词法分析实验

实验一、词法分析实验

商业软件3班  谭颖欣 244

一、        实验目的

 

编制一个词法分析程序。通过设计一个编译词法分析程序，实现对词法分析转换的理解，加深对转换过程的认识，通过这个软件把理论知识运用到实际之中。

二、        实验内容和要求

输入：源程序字符串

输出：二元组（种别，单词本身

三、        实验方法、步骤及结果测试

 

1. 1.      源程序名：词法分析_244谭颖欣.c

可执行程序名：词法分析_244谭颖欣.exe

1. 2.      原理分析及流程图

   #include<stdio.h>
   #define max 200
   int i,n,syn;
   
   char pro[max],lin[20];
   char *word[6]={"begin","if","then","while","do","end"};
   char ch;
   scaner()
   {
       int j=0;
       for(n=0;n<20;n++)
           lin[n]=NULL;
           ch=pro[i++];
           while(ch==' ')
               ch=pro[i++];
           if((ch>='A'&&ch<='Z')||(ch>='a'&&ch<='Z')||(ch>=48&&ch<=57))
           {
              if((ch>='A'&&ch<='Z')||(ch>='a'&&ch<='Z'))
              {
                  lin[j++]=ch;
                  ch=pro[i++];
                  while((ch>='A'&&ch<='Z')||(ch>='a'&&ch<='Z')||(ch>=48&&ch<=57))
                  {
                      lin[j++]=ch;
                  ch=pro[i++];
                  }
                   lin[j]='\0';
                   i--;
                   syn=10;
                   for(n=0;n<6;n++)
                       if(strcmp(lin,word[n])==0)
                   {
                       syn=n+1;
                       break;
                   }
              }
              else
              {
                  while(ch>=48&&ch<=57)
                  {
                      lin[j++]=ch;
                      ch=pro[i++];
                  }
                  i--;
                  lin[j]='\0';
                  syn=11;
              }
           }
           else
           {
               if(ch=='<')
                   {lin[j++]=ch;
               ch=pro[i++];
               if (ch=='>')
                   {
                       syn=21;
               lin[j++]=ch;
               lin[j]='\0';
               }
               else if(ch=='=')
                   {
                       syn=22;
               lin[j++]=ch;
               lin[j]='\0';
               }
               else
                   {
                       syn=20;
               lin[j]='\0';
               i--;
               }
                   }
               else if(ch=='>')
                   { lin[j++]=ch;
               ch=pro[i++];
               if (ch=='=')
                   {
                       syn=24;
               lin[j++]=ch;
               lin[j]='\0';
               }
               else
                   {
                       syn=23;
               lin[j]='\0';
               i--;
               }
               }
               else if(ch==':')
                   {
                       lin[j++]=ch;
               ch=pro[i++];
               if (ch=='=')
                   {
                       syn=18;
               lin[j++]=ch;
               lin[j]='\0';}
               else
                   {
                       syn=17;
               lin[j]='\0';
               i--;
               }
               }
               else if(ch=='+')
                   {syn=13;
               lin[j++]=ch;
               lin[j]='\0';
               }
               else if(ch=='-')
                   {
                       syn=14;
               lin[j++]=ch;
               lin[j]='\0';}
               else if(ch=='*')
                   {
                       syn=15;
               lin[j++]=ch;
               lin[j]='\0';}
               else if(ch=='/')
                   {
                       syn=16;
               lin[j++]=ch;
               lin[j]='\0';
               }
               else if(ch=='=')
                   {
                       syn=25;
               lin[j++]=ch;
               lin[j]='\0';
               }
               else if(ch==';')
                   {
                       syn=26;
               lin[j++]=ch;
               lin[j]='\0';
               }
               else if(ch=='(')
                           {
                               syn=27;
               lin[j++]=ch;
               lin[j]='\0';
               }
               else if(ch==')')
                   {
                       syn=28;
               lin[j++]=ch;
               lin[j]='\0';}
               else if(ch=='#')
               {
                   syn=0;
                   lin[j++]=ch;
                   lin[j]='\0';
               }
               else
                       syn=-1;
               }
                       return syn;
           }
   
