trunk/tests/encodings.c

/*
    encodings.c - test handling different character encodings
    Copyright (C) 2008, 2009, 2010 siliconforks.com

    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 of the License, 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.
*/

#include <config.h>

#include <assert.h>
#include <string.h>

#include "encoding.h"
#include "stream.h"

int main(void) {
  jschar * characters;
  size_t num_characters; 
  int result;

  /* e, e grave, e acute, e circumflex */
  uint8_t utf8[] = {
    'e',
    0xc3,
    0xa8,
    0xc3,
    0xa9,
    0xc3,
    0xaa,
  };

  result = jscoverage_bytes_to_characters("UTF-8", utf8, 7, &characters, &num_characters);

#if HAVE_ICONV || HAVE_MULTIBYTETOWIDECHAR
  assert(result == 0);
  assert(num_characters == 4);
  assert(characters[0] == 'e');
  assert(characters[1] == 0xe8);
  assert(characters[2] == 0xe9);
  assert(characters[3] == 0xea);

  free(characters);
#else
  assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
#endif

  /*
  BOM is 0xfeff
  = 1111 1110 1111 1111
  UTF: 1110---- 10------ 10------
     = 11101111 10111011 10111111
     = EF BB BF
  */
  uint8_t utf8_with_bom[] = {
    0xef,
    0xbb,
    0xbf,
    'e',
    0xc3,
    0xa8,
    0xc3,
    0xa9,
    0xc3,
    0xaa,
  };

  result = jscoverage_bytes_to_characters("UTF-8", utf8_with_bom, 10, &characters, &num_characters);

#if HAVE_ICONV || HAVE_MULTIBYTETOWIDECHAR
  assert(result == 0);
  assert(num_characters == 4);
  assert(characters[0] == 'e');
  assert(characters[1] == 0xe8);
  assert(characters[2] == 0xe9);
  assert(characters[3] == 0xea);

  free(characters);
#else
  assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
#endif

  uint8_t utf16be[] = {
    0, 'e',
    0, 0xe8,
    0, 0xe9,
    0, 0xea,
  };

  result = jscoverage_bytes_to_characters("UTF-16BE", utf16be, 8, &characters, &num_characters);

#ifdef HAVE_ICONV
  assert(result == 0);
  assert(num_characters == 4);
  assert(characters[0] == 'e');
  assert(characters[1] == 0xe8);
  assert(characters[2] == 0xe9);
  assert(characters[3] == 0xea);

  free(characters);
#else
  assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
#endif

  uint8_t utf16be_with_bom[] = {
    0xfe, 0xff,
    0, 'e',
    0, 0xe8,
    0, 0xe9,
    0, 0xea,
  };

  result = jscoverage_bytes_to_characters("UTF-16BE", utf16be_with_bom, 10, &characters, &num_characters);

#ifdef HAVE_ICONV
  assert(result == 0);
  assert(num_characters == 4);
  assert(characters[0] == 'e');
  assert(characters[1] == 0xe8);
  assert(characters[2] == 0xe9);
  assert(characters[3] == 0xea);

  free(characters);
#else
  assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
#endif

  uint8_t utf16le[] = {
    'e', 0,
    0xe8, 0,
    0xe9, 0,
    0xea, 0,
  };

  result = jscoverage_bytes_to_characters("UTF-16LE", utf16le, 8, &characters, &num_characters);

#ifdef HAVE_ICONV
  assert(result == 0);
  assert(num_characters == 4);
  assert(characters[0] == 'e');
  assert(characters[1] == 0xe8);
  assert(characters[2] == 0xe9);
  assert(characters[3] == 0xea);

  free(characters);
#else
  assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
#endif

  uint8_t utf16le_with_bom[] = {
    0xff, 0xfe,
    'e', 0,
    0xe8, 0,
    0xe9, 0,
    0xea, 0,
  };

  result = jscoverage_bytes_to_characters("UTF-16LE", utf16le_with_bom, 10, &characters, &num_characters);

