《编译原理》--词法分析的实现 一一创作

《编译原理》–词法分析的实现

输入与输出

要输入的文件在E:\lll.txt中，通过读取其中的文本进行词法分析 以$结束
输出的结果保存在E:\mmm.txt中，输入输出结果如下；
程序运行结果图：

E:\lll.txt中的文件

E:\mmm.txt文件：

源代码如下

// Lexical_Analysis.cpp : 定义控制台应用程序的入口点。

#include “stdio.h”
#include “stdlib.h”
#include “string.h”
#include “iostream”
using namespace std;
//词法分析程序
//首先定义种别码
/*
11 第一类：标识符 letter(letter | digit)* 无穷集
12 第二类：常数 (digit)+ 无穷集
13 第三类：保留字(32)
14 auto break case char const continue
15 default do double else enum extern
16 float for goto if int long
17 register return short signed sizeof static
18 struct switch typedef union unsigned void
19 volatile while
20
21 第四类：界符 ‘/’、‘//’、 () { } [ ] " " ’
22 第五类：运算符 <、<=、>、>=、=、+、-、、/、^、
23
24 对所有可数符号进行编码：
25 <$,0>
26 <auto,1>
27 …
28 <while,32>
29 <+，33>
30 <-,34>
31 <*,35>
32 </,36>
33 <<,37>
34 <<=,38>
35 <>,39>
36 <>=,40>
37 <=,41>
38 <==,42>
39 <!=,43>
40 <;,44>
41 <(,45>
42 <),46>
43 <^,47>
44 <,48>
45 <",49>
46 <’,50>
47 <#,51>
48 <&,52>
49 <&&,53>
50 <|,54>
51 <||,55>
52 <%,56>
53 <~,57>
54 <<<,58>左移
55 <>>,59>右移
56 <[,60>
57 <],61>
58 <{,62>
59 <},63>
60 <,64>
61 <.,65>
62 <?,66>
63 <:,67>
64 <!,68>
65 “[”,"]","{","}"
66 <常数99 ,数值>
67 <标识符100 ，标识符指针>
68
69
70 */

 /****************************************************************************************/
 //全局变量，保留字表
 static char reserveWord[32][20] = {
    "auto", "break", "case", "char", "const", "continue",
    "default", "do", "double", "else", "enum", "extern",
     "float", "for", "goto", "if", "int", "long",
     "register", "return", "short", "signed", "sizeof", "static",
     "struct", "switch", "typedef", "union", "unsigned", "void",
     "volatile", "while"
 };

//界符运算符表,根据需要可以自行增加
static char operatorOrDelimiter[36][10] = {
“+”, “-”, “*”, “/”, “<”, “<=”, “>”, “>=”, “=”, “==”,
“!=”, “;”, “(”, “)”, “^”, “,”, “”", “’”, “#”, “&”,
“&&”, “|”, “||”, “%”, “~”, “<<”, “>>”, “[”, “]”, “{”,
“}”, “\”, “.”, “?”, “:”, “!”
};

static char IDentifierTbl[1000][50] = { “” };//标识符表
/****************************************************************************************/

/查找保留字*********/
int searchReserve(char reserveWord[][20], char s[])
{
for (int i = 0; i < 32; i++)
{
if (strcmp(reserveWord[i], s) == 0)
{//若成功查找，则返回种别码
return i + 1;//返回种别码
}
}
return -1;//否则返回-1，代表查找不成功，即为标识符
}
/查找保留字*********/

/*判断是否为字母/
bool IsLetter(char letter)
{//注意C语言允许下划线也为标识符的一部分可以放在首部或其他地方
if (letter >= ‘a’&&letter <= ‘z’ || letter >= ‘A’&&letter <= ‘Z’ || letter == ‘_’)
{
return true;
}
else
{
return false;
}
}
/*判断是否为字母/

/判断是否为数字*******/
bool IsDigit(char digit)
{
if (digit >= ‘0’&&digit <= ‘9’)
{
return true;
}
else
{
return false;
}
}
/判断是否为数字*******/

