aha.cpp

类高级语言的词法分析程序 在keyword里是关健词 origin输入源文件 token输出结果

/*
   类高级程序设计语言的词法分析程序
*/
#include<stdio.h>
#include<string.h>
#include<stdlib.h>
#include<ctype.h>

void Sort(char* inputword,FILE* Originalfile);
void RecogID(char* input,FILE* Originalfile);				//处理标识符
void RecogDig(char*input,FILE* Originalfile);				//处理数字
void RecogDel(char* input,FILE* Originalfile);				//处理界符
void HandleCom(char* input,FILE* Originalfile);				//处理注释

int Iskeyword(char word);
int IsNumber(char next);

void Initiate(struct keywordchain* keywordtable);
void Lookup(struct keywordchain* keywordtable,char value[],struct tokenform* token, int singal);
void Writetoken(struct tokenform token);
void Scanner();

//定义符号表结构
struct keywordchain
{
  int id;
  char* value;
  struct keywordchain* next;
};
struct keywordchain keywordtable;//定义符号表 
int lines =0;//用来统计行数


struct tokenform				//定义token结构
{
  int id;
  struct keywordchain* reference;
};

int main()
{
	Scanner();
	return 0;
}
//从源程序文件中读取原程序
void Scanner()
{
  Initiate(&keywordtable);
  FILE* origin;
  char input;
  if((origin=fopen("origin.txt","r"))==NULL)
	  printf("文件打开失败！\n");
   else
   {
		fscanf(origin,"%c",&input);
     
		while(input!=EOF)
			Sort(&input,origin);
   }
   fclose(origin);
}
//分类函数用来识别各类单词
void Sort(char* input,FILE* Originalfile)
{
  if(isalpha(*input))
  	  RecogID(input,Originalfile);

  else if(isdigit(*input))
  	  RecogDig(input,Originalfile);

  else if(*input == '/')
  	  HandleCom(input,Originalfile);

  else if(*input == ' '||*input == '\n'||*input == '\t')
  {
	  if(*input == '\n')
		  lines++;
	  *input = fgetc(Originalfile);
  }
  else
      RecogDel(input,Originalfile);
}

//处理关键字和标识符
void RecogID(char* input,FILE* Originalfile)
 {
   char word[100];
   char next='a';				//为使while循环开始
   int i=0;
   struct tokenform token;
   word[i] = *input;
   
   while(isdigit(next)||isalpha(next))			//读关键字或标识符
   {
	 fscanf(Originalfile,"%c",&next);
     if(isdigit(next)||isalpha(next))
		  word[++i] = next;
   }
   
   *input = next;
   word[++i] = '\0';
   Lookup(&keywordtable,word,&token,1);
   Writetoken(token);
 }

//处理注释部分 
void HandleCom(char* input,FILE* Originalfile)
{
    char word[100];
	bool flag =false;
	char next, next1='a';							//给next赋初值
	int i=0;										//计数
	word[i] = *input;
    fscanf(Originalfile,"%c",&next);
	
	if(next = '*')									//以/*开头的注释方式
	{
        
		while(flag == false)
		{
		   if(fscanf(Originalfile,"%c",&next1)==EOF)  //读到文件结尾
				 break;
		   
		   if(next == '*' && next1 =='/' && i!=0)     //防止/*/情况误认为结束
				flag = true;
		   
		   i++;
		   next = next1;
		}
	   
		if(flag == false)
			printf("第%d行注解未完\n",lines);
		
		if(fscanf(Originalfile,"%c",&next) == EOF)	 //处理下一字符
			*input = EOF;
	    else
			*input = next;
	}
	else if(next == '/')							//以//为开头的注释方式
	{
		while(next != '\n')							//读取全部注释
			fscanf(Originalfile,"%c",&next);
	
