1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
|
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.
//
// THIS IS AUTOGENERATED FILE
// USE ENCODINGDATA TOOL TO GENERATE SUCH FILE
//
namespace System.Text
{
internal static partial class EncodingTable
{
//
// s_encodingNames is the concatenation of all supported IANA names for each codepage.
// This is done rather than using a large readonly array of strings to avoid
// generating a large amount of code in the static constructor.
// Using indices from s_encodingNamesIndices, we binary search this string when mapping
// an encoding name to a codepage. Note that these names are all lowercase and are
// sorted alphabetically.
//
private const string s_encodingNames =
"ansi_x3.4-1968" + // 20127
"ansi_x3.4-1986" + // 20127
"ascii" + // 20127
"cp367" + // 20127
"cp819" + // 28591
"csascii" + // 20127
"csisolatin1" + // 28591
"csunicode11utf7" + // 65000
"ibm367" + // 20127
"ibm819" + // 28591
"iso-10646-ucs-2" + // 1200
"iso-8859-1" + // 28591
"iso-ir-100" + // 28591
"iso-ir-6" + // 20127
"iso646-us" + // 20127
"iso8859-1" + // 28591
"iso_646.irv:1991" + // 20127
"iso_8859-1" + // 28591
"iso_8859-1:1987" + // 28591
"l1" + // 28591
"latin1" + // 28591
"ucs-2" + // 1200
"unicode" + // 1200
"unicode-1-1-utf-7" + // 65000
"unicode-1-1-utf-8" + // 65001
"unicode-2-0-utf-7" + // 65000
"unicode-2-0-utf-8" + // 65001
"unicodefffe" + // 1201
"us" + // 20127
"us-ascii" + // 20127
"utf-16" + // 1200
"utf-16be" + // 1201
"utf-16le" + // 1200
"utf-32" + // 12000
"utf-32be" + // 12001
"utf-32le" + // 12000
"utf-7" + // 65000
"utf-8" + // 65001
"x-unicode-1-1-utf-7" + // 65000
"x-unicode-1-1-utf-8" + // 65001
"x-unicode-2-0-utf-7" + // 65000
"x-unicode-2-0-utf-8"; // 65001
//
// s_encodingNameIndices contains the start index of every encoding name in the string
// s_encodingNames. We infer the length of each string by looking at the start index
// of the next string.
//
private static readonly int[] s_encodingNameIndices = new int[]
{
0, // ansi_x3.4-1968 (20127)
14, // ansi_x3.4-1986 (20127)
28, // ascii (20127)
33, // cp367 (20127)
38, // cp819 (28591)
43, // csascii (20127)
50, // csisolatin1 (28591)
61, // csunicode11utf7 (65000)
76, // ibm367 (20127)
82, // ibm819 (28591)
88, // iso-10646-ucs-2 (1200)
103, // iso-8859-1 (28591)
113, // iso-ir-100 (28591)
123, // iso-ir-6 (20127)
131, // iso646-us (20127)
140, // iso8859-1 (28591)
149, // iso_646.irv:1991 (20127)
165, // iso_8859-1 (28591)
175, // iso_8859-1:1987 (28591)
190, // l1 (28591)
192, // latin1 (28591)
198, // ucs-2 (1200)
203, // unicode (1200)
210, // unicode-1-1-utf-7 (65000)
227, // unicode-1-1-utf-8 (65001)
244, // unicode-2-0-utf-7 (65000)
261, // unicode-2-0-utf-8 (65001)
278, // unicodefffe (1201)
289, // us (20127)
291, // us-ascii (20127)
299, // utf-16 (1200)
305, // utf-16be (1201)
313, // utf-16le (1200)
321, // utf-32 (12000)
327, // utf-32be (12001)
335, // utf-32le (12000)
343, // utf-7 (65000)
348, // utf-8 (65001)
353, // x-unicode-1-1-utf-7 (65000)
372, // x-unicode-1-1-utf-8 (65001)
391, // x-unicode-2-0-utf-7 (65000)
410, // x-unicode-2-0-utf-8 (65001)
429
};
//
// s_codePagesByName contains the list of supported codepages which match the encoding
// names listed in s_encodingNames. The way mapping works is we binary search
// s_encodingNames using s_encodingNamesIndices until we find a match for a given name.
// The index of the entry in s_encodingNamesIndices will be the index of codepage in
// s_codePagesByName.
