| 1 | /* |
| 2 | * Copyright (c) 2015, Intel Corporation |
| 3 | * |
| 4 | * Redistribution and use in source and binary forms, with or without |
| 5 | * modification, are permitted provided that the following conditions are met: |
| 6 | * |
| 7 | * * Redistributions of source code must retain the above copyright notice, |
| 8 | * this list of conditions and the following disclaimer. |
| 9 | * * Redistributions in binary form must reproduce the above copyright |
| 10 | * notice, this list of conditions and the following disclaimer in the |
| 11 | * documentation and/or other materials provided with the distribution. |
| 12 | * * Neither the name of Intel Corporation nor the names of its contributors |
| 13 | * may be used to endorse or promote products derived from this software |
| 14 | * without specific prior written permission. |
| 15 | * |
| 16 | * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" |
| 17 | * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE |
| 18 | * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE |
| 19 | * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE |
| 20 | * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR |
| 21 | * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF |
| 22 | * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS |
| 23 | * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN |
| 24 | * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) |
| 25 | * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE |
| 26 | * POSSIBILITY OF SUCH DAMAGE. |
| 27 | */ |
| 28 | |
| 29 | #include "config.h" |
| 30 | |
| 31 | #include "utf8_validate.h" |
| 32 | |
| 33 | #include "ue2common.h" |
| 34 | #include "util/unicode_def.h" |
| 35 | |
| 36 | #include <cstring> |
| 37 | |
| 38 | namespace ue2 { |
| 39 | |
| 40 | static |
| 41 | bool hasValidContBytes(const u8 *s, size_t num) { |
| 42 | /* continuer bytes must all be of the form 10xx xxxx */ |
| 43 | for (size_t i = 0; i < num; i++) { |
| 44 | if ((s[i] & 0xc0) != UTF_CONT_BYTE_HEADER) { |
| 45 | return false; |
| 46 | } |
| 47 | } |
| 48 | return true; |
| 49 | } |
| 50 | |
| 51 | static |
| 52 | bool isAllowedCodepoint(u32 val) { |
| 53 | if (val >= 0xd800 && val <= 0xdfff) { |
| 54 | return false; // High and low surrogate halves |
| 55 | } |
| 56 | if (val > 0x10ffff) { |
| 57 | return false; // As per limit in RFC 3629 |
| 58 | } |
| 59 | |
| 60 | return true; |
| 61 | } |
| 62 | |
| 63 | bool isValidUtf8(const char *expression, const size_t len) { |
| 64 | if (!expression) { |
| 65 | return true; |
| 66 | } |
| 67 | |
| 68 | const u8 *s = (const u8 *)expression; |
| 69 | u32 val; |
| 70 | |
| 71 | size_t i = 0; |
| 72 | while (i < len) { |
| 73 | DEBUG_PRINTF("byte %zu: 0x%02x\n" , i, s[i]); |
| 74 | // One octet. |
| 75 | if (s[i] < 0x7f) { |
| 76 | DEBUG_PRINTF("one octet\n" ); |
| 77 | i++; |
| 78 | continue; |
| 79 | } |
| 80 | |
| 81 | // Two octets. |
| 82 | if ((s[i] & 0xe0) == UTF_TWO_BYTE_HEADER) { |
| 83 | DEBUG_PRINTF("two octets\n" ); |
| 84 | if (i + 2 > len) { |
| 85 | break; |
| 86 | } |
| 87 | if (!hasValidContBytes(&s[i] + 1, 1)) { |
| 88 | break; |
| 89 | } |
| 90 | val = ((s[i] & 0x1f) << 6) | (s[i + 1] & UTF_CONT_BYTE_VALUE_MASK); |
| 91 | DEBUG_PRINTF("val=0x%x\n" , val); |
| 92 | if (val < 1U << 7) { |
| 93 | DEBUG_PRINTF("overlong encoding\n" ); |
| 94 | break; |
| 95 | } |
| 96 | if (!isAllowedCodepoint(val)) { |
| 97 | DEBUG_PRINTF("codepoint not allowed\n" ); |
| 98 | break; |
| 99 | } |
| 100 | i += 2; |
| 101 | continue; |
| 102 | } |
| 103 | |
| 104 | // Three octets. |
| 105 | if ((s[i] & 0xf0) == UTF_THREE_BYTE_HEADER) { |
| 106 | DEBUG_PRINTF("three octets\n" ); |
| 107 | if (i + 3 > len) { |
| 108 | break; |
| 109 | } |
| 110 | if (!hasValidContBytes(&s[i] + 1, 2)) { |
| 111 | break; |
| 112 | } |
| 113 | val = ((s[i] & 0xf) << 12) | |
| 114 | ((s[i + 1] & UTF_CONT_BYTE_VALUE_MASK) << 6) | |
| 115 | (s[i + 2] & UTF_CONT_BYTE_VALUE_MASK); |
| 116 | if (val < 1U << 11) { |
| 117 | DEBUG_PRINTF("overlong encoding\n" ); |
| 118 | break; |
| 119 | } |
| 120 | if (!isAllowedCodepoint(val)) { |
| 121 | DEBUG_PRINTF("codepoint not allowed\n" ); |
| 122 | break; |
| 123 | } |
| 124 | i += 3; |
| 125 | continue; |
| 126 | } |
| 127 | |
| 128 | // Four octets. |
| 129 | if ((s[i] & 0xf8) == UTF_FOUR_BYTE_HEADER) { |
| 130 | DEBUG_PRINTF("four octets\n" ); |
| 131 | if (i + 4 > len) { |
| 132 | break; |
| 133 | } |
| 134 | if (!hasValidContBytes(&s[i] + 1, 3)) { |
| 135 | break; |
| 136 | } |
| 137 | val = ((s[i] & 0xf) << 18) | |
| 138 | ((s[i + 1] & UTF_CONT_BYTE_VALUE_MASK) << 12) | |
| 139 | ((s[i + 2] & UTF_CONT_BYTE_VALUE_MASK) << 6) | |
| 140 | (s[i + 3] & UTF_CONT_BYTE_VALUE_MASK); |
| 141 | if (val < 1U << 16) { |
| 142 | DEBUG_PRINTF("overlong encoding\n" ); |
| 143 | break; |
| 144 | } |
| 145 | if (!isAllowedCodepoint(val)) { |
| 146 | DEBUG_PRINTF("codepoint not allowed\n" ); |
| 147 | break; |
| 148 | } |
| 149 | i += 4; |
| 150 | continue; |
| 151 | } |
| 152 | |
| 153 | // Something else? |
| 154 | DEBUG_PRINTF("bad byte 0x%02x\n" , s[i]); |
| 155 | break; |
| 156 | } |
| 157 | |
| 158 | DEBUG_PRINTF("i=%zu, len=%zu\n" , i, len); |
| 159 | return i == len; |
| 160 | } |
| 161 | |
| 162 | } // namespace ue2 |
| 163 | |