C++ CDictionary::GetMaxMatch方法代码示例

bool CSegGraph::GenerateWordNet(char *sSentence,CDictionary &dictCore,bool	bOriginalFreq)
{
//Gernerate the word net from the sLine, that's list all the possible word
	unsigned int i=0,j,nLen=strlen(sSentence);
	char sWord[WORD_MAXLENGTH]="",sTempWord[WORD_MAXLENGTH]="",sWordMatch[WORD_MAXLENGTH];
	int nWordIndex=0,nHandleTemp,k,nPOS;
	int nMatchFreq[20],nMatchHandle[20],nTotalFreq,nMatchCount;
	double dValue=0;
	m_nAtomCount=0;
	m_segGraph.SetEmpty();//Set segmentation graph empty

	AtomSegment(sSentence);
	//Atomic Segmentation

    for(i=0;i<m_nAtomCount;i++)//Init the cost array
    {
		if(m_nAtomPOS[i]==CT_CHINESE)//The atom is a Chinese Char
		{
			if(!bOriginalFreq)//Not original frequency
				m_segGraph.SetElement(i,i+1,log(MAX_FREQUENCE),0);//init the link with the maximum value
			else
				m_segGraph.SetElement(i,i+1,0,0,m_sAtom[i]);//init the link with the maximum value
		}
		else//Other atom
		{
			strcpy(sWord,m_sAtom[i]);//init the word 
			dValue=MAX_FREQUENCE;
			switch(m_nAtomPOS[i])
			{
			case CT_INDEX:
			case CT_NUM:
				nPOS=-27904;//'m'*256
				strcpy(sWord,"未##数");
				dValue=0;
				break;
			case CT_DELIMITER:
				nPOS=30464;//'w'*256;
				break;
			case CT_LETTER:
				nPOS=-'n'*256-'x';//
				dValue=0;
				strcpy(sWord,"未##串");
				break;
			case CT_SINGLE://12021-2129-3121
				if(GetCharCount("+-1234567890",m_sAtom[i])==(int)strlen(m_sAtom[i]))
				{
					nPOS=-27904;//'m'*256
					strcpy(sWord,"未##数");
				}
				else
				{
					nPOS=-'n'*256-'x';//
					strcpy(sWord,"未##串");
				}
				dValue=0;
				break;
			default:
				nPOS=m_nAtomPOS[i];//'?'*256;
				break;
			}
			if(!bOriginalFreq)//Not original frequency
				m_segGraph.SetElement(i,i+1,0,nPOS);//init the link with minimum
			else
				m_segGraph.SetElement(i,i+1,dValue,nPOS,sWord);//init the link with minimum
		}
    }
	i=0;
	while(i<m_nAtomCount)//All the word
	{
	  strcpy(sWord,m_sAtom[i]);//Get the current atom
	  j=i+1;
	  if(strcmp(sWord,"月")==0&&strcmp(m_sAtom[i+1],"份")==0)//Don't split 月份
		  j+=1;
	  while(j<=m_nAtomCount&&dictCore.GetMaxMatch(sWord,sWordMatch,&nHandleTemp))
	  {//Add a condition to control the end of string
	   //retrieve the dictionary with the word
          if(strcmp(sWordMatch,sWord)==0)//find the current word
		  {
			  nTotalFreq=0;
			  dictCore.GetHandle(sWord,&nMatchCount,nMatchHandle,nMatchFreq);
			  for(k=0;k<nMatchCount;k++)//Add the frequency
			  {
				 nTotalFreq+=nMatchFreq[k];
			  }
			  //Adding a rule to exclude some words to be formed.
			  if(strlen(sWord)==4&&i>=1&&(IsAllNum((unsigned char *)m_sAtom[i-1])||IsAllChineseNum(m_sAtom[i-1]))&&(strncmp(sWord,"年",2)==0||strncmp(sWord,"月",2)==0))
			  {//1年内、1999年末
			     if(CC_Find("末内中底前间初",sWord+2))
				     break;
			  }
			  if(nMatchCount==1)//The possible word has only one POS, store it
			  {
				if(!bOriginalFreq)//Not original frequency
					m_segGraph.SetElement(i,j,-log(nTotalFreq+1)+log(MAX_FREQUENCE),nMatchHandle[0]);
				else
					m_segGraph.SetElement(i,j,nTotalFreq,nMatchHandle[0],sWord);
			  }
			  else 
			  {
					if(!bOriginalFreq)//Not original frequency
//.........这里部分代码省略.........