编译原理头歌实验：词法分析程序设计与实现（C语言版）

1.实验描述

任务描述

本关任务：加深对词法分析器的工作过程的理解；加强对词法分析方法的掌握；能够采用一种编程语言实现简单的词法分析程序；能够使用自己编写的分析程序对简单的程序段进行词法分析。

编程要求

根据提示，在右侧编辑器补充代码标示符、数字符及其他字符符号的识别程序后，点击评测运行程序，系统会自动进行结果对比。

测试说明

平台会对你编写的代码进行测试：

测试输入：

using namespace std; int main() {
int year;
cout << “hello” << endl;
return 0; }

2.实验操作提示

2.1定义目标语言的可用符号表和构词规则。

我们需要对五种单词符号进行识别分析，这里将单词符号分为三大块进行识别。首先判断字符是否为关键字或者标识符，并与已定义好的关键字进行比较，从而判断为关键字或者标识符；然后是数字的识别；最后是其他字符的判断，它们被一一定义好的判断进行识别，这样所有的字符便被识别出来了。标示符和关键字的判断

if ((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z'))  //可能是标示符或者关键字

字符与关键字的区别通过对比得出：

if (strcmp(token, rwtab1[n]) == 0)
         {
             syn = 2;
             break;
         }
         else if (strcmp(token, rwtab[n]) == 0) {
             syn = 1;
             break;
         }
 }

对于数字的识别：

else if ((ch >= '0' && ch <= '9'))  //数字 

其他字符的识别，他们被一一定义进行识别：

else switch (ch)   //其他字符 
 {
 case'<':m = 0; token[m++] = ch;
     ch = prog[p++];
     if (ch == '>')
     {
         syn = 4;
         token[m++] = ch;
     }
     else if (ch == '=')
     {
         syn = 4;
         token[m++] = ch;
     }
     else
     {
         syn = 4;
         p--;
     }
     break;
 case'>':m = 0; token[m++] = ch;
     ch = prog[p++];
     if (ch == '=')
     {
         syn = 4;
         token[m++] = ch;
     }
     else
     {
         syn = 4;
         p--;
     }
     break;
 case':':m = 0; token[m++] = ch;
     ch = prog[p++];
     if (ch == '=')
     {
         syn = 4;
         token[m++] = ch;
     }
     else
     {
         syn = 4;
         p--;
     }
     break;
 case'*':syn = 4; token[0] = ch; break;
 case'/':syn = 4; token[0] = ch; break;
 case'+':syn = 4; token[0] = ch; break;
 case'-':syn = 4; token[0] = ch; break;
 case'=':syn = 4; token[0] = ch; break;
 case';':syn = 5; token[0] = ch; break;
 case',':syn = 5; token[0] = ch; break;
 case'(':syn = 5; token[0] = ch; break;
 case')':syn = 5; token[0] = ch; break;
 case'{':syn = 5; token[0] = ch; break;
 case'}':syn = 5; token[0] = ch; break;
 case'#':syn = 0; token[0] = ch; break;
 case'\n':syn = -2; break;
 default: syn = -1; break;
 }
}

依次读入源程序符号，对源程序进行单词切分和识别，直到源程序结束。
字符的输入我们使用cin.get() 获取，并切分保存在 prog中：

p = 0;
 row = 1;
 cout << "Please input string:" << endl;
 do
 {
     cin.get(ch);
     prog[p++] = ch;
 } while (ch != '#');
 p = 0; 

对正确的单词，按照它的种别以<种别码，值>的形式保存在符号表中；

对不正确的单词，做出错误处理。
单词识别后，我们对返回的符号按3，4的规则进行输出：

{
     scaner();
     switch (syn)
     {
     case 0: break;
     case 3: cout << "(" << syn << "," << sum << ")" << endl; break;
     case -1: cout << "Error in row " << row << "!" << endl; break;
     case -2: row = row++; break;
     default: cout << "(" << syn << "," << token << ")" << endl; break;
     }
 } while (syn != 0); 

