词法分析器代码

前几日，学习了编译原理，写了一个词法分析器，以供自己学习之用，分析器写的有点简陋，有待改进

代码如下：

#include <stdio.h>

#include <string.h>

#include <process.h>

#define MAX 50

void main()

{

FILE *in,*out;/*存放输入字符串和输出单词串的文件*/

char arr[MAX];/*arr数组存放单词符号*/

char currentchar;/*currentchar存放当前输入字符*/

int i=0;/*arr数组的一个指针*/

/*以读方式打开输入文件*/

if((in=fopen("infile.txt","r"))==NULL)

{

printf("can not open file\n");

exit(0);

}

/*以写方式打开输出文件*/

if((out=fopen("outfile.txt","w"))==NULL)

{

printf("cannout open outfile\n");

exit(1);

}

//去掉开头空格

currentchar=fgetc(in);

while(currentchar==' ')

{

currentchar=fgetc(in);

}

int ch;

while(currentchar!='@')

{

/*常数部分判断*/

if((currentchar>='a'&&currentchar<='z')||(currentchar>='A'&&currentchar<='Z')||(currentchar>='0'&&currentchar<='9')||currentchar=='('||currentchar==')'||currentchar=='{'||currentchar=='}'||currentchar=='>'||currentchar=='<'||currentchar==';'||currentchar==':'||currentchar=='+'||currentchar=='-'||currentchar=='*'||currentchar=='/'||currentchar=='='||currentchar=='!'||currentchar=='&'||(ch=currentchar)=='\n'||currentchar==' '||currentchar=='['||currentchar==']')

{

i=0;//清空arr字符数组

if(currentchar>='0'&&currentchar<='9')

{

arr[i++]=currentchar;

currentchar=fgetc(in);//再读入下一个字符

while(currentchar>='0'&&currentchar<='9')

{

arr[i++]=currentchar;

currentchar=fgetc(in);

}

if(currentchar!='.')//如果当前读入的符号不为小数点，则常数读完毕，输出此常数

{

arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",15,'"',arr,'"',")");//格式化输出到目标文件，15代表种别码， arr为内码值，规定用数字本身代表

}

else//当前字符为小数点则继续向下读入

{

arr[i++]=currentchar;

currentchar=fgetc(in);

while(currentchar>='0'&&currentchar<='9')

{

arr[i++]=currentchar;

currentchar=fgetc(in);

}

arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",15,'"',arr,'"',")");

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

}

/*判断标识符和关键字部分*/

if((currentchar>='a'&&currentchar<='z')||(currentchar>='A'&&currentchar<='Z'))

{

i=0;//清空arr字符数组

while((currentchar>='a'&&currentchar<='z')||(currentchar>='0'&&currentchar<='9')||(currentchar>='A'&&currentchar<='Z'))

{

arr[i++]=currentchar;

currentchar=fgetc(in);

}

//把字符数组arr和关键字表比较，判断单词串是关键字还是标识符

arr[i++]='\0';

if(strcmp(arr,"if")==0)

fprintf(out,"%s%d,%c%s%c%s\n","(",0,'"',arr,'"',")");

else if(strcmp(arr,"else")==0)

fprintf(out,"%s%d,%c%s%c%s\n","(",1,'"',arr,'"',")");

else if(strcmp(arr,"while")==0)

fprintf(out,"%s%d,%c%s%c%s\n","(",2,'"',arr,'"',")");

else if(strcmp(arr,"do")==0)

fprintf(out,"%s%d,%c%s%c%s\n","(",3,'"',arr,'"',")");

else

fprintf(out,"%s%d,%c%s%c%s\n","(",14,'"',arr,'"',")");

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

//判断标识符包括：+, -, *, /, (, ), {, }, <, >, ;, :, !=, >=, <=, ==, =.

if(currentchar=='+')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",9,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='-')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",10,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='*')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",11,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='/')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",12,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='=')

{

i=0;

arr[i++]=currentchar;

currentchar=fgetc(in);

if(currentchar=='=')

{

arr[i++]=currentchar;

arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",13,'"',arr,'"',")");

currentchar=fgetc(in);

}

else

{ arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",17,'"',arr,'"',")");

}

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar==';')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",4,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='{')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",5,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='}')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",6,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='[')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",20,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar==']')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",21,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='(')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",7,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar==')')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",8,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar==':')

{

i=0;

arr[i++]=currentchar;

currentchar=fgetc(in);

if(currentchar==':')

{

arr[i++]=currentchar;

arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",18,'"',arr,'"',")");

currentchar=fgetc(in);

}

else

{ arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",16,'"',arr,'"',")");

}

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='>')

{

i=0;

arr[i++]=currentchar;

currentchar=fgetc(in);

if(currentchar=='=')

{

arr[i++]=currentchar;

arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",13,'"',arr,'"',")");

currentchar=fgetc(in);

}

else

{ arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",13,'"',arr,'"',")");

}

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='<')

{

i=0;

arr[i++]=currentchar;

currentchar=fgetc(in);

if(currentchar=='=')

{

arr[i++]=currentchar;

arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",13,'"',arr,'"',")");

currentchar=fgetc(in);

}

else

{ arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",13,'"',arr,'"',")");

}

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='!')

{

i=0;

arr[i++]=currentchar;

currentchar=fgetc(in);

if(currentchar=='=')

{

arr[i++]=currentchar;

arr[i++]='\0';

fprintf(out,"%s%d,%c%s%c%s\n","(",13,'"',arr,'"',")");

currentchar=fgetc(in);

}

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

if(currentchar=='&')

{

fprintf(out,"%s%d,%c%c%c%s\n","(",19,'"',currentchar,'"',")");

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

while((ch=currentchar)=='\n')

{

currentchar=fgetc(in);

}

while(currentchar==' ')

{

currentchar=fgetc(in);

}

}

else

{

fprintf(out,"%s,%c%c%c\n","error",'"',currentchar,'"');

currentchar=fgetc(in);

}

}//结束开头while语句

/*关闭文件退出*/

fclose(in);

fclose(out);

}

注：在程序当前目录里自己建立一个文本文档，取名为infile.txt,所有需要分析的程序都写在此文本文档里，程序的结尾必须以“@”标志符结束。程序结果输出在同目录，文件名为outfile.txt,此文件为自动生成。种别码就不给出了，输的很麻烦哦。拉拉拉

本程序在Win2000server机上，使用Microsoft Visual Studio .NET调试通过。

2004年11月11日

1:02:22