关闭

修改源代码,让Lua支持中文,中英混合变量名

标签: luatokenstringbufferwarningsconcatenation
6801人阅读 评论(11) 收藏 举报

/*
** 作者:苏晓  时间:2006年5月24日
** 若有转载请注明出处,谢谢!
*/

Lua脚本的执行效率是相当高的,源文件用纯C写成相当小巧,其可扩展性相当强,前途一片光明。
其源文件写得不复杂,相当值得一读。
作为中国人,在编程语言的使用上如果能够使用中文作为变量名是非常好的一件事。但是标准的Lua并不支持中文变量名。虽然可以在字符串中处理中文。
其实只要修改少量代码就可以让Lua支持中文变量名。

打开lua的源文件文件夹(包)可以从文件名知道,llex.h,llex.c是用来做文件语法分析的。
备份llex.c为llex_old.c
打开llex.c进行修改如下:

/*
 ** $Id: llex.c,v 1.119 2003/03/24 12:39:34 roberto Exp $
 ** Lexical Analyzer
 ** See Copyright Notice in lua.h
 */


#include <ctype.h>
#include <string.h>

#define llex_c

#include "lua.h"

#include "ldo.h"
#include "llex.h"
#include "lobject.h"
#include "lparser.h"
#include "lstate.h"
#include "lstring.h"
#include "lzio.h"



#define next(LS) (LS->current = zgetc(LS->z))



/* ORDER RESERVED */
static const char *const token2string[] =
{
  "and", "break", "do", "else", "elseif", "end", "false", "for", "function",
    "if", "in", "local", "nil", "not", "or", "repeat", "return", "then", "true",
    "until", "while", "*name", "..", "...", "==", ">=", "<=", "~=", "*number",
    "*string", "<eof>"
};


void luaX_init(lua_State *L)
{
  int i;
  for (i = 0; i < NUM_RESERVED; i++)
  {
    TString *ts = luaS_new(L, token2string[i]);
    luaS_fix(ts); /* reserved words are never collected */
    lua_assert(strlen(token2string[i]) + 1 <= TOKEN_LEN);
    ts->tsv.reserved = cast(lu_byte, i + 1); /* reserved word */
  }
}


#define MAXSRC          80


void luaX_checklimit(LexState *ls, int val, int limit, const char *msg)
{
  if (val > limit)
  {
    msg = luaO_pushfstring(ls->L, "too many %s (limit=%d)", msg, limit);
    luaX_syntaxerror(ls, msg);
  }
}


void luaX_errorline(LexState *ls, const char *s, const char *token, int line)
{
  lua_State *L = ls->L;
  char buff[MAXSRC];
  luaO_chunkid(buff, getstr(ls->source), MAXSRC);
  luaO_pushfstring(L, "%s:%d: %s near `%s'", buff, line, s, token);
  luaD_throw(L, LUA_ERRSYNTAX);
}


static void luaX_error(LexState *ls, const char *s, const char *token)
{
  luaX_errorline(ls, s, token, ls->linenumber);
}


void luaX_syntaxerror(LexState *ls, const char *msg)
{
  const char *lasttoken;
  switch (ls->t.token)
  {
    case TK_NAME:
      lasttoken = getstr(ls->t.seminfo.ts);
      break;
    case TK_STRING:
    case TK_NUMBER:
      lasttoken = luaZ_buffer(ls->buff);
      break;
    default:
      lasttoken = luaX_token2str(ls, ls->t.token);
      break;
  }
  luaX_error(ls, msg, lasttoken);
}


const char *luaX_token2str(LexState *ls, int token)
{
  if (token < FIRST_RESERVED)
  {
    lua_assert(token == (unsigned char)token);
    return luaO_pushfstring(ls->L, "%c", token);
  }
  else
    return token2string[token - FIRST_RESERVED];
}


static void luaX_lexerror(LexState *ls, const char *s, int token)
{
  if (token == TK_EOS)
    luaX_error(ls, s, luaX_token2str(ls, token));
  else
    luaX_error(ls, s, luaZ_buffer(ls->buff));
}


