compiler.cpp

一个很一般的编译程序 有词法分析

#include "head.h"

WORD word[BUFLINE];//单词量不能大于256
stateStack _stack;//状态栈
int G_table[20][8];//文法矩阵
fourexp *fourexpHead;//生成四元式链的头指针

Vn vn_stack[STACKSIZE];//生成四元式时用的非终结符栈
int vn_stack_top = 0;//非终结符的栈顶

void add_fourexp(){//四元式前面的计算地址
	int num = 0 ;
	fourexp * i = fourexpHead ;
	while( i ){
		i->address = num ;
		num++ ;
		i = i->next; 
	}
	i = fourexpHead;
	while( i ){
		if( i->isadd == true ){
			i->temp = i->chain->address+1;
		}
		i = i->next; 
	}
}//地址计算


void pop_vn(int i){//出栈
	vn_stack_top -= i;
}
void push_vn(Vn * vn_stack,Vn *s){//入栈
	vn_stack[vn_stack_top] = *s;
	vn_stack_top++;
}

void push(int n){//入栈
	if(_stack.top==STACKSIZE) {cout<<"语法分析栈满！"<<endl;exit(0);}
	_stack.stack[_stack.top]=n;
	_stack.top++;
}
void stackinit(){//状态栈初始化
	_stack.top = 0;
}
int pop(){//出栈
	if(_stack.top==0){cout<<"语法分析栈空！"<<endl;exit(0);}
	_stack.top--;
	return _stack.stack[_stack.top];
}
int gettop(){//取栈顶元素
	if(_stack.top==0){cout<<"语法分析栈空！"<<endl;exit(0);}
	return _stack.stack[_stack.top-1];
}
	
int isEmpty(stateStack stack){//判断栈是否为空
	if(stack.top==0) return 1;
	else return 0;
}

int  string_int(const char *str)//类型转换
{
 int num, i;
 num = *str - '0';
 i   = 1;
 while (str[i] && isdigit(str[i])) 
  num = num * 10 + str[i++] - '0';
 
 return num;
}
/*
char* int_string(int i){
int ran = i;
int isNeg = i<0?1:0;    //检查是否为负数
if(isNeg)  ran *= -1;      //输入负数时取相反数
int bits = 0;      //记录共有几位数字
int numBits[10];     //因为int的范围在-2147483648和2147483647之间,
          //不超过十位,所以数组长度取10
do         //把数字的各个位拆开
{
  numBits[bits] = ran%10;
  ran = (ran-numBits[bits])/10;
  bits++;
}
while(ran!=0);
char* str = new char[bits+isNeg+1]; //str是返回字符串的指针
str[0] = '-';      //负数的时候第一位保存负号
str[bits+isNeg] = '\0';    //字符串的结尾
for(int ii=isNeg;ii<bits+isNeg;ii++) //转换成字符串保存到str
{
  str[ii] = (char)(numBits[bits-(ii-isNeg)-1] + '0');
}
return str;
}
*/




int getLine(FILE* fp){ //获取文件行数
	FILE* p = fp;
	int line_Counter = 0;
	if(!p) { cout<<"空文件！"<<endl; exit(0);}

while(!feof(p))
{
	//cout<<(char)fgetc(p)<<"";
	if((char)fgetc(p)=='\n') line_Counter++;
}

	return line_Counter+1;
}

void error()
{
	cout<<"词法错误,标志符不能以数字开头"<<endl;
	exit(0);
}
void error1()
{
	cout<<"语法错误,输入正确句子"<<endl;
	exit(0);
}






int  lex(char * buf)//词法分析程序
{
	int i=0,j=0;
	int n=0;
	char tmp_name[10];
	while(buf[i]!='\0')
	{
		if(buf[i]==' '||buf[i]=='\n')//滤空
			i++;
		else if(isalpha(buf[i])||buf[i]=='_')//标志符判断
		{
			tmp_name[j]=buf[i];
			i++;
			while(isalnum(buf[i]))
			{
				j++;
				tmp_name[j]=buf[i];
				i++;
			}

