1 /* Test of conversion from UTF-8 to legacy encodings.
2 Copyright (C) 2007-2018 Free Software Foundation, Inc.
3
4 This program is free software: you can redistribute it and/or modify
5 it under the terms of the GNU General Public License as published by
6 the Free Software Foundation; either version 3 of the License, or
7 (at your option) any later version.
8
9 This program is distributed in the hope that it will be useful,
10 but WITHOUT ANY WARRANTY; without even the implied warranty of
11 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 GNU General Public License for more details.
13
14 You should have received a copy of the GNU General Public License
15 along with this program. If not, see <https://www.gnu.org/licenses/>. */
16
17 /* Written by Bruno Haible <bruno@clisp.org>, 2007. */
18
19 #include <config.h>
20
21 #include "uniconv.h"
22
23 #include <errno.h>
24 #include <stdlib.h>
25 #include <string.h>
26
27 #include "unistr.h"
28 #include "macros.h"
29
30 /* Magic number for detecting bounds violations. */
31 #define MAGIC 0x1983EFF1
32
33 static size_t *
new_offsets(size_t n)34 new_offsets (size_t n)
35 {
36 size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
37 offsets[n] = MAGIC;
38 return offsets;
39 }
40
41 int
main()42 main ()
43 {
44 static enum iconv_ilseq_handler handlers[] =
45 { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
46 size_t h;
47 size_t o;
48 size_t i;
49
50 #if HAVE_ICONV
51 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
52 ISO-8859-2, and UTF-8. */
53
54 /* Test conversion from UTF-8 to ISO-8859-1 with no errors. */
55 for (h = 0; h < SIZEOF (handlers); h++)
56 {
57 enum iconv_ilseq_handler handler = handlers[h];
58 static const uint8_t input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
59 static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
60 for (o = 0; o < 2; o++)
61 {
62 size_t *offsets = (o ? new_offsets (u8_strlen (input)) : NULL);
63 size_t length;
64 char *result = u8_conv_to_encoding ("ISO-8859-1", handler,
65 input, u8_strlen (input),
66 offsets,
67 NULL, &length);
68 ASSERT (result != NULL);
69 ASSERT (length == strlen (expected));
70 ASSERT (memcmp (result, expected, length) == 0);
71 if (o)
72 {
73 for (i = 0; i < 41; i++)
74 ASSERT (offsets[i] == (i < 1 ? i :
75 i == 1 ? (size_t)(-1) :
76 i < 13 ? i - 1 :
77 i == 13 ? (size_t)(-1) :
78 i < 20 ? i - 2 :
79 i == 20 ? (size_t)(-1) :
80 i < 40 ? i - 3 :
81 i == 40 ? (size_t)(-1) :
82 i - 4));
83 ASSERT (offsets[41] == MAGIC);
84 free (offsets);
85 }
86 free (result);
87 }
88 }
89
90 /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */
91 for (h = 0; h < SIZEOF (handlers); h++)
92 {
93 enum iconv_ilseq_handler handler = handlers[h];
94 static const uint8_t input[] = "Rafa\305\202 Maszkowski"; /* Rafał Maszkowski */
95 for (o = 0; o < 2; o++)
96 {
97 size_t *offsets = (o ? new_offsets (u8_strlen (input)) : NULL);
98 size_t length = 0xdead;
99 char *result = u8_conv_to_encoding ("ISO-8859-1", handler,
100 input, u8_strlen (input),
101 offsets,
102 NULL, &length);
103 switch (handler)
104 {
105 case iconveh_error:
106 ASSERT (result == NULL);
107 ASSERT (errno == EILSEQ);
108 ASSERT (length == 0xdead);
109 break;
110 case iconveh_question_mark:
111 {
112 static const char expected[] = "Rafa? Maszkowski";
113 static const char expected_translit[] = "Rafal Maszkowski";
114 ASSERT (result != NULL);
115 ASSERT (length == strlen (expected));
116 ASSERT (memcmp (result, expected, length) == 0
117 || memcmp (result, expected_translit, length) == 0);
118 if (o)
119 {
120 for (i = 0; i < 17; i++)
121 ASSERT (offsets[i] == (i < 5 ? i :
122 i == 5 ? (size_t)(-1) :
123 i - 1));
124 ASSERT (offsets[17] == MAGIC);
125 free (offsets);
126 }
127 free (result);
128 }
129 break;
130 case iconveh_escape_sequence:
131 {
132 static const char expected[] = "Rafa\\u0142 Maszkowski";
133 ASSERT (result != NULL);
134 ASSERT (length == strlen (expected));
135 ASSERT (memcmp (result, expected, length) == 0);
136 if (o)
137 {
138 for (i = 0; i < 17; i++)
139 ASSERT (offsets[i] == (i < 5 ? i :
140 i == 5 ? (size_t)(-1) :
141 i + 4));
142 ASSERT (offsets[17] == MAGIC);
143 free (offsets);
144 }
145 free (result);
146 }
147 break;
148 }
149 }
150 }
151
152 /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */
153 for (h = 0; h < SIZEOF (handlers); h++)
154 {
155 enum iconv_ilseq_handler handler = handlers[h];
156 static const uint8_t input[] = "\342";
157 for (o = 0; o < 2; o++)
158 {
159 size_t *offsets = (o ? new_offsets (u8_strlen (input)) : NULL);
160 size_t length;
161 char *result = u8_conv_to_encoding ("ISO-8859-1", handler,
162 input, u8_strlen (input),
163 offsets,
164 NULL, &length);
165 ASSERT (result != NULL);
166 ASSERT (length == strlen (""));
167 if (o)
168 {
169 ASSERT (offsets[0] == 0);
170 ASSERT (offsets[1] == MAGIC);
171 free (offsets);
172 }
173 free (result);
174 }
175 }
176
177 #endif
178
179 return 0;
180 }
181