编译原理试验2.cpp

你是不是很想要语法分析的源代码呢？！哈哈

#include<iostream>
#include<fstream>
#include<string>
using namespace std;

struct store
{
	int type;//标识符类型，0表示整型，1表示布尔型，2表示字符型
	int attribution;//36，表示标识符；37表示字符常量，38表示整数
	int define;//“0”值时表示没有被定义，“1”值时表示有定义
	char content[20];//记录标识符，字符常量和整数及其个数
};
store record[30];
static int record1=1;//记录record数组第一维的数值，即标识符等的个数

struct bexitnode
{
	int truesum;//真出口个数
	int trueexit[8];//存未知真出口的入口码
	int falsesum;//假出口个数
	int falseexit[8];//存未知假出口的入口码
	int entry;//入口四元式码
	int allsum;//四元式总个数
};//布尔表达式中使用
bexitnode bexit[15];
static int pbexit=0;

struct bnode{
		char first[20];
		char fu[4];
		char second[20];
	};//布尔表达式中使用

struct node//输出节点
{
	string output1;
	string output2;
	string output3;
	string output4;
	int Tnum2,Tnum3,Tnum4;
};
node output[60];
static int outputrec=0;
static int Trec=1;//记录T中间变量的个数
struct sentence_node
{
	char act;//s代表赋值，i代表if语句，t代表then语句，l代表else语句，w代表while语句，
	//r代表repeat语句，u表示until语句，b代表begin语句
	int truesum;//真出口个数
	int trueexit[5];//存未知真出口的入口码
	int falsesum;//假出口个数
	int falseexit[5];//存未知假出口的入口码
	int entry;//入口四元式码
	int row;
	int then;
};
sentence_node sentence[20];
int psentence=0;
int sentencerec=0;

void cifaline(char s[80],char* table[35],int & row);//处理一行程序
bool cifafenxi(const char  *filename);//词法分析函数

int numberexpression(char * a);//算术表达式是否合法判断
string single;//记录单个变量的表达式情况
int boolexpression(char * str);//布尔表达式是否合法判断
void fguiyue(int & b,int &c,int & pbexit,bexitnode bexit[],bnode bexp[]);//布尔表达式中归约f函数
void gguiyue(int& a,int &c,int & pbexit,bexitnode bexit[],string bsfu[]);//布尔表达式中归约g函数
int chartoint(char a);//从字符转换成为数字
int chattoint2(char a);//从字符转换成为数字
void outputerror(int type,char* str,char* word);//错误提示
int error;
char line[80];//存储文件的一行
static int row=1;//读入文件的第几行
static int position=0;//行的位置
int searchchar(ifstream & tow);//跳过空格和空行寻找字符
int programbegin(ifstream & tow);//编译程序开头
int var(ifstream & tow);//编译变量定义
int begin_end(ifstream & tow);//复合语句函数
int setvalue(ifstream & tow,char temp[],int sen[]);//赋值函数

void main()
{
	cout<<"                                编译原理实验二\n";
    cout<<"\n       姓名：林桂川    班级：计算机04级1班    学号：200433099345\n\n";
	const char* filename;
	string file;
	cout<<"input filename:";
	cin>>file;
	file+=".txt";
	filename=file.data();
	if (cifafenxi(filename))//词法分析
	{
	ifstream tow(filename,ios::in);
	if(programbegin(tow)==0)return;
	if(var(tow)==0)return;
	if(begin_end(tow)==0) return;
	tow.close();
	for(int j=0;j<outputrec;j++)
	{
		cout<<j<<"("<<output[j].output1<<",";
		if(output[j].output2.compare("T")==0)cout<<"T"<<output[j].Tnum2<<",";
		else cout<<output[j].output2<<",";
		if(output[j].output3.compare("T")==0)cout<<"T"<<output[j].Tnum3<<",";
		else cout<<output[j].output3<<",";
		if(output[j].output4.compare("T")==0)cout<<"T"<<output[j].Tnum4<<")";
		else if(output[j].output4.compare("j")==0)cout<<output[j].Tnum4<<")";
			else cout<<output[j].output4<<")";
		cout<<endl;
	}
	}
}

