view tests/test-striconv.c @ 8891:633babea5f62

Unconditionally include <config.h> in unit tests. * tests/test-alloca-opt.c: Remove #ifdef HAVE_CONFIG_H. * tests/test-allocsa.c, tests/test-arcfour.c, tests/test-arctwo.c, tests/test-argmatch.c, tests/test-argp.c, tests/test-array_list.c, tests/test-array_oset.c, tests/test-atexit.c, test-avltree_list.c, test-avltree_oset.c, test-avltreehash_list.c, test-base64.c, test-binary-io.c, test-c-ctype.c, test-c-strcasecmp.c, test-c-strcasestr.c, test-c-strncasecmp.c, test-c-strstr.c, test-canonicalize-lgpl.c, test-carray_list.c, test-crc.c, test-des.c, test-dirname.c, test-fflush.c, test-fprintf-posix.c, test-gc-arcfour.c, test-gc-arctwo.c, test-gc-des.c, test-gc-hmac-md5.c, test-gc-hmac-sha1.c, test-gc-md2.c, test-gc-md4.c, test-gc-md5.c, test-gc-pbkdf2-sha1.c, test-gc-rijndael.c, test-gc-sha1.c, test-gc.c, test-getpass.c, test-hmac-md5.c, test-hmac-sha1.c, test-iconv.c, test-linked_list.c, test-linkedhash_list.c, test-lock.c, test-mbscasecmp.c, test-mbscasestr1.c, test-mbscasestr2.c, test-mbscasestr3.c, test-mbscasestr4.c, test-mbschr.c, test-mbscspn.c, test-mbsncasecmp.c, test-mbspbrk.c, test-mbspcasecmp.c, test-mbsrchr.c, test-mbsspn.c, test-mbsstr1.c, test-mbsstr2.c, test-mbsstr3.c, test-md2.c, test-md4.c, test-md5.c, test-memmem.c, test-printf-posix.c, test-rbtree_list.c, test-rbtree_oset.c, test-rbtreehash_list.c, test-read-file.c, test-rijndael.c, test-snprintf-posix.c, test-snprintf.c, test-sprintf-posix.c, test-stdint.c, test-strcasestr.c, test-striconv.c, test-striconveh.c, test-striconveha.c, test-tls.c, test-vasnprintf-posix.c, test-vasnprintf-posix2.c, test-vasnprintf.c, test-vasprintf-posix.c, test-vasprintf.c, test-verify.c, test-vfprintf-posix.c, test-vprintf-posix.c, test-vsnprintf-posix.c, test-vsnprintf.c, test-vsprintf-posix.c, test-xvasprintf.c: Likewise.
author Eric Blake <ebb9@byu.net>
date Mon, 28 May 2007 16:49:41 +0000
parents 1f57552cdb11
children bbbbbf4cd1c5
line wrap: on
line source

/* Test of character set conversion.
   Copyright (C) 2007 Free Software Foundation, Inc.

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 2, or (at your option)
   any later version.

   This program 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 General Public License for more details.

   You should have received a copy of the GNU General Public License
   along with this program; if not, write to the Free Software Foundation,
   Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.  */

/* Written by Bruno Haible <bruno@clisp.org>, 2007.  */

#include <config.h>

#include "striconv.h"

#if HAVE_ICONV
# include <iconv.h>
#endif

#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#define ASSERT(expr) \
  do									     \
    {									     \
      if (!(expr))							     \
        {								     \
          fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
          abort ();							     \
        }								     \
    }									     \
  while (0)

int
main ()
{
#if HAVE_ICONV
  /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
     and UTF-8.  */
  iconv_t cd_88591_to_utf8 = iconv_open ("UTF-8", "ISO-8859-1");
  iconv_t cd_utf8_to_88591 = iconv_open ("ISO-8859-1", "UTF-8");

  ASSERT (cd_88591_to_utf8 != (iconv_t)(-1));
  ASSERT (cd_utf8_to_88591 != (iconv_t)(-1));

  /* ------------------------- Test mem_cd_iconv() ------------------------- */

  /* Test conversion from ISO-8859-1 to UTF-8 with no errors.  */
  {
    static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    char *result = NULL;
    size_t length = 0;
    int retval = mem_cd_iconv (input, strlen (input), cd_88591_to_utf8,
			       &result, &length);
    ASSERT (retval == 0);
    ASSERT (length == strlen (expected));
    ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with no errors.  */
  {
    static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    char *result = NULL;
    size_t length = 0;
    int retval = mem_cd_iconv (input, strlen (input), cd_utf8_to_88591,
			       &result, &length);
    ASSERT (retval == 0);
    ASSERT (length == strlen (expected));
    ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ.  */
  {
    static const char input[] = "\342\202\254"; /* EURO SIGN */
    char *result = NULL;
    size_t length = 0;
    int retval = mem_cd_iconv (input, strlen (input), cd_utf8_to_88591,
			       &result, &length);
    ASSERT (retval == -1 && errno == EILSEQ);
    ASSERT (result == NULL);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL.  */
  {
    static const char input[] = "\342";
    char *result = NULL;
    size_t length = 0;
    int retval = mem_cd_iconv (input, strlen (input), cd_utf8_to_88591,
			       &result, &length);
    ASSERT (retval == 0);
    ASSERT (length == 0);
    if (result != NULL)
      free (result);
  }

  /* ------------------------- Test str_cd_iconv() ------------------------- */

  /* Test conversion from ISO-8859-1 to UTF-8 with no errors.  */
  {
    static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    char *result = str_cd_iconv (input, cd_88591_to_utf8);
    ASSERT (result != NULL);
    ASSERT (strcmp (result, expected) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with no errors.  */
  {
    static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    char *result = str_cd_iconv (input, cd_utf8_to_88591);
    ASSERT (result != NULL);
    ASSERT (strcmp (result, expected) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ.  */
  {
    static const char input[] = "Costs: 27 \342\202\254"; /* EURO SIGN */
    char *result = str_cd_iconv (input, cd_utf8_to_88591);
    ASSERT (result == NULL && errno == EILSEQ);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL.  */
  {
    static const char input[] = "\342";
    char *result = str_cd_iconv (input, cd_utf8_to_88591);
    ASSERT (result != NULL);
    ASSERT (strcmp (result, "") == 0);
    free (result);
  }

  iconv_close (cd_88591_to_utf8);
  iconv_close (cd_utf8_to_88591);

  /* -------------------------- Test str_iconv() -------------------------- */

  /* Test conversion from ISO-8859-1 to UTF-8 with no errors.  */
  {
    static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    char *result = str_iconv (input, "ISO-8859-1", "UTF-8");
    ASSERT (result != NULL);
    ASSERT (strcmp (result, expected) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with no errors.  */
  {
    static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
    static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
    char *result = str_iconv (input, "UTF-8", "ISO-8859-1");
    ASSERT (result != NULL);
    ASSERT (strcmp (result, expected) == 0);
    free (result);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ.  */
  {
    static const char input[] = "Costs: 27 \342\202\254"; /* EURO SIGN */
    char *result = str_iconv (input, "UTF-8", "ISO-8859-1");
    ASSERT (result == NULL && errno == EILSEQ);
  }

  /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL.  */
  {
    static const char input[] = "\342";
    char *result = str_iconv (input, "UTF-8", "ISO-8859-1");
    ASSERT (result != NULL);
    ASSERT (strcmp (result, "") == 0);
    free (result);
  }

#endif

  return 0;
}