NUAA-编译原理-词法分析

写在前面:

对于中文的检错,列数Col的值可能存在问题,原因好像是最后一个字符会读很多次?

对于中文的检错:一个中文字符的编码是两个字节,每个字节都是以1开头(ancil码都是以0开头的)

文件结构:

源码: (LA.h)

/**
 * @filename: LA.cpp
 * @author 张大仙 1607212422@qq.com
 * @brief 词法分析函数
 * @version
 * @date 2022-09-19
 *
 *
 */

/**
 * COP compare operator 比较符
 * AOP assignment operator 赋值符
 * OOP operation operator 操作符
 * EOP end operator 结束符
 * SOP separate operator 分隔符
 */

#include <iostream>
#include <fstream>
#include <string>
#include <cstring>
using namespace std;

int Row, Col;                                                                 // 行列标记
FILE *in_file = fopen("D:\\vscodeworkspacde\\test\\infile1_for_LA.txt", "r"); //尽量学着用绝对路径
fstream out_file("D:\\vscodeworkspacde\\test\\outfile1_for_LA.txt", ios::out);

const string Key[] = {
    "", "program", "const", "var", "procedure", "begin", "if",
    "else", "end", "while", "call", "read", "write", "then", "odd", "do"}; // 定义关键字，第一个是占位符，无实际意义

/**
 * @brief 判断是不是空格 \t \r \n 如果是相应的 Row和Col会做出相应的变化
 * @param ch
 * @return true
 * @return false
 */
bool isBC(char ch)
{
   if (ch == ' ')
   { // 空格
      Col++;
      return true;
   }
   else if (ch == '\t')
   { // tab
      Col += 4;
      return true;
   }
   else if (ch == '\r' || ch == '\n') // 回车
   {
      Row++;
      Col = 1;
      return true;
   }
   else
   {
      return false;
   }
}
/**
 * @brief 把ch连接到strToken
 *
 * @param strToken
 * @param ch
 */
void Concat(string &strToken, char ch)
{
   strToken.push_back(ch);
}
/**
 * @brief 如果ch是一个A-Za-z的就返回ture
 *
 * @param ch
 * @return true
 * @return false
 */
bool IsLetter(char ch)
{
   if (ch >= 'a' && ch <= 'z')
   {
      return true;
   }
   else if (ch >= 'A' && ch <= 'Z')
   {
      return true;
   }
   else
      return false;
}
/**
 * @brief 如果是一个0-9的数字返回ture
 *
 * @param ch
 * @return true
 * @return false
 */
bool IsDigit(char ch)
{
   if (ch >= '0' && ch <= '9')
   {
      return true;
   }
   else
      return false;
}
/**
 * @brief 如果是Key中的系统保留字 返回其下标
 *
 * @param strToken
 * @return int
 */
int Reserve(string strToken)
{
   for (int i = 1; i <= 15; i++)
   {
      if (strToken == Key[i])
      {
         return i;
      }
   }
   return 0;
}
/**
 * @brief 如果不是EOF 将ch退回到读入流中去
 *
 * @param ch
 */
void Retract(char ch)
{
   if (ch != EOF)
   {
      ungetc(ch, in_file);
   }
}

/**
 * @brief 词法分析实现函数
 *
 * @return int
 */
int LA()
{
   if (!in_file)
   {
      cout << "输入文件打开失败" << endl;
      exit(1);
   }

   if (!out_file.is_open())
   {
      cout << "输出文件打开失败" << endl;
      exit(2);
   }

   Row = Col = 1;
   string strToken = "";
   char ch; //从缓冲区读进来的字符

   while (1)
   {
      ch = fgetc(in_file);
      if (ch == EOF || feof(in_file))
         break;
      // 1.判断是否为空白
      if (isBC(ch))
      {
         strToken = "";
      }
      // 2.判断是否为字母
      else if (IsLetter(ch))
      {
         //将所有字符连接起来
         while (IsDigit(ch) || IsLetter(ch))
         {
            Concat(strToken, ch);
            Col++;
            ch = fgetc(in_file);
         }