void outputerror(int type,char* str,char* word)
{
	error++;
	switch(type)
	{
			case 1:
		cout<<"ERROR "<<error<<"(line "<<row<<"): 缺少关键字说明"<<word<<endl;
		break;
	case 2:
		if (str=="lack_sym")
			cout<<"ERROR "<<error<<"(line"<<row<<"): 缺少标点符号 "<<word<<endl;
		else
			if (str=="false")
				cout<<"ERROR "<<error<<"(line "<<row<<"): 非法标志符 "<<endl;
			else
				if(str=="keyword")
					cout<<"ERROR "<<error<<"(line "<<row<<"): 标志符声明不能为关键字 "<<endl;
				else
					if (str=="lack")
						cout<<"ERROR "<<error<<"(line "<<row<<"): 缺少标志符"<<endl;
						else
							if (str=="error")
							   	cout<<"ERROR "<<error<<"(line "<<row<<"): 变量声明有误"<<endl;
							else
                                                             if(str=="no_sym")
								cout<<"ERROR "<<error<<"(line "<<row<<"): "
								<<"非法符号"<<endl;
                                                                 else
								cout<<"ERROR "<<error<<"(line "<<row<<"): "
								<<"未声明变量"<<endl;
		break;
	case 3:
		cout<<"ERROR "<<error<<"(line "<<row<<"): 字符常数缺右边的单引号'"<<endl;
		break;
	case 4:
		cout<<"ERROR "<<error<<"(line "<<row<<"): 注释部分缺右边的界符*/"<<endl;
		break;
	case 5:
		cout<<"ERROR "<<error<<"(line "<<row<<"): 此simple语言不提供字符型和布尔型的赋值,请修改"<<endl;
	case 6:
		cout<<"ERROR "<<error<<"(line "<<row<<"): "<<str<<"缺少"<<word<<"的匹配 "<<endl;
		break;
	case 7:
		cout<<"ERROR "<<error<<"(line "<<row<<"): "<<word<<"说明后面缺少标志符 "<<endl;
		break;
	case 8:
		cout<<"ERROR "<<error<<"(line "<<row<<"): "<<str<<" "<<word<<" 在文中未预料出现 "<<endl;
		break;
	case 9:
		cout<<"ERROR "<<error<<"(line "<<row<<"):  未预见文件结尾 "<<endl;
		break;
	case 10:
		cout<<"ERROR "<<error<<"(line "<<row<<"): 赋值语句错误"<<endl;
		break;
	case 11:
		cout<<"ERROR "<<error<<"(line "<<row<<"): "<<" 句子语法构造出错 "<<word<<endl;
		break;
	case 12:
		cout<<"ERROR "<<error<<"(line "<<row<<"): "<<"类型不匹配 "<<endl;
		break;
	case 13:
		cout<<"ERROR "<<error<<"(line "<<row<<"): "<<"程序已结束,"<<word<<"以下为非法语句"<<endl;
		break;
	case 14:
		cout<<"ERROR "<<error<<"(line "<<row<<"): "<<"表达式 "<<word<<" 出错"<<endl;
		break;
	case 15:
		cout<<"ERROR "<<error<<"(line "<<row<<"): "<<"布尔表达式 "<<word<<" 中出现非布尔型变量"<<endl;
		break;
	case 16:
		cout<<"ERROR "<<error<<"(line "<<row<<"): "<<"缺少逻辑表达式"<<endl;
		break;
	}
}
int searchchar(ifstream & tow)//跳跃空格函数
{
	for(;line[position]==' '||line[position]=='\0';)
	{
		for(;line[position]==' ';position++);
		if(line[position]=='\0')
		{
			if(tow.eof())
			{
				if(sentencerec!=0)
				{
					outputerror(9,"","");
					return 0;
				}
				else return 1;
			}
			tow.getline (line,80);
			position=0;
			row++;
		}
	}
	return 2;
}
int programbegin(ifstream & tow)
{
	tow.getline(line,80);
	searchchar(tow);
	char temp[20];
	int i;
	for(i=0;line[position]!=' '&&line[position]!='\0';i++,position++)temp[i]=line[position];
	temp[i]='\0';
	if(strcmp(temp,"program")!=0)
	{
		outputerror(1,"","program");
		return 0;
	}
	output[outputrec].output1="program";//
	searchchar(tow);
	for(i=0;line[position]!=' '&&line[position]!=';'&&line[position]!='\0';i++,position++)
		temp[i]=line[position];
	temp[i]='\0';
	for(i=1;strcmp(temp,record[i].content)!=0&&i<record1;i++);
	if(i==record1)
	{
		outputerror(2,"lack","");
		return 0;
	}
	output[outputrec].output2.assign(temp);
	output[outputrec].output3="-";
	output[outputrec].output4="-";
	outputrec++;
	searchchar(tow);
	if(line[position]!=';')
	{
		outputerror(2,"lack_sym",";");
		return 0;
	}
	position++;
	return 1;
}

