char *
xstr_iconv (const char *src, const char *from_codeset, const char *to_codeset)
{
char *result = str_iconv (src, from_codeset, to_codeset);
if (result == NULL && errno == ENOMEM)
xalloc_die ();
return result;
}
/**
* stringprep_convert:
* @str: input zero-terminated string.
* @to_codeset: name of destination character set.
* @from_codeset: name of origin character set, as used by @str.
*
* Convert the string from one character set to another using the
* system's iconv() function.
*
* Return value: Returns newly allocated zero-terminated string which
* is @str transcoded into to_codeset.
**/
char *
stringprep_convert (const char *str,
const char *to_codeset, const char *from_codeset)
{
#if HAVE_ICONV
return str_iconv (str, from_codeset, to_codeset);
#else
char *p;
fprintf (stderr, "libidn: warning: libiconv not installed, cannot "
"convert data to UTF-8\n");
p = malloc (strlen (str) + 1);
if (!p)
return NULL;
return strcpy (p, str);
#endif
}
static char *
locale_to_utf8 (char *str)
{
#if HAVE_LANGINFO_CODESET
if (str)
{
char *from = nl_langinfo (CODESET);
char *q = str_iconv (str, from, "UTF-8");
if (!q)
fprintf (stderr, "warning: Could not convert string to UTF-8...\n");
else
{
free (str);
str = q;
}
}
#endif
return str;
}
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);
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;
}
