/
TextInfo.cs
760 lines (653 loc) · 29.3 KB
/
TextInfo.cs
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
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
using System.Buffers;
using System.Diagnostics;
using System.Diagnostics.CodeAnalysis;
using System.Runtime.CompilerServices;
using System.Runtime.InteropServices;
using System.Runtime.Serialization;
using System.Text;
using System.Text.Unicode;
namespace System.Globalization
{
/// <summary>
/// This Class defines behaviors specific to a writing system.
/// A writing system is the collection of scripts and orthographic rules
/// required to represent a language as text.
/// </summary>
public sealed partial class TextInfo : ICloneable, IDeserializationCallback
{
private enum Tristate : byte
{
NotInitialized = 0,
False = 1,
True = 2
}
private string? _listSeparator;
private bool _isReadOnly;
private readonly string _cultureName;
private readonly CultureData _cultureData;
private bool HasEmptyCultureName { get { return _cultureName.Length == 0; } }
// // Name of the text info we're using (ie: _cultureData.TextInfoName)
private readonly string _textInfoName;
private Tristate _isAsciiCasingSameAsInvariant = Tristate.NotInitialized;
// Invariant text info
internal static readonly TextInfo Invariant = new TextInfo(CultureData.Invariant, readOnly: true) { _isAsciiCasingSameAsInvariant = Tristate.True };
internal TextInfo(CultureData cultureData)
{
// This is our primary data source, we don't need most of the rest of this
_cultureData = cultureData;
_cultureName = _cultureData.CultureName;
_textInfoName = _cultureData.TextInfoName;
if (GlobalizationMode.UseNls)
{
_sortHandle = CompareInfo.NlsGetSortHandle(_textInfoName);
}
}
private TextInfo(CultureData cultureData, bool readOnly)
: this(cultureData)
{
SetReadOnlyState(readOnly);
}
void IDeserializationCallback.OnDeserialization(object? sender)
{
throw new PlatformNotSupportedException();
}
public int ANSICodePage => _cultureData.ANSICodePage;
public int OEMCodePage => _cultureData.OEMCodePage;
public int MacCodePage => _cultureData.MacCodePage;
public int EBCDICCodePage => _cultureData.EBCDICCodePage;
// Just use the LCID from our text info name
public int LCID => CultureInfo.GetCultureInfo(_textInfoName).LCID;
public string CultureName => _textInfoName;
public bool IsReadOnly => _isReadOnly;
public object Clone()
{
object o = MemberwiseClone();
((TextInfo)o).SetReadOnlyState(false);
return o;
}
/// <summary>
/// Create a cloned readonly instance or return the input one if it is
/// readonly.
/// </summary>
public static TextInfo ReadOnly(TextInfo textInfo)
{
ArgumentNullException.ThrowIfNull(textInfo);
if (textInfo.IsReadOnly)
{
return textInfo;
}
TextInfo clonedTextInfo = (TextInfo)(textInfo.MemberwiseClone());
clonedTextInfo.SetReadOnlyState(true);
return clonedTextInfo;
}
private void VerifyWritable()
{
if (_isReadOnly)
{
throw new InvalidOperationException(SR.InvalidOperation_ReadOnly);
}
}
internal void SetReadOnlyState(bool readOnly)
{
_isReadOnly = readOnly;
}
/// <summary>
/// Returns the string used to separate items in a list.
/// </summary>
public string ListSeparator
{
get => _listSeparator ??= _cultureData.ListSeparator;
set
{
ArgumentNullException.ThrowIfNull(value);
VerifyWritable();
_listSeparator = value;
}
}
/// <summary>
/// Converts the character or string to lower case. Certain locales
/// have different casing semantics from the file systems in Win32.
