Examples of Lexeme

Examples of org.wltea.analyzer.Lexeme

69
70
71
72
73
74
75
76
77
78
79
   
    for(String t : testStr){
      System.out.println(t); 
      IKSegmentation ikSeg = new IKSegmentation(new StringReader(t) , true);
      try {
        Lexeme l = null;
        while( (l = ikSeg.next()) != null){
          System.out.println(l);
        }
      } catch (IOException e) {
        // TODO Auto-generated catch block
View Full Code Here

Examples of org.wltea.analyzer.Lexeme

135
136
137
138
139
140
141
142
143
144
145
    testStr.add("广州市越秀区广州大道中131-133号信龙大厦");
    for(String t : testStr){
      System.out.println(t); 
      IKSegmentation ikSeg = new IKSegmentation(new StringReader(t) , false);
      try {
        Lexeme l = null;
        while( (l = ikSeg.next()) != null){
          System.out.println(l);
        }
      } catch (IOException e) {
        // TODO Auto-generated catch block
View Full Code Here

Examples of org.wltea.analyzer.core.Lexeme

71
72
73
74
75
76
77
78
79
80
81
  private static List<Lexeme> doAnalyze(String keywords){
    List<Lexeme> lexemes = new ArrayList<Lexeme>();

    IKSegmenter ikSeg = new IKSegmenter(new StringReader(keywords));
    try{
      Lexeme l = null;
      while( (l = ikSeg.next()) != null){
        lexemes.add(l);
      }
    }catch(IOException e){
      e.printStackTrace();
View Full Code Here

Examples of org.wltea.analyzer.core.Lexeme

83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
  public boolean incrementToken() throws IOException {
    //清除所有的词元属性
    clearAttributes();
        skippedPositions = 0;

        Lexeme nextLexeme = _IKImplement.next();
    if(nextLexeme != null){
            posIncrAtt.setPositionIncrement(skippedPositions +1 );

      //将Lexeme转成Attributes
      //设置词元文本
      termAtt.append(nextLexeme.getLexemeText());
      //设置词元长度
      termAtt.setLength(nextLexeme.getLength());
      //设置词元位移
//      offsetAtt.setOffset(nextLexeme.getBeginPosition(), nextLexeme.getEndPosition());
            offsetAtt.setOffset(correctOffset(nextLexeme.getBeginPosition()), correctOffset(nextLexeme.getEndPosition()));

            //记录分词的最后位置
      endPosition = nextLexeme.getEndPosition();
      //记录词元分类
      typeAtt.setType(nextLexeme.getLexemeTypeString());     
      //返会true告知还有下个词元
      return true;
    }
    //返会false告知词元输出完毕
    return false;
View Full Code Here

Examples of r194.Lexer.Lexeme

14
15
16
17
18
19
20
21
22
23
24
  }
 
  public void filterTokens(){
    List<Lexeme> newTokens = new ArrayList<>();
    for (int i = 0; i < tokens.size(); i++) {
      Lexeme t = tokens.get(i);
      if (t.type != Token.WHITESPACE){
        newTokens.add(t);
      }
    }
    tokens = newTokens;
View Full Code Here

Examples of r194.Lexer.Lexeme

65
66
67
68
69
70
71
72
73
    }
  }
 
  public Lexeme lookahead(int i) {
    if (position + i >= tokens.size()){
      return new Lexeme("", Token.EOF);
    }
    return tokens.get(position + i);
  }
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.