browser/components/translation/cld2/public/encodings.h@6474c204b198 (annotated)
browser/components/translation/cld2/public/encodings.h
Wed, 31 Dec 2014 06:09:35 +0100
- author
- Michael Schloh von Bennewitz <michael@schloh.com>
- date
- Wed, 31 Dec 2014 06:09:35 +0100
- changeset 0
- 6474c204b198
- permissions
- -rw-r--r--
Cloned upstream origin tor-browser at tor-browser-31.3.0esr-4.5-1-build1
revision ID fc1c9ff7c1b2defdbc039f12214767608f46423f for hacking purpose.
| michael@0 | 1 | // Copyright 2013 Google Inc. All Rights Reserved. |
| michael@0 | 2 | // |
| michael@0 | 3 | // Licensed under the Apache License, Version 2.0 (the "License"); |
| michael@0 | 4 | // you may not use this file except in compliance with the License. |
| michael@0 | 5 | // You may obtain a copy of the License at |
| michael@0 | 6 | // |
| michael@0 | 7 | // http://www.apache.org/licenses/LICENSE-2.0 |
| michael@0 | 8 | // |
| michael@0 | 9 | // Unless required by applicable law or agreed to in writing, software |
| michael@0 | 10 | // distributed under the License is distributed on an "AS IS" BASIS, |
| michael@0 | 11 | // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| michael@0 | 12 | // See the License for the specific language governing permissions and |
| michael@0 | 13 | // limitations under the License. |
| michael@0 | 14 | |
| michael@0 | 15 | // |
| michael@0 | 16 | // Author: dsites@google.com (Dick Sites) |
| michael@0 | 17 | // |
| michael@0 | 18 | |
| michael@0 | 19 | #ifndef I18N_ENCODINGS_CLD2_PUBLIC_ENCODINGS_H__ |
| michael@0 | 20 | #define I18N_ENCODINGS_CLD2_PUBLIC_ENCODINGS_H__ |
| michael@0 | 21 | |
| michael@0 | 22 | namespace CLD2 { |
| michael@0 | 23 | |
| michael@0 | 24 | enum Encoding { |
| michael@0 | 25 | ISO_8859_1 = 0, // ASCII |
| michael@0 | 26 | ISO_8859_2 = 1, // Latin2 |
| michael@0 | 27 | ISO_8859_3 = 2, // |
| michael@0 | 28 | ISO_8859_4 = 3, // Latin4 |
| michael@0 | 29 | ISO_8859_5 = 4, // ISO-8859-5 |
| michael@0 | 30 | ISO_8859_6 = 5, // Arabic |
| michael@0 | 31 | ISO_8859_7 = 6, // Greek |
| michael@0 | 32 | ISO_8859_8 = 7, // Hebrew |
| michael@0 | 33 | ISO_8859_9 = 8, // |
| michael@0 | 34 | ISO_8859_10 = 9, // |
| michael@0 | 35 | JAPANESE_EUC_JP = 10, // EUC_JP |
| michael@0 | 36 | JAPANESE_SHIFT_JIS = 11, // SJS |
| michael@0 | 37 | JAPANESE_JIS = 12, // JIS |
| michael@0 | 38 | CHINESE_BIG5 = 13, // BIG5 |
| michael@0 | 39 | CHINESE_GB = 14, // GB |
| michael@0 | 40 | CHINESE_EUC_CN = 15, // Misnamed. Should be EUC_TW. Was Basis Tech |
| michael@0 | 41 | // CNS11643EUC, before that EUC-CN(!) |
| michael@0 | 42 | KOREAN_EUC_KR = 16, // KSC |
| michael@0 | 43 | UNICODE_UNUSED = 17, // Unicode |
| michael@0 | 44 | CHINESE_EUC_DEC = 18, // Misnamed. Should be EUC_TW. Was |
| michael@0 | 45 | // CNS11643EUC, before that EUC. |
| michael@0 | 46 | CHINESE_CNS = 19, // Misnamed. Should be EUC_TW. Was |
| michael@0 | 47 | // CNS11643EUC, before that CNS. |
| michael@0 | 48 | CHINESE_BIG5_CP950 = 20, // BIG5_CP950 |
| michael@0 | 49 | JAPANESE_CP932 = 21, // CP932 |
| michael@0 | 50 | UTF8 = 22, |
| michael@0 | 51 | UNKNOWN_ENCODING = 23, |
| michael@0 | 52 | ASCII_7BIT = 24, // ISO_8859_1 with all characters <= 127. |
| michael@0 | 53 | RUSSIAN_KOI8_R = 25, // KOI8R |
| michael@0 | 54 | RUSSIAN_CP1251 = 26, // CP1251 |
