UNPKG

8.29 kBJavaScriptView Raw
1"use strict";
2
3// Description of supported double byte encodings and aliases.
4// Tables are not require()-d until they are needed to speed up library load.
5// require()-s are direct to support Browserify.
6
7module.exports = {
8
9 // == Japanese/ShiftJIS ====================================================
10 // All japanese encodings are based on JIS X set of standards:
11 // JIS X 0201 - Single-byte encoding of ASCII + ¥ + Kana chars at 0xA1-0xDF.
12 // JIS X 0208 - Main set of 6879 characters, placed in 94x94 plane, to be encoded by 2 bytes.
13 // Has several variations in 1978, 1983, 1990 and 1997.
14 // JIS X 0212 - Supplementary plane of 6067 chars in 94x94 plane. 1990. Effectively dead.
15 // JIS X 0213 - Extension and modern replacement of 0208 and 0212. Total chars: 11233.
16 // 2 planes, first is superset of 0208, second - revised 0212.
17 // Introduced in 2000, revised 2004. Some characters are in Unicode Plane 2 (0x2xxxx)
18
19 // Byte encodings are:
20 // * Shift_JIS: Compatible with 0201, uses not defined chars in top half as lead bytes for double-byte
21 // encoding of 0208. Lead byte ranges: 0x81-0x9F, 0xE0-0xEF; Trail byte ranges: 0x40-0x7E, 0x80-0x9E, 0x9F-0xFC.
22 // Windows CP932 is a superset of Shift_JIS. Some companies added more chars, notably KDDI.
23 // * EUC-JP: Up to 3 bytes per character. Used mostly on *nixes.
24 // 0x00-0x7F - lower part of 0201
25 // 0x8E, 0xA1-0xDF - upper part of 0201
26 // (0xA1-0xFE)x2 - 0208 plane (94x94).
27 // 0x8F, (0xA1-0xFE)x2 - 0212 plane (94x94).
28 // * JIS X 208: 7-bit, direct encoding of 0208. Byte ranges: 0x21-0x7E (94 values). Uncommon.
29 // Used as-is in ISO2022 family.
30 // * ISO2022-JP: Stateful encoding, with escape sequences to switch between ASCII,
31 // 0201-1976 Roman, 0208-1978, 0208-1983.
32 // * ISO2022-JP-1: Adds esc seq for 0212-1990.
33 // * ISO2022-JP-2: Adds esc seq for GB2313-1980, KSX1001-1992, ISO8859-1, ISO8859-7.
34 // * ISO2022-JP-3: Adds esc seq for 0201-1976 Kana set, 0213-2000 Planes 1, 2.
35 // * ISO2022-JP-2004: Adds 0213-2004 Plane 1.
36 //
37 // After JIS X 0213 appeared, Shift_JIS-2004, EUC-JISX0213 and ISO2022-JP-2004 followed, with just changing the planes.
38 //
39 // Overall, it seems that it's a mess :( http://www8.plala.or.jp/tkubota1/unicode-symbols-map2.html
40
41 'shiftjis': {
42 type: '_dbcs',
43 table: function() { return require('./tables/shiftjis.json') },
44 encodeAdd: {'\u00a5': 0x5C, '\u203E': 0x7E},
45 encodeSkipVals: [{from: 0xED40, to: 0xF940}],
46 },
47 'csshiftjis': 'shiftjis',
48 'mskanji': 'shiftjis',
49 'sjis': 'shiftjis',
50 'windows31j': 'shiftjis',
51 'ms31j': 'shiftjis',
52 'xsjis': 'shiftjis',
53 'windows932': 'shiftjis',
54 'ms932': 'shiftjis',
55 '932': 'shiftjis',
56 'cp932': 'shiftjis',
57
58 'eucjp': {
59 type: '_dbcs',
60 table: function() { return require('./tables/eucjp.json') },
61 encodeAdd: {'\u00a5': 0x5C, '\u203E': 0x7E},
62 },
63
64 // TODO: KDDI extension to Shift_JIS
65 // TODO: IBM CCSID 942 = CP932, but F0-F9 custom chars and other char changes.
66 // TODO: IBM CCSID 943 = Shift_JIS = CP932 with original Shift_JIS lower 128 chars.
67
68
69 // == Chinese/GBK ==========================================================
70 // http://en.wikipedia.org/wiki/GBK
71 // We mostly implement W3C recommendation: https://www.w3.org/TR/encoding/#gbk-encoder
72
73 // Oldest GB2312 (1981, ~7600 chars) is a subset of CP936
74 'gb2312': 'cp936',
75 'gb231280': 'cp936',
76 'gb23121980': 'cp936',
77 'csgb2312': 'cp936',
78 'csiso58gb231280': 'cp936',
79 'euccn': 'cp936',
80
81 // Microsoft's CP936 is a subset and approximation of GBK.