int var (ifstream & tow)
{
	searchchar(tow);
	char temp[20];
	int i,j;
	for(i=0;line[position]!=' '&&line[position]!='\0'&&line[position]!=','&&line[position]!=':';i++,position++)
		temp[i]=line[position];
	temp[i]='\0';
	if(strcmp(temp,"var")==0)
	{
		string bsfu[8];
		int bsfurec=0;
		for(;;)
		{
			searchchar(tow);
			if(!(line[position]>=65&&line[position]<=90||line[position]>=97&&line[position]<=122))
			{
				outputerror(2,"error","");
				return 0;
			}
			for(i=0;(line[position]>=65&&line[position]<=90||line[position]>=97&&line[position]<=122)||
				(line[position]>=48&&line[position]<=57);i++,position++)
				temp[i]=line[position];
			temp[i]='\0';
			if(strcmp(temp,"begin")==0)	return 1;
			else 
			{
				for(j=1;strcmp(temp,record[j].content)!=0&&j<record1;j++);
				if(j==record1)//标识符是关键字
				{
					outputerror(2,"keyword","");
					return 0;
				}
				else if(record[j].define==1)
				{
					outputerror(11,"","");
					return 0;
				}
					
			}
			bsfu[bsfurec].assign(temp);
			bsfurec++;
			searchchar(tow);
			if(line[position]!=','&&line[position]!=':'&&line[position+1]!='=')
			{
				outputerror(2,"error","");
				return 0;
			}
			if(line[position]==',')
			{
				position++;
				continue;
			}
			else
			{
				position++;
				searchchar(tow);
				if(!(line[position]>=65&&line[position]<=90||line[position]>=97&&line[position]<=122))
				{
				    outputerror(2,"error","");
				    return 0;
				}
				for(i=0;(line[position]>=65&&line[position]<=90||line[position]>=97&&line[position]<=122)||
				(line[position]>=48&&line[position]<=57);i++,position++)
				temp[i]=line[position];
				temp[i]='\0';
				if(strcmp(temp,"integer")==0)
				{
					for(i=0;i<bsfurec;i++)
					{
						for(j=1;bsfu[i].compare(record[j].content)!=0;j++);
						record[j].define=1;
						record[j].type=0;
					}
					bsfurec=0;
				}
				else if(strcmp(temp,"bool")==0)
				{
					for(i=0;i<bsfurec;i++)
					{
						for(j=1;bsfu[i].compare(record[j].content)!=0&&j<record1;j++);
						if(j==record1)//标识符是关键字
						{
							outputerror(2,"keyword","");
							return 0;
						}
						record[j].define=1;
						record[j].type=1;
					}
					bsfurec=0;
				}
				else if(strcmp(temp,"char")==0)
				{
					for(i=0;i<bsfurec;i++)
					{
						for(j=1;bsfu[i].compare(record[j].content)!=0&&j<record1;j++);
						if(j==record1)//标识符是关键字
						{
							outputerror(2,"keyword","");
							return 0;
						}
						record[j].define=1;
						record[j].type=2;
					}
					bsfurec=0;
				}
				else
				{
					outputerror(2,"error","");
					return 0;
				}
				searchchar(tow);
				if(line[position]!=';')
				{
					outputerror(2,"lack_sym",";");
					return 0;
				}
				position++;
			}
		}//for
	}//strcmp(temp,"var")==0
	else if(strcmp(temp,"begin")==0)	return 1;
	else
	{
		outputerror(1,"","var");
		return 0;
	}
}
int begin_end(ifstream & tow)
{
	int sen[20];
	sentence[psentence].act='b';
	sentence[psentence].entry=outputrec;
    sen[sentencerec]=psentence;
	sentencerec++;
	psentence++;
	char temp[20];
	char str[30];
	int i;
	for(;;)
	{
		searchchar(tow);
		if(!(line[position]>=65&&line[position]<=90||line[position]>=97&&line[position]<=122))
		{
			outputerror(11,"","");
			return 0;
		}
		for(i=0;(line[position]>=65&&line[position]<=90||line[position]>=97&&line[position]<=122)||
			(line[position]>=48&&line[position]<=57);i++,position++)
			temp[i]=line[position];
		temp[i]='\0';
		if(strcmp(temp,"if")==0)
		{
			searchchar(tow);
			for(i=0;!(line[position+1]=='t'&&line[position+2]=='h'&&line[position+3]=='e'&&line[position+4]=='n')
				&&line[position]!='\0';i++,position++)str[i]=line[position];
			str[i]='\0';
			if(boolexpression(str)==0)return 0;
			sentence[psentence].act='i';
			sentence[psentence].entry=bexit[0].entry;
			sentence[psentence].falsesum=bexit[0].falsesum;
			sentence[psentence].truesum=bexit[0].truesum;
			for(i=0;i<bexit[0].falsesum;i++)sentence[psentence].falseexit[i]=bexit[0].falseexit[i];
			for(i=0;i<bexit[0].truesum;i++)sentence[psentence].trueexit[i]=bexit[0].trueexit[i];
			sentence[psentence].row=row;
			sen[sentencerec]=psentence;
			sentencerec++;
			psentence++;
		}
		else 
			if(strcmp(temp,"then")==0)
		{
			sentence[psentence].act='t';
			sentence[psentence].entry=outputrec;
			sentence[psentence].row=row;
			sen[sentencerec]=psentence;
			sentencerec++;
			psentence++;
		}
		else 
			if(strcmp(temp,"else")==0)
		{
			sentence[psentence].act='l';
			sentence[psentence].entry=outputrec;
			sentence[psentence].row=row;
			sen[sentencerec]=psentence;
			sentencerec++;
			psentence++;
		}
		else 
			if(strcmp(temp,"while")==0)
		{
			searchchar(tow);
			for(i=0;!(line[position]=='d'&&line[position+1]=='o')
				&&line[position]!='\0';i++,position++)str[i]=line[position];
			str[i]='\0';
			if(boolexpression(str)==0)return 0;
			sentence[psentence].act='w';
			sentence[psentence].entry=bexit[0].entry;
			sentence[psentence].falsesum=bexit[0].falsesum;
			sentence[psentence].truesum=bexit[0].truesum;
		    for(i=0;i<bexit[0].falsesum;i++)sentence[psentence].falseexit[i]=bexit[0].falseexit[i];
			for(i=0;i<bexit[0].truesum;i++)sentence[psentence].trueexit[i]=bexit[0].trueexit[i];
			sentence[psentence].row=row;
			sen[sentencerec]=psentence;
			sentencerec++;
			psentence++;
			searchchar(tow);
			if(line[position]=='d'&&line[position+1]=='o')
			{
				sentence[psentence].act='d';
			    sentence[psentence].entry=outputrec;
			    sen[sentencerec]=psentence;
			    sentencerec++;
			    psentence++;
				position+=2;
			}
			else
			{
				outputerror(6,"while","do");
				return 0;
				
