Examples of stem()


Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer.stem()

            vectorCreator = (WVTVectorCreator) config.getComponentForStep(WVTConfiguration.STEP_VECTOR_CREATION, d);

            // Process the document

            TokenEnumeration tokens = stemmer.stem(wordFilter.filter(tokenizer.tokenize(charConverter.convertChars(new StringReader(text), d), d), d), d);

            while (tokens.hasMoreTokens()) {
                wordList.addWordOccurance(tokens.nextToken());
            }
View Full Code Here

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer.stem()

                wordFilter = (WVTWordFilter) config.getComponentForStep(WVTConfiguration.STEP_WORDFILTER, d);
                stemmer = (WVTStemmer) config.getComponentForStep(WVTConfiguration.STEP_STEMMER, d);

                // Process the document

                TokenEnumeration tokens = stemmer.stem(wordFilter.filter(tokenizer.tokenize(charConverter.convertChars(infilter.convertToPlainText(loader.loadDocument(d), d), d), d), d), d);

                while (tokens.hasMoreTokens()) {
                    listener.processWord(tokens.nextToken());
                }
View Full Code Here

Examples of org.carrot2.text.linguistic.IStemmer.stem()

            if (buffer.length < word.length) buffer = new char [word.length];

            final boolean different = CharArrayUtils.toLowerCase(word, buffer);

            mutableCharArray.reset(buffer, 0, word.length);
            final CharSequence stemmed = stemmer.stem(mutableCharArray);
            if (stemmed != null)
            {
                mutableCharArray.reset(stemmed);
                stemImages[i] = context.intern(mutableCharArray);
            }
View Full Code Here

Examples of org.tartarus.snowball.EnglishStemmer.stem()

          if( mp.isTagOf(POSTag.UN)
              && mp.getCharSet() == CharSetType.ENGLISH )
          {
            keyword = new Keyword(mp);
            engStemmer.setCurrent(keyword.getString().toLowerCase());
            engStemmer.stem();
            keyword.setString(engStemmer.getCurrent());
            ret.add(keyword);
          }
          // 사랑하 로 추출된 경우 명사 '사랑'을 색인어로 추출
          else if( mp.isTagOf(POSTag.V) ) {
View Full Code Here

Examples of org.tartarus.snowball.SnowballStemmer.stem()

        for (String part : stopWord.split(" ")) {
          if (sb.length() > 0)
            sb.append(" ");
          stemmer.setCurrent(part);
          stemmer.stem();
          sb.append(stemmer.getCurrent());
        }

        stopSet.add(sb.toString());
      }
View Full Code Here

Examples of org.tartarus.snowball.SnowballStemmer.stem()

        {
          continue;
        }
       
        stemmer.setCurrent(words[i]);
        stemmer.stem();
        String stemmed = stemmer.getCurrent();
       
        if(!loadedWords.contains(stemmed))
        {
          continue;
View Full Code Here

Examples of org.tartarus.snowball.SnowballStemmer.stem()

      {
        continue;
      }
     
      stemmer.setCurrent(words[i]);
      stemmer.stem();
      String stemmed = stemmer.getCurrent();
     
      if(!loadedWords.contains(stemmed))
      {
        continue;
View Full Code Here

Examples of org.tartarus.snowball.SnowballStemmer.stem()

      {
        continue;
      }
     
      stemmer.setCurrent(words[i]);
      stemmer.stem();
      String stemmed = stemmer.getCurrent();
     
     
      if(text.indexOf(stemmed) >= 0)
      {
View Full Code Here

Examples of org.tartarus.snowball.SnowballStemmer.stem()

      {
        continue;
      }
     
      stemmer.setCurrent(words[i]);
      stemmer.stem();
      String stemmed = stemmer.getCurrent();
     
      if(VerifyParents.getParent(fields.get(1)) == null)
      {
        if(stemWordsTotal.containsKey(stemmed))
View Full Code Here

Examples of org.tartarus.snowball.ext.EnglishStemmer.stem()

    String[] test = {"bank", "banks", "banking", "banker", "banked", "bankers"};//<co id="stemmer.co.test"/>
    String[] gold = {"bank", "bank", "bank", "banker", "bank", "banker"};//<co id="stemmer.co.gold"/>
    for (int i = 0; i < test.length; i++) {
      english.setCurrent(test[i]);//<co id="stemmer.co.set"/>
      english.stem();//<co id="stemmer.co.stem"/>
      System.out.println("English: " + english.getCurrent());
      assertTrue(english.getCurrent() + " is not equal to " + gold[i], english.getCurrent().equals(gold[i]) == true);
    }
    /*
<calloutlist>
 
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.