编译原理实验一-词法分析器

最新推荐文章于 2023-06-05 13:07:09 发布

原创最新推荐文章于 2023-06-05 13:07:09 发布 · 5.6k 阅读

124 ·

CC 4.0 BY-SA版权

文章标签：

#字符串 #c++ #c语言

计算机基础专栏收录该内容

11 篇文章

订阅专栏

本文介绍了一个词法分析程序的设计与实现，旨在帮助读者理解如何从源代码中识别出具有独立意义的单词，并将其分类为标识符、关键字、常数、运算符和分隔符等类别。文章详细展示了代码实现过程，包括状态转换图、关键函数定义等。

一、实验目的

实验目的和要求通过编写词法分析程序，熟悉其识别单词的基本思想及构造方法。

二、实验要求

编制一个读单词过程，从输入的源程序中，识别出各个具有独立意义的单词，即基本保留字、标识符、常数、运算符、分隔符五大类。并依次输出各个单词的内部编码、单词符号自身值、字符类型。（遇到错误时可显示“Error”，并输出该字符，然后跳过该字符继续识别）。
(1) 标识符(变量)
ID=letter(letter|digit)*

(2) 关键字
void,main,short,long,int,double,float,while,if,else,for,break,return,char

(1) 实数
整数或小数

(2) 运算符
加减乘除以及 < <= == > >=

(3) 分隔符

, ; ( ) { }

部分状态转换图

在这里插入图片描述

代码实现

#include <iostream>
#include <fstream>
#include <string>
#include<map>
#include <cstdio>
#include <cstdlib>
#define SIZE(a)(sizeof(a)/sizeof(a[0])) //求元素个数
using namespace std;
char op[] = {'+','-','*','/'};
void set_mp(map<int,string>&mp) {
    mp[1] = "标识符";
    mp[2] = "关键字";
    mp[3] = "运算符";
    mp[4] = "分隔符";
    mp[5] = "整数";
    mp[6] = "小数";

}
int find_k(string s){//查找s是否在保留字表keyword中
    string keyword[] = {"void","main","short","long","int","double","float","while","if","else","for","break","return","char" };//keyword表
    for (int i = 0; i < SIZE(keyword); i++) {
        if (s.compare(keyword[i]) == 0)return 1;//是保留字，返回1
    }
    return 0;//不是保留字，返回0
}

int isLimit(char c) {
    if (c == ',' || c == ';' || c == '(' || c == ')' || c == '{' || c == '}') {//识别分界符 4
            return 1;
        }
        return 0;
}

int isOp(char c) {
    int p = -1;
    for(int i = 0; i < 4; i++) {
        if(c == op[i]) p = i;
    }
    return p;
}

int main()
{
    ifstream in("input.txt");
    ofstream out("output.txt");
    string s;
    char word;
    int op_pos = -1;
    map<int,string>mp;
    set_mp(mp);
    word = in.get();

    while (!in.eof()) {
        if (isLimit(word)) {//识别分界符
            out << "<" << word << ",4,"<<mp[4]<<">\n";
            word = in.get();
        }else if (isdigit(word)) {//识别整数/实数
            s = "";
            while (isdigit(word)) {
                s += word;
                word = in.get();
                if (word == '.') {//如果出现小数点，有可能是常实数
                    s += word;
                    word = in.get();
                    if (isdigit(word)) {
                        while (isdigit(word)) {
                            s += word;
                            word = in.get();
                        }
                        out << "<" << s << ",6,"<<mp[6]<<">\n";//常实数
                        break;
                    }
                    else out << s + " is error!\n";//如果小数点后没有数字，则报错
                }
                if (!isdigit(word)) {
                    out << "<" << s << ",5,"<<mp[5]<<">\n";//常整数
                    break;
                }
            }
        }else if (isalpha(word) || word == '_') {//识别标识符/保留字
            s = "";
            while (isalpha(word) || isdigit(word) || word =='_') {
                s += word;
                word = in.get();
            }
            if (find_k(s)) {//在keyword表中查找s是否是保留字
                out << "<" << s << ",2,"<<mp[2]<<">\n";//保留字
            }
            else out << "<" << s << ",1,"<<mp[1]<<">\n";//标识符
        }else if (word == '>') {//后面都是运算符
            s = "";
            s += word;
            word = in.get();
            if (word == '=') {//">="
                s += word;
                word = in.get();
            }
            out << "<" << s << ",3,"<<mp[3]<<">\n";
        }
        else if (word == '<') {
            s = "";
            s += word;
            word = in.get();
            if (word == '=') {//"<="
                s += word;
                word = in.get();
            }
            out << "<" << s << ",3,"<<mp[3]<<">\n";
        }else if (word == '=') {
            s = "";
            s += word;
            word = in.get();
            if (word == '=') {//"=="
                s += word;
                word = in.get();
            }
            out << "<" << s << ",3,"<<mp[3]<<">\n";
        }else if((op_pos = isOp(word)) != -1) {
            out << "<" << word << ",3,"<<mp[3]<<">\n";
            word = in.get();
        }else {//跳过当前单词
            word = in.get();
        }
    }
    return 0;
}

测试数据

int main()
{
   int i,ans;
   char c;
   scan c;
   double b=1.5;
   float f;
   for(i=0;i<5;i=i+1)
   {
       ans=ans+1;
   }
   print ans;
   return 0;
}

输出结果

<int,2,关键字>
<main,2,关键字>
<(,4,分隔符>
<),4,分隔符>
<{,4,分隔符>
<int,2,关键字>
<i,1,标识符>
<,,4,分隔符>
<ans,1,标识符>
<;,4,分隔符>
<char,2,关键字>
<c,1,标识符>
<;,4,分隔符>
<scan,1,标识符>
<c,1,标识符>
<;,4,分隔符>
<double,2,关键字>
<b,1,标识符>
<=,3,运算符>
<1.5,6,小数>
<;,4,分隔符>
<float,2,关键字>
<f,1,标识符>
<;,4,分隔符>
<for,2,关键字>
<(,4,分隔符>
<i,1,标识符>
<=,3,运算符>
<0,5,整数>
<;,4,分隔符>
<i,1,标识符>
<<,3,运算符>
<5,5,整数>
<;,4,分隔符>
<i,1,标识符>
<=,3,运算符>
<i,1,标识符>
<1,5,整数>
<),4,分隔符>
<{,4,分隔符>
<ans,1,标识符>
<=,3,运算符>
<ans,1,标识符>
<1,5,整数>
<;,4,分隔符>
<},4,分隔符>
<print,1,标识符>
<ans,1,标识符>
<;,4,分隔符>
<return,2,关键字>
<0,5,整数>
<;,4,分隔符>
<},4,分隔符>