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
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
|
// ==++==
//
// Copyright (c) Microsoft Corporation. All rights reserved.
//
// ==--==
////////////////////////////////////////////////////////////////////////////
//
// Class: CharacterInfo
//
// Purpose: This class implements a set of methods for retrieving
// character type information. Character type information is
// independent of culture and region.
//
// Date: August 12, 1998
//
////////////////////////////////////////////////////////////////////////////
namespace System.Globalization {
//This class has only static members and therefore doesn't need to be serialized.
using System;
using System.Threading;
using System.Runtime.InteropServices;
using System.Runtime.CompilerServices;
using System.Runtime.Versioning;
using System.Reflection;
using System.Security;
using System.Diagnostics.Contracts;
public static class CharUnicodeInfo
{
//--------------------------------------------------------------------//
// Internal Information //
//--------------------------------------------------------------------//
//
// Native methods to access the Unicode category data tables in charinfo.nlp.
//
internal const char HIGH_SURROGATE_START = '\ud800';
internal const char HIGH_SURROGATE_END = '\udbff';
internal const char LOW_SURROGATE_START = '\udc00';
internal const char LOW_SURROGATE_END = '\udfff';
internal const int UNICODE_CATEGORY_OFFSET = 0;
internal const int BIDI_CATEGORY_OFFSET = 1;
#pragma warning disable 414
static bool s_initialized = InitTable();
#pragma warning restore
// The native pointer to the 12:4:4 index table of the Unicode cateogry data.
[SecurityCritical]
unsafe static ushort* s_pCategoryLevel1Index;
[SecurityCritical]
unsafe static byte* s_pCategoriesValue;
// The native pointer to the 12:4:4 index table of the Unicode numeric data.
// The value of this index table is an index into the real value table stored in s_pNumericValues.
[SecurityCritical]
unsafe static ushort* s_pNumericLevel1Index;
// The numeric value table, which is indexed by s_pNumericLevel1Index.
// Every item contains the value for numeric value.
// unsafe static double* s_pNumericValues;
// To get around the IA64 alignment issue. Our double data is aligned in 8-byte boundary, but loader loads the embeded table starting
// at 4-byte boundary. This cause a alignment issue since double is 8-byte.
[SecurityCritical]
unsafe static byte* s_pNumericValues;
// The digit value table, which is indexed by s_pNumericLevel1Index. It shares the same indice as s_pNumericValues.
// Every item contains the value for decimal digit/digit value.
[SecurityCritical]
unsafe static DigitValues* s_pDigitValues;
internal const String UNICODE_INFO_FILE_NAME = "charinfo.nlp";
// The starting codepoint for Unicode plane 1. Plane 1 contains 0x010000 ~ 0x01ffff.
internal const int UNICODE_PLANE01_START = 0x10000;
//
// This is the header for the native data table that we load from UNICODE_INFO_FILE_NAME.
//
// Excplicit layout is used here since a syntax like char[16] can not be used in sequential layout.
[StructLayout(LayoutKind.Explicit)]
internal unsafe struct UnicodeDataHeader {
[FieldOffset(0)]
internal char TableName; // WCHAR[16]
[FieldOffset(0x20)]
internal ushort version; // WORD[4]
[FieldOffset(0x28)]
internal uint OffsetToCategoriesIndex; // DWORD
[FieldOffset(0x2c)]
internal uint OffsetToCategoriesValue; // DWORD
[FieldOffset(0x30)]
internal uint OffsetToNumbericIndex; // DWORD
[FieldOffset(0x34)]
internal uint OffsetToDigitValue; // DWORD
[FieldOffset(0x38)]
internal uint OffsetToNumbericValue; // DWORD
}
// NOTE: It's important to specify pack size here, since the size of the structure is 2 bytes. Otherwise,
// the default pack size will be 4.
