📄 词法分析程序.cpp

📁 c++6.0上实现的s语言词法分析器
💻 CPP
字号:
# include <stdio.h>
# include <string.h>
# include <stdlib.h>
# define LENGTH 61
# define N		100
/*******************************************************/
typedef struct token{
	int label;
	char name[30];
	int code;
	int addr;
}token;
typedef struct KeyWord{
	char name[30];
	int code;
}KeyWord;
typedef struct symble{
	int number;
	int type;
	char name[30];
}symble;
/****************************************************/
char ch;
int var_count;
int error_count;
int label_count;
int code_count;
int addr_count;
int LineOfPro;
char filename[30];
FILE *KeyFin;
FILE *SourceFin;
FILE *TokenFout;
FILE *SymbleFout;
KeyWord key[LENGTH];
token CurrentToken;
symble CurrentSimble;
symble SymbleList[N];
/*****************************************************/
void Scanner();
void ScannerInit();
void IsAlpha();
void IsNumber();
void IsAnotation();
void IsChar();
void IsOther();
void OutPut();
void Error(int a);
int WordHave();
int strcmp(char *s,char *t) {
	for(;*s==*t;s++,t++)
		if(*s==0)return 0;
		return 1;
}
/*****************************************************/
int main(){
	int i=0,j=0;
	code_count=0;
	LineOfPro=0;
	var_count=0;
	addr_count=1;
	label_count=1;
	for(i=0;i<N;i++){
		SymbleList[i].number=0;
		SymbleList[i].type=0;
		for(j=0;j<30;j++) SymbleList[i].name[j]='\0';
	}
		Scanner();
		return 0;
}
/*************************************************/
void Scanner(){
	int i=0;
	error_count=0;
	ScannerInit();
	printf("*************************************************\n");
	printf("         语言词法分析器\n");
	printf("*************************************************\n");
	printf("输入源文件名：");
	for(;;){
		scanf("%c",&filename[i]);
		if(filename[i]==10) break;
		i++;
	}
	filename[i]='\0';
	if((SourceFin=fopen(filename,"rt"))==NULL){
		printf("无法打开文件 %s.\n",filename);
		exit(1);
	}
	if((TokenFout=fopen("token.txt","wt+"))==NULL){
		printf("无法打开文件 token.txt.\n");
		exit(1);
	}
	if((SymbleFout=fopen("symble.txt","wt+"))==NULL){
		printf("无法打开文件 symble.txt.\n");
		exit(1);
	}
	ch=fgetc(SourceFin);
	while(ch!=EOF){
		for(i=0;i<30;i++)
			CurrentToken.name[i]='\0';
		if((ch>47)&&(ch<58))
			IsNumber();
		else{
			if(((ch>64)&&(ch<90))||((ch>96)&&(ch<123))||ch=='_')
				IsAlpha();
			else{
				if(ch=='/') IsAnotation();
				else if(ch=='\'') IsChar();
				     else IsOther();
			}
		}
	}
	fclose(SourceFin);
	fclose(TokenFout);
	fclose(SymbleFout);
	printf("分析完毕.\n");
}
/***********  初始化  ********************************/
void ScannerInit() {
	 if((KeyFin=fopen("ni.txt","rt"))==NULL)
	 {printf("cannot open ni.txt.\n");
	  exit(1);
	 }
	 for(int i=0;i<60;i++)for(int k=0;k<30;k++)key[i].name[k]='\0';
	 for(i=1;i<60;i++){           /*读入编码表*/
		 fscanf(KeyFin,"%s %d",key[i].name,&key[i].code);
	 }
	 fclose(KeyFin);
}
/***********************************数字处理*************/
void IsNumber(){
	int k=0;
	int flag=0;
	char ch1;
	while(((ch>47)&&(ch<58))){
		CurrentToken.name[k++]=ch;
		ch=fgetc(SourceFin);
		if(ch=='.'){flag=1;break;}
	}
	CurrentToken.code=28;
	CurrentToken.addr=addr_count++;
	CurrentToken.label=label_count++;
	if(flag){
		ch1=fgetc(SourceFin);
		if((ch1>47)&&(ch1<58)) CurrentToken.name[k++]=ch;
		    else Error(2);
		ch=ch1;
		while((ch>47)&&(ch<58)){
			CurrentToken.name[k++]=ch;
			ch=fgetc(SourceFin);
		}
		CurrentToken.code=29;
		if(ch=='.'){
			Error(2);
			ch=fgetc(SourceFin);
			while((ch>47)&&(ch<58)) ch=fgetc(SourceFin);
		}
		if(((ch>64)&&(ch<90))||((ch>96)&&(ch<123))){
			Error(2);
			while(((ch>64)&&(ch<90))||((ch>96)&&(ch<123))){
				ch=fgetc(SourceFin);
