1 /* $NetBSD: test-utf8.c,v 1.1.1.1 2011/04/13 18:16:00 elric Exp $ */ 2 3 /* 4 * Copyright (c) 2004 Kungliga Tekniska Högskolan 5 * (Royal Institute of Technology, Stockholm, Sweden). 6 * All rights reserved. 7 * 8 * Redistribution and use in source and binary forms, with or without 9 * modification, are permitted provided that the following conditions 10 * are met: 11 * 12 * 1. Redistributions of source code must retain the above copyright 13 * notice, this list of conditions and the following disclaimer. 14 * 15 * 2. Redistributions in binary form must reproduce the above copyright 16 * notice, this list of conditions and the following disclaimer in the 17 * documentation and/or other materials provided with the distribution. 18 * 19 * 3. Neither the name of the Institute nor the names of its contributors 20 * may be used to endorse or promote products derived from this software 21 * without specific prior written permission. 22 * 23 * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND 24 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 25 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 26 * ARE DISCLAIMED. IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE 27 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 28 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 29 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 30 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 31 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 32 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 33 * SUCH DAMAGE. 34 */ 35 36 #ifdef HAVE_CONFIG_H 37 #include <config.h> 38 #endif 39 #include <stdio.h> 40 #include <string.h> 41 #include <err.h> 42 #include "windlocl.h" 43 44 static const char *failing_testcases[] = { 45 "\x80", 46 "\xFF", 47 "\xC0", 48 "\xDF", 49 "\xE0", 50 "\xEF", 51 "\xF0", 52 "\xF7", 53 "\xC0\x01", 54 "\xC0\x7F", 55 "\xC0\xFF", 56 "\xC0\x80\x80", 57 "\xE0\x01", 58 "\xE0\x7F", 59 "\xE0\x80", 60 "\xE0\xFF", 61 "\xE0\x80\x20", 62 "\xE0\x80\xFF", 63 "\xE0\x80\x80\x80", 64 "\xF0\x01", 65 "\xF0\x80", 66 "\xF0\x80\x01", 67 "\xF0\x80\x80", 68 "\xF0\x80\x80\x01", 69 "\xF0\x80\x80\xFF", 70 NULL 71 }; 72 73 #define MAX_LENGTH 10 74 75 struct testcase { 76 const char *utf8_str; 77 size_t len; 78 uint32_t u[MAX_LENGTH]; 79 int invalid_ucs2; 80 }; 81 82 static const struct testcase testcases[] = { 83 {"", 0, {0}}, 84 {"\x01", 1, {1}}, 85 {"\x7F", 1, {0x7F}}, 86 {"\x01\x7F", 2, {0x01, 0x7F}}, 87 {"\xC0\x80", 1, {0}}, 88 {"\xC0\x81", 1, {1}}, 89 {"\xC1\x80", 1, {0x40}}, 90 {"\xDF\xBF", 1, {0x7FF}}, 91 {"\xE0\x80\x80", 1, {0}}, 92 {"\xE0\x80\x81", 1, {1}}, 93 {"\xE0\x81\x80", 1, {0x40}}, 94 {"\xE1\x80\x80", 1, {0x1000}}, 95 {"\xEF\xBF\xBF", 1, {0xFFFF}}, 96 {"\xF0\x80\x80\x80", 1, {0}}, 97 {"\xF0\x80\x80\x81", 1, {1}}, 98 {"\xF0\x80\x81\x80", 1, {0x40}}, 99 {"\xF0\x81\x80\x80", 1, {0x1000}}, 100 {"\xF1\x80\x80\x80", 1, {0x40000}}, 101 {"\xF7\xBF\xBF\xBF", 1, {0X1FFFFF}, 1}, 102 }; 103 104 int 105 main(void) 106 { 107 unsigned failures = 0; 108 unsigned i; 109 const char **s; 110 int ret; 111 size_t len, len2; 112 uint32_t u[MAX_LENGTH]; 113 char str[MAX_LENGTH * 4]; 114 115 for (s = failing_testcases; *s != NULL; ++s) { 116 len = MAX_LENGTH; 117 ret = wind_utf8ucs4(*s, u, &len); 118 if (ret == 0) { 119 printf("utf8 decode of \"%s\" should have failed\n", *s); 120 ++failures; 121 } 122 } 123 124 for (i = 0; i < sizeof(testcases)/sizeof(testcases[0]); ++i) { 125 const struct testcase *t = &testcases[i]; 126 127 ret = wind_utf8ucs4_length(t->utf8_str, &len); 128 if (ret) { 129 printf("utf8ucs4 length of \"%s\" should have succeeded\n", 130 t->utf8_str); 131 ++failures; 132 continue; 133 } 134 if (len != t->len) { 135 printf("utf8ucs4_length of \"%s\" has wrong length: " 136 "expected: %u, actual: %u\n", 137 t->utf8_str, (unsigned int)t->len, (unsigned int)len); 138 ++failures; 139 continue; 140 } 141 142 len = MAX_LENGTH; 143 ret = wind_utf8ucs4(t->utf8_str, u, &len); 144 if (ret) { 145 printf("utf8 decode of \"%s\" should have succeeded\n", 146 t->utf8_str); 147 ++failures; 148 continue; 149 } 150 if (len != t->len) { 151 printf("utf8 decode of \"%s\" has wrong length: " 152 "expected: %u, actual: %u\n", 153 t->utf8_str, (unsigned int)t->len, (unsigned int)len); 154 ++failures; 155 continue; 156 } 157 if (memcmp(t->u, u, len * sizeof(uint32_t)) != 0) { 158 printf("utf8 decode of \"%s\" has wrong data\n", 159 t->utf8_str); 160 ++failures; 161 continue; 162 } 163 if (t->invalid_ucs2 == 0) { 164 len2 = sizeof(str); 165 ret = wind_ucs4utf8(u, len, str, &len2); 166 if (ret) { 167 printf("ucs4 decode of \"%s\" should have succeeded\n", 168 t->utf8_str); 169 ++failures; 170 continue; 171 } 172 } 173 } 174 175 return failures != 0; 176 } 177