1 /*-
2 * Copyright (c) 2019 Martin Matuska
3 * All rights reserved.
4 *
5 * Redistribution and use in source and binary forms, with or without
6 * modification, are permitted provided that the following conditions
7 * are met:
8 * 1. Redistributions of source code must retain the above copyright
9 * notice, this list of conditions and the following disclaimer.
10 * 2. Redistributions in binary form must reproduce the above copyright
11 * notice, this list of conditions and the following disclaimer in the
12 * documentation and/or other materials provided with the distribution.
13 *
14 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR(S) ``AS IS'' AND ANY EXPRESS OR
15 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
16 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
17 * IN NO EVENT SHALL THE AUTHOR(S) BE LIABLE FOR ANY DIRECT, INDIRECT,
18 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
19 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
20 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
21 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
22 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
23 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
24 */
25 #include "test.h"
26
27 #include <locale.h>
28
29 static void
test_read_format_lha_filename_UTF16_UTF8(const char * refname)30 test_read_format_lha_filename_UTF16_UTF8(const char *refname)
31 {
32 struct archive *a;
33 struct archive_entry *ae;
34
35 /*
36 * Read LHA filename in en_US.UTF-8.
37 */
38 if (NULL == setlocale(LC_ALL, "en_US.UTF-8")) {
39 skipping("en_US.UTF-8 locale not available on this system.");
40 return;
41 }
42 /*
43 * Create a read object only for a test that platform support
44 * a character-set conversion because we can read a character-set
45 * of filenames from the header of an lha archive file and so we
46 * want to test that it works well.
47 */
48 assert((a = archive_read_new()) != NULL);
49 assertEqualIntA(a, ARCHIVE_OK, archive_read_support_format_all(a));
50 if (ARCHIVE_OK != archive_read_set_options(a, "hdrcharset=CP932")) {
51 assertEqualInt(ARCHIVE_OK, archive_read_free(a));
52 skipping("This system cannot convert character-set"
53 " from CP932 to UTF-8.");
54 return;
55 }
56 if (ARCHIVE_OK != archive_read_set_options(a, "hdrcharset=UTF-16")) {
57 assertEqualInt(ARCHIVE_OK, archive_read_free(a));
58 skipping("This system cannot convert character-set"
59 " from UTF-16 to UTF-8.");
60 return;
61 }
62 assertEqualInt(ARCHIVE_OK, archive_read_free(a));
63 assert((a = archive_read_new()) != NULL);
64 assertEqualIntA(a, ARCHIVE_OK, archive_read_support_filter_all(a));
65 assertEqualIntA(a, ARCHIVE_OK, archive_read_support_format_all(a));
66 assertEqualIntA(a, ARCHIVE_OK,
67 archive_read_open_filename(a, refname, 10240));
68
69 /* Note that usual Japanese filenames are tested in other cases */
70 #if defined(__APPLE__)
71 /* NFD normalization */
72 /* U:O:A:u:o:a: */
73 #define UMLAUT_DIRNAME "\x55\xcc\x88\x4f\xcc\x88\x41\xcc\x88\x75\xcc\x88\x6f"\
74 "\xcc\x88\x61\xcc\x88/"
75 /* a:o:u:A:O:U:.txt */
76 #define UMLAUT_FNAME "\x61\xcc\x88\x6f\xcc\x88\x75\xcc\x88\x41\xcc\x88"\
77 "\x4f\xcc\x88\x55\xcc\x88.txt"
78 #else
79 /* NFC normalization */
80 /* U:O:A:u:o:a: */
81 #define UMLAUT_DIRNAME "\xc3\x9c\xc3\x96\xc3\x84\xc3\xbc\xc3\xb6\xc3\xa4/"
82 /* a:o:u:A:O:U:.txt */
83 #define UMLAUT_FNAME "\xc3\xa4\xc3\xb6\xc3\xbc\xc3\x84\xc3\x96\xc3\x9c.txt"
84 #endif
85
86 /* "Test" in Japanese Katakana */
87 #define KATAKANA_FNAME "\xe3\x83\x86\xe3\x82\xb9\xe3\x83\x88.txt"
88 #define KATAKANA_DIRNAME "\xe3\x83\x86\xe3\x82\xb9\xe3\x83\x88/"
89
90 /* Verify regular file. U:O:A:u:o:a:/a:o:u:A:O:U:.txt */
91 assertEqualIntA(a, ARCHIVE_OK, archive_read_next_header(a, &ae));
92 assertEqualString(UMLAUT_DIRNAME UMLAUT_FNAME, archive_entry_pathname(ae));
93 assertEqualInt(12, archive_entry_size(ae));
94
95 /* Verify directory. U:O:A:u:o:a:/ */
96 assertEqualIntA(a, ARCHIVE_OK, archive_read_next_header(a, &ae));
97 assertEqualString(UMLAUT_DIRNAME, archive_entry_pathname(ae));
98 assertEqualInt(0, archive_entry_size(ae));
99
100 /* Verify regular file. U:O:A:u:o:a:/("Test" in Japanese).txt */
101 assertEqualIntA(a, ARCHIVE_OK, archive_read_next_header(a, &ae));
102 assertEqualString(UMLAUT_DIRNAME KATAKANA_FNAME,
103 archive_entry_pathname(ae));
104 assertEqualInt(25, archive_entry_size(ae));
105
106 /* Verify regular file. ("Test" in Japanese)/a:o:u:A:O:U:.txt */
107 assertEqualIntA(a, ARCHIVE_OK, archive_read_next_header(a, &ae));
108 assertEqualString(KATAKANA_DIRNAME UMLAUT_FNAME,
109 archive_entry_pathname(ae));
110 assertEqualInt(12, archive_entry_size(ae));
111
112 /* Verify directory. ("Test" in Japanese)/ */
113 assertEqualIntA(a, ARCHIVE_OK, archive_read_next_header(a, &ae));
114 assertEqualString(KATAKANA_DIRNAME, archive_entry_pathname(ae));
115 assertEqualInt(0, archive_entry_size(ae));
116
117 /* Verify regular file. a:o:u:A:O:U:.txt */
118 assertEqualIntA(a, ARCHIVE_OK, archive_read_next_header(a, &ae));
119 assertEqualString(UMLAUT_FNAME, archive_entry_pathname(ae));
120 assertEqualInt(12, archive_entry_size(ae));
121
122 /* End of archive. */
123 assertEqualIntA(a, ARCHIVE_EOF, archive_read_next_header(a, &ae));
124
125 /* Verify archive format. */
126 assertEqualIntA(a, ARCHIVE_FILTER_NONE, archive_filter_code(a, 0));
127 assertEqualIntA(a, ARCHIVE_FORMAT_LHA, archive_format(a));
128
129 /* Close the archive. */
130 assertEqualInt(ARCHIVE_OK, archive_read_close(a));
131 assertEqualInt(ARCHIVE_OK, archive_read_free(a));
132 }
133
DEFINE_TEST(test_read_format_lha_filename_UTF16)134 DEFINE_TEST(test_read_format_lha_filename_UTF16)
135 {
136 /* A sample file was created with Unlha32.dll. */
137 const char *refname = "test_read_format_lha_filename_utf16.lzh";
138 extract_reference_file(refname);
139
140 test_read_format_lha_filename_UTF16_UTF8(refname);
141 }
142
143