1 | ;
|
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 |
|
7 | module.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 | };
|