static void inclinenumber(LexState *LS)
{
  next(LS); /* skip `/n' */
  ++LS->linenumber;
  luaX_checklimit(LS, LS->linenumber, MAX_INT, "lines in a chunk");
}


void luaX_setinput(lua_State *L, LexState *LS, ZIO *z, TString *source)
{
  LS->L = L;
  LS->lookahead.token = TK_EOS; /* no look-ahead token */
  LS->z = z;
  LS->fs = NULL;
  LS->linenumber = 1;
  LS->lastline = 1;
  LS->source = source;
  next(LS); /* read first char */
  if (LS->current == '#')
  {
    do
    {
       /* skip first line */
      next(LS);
    }
    while (LS->current != '/n' && LS->current != EOZ);
  }
}



/*
 ** =======================================================
 ** LEXICAL ANALYZER
 ** =======================================================
 */


/* use buffer to store names, literal strings and numbers */

/* extra space to allocate when growing buffer */
#define EXTRABUFF	32

/* maximum number of chars that can be read without checking buffer size */
#define MAXNOCHECK	5

#define checkbuffer(LS, len)	/
if (((len)+MAXNOCHECK)*sizeof(char) > luaZ_sizebuffer((LS)->buff)) /
luaZ_openspace((LS)->L, (LS)->buff, (len)+EXTRABUFF)

#define save(LS, c, l) /
(luaZ_buffer((LS)->buff)[l++] = cast(char, c))
#define save_and_next(LS, l)  (save(LS, LS->current, l), next(LS))

/*readname 是原来用来读入变量名称的。可以注释掉*/
static size_t readname(LexState *LS)
{
  size_t l = 0;
  checkbuffer(LS, l);
  do
  {
    checkbuffer(LS, l);
    save_and_next(LS, l);
  }
  while (isalnum(LS->current) || LS->current == '_');
  save(LS, '/0', l)
    ;
  return l - 1;
}

/*开始添加支持中英文变量名*/
/*因为LS->current是int类型!*/

static int isChineseCode(int charint)
{
  return (charint > 0x80);
};
/*如果要求速度用(LS->current>0x80)替换掉isChineseCode函数调用更好*/
static size_t readChinesename(LexState *LS)
{
  size_t l = 0;
  checkbuffer(LS, l);
  do
  {
    if (isChineseCode(LS->current))
    {
      checkbuffer(LS, l);
      save_and_next(LS, l);
      checkbuffer(LS, l);
      save_and_next(LS, l); //处理了一个中文字符
    }
    else
    {
      checkbuffer(LS, l);
      save_and_next(LS, l); //处理英文字符或者下划线
    };
  }
  while (isChineseCode(LS->current) || LS->current == '_' || isalnum(LS
    ->current));
  save(LS, '/0', l)
    ;
  return l - 1;
};


/* LUA_NUMBER */
static void read_numeral(LexState *LS, int comma, SemInfo *seminfo)
{
  size_t l = 0;
  checkbuffer(LS, l);
  if (comma)
    save(LS, '.', l);
  while (isdigit(LS->current))
  {
    checkbuffer(LS, l);
    save_and_next(LS, l);
  }
  if (LS->current == '.')
  {
    save_and_next(LS, l);
    if (LS->current == '.')
    {
      save_and_next(LS, l);
      save(LS, '/0', l);
      luaX_lexerror(LS,
        "ambiguous syntax (decimal point x string concatenation)", TK_NUMBER);
    }
  }
  while (isdigit(LS->current))
  {
    checkbuffer(LS, l);
    save_and_next(LS, l);
  }
  if (LS->current == 'e' || LS->current == 'E')
  {
    save_and_next(LS, l); /* read `E' */
    if (LS->current == '+' || LS->current == '-')
      save_and_next(LS, l);
     /* optional exponent sign */
    while (isdigit(LS->current))
    {
      checkbuffer(LS, l);
      save_and_next(LS, l);
    }
  }
  save(LS, '/0', l);
  if (!luaO_str2d(luaZ_buffer(LS->buff), &seminfo->r))
    luaX_lexerror(LS, "malformed number", TK_NUMBER);
}


