about summary refs log tree commit diff
path: root/iconv/gconv_charset.h
blob: b39b09aea1d2906d8b68c73f0bc02f5fd3e8d088 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
/* Charset name normalization.
   Copyright (C) 2001-2020 Free Software Foundation, Inc.
   This file is part of the GNU C Library.
   Contributed by Ulrich Drepper <drepper@cygnus.com>, 2001.

   The GNU C Library is free software; you can redistribute it and/or
   modify it under the terms of the GNU Lesser General Public
   License as published by the Free Software Foundation; either
   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public
   License along with the GNU C Library; if not, see
   <https://www.gnu.org/licenses/>.  */

#include <ctype.h>
#include <locale.h>
#include <stdbool.h>
#include <string.h>
#include <sys/stat.h>
#include <stdlib.h>
#include "gconv_int.h"


/* An iconv encoding is in the form of a triplet, with parts separated by
   a '/' character.  The first part is the standard name, the second part is
   the character set, and the third part is the error handler.  If the first
   part is sufficient to identify both the standard and the character set
   then the second part can be empty e.g. UTF-8//.  If the first part is not
   sufficient to identify both the standard and the character set then the
   second part is required e.g. ISO-10646/UTF8/.  If neither the first or
   second parts are provided e.g. //, then the current locale is used.
   The actual values used in the first and second parts are not entirely
   relevant to the implementation.  The values themselves are used in a hash
   table to lookup modules and so the naming convention of the first two parts
   is somewhat arbitrary and only helps locate the entries in the cache.
   The third part is the error handler and is comprised of a ',' or '/'
   separated list of suffixes.  Currently, we support "TRANSLIT" for
   transliteration and "IGNORE" for ignoring conversion errors due to
   unrecognized input characters.  */
#define GCONV_TRIPLE_SEPARATOR "/"
#define GCONV_SUFFIX_SEPARATOR ","
#define GCONV_TRANSLIT_SUFFIX "TRANSLIT"
#define GCONV_IGNORE_ERRORS_SUFFIX "IGNORE"


/* This function accepts the charset names of the source and destination of the
   conversion and populates *conv_spec with an equivalent conversion
   specification that may later be used by __gconv_open.  The charset names
   might contain options in the form of suffixes that alter the conversion,
   e.g. "ISO-10646/UTF-8/TRANSLIT".  It processes the charset names, ignoring
   and truncating any suffix options in fromcode, and processing and truncating
   any suffix options in tocode.  Supported suffix options ("TRANSLIT" or
   "IGNORE") when found in tocode lead to the corresponding flag in *conv_spec
   to be set to true.  Unrecognized suffix options are silently discarded.  If
   the function succeeds, it returns conv_spec back to the caller.  It returns
   NULL upon failure.  */
struct gconv_spec *
__gconv_create_spec (struct gconv_spec *conv_spec, const char *fromcode,
                     const char *tocode);
libc_hidden_proto (__gconv_create_spec)


/* This function frees all heap memory allocated by __gconv_create_spec.  */
static void __attribute__ ((unused))
gconv_destroy_spec (struct gconv_spec *conv_spec)
{
  free (conv_spec->fromcode);
  free (conv_spec->tocode);
  return;
}


/* This function copies in-order, characters from the source 's' that are
   either alpha-numeric or one in one of these: "_-.,:/" - into the destination
   'wp' while dropping all other characters.  In the process, it converts all
   alphabetical characters to upper case.  It then appends up to two '/'
   characters so that the total number of '/'es in the destination is 2.  */
static inline void __attribute__ ((unused, always_inline))
strip (char *wp, const char *s)
{
  int slash_count = 0;

  while (*s != '\0')
    {
      if (__isalnum_l (*s, _nl_C_locobj_ptr)
	  || *s == '_' || *s == '-' || *s == '.' || *s == ',' || *s == ':')
	*wp++ = __toupper_l (*s, _nl_C_locobj_ptr);
      else if (*s == '/')
	{
	  if (++slash_count == 3)
	    break;
	  *wp++ = '/';
	}
      ++s;
    }

  while (slash_count++ < 2)
    *wp++ = '/';

  *wp = '\0';
}


static inline char * __attribute__ ((unused, always_inline))
upstr (char *dst, const char *str)
{
  char *cp = dst;
  while ((*cp++ = __toupper_l (*str++, _nl_C_locobj_ptr)) != '\0')
    /* nothing */;
  return dst;
}