[StructLayout(LayoutKind.Sequential, Pack=2)]
internal struct DigitValues {
internal sbyte decimalDigit;
internal sbyte digit;
}
unsafe private static int EndianSwap(int value)
{
if (!BitConverter.IsLittleEndian) {
byte *ptr = (byte *) &value;
int res;
byte *buf = (byte *) &res;
int t = sizeof(int) - 1;
for (int i = 0; i < sizeof(int); i++)
buf[t-i] = ptr[i];
return(res);
} else
return(value);
}
unsafe private static uint EndianSwap(uint value)
{
if (!BitConverter.IsLittleEndian) {
byte *ptr = (byte *) &value;
uint res;
byte *buf = (byte *) &res;
uint t = sizeof(uint) - 1;
for (uint i = 0; i < sizeof(uint); i++)
buf[t-i] = ptr[i];
return(res);
} else
return(value);
}
unsafe private static ushort EndianSwap(ushort value)
{
if (!BitConverter.IsLittleEndian) {
byte *ptr = (byte *) &value;
ushort res;
byte *buf = (byte *) &res;
ushort t = sizeof(ushort) - 1;
for (ushort i = 0; i < sizeof(ushort); i++)
buf[t-i] = ptr[i];
return(res);
} else
return(value);
}
unsafe private static double EndianSwap(double value)
{
if (!BitConverter.IsLittleEndian) {
byte *ptr = (byte *) &value;
double res;
byte *buf = (byte *) &res;
ushort t = sizeof(double) - 1;
for (ushort i = 0; i < sizeof(double); i++)
buf[t-i] = ptr[i];
return(res);
} else
return(value);
}
//We need to allocate the underlying table that provides us with the information that we
//use. We allocate this once in the class initializer and then we don't need to worry
//about it again.
//
[System.Security.SecuritySafeCritical] // auto-generated
[ResourceExposure(ResourceScope.None)]
[ResourceConsumption(ResourceScope.Process, ResourceScope.Process)]
unsafe static bool InitTable() {
// Go to native side and get pointer to the native table
byte * pDataTable = GlobalizationAssembly.GetGlobalizationResourceBytePtr(typeof(CharUnicodeInfo).Assembly, UNICODE_INFO_FILE_NAME);
UnicodeDataHeader* mainHeader = (UnicodeDataHeader*)pDataTable;
// Set up the native pointer to different part of the tables.
s_pCategoryLevel1Index = (ushort*) (pDataTable + EndianSwap(mainHeader->OffsetToCategoriesIndex));
s_pCategoriesValue = (byte*) (pDataTable + EndianSwap(mainHeader->OffsetToCategoriesValue));
s_pNumericLevel1Index = (ushort*) (pDataTable + EndianSwap(mainHeader->OffsetToNumbericIndex));
s_pNumericValues = (byte*) (pDataTable + EndianSwap(mainHeader->OffsetToNumbericValue));
s_pDigitValues = (DigitValues*) (pDataTable + EndianSwap(mainHeader->OffsetToDigitValue));
return true;
}
////////////////////////////////////////////////////////////////////////
//
// Actions:
// Convert the BMP character or surrogate pointed by index to a UTF32 value.
// This is similar to Char.ConvertToUTF32, but the difference is that
// it does not throw exceptions when invalid surrogate characters are passed in.
//
// WARNING: since it doesn't throw an exception it CAN return a value
// in the surrogate range D800-DFFF, which are not legal unicode values.
//
////////////////////////////////////////////////////////////////////////
internal static int InternalConvertToUtf32(String s, int index) {
Contract.Assert(s != null, "s != null");
Contract.Assert(index >= 0 && index < s.Length, "index < s.Length");
if (index < s.Length - 1) {
int temp1 = (int)s[index] - HIGH_SURROGATE_START;
if (temp1 >= 0 && temp1 <= 0x3ff) {
int temp2 = (int)s[index+1] - LOW_SURROGATE_START;
if (temp2 >= 0 && temp2 <= 0x3ff) {
// Convert the surrogate to UTF32 and get the result.
return ((temp1 * 0x400) + temp2 + UNICODE_PLANE01_START);
}
}
}
return ((int)s[index]);
}
////////////////////////////////////////////////////////////////////////
//
// Convert a character or a surrogate pair starting at index of string s
// to UTF32 value.
//
// Parameters:
// s The string
// index The starting index. It can point to a BMP character or
// a surrogate pair.
// len The length of the string.
// charLength [out] If the index points to a BMP char, charLength
// will be 1. If the index points to a surrogate pair,
// charLength will be 2.
//
// WARNING: since it doesn't throw an exception it CAN return a value
// in the surrogate range D800-DFFF, which are not legal unicode values.