static void read_long_string(LexState *LS, SemInfo *seminfo)
{
  int cont = 0;
  size_t l = 0;
  checkbuffer(LS, l);
  save(LS, '[', l); /* save first `[' */
  save_and_next(LS, l); /* pass the second `[' */
  if (LS->current == '/n')
   /* string starts with a newline? */
    inclinenumber(LS);
   /* skip it */
  for (;;)
  {
    checkbuffer(LS, l);
    switch (LS->current)
    {
      case EOZ:
        save(LS, '/0', l);
        luaX_lexerror(LS, (seminfo) ? "unfinished long string" :
          "unfinished long comment", TK_EOS);
        break; /* to avoid warnings */
      case '[':
        save_and_next(LS, l);
        if (LS->current == '[')
        {
          cont++;
          save_and_next(LS, l);
        }
        continue;
      case ']':
        save_and_next(LS, l);
        if (LS->current == ']')
        {
          if (cont == 0)
            goto endloop;
          cont--;
          save_and_next(LS, l);
        }
        continue;
      case '/n':
        save(LS, '/n', l);
        inclinenumber(LS);
        if (!seminfo)
          l = 0;
         /* reset buffer to avoid wasting space */
        continue;
      default:
        save_and_next(LS, l);
    }
  }
  endloop: save_and_next(LS, l); /* skip the second `]' */
  save(LS, '/0', l);
  if (seminfo)
    seminfo->ts = luaS_newlstr(LS->L, luaZ_buffer(LS->buff) + 2, l - 5);
}


static void read_string(LexState *LS, int del, SemInfo *seminfo)
{
  size_t l = 0;
  checkbuffer(LS, l);
  save_and_next(LS, l);
  while (LS->current != del)
  {
    checkbuffer(LS, l);
    switch (LS->current)
    {
      case EOZ:
        save(LS, '/0', l);
        luaX_lexerror(LS, "unfinished string", TK_EOS);
        break; /* to avoid warnings */
      case '/n':
        save(LS, '/0', l);
        luaX_lexerror(LS, "unfinished string", TK_STRING);
        break; /* to avoid warnings */
      case '//':
        next(LS); /* do not save the `/' */
        switch (LS->current)
        {
        case 'a':
          save(LS, '/a', l);
          next(LS);
          break;
        case 'b':
          save(LS, '/b', l);
          next(LS);
          break;
        case 'f':
          save(LS, '/f', l);
          next(LS);
          break;
        case 'n':
          save(LS, '/n', l);
          next(LS);
          break;
        case 'r':
          save(LS, '/r', l);
          next(LS);
          break;
        case 't':
          save(LS, '/t', l);
          next(LS);
          break;
        case 'v':
          save(LS, '/v', l);
          next(LS);
          break;
        case '/n':
          save(LS, '/n', l);
          inclinenumber(LS);
          break;
        case EOZ:
          break; /* will raise an error next loop */
        default:
          {
            if (!isdigit(LS->current))
              save_and_next(LS, l);
             /* handles //, /", /', and /? */
            else
            {
               /* /xxx */
              int c = 0;
              int i = 0;
              do
              {
                c = 10 * c + (LS->current - '0');
                next(LS);
              }
              while (++i < 3 && isdigit(LS->current));
              if (c > UCHAR_MAX)
              {
                save(LS, '/0', l);
                luaX_lexerror(LS, "escape sequence too large", TK_STRING);
              }
              save(LS, c, l);
            }
          }
        }
        break;
      default:
        save_and_next(LS, l);
    }
  }
  save_and_next(LS, l); /* skip delimiter */
  save(LS, '/0', l);
  seminfo->ts = luaS_newlstr(LS->L, luaZ_buffer(LS->buff) + 1, l - 3);
}