/// </summary>
public char ToLower(char c)
{
if (GlobalizationMode.Invariant)
{
return InvariantModeCasing.ToLower(c);
}
if (UnicodeUtility.IsAsciiCodePoint(c) && IsAsciiCasingSameAsInvariant)
{
return ToLowerAsciiInvariant(c);
}
return ChangeCase(c, toUpper: false);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
internal static char ToLowerInvariant(char c)
{
if (UnicodeUtility.IsAsciiCodePoint(c))
{
return ToLowerAsciiInvariant(c);
}
if (GlobalizationMode.Invariant)
{
return InvariantModeCasing.ToLower(c);
}
return Invariant.ChangeCase(c, toUpper: false);
}
public string ToLower(string str)
{
ArgumentNullException.ThrowIfNull(str);
if (GlobalizationMode.Invariant)
{
return InvariantModeCasing.ToLower(str);
}
return ChangeCaseCommon<ToLowerConversion>(str);
}
private unsafe char ChangeCase(char c, bool toUpper)
{
Debug.Assert(!GlobalizationMode.Invariant);
char dst = default;
ChangeCaseCore(&c, 1, &dst, 1, toUpper);
return dst;
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
internal void ChangeCaseToLower(ReadOnlySpan<char> source, Span<char> destination)
{
Debug.Assert(destination.Length >= source.Length);
ChangeCaseCommon<ToLowerConversion>(source, destination);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
internal void ChangeCaseToUpper(ReadOnlySpan<char> source, Span<char> destination)
{
Debug.Assert(destination.Length >= source.Length);
ChangeCaseCommon<ToUpperConversion>(source, destination);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private unsafe void ChangeCaseCommon<TConversion>(ReadOnlySpan<char> source, Span<char> destination) where TConversion : struct
{
Debug.Assert(!GlobalizationMode.Invariant);
Debug.Assert(typeof(TConversion) == typeof(ToUpperConversion) || typeof(TConversion) == typeof(ToLowerConversion));
if (source.IsEmpty)
{
return;
}
bool toUpper = typeof(TConversion) == typeof(ToUpperConversion); // JIT will treat this as a constant in release builds
int charsConsumed = 0;
if (IsAsciiCasingSameAsInvariant)
{
OperationStatus operationStatus = toUpper
? Ascii.ToUpper(source, destination, out charsConsumed)
: Ascii.ToLower(source, destination, out charsConsumed);
if (operationStatus != OperationStatus.InvalidData)
{
Debug.Assert(operationStatus == OperationStatus.Done);
return;
}
}
fixed (char* pSource = &MemoryMarshal.GetReference(source))
fixed (char* pDestination = &MemoryMarshal.GetReference(destination))
{
ChangeCaseCore(pSource + charsConsumed, source.Length - charsConsumed, pDestination + charsConsumed, destination.Length - charsConsumed, toUpper);
}
}
private unsafe string ChangeCaseCommon<TConversion>(string source) where TConversion : struct
{
Debug.Assert(typeof(TConversion) == typeof(ToUpperConversion) || typeof(TConversion) == typeof(ToLowerConversion));
bool toUpper = typeof(TConversion) == typeof(ToUpperConversion); // JIT will treat this as a constant in release builds
Debug.Assert(!GlobalizationMode.Invariant);
Debug.Assert(source != null);
// If the string is empty, we're done.
if (source.Length == 0)
{
return string.Empty;
}
fixed (char* pSource = source)
{
nuint currIdx = 0; // in chars
// If this culture's casing for ASCII is the same as invariant, try to take
// a fast path that'll work in managed code and ASCII rather than calling out
// to the OS for culture-aware casing.
if (IsAsciiCasingSameAsInvariant)
{
// Read 2 chars (one 32-bit integer) at a time
if (source.Length >= 2)
{
nuint lastIndexWhereCanReadTwoChars = (uint)source.Length - 2;
do
{
// See the comments in ChangeCaseCommon<TConversion>(ROS<char>, Span<char>) for a full explanation of the below code.
