good.c

本人写的简单C词法分析器

 #include <ctype.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <malloc.h>

 /*FILE *output;*/

  struct keyword
 {
     char str[10];
     int  type;
     int value;
  }kword[32]={
   {"outo",0,1},{"break",0,2},{"case",0,3},{"char",0,4},
   {"const",0,5},{"continue",0,6},{"default",0,7},{"do",0,8},
   {"double",0,9},{"else",0,10}, {"enum",0,11},{"extern",0,12},
   {"float",0,13},{"for",0,14},{"goto",0,15},{"if",0,16},
   {"int",0,17},{"long",0,18},{"register",0,19},{"return",0,20},
   {"short",0,21},{"signed",0,22},{"sizeof",0,23},{"static",0,24},
   {"struct",0,25},{"switch",0,26},{"typedef",0,7},{"union",0,28},
   {"unsigned",0,29},{"void",0,30},{"volatile",0,31},{"while",0,32}
   };
   struct seperate
   {
     char ch;
     int type;
     int value;
    }sep[13]={
    {'#',1,1},{'(',1,2},{')',1,3},{'[',1,4},
    {']',1,5},{'\'',1,6},{';',1,7},{':',1,8},
    {'{',1,9},{'}',1,10},{',',1,11},{'\\',1,12},
    {'\"',1,13}
    };
    struct calculate
    {
      char str[4];
      int type;
      int value;
     }cal[36]={
      {"!",2,1},{"%",2,2},{"^",2,3},{"&",2,4},
      {"*",2,5},{"-",2,6},{"+",2,7},{"=",2,8},
      {"~",2,9},{"|",2,10},{"<",2,11},{">",2,12},
      {"||",2,13},{"/",2,14},{"?",2,15},{"+=",2,16},
      {"-=",2,17},{"*=",2,18},{"/=",2,19},{"%=",2,20},
      {"<<=",2,21},{">>=",2,22},{"&=",2,23},{"^=",2,24},
      {"|=",2,25},{"->",2,26},{"++",2,27},{"--",2,28},
      {">>",2,29},{"<<",2,30},{"<=",2,31},{">=",2,32},
      {"!=",2,33},{"==",2,34},{"&&",2,35},{".",2,36}
      };
     /* struct id
      { 标识符
        char str[10];
        int type;
        int value;*/
 /*==========================主函数区=========================*/
    main()
    {
       FILE *input,*output;
       int i;
       char ch,pre,tem, token[256]="";
       if ((input=fopen("c:\\intext.txt","r"))==NULL)
          return 0;
         if ((output=fopen("c:\\outtext.txt","w"))==NULL)
             return 0;


        while(!feof(input))
        {
          ch=fgetc(input);
          while((ch==' '||ch=='\r'||ch=='\n')&&!feof(input))/*过滤空格*/
            ch=fgetc(input);
          if(isalpha(ch)) /*字母的情况 */
          {
            while((isalnum(ch)||ch=='_')&&!feof(input))
            {
             token[strlen(token)+1]='\0';
             token[strlen(token)]=ch;
             ch=fgetc(input);
             }
            if(!feof(input))
            fseek(input,-1,1);
            for(i=0;i<32;i++)
              if(strcmp(token,kword[i].str)==0)
                {
                 printf(" <%s,%d>",kword[i].str,kword[i].type);
                 fprintf(output," <%s,%d>\n",kword[i].str,kword[i].type);
                 break;
                 }
            if(i==32)
            printf(" <%s,3>",token);
            fprintf(output," <%s,3>\n",token);
            token[0]='\0';
            }


            else if(isdigit(ch)) /*数字的情况*/
           {
              while(isdigit(ch)&&!feof(input))
            {
             token[strlen(token)+1]='\0';
             token[strlen(token)]=ch;
             ch=fgetc(input);
             }
               if(ch!='.')
               {
                  if(ch=='e'||ch=='E')
                 {
                     /* */token[strlen(token)+1]='\0';
                     token[strlen(token)]=ch;
                     ch=fgetc(input);
                    while(isdigit(ch)&&!feof(input))
                     {
                         token[strlen(token)+1]='\0';
                         token[strlen(token)]=ch;
                         ch=fgetc(input);
                      }

