词法分析

---恢复内容开始---

词法分析程序的功能

输入：所给文法的源程序字符串

输出：二元组（syn,token或sum）构成的序列

其中syn为单词种别码；token为存放的单词自身字符串；sum为整形常数。

例如：对源程序begin x=9;if x>9 then x:=2*x+|/3;end#的源文件，经过词法分析后输出如下序列：

（1，begin）（10，x）(18,:=)(11,9)(26,;)(2,if).......

 

 

#include <stdio.h>  
#include <string.h>  
#include<stdlib.h>  
char prog[80],token[8],ch;  
int syn,p,m,n,sum;  
char *rwtab[6]={"begin","if","then","while","do","end"};  
   
void scaner();  
  
void main()  
{  
    p=0;  
    printf("
 please input a string(end with'#'):
");  
      
    do{  
            scanf("%c",&ch);  
            prog[p++]=ch;  
    }while(ch!='#');  
      
    p=0;  
    do{  
            scaner();  
            switch(syn)  
            {  
                case 11:  
                    printf("( %-10d%5d )
",sum,syn);  
                break;  
                  
                case -1:  
                    printf("you have input a wrong string
");    
                    getchar(); 
               exit(0);  
                  
                default:   
                printf("( %-10s%5d )
",token,syn);  
                break;  
            }  
        }while(syn!=0);
    getchar();
 }  
  
void scaner()  
{    
    sum=0;  
      
    for(m=0;m<8;m++)  
        token[m++]=NULL;  
      
        ch=prog[p++];  
        m=0;  
          
    while((ch==' ')||(ch=='
'))  
        ch=prog[p++];  
      
    if(((ch<='z')&&(ch>='a'))||((ch<='Z')&&(ch>='A')))  
     {   
        while(((ch<='z')&&(ch>='a'))||((ch<='Z')&&(ch>='A'))||((ch>='0')&&(ch<='9')))  
        {  
            token[m++]=ch;  
            ch=prog[p++];  
        }  
          
        p--;  
        syn=10;  
  
        for(n=0;n<6;n++)  
        if(strcmp(token,rwtab[n])==0)  
        {   
            syn=n+1;  
            break;  
        }  
     }  
     else if((ch>='0')&&(ch<='9'))  
     {   
        while((ch>='0')&&(ch<='9'))  
        {  
            sum=sum*10+ch-'0';  
            ch=prog[p++];  
        }  
        p--;  
        syn=11;  
    }  
    else   
    {  
        switch(ch)  
        {  
        case '<':token[m++]=ch;  
            ch=prog[p++];  
            if(ch=='=')  
            {   
                syn=22;  
                token[m++]=ch;  
            }  
            else  
            {    
                syn=20;  
                p--;  
            }  
        break;  
  
        case '>':token[m++]=ch;  
            ch=prog[p++];  
            if(ch=='=')  
            {  
                syn=24;  
                token[m++]=ch;  
            }  
            else  
            {   
                syn=23;  
                p--;  
            }  
        break;  
  
        case '+':token[m++]=ch;  
            ch=prog[p++];  
            if(ch=='+')  
            {  
                syn=17;  
                token[m++]=ch;  
            }  
            else  
            {  
                syn=13;  
                p--;  
            }  
        break;  
  
        case '-':  
            token[m++]=ch;  
            ch=prog[p++];  
            if(ch=='-')  
            {  
                syn=29;  
                token[m++]=ch;  
            }  
            else  
            {   
                syn=14;  
                p--;  
            }  
        break;  
  
        case '!':  
            ch=prog[p++];  
            if(ch=='=')  
            {   
                syn=21;  
                token[m++]=ch;  
            }  
            else  
            {   
                syn=31;  
                p--;  
            }  
        break;  
  
        case '=':  
            token[m++]=ch;  
            ch=prog[p++];  
            if(ch=='=')  
            {  
                syn=25;  
                token[m++]=ch;  
            }  
            else  
            {  
                syn=18;  
                p--;  
            }  
        break;  
  
        case '*':  
            syn=15;  
            token[m++]=ch;  
        break;  
  
        case '/':  
            syn=16;  
            token[m++]=ch;  
        break;  
  
        case '(':   
            syn=27;  
            token[m++]=ch;  
        break;  
  
        case ')':  
            syn=28;  
            token[m++]=ch;  
        break;  
  
        case '{':   
            syn=5;  
            token[m++]=ch;  
        break;  
  
        case '}':   
            syn=6;  
            token[m++]=ch;  
        break;  
  
        case ';':  
            syn=26;  
            token[m++]=ch;  
        break;  
  
        case '"':  
            syn=30;  
            token[m++]=ch;  
        break;  
  
        case '#':   
            syn=0;  
            token[m++]=ch;  
        break;  
  
        case ':':  
            syn=17;  
            token[m++]=ch;  
        break;  
  
        default:  
            syn=-1;  
        break;  
        }  
    }  
        token[m++]='';  
} 

---恢复内容结束---