uint tempValue = Unsafe.ReadUnaligned<uint>(pSource + currIdx);
if (!Utf16Utility.AllCharsInUInt32AreAscii(tempValue))
{
goto NotAscii;
}
if ((toUpper) ? Utf16Utility.UInt32ContainsAnyLowercaseAsciiChar(tempValue) : Utf16Utility.UInt32ContainsAnyUppercaseAsciiChar(tempValue))
{
goto AsciiMustChangeCase;
}
currIdx += 2;
} while (currIdx <= lastIndexWhereCanReadTwoChars);
}
// If there's a single character left to convert, do it now.
if ((source.Length & 1) != 0)
{
uint tempValue = pSource[currIdx];
if (tempValue > 0x7Fu)
{
goto NotAscii;
}
if ((toUpper) ? ((tempValue - 'a') <= (uint)('z' - 'a')) : ((tempValue - 'A') <= (uint)('Z' - 'A')))
{
goto AsciiMustChangeCase;
}
}
// We got through all characters without finding anything that needed to change - done!
return source;
AsciiMustChangeCase:
{
// We reached ASCII data that requires a case change.
// This will necessarily allocate a new string, but let's try to stay within the managed (non-localization tables)
// conversion code path if we can.
string result = string.FastAllocateString(source.Length); // changing case uses simple folding: doesn't change UTF-16 code unit count
// copy existing known-good data into the result
Span<char> resultSpan = new Span<char>(ref result.GetRawStringData(), result.Length);
source.AsSpan(0, (int)currIdx).CopyTo(resultSpan);
// and re-run the fast span-based logic over the remainder of the data
ChangeCaseCommon<TConversion>(source.AsSpan((int)currIdx), resultSpan.Slice((int)currIdx));
return result;
}
}
NotAscii:
{
// We reached non-ASCII data *or* the requested culture doesn't map ASCII data the same way as the invariant culture.
// In either case we need to fall back to the localization tables.
string result = string.FastAllocateString(source.Length); // changing case uses simple folding: doesn't change UTF-16 code unit count
if (currIdx > 0)
{
// copy existing known-good data into the result
Span<char> resultSpan = new Span<char>(ref result.GetRawStringData(), result.Length);
source.AsSpan(0, (int)currIdx).CopyTo(resultSpan);
}
// and run the culture-aware logic over the remainder of the data
fixed (char* pResult = result)
{
ChangeCaseCore(pSource + currIdx, source.Length - (int)currIdx, pResult + currIdx, result.Length - (int)currIdx, toUpper);
}
return result;
}
}
}
internal static unsafe string ToLowerAsciiInvariant(string s)
{
if (s.Length == 0)
{
return string.Empty;
}
int i = s.AsSpan().IndexOfAnyInRange('A', 'Z');
if (i < 0)
{
return s;
}
fixed (char* pSource = s)
{
string result = string.FastAllocateString(s.Length);
fixed (char* pResult = result)
{
s.AsSpan(0, i).CopyTo(new Span<char>(pResult, result.Length));
pResult[i] = (char)(pSource[i] | 0x20);
i++;
while (i < s.Length)
{
pResult[i] = ToLowerAsciiInvariant(pSource[i]);
i++;
}
}
return result;
}
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static char ToLowerAsciiInvariant(char c)
{
if (char.IsAsciiLetterUpper(c))
{
// on x86, extending BYTE -> DWORD is more efficient than WORD -> DWORD
c = (char)(byte)(c | 0x20);
}
return c;
}
/// <summary>
/// Converts the character or string to upper case. Certain locales
/// have different casing semantics from the file systems in Win32.
