xed/tests/smart-converter.c

354 lines
8.6 KiB
C
Raw Permalink Normal View History

2011-11-07 13:46:58 -06:00
/*
* smart-converter.c
2016-01-25 08:13:49 -06:00
* This file is part of xedit
2011-11-07 13:46:58 -06:00
*
* Copyright (C) 2009 - Ignacio Casal Quinteiro
*
2016-01-25 08:13:49 -06:00
* xedit is free software; you can redistribute it and/or modify
2011-11-07 13:46:58 -06:00
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
2016-01-25 08:13:49 -06:00
* xedit is distributed in the hope that it will be useful,
2011-11-07 13:46:58 -06:00
* 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
2016-01-25 08:13:49 -06:00
* along with xedit; if not, write to the Free Software
2011-11-07 13:46:58 -06:00
* Foundation, Inc., 51 Franklin St, Fifth Floor,
* Boston, MA 02110-1301 USA
*/
2016-01-25 08:13:49 -06:00
#include "xedit-smart-charset-converter.h"
#include "xedit-encodings.h"
2011-11-07 13:46:58 -06:00
#include <gio/gio.h>
#include <glib.h>
2015-08-03 14:32:35 -05:00
#include <glib/gprintf.h>
2011-11-07 13:46:58 -06:00
#include <string.h>
#define TEXT_TO_CONVERT "this is some text to make the tests"
#define TEXT_TO_GUESS "hello \xe6\x96\x87 world"
static void
print_hex (gchar *ptr, gint len)
{
gint i;
for (i = 0; i < len; ++i)
{
g_printf ("\\x%02x", (unsigned char)ptr[i]);
}
g_printf ("\n");
}
static gchar *
get_encoded_text (const gchar *text,
gsize nread,
2016-01-25 08:13:49 -06:00
const XeditEncoding *to,
const XeditEncoding *from,
2011-11-07 13:46:58 -06:00
gsize *bytes_written_aux,
gboolean care_about_error)
{
GCharsetConverter *converter;
gchar *out, *out_aux;
gsize bytes_read, bytes_read_aux;
gsize bytes_written;
GConverterResult res;
GError *err;
2016-01-25 08:13:49 -06:00
converter = g_charset_converter_new (xedit_encoding_get_charset (to),
xedit_encoding_get_charset (from),
2011-11-07 13:46:58 -06:00
NULL);
out = g_malloc (200);
out_aux = g_malloc (200);
err = NULL;
bytes_read_aux = 0;
*bytes_written_aux = 0;
if (nread == -1)
{
nread = strlen (text);
}
do
{
res = g_converter_convert (G_CONVERTER (converter),
text + bytes_read_aux,
nread,
out_aux,
200,
G_CONVERTER_INPUT_AT_END,
&bytes_read,
&bytes_written,
&err);
memcpy (out + *bytes_written_aux, out_aux, bytes_written);
bytes_read_aux += bytes_read;
*bytes_written_aux += bytes_written;
nread -= bytes_read;
} while (res != G_CONVERTER_FINISHED && res != G_CONVERTER_ERROR);
if (care_about_error)
{
g_assert_no_error (err);
}
else if (err)
{
g_printf ("** You don't care, but there was an error: %s", err->message);
return NULL;
}
out[*bytes_written_aux] = '\0';
if (!g_utf8_validate (out, *bytes_written_aux, NULL) && !care_about_error)
{
if (!care_about_error)
{
return NULL;
}
else
{
g_assert_not_reached ();
}
}
return out;
}
static GSList *
get_all_encodings ()
{
GSList *encs = NULL;
gint i = 0;
while (TRUE)
{
2016-01-25 08:13:49 -06:00
const XeditEncoding *enc;
2011-11-07 13:46:58 -06:00
2016-01-25 08:13:49 -06:00
