C++使用自动机实现简单的词法分析

该博客介绍了一种使用C++通过自动机实现Pascal语言中常量定义的解析方法。通过两个状态转换表分别处理标识符和变量的分析,识别字符串、字符、整数和浮点数等常量类型。代码中包含了去除空格、判断子串、分割字符串等辅助函数,最后对输入的常量声明进行分析并输出结果。
摘要由CSDN通过智能技术生成

c++使用自动机简单的实现Pascal的常量定义。
样例输入为

   const count1=2180,sum1=6881.655, 12char1='f',count2=65,max1=169,char2='@',sum2=.0815,str1="abcds f 89h",max2=1.6229,str2="good night!";

构造两个自动机,分别用于标识符的分析和变量的分析。
用状态转换表来表示自动机。如下图。
在这里插入图片描述
在这里插入图片描述

具体实现代码如下。

#include<bits/stdc++.h>
#include<unordered_map>
using namespace std;

// 标识符的状态转换表
unordered_map<string,vector<string>> name_table = {
{"start",{"variable","end","end","end"}},
{"variable",{"variable","variable","end","end"}},
{"end",{"end","end","end","end"}}
};

// 变量的状态转换表
unordered_map<string,vector<string>> value_table = {
{"start",{"string","char","int","int","err","float","err"}},
{"string",{"string_end","string","string","string","string","string","string"}},
{"char",{"already_char","already_char","already_char","already_char","already_char","already_char","already_char"}},
{"already_char",{"err","char_end","err","err","err","err","err"}},
{"int",{"err","err","err","int_end","err","float","err"}},
{"float",{"err","err","err","float_end","err","err","err"}},
{"string_end",{"err","err","err","err","err","err","err"}},
{"char_end",{"err","err","err","err","err","err","err"}},
{"int_end",{"err","err","err","int_end","err","float","err"}},
{"float_end",{"err","err","err","float_end","err","err","err"}},
{"err",{"err","err","err","err","err","err","err"}}
};

int string_count = 0;
int char_count = 0;
int int_count = 0;
int float_count = 0;

// 去除字符串两侧的空格
void trim(string &s){
	s.erase(0,s.find_first_not_of(" "));
	s.erase(s.find_last_not_of(" ")+1,s.length()-1);
} 

// 判断字符串开头的子串
bool start_with(string s,string st){
	for(int i=0;i<st.length();i++){
		if(s[i] != st[i]) return false;
	}
	return true;
}

int get_col(char c,string type){
	if(type == "name"){
		if(isalpha(c)) return 0;
		if(isdigit(c)) return 1;
		if(c == '=') return 2;
		else return 3;
	}
	if(type == "value"){
		if(c == '"') return 0;
		else if(c == '\'') return 1;
		else if(c== '+' || c=='-') return 2;
		else if(isdigit(c)) return 3;
		else if(isalpha(c)) return 4;
		else if(c=='.') return 5;
		else return 6;
	}
}

// 分割字符串
vector<string> split(string s,char c){
	vector<string> res;
	int start = 0;
	int co = 10;
	while(s.find(c) != s.npos){
		int pos = s.find(c);
		res.push_back(s.substr(start,pos));
		s.erase(start,pos+1);
	}
	res.push_back(s);
	return res;
}

// 标识符分析
bool token_analysis(string s,string state){
	trim(s);
	for(int i=0;i<s.length();i++){
		state = name_table[state][get_col(s[i],"name")];
		if(state == "end"){
			if(s[i] == '='){
				return true;
			}else{
				s.erase(s.find('='));
				cout << s << "(Wrong!It is not a identifier!)" << "\n";
				return false;
			}
		}	
	}
}

// 变量分析
void variable_analysis(string name,string s,string state){
	trim(name);
	trim(s);
	if(s[s.length()-1] == ';') s.erase(s.length()-1);
	for(int i=0;i<s.length();i++){
		state = value_table[state][get_col(s[i],"value")];
	}
	if(state == "string_end"){
		string_count++;
		cout << name << "(string," << s << ")" <<"\n";
		return ;
	} else if(state == "char_end"){
		char_count++;
		cout << name << "(char," << s << ")" <<"\n";
		return ;
	} else if(state == "int_end"){
		int_count++;
		cout << name << "(int," << s << ")" <<"\n";
		return ;
	} else if(state == "float_end"){
		float_count++;
		cout << name << "(float," << s << ")" <<"\n";
		return ;
	} else {
		cout << s << "(Wrong!The format of the value string is not correct!)" << "\n";
		return ;
	}
}

int main(){
	string s;
	getline(cin,s);
	trim(s);
	if(!start_with(s,"const")){
		cout << "It is not a constant declaration!" << endl;
	} else {
		s.erase(0,5);
		trim(s);
		vector<string> tokens;
		tokens = split(s,',');
		for(int i=0;i<tokens.size();i++){
			vector<string> token = split(tokens[i],'=');
			if(token_analysis(token[0]+"=","start")){
				variable_analysis(token[0],token[1],"start");
			} else {
				continue;
			}
		}
		cout<<"int_num="<<int_count<<";"<<"char_num="<<char_count<<";"<<"string_num="<<string_count<<";"<<"float_num="<<float_count<<"."<<"\n";
	}
	return 0;
}

运行的结果如图。
在这里插入图片描述

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值