				while((ch>47)&&(ch<58)) ch=fgetc(SourceFin);
			}
		}
	}
	OutPut();
}
/**************字母处理*********************/
void IsAlpha(){
	int i,h;
	h=0;i=0;
	while(((ch>64)&&(ch<90))||((ch>96)&&(ch<123))||ch=='_'){
		CurrentToken.name[i++]=ch;
		ch=fgetc(SourceFin);
	}
	for(i=1;i<LENGTH;i++){ /*判断输入字符是否为保留字*/
		h=strcmp(CurrentToken.name,key[i].name);
		if(!h) break;
	}
	if(!h){
		CurrentToken.code=key[i].code;
		CurrentToken.addr=-1;
	}
	else{
		CurrentToken.code=27;
	    CurrentToken.addr=addr_count++;
	}
	CurrentToken.label=label_count++;
	OutPut();
}
/*******************注释处理*********************/
void IsAnotation(){
	char ch1;
	ch1=ch;
	ch=fgetc(SourceFin);
	if(ch=='*') for(;;){ch=fgetc(SourceFin);
	                    if(ch==EOF){Error(3);break;}
						if(ch=='*'){
							ch1=ch;
							ch=fgetc(SourceFin);
							if(ch=='/'){ch=fgetc(SourceFin);break;}
						}
	}
	else{
		CurrentToken.name[0]='/';
		CurrentToken.code=39;
		CurrentToken.addr=-1;
		CurrentToken.label=label_count++;
		OutPut();
	}
}
/***************字符串处理*******************/
void IsChar(){
	int i=0;
	for(;;){
		ch=fgetc(SourceFin);
		CurrentToken.code=30;
		if(ch!='\'')CurrentToken.name[i++]=ch;
		else break;
	}
	CurrentToken.addr=addr_count++;
	CurrentToken.label=label_count++;
	OutPut();
	ch=fgetc(SourceFin);
}
/******************其他情况处理****************/
void IsOther(){
	char ch1;
	int i;
	for(i=0;i<30;i++) CurrentToken.name[i]='\0';
	switch(ch){
	    case '(':CurrentToken.name[0]='(';
	             CurrentToken.code=32;
			     CurrentToken.addr=-1;
				 CurrentToken.label=label_count++;
				 OutPut();
				 ch=fgetc(SourceFin);
				 break;
		case ')':CurrentToken.name[0]=')';
	             CurrentToken.code=33;
			     CurrentToken.addr=-1;
				 CurrentToken.label=label_count++;
				 OutPut();
				 ch=fgetc(SourceFin);
				 break;
		case '*':CurrentToken.name[0]='*';
	             CurrentToken.code=34;
			     CurrentToken.addr=-1;
				 CurrentToken.label=label_count++;
				 OutPut();
				 ch=fgetc(SourceFin);
				 break;
		case '+':CurrentToken.name[0]='+';
	             CurrentToken.code=35;
			     CurrentToken.addr=-1;
				 CurrentToken.label=label_count++;
				 OutPut();
				 ch=fgetc(SourceFin);
				 break;
		case ',':CurrentToken.name[0]=',';
	             CurrentToken.code=37;
			     CurrentToken.addr=-1;
				 CurrentToken.label=label_count++;
				 OutPut();
				 ch=fgetc(SourceFin);
				 break;
		case '-':CurrentToken.name[0]='-';
	             CurrentToken.code=36;
			     CurrentToken.addr=-1;
				 CurrentToken.label=label_count++;
				 OutPut();
				 ch=fgetc(SourceFin);
				 break;
		case '.':CurrentToken.name[0]='.';
	             CurrentToken.code=38;
			     CurrentToken.addr=-1;
				 CurrentToken.label=label_count++;
				 OutPut();
				 ch=fgetc(SourceFin);
				 break;
		case ':':ch1=ch;
			     ch=fgetc(SourceFin);
				 if(ch!='='){
					 CurrentToken.name[0]=':';
	                 CurrentToken.code=40;
			         CurrentToken.addr=-1;
				     CurrentToken.label=label_count++;
				     OutPut();
				 }
				 else{
					 CurrentToken.name[0]=':';
                     CurrentToken.name[1]='=';
	                 CurrentToken.code=41;
			         CurrentToken.addr=-1;
				     CurrentToken.label=label_count++;
				     OutPut();
				     ch=fgetc(SourceFin);
				 }
				 break;
		case ';':CurrentToken.name[0]=';';
	             CurrentToken.code=42;
			     CurrentToken.addr=-1;
				 CurrentToken.label=label_count++;
				 OutPut();
				 ch=fgetc(SourceFin);
				 break;
		case '<':ch1=fgetc(SourceFin);
			     if(ch1=='='){
			         CurrentToken.name[0]='<';