//
// Returns:
// The UTF32 value
//
////////////////////////////////////////////////////////////////////////
internal static int InternalConvertToUtf32(String s, int index, out int charLength) {
Contract.Assert(s != null, "s != null");
Contract.Assert(s.Length > 0, "s.Length > 0");
Contract.Assert(index >= 0 && index < s.Length, "index >= 0 && index < s.Length");
charLength = 1;
if (index < s.Length - 1) {
int temp1 = (int)s[index] - HIGH_SURROGATE_START;
if (temp1 >= 0 && temp1 <= 0x3ff) {
int temp2 = (int)s[index+1] - LOW_SURROGATE_START;
if (temp2 >= 0 && temp2 <= 0x3ff) {
// Convert the surrogate to UTF32 and get the result.
charLength++;
return ((temp1 * 0x400) + temp2 + UNICODE_PLANE01_START);
}
}
}
return ((int)s[index]);
}
////////////////////////////////////////////////////////////////////////
//
// IsWhiteSpace
//
// Determines if the given character is a white space character.
//
////////////////////////////////////////////////////////////////////////
internal static bool IsWhiteSpace(String s, int index)
{
Contract.Assert(s != null, "s!=null");
Contract.Assert(index >= 0 && index < s.Length, "index >= 0 && index < s.Length");
UnicodeCategory uc = GetUnicodeCategory(s, index);
// In Unicode 3.0, U+2028 is the only character which is under the category "LineSeparator".
// And U+2029 is th eonly character which is under the category "ParagraphSeparator".
switch (uc) {
case (UnicodeCategory.SpaceSeparator):
case (UnicodeCategory.LineSeparator):
case (UnicodeCategory.ParagraphSeparator):
return (true);
}
return (false);
}
internal static bool IsWhiteSpace(char c)
{
UnicodeCategory uc = GetUnicodeCategory(c);
// In Unicode 3.0, U+2028 is the only character which is under the category "LineSeparator".
// And U+2029 is th eonly character which is under the category "ParagraphSeparator".
switch (uc) {
case (UnicodeCategory.SpaceSeparator):
case (UnicodeCategory.LineSeparator):
case (UnicodeCategory.ParagraphSeparator):
return (true);
}
return (false);
}
//
// This is called by the public char and string, index versions
//
// Note that for ch in the range D800-DFFF we just treat it as any other non-numeric character
//
[System.Security.SecuritySafeCritical] // auto-generated
internal unsafe static double InternalGetNumericValue(int ch) {
Contract.Assert(ch >= 0 && ch <= 0x10ffff, "ch is not in valid Unicode range.");
// Get the level 2 item from the highest 12 bit (8 - 19) of ch.
ushort index = EndianSwap(s_pNumericLevel1Index[ch >> 8]);
// Get the level 2 WORD offset from the 4 - 7 bit of ch. This provides the base offset of the level 3 table.
// The offset is referred to an float item in m_pNumericFloatData.
// Note that & has the lower precedence than addition, so don't forget the parathesis.
index = EndianSwap(s_pNumericLevel1Index[index + ((ch >> 4) & 0x000f)]);
byte* pBytePtr = (byte*)&(s_pNumericLevel1Index[index]);
// Get the result from the 0 -3 bit of ch.
#if WIN64
// To get around the IA64 alignment issue. Our double data is aligned in 8-byte boundary, but loader loads the embeded table starting
// at 4-byte boundary. This cause a alignment issue since double is 8-byte.
byte* pSourcePtr = &(s_pNumericValues[pBytePtr[(ch & 0x000f)] * sizeof(double)]);
if (((long)pSourcePtr % 8) != 0) {
// We are not aligned in 8-byte boundary. Do a copy.
double ret;
byte* retPtr = (byte*)&ret;
Buffer.Memcpy(retPtr, pSourcePtr, sizeof(double));
return (ret);
}
return (((double*)s_pNumericValues)[pBytePtr[(ch & 0x000f)]]);
#else
return EndianSwap(((double*)s_pNumericValues)[pBytePtr[(ch & 0x000f)]]);
#endif
}
//
// This is called by the public char and string, index versions
//
// Note that for ch in the range D800-DFFF we just treat it as any other non-numeric character
//
[System.Security.SecuritySafeCritical] // auto-generated
internal unsafe static DigitValues* InternalGetDigitValues(int ch) {
Contract.Assert(ch >= 0 && ch <= 0x10ffff, "ch is not in valid Unicode range.");
// Get the level 2 item from the highest 12 bit (8 - 19) of ch.
ushort index = s_pNumericLevel1Index[ch >> 8];
// Get the level 2 WORD offset from the 4 - 7 bit of ch. This provides the base offset of the level 3 table.
