root/maint/gnulib/tests/uniconv/test-u32-strconv-from-enc.c

/* */

DEFINITIONS

1. main

   1 /* Test of conversion to UTF-32 from legacy encodings.
   2    Copyright (C) 2007-2021 Free Software Foundation, Inc.
   3 
   4    This program is free software: you can redistribute it and/or modify
   5    it under the terms of the GNU General Public License as published by
   6    the Free Software Foundation; either version 3 of the License, or
   7    (at your option) any later version.
   8 
   9    This program is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12    GNU General Public License for more details.
  13 
  14    You should have received a copy of the GNU General Public License
  15    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  16 
  17 /* Written by Bruno Haible <bruno@clisp.org>, 2007.  */
  18 
  19 #include <config.h>
  20 
  21 #include "uniconv.h"
  22 
  23 #include <stdlib.h>
  24 
  25 #include "unistr.h"
  26 #include "macros.h"
  27 extern int iconv_supports_encoding (const char *encoding);
  28 
  29 int
  30 main ()
     /*  */
  31 {
  32 #if HAVE_ICONV
  33   static enum iconv_ilseq_handler handlers[] =
  34     { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
  35   size_t h;
  36 
  37   /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
  38      ISO-8859-2, and UTF-8.  */
  39 
  40   /* Test conversion from ISO-8859-1 to UTF-16 with no errors.  */
  41   for (h = 0; h < SIZEOF (handlers); h++)
  42     {
  43       enum iconv_ilseq_handler handler = handlers[h];
  44       static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
  45       static const uint32_t expected[] = /* Ärger mit bösen Bübchen ohne Augenmaß */
  46         {
  47           0xC4, 'r', 'g', 'e', 'r', ' ', 'm', 'i', 't', ' ', 'b', 0xF6, 's',
  48           'e', 'n', ' ', 'B', 0xFC, 'b', 'c', 'h', 'e', 'n', ' ', 'o', 'h',
  49           'n', 'e', ' ', 'A', 'u', 'g', 'e', 'n', 'm', 'a', 0xDF, 0
  50         };
  51       uint32_t *result = u32_strconv_from_encoding (input, "ISO-8859-1", handler);
  52       ASSERT (result != NULL);
  53       ASSERT (u32_strcmp (result, expected) == 0);
  54       free (result);
  55     }
  56 
  57   /* Test conversion from ISO-8859-2 to UTF-16 with no errors.  */
  58   for (h = 0; h < SIZEOF (handlers); h++)
  59     {
  60       enum iconv_ilseq_handler handler = handlers[h];
  61       static const char input[] = "Rafa\263 Maszkowski"; /* Rafał Maszkowski */
  62       static const uint32_t expected[] =
  63         {
  64           'R', 'a', 'f', 'a', 0x0142, ' ', 'M', 'a', 's', 'z', 'k', 'o', 'w',
  65           's', 'k', 'i', 0
  66         };
  67       uint32_t *result = u32_strconv_from_encoding (input, "ISO-8859-2", handler);
  68       ASSERT (result != NULL);
  69       ASSERT (u32_strcmp (result, expected) == 0);
  70       free (result);
  71     }
  72 
  73   /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2.  */
  74 # if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__ || defined __sun)
  75   if (iconv_supports_encoding ("ISO-2022-JP-2"))
  76     {
  77       /* Test conversions from autodetect_jp to UTF-16.  */
  78       for (h = 0; h < SIZEOF (handlers); h++)
  79         {
  80           enum iconv_ilseq_handler handler = handlers[h];
  81           static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* こんにちは in EUC-JP */
  82           static const uint32_t expected[] = /* こんにちは */
  83             {
  84               0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
  85             };
  86           uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
  87           ASSERT (result != NULL);
  88           ASSERT (u32_strcmp (result, expected) == 0);
  89           free (result);
  90         }
  91       for (h = 0; h < SIZEOF (handlers); h++)
  92         {
  93           enum iconv_ilseq_handler handler = handlers[h];
  94           static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* こんにちは in Shift_JIS */
  95           static const uint32_t expected[] = /* こんにちは */
  96             {
  97               0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
  98             };
  99           uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
 100           ASSERT (result != NULL);
 101           ASSERT (u32_strcmp (result, expected) == 0);
 102           free (result);
 103         }
 104       for (h = 0; h < SIZEOF (handlers); h++)
 105         {
 106           enum iconv_ilseq_handler handler = handlers[h];
 107           static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* こんにちは in ISO-2022-JP-2 */
 108           static const uint32_t expected[] = /* こんにちは */
 109             {
 110               0x3053, 0x3093, 0x306B, 0x3061, 0x306F, 0
 111             };
 112           uint32_t *result = u32_strconv_from_encoding (input, "autodetect_jp", handler);
 113           ASSERT (result != NULL);
 114           ASSERT (u32_strcmp (result, expected) == 0);
 115           free (result);
 116         }
 117     }
 118 # endif
 119 
 120 #endif
 121 
 122   return 0;
 123 }

/* */