君子抉第三天（4月20日）-优快云博客

本文介绍了使用Flex工具实现词法分析器的过程，包括Flex的安装配置、词法单元定义及如何生成词法分析器代码等内容。通过示例代码详细说明了如何识别关键字、标识符等元素。

本来应该在4月20日写的,由于种种原因没有写,今天将它补起来.这是正式的按君子抉中的计划来写博客的第二天,今天搞那个垂直搜索搞了一上午,以前还感觉搞这个有点激情,现在感觉完全是一种累赘,还得写文档,麻烦啊.下午才干了点真正有点意思的东西-----flex.

以前从来没有接触过flex,那次听兴旺说要做一个自动的词法分析器,用flex来实现,研究了半天,最后总算明白了.而且今天我才明白原来编程最痛苦的事不是代码怎么写,而是在哪里编写代码.刚开始在网上搜索了半天,都是讲解flex的程序怎么编写,就是没说,写了在哪里进行编译.最后找了半天,明白了.

先下载flex-2.5.4a-1.exe,然后进行安装,我是安装到了D:\GnuWin32,然后在环境变量的path加上一句: ;D:\GnuWin32\bin

再到DOS命令下进行测试安装好了没有,输入 flex -V 即可.这个是大写V.之后就是编写.l文件.编写好.l文件之后,在DOS命令行下定位到你的.l文件的目录,让后输入flex test.l 回车即可.这里test.l是你的.l文件的文件名.让后在test.l文件的同一目录就会生成一个 lex.yy.c.这个文件就可以在Visual Studio中进行编译了.下面这个是我改写的词法分析器的flex的.l文件的代码.

% {
#include < stdio.h >
#include < stdlib.h >
/* 保留字 */
#include < string .h >
char * key[] = { " " , " 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 " };

int IsKeyWord( char * lex) ; /* 判断字符串是否是保留字 */

void print();                             // 输出token序列；
void main( int argc, char * argv[]);          // 主函数；
struct token{                             // 二元组；
       char * idproperty;     // token属性值；
       char * idname;     // 识别的token名字；
}entity[ 1000 ];      // 定义1000个这样的token，大小可改变；
char * filename;                            // 保存结果的文件名；
int errnum = 0 ;      // 错误token的数目；
int value;      // 属性值int型；
int linenum = 1 ;      // 行数；
int count = 0 ;      // token的个数；
int flag = 0 ;
FILE * fpin;      // 测试文件指针；
FILE * fpout;      // 结果文件指针；
% }
digit         [ 0 - 9 ]
letter        [_a - zA - Z]
number        {digit} +
identifier    {letter}({letter} | {digit}) *
wrongid       ({digit} + ){letter}({letter} | {digit}) *
newline       [\n]
whitespace    [\t] +
allchar             [ ^ 0 ] | 0
string_l            \ " {allchar}?\ "
%%
{string_l}        {value = 6 ;print();}                                             // 字符串常量
{identifier}   {value = IsKeyWord(yytext); print();}   // 标识符---0 关键字---1
{wrongid}   {value = 7 ;print();}                                         // 错误标识符
{number}   {value = 2 ;print();}                                             // 数字常量

" ++ "           |
" -- "           |
" -> "        |
" && "      |
" || "      |
" <= "      |
" == "         |
" != "      |
" >= "      |
" >> "      |
" << "      |
" *= "      |
" /= "      |
" %= "        |
" += "      |
" -= "      |
" &= "      |
" |= "      |
" ^= "                     {value = 4 ;print();}             /* 组合运算符 */
" + "              |
" - "              |
" * "              |
" / "           |
" ! "      |
" % "       |
" & "       |
" | "                    {value = 3 ;print();}                                 /* 基本运算符 */
" , "              |
" ; "              |
" { "              |
" } "              |
" ( "              |
" ) "              |
" . "              |
" # "              |
" ' "               {value = 5 ;print();}                 /* 分界符 */
{newline}   {linenum += 1 ;}
{whitespace}   {;}
" "     {;}
.    {value = 7 ;print();}                  /* 其他不识别 */
%%
int yywrap()
{
    fclose(fpin);
     return 1 ;
}

void print()
{
    count += 1 ;
     if (flag != 1 ){
        if ((fpout = fopen(filename, " a " )) == NULL){
           printf( " 无法打开文件! \n " );
           exit( 0 );
       }
    }
     if (value <= 6 ){
        switch (value){
              case 0 :entity[count - 1 ].idproperty = " 标识符 " ; break ;
              case 1 :entity[count - 1 ].idproperty = " 关键字 " ; break ;
              case 2 :entity[count - 1 ].idproperty = " 数字常量 " ; break ;
              case 3 :entity[count - 1 ].idproperty = " 基本运算符 " ; break ;
              case 4 :entity[count - 1 ].idproperty = " 组合运算符 " ; break ;
              case 5 :entity[count - 1 ].idproperty = " 分界符 " ; break ;
                  case 6 :entity[count - 1 ].idproperty = " 字符串常量 " ; break ;
       }
       entity[count - 1 ].idname = yytext;
       fprintf(fpout, " %d < %s , %s > \n " ,count,entity[count - 1 ].idname,entity[count - 1 ].idproperty);
    } else {
         errnum += 1 ;
          switch (value){
                case 8 :entity[count - 1 ].idproperty = " 错误标识符: " ; break ;
                case 7 :entity[count - 1 ].idproperty = " 不识别: " ; break ;
         }
         entity[count - 1 ].idname = yytext;
         fprintf(fpout, " %d [line:%d]:%s\ " % s\ " \n " ,count,linenum,entity[count - 1 ].idproperty,entity[count - 1 ].idname);
    }
     if (flag != 1 )fclose(fpout);
}
/* 判断字符串是否是保留字 */

/*     如果不是就返回 0 */

int IsKeyWord( char * lex)
{
     int i;
     for ( i = 1 ;i <= 32 ;i ++ )
    {
         if (strcmp(lex,key[i]) == 0 )
             return 1 ;
    }
     return 0 ;
}
void main( int argc, char * argv[])
{
     if (argc == 1 ){
      printf( " please input the C program(ctrl+z to end) \n " );
      flag = 1 ;
      fpin = stdin;
      fpout = stdout;
    }
     if (argc == 2 )argv[ 2 ] = " defresult.txt " ;
    filename = argv[ 2 ];
     if (flag != 1 ){
        if ((fpin = fopen(argv[ 1 ], " r " )) == NULL){
           printf( " cannot open the file \n " );
           exit( 0 );
       }
    }
    yyin = fpin;
    yylex();
     if (flag != 1 ){
        if ((fpout = fopen(filename, " a " )) == NULL){
           printf( " cannot write the file \n " );
           exit( 0 );
       }
    }
    fprintf(fpout, " \n " );
    fprintf(fpout, " %d symbol(s) found. \n %d error(s) found. \n " ,count,errnum);
    fprintf(fpout, " ======================================================================= \n " );
     if (flag != 1 )fclose(fpout);
    yywrap();

}