luc14n0/glib
1
0
Fork 0
mirror of https://gitlab.gnome.org/GNOME/glib.git synced 2025-03-30 20:33:08 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'unicode-normalize-test' into 'main'

Browse Source 
Move test tests/unicode-normalize.c to glib/tests/

See merge request GNOME/glib!2586
This commit is contained in:
Philip Withnall 2022-04-08 10:54:57 +00:00
commit 690e64afef
4 changed files with 19202 additions and 210 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19047
glib/tests/NormalizationTest.txt Normal file
View File

File diff suppressed because it is too large Load Diff

1
glib/tests/meson.build
View File

@ -126,6 +126,7 @@ glib_tests = {
'utils' : {}, 'utils' : {},
'unicode' : {}, 'unicode' : {},
'unicode-encoding' : {}, 'unicode-encoding' : {},
'unicode-normalize': {},
'uri' : {}, 'uri' : {},
'1bit-mutex' : {}, '1bit-mutex' : {},
'1bit-emufutex' : { '1bit-emufutex' : {

154
glib/tests/unicode-normalize.c Normal file
View File

@ -0,0 +1,154 @@
#undef G_DISABLE_ASSERT
#undef G_LOG_DOMAIN
#include <glib.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
static char *
decode (const gchar *input)
{
unsigned ch;
int offset = 0;
GString *result = g_string_new (NULL);
do
{
g_assert_cmpint (sscanf (input + offset, "%x", &ch), ==, 1);
g_string_append_unichar (result, ch);
while (input[offset] && input[offset] != ' ')
offset++;
while (input[offset] && input[offset] == ' ')
offset++;
}
while (input[offset]);
return g_string_free (result, FALSE);
}
const char *names[4] = {
"NFD",
"NFC",
"NFKD",
"NFKC"
};
static void
test_form (int line,
GNormalizeMode mode,
gboolean do_compat,
int expected,
char **c,
char **raw)
{
int i;
gboolean mode_is_compat = (mode == G_NORMALIZE_NFKC ||
mode == G_NORMALIZE_NFKD);
if (mode_is_compat || !do_compat)
{
for (i = 0; i < 3; i++)
{
char *result = g_utf8_normalize (c[i], -1, mode);
g_assert_cmpstr (result, ==, c[expected]);
g_free (result);
}
}
if (mode_is_compat || do_compat)
{
for (i = 3; i < 5; i++)
{
char *result = g_utf8_normalize (c[i], -1, mode);
g_assert_cmpstr (result, ==, c[expected]);
g_free (result);
}
}
}
static void
process_one (int line, gchar **columns)
{
char *c[5];
int i;
for (i = 0; i < 5; i++)
{
c[i] = decode (columns[i]);
g_assert_nonnull (c[i]);
}
test_form (line, G_NORMALIZE_NFD, FALSE, 2, c, columns);
test_form (line, G_NORMALIZE_NFD, TRUE, 4, c, columns);
test_form (line, G_NORMALIZE_NFC, FALSE, 1, c, columns);
test_form (line, G_NORMALIZE_NFC, TRUE, 3, c, columns);
test_form (line, G_NORMALIZE_NFKD, TRUE, 4, c, columns);
test_form (line, G_NORMALIZE_NFKC, TRUE, 3, c, columns);
for (i = 0; i < 5; i++)
g_free (c[i]);
}
static void
test_unicode_normalize (void)
{
GIOChannel *in;
GError *error = NULL;
gchar *filename = NULL;
GString *buffer = g_string_new (NULL);
int line = 1;
filename = g_test_build_filename (G_TEST_DIST, "NormalizationTest.txt", NULL);
g_assert_nonnull (filename);
in = g_io_channel_new_file (filename, "r", &error);
g_assert_no_error (error);
g_assert_nonnull (in);
g_free (filename);
while (TRUE)
{
gsize term_pos;
gchar **columns;
if (g_io_channel_read_line_string (in, buffer, &term_pos, &error) != G_IO_STATUS_NORMAL)
break;
buffer->str[term_pos] = '\0';
if (buffer->str[0] == '#') /* Comment */
goto next;
if (buffer->str[0] == '@') /* Part */
{
fprintf (stderr, "\nProcessing %s\n", buffer->str + 1);
goto next;
}
columns = g_strsplit (buffer->str, ";", -1);
if (!columns[0])
goto next;
process_one (line, columns);
g_strfreev (columns);
next:
g_string_truncate (buffer, 0);
line++;
}
g_assert_no_error (error);
g_io_channel_unref (in);
g_string_free (buffer, TRUE);
}
int
main (int argc, char **argv)
{
g_test_init (&argc, &argv, NULL);
g_test_add_func ("/unicode/normalize", test_unicode_normalize);
return g_test_run ();
}