//
private static readonly ushort[] s_codePagesByName = new ushort[]
{
20127, // ansi_x3.4-1968
20127, // ansi_x3.4-1986
20127, // ascii
20127, // cp367
28591, // cp819
20127, // csascii
28591, // csisolatin1
65000, // csunicode11utf7
20127, // ibm367
28591, // ibm819
1200, // iso-10646-ucs-2
28591, // iso-8859-1
28591, // iso-ir-100
20127, // iso-ir-6
20127, // iso646-us
28591, // iso8859-1
20127, // iso_646.irv:1991
28591, // iso_8859-1
28591, // iso_8859-1:1987
28591, // l1
28591, // latin1
1200, // ucs-2
1200, // unicode
65000, // unicode-1-1-utf-7
65001, // unicode-1-1-utf-8
65000, // unicode-2-0-utf-7
65001, // unicode-2-0-utf-8
1201, // unicodefffe
20127, // us
20127, // us-ascii
1200, // utf-16
1201, // utf-16be
1200, // utf-16le
12000, // utf-32
12001, // utf-32be
12000, // utf-32le
65000, // utf-7
65001, // utf-8
65000, // x-unicode-1-1-utf-7
65001, // x-unicode-1-1-utf-8
65000, // x-unicode-2-0-utf-7
65001 // x-unicode-2-0-utf-8
};
//
// When retrieving the value for System.Text.Encoding.WebName or
// System.Text.Encoding.EncodingName given System.Text.Encoding.CodePage,
// we perform a linear search on s_mappedCodePages to find the index of the
// given codepage. This is used to index WebNameIndices to get the start
// index of the web name in the string WebNames, and to index
// s_englishNameIndices to get the start of the English name in
// s_englishNames. In addition, this arrays indices correspond to the indices
// into s_uiFamilyCodePages and s_flags.
//
private static readonly ushort[] s_mappedCodePages = new ushort[]
{
1200, // utf-16
1201, // utf-16be
12000, // utf-32
12001, // utf-32be
20127, // us-ascii
28591, // iso-8859-1
65000, // utf-7
65001 // utf-8
};
//
// s_uiFamilyCodePages is indexed by the corresponding index in s_mappedCodePages.
//
private static readonly int[] s_uiFamilyCodePages = new int[]
{
1200,
1200,
1200,
1200,
1252,
1252,
1200,
1200
};
//
// s_webNames is a concatenation of the default encoding names
// for each code page. It is used in retrieving the value for
// System.Text.Encoding.WebName given System.Text.Encoding.CodePage.
// This is done rather than using a large readonly array of strings to avoid
// generating a large amount of code in the static constructor.
//
private const string s_webNames =
"utf-16" + // 1200
"utf-16BE" + // 1201
"utf-32" + // 12000
"utf-32BE" + // 12001
"us-ascii" + // 20127
"iso-8859-1" + // 28591
"utf-7" + // 65000
"utf-8"; // 65001
//
// s_webNameIndices contains the start index of each code page's default
// web name in the string s_webNames. It is indexed by an index into
// s_mappedCodePages.
//
private static readonly int[] s_webNameIndices = new int[]
{
0, // utf-16 (1200)
6, // utf-16be (1201)
14, // utf-32 (12000)
20, // utf-32be (12001)
28, // us-ascii (20127)
36, // iso-8859-1 (28591)
46, // utf-7 (65000)
51, // utf-8 (65001)
56
};
//
// s_englishNames is the concatenation of the English names for each codepage.
// It is used in retrieving the value for System.Text.Encoding.EncodingName
// given System.Text.Encoding.CodePage.
// This is done rather than using a large readonly array of strings to avoid
// generating a large amount of code in the static constructor.
//
private const string s_englishNames =
"Unicode" + // 1200
"Unicode (Big-Endian)" + // 1201
"Unicode (UTF-32)" + // 12000
"Unicode (UTF-32 Big-Endian)" + // 12001
"US-ASCII" + // 20127
"Western European (ISO)" + // 28591
"Unicode (UTF-7)" + // 65000
"Unicode (UTF-8)"; // 65001
//
// s_englishNameIndices contains the start index of each code page's English
// name in the string s_englishNames. It is indexed by an index into
// s_mappedCodePages.
//
private static readonly int[] s_englishNameIndices = new int[]
{
0, // Unicode (1200)
7, // Unicode (Big-Endian) (1201)
27, // Unicode (UTF-32) (12000)
43, // Unicode (UTF-32 Big-Endian) (12001)
70, // US-ASCII (20127)
78, // Western European (ISO) (28591)
100, // Unicode (UTF-7) (65000)
115, // Unicode (UTF-8) (65001)
130
};
// redeclaring these constants here for readability below
private const uint MIMECONTF_MAILNEWS = Encoding.MIMECONTF_MAILNEWS;
private const uint MIMECONTF_BROWSER = Encoding.MIMECONTF_BROWSER;
private const uint MIMECONTF_SAVABLE_MAILNEWS = Encoding.MIMECONTF_SAVABLE_MAILNEWS;
private const uint MIMECONTF_SAVABLE_BROWSER = Encoding.MIMECONTF_SAVABLE_BROWSER;
//
//s_flags is indexed by the corresponding index in s_mappedCodePages.
//
private static readonly uint[] s_flags = new uint[]
{
MIMECONTF_SAVABLE_BROWSER,
0,
0,
0,
MIMECONTF_MAILNEWS | MIMECONTF_SAVABLE_MAILNEWS,
MIMECONTF_MAILNEWS | MIMECONTF_BROWSER | MIMECONTF_SAVABLE_MAILNEWS | MIMECONTF_SAVABLE_BROWSER,
MIMECONTF_MAILNEWS | MIMECONTF_SAVABLE_MAILNEWS,
MIMECONTF_MAILNEWS | MIMECONTF_BROWSER | MIMECONTF_SAVABLE_MAILNEWS | MIMECONTF_SAVABLE_BROWSER
};
}
}
|
