How to use

com.chenlb.mmseg4j.Word

constructor

private Word createWord(StringBuilder bufSentence, int startIdx, String type) {
  return new Word(toChars(bufSentence), startIdx, type);
}
 

private Word createWord(StringBuilder bufSentence, int startIdx, String type) {
  return new Word(toChars(bufSentence), startIdx, type);
}
 

private Word createWord(StringBuilder bufSentence, int startIdx, String type) {
  return new Word(toChars(bufSentence), startIdx, type);
}
 

private Word createWord(StringBuilder bufSentence, String type) {
  return new Word(toChars(bufSentence), startIdx(bufSentence), type);
}
 

private Word createWord(StringBuilder bufSentence, String type) {
  return new Word(toChars(bufSentence), startIdx(bufSentence), type);
}
 

private Word createWord(StringBuilder bufSentence, String type) {
  return new Word(toChars(bufSentence), startIdx(bufSentence), type);
}
 

int idx = search(chs, offset, 1);
if(idx > -1) {
  cks.add(new Word(chs, senStartOffset, offset, 2));
  end = offset+2;
  n++;
} else if(offset >= end) {	//有单字
  cks.add(new Word(chs, senStartOffset, offset, 1));
  end = offset+1;
cks.add(new Word(chs, senStartOffset, offset, 1));

int idx = search(chs, offset, 1);
if(idx > -1) {
  cks.add(new Word(chs, senStartOffset, offset, 2));
  end = offset+2;
  n++;
} else if(offset >= end) {	//有单字
  cks.add(new Word(chs, senStartOffset, offset, 1));
  end = offset+1;
cks.add(new Word(chs, senStartOffset, offset, 1));

int idx = search(chs, offset, 1);
if(idx > -1) {
  cks.add(new Word(chs, senStartOffset, offset, 2));
  end = offset+2;
  n++;
} else if(offset >= end) {	//有单字
  cks.add(new Word(chs, senStartOffset, offset, 1));
  end = offset+1;
cks.add(new Word(chs, senStartOffset, offset, 1));

private Chunk createChunk(Sentence sen, char[] chs, int[] tailLen, int[] offsets, CharNode[] cns/*, char[][] cks*/) {
  Chunk ck = new Chunk();
  
  for(int i=0; i<3; i++) {
    if(offsets[i] < chs.length) {
      ck.words[i] = new Word(chs, sen.getStartOffset(), offsets[i], tailLen[i]+1);//new Word(cks[i], sen.getStartOffset()+offsets[i]);
      if(tailLen[i] == 0) {	//单字的要取得"字频计算出自由度"
        CharNode cn = cns[i];    //dic.head(chs[offsets[i]]);
        if(cn !=null) {
          ck.words[i].setDegree(cn.getFreq());
        }
      }
    }
  }
  return ck;
}
 

private Chunk createChunk(Sentence sen, char[] chs, int[] tailLen, int[] offsets, CharNode[] cns/*, char[][] cks*/) {
  Chunk ck = new Chunk();
  
  for(int i=0; i<3; i++) {
    if(offsets[i] < chs.length) {
      ck.words[i] = new Word(chs, sen.getStartOffset(), offsets[i], tailLen[i]+1);//new Word(cks[i], sen.getStartOffset()+offsets[i]);
      if(tailLen[i] == 0) {	//单字的要取得"字频计算出自由度"
        CharNode cn = cns[i];    //dic.head(chs[offsets[i]]);
        if(cn !=null) {
          ck.words[i].setDegree(cn.getFreq());
        }
      }
    }
  }
  return ck;
}
 

private Chunk createChunk(Sentence sen, char[] chs, int[] tailLen, int[] offsets, CharNode[] cns/*, char[][] cks*/) {
  Chunk ck = new Chunk();
  
  for(int i=0; i<3; i++) {
    if(offsets[i] < chs.length) {
      ck.words[i] = new Word(chs, sen.getStartOffset(), offsets[i], tailLen[i]+1);//new Word(cks[i], sen.getStartOffset()+offsets[i]);
      if(tailLen[i] == 0) {	//单字的要取得"字频计算出自由度"
        CharNode cn = cns[i];    //dic.head(chs[offsets[i]]);
        if(cn !=null) {
          ck.words[i].setDegree(cn.getFreq());
        }
      }
    }
  }
  return ck;
}
 

  public Chunk seg(Sentence sen) {
    Chunk chunk = new Chunk();
    char[] chs = sen.getText();
    for(int k=0; k<3&&!sen.isFinish(); k++) {
      int offset = sen.getOffset();
      int maxLen;

      //有了 key tree 的支持可以从头开始 max match
      maxLen = dic.maxMatch(chs, offset);
      
      chunk.words[k] = new Word(chs, sen.getStartOffset(), offset, maxLen+1);

      offset += maxLen + 1;
      sen.setOffset(offset);
    }
    
    return chunk;
  }
}

  public Chunk seg(Sentence sen) {
    Chunk chunk = new Chunk();
    char[] chs = sen.getText();
    for(int k=0; k<3&&!sen.isFinish(); k++) {
      int offset = sen.getOffset();
      int maxLen = 0;

      //有了 key tree 的支持可以从头开始 max match
      maxLen = dic.maxMatch(chs, offset);
      
      chunk.words[k] = new Word(chs, sen.getStartOffset(), offset, maxLen+1);

      offset += maxLen + 1;
      sen.setOffset(offset);
    }
    
    return chunk;
  }
}

bufWord.add(new Word(new char[] {bufSentence.charAt(i)}, startIdx++, Word.TYPE_LETTER_NUMBER));

  public Chunk seg(Sentence sen) {
    Chunk chunk = new Chunk();
    char[] chs = sen.getText();
    for(int k=0; k<3&&!sen.isFinish(); k++) {
      int offset = sen.getOffset();
      int maxLen = 0;

      //有了 key tree 的支持可以从头开始 max match
      maxLen = dic.maxMatch(chs, offset);
      
      chunk.words[k] = new Word(chs, sen.getStartOffset(), offset, maxLen+1);

      offset += maxLen + 1;
      sen.setOffset(offset);
    }
    
    return chunk;
  }
}

bufWord.add(new Word(new char[] {bufSentence.charAt(i)}, startIdx++, Word.TYPE_LETTER_NUMBER));

bufWord.add(new Word(new char[] {bufSentence.charAt(i)}, startIdx++, Word.TYPE_LETTER_NUMBER));