                  }

                       fseek(input,-1,1);
                       printf( "<%s,40>",token);
                       fprintf(output,"<%s,40>\n",token);
                       token[0]='\0';
                }
                else
                {
                     /* */token[strlen(token)+1]='\0';
                     token[strlen(token)]=ch;
                     ch=fgetc(input);
                    while(isdigit(ch)&&!feof(input))
                     {
                         token[strlen(token)+1]='\0';
                         token[strlen(token)]=ch;
                         ch=fgetc(input);
                      }
                     if(ch=='e'||ch=='E')
                      {
                        /* */token[strlen(token)+1]='\0';
                        token[strlen(token)]=ch;
                        ch=fgetc(input);
                        while(isdigit(ch)&&!feof(input))
                        {
                          token[strlen(token)+1]='\0';
                          token[strlen(token)]=ch;
                          ch=fgetc(input);
                         }

                       }
                     fseek(input,-1,1);
                     printf(" <%s,41>",token);
                     fprintf(output," <%s,41>\n",token);
                     token[0]='\0';
                   }
              }


         else if(isseperate(ch))   /* 分隔符的情况*/
           {
             if(ch=='\'')
            {
               ch=fgetc(input);
               token[strlen(token)+1]='\0';
               token[strlen(token)]=ch;
               ch=fgetc(input);
               token[strlen(token)+1]='\0';
                token[strlen(token)]=ch;
                 ch=fgetc(input);
               if(ch!='\'')
                {
                 token[strlen(token)-1]='\0';
                 fseek(input,-1,1);
                 }
                printf(" <%s,42>",token);
                fprintf(output," <%s,42>\n",token);
                token[0]='\0';
               }
               else if(ch=='\"')
             {
               ch=fgetc(input);
               while(ch!='\"'&&!feof(input))
               {
                /**/ token[strlen(token)+1]='\0';
                 token[strlen(token)]=ch;
                 ch=fgetc(input);
                }
                fseek(input,-1,1);
                printf(" <%s,43>",token);
                fprintf(output," <%s,43>\n",token);
                ch=fgetc(input);
                token[0]='\0';

             }
               else
               {
                 for(i=0;i<13;i++)
                   if(ch==sep[i].ch)
                     printf(" <%c,%d>", sep[i].ch,sep[i].type);
                     fprintf(output," <%c,%d>\n", sep[i].ch,sep[i].type);
                }
         }


         else if(iscal(ch))
         {
            token[strlen(token)+1]='\0';
            token[strlen(token)]=ch;
            pre=ch;
            ch=fgetc(input);
            if(ch==pre||ch=='=')
            {
               token[strlen(token)+1]='\0';
               token[strlen(token)]=ch;
               if(ch==pre&&(ch=='<'||ch=='>'))
                 {
                   ch=fgetc(input);
                   if(ch=='=')
                    {
                      token[strlen(token)+1]='\0';
                      token[strlen(token)]=ch;
                     }
                    else
                      fseek(input,-1,1);
                   }

                 for(i=0;i<36;i++)
                {
                   if(strcmp(token,cal[i].str)==0)
                    {
                      printf(" <%s,%d>",cal[i].str,cal[i].type);
                      fprintf(output," <%s,%d>\n",cal[i].str,cal[i].type);
                      token[0]='\0';
                       break;
                     }


                }
                if (i==36)
                  printf("it's a wrong calcurate");

            }
            else if((pre=='/')&&(ch=='*'))
              {
                pre=fgetc(input);
                ch=fgetc(input);
                 while(!(pre=='*'&&ch=='/'))
                 {
                   pre=ch;
                   ch=fgetc(input);
                   }
                  ch=fgetc(input);
                }
            else
            {
               if (!feof(input))
                  fseek(input,-1,1);

              for(i=0;i<36;i++)
              {
                 if(strcmp(token,cal[i].str)==0)
                {
                  printf(" <%s,%d>",cal[i].str,cal[i].type);
                  fprintf(output," <%s,%d>\n",cal[i].str,cal[i].type);
                  token[0]='\0';

                  break;
                 }


              }

             }
          /* ch=fgetc(input);
           printf("result=%c", ch);*/


         }

      }
      fclose(input);
      getchar();
    }

    int isseperate(char ch)/*判断是否分割符*/
         {
         if(ch=='#'||ch=='('||ch==')'||ch=='\''||
           ch=='['||ch==']'||ch=='\"'||ch==';'||
           ch=='{'||ch=='}'||ch==','||ch=='\\'||ch==':')
           return 1;
           return 0;
        }
    int iscal(char ch)/*判断是否运算符*/
         {
          if(ch=='!'||ch=='%'||ch=='^'||ch=='&'||ch=='*'||
          ch=='-'||ch=='+'||ch=='='||ch=='~'||ch=='/'||
          ch=='.'||ch=='<'||ch=='>'||ch=='|'||ch=='?')
          return 1;
          return 0;
         }