#ifdef HAVE_ICONV
  assert(result == 0);
  assert(num_characters == 4);
  assert(characters[0] == 'e');
  assert(characters[1] == 0xe8);
  assert(characters[2] == 0xe9);
  assert(characters[3] == 0xea);

  free(characters);
#else
  assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
#endif

  /* bogus encoding */
  uint8_t bogus[] = {'b', 'o', 'g', 'u', 's'};

  result = jscoverage_bytes_to_characters("BOGUS", bogus, 5, &characters, &num_characters);

  assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);

#ifdef HAVE_ICONV
  /* malformed US-ASCII */
  /* NOTE: Windows simply discards the high bit */
  uint8_t malformed_ascii[] = {
    'e',
    0xe8,
    0xe9,
    0xea,
  };

  result = jscoverage_bytes_to_characters("US-ASCII", malformed_ascii, 4, &characters, &num_characters);

  assert(result == JSCOVERAGE_ERROR_INVALID_BYTE_SEQUENCE);
#endif

  /* malformed UTF-8 */
  uint8_t malformed_utf8[] = {
    'e',
    0xe8,
    0xe9,
    0xea,
  };

  result = jscoverage_bytes_to_characters("UTF-8", malformed_utf8, 4, &characters, &num_characters);

#if HAVE_ICONV || HAVE_MULTIBYTETOWIDECHAR
  assert(result == JSCOVERAGE_ERROR_INVALID_BYTE_SEQUENCE);
#else
  assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
#endif

