | |
CharTermAttribute term = ts.getAttribute(CharTermAttribute.class); | |
BaseFormAttribute base = ts.getAttribute(BaseFormAttribute.class); | |
PartOfSpeechAttribute pos = ts.getAttribute(PartOfSpeechAttribute.class); | |
ReadingAttribute read = ts.getAttribute(ReadingAttribute.class); | |
InflectionAttribute inflect = ts.getAttribute(InflectionAttribute.class); | |
System.out.println(term); | |
System.out.println(base); | |
System.out.println(pos); | |
System.out.println(read); | |
System.out.println(inflect); | |
} | |
} catch (IOException ioe) { | |
ioe.printStackTrace(); | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment