编译原理系列 实验一词法分析

刚好把四次实验都给做完了，在实验过程中发现学长学姐留下的实验参考不太够……就留下我的实验结果供大家参考吧~

目录

• 实验一 词法分析实验
  • 一、实验目的
  • 二、题目
  • 三、源程序

实验一 词法分析实验

一、实验目的

根据PL/0语言的文法规范，编写PL/0语言的词法分析程序。要求：
把词法分析器设计成一个独立一遍的过程。
词法分析器的输出形式采用二元式序列，即：(单词种类, 单词的值）。

二、题目

【样例输入】

const a=10;
var b,c;
begin
read(b);
c:=a+b;
write(c)
end.

【样例输出】

(constsym,const)
(ident,a)
(eql,=)
(number,10)
(semicolon,;)
(varsym,var)
(ident,b)
(comma,,)
(ident,c)
(semicolon,;)
(beginsym,begin)
(readsym,read)
(lparen,()
(ident,b)
(rparen,))
(semicolon,;)
(ident,c)
(becomes,:=)
(ident,a)
(plus,+)
(ident,b)
(semicolon,;)
(writesym,write)
(lparen,()
(ident,c)
(rparen,))
(endsym,end)
(period,.)

三、源程序

#include<fstream>
#include<cstring>
#include<string>
#include<fstream>
#include<sstream>
#include<iostream>
#include<map>
#include<bits/stdc++.h>
using namespace std;

map<string,string> words;
std::map<string,string>::iterator it;//words的指针
void words_init(){//对应关系进行初始化
    words["+"]="plus";
    words["-"]="minus";
    words["*"]="times";
    words["/"]="slash";
    words["="]="eql";
    words["<>"]="neq";
    words["<"]="lss";
    words["<="]="leq";
    words[">"]="gtr";
    words[">="]="geq";
    words[":="]="becomes";
    words["("]="lparen";
    words[")"]="rparen";
    words[","]="comma";
    words[";"]="semicolon";
    words["."]="period";
    words["read"]="readsym";
    words["then"]="thensym";
    words["if"]="ifsym";
    words["odd"]="oddsym";
    words["procedure"]="proceduresym";
    words["var"]="varsym";
    words["while"]="whilesym";
    words["write"]="writesym";
    words["begin"]="beginsym";
    words["do"]="dosym";
    words["end"]="endsym";
    words["call"]="callsym";
    words["const"]="constsym";
}

int main(){
    words_init();//初始化

    // 读入输入串
    char ins[100];
    int i=0;
    ins[i] = getchar();
    while(ins[i] != '.'){
        ins[++i] = getchar();
    }
    string inputs = ins;

    // 处理输入串
    int insize=inputs.length();
    string word;
    for(int i=0; i<insize; i++)
    {
        // 空白符跳过
        while(inputs[i] == ' ' || inputs[i] == '\n')
            i++;

        // 标志符/基本字捕捉
        if(isalpha(inputs[i])){
            // 拿出一个标志符/基本字
            word = inputs[i++];
            while(isalpha(inputs[i]) || isdigit(inputs[i]))
                word += inputs[i++];
            // 在map中找到相应的词性，并输出
            it = words.find(word);
            if(it != words.end())
                cout << "(" << words[word] << "," << word << ")" << endl;
            else
                cout << "(ident" << "," << word << ")" << endl;
            i--;
        }

        // 常数
        else if(isdigit(inputs[i])){
            // 拿出常数
            word=inputs[i++];
            while(isdigit(inputs[i]))
                word+=inputs[i++];
            cout << "(number" << "," << word << ")" << endl;
            i--;
        }

        // <、<=号
        else if(inputs[i]=='<'){
            word=inputs[i++];
            if(inputs[i]=='>'){
                word+=inputs[i];
                cout << "(" << words[word] << "," << word << ")" << endl;
            }else if(inputs[i]=='='){
                word+=inputs[i];
                cout << "(" <<words[word] << "," << word << ")" << endl;
            }else if(inputs[i]!=' '||!isdigit(inputs[i])||!isalpha(inputs[i])){
                cout << "(" << words[word] << "," << word << ")" << endl;
            }else{
                //cout << "error!" << endl;
            }
            i--;
        }

        // >、>=
        else if(inputs[i]=='>'){
            word=inputs[i++];
            if(inputs[i]=='='){
                word+=inputs[i];
                cout<<"("<<words[word]<<","<<word<<")"<<endl;
            }else if(inputs[i]!=' '||!isdigit(inputs[i])||!isalpha(inputs[i])){
                cout<<"("<<words[word]<<","<<word<<")"<<endl;
            }else{
                //cout<<"error!"<<endl;
            }
            i--;
        }

        //:=
        else if(inputs[i]==':'){
            word=inputs[i++];
            if(inputs[i]=='='){
                word+=inputs[i];
                cout<<"("<<words[word]<<","<<word<<")"<<endl;
            }else{
                //cout<<"error!"<<endl;
            }
            //i--;
        }

        //其他的基本字
        else{
            word=inputs[i];
            it=words.find(word);
            if(it!=words.end()){
                cout<<"("<<words[word]<<","<<word<<")"<<endl;
            }else{
                //cout<<"error!"<<endl;
            }
        }
    }

    return 0;
}