  return 0;
}
1	/*
2	encodings.c - test handling different character encodings
3	Copyright (C) 2008, 2009, 2010 siliconforks.com
4
5	This program is free software; you can redistribute it and/or modify
6	it under the terms of the GNU General Public License as published by
7	the Free Software Foundation; either version 2 of the License, or
8	(at your option) any later version.
9
10	This program is distributed in the hope that it will be useful,
11	but WITHOUT ANY WARRANTY; without even the implied warranty of
12	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13	GNU General Public License for more details.
14
15	You should have received a copy of the GNU General Public License along
16	with this program; if not, write to the Free Software Foundation, Inc.,
17	51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
18	*/
19
20	#include <config.h>
21
22	#include <assert.h>
23	#include <string.h>
24
25	#include "encoding.h"
26	#include "stream.h"
27
28	int main(void) {
29	jschar * characters;
30	size_t num_characters;
31	int result;
32
33	/* e, e grave, e acute, e circumflex */
34	uint8_t utf8[] = {
35	'e',
36	0xc3,
37	0xa8,
38	0xc3,
39	0xa9,
40	0xc3,
41	0xaa,
42	};
43
44	result = jscoverage_bytes_to_characters("UTF-8", utf8, 7, &characters, &num_characters);
45
46	#if HAVE_ICONV \|\| HAVE_MULTIBYTETOWIDECHAR
47	assert(result == 0);
48	assert(num_characters == 4);
49	assert(characters[0] == 'e');
50	assert(characters[1] == 0xe8);
51	assert(characters[2] == 0xe9);
52	assert(characters[3] == 0xea);
53
54	free(characters);
55	#else
56	assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
57	#endif
58
59	/*
60	BOM is 0xfeff
61	= 1111 1110 1111 1111
62	UTF: 1110---- 10------ 10------
63	= 11101111 10111011 10111111
64	= EF BB BF
65	*/
66	uint8_t utf8_with_bom[] = {
67	0xef,
68	0xbb,
69	0xbf,
70	'e',
71	0xc3,
72	0xa8,
73	0xc3,
74	0xa9,
75	0xc3,
76	0xaa,
77	};
78
79	result = jscoverage_bytes_to_characters("UTF-8", utf8_with_bom, 10, &characters, &num_characters);
80
81	#if HAVE_ICONV \|\| HAVE_MULTIBYTETOWIDECHAR
82	assert(result == 0);
83	assert(num_characters == 4);
84	assert(characters[0] == 'e');
85	assert(characters[1] == 0xe8);
86	assert(characters[2] == 0xe9);
87	assert(characters[3] == 0xea);
88
89	free(characters);
90	#else
91	assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
92	#endif
93
94	uint8_t utf16be[] = {
95	0, 'e',
96	0, 0xe8,
97	0, 0xe9,
98	0, 0xea,
99	};
100
101	result = jscoverage_bytes_to_characters("UTF-16BE", utf16be, 8, &characters, &num_characters);
102
103	#ifdef HAVE_ICONV
104	assert(result == 0);
105	assert(num_characters == 4);
106	assert(characters[0] == 'e');
107	assert(characters[1] == 0xe8);
108	assert(characters[2] == 0xe9);
109	assert(characters[3] == 0xea);
110
111	free(characters);
112	#else
113	assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
114	#endif
115
116	uint8_t utf16be_with_bom[] = {
117	0xfe, 0xff,
118	0, 'e',
119	0, 0xe8,
120	0, 0xe9,
121	0, 0xea,
122	};
123
124	result = jscoverage_bytes_to_characters("UTF-16BE", utf16be_with_bom, 10, &characters, &num_characters);
125
126	#ifdef HAVE_ICONV
127	assert(result == 0);
128	assert(num_characters == 4);
129	assert(characters[0] == 'e');
130	assert(characters[1] == 0xe8);
131	assert(characters[2] == 0xe9);
132	assert(characters[3] == 0xea);
133
134	free(characters);
135	#else
136	assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
137	#endif
138
139	uint8_t utf16le[] = {
140	'e', 0,
141	0xe8, 0,
142	0xe9, 0,
143	0xea, 0,
144	};
145
146	result = jscoverage_bytes_to_characters("UTF-16LE", utf16le, 8, &characters, &num_characters);
147
148	#ifdef HAVE_ICONV
149	assert(result == 0);
150	assert(num_characters == 4);
151	assert(characters[0] == 'e');
152	assert(characters[1] == 0xe8);
153	assert(characters[2] == 0xe9);
154	assert(characters[3] == 0xea);
155
156	free(characters);
157	#else
158	assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
159	#endif
160
161	uint8_t utf16le_with_bom[] = {
162	0xff, 0xfe,
163	'e', 0,
164	0xe8, 0,
165	0xe9, 0,
166	0xea, 0,
167	};
168
169	result = jscoverage_bytes_to_characters("UTF-16LE", utf16le_with_bom, 10, &characters, &num_characters);
170
171	#ifdef HAVE_ICONV
172	assert(result == 0);
173	assert(num_characters == 4);
174	assert(characters[0] == 'e');
175	assert(characters[1] == 0xe8);
176	assert(characters[2] == 0xe9);
177	assert(characters[3] == 0xea);
178
179	free(characters);
180	#else
181	assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
182	#endif
183
184	/* bogus encoding */
185	uint8_t bogus[] = {'b', 'o', 'g', 'u', 's'};
186
187	result = jscoverage_bytes_to_characters("BOGUS", bogus, 5, &characters, &num_characters);
188
189	assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
190
191	#ifdef HAVE_ICONV
192	/* malformed US-ASCII */
193	/* NOTE: Windows simply discards the high bit */
194	uint8_t malformed_ascii[] = {
195	'e',
196	0xe8,
197	0xe9,
198	0xea,
199	};
200
201	result = jscoverage_bytes_to_characters("US-ASCII", malformed_ascii, 4, &characters, &num_characters);
202
203	assert(result == JSCOVERAGE_ERROR_INVALID_BYTE_SEQUENCE);
204	#endif
205
206	/* malformed UTF-8 */
207	uint8_t malformed_utf8[] = {
208	'e',
209	0xe8,
210	0xe9,
211	0xea,
212	};
213
214	result = jscoverage_bytes_to_characters("UTF-8", malformed_utf8, 4, &characters, &num_characters);
215
216	#if HAVE_ICONV \|\| HAVE_MULTIBYTETOWIDECHAR
217	assert(result == JSCOVERAGE_ERROR_INVALID_BYTE_SEQUENCE);
218	#else
219	assert(result == JSCOVERAGE_ERROR_ENCODING_NOT_SUPPORTED);
220	#endif
221
222	return 0;
223	}