| michael@0 | 55 | |
| michael@0 | 56 | //---------------------------------------------------------- |
| michael@0 | 57 | MSFT_CP1252 = 27, // 27: CP1252 aka MSFT euro ascii |
| michael@0 | 58 | RUSSIAN_KOI8_RU = 28, // CP21866 aka KOI8-U, used for Ukrainian. |
| michael@0 | 59 | // Misnamed, this is _not_ KOI8-RU but KOI8-U. |
| michael@0 | 60 | // KOI8-U is used much more often than KOI8-RU. |
| michael@0 | 61 | MSFT_CP1250 = 29, // CP1250 aka MSFT eastern european |
| michael@0 | 62 | ISO_8859_15 = 30, // aka ISO_8859_0 aka ISO_8859_1 euroized |
| michael@0 | 63 | //---------------------------------------------------------- |
| michael@0 | 64 | |
| michael@0 | 65 | //---------------------------------------------------------- |
| michael@0 | 66 | MSFT_CP1254 = 31, // used for Turkish |
| michael@0 | 67 | MSFT_CP1257 = 32, // used in Baltic countries |
| michael@0 | 68 | //---------------------------------------------------------- |
| michael@0 | 69 | |
| michael@0 | 70 | //---------------------------------------------------------- |
| michael@0 | 71 | //---------------------------------------------------------- |
| michael@0 | 72 | ISO_8859_11 = 33, // aka TIS-620, used for Thai |
| michael@0 | 73 | MSFT_CP874 = 34, // used for Thai |
| michael@0 | 74 | MSFT_CP1256 = 35, // used for Arabic |
| michael@0 | 75 | |
| michael@0 | 76 | //---------------------------------------------------------- |
| michael@0 | 77 | MSFT_CP1255 = 36, // Logical Hebrew Microsoft |
| michael@0 | 78 | ISO_8859_8_I = 37, // Iso Hebrew Logical |
| michael@0 | 79 | HEBREW_VISUAL = 38, // Iso Hebrew Visual |
| michael@0 | 80 | //---------------------------------------------------------- |
| michael@0 | 81 | |
| michael@0 | 82 | //---------------------------------------------------------- |
| michael@0 | 83 | CZECH_CP852 = 39, |
| michael@0 | 84 | CZECH_CSN_369103 = 40, // aka ISO_IR_139 aka KOI8_CS |
| michael@0 | 85 | MSFT_CP1253 = 41, // used for Greek |
| michael@0 | 86 | RUSSIAN_CP866 = 42, |
| michael@0 | 87 | //---------------------------------------------------------- |
| michael@0 | 88 | |
| michael@0 | 89 | //---------------------------------------------------------- |
| michael@0 | 90 | // Handled by iconv in glibc |
| michael@0 | 91 | ISO_8859_13 = 43, |
| michael@0 | 92 | ISO_2022_KR = 44, |
| michael@0 | 93 | GBK = 45, |
| michael@0 | 94 | GB18030 = 46, |
| michael@0 | 95 | BIG5_HKSCS = 47, |
| michael@0 | 96 | ISO_2022_CN = 48, |
| michael@0 | 97 | |
| michael@0 | 98 | //----------------------------------------------------------- |
| michael@0 | 99 | // Following 4 encodings are deprecated (font encodings) |
| michael@0 | 100 | TSCII = 49, |
| michael@0 | 101 | TAMIL_MONO = 50, |
| michael@0 | 102 | TAMIL_BI = 51, |
| michael@0 | 103 | JAGRAN = 52, |
| michael@0 | 104 | |
| michael@0 | 105 | |
| michael@0 | 106 | MACINTOSH_ROMAN = 53, |
| michael@0 | 107 | UTF7 = 54, |
| michael@0 | 108 | |
| michael@0 | 109 | //----------------------------------------------------------- |
| michael@0 | 110 | // Following 2 encodings are deprecated (font encodings) |
| michael@0 | 111 | BHASKAR = 55, // Indic encoding - Devanagari |
| michael@0 | 112 | HTCHANAKYA = 56, // 56 Indic encoding - Devanagari |
| michael@0 | 113 | |