enc = xedit_encoding_get_from_index (i);
2011-11-07 13:46:58 -06:00
if (enc == NULL)
break;
encs = g_slist_prepend (encs, (gpointer)enc);
i++;
}
return encs;
}
static gchar *
do_test (const gchar *test_in,
const gchar *enc,
GSList *encodings,
gsize nread,
2016-01-25 08:13:49 -06:00
const XeditEncoding **guessed)
2011-11-07 13:46:58 -06:00
{
2016-01-25 08:13:49 -06:00
XeditSmartCharsetConverter *converter;
2011-11-07 13:46:58 -06:00
gchar *out, *out_aux;
gsize bytes_read, bytes_read_aux;
gsize bytes_written, bytes_written_aux;
GConverterResult res;
GError *err;
if (enc != NULL)
{
encodings = NULL;
2016-01-25 08:13:49 -06:00
encodings = g_slist_prepend (encodings, (gpointer)xedit_encoding_get_from_charset (enc));
2011-11-07 13:46:58 -06:00
}
2016-01-25 08:13:49 -06:00
converter = xedit_smart_charset_converter_new (encodings);
2011-11-07 13:46:58 -06:00
out = g_malloc (200);
out_aux = g_malloc (200);
err = NULL;
bytes_read_aux = 0;
bytes_written_aux = 0;
do
{
res = g_converter_convert (G_CONVERTER (converter),
test_in + bytes_read_aux,
nread,
out_aux,
200,
G_CONVERTER_INPUT_AT_END,
&bytes_read,
&bytes_written,
&err);
memcpy (out + bytes_written_aux, out_aux, bytes_written);
bytes_read_aux += bytes_read;
bytes_written_aux += bytes_written;
nread -= bytes_read;
} while (res != G_CONVERTER_FINISHED && res != G_CONVERTER_ERROR);
g_assert_no_error (err);
out[bytes_written_aux] = '\0';
if (guessed != NULL)
2016-01-25 08:13:49 -06:00
*guessed = xedit_smart_charset_converter_get_guessed (converter);
2011-11-07 13:46:58 -06:00
return out;
}
static void
do_test_roundtrip (const char *str, const char *charset)
{
gsize len;
gchar *buf, *p;
GInputStream *in, *tmp;
GCharsetConverter *c1;
2016-01-25 08:13:49 -06:00
XeditSmartCharsetConverter *c2;
2011-11-07 13:46:58 -06:00
gsize n, tot;
GError *err;
GSList *enc = NULL;
len = strlen(str);
buf = g_new0 (char, len);
in = g_memory_input_stream_new_from_data (str, -1, NULL);
c1 = g_charset_converter_new (charset, "UTF-8", NULL);
tmp = in;
in = g_converter_input_stream_new (in, G_CONVERTER (c1));
g_object_unref (tmp);
g_object_unref (c1);
2016-01-25 08:13:49 -06:00
enc = g_slist_prepend (enc, (gpointer)xedit_encoding_get_from_charset (charset));
c2 = xedit_smart_charset_converter_new (enc);
2011-11-07 13:46:58 -06:00
g_slist_free (enc);
tmp = in;
in = g_converter_input_stream_new (in, G_CONVERTER (c2));
g_object_unref (tmp);
g_object_unref (c2);
tot = 0;
p = buf;
n = len;
while (TRUE)
{
gssize res;
err = NULL;
res = g_input_stream_read (in, p, n, NULL, &err);
g_assert_no_error (err);
if (res == 0)
break;
p += res;
n -= res;
tot += res;
}
g_assert_cmpint (tot, ==, len);
g_assert_cmpstr (str, ==, buf);
g_free (buf);
g_object_unref (in);
}
static void
test_utf8_utf8 ()
{
gchar *aux;
aux = do_test (TEXT_TO_CONVERT, "UTF-8", NULL, strlen (TEXT_TO_CONVERT), NULL);
g_assert_cmpstr (aux, ==, TEXT_TO_CONVERT);
aux = do_test ("foobar\xc3\xa8\xc3\xa8\xc3\xa8zzzzzz", "UTF-8", NULL, 18, NULL);