int luaX_lex(LexState *LS, SemInfo *seminfo)
{
  for (;;)
  {
    switch (LS->current)
    {

      case '/n':
        {
          inclinenumber(LS);
          continue;
        }
      case '-':
        {
          next(LS);
          if (LS->current != '-')
            return '-';
          /* else is a comment */
          next(LS);
          if (LS->current == '[' && (next(LS), LS->current == '['))
            read_long_string(LS, NULL);
           /* long comment */
          else
           /* short comment */
            while (LS->current != '/n' && LS->current != EOZ)
              next(LS);
          continue;
        }
      case '[':
        {
          next(LS);
          if (LS->current != '[')
            return '[';
          else
          {
            read_long_string(LS, seminfo);
            return TK_STRING;
          }
        }
      case '=':
        {
          next(LS);
          if (LS->current != '=')
            return '=';
          else
          {
            next(LS);
            return TK_EQ;
          }
        }
      case '<':
        {
          next(LS);
          if (LS->current != '=')
            return '<';
          else
          {
            next(LS);
            return TK_LE;
          }
        }
      case '>':
        {
          next(LS);
          if (LS->current != '=')
            return '>';
          else
          {
            next(LS);
            return TK_GE;
          }
        }
      case '~':
        {
          next(LS);
          if (LS->current != '=')
            return '~';
          else
          {
            next(LS);
            return TK_NE;
          }
        }
      case '"':
      case '/'':
        {
          read_string(LS, LS->current, seminfo);
          return TK_STRING;
        }
      case '.':
        {
          next(LS);
          if (LS->current == '.')
          {
            next(LS);
            if (LS->current == '.')
            {
              next(LS);
              return TK_DOTS; /* ... */
            }
            else
              return TK_CONCAT;
             /* .. */
          }
          else if (!isdigit(LS->current))
            return '.';
          else
          {
            read_numeral(LS, 1, seminfo);
            return TK_NUMBER;
          }
        }
      case EOZ:
        {
          return TK_EOS;
        }
      default:
        {
          if (isspace(LS->current))
          {
            next(LS);
            continue;
          }
          else if (isdigit(LS->current))
          {
            read_numeral(LS, 0, seminfo);
            return TK_NUMBER;
          }
          /*修改这里支持中英文变量名*/
          else if (isalpha(LS->current) || LS->current == '_' || isChineseCode
            (LS->current))
          {
            /* identifier or reserved word */
            size_t l = readChinesename(LS);
            TString *ts = luaS_newlstr(LS->L, luaZ_buffer(LS->buff), l);
            if (ts->tsv.reserved > 0)
             /* reserved word? */
              return ts->tsv.reserved - 1+FIRST_RESERVED;
            seminfo->ts = ts;
            return TK_NAME;
          }
          else
          {
            int c = LS->current;
            if (iscntrl(c))
              luaX_error(LS, "invalid control char", luaO_pushfstring(LS->L,
                "char(%d)", c));
            next(LS);
            return c; /* single-char tokens (+ - / ...) */
          }
        }
    }
  }
}

#undef next

找到处理变量名的地方,共两处,一处是当一些关键符号处理完毕怎么开始处理变量名,就是luaX_lex函数末尾的地方;一处是如何处理变量名,原本使用函数readname处理。
分别改为自定义的代码。好了就这样。
重新编译,生成的Lua.exe或者其他的东西,都可以支持中文变量名了。
随便写一个:test.lua
我=1
你=2
他=3
all我们haha=4
object={};
object.人="人类";
function 显示(some)
print("一切正常!"..some)
end
print(object.人);
print(你..我..他..all我们haha);
显示(我);
执行lua test.lua就知道好用了。 
0
0

查看评论
* 以上用户言论只代表其个人观点,不代表CSDN网站的观点或立场
    个人资料
    • 访问:127685次
    • 积分:1855
    • 等级:
    • 排名:千里之外
    • 原创:50篇
    • 转载:7篇
    • 译文:0篇
    • 评论:71条
    文章分类
    最新评论