lib/glob/xmbsrtowcs.c

   1 /* xmbsrtowcs.c -- replacement function for mbsrtowcs */
   2
   3 /* Copyright (C) 2002-2004 Free Software Foundation, Inc.
   4
   5    This file is part of GNU Bash, the Bourne Again SHell.
   6
   7    Bash is free software; you can redistribute it and/or modify it under
   8    the terms of the GNU General Public License as published by the Free
   9    Software Foundation; either version 2, or (at your option) any later
  10    version.
  11
  12    Bash is distributed in the hope that it will be useful, but WITHOUT ANY
  13    WARRANTY; without even the implied warranty of MERCHANTABILITY or
  14    FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
  15    for more details.
  16
  17    You should have received a copy of the GNU General Public License along
  18    with Bash; see the file COPYING.  If not, write to the Free Software
  19    Foundation, 59 Temple Place, Suite 330, Boston, MA 02111 USA. */
  20 #include <config.h>
  21
  22 #include <bashansi.h>
  23
  24 /* <wchar.h>, <wctype.h> and <stdlib.h> are included in "shmbutil.h".
  25    If <wchar.h>, <wctype.h>, mbsrtowcs(), exist, HANDLE_MULTIBYTE
  26    is defined as 1. */
  27 #include <shmbutil.h>
  28
  29 #if HANDLE_MULTIBYTE
  30 /* On some locales (ex. ja_JP.sjis), mbsrtowc doesn't convert 0x5c to U<0x5c>.
  31    So, this function is made for converting 0x5c to U<0x5c>. */
  32
  33 static mbstate_t local_state;
  34 static int local_state_use = 0;
  35
  36 size_t
  37 xmbsrtowcs (dest, src, len, pstate)
  38     wchar_t *dest;
  39     const char **src;
  40     size_t len;
  41     mbstate_t *pstate;
  42 {
  43   mbstate_t *ps;
  44   size_t mblength, wclength, n;
  45
  46   ps = pstate;
  47   if (pstate == NULL)
  48     {
  49       if (!local_state_use)
  50         {
  51           memset (&local_state, '\0', sizeof(mbstate_t));
  52           local_state_use = 1;
  53         }
  54       ps = &local_state;
  55     }
  56
  57   n = strlen (*src);
  58
  59   if (dest == NULL)
  60     {
  61       wchar_t *wsbuf;
  62       const char *mbs;
  63       mbstate_t psbuf;
  64
  65       /* It doesn't matter if malloc fails here, since mbsrtowcs should do
  66          the right thing with a NULL first argument. */
  67       wsbuf = (wchar_t *) malloc ((n + 1) * sizeof(wchar_t));
  68       mbs = *src;
  69       psbuf = *ps;
  70
  71       wclength = mbsrtowcs (wsbuf, &mbs, n, &psbuf);
  72
  73       if (wsbuf)
  74         free (wsbuf);
  75       return wclength;
  76     }
  77
  78   for (wclength = 0; wclength < len; wclength++, dest++)
  79     {
  80       if (mbsinit(ps))
  81         {
  82           if (**src == '\0')
  83             {
  84               *dest = L'\0';
  85               *src = NULL;
  86               return (wclength);
  87             }
  88           else if (**src == '\\')
  89             {
  90               *dest = L'\\';
  91               mblength = 1;
  92             }
  93           else
  94             mblength = mbrtowc(dest, *src, n, ps);
  95         }
  96       else
  97         mblength = mbrtowc(dest, *src, n, ps);
  98
  99       /* Cannot convert multibyte character to wide character. */
 100       if (mblength == (size_t)-1 || mblength == (size_t)-2)
 101         return (size_t)-1;
 102
 103       *src += mblength;
 104       n -= mblength;
 105
 106       /* The multibyte string  has  been  completely  converted,
 107          including  the terminating '\0'. */
 108       if (*dest == L'\0')
 109         {
 110           *src = NULL;
 111           break;
 112         }
 113     }
 114
 115     return (wclength);
 116 }
 117
 118 /* Convert a multibyte string to a wide character string. Memory for the
 119    new wide character string is obtained with malloc.
 120
 121    The return value is the length of the wide character string. Returns a
 122    pointer to the wide character string in DESTP. If INDICESP is not NULL,
 123    INDICESP stores the pointer to the pointer array. Each pointer is to
 124    the first byte of each multibyte character. Memory for the pointer array
 125    is obtained with malloc, too.