/// </summary>
public char ToUpper(char c)
{
if (GlobalizationMode.Invariant)
{
return InvariantModeCasing.ToUpper(c);
}
if (UnicodeUtility.IsAsciiCodePoint(c) && IsAsciiCasingSameAsInvariant)
{
return ToUpperAsciiInvariant(c);
}
return ChangeCase(c, toUpper: true);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
internal static char ToUpperInvariant(char c)
{
if (UnicodeUtility.IsAsciiCodePoint(c))
{
return ToUpperAsciiInvariant(c);
}
if (GlobalizationMode.Invariant)
{
return InvariantModeCasing.ToUpper(c);
}
return Invariant.ChangeCase(c, toUpper: true);
}
public string ToUpper(string str)
{
ArgumentNullException.ThrowIfNull(str);
if (GlobalizationMode.Invariant)
{
return InvariantModeCasing.ToUpper(str);
}
return ChangeCaseCommon<ToUpperConversion>(str);
}
[MethodImpl(MethodImplOptions.AggressiveInlining)]
private static char ToUpperAsciiInvariant(char c)
{
if (char.IsAsciiLetterLower(c))
{
c = (char)(c & 0x5F); // = low 7 bits of ~0x20
}
return c;
}
private bool IsAsciiCasingSameAsInvariant
{
[MethodImpl(MethodImplOptions.AggressiveInlining)]
get
{
if (_isAsciiCasingSameAsInvariant == Tristate.NotInitialized)
{
PopulateIsAsciiCasingSameAsInvariant();
}
Debug.Assert(_isAsciiCasingSameAsInvariant == Tristate.True || _isAsciiCasingSameAsInvariant == Tristate.False);
return _isAsciiCasingSameAsInvariant == Tristate.True;
}
}
[MethodImpl(MethodImplOptions.NoInlining)]
private void PopulateIsAsciiCasingSameAsInvariant()
{
bool compareResult = CultureInfo.GetCultureInfo(_textInfoName).CompareInfo.Compare("abcdefghijklmnopqrstuvwxyz", "ABCDEFGHIJKLMNOPQRSTUVWXYZ", CompareOptions.IgnoreCase) == 0;
_isAsciiCasingSameAsInvariant = (compareResult) ? Tristate.True : Tristate.False;
}
/// <summary>
/// Returns true if the dominant direction of text and UI such as the
/// relative position of buttons and scroll bars
/// </summary>
public bool IsRightToLeft => _cultureData.IsRightToLeft;
public override bool Equals([NotNullWhen(true)] object? obj)
{
return obj is TextInfo otherTextInfo
&& CultureName.Equals(otherTextInfo.CultureName);
}
public override int GetHashCode() => CultureName.GetHashCode();
public override string ToString()
{
return "TextInfo - " + _cultureData.CultureName;
}
/// <summary>
/// Titlecasing refers to a casing practice wherein the first letter of a word is an uppercase letter
/// and the rest of the letters are lowercase. The choice of which words to titlecase in headings
/// and titles is dependent on language and local conventions. For example, "The Merry Wives of Windor"
/// is the appropriate titlecasing of that play's name in English, with the word "of" not titlecased.
/// In German, however, the title is "Die lustigen Weiber von Windsor," and both "lustigen" and "von"
/// are not titlecased. In French even fewer words are titlecased: "Les joyeuses commeres de Windsor."
///
/// Moreover, the determination of what actually constitutes a word is language dependent, and this can
/// influence which letter or letters of a "word" are uppercased when titlecasing strings. For example
/// "l'arbre" is considered two words in French, whereas "can't" is considered one word in English.
/// </summary>
public unsafe string ToTitleCase(string str)
{
ArgumentNullException.ThrowIfNull(str);
if (str.Length == 0)
{
return str;
}
StringBuilder result = new StringBuilder();
string? lowercaseData = null;
// Store if the current culture is Dutch (special case)
bool isDutchCulture = CultureName.StartsWith("nl-", StringComparison.OrdinalIgnoreCase);
for (int i = 0; i < str.Length; i++)
{
UnicodeCategory charType = CharUnicodeInfo.GetUnicodeCategoryInternal(str, i, out int charLen);
if (char.CheckLetter(charType))
{
// Special case to check for Dutch specific titlecasing with "IJ" characters
// at the beginning of a word
if (isDutchCulture && i < str.Length - 1 && (str[i] == 'i' || str[i] == 'I') && (str[i + 1] == 'j' || str[i + 1] == 'J'))
{
result.Append("IJ");
i += 2;
}
else
{
// Do the titlecasing for the first character of the word.
i = AddTitlecaseLetter(ref result, ref str, i, charLen) + 1;
}
// Convert the characters until the end of the this word
// to lowercase.
