33.txt

编译原理课程实验

#include<stdio.h>
#include<string.h>
#include<ctype.h>
//定义缓冲区大小
#define  BUFFERLEN  2048
//定义缓冲区索引
int  front=0,rear=0;
//定义缓冲区并初始化
char buffer[BUFFERLEN]={0};
//用于指示装入哪半个缓冲区
int  position=0;
//全局变量指示行号
int  line;
//filename: 要解析的源文件名
FILE * fin;
//临时数组,用于存储标识符或关键字
char id[100];
//临时数组索引
int  dex=0;
//每行单词计数器
int  count=0;
//临时字符，用于存储字符
char achar;
//符号结构定义
struct token{
	int   lineno;//行号
	int   position;//在该行中的位置
	int   wordkey;//符号类型,用十六进制表示
    char* value;
	struct token* next_token;
}token;
//变量表
struct token* token_list_head=NULL;
//关键字表
char* keyword[]={
	"abstract",
	"boolean",
	"break",
	"byte",
	"case",
	"catch",
	"char",
	"class",
	"const",
	"continue",
	"default",
	"do",
	"double",
	"else",
	"extends",
	"false",
	"final",
	"finally",
	"float",
	"for",
	"goto",
	"if",
	"implements",
	"import"
	"instanceof",
	"int",
	"interface",
	"long",
	"native",
	"new",
	"null",
	"package",
	"private",
	"protect",
	"public",
	"return",
	"short",
	"static",
	"super",
	"switch",
	"synchronized",
	"this",
	"throw",
	"throws",
	"transient",
	"true",
	"try",
	"void",
	"volatile",
	"while"
};
//将源文件装入缓冲区
void  load(FILE * fin,int flag){
	if(flag==0){
	    fread(buffer,sizeof(char),1023,fin);
		rear=0;
	}
	else{
		fread(buffer+1024,sizeof(char),1023,fin);
		rear=1025;
	}
}
//在关键字表中进行查找,若照到则返回1，否则返回0
int lookup_keyword(char* word){
	int i;
	for(i=0;i<49;i++){
		if(strcmp(word,keyword[i])==0)
			return 0;
	}
	if(i==49)
		return 1;
}

//获取一个符号
struct token* get_token(){
	int i;
    struct token* token_pointer;
	char ch=buffer[rear];

	//如果是回车，只是将行号加1
	if(ch=='\n'){
		line++;
	}
	//如果遇到缓冲区结尾，装入另一半缓冲区
	else if(ch==EOF){
		position++;
		fseek(fin,1023,1);
		if(position/2==0){
		    load(fin,0);
		}
		else{
			 load(fin,1);
		}
		ch=buffer[rear];
	}
	//如果是空格，只是将其跳过，并将所有空格用一个属性字表示
	else if(isspace(ch)){
	    do{
			ch=buffer[++rear];
		    if(ch=='\n'){
				rear++;//?
		        line++;
			}
			else if(ch==EOF){
	            position++;
		        fseek(fin,1023,1);
	        	if(position/2==0){
		            load(fin,0);
				}
	        	else{
		        	load(fin,1);
				}
		        ch=buffer[rear];
			}
		}while(isspace(ch));
		front=rear;
     
        token_pointer=(struct token*)malloc(sizeof(token));
	    token_pointer->lineno=line;
	    token_pointer->wordkey=0x102;
		token_pointer->value=(char*)malloc(2*sizeof(char));
		strcpy(token_pointer->value," ");
		token_pointer->next_token=token_list_head;
		token_list_head=token_pointer;
	}
	//判断关键字和标识符及布尔值
	if(isalnum(ch)||ch=='_'||ch=='$'){
	    do{
			ch=buffer[++rear];
			if(ch=='\n'){
		        //error
			}
			if(ch==EOF){
	            position++;
		        fseek(fin,1023,1);
	        	if(position/2==0){
		            load(fin,0);
				}
	        	else{
		        	load(fin,1);
				}
		        ch=buffer[rear];
			}
		}while(isalnum(ch)||isdigit(ch)||ch=='_'||ch=='$');
		i=front;
		while(i!=rear){
			if(buffer[i]==EOF){
				i=(rear/1024)*1024;
			}
			id[dex]=buffer[i];
			dex++;
			i++;
		}
		//创建一块token结构
		token_pointer=(struct token*)malloc(sizeof(token));
	    token_pointer->lineno=line;
			
    	token_pointer->value=(char *)malloc(dex*sizeof(char));
	    strcpy(token_pointer->value,id);

		token_pointer->next_token=token_list_head;
		token_list_head=token_pointer;
		//在关键字表中查找
		if(lookup_keyword(id)){
			token_pointer->wordkey=0x104;
		}
		else{
			if(strcmp(id,"true")==0 || strcmp(id,"false")==0){
				token_pointer->wordkey=0x103;
			}
			else{
				token_pointer->wordkey=0x103;
		    }
		}
		front=rear;
		//将临时变量存储数组索引置零
		dex=0;
		//将临时变量存储数组清零
		memset(id,0,100);
	}
	if(ch=='/'){
		ch=buffer[++rear];
		if(ch==EOF){
	        position++;
		    fseek(fin,1023,1);
	        if(position/2==0){
		        load(fin,0);
			}
	        else{
		        load(fin,1);
			}
		    ch=buffer[rear];
		}
		else if(ch=='/'){
		    do{
		        ch=buffer[++rear];
			    if(ch==EOF){
	                position++;
		            fseek(fin,1023,1);
	        	    if(position/2==0){
		                load(fin,0);
					} 
	        	    else{
		        	    load(fin,1);
					}
		            ch=buffer[rear];
				}
			}while(ch!='\n');
			