 126    If conversion is failed, the return value is (size_t)-1 and the values
 127    of DESTP and INDICESP are NULL. */
 128
 129 #define WSBUF_INC 32
 130
 131 size_t
 132 xdupmbstowcs (destp, indicesp, src)
 133     wchar_t **destp;    /* Store the pointer to the wide character string */
 134     char ***indicesp;   /* Store the pointer to the pointer array. */
 135     const char *src;    /* Multibyte character string */
 136 {
 137   const char *p;        /* Conversion start position of src */
 138   wchar_t wc;           /* Created wide character by conversion */
 139   wchar_t *wsbuf;       /* Buffer for wide characters. */
 140   char **indices;       /* Buffer for indices. */
 141   size_t wsbuf_size;    /* Size of WSBUF */
 142   size_t wcnum;         /* Number of wide characters in WSBUF */
 143   mbstate_t state;      /* Conversion State */
 144
 145   /* In case SRC or DESP is NULL, conversion doesn't take place. */
 146   if (src == NULL || destp == NULL)
 147     {
 148       if (destp)
 149         *destp = NULL;
 150       return (size_t)-1;
 151     }
 152
 153   memset (&state, '\0', sizeof(mbstate_t));
 154   wsbuf_size = WSBUF_INC;
 155
 156   wsbuf = (wchar_t *) malloc (wsbuf_size * sizeof(wchar_t));
 157   if (wsbuf == NULL)
 158     {
 159       *destp = NULL;
 160       return (size_t)-1;
 161     }
 162
 163   indices = (char **) malloc (wsbuf_size * sizeof(char *));
 164   if (indices == NULL)
 165     {
 166       free (wsbuf);
 167       *destp = NULL;
 168       return (size_t)-1;
 169     }
 170
 171   p = src;
 172   wcnum = 0;
 173   do
 174     {
 175       size_t mblength;  /* Byte length of one multibyte character. */
 176
 177       if (mbsinit (&state))
 178         {
 179           if (*p == '\0')
 180             {
 181               wc = L'\0';
 182               mblength = 1;
 183             }
 184           else if (*p == '\\')
 185             {
 186               wc = L'\\';
 187               mblength = 1;
 188             }
 189           else
 190             mblength = mbrtowc(&wc, p, MB_LEN_MAX, &state);
 191         }
 192       else
 193         mblength = mbrtowc(&wc, p, MB_LEN_MAX, &state);
 194
 195       /* Conversion failed. */
 196       if (MB_INVALIDCH (mblength))
 197         {
 198           free (wsbuf);
 199           free (indices);
 200           *destp = NULL;
 201           return (size_t)-1;
 202         }
 203
 204       ++wcnum;
 205
 206       /* Resize buffers when they are not large enough. */
 207       if (wsbuf_size < wcnum)
 208         {
 209           wchar_t *wstmp;
 210           char **idxtmp;
 211
 212           wsbuf_size += WSBUF_INC;
 213
 214           wstmp = (wchar_t *) realloc (wsbuf, wsbuf_size * sizeof (wchar_t));
 215           if (wstmp == NULL)
 216             {
 217               free (wsbuf);
 218               free (indices);
 219               *destp = NULL;
 220               return (size_t)-1;
 221             }
 222           wsbuf = wstmp;
 223
 224           idxtmp = (char **) realloc (indices, wsbuf_size * sizeof (char **));
 225           if (idxtmp == NULL)
 226             {
 227               free (wsbuf);
 228               free (indices);
 229               *destp = NULL;
 230               return (size_t)-1;
 231             }
 232           indices = idxtmp;
 233         }
 234
 235       wsbuf[wcnum - 1] = wc;
 236       indices[wcnum - 1] = (char *)p;
 237       p += mblength;
 238     }
 239   while (MB_NULLWCH (wc) == 0);
 240
 241   /* Return the length of the wide character string, not including `\0'. */
 242   *destp = wsbuf;
 243   if (indicesp != NULL)
 244     *indicesp = indices;
 245   else
 246     free (indices);
 247
 248   return (wcnum - 1);
 249 }
 250
 251 #endif /* HANDLE_MULTIBYTE */