一、原文章:词法分析器(分析C语言)
二、该词法分析器种别码表
三、词法分析器实现思路描述:
1.首先用一个数组来存储txt文本中非空白字符,并将存储字符的个数记录下来。
2.用scan()函数扫描数组中的字符,用index来定位当前扫描到的字符位置。
3.判断当前字符是哪种类型:
(1)若是字母,则有可能是关键字或标识符,需继续看下一个字符。若是关键字,再判断具体是哪个种别码;若是标识符,种别码为0。
(2)若是数字,是常量,种别码为24。
(3)若是运算符或界符,则需继续看下一个字符(因为可能是<=、>=、==、!=),再判断具体是哪个种别码。
(4)若不是以上三种,则输出。
二、用C语言改写并优化:
#pragma warning(disable:4996)
#include <stdio.h>
#include <ctype.h>
#include <string.h>
#include <stdlib.h>
const int MAXN = 1000;
const int MINN = 20;
bool isKey(char* s) //是否是关键字
{
const char* letter[6] = { "main","int","if","else","while","do" };
for (int i = 0; i < 6; i++)
{
if (strcmp(s, letter[i]) == 0)
return true;
}
return false;
}
bool isOpebounder(char s) //是否是界符或运算符
{
const char* str = "><=!(){},;+-*/";
if (memchr(str, s, strlen(str)) != NULL)
return true;
else
return false;
}
int kindofKey(char* str) //判断哪种关键字 并返回其种别码
{
const char* key[6] = { "main","int","if","else","while","do" };
const int arr[6] = { 1,2,3,4,5,6 };
for (int i = 0; i < 6; i++)
{
if (strcmp(str, key[i]) == 0)
return arr[i];
}
}
int kindofOpebounder(char* str) //判断哪种运算符和界符 并返回其种别码
{
const char* opebounder[17] = { "<",">","!=",">=","<=","==",",",";","(",")","{","}","+","-","*","/","=" };
const int arr[MINN] = { 7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23 };
for (int i = 0; i < 17; i++)
{
if (strcmp(str, opebounder[i]) == 0)
return arr[i];
}
}
char* firstLetter(char* s) //首字符为字母
{
int size = 0;//单词长度
char str[MINN] = ""; //单词
char c; //存储当前字符的下一个 方便作为实参以识别类型
str[size++] = *s; //保存当前字符并增加长度
while (c = *(s + size))
{
if (islower(c) || isdigit(c)) //下一个字符是字母或数字则保存在str中
str[size++] = c;
else
break;
if (isKey(str)) //如果单词恰好是关键字 则终止循环
break;
}
return str;
}
char* firstNumber(char* s) //首字符为数字
{
int size = 0;
char str[MINN] = "";
char c;
str[size++] = *s;
while (c = *(s + size))
{
if (isdigit(c)) //下一个字符是字母或数字则保存在str中
str[size++] = c;
else
break;
}
return str;
}
char* firstOpebounder(char* s) //首字符为运算符和界符
{
char arr[MINN] = ">=<!";
char str[MINN] = "";
char c = *(s + 1);
str[0] = *s;
if (memchr(arr, *s, strlen(arr)) != NULL)
{
if (c == '=')
str[1] = '=';
}
return str;
}
int Type(char* s) //判断单词的首字母为哪种类型
{
if (islower(*s))
return 1;
else if (isdigit(*s))
return 2;
else if (isOpebounder(*s))
return 3;
else
return 4;
}
void scan(char* s, int n)
{
for (int index = 0; index < n;index++)
{
char str[MINN] = ""; //存储单词
switch (Type(s + index))
{
case 1:
{
//首字符为字母 可能是关键字或标识符 接下来持续读取字母形成单词
strcpy(str, firstLetter(s + index));
if (isKey(str))
printf("(%s,%d)\n", str, kindofKey(str));
else
printf("(%s,0)\n", str);
index += (strlen(str) - 1);
break;
}
case 2:
{
//首字符为数字,只能是常量
strcpy(str, firstNumber(s+index));
printf("(%s,24)\n", str);
index += (strlen(str) - 1);
break;
}
case 3:
{
//首字符为运算符和界符
strcpy(str, firstOpebounder(s+index));
printf("(%s,%d)\n", str, kindofOpebounder(str));
index += (strlen(str) - 1);
break;
}
default:
{
//其他
printf("(%c,error)\n", *(s+index));
}
}
}
}
int main(void)
{
char letter[MAXN] = ""; //存储要扫描的字符
int size = 0; //字符的个数
//与s.txt文件连接并读取里面的内容
FILE* fp;
fp = fopen("s.txt", "r");
char ch = getc(fp);
while (ch != EOF)
{
if (ch != ' '&&ch !='\n') //保存非空白字符
{
letter[size] = ch;
size++;
}
ch = getc(fp);
}
fclose(fp);
//开始扫,并将结果以二元的形式打印在屏幕上
scan(letter, size);
return 0;
}
三、文本内容及结果截图: