1/* Test of character set conversion. 2 Copyright (C) 2007 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 "striconv.h" 22 23#if HAVE_ICONV 24# include <iconv.h> 25#endif 26 27#include <errno.h> 28#include <stdio.h> 29#include <stdlib.h> 30#include <string.h> 31 32#define ASSERT(expr) \ 33 do \ 34 { \ 35 if (!(expr)) \ 36 { \ 37 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \ 38 abort (); \ 39 } \ 40 } \ 41 while (0) 42 43int 44main () 45{ 46#if HAVE_ICONV 47 /* Assume that iconv() supports at least the encodings ASCII, ISO-8859-1, 48 and UTF-8. */ 49 iconv_t cd_88591_to_utf8 = iconv_open ("UTF-8", "ISO-8859-1"); 50 iconv_t cd_utf8_to_88591 = iconv_open ("ISO-8859-1", "UTF-8"); 51 52 ASSERT (cd_88591_to_utf8 != (iconv_t)(-1)); 53 ASSERT (cd_utf8_to_88591 != (iconv_t)(-1)); 54 55 /* ------------------------- Test mem_cd_iconv() ------------------------- */ 56 57 /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */ 58 { 59 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; 60 static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237"; 61 char *result = NULL; 62 size_t length = 0; 63 int retval = mem_cd_iconv (input, strlen (input), cd_88591_to_utf8, 64 &result, &length); 65 ASSERT (retval == 0); 66 ASSERT (length == strlen (expected)); 67 ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0); 68 free (result); 69 } 70 71 /* Test conversion from UTF-8 to ISO-8859-1 with no errors. */ 72 { 73 static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237"; 74 static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; 75 char *result = NULL; 76 size_t length = 0; 77 int retval = mem_cd_iconv (input, strlen (input), cd_utf8_to_88591, 78 &result, &length); 79 ASSERT (retval == 0); 80 ASSERT (length == strlen (expected)); 81 ASSERT (result != NULL && memcmp (result, expected, strlen (expected)) == 0); 82 free (result); 83 } 84 85 /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */ 86 { 87 static const char input[] = "\342\202\254"; /* EURO SIGN */ 88 char *result = NULL; 89 size_t length = 0; 90 int retval = mem_cd_iconv (input, strlen (input), cd_utf8_to_88591, 91 &result, &length); 92 ASSERT (retval == -1 && errno == EILSEQ); 93 ASSERT (result == NULL); 94 } 95 96 /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */ 97 { 98 static const char input[] = "\342"; 99 char *result = NULL; 100 size_t length = 0; 101 int retval = mem_cd_iconv (input, strlen (input), cd_utf8_to_88591, 102 &result, &length); 103 ASSERT (retval == 0); 104 ASSERT (length == 0); 105 if (result != NULL) 106 free (result); 107 } 108 109 /* ------------------------- Test str_cd_iconv() ------------------------- */ 110 111 /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */ 112 { 113 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; 114 static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237"; 115 char *result = str_cd_iconv (input, cd_88591_to_utf8); 116 ASSERT (result != NULL); 117 ASSERT (strcmp (result, expected) == 0); 118 free (result); 119 } 120 121 /* Test conversion from UTF-8 to ISO-8859-1 with no errors. */ 122 { 123 static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237"; 124 static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; 125 char *result = str_cd_iconv (input, cd_utf8_to_88591); 126 ASSERT (result != NULL); 127 ASSERT (strcmp (result, expected) == 0); 128 free (result); 129 } 130 131 /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */ 132 { 133 static const char input[] = "Costs: 27 \342\202\254"; /* EURO SIGN */ 134 char *result = str_cd_iconv (input, cd_utf8_to_88591); 135 ASSERT (result == NULL && errno == EILSEQ); 136 } 137 138 /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */ 139 { 140 static const char input[] = "\342"; 141 char *result = str_cd_iconv (input, cd_utf8_to_88591); 142 ASSERT (result != NULL); 143 ASSERT (strcmp (result, "") == 0); 144 free (result); 145 } 146 147 iconv_close (cd_88591_to_utf8); 148 iconv_close (cd_utf8_to_88591); 149 150 /* -------------------------- Test str_iconv() -------------------------- */ 151 152 /* Test conversion from ISO-8859-1 to UTF-8 with no errors. */ 153 { 154 static const char input[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; 155 static const char expected[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237"; 156 char *result = str_iconv (input, "ISO-8859-1", "UTF-8"); 157 ASSERT (result != NULL); 158 ASSERT (strcmp (result, expected) == 0); 159 free (result); 160 } 161 162 /* Test conversion from UTF-8 to ISO-8859-1 with no errors. */ 163 { 164 static const char input[] = "\303\204rger mit b\303\266sen B\303\274bchen ohne Augenma\303\237"; 165 static const char expected[] = "\304rger mit b\366sen B\374bchen ohne Augenma\337"; 166 char *result = str_iconv (input, "UTF-8", "ISO-8859-1"); 167 ASSERT (result != NULL); 168 ASSERT (strcmp (result, expected) == 0); 169 free (result); 170 } 171 172 /* Test conversion from UTF-8 to ISO-8859-1 with EILSEQ. */ 173 { 174 static const char input[] = "Costs: 27 \342\202\254"; /* EURO SIGN */ 175 char *result = str_iconv (input, "UTF-8", "ISO-8859-1"); 176 ASSERT (result == NULL && errno == EILSEQ); 177 } 178 179 /* Test conversion from UTF-8 to ISO-8859-1 with EINVAL. */ 180 { 181 static const char input[] = "\342"; 182 char *result = str_iconv (input, "UTF-8", "ISO-8859-1"); 183 ASSERT (result != NULL); 184 ASSERT (strcmp (result, "") == 0); 185 free (result); 186 } 187 188#endif 189 190 return 0; 191} 192