82 'windows936': 'cp936',
83 'ms936': 'cp936',
84 '936': 'cp936',
85 'cp936': {
86 type: '_dbcs',
87 table: function() { return require('./tables/cp936.json') },
88 },
89
90 // GBK (~22000 chars) is an extension of CP936 that added user-mapped chars and some other.
91 'gbk': {
92 type: '_dbcs',
93 table: function() { return require('./tables/cp936.json').concat(require('./tables/gbk-added.json')) },
94 },
95 'xgbk': 'gbk',
96 'isoir58': 'gbk',
97
98 // GB18030 is an algorithmic extension of GBK.
99 // Main source: https://www.w3.org/TR/encoding/#gbk-encoder
100 // http://icu-project.org/docs/papers/gb18030.html
101 // http://source.icu-project.org/repos/icu/data/trunk/charset/data/xml/gb-18030-2000.xml
102 // http://www.khngai.com/chinese/charmap/tblgbk.php?page=0
103 'gb18030': {
104 type: '_dbcs',
105 table: function() { return require('./tables/cp936.json').concat(require('./tables/gbk-added.json')) },
106 gb18030: function() { return require('./tables/gb18030-ranges.json') },
107 encodeSkipVals: [0x80],
108 encodeAdd: {'€': 0xA2E3},
109 },
110
111 'chinese': 'gb18030',
112
113
114 // == Korean ===============================================================
115 // EUC-KR, KS_C_5601 and KS X 1001 are exactly the same.
116 'windows949': 'cp949',
117 'ms949': 'cp949',
118 '949': 'cp949',
119 'cp949': {
120 type: '_dbcs',
121 table: function() { return require('./tables/cp949.json') },
122 },
123
124 'cseuckr': 'cp949',
125 'csksc56011987': 'cp949',
126 'euckr': 'cp949',
127 'isoir149': 'cp949',
128 'korean': 'cp949',
129 'ksc56011987': 'cp949',
130 'ksc56011989': 'cp949',
131 'ksc5601': 'cp949',
132
133
134 // == Big5/Taiwan/Hong Kong ================================================
135 // There are lots of tables for Big5 and cp950. Please see the following links for history:
136 // http://moztw.org/docs/big5/ http://www.haible.de/bruno/charsets/conversion-tables/Big5.html
137 // Variations, in roughly number of defined chars:
138 // * Windows CP 950: Microsoft variant of Big5. Canonical: http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP950.TXT
139 // * Windows CP 951: Microsoft variant of Big5-HKSCS-2001. Seems to be never public. http://me.abelcheung.org/articles/research/what-is-cp951/
140 // * Big5-2003 (Taiwan standard) almost superset of cp950.
141 // * Unicode-at-on (UAO) / Mozilla 1.8. Falling out of use on the Web. Not supported by other browsers.
142 // * Big5-HKSCS (-2001, -2004, -2008). Hong Kong standard.
143 // many unicode code points moved from PUA to Supplementary plane (U+2XXXX) over the years.
144 // Plus, it has 4 combining sequences.
145 // Seems that Mozilla refused to support it for 10 yrs. https://bugzilla.mozilla.org/show_bug.cgi?id=162431 https://bugzilla.mozilla.org/show_bug.cgi?id=310299
146 // because big5-hkscs is the only encoding to include astral characters in non-algorithmic way.
147 // Implementations are not consistent within browsers; sometimes labeled as just big5.
148 // MS Internet Explorer switches from big5 to big5-hkscs when a patch applied.
149 // Great discussion & recap of what's going on https://bugzilla.mozilla.org/show_bug.cgi?id=912470#c31
150 // In the encoder, it might make sense to support encoding old PUA mappings to Big5 bytes seq-s.
151 // Official spec: http://www.ogcio.gov.hk/en/business/tech_promotion/ccli/terms/doc/2003cmp_2008.txt
152 // http://www.ogcio.gov.hk/tc/business/tech_promotion/ccli/terms/doc/hkscs-2008-big5-iso.txt
153 //
154 // Current understanding of how to deal with Big5(-HKSCS) is in the Encoding Standard, http://encoding.spec.whatwg.org/#big5-encoder
155 // Unicode mapping (http://www.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/OTHER/BIG5.TXT) is said to be wrong.
156
157 'windows950': 'cp950',
158 'ms950': 'cp950',
159 '950': 'cp950',
160 'cp950': {
161 type: '_dbcs',
162 table: function() { return require('./tables/cp950.json') },
163 },
164
165 // Big5 has many variations and is an extension of cp950. We use Encoding Standard's as a consensus.
166 'big5': 'big5hkscs',
167 'big5hkscs': {
168 type: '_dbcs',
169 table: function() { return require('./tables/cp950.json').concat(require('./tables/big5-added.json')) },
170 encodeSkipVals: [0xa2cc],
171 },
172
173 'cnbig5': 'big5hkscs',
174 'csbig5': 'big5hkscs',
175 'xxbig5': 'big5hkscs',
176};