1/* Test of conversion to UTF-8 from legacy encodings.
2   Copyright (C) 2007-2010 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 <http://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 <stdlib.h>
24#include <string.h>
25
26#include "unistr.h"
27#include "macros.h"
28
29/* Magic number for detecting bounds violations.  */
30#define MAGIC 0x1983EFF1
31
32static size_t *
33new_offsets (size_t n)
34{
35  size_t *offsets = (size_t *) malloc ((n + 1) * sizeof (size_t));
36  offsets[n] = MAGIC;
37  return offsets;
38}
39
40int
41main ()
42{
43  static enum iconv_ilseq_handler handlers[] =
44    { iconveh_error, iconveh_question_mark, iconveh_escape_sequence };
45  size_t h;
46  size_t o;
47  size_t i;
48
49#if HAVE_ICONV
50  /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1,
51     ISO-8859-2, and UTF-8.  */
52
53  /* Test conversion from ISO-8859-1 to UTF-8 with no errors.  */
54  for (h = 0; h < SIZEOF (handlers); h++)
55    {
56      enum iconv_ilseq_handler handler = handlers[h];
57      static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337";
58      static const uint8_t expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237";
59      for (o = 0; o < 2; o++)
60        {
61          size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
62          size_t length;
63          uint8_t *result = u8_conv_from_encoding ("ISO-8859-1", handler,
64                                                   input, strlen (input),
65                                                   offsets,
66                                                   NULL, &length);
67          ASSERT (result != NULL);
68          ASSERT (length == u8_strlen (expected));
69          ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
70          if (o)
71            {
72              for (i = 0; i < 37; i++)
73                ASSERT (offsets[i] == (i < 1 ? i :
74                                       i < 12 ? i + 1 :
75                                       i < 18 ? i + 2 :
76                                       i + 3));
77              ASSERT (offsets[37] == MAGIC);
78              free (offsets);
79            }
80          free (result);
81        }
82    }
83
84  /* Test conversion from ISO-8859-2 to UTF-8 with no errors.  */
85  for (h = 0; h < SIZEOF (handlers); h++)
86    {
87      enum iconv_ilseq_handler handler = handlers[h];
88      static const char input[] = "Rafa\263 Maszkowski"; /* Rafa�� Maszkowski */
89      static const uint8_t expected[] = "Rafa\305\202 Maszkowski";
90      for (o = 0; o < 2; o++)
91        {
92          size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
93          size_t length;
94          uint8_t *result = u8_conv_from_encoding ("ISO-8859-2", handler,
95                                                   input, strlen (input),
96                                                   offsets,
97                                                   NULL, &length);
98          ASSERT (result != NULL);
99          ASSERT (length == u8_strlen (expected));
100          ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
101          if (o)
102            {
103              for (i = 0; i < 16; i++)
104                ASSERT (offsets[i] == (i < 5 ? i :
105                                       i + 1));
106              ASSERT (offsets[16] == MAGIC);
107              free (offsets);
108            }
109          free (result);
110        }
111    }
112
113  /* autodetect_jp is only supported when iconv() support ISO-2022-JP-2.  */
114# if defined _LIBICONV_VERSION || !(defined _AIX || defined __sgi || defined __hpux || defined __osf__ || defined __sun)
115  /* Test conversions from autodetect_jp to UTF-8.  */
116  for (h = 0; h < SIZEOF (handlers); h++)
117    {
118      enum iconv_ilseq_handler handler = handlers[h];
119      static const char input[] = "\244\263\244\363\244\313\244\301\244\317"; /* ��������������� in EUC-JP */
120      static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* ��������������� */
121      for (o = 0; o < 2; o++)
122        {
123          size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
124          size_t length;
125          uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler,
126                                                   input, strlen (input),
127                                                   offsets,
128                                                   NULL, &length);
129          ASSERT (result != NULL);
130          ASSERT (length == u8_strlen (expected));
131          ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
132          if (o)
133            {
134              for (i = 0; i < 10; i++)
135                ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
136              ASSERT (offsets[10] == MAGIC);
137              free (offsets);
138            }
139          free (result);
140        }
141    }
142  for (h = 0; h < SIZEOF (handlers); h++)
143    {
144      enum iconv_ilseq_handler handler = handlers[h];
145      static const char input[] = "\202\261\202\361\202\311\202\277\202\315"; /* ��������������� in Shift_JIS */
146      static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* ��������������� */
147      for (o = 0; o < 2; o++)
148        {
149          size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
150          size_t length;
151          uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler,
152                                                   input, strlen (input),
153                                                   offsets,
154                                                   NULL, &length);
155          ASSERT (result != NULL);
156          ASSERT (length == u8_strlen (expected));
157          ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
158          if (o)
159            {
160              for (i = 0; i < 10; i++)
161                ASSERT (offsets[i] == ((i % 2) == 0 ? (i / 2) * 3 : (size_t)(-1)));
162              ASSERT (offsets[10] == MAGIC);
163              free (offsets);
164            }
165          free (result);
166        }
167    }
168  for (h = 0; h < SIZEOF (handlers); h++)
169    {
170      enum iconv_ilseq_handler handler = handlers[h];
171      static const char input[] = "\033$B$3$s$K$A$O\033(B"; /* ��������������� in ISO-2022-JP-2 */
172      static const uint8_t expected[] = "\343\201\223\343\202\223\343\201\253\343\201\241\343\201\257"; /* ��������������� */
173      for (o = 0; o < 2; o++)
174        {
175          size_t *offsets = (o ? new_offsets (strlen (input)) : NULL);
176          size_t length;
177          uint8_t *result = u8_conv_from_encoding ("autodetect_jp", handler,
178                                                   input, strlen (input),
179                                                   offsets,
180                                                   NULL, &length);
181          ASSERT (result != NULL);
182          ASSERT (length == u8_strlen (expected));
183          ASSERT (u8_cmp (result, expected, u8_strlen (expected)) == 0);
184          if (o)
185            {
186              for (i = 0; i < 16; i++)
187                ASSERT (offsets[i] == (i == 0 ? 0 :
188                                       i == 5 ? 3 :
189                                       i == 7 ? 6 :
190                                       i == 9 ? 9 :
191                                       i == 11 ? 12 :
192                                       i == 13 ? 15 :
193                                       (size_t)(-1)));
194              ASSERT (offsets[16] == MAGIC);
195              free (offsets);
196            }
197          free (result);
198        }
199    }
200# endif
201
202#endif
203
204  return 0;
205}
206