lexical analysis.cpp

为了实现的编译程序实用

#include "stdio.h"
#include "string.h"
#include "stdlib.h"

#define VALWORDNUM 35 //单词数
#define WORDLEN 20    //单词最大长度
#define BUFLEN 1024   //缓冲区长度

typedef struct {
	char val[5];         //种别
	char word[15];   //单词
}VAL_WORD;

//单词种别表
VAL_WORD val_word[VALWORDNUM] =
{   
	{"1",  "PROGRAM"},{"2", "CONST"},{"3",        "VAR"},{"4","INTEGER"},{"5", "LONG"},	
	{"6","PROCEDURE"},{"7",    "IF"},{"8",       "THEN"},{"9",  "WHILE"},{"10",  "DO"},	
	{"11",    "READ"},{"12","WRITE"},{"13",     "BEGIN"},{"14",   "END"},{"15", "ODD"},	
	{"16",       "+"},{"17",    "-"},{"18",         "*"},{"19",     "/"},{"20",   "="},
	{"21",      "<>"},{"22",    "<"},{"23",        "<="},{"24",     ">"},{"25",  ">="},
	{"26",       "."},{"27",    ","},{"28",         ";"},{"29",     ":"},{"30",  ":="},
	{"31",       "("},{"32",    ")"},{"33","无符号整数"},{"34","标识符"},{"35",   "#"}	 	 
};

void proprocess(char filename[],char buf[])//预处理
{
    FILE *fp;
	int i = 0;
	char curchar;
	fp = fopen(filename,"rb");
	while(!feof(fp)&&fread(&curchar,sizeof(char),1,fp)==1)
		buf[i++]=curchar;
    buf[i]='#';
	fclose(fp);
}
void concat(char word[],char c)//拼接单词
{
	for(int i=0;word[i]!='\0';i++);
	word[i++]=c;
	word[i]='\0';
}

char* getval(char word[])//获取单词种别
{
	for(int i=0;i<VALWORDNUM;i++)
		if(strcmp(val_word[i].word,word)==0)return val_word[i].val;
	return "0";
}
void error(int line,int row)
{
	printf(">>>>>  分析有错误!\n\n");
	printf(">>>>>  ERROR IN %3d LINE %3d ROW\n",line,row);
	exit(0);
}
VAL_WORD lexical(char buf[])
{
	VAL_WORD v={"\0","\0"};
	static int i=0,row=0,line=1;
	char word[WORDLEN] = {'\0'};
	while(buf[i]==' '||buf[i]=='\n'||buf[i]=='\f'||buf[i]==13||buf[i]==10)//删除空格类字符，包括回车、制表符空格
	{
		i++;
		row++;
		if(buf[i]==10){line++;row=0;}
	}
    //标识符
	if((buf[i]>='A'&&buf[i]<'Z')){
		while((buf[i]>='A'&&buf[i]<'Z')||(buf[i]>='0'&&buf[i]<'9'))
		{
			concat(word,buf[i++]);
			row++;
		}
		strcpy(v.val,getval(word));
		if(strcmp(v.val,"0")==0)strcpy(v.val,"34");
		strcpy(v.word,word);
		return v;
	}
    //无符号整数
	if(buf[i]>='0'&&buf[i]<'9'){
		while(buf[i]>='0'&&buf[i]<'9'){
			concat(word,buf[i++]);
			row++;
		}
		strcpy(v.val,getval(word));
		if(strcmp(v.val,"0")==0)strcpy(v.val,"33");
	    strcpy(v.word,word);
		return v;
	}
	//其他
	switch(buf[i]){
		case '+':strcpy(v.word,"+");break;
		case '-':strcpy(v.word,"-");break;
		case '*':strcpy(v.word,"*");break;
		case '/':strcpy(v.word,"/");break;
		case '=':strcpy(v.word,"=");break;
		case '<':if(buf[i+1]=='>'){strcpy(v.word,"<>");i++;row++;}
			     else if(buf[i+1]=='='){strcpy(v.word,"<=");i++;row++;}
				 else strcpy(v.word,"<");
				 break;
		case '>':if(buf[i+1]=='='){strcpy(v.word,">=");i++;row++;}
				 strcpy(v.word,">");
				 break;
		case '.':strcpy(v.word,".");break;
		case ',':strcpy(v.word,",");break;
		case ';':strcpy(v.word,";");break;
		case ':':if(buf[i+1]=='='){strcpy(v.word,":=");i++;row++;}
			     strcpy(v.word,":");
				 break;
		case '(':strcpy(v.word,"(");break;
	    case ')':strcpy(v.word,")");break;
		case '#':strcpy(v.word,"#");break;
		default:strcpy(v.val,"0");
			    error(line,row);
				break;
	}
	i++;
	row++;
	strcpy(v.val,getval(v.word));
	return v;
}

void main()
{
    FILE *fp;
	VAL_WORD v={0," "};
	char sourcefile[20] =  "source.pas" ;
	char lexicalfile[20] = "lexical.dc" ;	
	char buf[BUFLEN]={'\0'};
	printf(">>>>>  分析正在进行中....\n\n");
	proprocess(sourcefile,buf);
	printf("源程序:\n%s\n\n",buf);
	fp = fopen(lexicalfile,"wb");
	printf("二元式为:\n%5s%15s\n","种别","单词");
	while(strcmp(v.word,"#")!=0){
		v=lexical(buf);
		printf("%5s%15s\n",v.val,v.word);
		fwrite(&v.val,sizeof(int),1,fp);
		fwrite(&v.word,15*sizeof(char),1,fp);
	}
	fclose(fp);
	printf("\n\n>>>>>  分析成功结束!\n\n");
}