   void main()
   {
       int i=0 ;
       printf("**************************************************************************\n");
       printf("*********************************种别编码*********************************\n");
       printf("**************************************************************************\n");
       printf("(1,begin)       (2,if)                 (3,then)         (4,while)    (5,do)\n");
       printf("(6,end)         (10,基本标示符)        (11,数字)        (13, )       (14,-)\n");
       printf("(15,*)          (16,/)                 (17,:)           (18,:=)      (20,<)\n");
       printf("(21,<>)         (22,<=)                (23,>)           (24,>=)      (25,=)\n");
       printf("(26,;)          (27,()                 (28,))           (0,#)\n");
       read();
       printf( "读入的字符串如下: \n\n" );
       puts(pro);
       printf( "词法分析结果如下:\n" );
       printf( "\n" );
       do   {
               scaner();
       switch(syn)
       {
           case 11:
               printf ("(%d,%s)\n",syn,lin);
               break;
               case -1:
                   printf("错误符号\n");
                   break;
                   default:
                       printf ("(%d,%s)",syn,lin); }
                       } while (syn!=0);
                       printf( "\n词法分析结束\n" );
                        scanf("%c",&i);

2. 1. 3.      主要程序段及其解释：

   2.  if((ch>='A'&&ch<='Z')||(ch>='a'&&ch<='Z')||(ch>=48&&ch<=57))
              {
                 if((ch>='A'&&ch<='Z')||(ch>='a'&&ch<='Z'))
                 {
                     lin[j++]=ch;
                     ch=pro[i++];
                     while((ch>='A'&&ch<='Z')||(ch>='a'&&ch<='Z')||(ch>=48&&ch<=57))
                     {
                         lin[j++]=ch;
                     ch=pro[i++];
                     }
                      lin[j]='\0';
                      i--;
                      syn=10;
                      for(n=0;n<6;n++)
                          if(strcmp(lin,word[n])==0)
                      {
                          syn=n+1;
                          break;
                      }
                 }
                 else
                 {
                     while(ch>=48&&ch<=57)
                     {
                         lin[j++]=ch;
                         ch=pro[i++];
                     }
                     i--;
                     lin[j]='\0';
                     syn=11;
                 }
              }
              else
              {
                  if(ch=='<')
                      {lin[j++]=ch;
                  ch=pro[i++];
                  if (ch=='>')
                      {
                          syn=21;
                  lin[j++]=ch;
                  lin[j]='\0';
                  }
                  else if(ch=='=')
                      {
                          syn=22;
                  lin[j++]=ch;
                  lin[j]='\0';
                  }
                  else
                      {
                          syn=20;
                  lin[j]='\0';
                  i--;
                  }
                      }
                  else if(ch=='>')
                      { lin[j++]=ch;
                  ch=pro[i++];
                  if (ch=='=')
                      {
                          syn=24;
                  lin[j++]=ch;
                  lin[j]='\0';
                  }
                  else
                      {
                          syn=23;
                  lin[j]='\0';
                  i--;
                  }
                  }
                  else if(ch==':')
                      {
                          lin[j++]=ch;
                  ch=pro[i++];
                  if (ch=='=')
                      {
                          syn=18;
                  lin[j++]=ch;
                  lin[j]='\0';}
                  else
                      {
                          syn=17;
                  lin[j]='\0';
                  i--;
                  }
                  }
                  else if(ch=='+')
                      {syn=13;
                  lin[j++]=ch;
                  lin[j]='\0';
                  }
                  else if(ch=='-')
                      {
                          syn=14;
                  lin[j++]=ch;
                  lin[j]='\0';}
                  else if(ch=='*')
                      {
                          syn=15;
                  lin[j++]=ch;
                  lin[j]='\0';}
                  else if(ch=='/')
                      {
                          syn=16;
                  lin[j++]=ch;
                  lin[j]='\0';
                  }
                  else if(ch=='=')
                      {
                          syn=25;
                  lin[j++]=ch;
                  lin[j]='\0';
                  }
                  else if(ch==';')
                      {
                          syn=26;
                  lin[j++]=ch;
                  lin[j]='\0';
                  }
                  else if(ch=='(')
                              {
                                  syn=27;
                  lin[j++]=ch;
                  lin[j]='\0';
                  }
                  else if(ch==')')
                      {
                          syn=28;
                  lin[j++]=ch;
                  lin[j]='\0';}
                  else if(ch=='#')
                  {
                      syn=0;
                      lin[j++]=ch;
                      lin[j]='\0';
                  }
                  else
                          syn=-1;
                  }
                          return syn;
              }

   3. 判断词的种类
   4. .      运行结果及分析
   5. 

      四、        实验总结

      对于词法分析的输入，有些不懂。通过用字符数组的方式储存来解决。