| michael@0 | 114 | //----------------------------------------------------------- |
| michael@0 | 115 | UTF16BE = 57, // big-endian UTF-16 |
| michael@0 | 116 | UTF16LE = 58, // little-endian UTF-16 |
| michael@0 | 117 | UTF32BE = 59, // big-endian UTF-32 |
| michael@0 | 118 | UTF32LE = 60, // little-endian UTF-32 |
| michael@0 | 119 | //----------------------------------------------------------- |
| michael@0 | 120 | |
| michael@0 | 121 | //----------------------------------------------------------- |
| michael@0 | 122 | // An encoding that means "This is not text, but it may have some |
| michael@0 | 123 | // simple ASCII text embedded". Intended input conversion |
| michael@0 | 124 | // is to keep strings of >=4 seven-bit ASCII characters |
| michael@0 | 125 | BINARYENC = 61, |
| michael@0 | 126 | //----------------------------------------------------------- |
| michael@0 | 127 | |
| michael@0 | 128 | //----------------------------------------------------------- |
| michael@0 | 129 | // Some Web pages allow a mixture of HZ-GB and GB-2312 by using |
| michael@0 | 130 | // ~{ ... ~} for 2-byte pairs, and the browsers support this. |
| michael@0 | 131 | HZ_GB_2312 = 62, |
| michael@0 | 132 | //----------------------------------------------------------- |
| michael@0 | 133 | |
| michael@0 | 134 | //----------------------------------------------------------- |
| michael@0 | 135 | // Some external vendors make the common input error of |
| michael@0 | 136 | // converting MSFT_CP1252 to UTF8 *twice*. |
| michael@0 | 137 | UTF8UTF8 = 63, |
| michael@0 | 138 | //----------------------------------------------------------- |
| michael@0 | 139 | |
| michael@0 | 140 | //----------------------------------------------------------- |
| michael@0 | 141 | // Following 6 encodings are deprecated (font encodings) |
| michael@0 | 142 | TAM_ELANGO = 64, // Elango - Tamil |
| michael@0 | 143 | TAM_LTTMBARANI = 65, // Barani - Tamil |
| michael@0 | 144 | TAM_SHREE = 66, // Shree - Tamil |
| michael@0 | 145 | TAM_TBOOMIS = 67, // TBoomis - Tamil |
| michael@0 | 146 | TAM_TMNEWS = 68, // TMNews - Tamil |
| michael@0 | 147 | TAM_WEBTAMIL = 69, // Webtamil - Tamil |
| michael@0 | 148 | //----------------------------------------------------------- |
| michael@0 | 149 | |
| michael@0 | 150 | //----------------------------------------------------------- |
| michael@0 | 151 | // Shift_JIS variants used by Japanese cell phone carriers. |
| michael@0 | 152 | KDDI_SHIFT_JIS = 70, |
| michael@0 | 153 | DOCOMO_SHIFT_JIS = 71, |
| michael@0 | 154 | SOFTBANK_SHIFT_JIS = 72, |
| michael@0 | 155 | // ISO-2022-JP variants used by KDDI and SoftBank. |
| michael@0 | 156 | KDDI_ISO_2022_JP = 73, |
| michael@0 | 157 | SOFTBANK_ISO_2022_JP = 74, |
| michael@0 | 158 | //----------------------------------------------------------- |
| michael@0 | 159 | |
| michael@0 | 160 | NUM_ENCODINGS = 75, // Always keep this at the end. It is not a |
| michael@0 | 161 | // valid Encoding enum, it is only used to |
| michael@0 | 162 | // indicate the total number of Encodings. |
| michael@0 | 163 | }; |
| michael@0 | 164 | |
| michael@0 | 165 | } // End namespace CLD2 |
| michael@0 | 166 | |
| michael@0 | 167 | #endif // I18N_ENCODINGS_CLD2_PUBLIC_ENCODINGS_H__ |
| michael@0 | 168 | |
| michael@0 | 169 |
