编译原理——词法分析器

       输入为字符串（或待进行词法分析的源程序），输出为单词串，即由（单词，类别）所组成的二元组序列；

有一定的错误检查能力，例如能发现2a这类不能作为单词的字符串。

       保留字表没有做全，用时自行添加即可。

---

C++实现如下：

#include<fstream>
#include<cstring>
#include<string>
#include<fstream>
#include<sstream>
#include<iostream>
#include<map>
#include<bits/stdc++.h>
using namespace std;
map<string,string> word;//保留字表 
std::map<string,string>::iterator it;//查找保留字的迭代器
void map_init(){//对应关系进行初始化
	word["for"]="保留字";
	word["else"]="保留字";
	word["const"]="保留字";
	word["do"]="保留字";
	word["endl"]="保留字";
	word["if"]="保留字";
	word["cout"]="保留字";
	word["void"]="保留字";
	word["read"]="保留字";
	word["then"]="保留字";
	word["cin"]="保留字";
	word["while"]="保留字";
	word["break"]="保留字";
	word["int"]="保留字";
	word["double"]="保留字";
	word["float"]="保留字";
	word["long"]="保留字";
	word["main"]="保留字";
	word["continue"]="保留字";
	word["return"]="保留字";
	word["bool"]="保留字";
	word["string"]="保留字";
	word["getline"]="保留字";
	word["true"]="保留字";
	word["false"]="保留字";
	word["+"]="运算符";
	word["-"]="运算符";
	word["*"]="运算符";
	word["/"]="运算符";
	word["="]="运算符";
	word["<"]="运算符";
	word["<="]="运算符";
	word["<<"]="运算符";
	word[">>"]="运算符";
	word[">"]="运算符";
	word["%"]="运算符";
	word[">="]="运算符";
	word["=="]="运算符";
	word["!="]="运算符";
	word["|"]="运算符";
	word["||"]="运算符";
	word["&"]="运算符";
	word["&&"]="运算符";
	word["("]="界符";
	word[")"]="界符";
	word[","]="分隔符";
	word[";"]="界符";
	word["."]="运算符";
	word["->"]="运算符";
	word["["]="界符";
	word["]"]="界符";
	word["{"]="界符";
	word["}"]="界符";
	word["}"]="界符";
	word["'"]="界符";
}
int main(){
	map_init();		//初始化
	char ch;
	char a;
	string word1;		//识别单词
	string str;		//字符识别
	ifstream infile("E:\\编译原理\\ans.txt");	//源程序文件路径输入 
	ostringstream buf;
	while(buf&&infile.get(ch)) buf.put(ch);		//将文件中的字符读出来
	str= buf.str();		//获取得到的字符
	int csize=str.length();
	for(int i=0;i<csize;i++){		//对整个字符串进行遍历
		while(str[i]==' '||str[i]=='\n'||str[i]=='	') i++;		//若最开始为空格、制表符或换行符，则将指针的位置往后移
		if(isalpha(str[i])){	//对标识符和保留字进行识别,调用库函数isalpha() 
			word1=str[i++];
			while(isalpha(str[i])||isdigit(str[i])){
				word1+=str[i++];
			}
			it=word.find(word1);
			if(it!=word.end()){		//判断是不是保留字，若为保留字则进行输出
				cout<<word1<<","<<word[word1]<<endl;
			}
			else{	//否则直接输出 
				cout<<word1<<",标识符"<<endl;
			}
			i--;
		}
		else if(isdigit(str[i])){	//判断是不是常数，调用库函数isdigit()
			word1=str[i++];
			while(isdigit(str[i])){
				word1+=str[i++];
			}
			if(isalpha(str[i])){
				while(isalpha(str[i])||isdigit(str[i])){
					word1+=str[i++];
				}
				cout<<word1<<",非法定义的标识符"<<endl;
			}
			else{
				cout<<word1<<",数字"<<endl;
			}
			i--;
		}else if(str[i]=='<'){//对<,<=,<<分别进行判断
			word1=str[i++];
			if(str[i]=='='){
				word1+=str[i];
				cout<<word1<<","<<word[word1]<<endl;
				i++;
			}else if(str[i]=='<'){
				word1+=str[i];
				cout<<word1<<","<<word[word1]<<endl;
				i++;
			}else if(str[i]!=' '||!isdigit(str[i])||!isalpha(str[i])){
				cout<<word1<<","<<word[word1]<<endl;
			}else{
				cout<<"error!"<<endl;
				break;
			}
			i--;
		}else if(str[i]=='>'){//对>,>=,>>分别进行判断
			word1=str[i++];
			if(str[i]=='='){
				word1+=str[i];
				cout<<word1<<","<<word[word1]<<endl;
				i++;
			}else if(str[i]=='>'){
				word1+=str[i];
				cout<<word1<<","<<word[word1]<<endl;
				i++;
			}else if(str[i]!=' '||!isdigit(str[i])||!isalpha(str[i])){
				cout<<word1<<","<<word[word1]<<endl;
			}else{
				cout<<"error!"<<endl;
				break;
			}
			i--;
		}else if(str[i]=='-'){//对-,->进行判断
			word1=str[i++];
			if(str[i]=='>'){
				word1+=str[i];
				cout<<word1<<","<<word[word1]<<endl;
				i++;
			}else if(str[i]!=' '||!isdigit(str[i])||!isalpha(str[i])){
				cout<<word1<<","<<word[word1]<<endl;
			}else{
				cout<<"error!"<<endl;
				break;
			}
			i--;
		}else if(str[i]=='='){//对==分别进行判断
			word1=str[i++];
			if(str[i]=='='){
				word1+=str[i];
				cout<<word1<<","<<word[word1]<<endl;
				i++;
			}else if(str[i]!=' '||!isdigit(str[i])||!isalpha(str[i])){
				cout<<word1<<","<<word[word1]<<endl;
			}else{
				cout<<"error!"<<endl;
				break;
			}
			i--;
		}else if(str[i]=='!'){//对!=分别进行判断
			word1=str[i++];
			if(str[i]=='='){
				word1+=str[i];
				cout<<word1<<","<<word[word1]<<endl;
				i++;
			}else if(str[i]!=' '||!isdigit(str[i])||!isalpha(str[i])){
				cout<<word1<<","<<word[word1]<<endl;
			}else{
				cout<<"error!"<<endl;
				break;
			}
			i--;
		}else if(str[i]=='|'){//对|,||分别进行判断
			word1=str[i++];
			if(str[i]=='|'){
				word1+=str[i];
				cout<<word1<<","<<word[word1]<<endl;
				i++;
			}else if(str[i]!=' '||!isdigit(str[i])||!isalpha(str[i])){
				cout<<word1<<","<<word[word1]<<endl;
			}else{
				cout<<"error!"<<endl;
				break;
			}
			i--;
		}else if(str[i]=='&'){//对&,&&分别进行判断
			word1=str[i++];
			if(str[i]=='&'){
				word1+=str[i];
				cout<<word1<<","<<word[word1]<<endl;
				i++;
			}else if(str[i]!=' '||!isdigit(str[i])||!isalpha(str[i])){
				cout<<word1<<","<<word[word1]<<endl;
			}else{
				cout<<"error!"<<endl;
				break;
			}
			i--;
		}else if(str[i]=='"'){//对字符串进行判断
			word1=str[i++];
			while(str[i]!='"'){
				word1+=str[i++];
			}
			word1+=str[i++];
			cout<<word1<<",字符串"<<endl;
			i--;
		}else{	//对其他的基本字依次进行判断
			word1=str[i];
			it=word.find(word1);
			if(it!=word.end()){
				cout<<word1<<","<<word[word1]<<endl;
			}else{
				cout<<"error!"<<endl;
				break;
			}
		}
	}
	infile.close();
	return 0;
}

ans.txt文件为要识别的源程序文件，将要识别的源程序放入其中即可。