lex.cpp

lex语法分析

	CstrFormat("all record word num :",nRecAllWordNum,cstrShow,15);
	filWrite.WriteString(cstrShow);
	filWrite.WriteString("\n");
	if(bHaveUnkownTag)
		filWrite.WriteString("Have Unknown Tag");
	else 
		filWrite.WriteString("Not Have Unkown Tag");
	filWrite.WriteString("\n");
	filWrite.WriteString("\n");
	int nRecWordSum;
	int nAllWordSum;
	TitleFormat(cstrShow);
	filWrite.WriteString(cstrShow);
	filWrite.WriteString("\n");

	nAllWordSum = AllWordNumFormat(cstrShow);
	// 想加数组liblexic.m_aryAllWordTagNum[i]
	filWrite.WriteString(cstrShow);
	filWrite.WriteString("\n");

	nRecWordSum = RecWordNumFormat(cstrShow);
	// 想加数组liblexic.m_aryRecWordTagNum[i]
	filWrite.WriteString(cstrShow);
	filWrite.WriteString("\n");

	TitleHyphenFormat(cstrShow);
	filWrite.WriteString(cstrShow);
	filWrite.WriteString("\n");
	
	AllSubRecNumFormat(cstrShow);
	filWrite.WriteString(cstrShow);
	filWrite.WriteString("\n");

	CstrFormat("所有的单词数 :",nAllWordSum,cstrShow,30);
	filWrite.WriteString(cstrShow);
	filWrite.WriteString("\n");
	CstrFormat("所有已记录的单词数 :",nRecWordSum,cstrShow,30);
	filWrite.WriteString(cstrShow);
	filWrite.WriteString("\n");

	filRead.Close();
	filWrite.Close();
}
void TitleFormat(char* cstrShow)
{
	char cstr[1024]="";
	char cstr1[10];
	int i;
	CstrFormatChar(cstr,"Unknown",cstrShow,0);
	strcpy(cstr,cstrShow);
	for(i=0; i<61; i++)
	{
		strcpy(cstr1,CTagConst::m_strTags[i].c_str());
		CstrFormatChar(cstr,cstr1,cstrShow,(i+1)*10);
		strcpy(cstr,cstrShow);
	}
	
}
void TitleHyphenFormat(char* cstrShow)
{
	char cstr[1024]="";
	char cstr1[11] = "----------";
	int i;
	for(i=0; i<62; i++)
	{
		CstrFormatChar(cstr,cstr1,cstrShow,i*10);
		strcpy(cstr,cstrShow);
	}
}
int AllWordNumFormat(char* cstrShow)
{
	int i;
	int nRet=0;
	char cstr[1024]="";
	for(i=0; i<62; i++)
	{
		CstrFormat(cstr,liblexic.m_aryAllWordTagNum[i],cstrShow,i*10);
		strcpy(cstr,cstrShow);
		nRet += liblexic.m_aryAllWordTagNum[i];
	}
	return nRet;
}
int RecWordNumFormat(char* cstrShow)
{
	int i;
	int nRet=0;
	char cstr[1024]="";
	for(i=0; i<62; i++)
	{
		CstrFormat(cstr,liblexic.m_aryRecWordTagNum[i],cstrShow,i*10);
		strcpy(cstr,cstrShow);
		nRet += liblexic.m_aryRecWordTagNum[i];
	}
	return nRet;
}
int AllSubRecNumFormat(char* cstrShow)
{
	int i;
	int nRet=0;
	char cstr[1024]="";
	for(i=0; i<62; i++)
	{
		CstrFormat(cstr,
			liblexic.m_aryAllWordTagNum[i] - liblexic.m_aryRecWordTagNum[i],
			cstrShow,i*10);
		strcpy(cstr,cstrShow);
		nRet += liblexic.m_aryAllWordTagNum[i] - liblexic.m_aryRecWordTagNum[i];
	}
	return nRet;
}
int SumWordFreq(CLexBTree::SCell& cell)
{
	int i;
	int sum;
	for(i=0,sum=0; i<TAGNUM_IN_CELL; i++)
	{
		if(0 == cell.aryTag[i]){ // 表示已无已存在的标记，到了空白标记处了
			break;
		}
		else {
			sum += cell.aryTagCount[i];
		}
	}
	return sum;
}
bool HaveTagUnknown(CLexBTree::SCell& cell)
{
	int i;
	bool bHave;
	for(i=0,bHave=false; 
	(i<TAGNUM_IN_CELL) && !bHave;
	i++)
	{
		if(0 == cell.aryTag[i]){ // 表示已无已存在的标记，到了空白标记处了
			break;
		}
		else if(CTagConst::tagUNKNOWN == cell.aryTag[i]) {
			bHave = true;
		}
	}
	return bHave;
}
int SumCellTagNum(CLexBTree::SCell& cell)
{
	int i;
	int sum;
	for(i=0,sum=0; i<TAGNUM_IN_CELL; i++)
	{
		if(0 == cell.aryTag[i]){ // 表示已无已存在的标记，到了空白标记处了
			break;
		}
		else {
			sum ++;
		}
	}
	return sum;
}
//void CstrFormat(char* cstrSrc,int nSrc,char* cstrDest,int dist)
//{
//	int i,j;
//	int len;
//	char cstrIntReverse[12];
//	len = strlen(cstrSrc);
//	for(i=0; i<len; i++)
//	{
//		cstrDest[i] = cstrSrc[i];
//	}
//	for(; i<dist; i++)
//	{
//		cstrDest[i] = '\040';
//	}
//	if(0==nSrc) {
//		cstrIntReverse[0] = '0';
//		cstrIntReverse[1] = '\0';
//	}
//	else {
//		for(j=0; nSrc!=0; )
//		{
//			cstrIntReverse[j++] = nSrc%10 + '0';
//			nSrc = nSrc/10;
//		}
//		cstrIntReverse[j] = '\0';
//	}
//
//	len = strlen(cstrIntReverse);
//	for(j=len-1; j>=0; i++,j--)
//	{
//		cstrDest[i] = cstrIntReverse[j];
//	}
//	cstrDest[i] = '\0';
//
//}
void CstrFormat(char* cstrSrc,int nSrc,char* cstrDest,int dist)
{
	char cstrInt[128];
	itoa(nSrc,cstrInt,10);
	CstrFormatChar(cstrSrc,cstrInt,cstrDest,dist);
}
void CstrFormatEx(char* cstrSrc,int nSrc,char* cstrDest,int dist)
{
	char cstrInt[128];
	itoa(nSrc,cstrInt,10);
	CstrFormatCharEx(cstrSrc,cstrInt,cstrDest,dist);
}
void CstrFormatChar(char* cstrSrc1,char* cstrSrc2,char* cstrDest,int dist)
{
	int i,j;
	int len;

	len = strlen(cstrSrc1);
	for(i=0; i<len; i++)
	{
		cstrDest[i] = cstrSrc1[i];
	}
	for(; i<dist; i++)
	{
		cstrDest[i] = '\040';
	}
	len = strlen(cstrSrc2);
	for(j=0; j<len; i++,j++)
	{
		cstrDest[i] = cstrSrc2[j];
	}
	cstrDest[i] = '\0';

}
void CstrFormatCharEx(char* cstrSrc1,char* cstrSrc2,char* cstrDest,int dist)
{
	int i,j;
	int len;

	len = strlen(cstrSrc1);
	for(i=0; i<len; i++)
	{
		cstrDest[i] = cstrSrc1[i];
	}
	len = strlen(cstrSrc2);
	for(; i<dist-len; i++)
	{
		cstrDest[i] = '\040';
	}

	for(j=0; j<len; i++,j++)
	{
		cstrDest[i] = cstrSrc2[j];
	}
	cstrDest[i] = '\0';
}
void ShowToFile1(void)
{
	char cstrShow[120];
	CLexBTree::SPage page;
	int naddr,i;
	CFile filRead("lexdict.dat",CFile::modeRead);
	CStdioFile filDot("dot.txt",CFile::modeCreate|CFile::modeWrite);
	CStdioFile filHavedot("hdot.txt",CFile::modeCreate|CFile::modeWrite);
	CStdioFile filHyphen("hyphen.txt",CFile::modeCreate|CFile::modeWrite);
	CStdioFile filPhrase("phrase.txt",CFile::modeCreate|CFile::modeWrite);
	int len;

	for(naddr=0; naddr!=-1; )
	{
		filRead.Seek(naddr* sizeof(CLexBTree::SPage),CFile::begin);
		filRead.Read((void*) &page,sizeof(CLexBTree::SPage));
		for(i=0; i<page.used_cell_slot_sum; i++) {
			len = strlen(page.cell_ary[i].word);
			if(strchr(page.cell_ary[i].word,'\040') != NULL) {
				CstrFormat(page.cell_ary[i].word,SumWordFreq(page.cell_ary[i]),
					cstrShow,35);
				filPhrase.WriteString(cstrShow);
				filPhrase.WriteString("\n");
			}
			else if(page.cell_ary[i].word[len-1] == '-') {
				CstrFormat(page.cell_ary[i].word,SumWordFreq(page.cell_ary[i]),
					cstrShow,35);
				filHyphen.WriteString(cstrShow);
				filHyphen.WriteString("\n");
			}
			else if(page.cell_ary[i].word[len-1] == '.') {
				CstrFormat(page.cell_ary[i].word,SumWordFreq(page.cell_ary[i]),
					cstrShow,35);
				filDot.WriteString(cstrShow);
				filDot.WriteString("\n");
			}
			else if(strchr(page.cell_ary[i].word,'.') != NULL) {
				CstrFormat(page.cell_ary[i].word,SumWordFreq(page.cell_ary[i]),
					cstrShow,35);
				filHavedot.WriteString(cstrShow);
				filHavedot.WriteString("\n");
			}
		}
		naddr = page.next_page_naddr;		
	}

	filDot.Close();
	filHavedot.Close();
	filHyphen.Close();
	filPhrase.Close();
	filRead.Close();
}
//这个函数里用到MFC 的 CFile类
void exec(char * cstr_fname)
{
	CStdioFile mfc_finput(cstr_fname,CFile::modeRead);

	string str,strWord;
	char cstr[MAX_CHARS_LINE];

	vector<SWordTag>::iterator iter;

		while(mfc_finput.ReadString(cstr,MAX_CHARS_LINE)) {
			if(cstr[strlen(cstr)-1]=='\n') {
				cstr[strlen(cstr)-1] = 0;  //ReadString会把回车符也算在字符串内
			}
			str = cstr;
			if(liblexic.Analyse(str)) {	
				for(iter=liblexic.m_vecWordTag.begin();
				iter!=liblexic.m_vecWordTag.end();
				iter++)
				{	
					strWord = (*iter).cstrWord;
					pBT->Manipulate(strWord,(*iter).nTag);
				}
			}
		}

	mfc_finput.Close();
}