// The offset is referred to an float item in m_pNumericFloatData.
// Note that & has the lower precedence than addition, so don't forget the parathesis.
index = s_pNumericLevel1Index[index + ((ch >> 4) & 0x000f)];
byte* pBytePtr = (byte*)&(s_pNumericLevel1Index[index]);
// Get the result from the 0 -3 bit of ch.
return &(s_pDigitValues[pBytePtr[(ch & 0x000f)]]);
}
[System.Security.SecuritySafeCritical] // auto-generated
internal unsafe static sbyte InternalGetDecimalDigitValue(int ch) {
return (InternalGetDigitValues(ch)->decimalDigit);
}
[System.Security.SecuritySafeCritical] // auto-generated
internal unsafe static sbyte InternalGetDigitValue(int ch) {
return (InternalGetDigitValues(ch)->digit);
}
////////////////////////////////////////////////////////////////////////
//
//Returns the numeric value associated with the character c. If the character is a fraction,
// the return value will not be an integer. If the character does not have a numeric value, the return value is -1.
//
//Returns:
// the numeric value for the specified Unicode character. If the character does not have a numeric value, the return value is -1.
//Arguments:
// ch a Unicode character
//Exceptions:
// ArgumentNullException
// ArgumentOutOfRangeException
//
////////////////////////////////////////////////////////////////////////
public static double GetNumericValue(char ch) {
return (InternalGetNumericValue(ch));
}
public static double GetNumericValue(String s, int index) {
if (s == null) {
throw new ArgumentNullException("s");
}
if (index < 0 || index >= s.Length) {
throw new ArgumentOutOfRangeException("index", Environment.GetResourceString("ArgumentOutOfRange_Index"));
}
Contract.EndContractBlock();
return (InternalGetNumericValue(InternalConvertToUtf32(s, index)));
}
////////////////////////////////////////////////////////////////////////
//
//Returns the decimal digit value associated with the character c.
//
// The value should be from 0 ~ 9.
// If the character does not have a numeric value, the return value is -1.
// From Unicode.org: Decimal Digits. Digits that can be used to form decimal-radix numbers.
//Returns:
// the decimal digit value for the specified Unicode character. If the character does not have a decimal digit value, the return value is -1.
//Arguments:
// ch a Unicode character
//Exceptions:
// ArgumentNullException
// ArgumentOutOfRangeException
//
////////////////////////////////////////////////////////////////////////
public static int GetDecimalDigitValue(char ch) {
return (InternalGetDecimalDigitValue(ch));
}
public static int GetDecimalDigitValue(String s, int index) {
if (s == null) {
throw new ArgumentNullException("s");
}
if (index < 0 || index >= s.Length) {
throw new ArgumentOutOfRangeException("index", Environment.GetResourceString("ArgumentOutOfRange_Index"));
}
Contract.EndContractBlock();
return (InternalGetDecimalDigitValue(InternalConvertToUtf32(s, index)));
}
////////////////////////////////////////////////////////////////////////
//
//Action: Returns the digit value associated with the character c.
// If the character does not have a numeric value, the return value is -1.
// From Unicode.org: If the character represents a digit, not necessarily a decimal digit,
// the value is here. This covers digits which do not form decimal radix forms, such as the compatibility superscript digits.
//
// An example is: U+2460 IRCLED DIGIT ONE. This character has digit value 1, but does not have associcated decimal digit value.
//
//Returns:
// the digit value for the specified Unicode character. If the character does not have a digit value, the return value is -1.
//Arguments:
// ch a Unicode character
//Exceptions:
// ArgumentNullException
// ArgumentOutOfRangeException
//
////////////////////////////////////////////////////////////////////////
public static int GetDigitValue(char ch) {
return (InternalGetDigitValue(ch));
}
public static int GetDigitValue(String s, int index) {
if (s == null) {
throw new ArgumentNullException("s");
}
if (index < 0 || index >= s.Length) {
throw new ArgumentOutOfRangeException("index", Environment.GetResourceString("ArgumentOutOfRange_Index"));
}
Contract.EndContractBlock();
return (InternalGetDigitValue(InternalConvertToUtf32(s, index)));
}
public static UnicodeCategory GetUnicodeCategory(char ch)
{
return (InternalGetUnicodeCategory(ch)) ;
}
#if MONO
public static UnicodeCategory GetUnicodeCategory(int codePoint) => GetUnicodeCategory((char)codePoint);
#endif
public static UnicodeCategory GetUnicodeCategory(String s, int index)
{
if (s==null)
throw new ArgumentNullException("s");
if (((uint)index)>=((uint)s.Length)) {
throw new ArgumentOutOfRangeException("index");
}
Contract.EndContractBlock();
return InternalGetUnicodeCategory(s, index);
}
internal unsafe static UnicodeCategory InternalGetUnicodeCategory(int ch) {
return ((UnicodeCategory)InternalGetCategoryValue(ch, UNICODE_CATEGORY_OFFSET));
}
////////////////////////////////////////////////////////////////////////
//
//Action: Returns the Unicode Category property for the character c.