int lowercaseStart = i;
// Use hasLowerCase flag to prevent from lowercasing acronyms (like "URT", "USA", etc)
// This is in line with Word 2000 behavior of titlecasing.
bool hasLowerCase = (charType == UnicodeCategory.LowercaseLetter);
// Use a loop to find all of the other letters following this letter.
while (i < str.Length)
{
charType = CharUnicodeInfo.GetUnicodeCategoryInternal(str, i, out charLen);
if (IsLetterCategory(charType))
{
if (charType == UnicodeCategory.LowercaseLetter)
{
hasLowerCase = true;
}
i += charLen;
}
else if (str[i] == '\'')
{
i++;
if (hasLowerCase)
{
lowercaseData ??= ToLower(str);
result.Append(lowercaseData, lowercaseStart, i - lowercaseStart);
}
else
{
result.Append(str, lowercaseStart, i - lowercaseStart);
}
lowercaseStart = i;
hasLowerCase = true;
}
else if (!IsWordSeparator(charType))
{
// This category is considered to be part of the word.
// This is any category that is marked as false in wordSeparator array.
i += charLen;
}
else
{
// A word separator. Break out of the loop.
break;
}
}
int count = i - lowercaseStart;
if (count > 0)
{
if (hasLowerCase)
{
lowercaseData ??= ToLower(str);
result.Append(lowercaseData, lowercaseStart, count);
}
else
{
result.Append(str, lowercaseStart, count);
}
}
if (i < str.Length)
{
// not a letter, just append it
i = AddNonLetter(ref result, ref str, i, charLen);
}
}
else
{
// not a letter, just append it
i = AddNonLetter(ref result, ref str, i, charLen);
}
}
return result.ToString();
}
private static int AddNonLetter(ref StringBuilder result, ref string input, int inputIndex, int charLen)
{
Debug.Assert(charLen == 1 || charLen == 2, "[TextInfo.AddNonLetter] CharUnicodeInfo.InternalGetUnicodeCategory returned an unexpected charLen!");
if (charLen == 2)
{
// Surrogate pair
result.Append(input[inputIndex++]);
result.Append(input[inputIndex]);
}
else
{
result.Append(input[inputIndex]);
}
return inputIndex;
}
private int AddTitlecaseLetter(ref StringBuilder result, ref string input, int inputIndex, int charLen)
{
Debug.Assert(charLen == 1 || charLen == 2, "[TextInfo.AddTitlecaseLetter] CharUnicodeInfo.InternalGetUnicodeCategory returned an unexpected charLen!");
if (charLen == 2)
{
// for surrogate pairs do a ToUpper operation on the substring
ReadOnlySpan<char> src = input.AsSpan(inputIndex, 2);
if (GlobalizationMode.Invariant)
{
SurrogateCasing.ToUpper(src[0], src[1], out char h, out char l);
result.Append(h);
result.Append(l);
}
else
{
Span<char> dst = stackalloc char[2];
ChangeCaseToUpper(src, dst);
result.Append(dst);
}
inputIndex++;
}
else
{
switch (input[inputIndex])
{
// For AppCompat, the Titlecase Case Mapping data from NDP 2.0 is used below.
