一个词法分析程序

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