g_assert_cmpstr (aux, ==, "foobar\xc3\xa8\xc3\xa8\xc3\xa8zzzzzz");
aux = do_test ("foobar\xc3\xa8\xc3\xa8\xc3\xa8zzzzzz", "UTF-8", NULL, 9, NULL);
g_assert_cmpstr (aux, ==, "foobar\xc3\xa8\xc3");
/* FIXME: Use the utf8 stream for a fallback? */
//do_test_with_error ("\xef\xbf\xbezzzzzz", encs, G_IO_ERROR_FAILED);
}
static void
test_xxx_xxx ()
{
GSList *encs, *l;
encs = get_all_encodings ();
/* Here we just test all encodings it is just to know that the conversions
are done ok */
for (l = encs; l != NULL; l = g_slist_next (l))
{
2016-01-25 08:13:49 -06:00
do_test_roundtrip (TEXT_TO_CONVERT, xedit_encoding_get_charset ((const XeditEncoding *)l->data));
2011-11-07 13:46:58 -06:00
}
g_slist_free (encs);
}
static void
test_empty ()
{
2016-01-25 08:13:49 -06:00
const XeditEncoding *guessed;
2011-11-07 13:46:58 -06:00
gchar *out;
GSList *encodings = NULL;
/* testing the case of an empty file and list of encodings with no
utf-8. In this case, the smart converter cannot determine the right
encoding (because there is no input), but should still default to
utf-8 for the detection */
2016-01-25 08:13:49 -06:00
encodings = g_slist_prepend (encodings, (gpointer)xedit_encoding_get_from_charset ("UTF-16"));
encodings = g_slist_prepend (encodings, (gpointer)xedit_encoding_get_from_charset ("ISO-8859-15"));
2011-11-07 13:46:58 -06:00
out = do_test ("", NULL, encodings, 0, &guessed);
g_assert_cmpstr (out, ==, "");
2016-01-25 08:13:49 -06:00
g_assert (guessed == xedit_encoding_get_utf8 ());
2011-11-07 13:46:58 -06:00
}
static void
test_guessed ()
{
GSList *encs = NULL;
gchar *aux, *aux2, *fail;
gsize aux_len, fail_len;
2016-01-25 08:13:49 -06:00
const XeditEncoding *guessed;
2011-11-07 13:46:58 -06:00
aux = get_encoded_text (TEXT_TO_GUESS, -1,
2016-01-25 08:13:49 -06:00
xedit_encoding_get_from_charset ("UTF-16"),
xedit_encoding_get_from_charset ("UTF-8"),
2011-11-07 13:46:58 -06:00
&aux_len,
TRUE);
fail = get_encoded_text (aux, aux_len,
2016-01-25 08:13:49 -06:00
xedit_encoding_get_from_charset ("UTF-8"),
xedit_encoding_get_from_charset ("ISO-8859-15"),
2011-11-07 13:46:58 -06:00
&fail_len,
FALSE);
g_assert (fail == NULL);
/* ISO-8859-15 should fail */
2016-01-25 08:13:49 -06:00
encs = g_slist_append (encs, (gpointer)xedit_encoding_get_from_charset ("ISO-8859-15"));
encs = g_slist_append (encs, (gpointer)xedit_encoding_get_from_charset ("UTF-16"));
2011-11-07 13:46:58 -06:00
aux2 = do_test (aux, NULL, encs, aux_len, &guessed);
2016-01-25 08:13:49 -06:00
g_assert (guessed == xedit_encoding_get_from_charset ("UTF-16"));
2011-11-07 13:46:58 -06:00
}
int main (int argc,
char *argv[])
{
g_test_init (&argc, &argv, NULL);
g_test_add_func ("/smart-converter/utf8-utf8", test_utf8_utf8);
//g_test_add_func ("/smart-converter/xxx-xxx", test_xxx_xxx);
g_test_add_func ("/smart-converter/guessed", test_guessed);
g_test_add_func ("/smart-converter/empty", test_empty);
return g_test_run ();
}