			}
		}
		else 
			if(strcmp(temp,"repeat")==0)
		{
			sentence[psentence].act='r';
			sentence[psentence].entry=outputrec;
			sentence[psentence].row=row;
			sen[sentencerec]=psentence;
			sentencerec++;
			psentence++;
		}
		else 
			if(strcmp(temp,"until")==0)
		{
			searchchar(tow);
			for(i=0;!(line[position+1]=='d'&&line[position+2]=='o')//
				&&line[position]!='\0';i++,position++)str[i]=line[position];
			str[i]='\0';
			if(boolexpression(str)==0)return 0;

			if(sen[sentencerec-1]==100&&sentence[sen[sentencerec-2]].act=='r')
			{
				 for(i=0;i<bexit[0].falsesum;i++)
						output[bexit[0].falseexit[i]].Tnum4=sentence[sen[sentencerec-2]].entry;
				for(i=0;i<bexit[0].truesum;i++)
						output[bexit[0].trueexit[i]].Tnum4=outputrec;
				sen[sentencerec-2]=100;
				sentencerec--;
			}
			else
			{
				outputerror(6,"repeat","until");
				return 0;
			}
		}
		else 
			if(strcmp(temp,"begin")==0)
		{
			sentence[psentence].act='b';
			sentence[psentence].entry=outputrec;
			sentence[psentence].row=row;
			sen[sentencerec]=psentence;
			sentencerec++;
			psentence++;
		}
		else 
			if(strcmp(temp,"end")==0)
		{
			if(sen[sentencerec-1]!=100)
			{
				if(sentence[sen[sentencerec-1]].act=='i')
				{
					outputerror(6,"","if");
					return 0;
				}
				else if(sentence[sen[sentencerec-1]].act=='w')
				{
					outputerror(6,"","while");