/编译预处理，取出无用的字符和注释**/
void filterResource(char r[], int pProject)
{
char tempString[10000];
int count = 0;
for (int i = 0; i <= pProject; i++)
{
if (r[i] == ‘/’&&r[i + 1] == ‘/’)
{//若为单行注释“//”,则去除注释后面的东西，直至遇到回车换行
while (r[i] != ‘\n’)
{
i++;//向后扫描
}
}
if (r[i] == ‘/’&&r[i + 1] == ‘’)
{//若为多行注释“/ 。。。/”则去除该内容
i += 2;
while (r[i] != '’ || r[i + 1] != ‘/’)
{
i++;//继续扫描
if (r[i] == ‘$’)
{
printf("注释出错，没有找到 /，程序结束！！！\n");
exit(0);
}
}
i += 2;//跨过“/”
}
if (r[i] != ‘\n’&&r[i] != ‘\t’&&r[i] != ‘\v’&&r[i] != ‘\r’)
{//若出现无用字符，则过滤；否则加载
tempString[count++] = r[i];
}
}
tempString[count] = ‘\0’;
strcpy(r, tempString);//产生净化之后的源程序
}
/编译预处理，取出无用的字符和注释**/

/****分析子程序，算法核心/
void Scanner(int &syn, char resourceProject[], char token[], int &pProject)
{//根据DFA的状态转换图设计
int i, count = 0;//count用来做token[]的指示器，收集有用字符
char ch;//作为判断使用
ch = resourceProject[pProject];
while (ch == ’ ')
{//过滤空格，防止程序因识别不了空格而结束
pProject++;
ch = resourceProject[pProject];
}
for (i = 0; i<20; i++)
{//每次收集前先清零
token[i] = ‘\0’;
}
if (IsLetter(resourceProject[pProject]))
{//开头为字母
token[count++] = resourceProject[pProject];//收集
pProject++;//下移
while (IsLetter(resourceProject[pProject]) || IsDigit(resourceProject[pProject]))
{//后跟字母或数字
token[count++] = resourceProject[pProject];//收集
pProject++;//下移
}//多读了一个字符既是下次将要开始的指针位置
token[count] = ‘\0’;
syn = searchReserve(reserveWord, token);//查表找到种别码
if (syn == -1)
{//若不是保留字则是标识符
syn = 100;//标识符种别码
}
return;
}
else if (IsDigit(resourceProject[pProject]))
{//首字符为数字
while (IsDigit(resourceProject[pProject]))
{//后跟数字
token[count++] = resourceProject[pProject];//收集
pProject++;
}//多读了一个字符既是下次将要开始的指针位置
token[count] = ‘\0’;
syn = 99;//常数种别码
}
else if (ch == ‘+’ || ch == ‘-’ || ch == '’ || ch == ‘/’ || ch == ‘;’ || ch == ‘(’ || ch == ‘)’ || ch == ‘^’
|| ch == ‘,’ || ch == ‘"’ || ch == ‘’’ || ch == ‘~’ || ch == ‘#’ || ch == ‘%’ || ch == ‘[’
|| ch == ‘]’ || ch == ‘{’ || ch == ‘}’ || ch == ‘\’ || ch == ‘.’ || ch == ‘?’ || ch == ‘:’)
{//若为运算符或者界符，查表得到结果
token[0] = resourceProject[pProject];
token[1] = ‘\0’;//形成单字符串
for (i = 0; i<36; i++)
{//查运算符界符表
if (strcmp(token, operatorOrDelimiter[i]) == 0)
{
syn = 33 + i;//获得种别码，使用了一点技巧，使之呈线性映射
break;//查到即推出
}
}
pProject++;//指针下移，为下一扫描做准备
return;
}
else if (resourceProject[pProject] == ‘<’)
{//<,<=,<<
pProject++;//后移，超前搜索
if (resourceProject[pProject] == ‘=’)
{
syn = 38;
}
else if (resourceProject[pProject] == ‘<’)
{//左移
pProject–;
syn = 58;
}
else
{
pProject–;
syn = 37;
}
pProject++;//指针下移
return;
}
else if (resourceProject[pProject] == ‘>’)
{//>,>=,>>
pProject++;
if (resourceProject[pProject] == ‘=’)
{
syn = 40;
}
else if (resourceProject[pProject] == ‘>’)
{
syn = 59;
}
else
{
pProject–;
syn = 39;
}
pProject++;
return;
}
else if (resourceProject[pProject] == ‘=’)
{//=.==
pProject++;
if (resourceProject[pProject] == ‘=’)
{
syn = 42;
}
else
{
pProject–;
syn = 41;
}
pProject++;
return;
}
else if (resourceProject[pProject] == ‘!’)
{//!,!=
pProject++;
if (resourceProject[pProject] == ‘=’)
{
syn = 43;
}
else
{
syn = 68;
pProject–;
}
pProject++;
return;
}
else if (resourceProject[pProject] == ‘&’)
{//&,&&
pProject++;
if (resourceProject[pProject] == ‘&’)
{
syn = 53;
}
else
{
pProject–;
syn = 52;
}
pProject++;
return;
}
else if (resourceProject[pProject] == ‘|’)
{//|,||
pProject++;
if (resourceProject[pProject] == ‘|’)
{
syn = 55;
}
else
{
pProject–;
syn = 54;
}
pProject++;
return;
}
else if (resourceProject[pProject] == ‘$’)
{//结束符
syn = 0;//种别码为0
}
else
{//不能被以上词法分析识别，则出错。
printf(“error：there is no exist %c \n”, ch);
exit(0);
}
}

