词法分析.cpp

编译原理 词法分析器 编译原理 词法分析器

#include<iostream.h>
#include<string.h>
#include<stdio.h>

#define LT 12
#define LE 13
#define EQ 14
#define NE 15
#define GT 16
#define GE 17
#define FZ 18
#define DIV 19


#define jing 20
#define semicolon 21
#define leftpar 22
#define rightpar 23
#define ID 24  //标志符  
#define INT 25//整数
#define YH 26


 

struct KeyWord        //关键字结构
{
 char *word;
 int id;
};

KeyWord keyword[]={    //关键字数组
 {"int",1},
 {"main",2},
 {"if",3},
 {"for",4},
 {"else",5},
 {"printf",6},
 {"scanf",7},
 {"float",8},
 {"double",9},
 {"stdio.h",10},
 {"include",11}
};


char TOKEN[20];
int graphnum=1;     //记录错误所在的位置


int lookup(char *string);
void out(int id,char *string);
void report_error(char ERR_CH);
bool isalpha(char c) ;
bool isdigit(char c);
bool isalnum(char c);
void scan(FILE *fp);

 

int lookup(char *string)
{
 for(int i=0;i<sizeof(keyword)/sizeof(KeyWord);i++)
 {
  if(strcmp(string,keyword[i].word)==0)
   return keyword[i].id;
 }
 return 0;
}

void out(int id,char *string)
{
 printf("(%d,%s)\n",id,string);;
}

void report_error(char ERR_CH)        //错误处理程序
{
 printf("undeclared identifler %c at the %d line!\n",ERR_CH,graphnum);
}

bool isalpha(char c)   
{
 if((c>='a'&&c<='z')||(c>='A'&&c<='Z'))
  return true;
 else
  return false;
}

bool isdigit(char c)
{
 if(c>='0'&&c<='9')
  return true;
 else
  return false;
}

bool isalnum(char c)
{
 if(isalpha(c)||isdigit(c))
  return true;
 else
  return false;
}

void scan(FILE *fp)
{
 char ch;
 int i,c;
 
 while(!feof(fp))
 {
 ch=fgetc(fp);
 if(isalpha(ch))  
 {
  TOKEN[0]=ch;
  ch=fgetc(fp);
  i=1;
  while(isalnum(ch))  
  {
   TOKEN[i]=ch;
   i++;
   ch=fgetc(fp);
  }
  TOKEN[i]='\0';
  fseek(fp,-1,1);
  c=lookup(TOKEN);
  if(c==0) 
   out(ID,TOKEN);
  else
   out(c," ");
 }
 else if(isdigit(ch))
 {
  TOKEN[0]=ch;
  ch=fgetc(fp);
  i=1;
  while(isdigit(ch))
  {
   TOKEN[i]=ch;
   i++;
   ch=fgetc(fp);
  }
  TOKEN[i]='\0';
  fseek(fp,-1,1);
  out(INT,TOKEN);
 }
 else
  switch(ch)
  {
   case '<': ch=fgetc(fp);
      if(ch=='=') 
       out(LE," ");
      else if(ch=='>') 
       out(NE," ");
      else
      {
       fseek(fp,-1,1);
       out(LT," ");
      }
      break;
   case '=':ch=fgetc(fp);
	   if(ch=='=')             
          out(EQ," ");
	   else {fseek(fp,-1,1);  out(FZ," ");}
	   break;
   case '>': ch=fgetc(fp);
      if(ch=='=')
       out(GE," ");
      else
      {
       fseek(fp,-1,1);
       out(GT," ");
      }
      break;
   case '/': ch=fgetc(fp);   //删除程序中的注释
      if(ch=='/')
      {
       do
       {
        ch=fgetc(fp);
       }while(ch!='\n');
       graphnum++;
      }
      else
      {
       fseek(fp,-1,1);
       out(DIV," ");
      }
      break;
   case '"':out(YH," ");
   case '{':out(leftpar," ");break;
   case '}':out(rightpar," ");break;
   case '(':out(leftpar," ");break;
   case ')':out(rightpar," ");break;
   case ';':out(semicolon," ");break;
   case '#':out(jing," ");break;
   case ' ': break;                 //删除程序中的空格              
   case '\n': graphnum++; break;   //删除程序中的回车,并记录程序编译到第几行            
   case '	': break;      //删除程序中的横向制表符
   case -1: break;      //删除文件尾符号
   default: report_error(ch);
     break;
  }

 }
 return;
}
void main()
{
 FILE *fp;
 fp=fopen("21.txt","r");
 scan(fp);
 fclose (fp);
}