//Returns:
// an value in UnicodeCategory enum
//Arguments:
// ch a Unicode character
//Exceptions:
// None
//
//Note that this API will return values for D800-DF00 surrogate halves.
//
////////////////////////////////////////////////////////////////////////
[System.Security.SecuritySafeCritical] // auto-generated
internal unsafe static byte InternalGetCategoryValue(int ch, int offset) {
Contract.Assert(ch >= 0 && ch <= 0x10ffff, "ch is not in valid Unicode range.");
// Get the level 2 item from the highest 12 bit (8 - 19) of ch.
ushort index = EndianSwap(s_pCategoryLevel1Index[ch >> 8]);
// Get the level 2 WORD offset from the 4 - 7 bit of ch. This provides the base offset of the level 3 table.
// Note that & has the lower precedence than addition, so don't forget the parathesis.
index = EndianSwap(s_pCategoryLevel1Index[index + ((ch >> 4) & 0x000f)]);
byte* pBytePtr = (byte*)&(s_pCategoryLevel1Index[index]);
// Get the result from the 0 -3 bit of ch.
byte valueIndex = pBytePtr[(ch & 0x000f)];
byte uc = s_pCategoriesValue[valueIndex * 2 + offset];
//
// Make sure that OtherNotAssigned is the last category in UnicodeCategory.
// If that changes, change the following assertion as well.
//
//Contract.Assert(uc >= 0 && uc <= UnicodeCategory.OtherNotAssigned, "Table returns incorrect Unicode category");
return (uc);
}
// internal static BidiCategory GetBidiCategory(char ch) {
// return ((BidiCategory)InternalGetCategoryValue(c, BIDI_CATEGORY_OFFSET));
// }
internal static BidiCategory GetBidiCategory(String s, int index) {
if (s==null)
throw new ArgumentNullException("s");
if (((uint)index)>=((uint)s.Length)) {
throw new ArgumentOutOfRangeException("index");
}
Contract.EndContractBlock();
return ((BidiCategory)InternalGetCategoryValue(InternalConvertToUtf32(s, index), BIDI_CATEGORY_OFFSET));
}
////////////////////////////////////////////////////////////////////////
//
//Action: Returns the Unicode Category property for the character c.
//Returns:
// an value in UnicodeCategory enum
//Arguments:
// value a Unicode String
// index Index for the specified string.
//Exceptions:
// None
//
////////////////////////////////////////////////////////////////////////
internal static UnicodeCategory InternalGetUnicodeCategory(String value, int index) {
Contract.Assert(value != null, "value can not be null");
Contract.Assert(index < value.Length, "index < value.Length");
return (InternalGetUnicodeCategory(InternalConvertToUtf32(value, index)));
}
////////////////////////////////////////////////////////////////////////
//
// Get the Unicode category of the character starting at index. If the character is in BMP, charLength will return 1.
// If the character is a valid surrogate pair, charLength will return 2.
//
////////////////////////////////////////////////////////////////////////
internal static UnicodeCategory InternalGetUnicodeCategory(String str, int index, out int charLength) {
Contract.Assert(str != null, "str can not be null");
Contract.Assert(str.Length > 0, "str.Length > 0");;
Contract.Assert(index >= 0 && index < str.Length, "index >= 0 && index < str.Length");
return (InternalGetUnicodeCategory(InternalConvertToUtf32(str, index, out charLength)));
}
internal static bool IsCombiningCategory(UnicodeCategory uc) {
Contract.Assert(uc >= 0, "uc >= 0");
return (
uc == UnicodeCategory.NonSpacingMark ||
uc == UnicodeCategory.SpacingCombiningMark ||
uc == UnicodeCategory.EnclosingMark
);
}
}
}
|