         //判断是关键字还是ID
         if (Reserve(strToken))
         {
            out_file << strToken << " RESERVED " << Row << ' ' << Col << endl;
         }
         else
         {
            out_file << strToken << " id " << Row << ' ' << Col << endl;
         }
         strToken = "";
         Retract(ch); //别忘了把刚才不满足while的那个字退回到读入流中
      }
      // 3.判断是否为数字
      else if (IsDigit(ch))
      {
         //将所有数字连接起来
         while (IsDigit(ch))
         {
            Concat(strToken, ch);
            Col++;
            ch = fgetc(in_file);
         }

         //以数字开头的ID，报错！
         if (IsLetter(ch))
         {

            //继续读完字符串
            while (IsLetter(ch) || IsDigit(ch))
            {
               Concat(strToken, ch);
               Col++;
               ch = fgetc(in_file);
            }
            cout << "[Lexical ERROR]"
                 << " [" << Row << "," << Col << "] "
                 << "Invalid ID: " << strToken << endl;
            out_file << strToken << " id " << Row << ' ' << Col << endl;
         }
         else
         {

            out_file << strToken << " INT " << Row << ' ' << Col << endl;
         }
         Retract(ch);
         strToken = "";
      }
      // 4.判断是否为中文字符
      else if (ch & 0x80)
      {
         ch = fgetc(in_file);

         if (ch & 0x80 && ch != -1)
         {
            cout << "在" << Row << "行" << Col << "列"
                 << "出现一个中文字符,出错了" << endl;
            Col += 1;
         }
         else
         {
            Retract(ch);
         }
      }
      // 5.判断是否为其他字符
      else
      {
         if (ch == '=')
         {
            Col++;
            out_file << ch << " COP " << Row << ' ' << Col << endl;
         }
         else if (ch == '<')
         {
            Col++;
            ch = fgetc(in_file);
            if (ch == '>')
            {
               Col++;
               out_file << "<> COP " << Row << ' ' << Col << endl;
            }
            else if (ch == '=')
            {
               Col++;
               out_file << "<= COP " << Row << ' ' << Col << endl;
            }
            else
            {
               out_file << "< COP " << Row << ' ' << Col << endl;
               Retract(ch);
            }
         }
         else if (ch == '>')
         {
            Col++;
            ch = fgetc(in_file);
            if (ch == '=')
            {
               Col++;
               out_file << ">= COP " << Row << ' ' << Col << endl;
            }
            else
            {
               out_file << "> COP " << Row << ' ' << Col << endl;
               Retract(ch);
            }
         }
         else if (ch == ':')
         {
            Col++;
            ch = fgetc(in_file);
            if (ch == '=')
            {
               Col++;
               out_file << ":= AOP " << Row << ' ' << Col << endl;
            }
            else
            {
               cout << "[LEXICAL ERROR]"
                    << " [" << Row << "," << Col << "] "
                    << "Missing \"=\" near the \":\" " << endl;
               out_file << ":= AOP " << Row << ' ' << Col << endl;
               Retract(ch);
            }
         }
         else if (ch == '+' || ch == '-' || ch == '*' || ch == '/')
         {
            Col++;
            out_file << ch << " OOP " << Row << ' ' << Col << endl;
         }
         else if (ch == ';')
         {
            Col++;
            out_file << ch << " EOP " << Row << ' ' << Col << endl;
         }
         else if (ch == '(' || ch == ')' || ch == ',' || ch == '.')
         {
            Col++;
            out_file << ch << " SOP " << Row << ' ' << Col << endl;
         }
         else
         {
            Col++;
            out_file << ch << " UNKNOWN " << Row << ' ' << Col << endl;
         }
      }
   }
   fclose(in_file);
   out_file.close();

   printf("-----词法分析已完成,结果存至out_file.txt文件中-----\n");

   return 0;
}

 最后:

鼠标悬浮在函数上会自动出现注释,原因是使用了插件

 使用方法见另一篇文章头部注释插件使用https://mp.csdn.net/mp_blog/creation/editor/126925377