3.实验代码展示

#include <stdio.h>
#include <string.h>
#include <iostream>
using namespace std;
char prog[1000], token[20];
char ch;
int syn, p, m = 0, n, row = 1, sum = 0;
// 扩充关键字表
const char* rwtab[10] = { "if","int","for","while","do","return","break","continue", "using", "namespace" };
const char* rwtab1[8] = { "main","a","b","c","d","e","f","g" };

void scaner()
{
    // 初始化token数组
    for (n = 0; n < 20; n++) token[n] = '\0';
    // 跳过空白字符
    while (p < strlen(prog) && (prog[p] == ' ' || prog[p] == '\t' || prog[p] == '\n'))
    {
        if (prog[p] == '\n')
            row++;
        p++;
    }
    if (p >= strlen(prog))
    {
        syn = 0;
        return;
    }
    ch = prog[p++];

    // 进行标示符或者关键字的识别
    if ((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z'))
    {
        m = 0;
        while ((ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') || (ch >= '0' && ch <= '9'))
        {
            token[m++] = ch;
            if (p >= strlen(prog))
                break;
            ch = prog[p++];
        }
        token[m] = '\0';
        if (p < strlen(prog))
            p--;
        syn = 2;
        for (n = 0; n < 10; n++) // 更新关键字表长度
        {
            if (strcmp(token, rwtab[n]) == 0)
            {
                syn = 1;
                break;
            }
        }
    }
    // 进行数字的识别
    else if (ch >= '0' && ch <= '9')
    {
        sum = 0;
        while (ch >= '0' && ch <= '9')
        {
            sum = sum * 10 + (ch - '0');
            if (p >= strlen(prog))
                break;
            ch = prog[p++];
        }
        if (p < strlen(prog))
            p--;
        syn = 3;
    }
    // 进行其他字符的识别
    else
    {
        switch (ch)
        {
        case '<':
            m = 0;
            token[m++] = ch;
            if (p < strlen(prog) && prog[p] == '<')
            {
                token[m++] = prog[p++];
                syn = 4;
            }
            else
            {
                syn = 4;
                p--;
            }
            break;
        case '>':
            m = 0;
            token[m++] = ch;
            if (p < strlen(prog) && prog[p] == '=')
            {
                token[m++] = prog[p++];
                syn = 4;
            }
            else
            {
                syn = 4;
                p--;
            }
            break;
        case ':':
            m = 0;
            token[m++] = ch;
            if (p < strlen(prog) && prog[p] == '=')
            {
                token[m++] = prog[p++];
                syn = 4;
            }
            else
            {
                syn = 4;
                p--;
            }
            break;
        case '*':
            syn = 4;
            token[0] = ch;
            break;
        case '/':
            syn = 4;
            token[0] = ch;
            if (p < strlen(prog) && prog[p] == '/') {
                token[1] = '/';
                syn = 5; // 注释符号作为界符处理
                p++;
            }
            break;
        case '+':
            syn = 4;
            token[0] = ch;
            break;
        case '-':
            syn = 4;
            token[0] = ch;
            break;
        case '=':
            syn = 4;
            token[0] = ch;
            break;
        case ';':
            syn = 5;
            token[0] = ch;
            break;
        case ',':
            syn = 5;
            token[0] = ch;
            break;
        case '(':
            syn = 5;
            token[0] = ch;
            break;
        case ')':
            syn = 5;
            token[0] = ch;
            break;
        case '{':
            syn = 5;
            token[0] = ch;
            break;
        case '}':
            syn = 5;
            token[0] = ch;
            break;
        case '#':
            syn = 0;
            token[0] = ch;
            break;
        case '"':
            syn = 5;
            token[0] = ch;
            break;
        default:
            syn = -1;
            break;
        }
    }
}

int main()
{
    // 输入
    p = 0;
    cout << "Please input string:" << endl;
    do
    {
        cin.get(ch);
        prog[p++] = ch;
    } while (ch != '#');
    prog[p] = '\0';
    p = 0;

    // 输出
    do
    {
        scaner();
        switch (syn)
        {
        case 0:
            break;
        case 3:
            cout << "(" << syn << "," << sum << ")" << endl;
            break;
        case -1:
            cout << "Error in row " << row << "!" << endl;
            break;
        default:
            cout << "(" << syn << "," << token << ")" << endl;
            break;
        }
    } while (syn != 0);
    return 0;
}    

这个词法分析器通过逐字符读取输入，根据字符的类型和上下文规则，识别出关键字、标识符、数字、运算符和分隔符。它能正确处理简单的 C++ 代码段，并输出每个记号的类型和内容。程序设计清晰，逻辑分明，适合学习词法分析的基本原理。

希望这个讲解能帮助你深入理解代码的实现过程！如果有疑问，欢迎评论区交流！