1
Fork 0
mirror of https://git.savannah.gnu.org/git/guile.git synced 2025-06-14 23:50:19 +02:00

Fix scm_to_utf8_stringn once and for all; optimize; add tests

* libguile/strings.c (scm_to_utf8_stringn): Fix another new bug in this
  recent comedy of errors: pass the size of the preallocated buffer to
  u32_to_u8.  Arrange to call 'scm_i_string_wide_chars' and
  'scm_i_string_length' only once each.  Rename local variables for
  improved code clarity.

* test-suite/standalone/test-conversion.c (test_to_utf8_stringn): New
  function to test scm_to_utf8_stringn.
This commit is contained in:
Mark H Weaver 2012-04-04 18:58:44 -04:00
parent 51853eee69
commit bbb9f000ad
2 changed files with 80 additions and 11 deletions

View file

@ -1929,28 +1929,28 @@ scm_to_utf8_stringn (SCM str, size_t *lenp)
NULL, lenp);
else
{
scm_t_uint32 *chars = (scm_t_uint32 *) scm_i_string_wide_chars (str);
scm_t_uint8 *buf, *ret;
size_t predicted_len, actual_len; /* length in bytes */
size_t num_chars = scm_i_string_length (str);
size_t num_bytes_predicted, num_bytes_actual;
predicted_len = u32_u8_length_in_bytes
((scm_t_uint32 *) scm_i_string_wide_chars (str),
scm_i_string_length (str));
num_bytes_predicted = u32_u8_length_in_bytes (chars, num_chars);
if (lenp)
{
*lenp = predicted_len;
buf = scm_malloc (predicted_len);
*lenp = num_bytes_predicted;
buf = scm_malloc (num_bytes_predicted);
}
else
{
buf = scm_malloc (predicted_len + 1);
buf[predicted_len] = 0;
buf = scm_malloc (num_bytes_predicted + 1);
buf[num_bytes_predicted] = 0;
}
ret = u32_to_u8 ((scm_t_uint32 *) scm_i_string_wide_chars (str),
scm_i_string_length (str), buf, &actual_len);
num_bytes_actual = num_bytes_predicted;
ret = u32_to_u8 (chars, num_chars, buf, &num_bytes_actual);
if (SCM_LIKELY (ret == buf && actual_len == predicted_len))
if (SCM_LIKELY (ret == buf && num_bytes_actual == num_bytes_predicted))
return (char *) ret;
/* An error: a bad codepoint. */

View file

@ -1078,6 +1078,74 @@ test_locale_strings ()
test_11 ("(string #\\f #\\nul)", NULL, 1, 0);
}
static void
test_to_utf8_stringn ()
{
scm_t_wchar wstr[] = { 0x20, /* 0x20 */
0xDF, /* 0xC3, 0x9F */
0x65E5, /* 0xE6, 0x97, 0xA5 */
0x1D400 }; /* 0xF0, 0x9D, 0x90, 0x80 */
SCM str0 = scm_from_utf32_stringn (wstr, 1); /* ASCII */
SCM str1 = scm_from_utf32_stringn (wstr, 2); /* Narrow */
SCM str2 = scm_from_utf32_stringn (wstr, 4); /* Wide */
char cstr0[] = { 0x20, 0 };
char cstr1[] = { 0x20, 0xC3, 0x9F, 0 };
char cstr2[] = { 0x20, 0xC3, 0x9F, 0xE6, 0x97, 0xA5,
0xF0, 0x9D, 0x90, 0x80, 0 };
char *cstr;
size_t len;
/* Test conversion of ASCII string */
cstr = scm_to_utf8_stringn (str0, &len);
if (len + 1 != sizeof (cstr0) || memcmp (cstr, cstr0, len))
{
fprintf (stderr, "fail: scm_to_utf8_stringn (<ASCII>, &len)");
exit (EXIT_FAILURE);
}
free (cstr);
cstr = scm_to_utf8_stringn (str0, NULL);
if (memcmp (cstr, cstr0, len + 1))
{
fprintf (stderr, "fail: scm_to_utf8_stringn (<ASCII>, NULL)");
exit (EXIT_FAILURE);
}
free (cstr);
/* Test conversion of narrow string */
cstr = scm_to_utf8_stringn (str1, &len);
if (len + 1 != sizeof (cstr1) || memcmp (cstr, cstr1, len))
{
fprintf (stderr, "fail: scm_to_utf8_stringn (<NARROW>, &len)");
exit (EXIT_FAILURE);
}
free (cstr);
cstr = scm_to_utf8_stringn (str1, NULL);
if (memcmp (cstr, cstr1, len + 1))
{
fprintf (stderr, "fail: scm_to_utf8_stringn (<NARROW>, NULL)");
exit (EXIT_FAILURE);
}
free (cstr);
/* Test conversion of wide string */
cstr = scm_to_utf8_stringn (str2, &len);
if (len + 1 != sizeof (cstr2) || memcmp (cstr, cstr2, len))
{
fprintf (stderr, "fail: scm_to_utf8_stringn (<WIDE>, &len)");
exit (EXIT_FAILURE);
}
free (cstr);
cstr = scm_to_utf8_stringn (str2, NULL);
if (memcmp (cstr, cstr2, len + 1))
{
fprintf (stderr, "fail: scm_to_utf8_stringn (<WIDE>, NULL)");
exit (EXIT_FAILURE);
}
free (cstr);
}
static void
test_is_exact ()
{
@ -1122,6 +1190,7 @@ tests (void *data, int argc, char **argv)
test_from_double ();
test_to_double ();
test_locale_strings ();
test_to_utf8_stringn ();
test_is_exact ();
test_is_inexact ();
}