	    fscanf(Originalfile,"%c",&next);			//读下一个字符
	    *input = next;
	}
 
}
//处理界符和算符 
void RecogDel(char* input,FILE* Originalfile)
{
    char word[100];
	struct tokenform token;
	int i=0;
	char next;
	word[i] = *input;
	if(*input == '>')
	{
       fscanf(Originalfile,"%c",&next);
	   if(next == '=')
	   {
          word[++i] = next;
		  word[++i] = '\0';
          Lookup(&keywordtable,word,&token,1);
	      fscanf(Originalfile,"%c",&next);
	  }
	  else
	  {
          word[++i] = '\0';
          Lookup(&keywordtable,word,&token,1);
	      fscanf(Originalfile,"%c",&next);
	  }
	}
    else if(*input == '<')
	{
       fscanf(Originalfile,"%c",&next);
	   if(next == '=')
	   {
          word[++i] = next;
		  word[++i] = '\0';
          Lookup(&keywordtable,word,&token,1);
	      fscanf(Originalfile,"%c",&next);
	  }
	 else if(next == '>')
	 {
          word[++i] = next;
		  word[++i] = '\0';
          Lookup(&keywordtable,word,&token,1);
	      fscanf(Originalfile,"%c",&next);
	 }
	 else 
	  {
          word[++i] = '\0';
          Lookup(&keywordtable,word,&token,1);
	      fscanf(Originalfile,"%c",&next);
	  }
	}
    else if((*input == '(')||(*input == ')')||(*input == '=')||(*input == '+')||(*input == '*'))		//算符
	{
	    word[++i] = '\0';
	    Lookup(&keywordtable,word,&token,1);
        fscanf(Originalfile,"%c",&next);
	}
	
	else if((*input == '&')||(*input == ';')||(*input == ',')||(*input == '|')||(*input == '!')||(*input == '{')||(*input == '}'))		//界符
	{
	   word[++i] = '\0';
	   Lookup(&keywordtable,word,&token,1);
	   fscanf(Originalfile,"%c",&next);
	}
   *input = next;
   Writetoken(token);
}

//处理常数部分
void RecogDig(char* input,FILE* Originalfile)
{
   char number[100];
   char next;
   int state = 1;
   int i = 0;
   struct tokenform token;
   number[i] = *input;
   
   while(state != 5)
   {
       fscanf(Originalfile,"%c",&next);
	   
	   if(state == 1)				//接受数据的自动机
	   {
			if(isdigit(next))
				state = 1;
			else if(next == '.')
				state = 2;
			else if (next == 'e')
				state = 4;
			else
				state = 5;
	   }
	   else if(state == 2)
	   {
			if(isdigit(next))
				state = 3;
			else
			{
				printf("数字格式输入错误！\n");
				state = 5;
			}
	   }
	   else if (state == 3)
	   {
			if(isdigit(next))
				state = 3;
			else if (next == 'e')
				state = 4;
			else
				state = 5;
	   }
	   else if (state == 4)
	   {
			if(isdigit(next))
				state = 4;
			else
				state = 5;
	   }

	   number[++i] = next;  
   }
   *input = next;
   number[i] = '\0'; 
   Lookup(&keywordtable,number,&token,0);
   Writetoken(token);
}

//将识别出来的token写入指定文件
void Writetoken(struct tokenform token)
{
   FILE* tokenfile;
   if((tokenfile=fopen("token.txt","a"))==NULL)
		printf("文件写入失败！\n");
   else
   {
       fprintf(tokenfile,"%s %d\n",token.reference->value,token.id);
	   fclose(tokenfile);
   }
}
 //判断给定字符是否符合关键字或标识符的要求
 
// 创建符号表
void Initiate(struct keywordchain* keyword)
{
  struct keywordchain* midpoint;
  int id;
  char name[30];
 
  FILE* keywordfile;
  if((keywordfile=fopen("keyword.txt","r"))==NULL)
		printf("文件打开失败！\n");
  keyword->id = 0;
  keyword->value = "none";
  while(fscanf(keywordfile,"%s%d",name,&id)!=EOF)
  {
     midpoint = (struct keywordchain*)malloc(sizeof(struct keywordchain));
     midpoint->id = id;
     midpoint->value = (char*)malloc(sizeof(name));
     strcpy(midpoint->value ,name);
	 midpoint->next = NULL;
     keyword->next = midpoint;
     keyword = midpoint;
  }
  //keywordtable = (struct keywordtable*)malloc(sizeof(struct keywordchain)); 
}

//查询符号表操作 

void Lookup(struct keywordchain* keyword,char value[],struct tokenform* token, int singal)
{
    struct keywordchain *reserve, *add;
	bool flag = false;
	while(keyword!=NULL)								
	{
	   if(!strcmp(keyword->value,value))				//如果是关键字，算符，界符
	   {
		   token->id = keyword->id;						//形成Token字
		   token->reference = keyword;
		   flag = true;
		   break;
	   }
	   reserve = keyword;
	   keyword = keyword->next;
	}
    if(flag == true)
		return ;
	else												//
	{
		add = (struct keywordchain*)malloc(sizeof(struct keywordchain));
	    add->value= (char*)malloc(sizeof(value));
	    strcpy(add->value,value);
	    if(singal == 1)
			add->id = 13;	
		else
			add->id = 12;
		add->next = NULL;
	    reserve->next = add;
	    token->id = add->id;
	    token->reference = add;
	}
}