int main()
{
//打开一个文件，读取其中的源程序
char resourceProject[10000];
char token[20] = { 0 };
int syn = -1, i;//初始化
int pProject = 0;//源程序指针
FILE *fp, *fp1;
if ((fp = fopen(“E:\lll.txt”, “r”)) == NULL)
{//打开源程序
cout << “can’t open this file”;
exit(0);
}
resourceProject[pProject] = fgetc(fp);
while (resourceProject[pProject] != ‘$’)
{//将源程序读入resourceProject[]数组
pProject++;
resourceProject[pProject] = fgetc(fp);
}
resourceProject[++pProject] = ‘\0’;
fclose(fp);
cout << endl << “源程序为:” << endl;
cout << resourceProject << endl;
//对源程序进行过滤
filterResource(resourceProject, pProject);
cout << endl << “过滤之后的程序:” << endl;
cout << resourceProject << endl;
pProject = 0;//从头开始读

	     if ((fp1 = fopen("E:\\mmm.txt", "w+")) == NULL)
	     {//打开源程序
	         cout << "can't open this file";
	         exit(0);
	     }
 while (syn != 0)
	     {
	        //启动扫描
		         Scanner(syn, resourceProject, token, pProject);
	       if (syn == 100)
         {//标识符
	             for (i = 0; i<1000; i++)
	             {//插入标识符表中
		                if (strcmp(IDentifierTbl[i], token) == 0)
				                 {//已在表中
				                     break;
				                 }
			               if (strcmp(IDentifierTbl[i], "") == 0)
				                {//查找空间
				                     strcpy(IDentifierTbl[i], token);
				                     break;
				                }
			            }
		          printf("(标识符  ,%s)\n", token);
		            fprintf(fp1, "(标识符   ,%s)\n", token);
		         }
	         else if (syn >= 1 && syn <= 32)
		         {//保留字
		             printf("(保留字   ,  %s)\n", reserveWord[syn - 1]);
		             fprintf(fp1, "(保留字   ,  %s)\n", reserveWord[syn - 1]);
		         }
	         else if (syn == 99)
		         {//const 常数
		             printf("(常数   ,   %s)\n", token);
		             fprintf(fp1, "(常数   ,   %s)\n", token);
		       }
	         else if (syn >= 33 && syn <= 43)
	         {
		             printf("(运算符   ,   %s)\n", operatorOrDelimiter[syn - 33]);
		             fprintf(fp1, "(运算符   ,   %s)\n", operatorOrDelimiter[syn - 33]);
		         }
			 else if (syn >= 44 && syn <= 68)
			 {
				 printf("(界符   ,   %s)\n", operatorOrDelimiter[syn - 33]);
				 fprintf(fp1, "(界符   ,   %s)\n", operatorOrDelimiter[syn - 33]);
			 }
	    }
     /*for (i = 0; i<100; i++)
	     {//插入标识符表中
		 if(IDentifierTbl[i]!=""){
	         printf("第%d个标识符：  %s\n", i + 1, IDentifierTbl[i]);
	         fprintf(fp1, "第%d个标识符：  %s\n", i + 1, IDentifierTbl[i]);
			 }
	     }*/
     fclose(fp1);
	 system("pause");
     return 0;
 }

##大家如果觉得有用的话欢迎点赞、评论、转载呦！！谢谢。