cifa.cpp

很全面很细致的词法分析程序

// cifa.cpp : Defines the entry point for the console application.
//词法分析程序  
#include <conio.h> 
#include "stdafx.h" 
#include "stdio.h"
#include "string.h"
#define ACC   -2

#define  sy_if      0
#define  sy_then    1
#define  sy_else    2
#define  sy_while   3
#define  sy_begin   4
#define  sy_do      5
#define  sy_end     6
#define   a         7
#define  semicolon  8
#define   e         9
#define  jinghao    10
#define   S         11
#define   L         12
#define   tempsy    15
#define   EA        18     //E and
#define   EO        19     //E or 
#define   plus      34
#define   times     36
#define   becomes   38
#define   op_and    39
#define   op_or     40
#define   op_not    41
#define   rop       42
#define   lparent   48
#define   rparent   49
#define   ident     56
#define   intconst  57

        char  ch='\0';         //当前字符 
        int  count=0;
		static char   spelling[10]={""};   //存放识别的字
		static char   line[81]={""};       //一行字符缓冲区
		char   *pline ;                    //字符缓冲区指针
		static  char  ntab1[100][10];
		struct ntab
		{
			int tc;
			int fc;
		}ntab2[200];
			int  label=0;       //存放临时变量的表的定义

		struct  rwords{
			char  sp[10];
			int   sy;
		};
		//存放文件的结构
		struct rwords reswords[10]={
			{"if",sy_if},
			{"do",sy_do},
			{"else",sy_else},
			{"while",sy_while},
			{"then",sy_then},
			{"begin",sy_begin},
			{"end",sy_end},
			{"and",op_and},
			{"or",op_or},
			{"not",op_not},
		};

		struct aa{
			int sy1;
			int pos;
		}buf[1000],    //词法分析结果缓冲区
		 n,            //当前字符
		 n1,           //当前表达式中的字符
		 E,
		 sstack[100],     //符号栈
		 ibuf[100],
		 stack[1000];

		 int nlength=10;
		 int tt1=0;
		 int lnum=0;
         FILE *cfile,*mfile;
        
         void readline()       //读文件读一行至缓冲区
		 {
		    char ch1;
			pline=line;
			ch1=getc(cfile);
			while(ch1 !='\n')
			{
			  *pline=ch1;
			  pline++;
			  ch1=getc(cfile);
			}

                  *pline='\0';
				  pline=line;
		 }

void  readch()
{
   if(ch=='\0')
   {
     readline();
	 lnum++;
   }
   ch=*pline;
   pline++;
}


//识符和关键字的识别
find(char spel[])        
{
  int ss1=0;
  int ii=0;
  while((ss1==0)&&(ii<nlength))
  {
    if(!strcmp(spel,ntab1[ii]))
	{ss1=1;
   	ii++;}
  }
  if(ss1==1)return ii-1;
  else return -1;
}

void identifier()
{
   int iii=0,j,k;
   int ss=0;
   k=0;
   do
   {
       spelling[k]=ch;
	   k++;
	   readch();
   }while(((ch>='a')&&(ch<='z'))||((ch>='0')&&(ch<='9')));
   pline--;
   spelling[k]='\0';
   while((ss==0)&&(iii<10))
   {
	   if(!strcmp(spelling,reswords[iii].sp))
		   ss=1;
	       iii++;
   }
   //关键字匹配
   if(ss==1)
   {
       buf[count].sy1=reswords[iii-1].sy;
   }
   else{
	   buf[count].sy1=ident;
	   j=find(spelling);
	   if(j==-1)
	   {
		   buf[count].pos=tt1;
		   strcpy(ntab1[tt1],spelling);
		   tt1++;
		   nlength++;
	   }
	   else buf[count].pos=j;
   }
   count++;
   for(k=0;k<10;k++)
	   spelling[k]=' ';
}

//数字识别
void number()
{
 int ivalue=0;
 int digit;
 do
 {
     digit=ch-'0';
	 ivalue=ivalue*10+digit;
	 readch();
 }while((ch>='0')&&(ch<='9'));
 buf[count].sy1=intconst;
 buf[count].pos=ivalue;
       count++;
	   pline--;
}

//扫描主函数
void scan()
{
   int i;
   while(ch!='~')
   {
    switch(ch)
	{
	case' ':
	       break;
    case 'a':
	case 'b':
	case 'c':
	case 'd':
    case 'e':
	case 'f':
	case 'g':
    case 'h':
	case 'i':
	case 'j':
	case 'k':
	case 'l':
	case 'm':
	case 'n':
	case 'o':
	case 'p':
	case 'q':
	case 'r':
	case 's':
	case 't':
	case 'u':
	case 'v':
	case 'w':
	case 'x':
	case 'y':
	case 'z':
          identifier();
		  break;
	case '0':
	case '1':
	case '2':
	case '3':
	case '4':
	case '5':
	case '6':
	case '7':
	case '8':
	case '9':
		number();
		break;
	   case '<':
		   readch();
		   if(ch=='=')
		   {
			   buf[count].pos=0;
		   }
		   else 
		   {
			   if(ch=='>')buf[count].pos=4;
			   else
			   {
				   buf[count].pos=1;
				   pline--;
			   }
		   }
		   buf[count].sy1=rop;
		   count++;
		   break;
	   case '>':
		   readch();
		   if(ch=='=')
		   {
			   buf[count].pos=2;
		   }
		   else
		   {
			   buf[count].pos=3;
			   pline--;
		   }
		   buf[count].sy1=rop;
		   count++;
		   break;
	   case '(':
		   buf[count].sy1=lparent;
		   count++;
		   break;
	   case ')':
		   buf[count].sy1=rparent;
		   count++;
		   break;
	   case '#':
		   buf[count].sy1=jinghao;
		   count++;
		   break;
	   case '+':
		   buf[count].sy1=plus;
		   count++;
		   break;
	   case '*':
		   buf[count].sy1=times;
		   count++;
		   break;
	   case ':':
		  readch();
		  if(ch=' ')
		   buf[count].sy1=becomes;
		  count++;
		   break;
	   case '=':
		   buf[count].sy1=rop;
		   buf[count].pos=5;
		   count++;
		   break;
	   case ';':
		   buf[count].sy1=semicolon;
		   count++;
		   break;
		   }
readch();
}
    buf[count].sy1=-1;
	}

void disp1()
{
	int temp1=0;
	printf("\n**********词法分析结果***********\n");
	printf("\n**类别编码*******内码值**\n");

	for(temp1=0;temp1<count;temp1++)
	{
		printf("%d\t%d\n",buf[temp1].sy1,buf[count].pos);
	}
	getch();
}

void disp3()
{
	int tttt;
	printf("二元式的个数和行数为：\n");
	printf("%d%d",lnum,count);
	getch();
	printf("\n*************变量表************\n");
	for(tttt=0;tttt<tt1;tttt++)
		printf("%d\t%s\n",tttt,ntab1[tttt]);
	getch();
}

void main()
{
 cfile=fopen("pas.c","r");
 readch();
 scan();

disp1();
disp3();
}