			memcpy(word[n].name,tmp_name,j+1);
			word[n].name[j+1]='\0';
			if(strcmp(word[n].name,"if")==0) {	word[n].id=IF; strcpy(word[n].name,"if");}
			else if(strcmp(word[n].name,"then")==0){	word[n].id=THEN; 	strcpy(word[n].name,"then");}
			else if(strcmp(word[n].name,"else")==0){	word[n].id=ELSE;	strcpy(word[n].name,"else");}
			else if(strcmp(word[n].name,"while")==0){	word[n].id=WHILE; 	strcpy(word[n].name,"while");}
			else if(strcmp(word[n].name,"do")==0){	word[n].id=DO; 	strcpy(word[n].name,"do");}
			else if(strcmp(word[n].name,"begin")==0){	word[n].id=BEGIN; 	strcpy(word[n].name,"begin");}
			else if(strcmp(word[n].name,"end")==0){	word[n].id=END; 	strcpy(word[n].name,"end");}
			else if(strcmp(word[n].name,"true")==0) { word[n].id = TRUE; word[n].value = 1;  strcpy(word[n].name,"true"); }
			else if(strcmp(word[n].name,"false")==0){ word[n].id = FALSE;word[n].value = 0;  strcpy(word[n].name,"false");}
			else{ word[n].id=I; word[n].value =0;}//标识符
			n++;
			j=0;
		}// endif
		else if(isdigit(buf[i]))//数字判断
		{
			while(isdigit(buf[i])){
				tmp_name[j]=buf[i];
				i++;
				j++;
			}
			if(isalpha(buf[i])) error();
			memcpy(word[n].name,tmp_name,j+1);
			word[n].name[j]='\0';
			word[n].id = CONST;
			word[n].value = string_int(word[n].name);
			n++;
			j=0;
		}
		else//运算符，界符判断
		{
			switch(buf[i])
			{
			case ':' ://赋值
				if(buf[i+1] == '='){
					word[n].id = EVALUATE;
				//	word[n].type = 1;
					strcpy(word[n].name,":=");
					n++;
				}
				else error();
			break;

			case ';':
				word[n].id =SEMICOLON;
			//	word[n].type = 4;
				strcpy(word[n].name,";");
				n++;
				break;

			case '&':
				word[n].id = AND;
			//	word[n].type = 1;
				strcpy(word[n].name,"&");
				n++;
				break;
			
			case '|':
				word[n].id = OR;
			//	word[n].type = 1;
				strcpy(word[n].name,"|");
				n++;
				break;

			case '>':
				word[n].id = GREAT;
			//	word[n].type = 1;
				strcpy(word[n].name,">");
				n++;
				break;

			case '<':
				word[n].id =LOW ;
			//	word[n].type = 1;
				strcpy(word[n].name,"<");
				n++;
				break;
			case '=':
				if(buf[i-1] != ':'){
				word[n].id = EQUAL;
			//	word[n].type = 1;
				strcpy(word[n].name,"=");
				n++;
				}
				break;

			case '+':
				word[n].id = PLUS;
			//	word[n].type = 1;
				strcpy(word[n].name,"+");
				n++;
				break;

			case '*':
				word[n].id = MULTIPLY;
			//	word[n].type = 1;
				strcpy(word[n].name,"*");
				n++;
				break;

			case '(':
				word[n].id = LEFT;
			//	word[n].type = 4;
				strcpy(word[n].name,"(");
				n++;
				break;

			case ')':
				word[n].id = RIGHT;
			//	word[n].type = 4;
				strcpy(word[n].name,")");
				n++;
				break;
		 	default :
			 	if(buf[i] == '#') goto lv;
				cout<<"有非法字符";
				exit(0);
			}
			i++;
		}
	}
lv:
	strcpy(word[n].name,"#");
//	word[n].type = 4;
		word[n].id=ACC;
	return n;//单词符号个数
}//词法分析







void G_init()//初始化文法矩阵
{
	for(int i=0;i<20;i++)               	
	for(int j=0;j<8;j++)
		G_table[i][j]=-1;
	G_table[0][0]=27;G_table[0][1]=23; //初始化文法表
	G_table[1][0]=23;G_table[1][1]=0;G_table[1][2]=25;G_table[1][3]=1;G_table[1][4]=23;G_table[1][5]=2;G_table[1][6]=23;
	G_table[2][0]=23;G_table[2][1]=0;G_table[2][2]=25;G_table[2][3]=1;G_table[2][4]=23;
	G_table[3][0]=23;G_table[3][1]=3;G_table[3][2]=25;G_table[3][3]=4;G_table[3][4]=23;
	G_table[4][0]=23;G_table[4][1]=5;G_table[4][2]=24;G_table[4][3]=6;
	G_table[5][0]=23;G_table[5][1]=7;G_table[5][2]=8;G_table[5][3]=26;
	G_table[6][0]=24;G_table[6][1]=23;G_table[6][2]=9;G_table[6][3]=24;
	G_table[7][0]=24;G_table[7][1]=23;
	G_table[8][0]=25;G_table[8][1]=25;G_table[8][2]=10;G_table[8][3]=25;
	G_table[9][0]=25;G_table[9][1]=25;G_table[9][2]=11;G_table[9][3]=25;
	G_table[10][0]=25;G_table[10][1]=7;G_table[10][2]=12;G_table[10][3]=7;
	G_table[11][0]=25;G_table[11][1]=7;G_table[11][2]=13;G_table[11][3]=7;
	G_table[12][0]=25;G_table[12][1]=7;G_table[12][2]=14;G_table[12][3]=7;
	G_table[13][0]=25;G_table[13][1]=15;