210
tests/unicode-normalize.c
View File

@ -1,210 +0,0 @@
#undef G_DISABLE_ASSERT
#undef G_LOG_DOMAIN
#include <glib.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
gboolean success = TRUE;
static char *
decode (const gchar *input)
{
unsigned ch;
int offset = 0;
GString *result = g_string_new (NULL);
do
{
if (sscanf (input + offset, "%x", &ch) != 1)
{
fprintf (stderr, "Error parsing character string %s\n", input);
exit (1);
}
g_string_append_unichar (result, ch);
while (input[offset] && input[offset] != ' ')
offset++;
while (input[offset] && input[offset] == ' ')
offset++;
}
while (input[offset]);
return g_string_free (result, FALSE);
}
const char *names[4] = {
"NFD",
"NFC",
"NFKD",
"NFKC"
};
static char *
encode (const gchar *input)
{
GString *result = g_string_new(NULL);
const gchar *p = input;
while (*p)
{
gunichar c = g_utf8_get_char (p);
g_string_append_printf (result, "%04X ", c);
p = g_utf8_next_char(p);
}
return g_string_free (result, FALSE);
}
static void
test_form (int line,
GNormalizeMode mode,
gboolean do_compat,
int expected,
char **c,
char **raw)
{
int i;
gboolean mode_is_compat = (mode == G_NORMALIZE_NFKC ||
mode == G_NORMALIZE_NFKD);
if (mode_is_compat || !do_compat)
{
for (i = 0; i < 3; i++)
{
char *result = g_utf8_normalize (c[i], -1, mode);
if (strcmp (result, c[expected]) != 0)
{
char *result_raw = encode(result);
fprintf (stderr, "\nFailure: %d/%d: %s\n", line, i + 1, raw[5]);
fprintf (stderr, " g_utf8_normalize (%s, %s) != %s but %s\n",
raw[i], names[mode], raw[expected], result_raw);
g_free (result_raw);
success = FALSE;
}
g_free (result);
}
}
if (mode_is_compat || do_compat)
{
for (i = 3; i < 5; i++)
{
char *result = g_utf8_normalize (c[i], -1, mode);
if (strcmp (result, c[expected]) != 0)
{
char *result_raw = encode(result);
fprintf (stderr, "\nFailure: %d/%d: %s\n", line, i, raw[5]);
fprintf (stderr, " g_utf8_normalize (%s, %s) != %s but %s\n",
raw[i], names[mode], raw[expected], result_raw);
g_free (result_raw);
success = FALSE;
}
g_free (result);
}
}
}
static gboolean
process_one (int line, gchar **columns)
{
char *c[5];
int i;
gboolean skip = FALSE;
for (i=0; i < 5; i++)
{
c[i] = decode(columns[i]);
if (!c[i])
skip = TRUE;
}
if (!skip)
{
test_form (line, G_NORMALIZE_NFD, FALSE, 2, c, columns);
test_form (line, G_NORMALIZE_NFD, TRUE, 4, c, columns);
test_form (line, G_NORMALIZE_NFC, FALSE, 1, c, columns);
test_form (line, G_NORMALIZE_NFC, TRUE, 3, c, columns);
test_form (line, G_NORMALIZE_NFKD, TRUE, 4, c, columns);
test_form (line, G_NORMALIZE_NFKC, TRUE, 3, c, columns);
}
for (i=0; i < 5; i++)
g_free (c[i]);
return TRUE;
}
int main (int argc, char **argv)
{
GIOChannel *in;
GError *error = NULL;
GString *buffer = g_string_new (NULL);
int line_to_do = 0;
int line = 1;
if (argc != 2 && argc != 3)
{
fprintf (stderr, "Usage: unicode-normalize NormalizationTest.txt LINE\n");
return 1;
}
if (argc == 3)
line_to_do = atoi(argv[2]);
in = g_io_channel_new_file (argv[1], "r", &error);
if (!in)
{
fprintf (stderr, "Cannot open %s: %s\n", argv[1], error->message);
return 1;
}
while (TRUE)
{
gsize term_pos;
gchar **columns;
if (g_io_channel_read_line_string (in, buffer, &term_pos, &error) != G_IO_STATUS_NORMAL)
break;
if (line_to_do && line != line_to_do)
goto next;
buffer->str[term_pos] = '\0';
if (buffer->str[0] == '#') /* Comment */
goto next;
if (buffer->str[0] == '@') /* Part */
{
fprintf (stderr, "\nProcessing %s\n", buffer->str + 1);
goto next;
}
columns = g_strsplit (buffer->str, ";", -1);
if (!columns[0])
goto next;
if (!process_one (line, columns))
return 1;
g_strfreev (columns);
next:
g_string_truncate (buffer, 0);
line++;
}
if (error)
{
fprintf (stderr, "Error reading test file, %s\n", error->message);
return 1;
}
g_io_channel_unref (in);
g_string_free (buffer, TRUE);
return !success;
}