					 CurrentToken.name[1]='=';
	                 CurrentToken.code=44;
			         CurrentToken.addr=-1;
				     CurrentToken.label=label_count++;
				     OutPut();
				     ch1=fgetc(SourceFin);
				 }
				 else{
					 if(ch1=='>'){
						 CurrentToken.name[0]='<';
					     CurrentToken.name[1]='>';
	                     CurrentToken.code=45;
			             CurrentToken.addr=-1;
				         CurrentToken.label=label_count++;
				         OutPut();
				         ch1=fgetc(SourceFin);
					 }
					 else{
						 CurrentToken.name[0]='<';
	                     CurrentToken.code=43;
			             CurrentToken.addr=-1;
				         CurrentToken.label=label_count++;
				         OutPut();
					 }
				 }
				 ch=ch1;
				 break;
		case '=':CurrentToken.name[0]='=';
	             CurrentToken.code=46;
			     CurrentToken.addr=-1;
				 CurrentToken.label=label_count++;
				 OutPut();
				 ch=fgetc(SourceFin);
				 break;
		case '>':ch1=fgetc(SourceFin);
			     if(ch1=='='){
			         CurrentToken.name[0]='>';
					 CurrentToken.name[1]='=';
	                 CurrentToken.code=48;
			         CurrentToken.addr=-1;
				     CurrentToken.label=label_count++;
				     OutPut();
				     ch1=fgetc(SourceFin);
				 }
				 else{
					 CurrentToken.name[0]='>';
	                     CurrentToken.code=47;
			             CurrentToken.addr=-1;
				         CurrentToken.label=label_count++;
				         OutPut();
				 }
				 ch=ch1;
				 break;
		 case 10:LineOfPro++;
			     ch=fgetc(SourceFin);
				 break;
		 case 13:LineOfPro++;
			     ch=fgetc(SourceFin);
				 break;
		 case ' ':ch=fgetc(SourceFin);
				 break;
		 case EOF:Error(4);break;
		 default :Error(1);ch=fgetc(SourceFin);
				  break;
		}
}
/****************输出模块******************/
void OutPut(){
	int flag,i=0;
	int k;
	/*查看符号表*/
	if((CurrentToken.code==27)||(CurrentToken.code==30)||(CurrentToken.code==28)||(CurrentToken.code==29)){
		CurrentSimble.number=CurrentToken.addr;
		CurrentSimble.type=CurrentToken.code;
		strcpy(CurrentSimble.name,CurrentToken.name);
		flag=WordHave();
		if(((CurrentToken.code==27)&&(flag==1))||(CurrentToken.code==30)||(CurrentToken.code==28)||(CurrentToken.code==29))
			fprintf(SymbleFout,"%3d  %3d  %s\n",CurrentSimble.number,CurrentSimble.type,CurrentSimble.name);
	}
	/*输出到token表*/
	for(;;) if(CurrentToken.name[i++]=='\0') break;
	fprintf(TokenFout,"%3d      %s",CurrentToken.label,CurrentToken.name);
	printf("%3d      %s",CurrentToken.label,CurrentToken.name);
	for(k=20-i;k>0;k--){fprintf(TokenFout," ");printf(" ");}
	fprintf(TokenFout,"%3d      %3d\n",CurrentToken.code,CurrentToken.addr);
	printf("%3d      %3d\n",CurrentToken.code,CurrentToken.addr);
}
/**************出错处理***************/
void Error(int a){
	error_count++;
	switch(a){
	   case 1:printf("error %2d 非法字符于 %3d 行.\n",error_count,LineOfPro+1);break;
	   case 2:printf("error %2d 实常数出错于 %3d 行.\n",error_count,LineOfPro+1);break;
	   case 3:printf("error %2d 没有匹配的注释符 '*/' \n",error_count);break;
	   case 4:printf("error %2d 非正常结束！ \n",error_count);break;
	   default :break;
	}
	return;
}
int WordHave(){
	int flag,i=0;
	for(i=0;i<var_count;i++){
		flag=strcmp(CurrentSimble.name,SymbleList[i].name);
		if(flag==0){
			CurrentToken.addr=SymbleList[i].number;
			return 0;
		}
	}
	SymbleList[var_count].number=CurrentToken.addr;
	SymbleList[var_count].type=CurrentToken.code;
	strcpy(SymbleList[var_count].name,CurrentToken.name);
	var_count++;
	return 1;
}
💿 文件大小 4 K
👤 上传用户 beixinning
📂 所属分类编译器/解释器
🏷️ 相关标签

#6.0 #语言 #分析器
⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -