词法分析程序（C）

#include <stdio.h>  
#include <string.h>  
  
char string[80],word[8],ch;  
int type,p,i,n,sum;  
char keyword[][6]={"begin","if","then","while","do","end"};    //关键字数组
   
void scaner(void);  
  
main()  
{  
    p=0;  
    printf("\n\n请输入一个程序段(以'#'结束):\n");  
    do{  
            scanf("%c",&ch);  
            string[p++]=ch;  
    }while(ch!='#');  
     printf("单词符号\t种别码 \n");  
    p=0;  
    do{  
            scaner();  
            switch(type)  
            {  
                case 11:  
                    printf("   %-10d%5d\n",sum,type);  
                break;  
                case -1:  
                    printf("有无法识别的字符\n");    
                    return 0;  
                break;       
                default:   
                printf("   %-10s%5d \n",word,type);  
                break;  
            }  
        }while(type!=0);  
 }  
  
void scaner(void)  
{    
    sum=0;  
    for(i=0;i<8;i++)  
       word[i++]= NULL;  
      

    ch=string[p++];  
    i=0;  
          
    while((ch==' ')||(ch=='\n'))  
        ch=string[p++];  
      
    if(((ch<='z')&&(ch>='a'))||((ch<='Z')&&(ch>='A')))  
     {   
        while(((ch<='z')&&(ch>='a'))||((ch<='Z')&&(ch>='A'))||((ch>='0')&&(ch<='9')))  
        {  
            word[i++]=ch;  
            ch=string[p++];  
        }
          
     p--; 
     type=10;                     //先将以字母开头的字符识别为标识符
  
        for(n=0;n<6;n++)  
        if(strcmp(word,keyword[n])==0)    //关键字数组比较，相同则表示为关键字，种别码即为下标值加一
        {   
            type=n+1;  
            break;  
        }  
    }                                   
    
    
    else if((ch>='0')&&(ch<='9'))  
     {   
        while((ch>='0')&&(ch<='9'))  
        {  
            sum=sum*10+ch-'0';    //将字符型转化为整形sum
            ch=string[p++];  
        }  
        p--;  
        type=11;  
     }  


    else                   //else语句内识别除关键字、标识符、数字以外的其他字符
    {  
        switch(ch)  
        {  
        case '+':  
            type=13;  
            word[i++]=ch;          
        break;  
  
        case '-':   
            type=14;
            word[i++]=ch;   
        break; 
        
         case '*':  
            type=15;  
            word[i++]=ch;  
        break;  
  
        case '/':  
            type=16;  
            word[i++]=ch;  
        break;  

        case ':':  
            word[i++]=ch;  
            ch=string[p++];  
         if(ch=='=')  
           {  
               type=18;  
               word[i++]=ch;  
           }  
            else  
            {   
                type=18;  
                p--;  
            }  
        break; 
        
        case '<':  
            word[i++]=ch;  
            ch=string[p++];  
            if(ch=='=')  
            {   
                type=21;  
                word[i++]=ch;  
            }  
            else  
            {    
                type=20;  
                p--;  
            }  
        break;  
  
        case '>':  
            word[i++]=ch;  
            ch=string[p++];  
            if(ch=='=')  
            {  
                type=24;  
                word[i++]=ch;  
            }  
            else  
            {   
                type=23;  
                p--;  
            }  
        break;
        
        case '=':  
                type=25;  
                word[i++]=ch;  
        break;  
  
        case ';':  
            type=26;  
            word[i++]=ch;  
        break;  

        case '(':   
            type=27;  
            word[i++]=ch;  
        break;  
  
        case ')':  
            type=28;  
            word[i++]=ch;  
        break;  
  
        case '#':   
            type=0;  
            word[i++]=ch;  
        break;  
  
        default:  
            type=-1;  
        break;  
        }  
    }  
        word[i++]='\0';                      //word字符数组变字符串
}