		}
		else if(ch=='*'){
			 do{
		        ch=buffer[++rear];
			    if(ch==EOF){
	                position++;
		            fseek(fin,1023,1);
	        	    if(position/2==0){
		                load(fin,0);
					} 
	        	    else{
		        	    load(fin,1);
					}
		            ch=buffer[rear];
				}
			}while(!(ch=='*'&& (ch=buffer[++rear])=='/'));
		}
		rear++;
		if(ch==EOF){
	        position++;
	        fseek(fin,1023,1);
	   	    if(position/2==0){
	            load(fin,0);
			} 
	        else{
		         load(fin,1);
			}
            ch=buffer[rear];
		}
     	front=rear;
     
        token_pointer=(struct token*)malloc(sizeof(token));
	    token_pointer->lineno=line;
	    token_pointer->wordkey=0x101;

		token_pointer->value=(char *)malloc(dex*sizeof(char));
	    strcpy(token_pointer->value,id);
		
		token_pointer->next_token=token_list_head;
		token_list_head=token_pointer;
	}
	//字符串解析
	else if(ch=='"'){
		while((ch=buffer[++rear])!='"'){
			if(ch=='\\'){
				ch=buffer[++rear];
				switch(ch){
					case ''':achar=''';
						break;
				    case 'r':achar='\r'
						break;
					case 'f':achar='\f'
				        break;
					case 't':achar='\t'
					    break;
					case 'b':achar='\b';
						break;
				    case 'n':achar='\n';
						break;
				    case 't':achar='\t';
						break;
				    case '\\':achar='\\';
						break;
				    case '"':achar='"';
						break;
				    case '\'':achar='\'';
						break;
				    default:
						//error
				}
			}
			id[dex++]=ch;
			if(dex==100){
				//
			}
		}
		rear++;
		if(ch==EOF){
	        position++;
	        fseek(fin,1023,1);
	   	    if(position/2==0){
	            load(fin,0);
			} 
	        else{
		         load(fin,1);
			}
            ch=buffer[rear];
		}
		front=rear;
		//将临时变量存储数组索引置零
    	token_pointer=(struct token*)malloc(sizeof(token));
	    token_pointer->lineno=line;
	    token_pointer->wordkey=0x106;

		token_pointer->value=(char *)malloc(dex*sizeof(char));
	    strcpy(token_pointer->value,id);
	
		token_pointer->next_token=token_list_head;
		token_list_head=token_pointer;
		
		dex=0;
		//将临时变量存储数组清零
		memset(id,0,100);


	}
	/********************************解析单个字符***************************/ 
	else if(ch=='\''){
		ch=buffer[++rear];
		if(ch==EOF){
	        position++;
	        fseek(fin,1023,1);
	   	    if(position/2==0){
	            load(fin,0);
			} 
	        else{
		         load(fin,1);
			}
            ch=buffer[rear];
		}
		if(ch=='\\'){
			ch=buffer[++rear];
			if(ch==EOF){
	            position++;
	            fseek(fin,1023,1);
	   	        if(position/2==0){
	                load(fin,0);
				}  
	            else{
		            load(fin,1);
				}
                ch=buffer[rear];
			}
			switch(ch){
               	case ''':achar=''';
					break;
				case 'r':achar='\r'
					break;
		    	case 'f':achar='\f'
			        break;
				case 't':achar='\t'
				    break;
				case 'b':achar='\b';
					break;
			    case 'n':achar='\n';
					break;
				case 't':achar='\t';
					break;
			    case '\\':achar='\\';
					break;
			    case '"':achar='"';
					break;
			    case '\'':achar='\'';
					break;
				default:
					//error
			}
		}
		else
			achar=ch;
		if((ch=buffer[++rear])!='\'')
			;//error

		
	}
	/**************************解析分界符及部分运算符*****************************/ 
	else{
		switch(ch){
			case '(':
				return L_BRACKET;
			case ')':
				return R_BRACKET;
			case '[':
				return L_MEDBRACKET;
			case ']':
				return R_MEDBRACKET;
			case '{':
				return L_BIGBRACKET;
			case '}':
				return R_BIGBRACKET;
			case ',':
				return COMMA;
			case ';':
				return SEMICOLON;
			case '%':
				return MOD;
			case '*':
				return MUL;
			case '/':
				return DIV;
			case '+':
				return ADD;
			case '-':
				return SUB;
			case ':':
				return COLON; 
			default:
				return EOI;
		

}	
int main(int argc,char * argv[]){
    
	char filename[100];
	int  i=0;

    //设立缓冲区标志位
	buffer[1023]=EOF;
    buffer[2047]=EOF;

	printf("Please enter file name:\n");
    scanf("%s",filename);

    //打开文件,并将1023个字符读入前一半缓冲区
	fin=fopen(filename,"r");
    if(fin==NULL){
		printf("FILE_CANNOT_OPEN\n");
	}
	else{
		load(fin,0);

	}
	for(i=0;i<40;i++){
		get_token();
	}
   

}