词法分析程序代码

  1 #include <stdio.h>
  2 #include <string.h>
  3 
  4 char prog[100],token[8],ch;
  5 int syn,p,m,n,sum;
  6 char *rwtab[6]={"begin","if","then","while","do","end"};
  7 
  8 void scaner(void);
  9 
 10 main()
 11 {
 12     p=0;
 13     printf("
 在下方输入你的字符串(按回车结束输入):
");
 14 
 15     do{
 16             scanf("%c",&ch);
 17             prog[p++]=ch;
 18     }while(ch!='
');
 19 
 20     p=0;
 21     do{
 22             scaner();
 23             switch(syn)
 24             {
 25                 case 11:
 26                     printf("( %-10d%5d )
",sum,syn);
 27                 break;
 28 
 29                 case -1:
 30                     printf("you have input a wrong string
");
 31                     return 0;
 32                 break;
 33 
 34                 default:
 35                 printf("( %-10s%5d )
",token,syn);
 36                 break;
 37             }
 38         }while(syn!=0);
 39 
 40  }
 41 
 42 void scaner(void)
 43 {
 44     sum=0;
 45 
 46     for(m=0;m<8;m++)
 47         token[m++]= NULL;
 48 
 49         ch=prog[p++];
 50         m=0;
 51 
 52     while((ch==' ')||(ch=='
'))
 53         ch=prog[p++];
 54 
 55     if(((ch<='z')&&(ch>='a'))||((ch<='Z')&&(ch>='A')))
 56      {
 57         while(((ch<='z')&&(ch>='a'))||((ch<='Z')&&(ch>='A'))||((ch>='0')&&(ch<='9')))
 58         {
 59             token[m++]=ch;
 60             ch=prog[p++];
 61         }
 62 
 63         p--;
 64         syn=10;
 65 
 66         for(n=0;n<6;n++)
 67         if(strcmp(token,rwtab[n])==0)
 68         {
 69             syn=n+1;
 70             break;
 71         }
 72      }
 73      else if((ch>='0')&&(ch<='9'))
 74      {
 75         while((ch>='0')&&(ch<='9'))
 76         {
 77             sum=sum*10+ch-'0';
 78             ch=prog[p++];
 79         }
 80         p--;
 81         syn=11;
 82     }
 83     else
 84     {
 85         switch(ch)
 86         {
 87         case '<':
 88             token[m++]=ch;
 89             ch=prog[p++];
 90             if(ch=='=')
 91             {
 92                 syn=21;
 93                 token[m++]=ch;
 94             }
 95             else
 96             {
 97                 syn=20;
 98                 p--;
 99             }
100         break;
101 
102         case '>':
103             token[m++]=ch;
104             ch=prog[p++];
105             if(ch=='=')
106             {
107                 syn=24;
108                 token[m++]=ch;
109             }
110             else
111             {
112                 syn=23;
113                 p--;
114             }
115         break;
116 
117         case '+':
118             syn=13;
119             token[m++]=ch;
120         break;
121 
122         case '-':
123             syn=14;
124             token[m++]=ch;
125         break;
126 
127         case '=':
128             syn=25;
129             token[m++]=ch;
130         break;
131 
132         case '*':
133             syn=15;
134             token[m++]=ch;
135         break;
136 
137         case '/':
138             syn=16;
139             token[m++]=ch;
140         break;
141 
142         case '(':
143             syn=27;
144             token[m++]=ch;
145         break;
146 
147         case ')':
148             syn=28;
149             token[m++]=ch;
150         break;
151 
152         case '<>':
153             syn=22;
154             token[m++]=ch;
155         break;
156 
157         case ';':
158             syn=26;
159             token[m++]=ch;
160         break;
161 
162         case '#':
163             syn=0;
164             token[m++]=ch;
165         break;
166 
167         case ':':
168             token[m++]=ch;
169             ch=prog[p++];
170             if(ch=='=')
171             {
172                 syn=18;
173                 token[m++]=ch;
174             }
175             else
176             {
177             syn=17;
178             token[m++]=ch;
179             }
180         break;
181 
182         default:
183             syn=-1;
184         break;
185         }
186     }
187         token[m++]='';
188 }