case (char)0x01C4: // DZ with Caron -> Dz with Caron
case (char)0x01C5: // Dz with Caron -> Dz with Caron
case (char)0x01C6: // dz with Caron -> Dz with Caron
result.Append((char)0x01C5);
break;
case (char)0x01C7: // LJ -> Lj
case (char)0x01C8: // Lj -> Lj
case (char)0x01C9: // lj -> Lj
result.Append((char)0x01C8);
break;
case (char)0x01CA: // NJ -> Nj
case (char)0x01CB: // Nj -> Nj
case (char)0x01CC: // nj -> Nj
result.Append((char)0x01CB);
break;
case (char)0x01F1: // DZ -> Dz
case (char)0x01F2: // Dz -> Dz
case (char)0x01F3: // dz -> Dz
result.Append((char)0x01F2);
break;
default:
result.Append(GlobalizationMode.Invariant ? InvariantModeCasing.ToUpper(input[inputIndex]) : ToUpper(input[inputIndex]));
break;
}
}
return inputIndex;
}
private unsafe void ChangeCaseCore(char* src, int srcLen, char* dstBuffer, int dstBufferCapacity, bool bToUpper)
{
if (GlobalizationMode.UseNls)
{
NlsChangeCase(src, srcLen, dstBuffer, dstBufferCapacity, bToUpper);
return;
}
#if TARGET_BROWSER
if (GlobalizationMode.Hybrid)
{
JsChangeCase(src, srcLen, dstBuffer, dstBufferCapacity, bToUpper);
return;
}
#elif TARGET_MACCATALYST || TARGET_IOS || TARGET_TVOS
if (GlobalizationMode.Hybrid)
{
ChangeCaseNative(src, srcLen, dstBuffer, dstBufferCapacity, bToUpper);
return;
}
#endif
IcuChangeCase(src, srcLen, dstBuffer, dstBufferCapacity, bToUpper);
}
// Used in ToTitleCase():
// When we find a starting letter, the following array decides if a category should be
// considered as word separator or not.
private const int c_wordSeparatorMask =
/* false */ (0 << 0) | // UppercaseLetter = 0,
/* false */ (0 << 1) | // LowercaseLetter = 1,
/* false */ (0 << 2) | // TitlecaseLetter = 2,
/* false */ (0 << 3) | // ModifierLetter = 3,
/* false */ (0 << 4) | // OtherLetter = 4,
/* false */ (0 << 5) | // NonSpacingMark = 5,
/* false */ (0 << 6) | // SpacingCombiningMark = 6,
/* false */ (0 << 7) | // EnclosingMark = 7,
/* false */ (0 << 8) | // DecimalDigitNumber = 8,
/* false */ (0 << 9) | // LetterNumber = 9,
/* false */ (0 << 10) | // OtherNumber = 10,
/* true */ (1 << 11) | // SpaceSeparator = 11,
/* true */ (1 << 12) | // LineSeparator = 12,
/* true */ (1 << 13) | // ParagraphSeparator = 13,
/* true */ (1 << 14) | // Control = 14,
/* true */ (1 << 15) | // Format = 15,
/* false */ (0 << 16) | // Surrogate = 16,
/* false */ (0 << 17) | // PrivateUse = 17,
/* true */ (1 << 18) | // ConnectorPunctuation = 18,
/* true */ (1 << 19) | // DashPunctuation = 19,
/* true */ (1 << 20) | // OpenPunctuation = 20,
/* true */ (1 << 21) | // ClosePunctuation = 21,
/* true */ (1 << 22) | // InitialQuotePunctuation = 22,
/* true */ (1 << 23) | // FinalQuotePunctuation = 23,
/* true */ (1 << 24) | // OtherPunctuation = 24,
/* true */ (1 << 25) | // MathSymbol = 25,
/* true */ (1 << 26) | // CurrencySymbol = 26,
/* true */ (1 << 27) | // ModifierSymbol = 27,
/* true */ (1 << 28) | // OtherSymbol = 28,
/* false */ (0 << 29); // OtherNotAssigned = 29;
private static bool IsWordSeparator(UnicodeCategory category)
{
return (c_wordSeparatorMask & (1 << (int)category)) != 0;
}
private static bool IsLetterCategory(UnicodeCategory uc)
{
return uc == UnicodeCategory.UppercaseLetter
|| uc == UnicodeCategory.LowercaseLetter
|| uc == UnicodeCategory.TitlecaseLetter
|| uc == UnicodeCategory.ModifierLetter
|| uc == UnicodeCategory.OtherLetter;
}
// A dummy struct that is used for 'ToUpper' in generic parameters
private readonly struct ToUpperConversion { }
// A dummy struct that is used for 'ToLower' in generic parameters
private readonly struct ToLowerConversion { }
}
}