编译原理实验之源程序的预处理及词法分析程序设计

---

作者：野孩子1991
来源：CSDN
原文：https://blog.csdn.net/u010668907/article/details/39141925
版权声明：本文为博主原创文章，转载请附上博文链接！

如下是我对野孩子代码的修正：
预处理代码：

#include<stdio.h>
#include<String.h>
int main()
{
 FILE *p;
 int  i=0,j=0;//
 char str[1000],str1[1000],c;
 if((p=fopen("e:\\test.txt","rt"))==NULL){
  printf("无法打开");
  return  0;
 }
 else{
  
  while((c=getc(p))!=EOF){
   str[i] = c; 
   i++;
  }
  fclose(p);
  str[i] = '\0';
  for(i=0;i<strlen(str);i++){
   if(str[i]=='/'&&str[i+1]=='/'){
    while(str[i++]!='\n'){}
    i--;
   }//单行注释
   else if(str[i]=='/'&&str[i+1]=='*'){
    while(!(str[i]=='*'&&str[i+1]=='/'))
	{
	i++;
	}
    i+=1;
   }//多行注释
   else if(str[i]==' '&&str[i+1]==' '){
    while(str[i]==' '){i++;}
    i--;
    if(str1[j-1]!=' ')
       str1[j++]=' ';
   }//多个空格，去除空格
   else if(str[i]=='\n') {
    if(str1[j-1]!=' ')
       str1[j++]=' ';}
   //换行处理，
   else if(str[i]==9){
    while(str[i]==9){
     i++;
    }
    if(str1[j-1]!=' ')
     str1[j++]=' ';
    i--;
   }//tab键处理
   else str1[j++] = str[i];//其他字符处理
  }
  str1[j] = '\0';
  if((p = fopen("e:\\test1.txt","w"))==NULL){
   printf("can not find it!");
   return 0;
  }
  else{
   if(fputs(str1,p)!=0){
    printf("存储失败！");
   }
   else printf("存储成功！");
  }
  fclose(p);
 }
 return 0;
}

词法分析器的代码如下：

#include<stdio.h>
#include<String.h>
int main(){
 FILE *p;
 int  falg = 0,len,i=0,j=0;//
 char *rwtab[27]={"","main","if","then","while","do",
  "static","int","double","struct","break","else","long",
  "switch","case","typedef","char","return","const","float",
  "short","continue","for","void","sizeof","default","do"};//26个
 char str[1000],str1[1000],c;
 int syn,num; int k; 
 char token[200];
 
 if((p=fopen("e:\\test1.txt","rt"))==NULL){
  printf("无法打开");
  return  0;
 }
 
  //fgets(str,1000,p);
  while((c=getc(p))!=EOF){
   str[i++] = c; 
  }
  fclose(p);
  if((p=fopen("e:\\test2.txt","w"))==NULL){
  printf("无法打开");
  return  0;
  }
  str[i] = '\0';
//printf("%s\n",str);
 for(i=0;str[i]!='\0';){
  j = 0;
  num = -1;
  if((str[i]>='a'&&str[i]<='z')||(str[i]>='A'&&str[i]<='Z')){
   while((str[i]>='a'&&str[i]<='z')||(str[i]>='A'&&str[i]<='Z')||(str[i]>='0'&&str[i]<='9')||str[i]=='_'){
    token[j++] = str[i++];
   } 
   token[j] = '\0';
   for( k=1;k<27;k++){
    if(strcmp(rwtab[k],token)==0)
     break;
   }
   if(k<25)
    syn = k;
   else if(k==25)
    syn = 39;
   else if(k==26)
    syn = 40;
   else syn = 25;
  }//关键字和标示符处理
  
 
  else if(str[i]>='0'&&str[i]<='9'){
   num = 0;
   while(str[i]>='0'&&str[i]<='9'){//当读到第一个为0~9的数字时接着读之后的数字 
    num = num*10+str[i]-'0';
    token[j++] = str[i++];
   }
   if((str[i]>='a'&&str[i]<='z')||
   (str[i]>='A'&&str[i]<='Z'))
  {
  	 num=-1;syn=-3;
  	 while((str[i]>='a'&&str[i]<='z')||
   (str[i]>='A'&&str[i]<='Z')||(str[i]>='0'&&str[i]<='9')){
    token[j++] = str[i++];
   }
  
  }
   else syn = 26;
  }//数字在此处处理
  
  else {
   if(str[i]==':'&&str[i+1]=='='){
    syn = 32;
    token[j++] = str[i];
    token[j++] = str[++i];
    i++;
   }
   else if(str[i]=='<'&&str[i+1]=='>'){
    syn = 34;
    token[j++] = str[i];
    token[j++] = str[++i];
    i++;
   }
   else if(str[i]=='<'&&str[i+1]=='='){
    syn = 35;
    token[j++] = str[i];
    token[j++] = str[++i]; 
    i++;
   }
   else if(str[i]=='>'&&str[i+1]=='='){
    syn = 36;
    token[j++] = str[i];
    token[j++] = str[++i];
    i++;
   }
   else if(str[i]==' '){
    i++;
    syn = -2;
   }//空格处理
   /*
   else if(str[i]!=' '){
    syn = -1;
    while(str[i++]!=' '){
     token[j++] = str[i];
    }
   }//不明字符的处理
   */
   else{
    switch(str[i]){
     case '+': syn = 27;break;
     case '-': syn = 28;break;
     case '*': syn = 29;break;
     case '/': syn = 30;break;
     case ':': syn = 31;break;
     case '<': syn = 33;break;
     case '>': syn = 36;break;
     case ';': syn = 41;break;
     case ')': syn = 43;break;
     case '(': syn = 42;break;
     case '#': syn = 0;break;
     case '=':syn = 38;break;
     default: syn = -1;break;
    }
    
    token[j++] = str[i++];
   }
  }
  token[j] = '\0';
  if(num!=-1){
   printf("%d %d\n",num,syn);
   
   
   
  }
  else if(syn!=-1&&syn !=-2 &&syn!=-3){
   printf("%s %d\n",token,syn);
   
  }
  else if(syn==-1){
   printf("%s error\n",token);
   
  }
  else if(syn == -3){
   printf("%s error ID\n",token);
   
  }
 }
 fclose(p);
 return 0;
}