wordanalyse.c

自己做的编译原理课程的词法分析器

#include "global.h"
#include "keyword.h"

int main(){
    char buffer[20];/*将每次读取的字符串存到一个缓冲区*/
    int length=0;/*记录读取字符串的长度*/
    struct record temp;/*定义词法分析器输出的中间结果的格式*/
	FILE *fpread;/*读源程序文件的指针*/
	FILE *fpwrite;/*写源程序文件的指针*/
        if((fpread=fopen("in.pas","rb"))==NULL){/*打开已知源文件，用mini-Pascal编写的原文件*/
			printf("\nERROR:源程序不存在.\n");
			exit(0);
		}
		if((fpwrite=fopen("out.pbj","wb"))==NULL){/*创建中间文件,保存词法分析器分析出的二元式文件*/
			printf("\nERROR.\n");
			exit(0);
		}
		flashBuffer(buffer,&temp);/*清空缓存*/
		if(!feof(fpread)){
			length=scan(buffer,fpread);/*读取字符串*/
		}
		while(!feof(fpread)){
			if(length==0){
				printf("\nERROR: Line  %d     非法字符\n",line);//输出词法分析器的错误，并指出错误发生的行号
			}
			else{
				temp.kind=look(buffer);//查关键字表，返回关键字的编码
				if(temp.kind==35){//是换行符则行号加一
					strcpy(temp.strName,"newline");
				}else{
					strcpy(temp.strName,buffer);
				}
				if(temp.kind==35)line++;
				printf("{ %s",temp.strName);
				printf("  %d }",temp.kind);
				printf("\n");
				outWord(temp,fpwrite);					
				flashBuffer(buffer,&temp);
			}
			length=scan(buffer,fpread);
	    }
		if(length){
			temp.kind=look(buffer);
			if(temp.kind==35){
				strcpy(temp.strName,"newline");
			}else{
				strcpy(temp.strName,buffer);
			}
			if(temp.kind==35)line++;
			printf("{ %s",temp.strName);
			printf("  %d }",temp.kind);
			printf("\n");
			outWord(temp,fpwrite);
			flashBuffer(buffer,&temp);
		}
		else{
			printf("\nERROR: Line  %d     非法字符\n",line);//输出词法分析器的错误，并指出错误发生的行号	
		}
		fclose(fpread);
		fclose(fpwrite);
	return 1;
}

void flashBuffer(char buffer[],struct record *temp)//清空函数
{
     int i=0;
     for(i=0;i<20;i++){
		 buffer[i]='\0';
		 temp->strName[i]='\0';
	 }
}

int scan(char buffer[],FILE *fpread){//读字符模块
    char word;
    int ptr=0;
    word=getc(fpread);
    while((word==' ')||(word=='\t')||(word=='\r')){
        word=getc(fpread); //保留字
    }
    if((word>='0')&&(word<='9')){  //常数
        while((word>='0')&&(word<='9')){
            buffer[ptr]=word;
            if(ptr<20){
                ptr++;
            }
            if(feof(fpread))
				break;
			else
				word=getc(fpread);
        }
    }
    else if(((word>='a')&&(word<='z'))||((word>='A')&&(word<='Z'))){ //标识符
        while(((word>='A')&&(word<='Z'))||((word>='a')&&(word<='z'))||((word>='0')&&(word<='9'))){
            buffer[ptr]=word;
            if(ptr<20){
                ptr++;
            }
			if(feof(fpread))
				break;
			else
				word=getc(fpread);
        }
    }
    else if(word=='+'){
        buffer[ptr]=word;
        ptr++;
    }
    else if(word=='-'){
        buffer[ptr]=word;
        ptr++;
    }
    else if(word=='*'){
        buffer[ptr]=word;
        ptr++;
    }
    else if(word=='/'){
        buffer[ptr]=word;
        ptr++;
    }
    else if(word==':'){
        buffer[ptr]=word;
        ptr++;
        if(!feof(fpread))
		{
			word=getc(fpread);
			if(word=='='){
				buffer[ptr]=word;
				ptr++;
			}
			else {
				ptr=0;
				fseek(fpread,-1L,SEEK_CUR);/*回退一个字符*/
			}
		}
    }
    else if(word=='='){
        buffer[ptr]=word;
        ptr++;
    }
    else if(word=='<'){
        buffer[ptr]=word;
        ptr++;
        if(!feof(fpread))
		{
			word=getc(fpread);
			if(word=='>'){
				buffer[ptr]=word;
				ptr++;
			}
			else {
				ptr=0;
				fseek(fpread,-1L,SEEK_CUR);/*回退一个字符*/
			}
		}
    }
	else if(word=='>'){
        buffer[ptr]=word;
        ptr++;
        if(!feof(fpread))
		{
			word=getc(fpread);
			if(word=='='){
				buffer[ptr]=word;
				ptr++;
			}
			else {
				ptr=0;
				fseek(fpread,-1L,SEEK_CUR);/*回退一个字符*/
			}
		}
    }
	else if(word=='<'){
        buffer[ptr]=word;
        ptr++;
        if(!feof(fpread))
		{
			word=getc(fpread);
			if(word=='='){
				buffer[ptr]=word;
				ptr++;
			}
			else {
				ptr=0;
				fseek(fpread,-1L,SEEK_CUR);/*回退一个字符*/
			}
		}
    }
    else if(word=='('){
        buffer[ptr]=word;
        ptr++;
    }
    else if(word==')'){
        buffer[ptr]=word;
        ptr++;
    }
    else if(word==','){
        buffer[ptr]=word;
        ptr++;
    }
	else if(word==';'){
        buffer[ptr]=word;
        ptr++;
    }
    else if(word=='.'){
        buffer[ptr]=word;
        ptr++;
    }
    else if(word=='\n'){
        buffer[ptr]=word;
        ptr++;
    }
	else
	{
		ptr=0;
	}
    return ptr;
}

int look(char word[]){//查保留字表模块
    int i;
    int location=0;
    for(i=0;i<KeyWordLength;i++){
        if(strcmp(word,keyWord[i])==0){
            location=i;
            return location;
        }
    }
    if((word[0]>='0')&&(word[0]<='9')){
        location=18;
    }
    else if(((word[0]>='a')&&(word[0]<='z'))||((word[0]>='A')&&(word[0]<='Z'))){
        location=17;
    }
    return location;
}

void outWord(struct record out,FILE *fpwrite){//输出单词模块
    fwrite(&out,sizeof(struct record),1,fpwrite);
}