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
|
namespace System.Text.RegularExpressions {
// for the IgnoreCase opcodes, the char data is stored lowercased
// two-byte integers are in little endian format
enum RxOp : byte {
// followed by count, min, max integers
Info,
False,
True,
// position anchors
AnyPosition,
StartOfString,
StartOfLine,
StartOfScan,
EndOfString,
EndOfLine,
End,
WordBoundary,
NoWordBoundary,
// latin1 strings
// followed by single byte length and latin1 bytes
// keep the order, see EmitString ()
String,
StringIgnoreCase,
StringReverse,
StringIgnoreCaseReverse,
// followed by two byte length and unicode chars (two bytes per char)
// a better setup may be to reference the chars in the patterns string
// (offset, length) pairs, at least when the pattern contains them,
// but this means we can't lowercase before hand: consider using a separate
// string/array
// keep the order, see EmitString ()
UnicodeString,
UnicodeStringIgnoreCase,
UnicodeStringReverse,
UnicodeStringIgnoreCaseReverse,
// latin1 single char
// followed by a latin1 byte
// keep the order, see EmitCharacter ()
Char,
NoChar,
CharIgnoreCase,
NoCharIgnoreCase,
CharReverse,
NoCharReverse,
CharIgnoreCaseReverse,
NoCharIgnoreCaseReverse,
// followed by latin1 min and max bytes
// keep the order, see EmitRange ()
Range,
NoRange,
RangeIgnoreCase,
NoRangeIgnoreCase,
RangeReverse,
NoRangeReverse,
RangeIgnoreCaseReverse,
NoRangeIgnoreCaseReverse,
// followed by lowbyte and length of the bitmap and by the bitmap
// keep the order, see EmitSet ()
Bitmap,
NoBitmap,
BitmapIgnoreCase,
NoBitmapIgnoreCase,
BitmapReverse,
NoBitmapReverse,
BitmapIgnoreCaseReverse,
NoBitmapIgnoreCaseReverse,
// unicode chars
// followed by a unicode char
// keep the order, see EmitCharacter ()
UnicodeChar,
NoUnicodeChar,
UnicodeCharIgnoreCase,
NoUnicodeCharIgnoreCase,
UnicodeCharReverse,
NoUnicodeCharReverse,
UnicodeCharIgnoreCaseReverse,
NoUnicodeCharIgnoreCaseReverse,
// followed by unicode char min and max chars
// keep the order, see EmitRange ()
UnicodeRange,
NoUnicodeRange,
UnicodeRangeIgnoreCase,
NoUnicodeRangeIgnoreCase,
UnicodeRangeReverse,
NoUnicodeRangeReverse,
UnicodeRangeIgnoreCaseReverse,
NoUnicodeRangeIgnoreCaseReverse,
// followed by lowchar and length of the bitmap and by the bitmap
UnicodeBitmap,
NoUnicodeBitmap,
UnicodeBitmapIgnoreCase,
NoUnicodeBitmapIgnoreCase,
UnicodeBitmapReverse,
NoUnicodeBitmapReverse,
UnicodeBitmapIgnoreCaseReverse,
NoUnicodeBitmapIgnoreCaseReverse,
// add reverse and negate versions of the categories
CategoryAny,
NoCategoryAny,
CategoryAnyReverse,
NoCategoryAnyReverse,
CategoryAnySingleline,
NoCategoryAnySingleline,
CategoryAnySinglelineReverse,
NoCategoryAnySinglelineReverse,
CategoryDigit,
NoCategoryDigit,
CategoryDigitReverse,
NoCategoryDigitReverse,
CategoryWord,
NoCategoryWord,
CategoryWordReverse,
NoCategoryWordReverse,
CategoryWhiteSpace,
NoCategoryWhiteSpace,
CategoryWhiteSpaceReverse,
NoCategoryWhiteSpaceReverse,
CategoryEcmaWord,
NoCategoryEcmaWord,
CategoryEcmaWordReverse,
NoCategoryEcmaWordReverse,
CategoryEcmaWhiteSpace,
NoCategoryEcmaWhiteSpace,
CategoryEcmaWhiteSpaceReverse,
NoCategoryEcmaWhiteSpaceReverse,
// followed by a unicode category value (byte)
CategoryUnicode,
NoCategoryUnicode,
CategoryUnicodeReverse,
NoCategoryUnicodeReverse,
CategoryUnicodeLetter,
NoCategoryUnicodeLetter,
CategoryUnicodeLetterReverse,
NoCategoryUnicodeLetterReverse,
CategoryUnicodeMark,
NoCategoryUnicodeMark,
CategoryUnicodeMarkReverse,
NoCategoryUnicodeMarkReverse,
CategoryUnicodeNumber,
NoCategoryUnicodeNumber,
CategoryUnicodeNumberReverse,
NoCategoryUnicodeNumberReverse,
CategoryUnicodeSeparator,
NoCategoryUnicodeSeparator,
CategoryUnicodeSeparatorReverse,
NoCategoryUnicodeSeparatorReverse,
CategoryUnicodePunctuation,
NoCategoryUnicodePunctuation,
CategoryUnicodePunctuationReverse,
NoCategoryUnicodePunctuationReverse,
CategoryUnicodeSymbol,
NoCategoryUnicodeSymbol,
CategoryUnicodeSymbolReverse,
NoCategoryUnicodeSymbolReverse,
CategoryUnicodeSpecials,
NoCategoryUnicodeSpecials,
CategoryUnicodeSpecialsReverse,
NoCategoryUnicodeSpecialsReverse,
CategoryUnicodeOther,
NoCategoryUnicodeOther,
CategoryUnicodeOtherReverse,
NoCategoryUnicodeOtherReverse,
// add more categories
// followed by Category value (byte)
CategoryGeneral,
NoCategoryGeneral,
CategoryGeneralReverse,
NoCategoryGeneralReverse,
// backreferences
// followed by two-byte reference number
// keep the order, see EmitReference ()
Reference,
ReferenceIgnoreCase,
ReferenceReverse,
ReferenceIgnoreCaseReverse,
// group/capture support
// followed by two-byte group id
OpenGroup,
CloseGroup,
BalanceStart,
Balance,
// followed by offset and two-byte group id
IfDefined,
// skip ahead num bytes
// followed by two-byte offset
Jump,
// followed by two-byte offset
SubExpression,
// followed by true and false two-byte offsets
Test,
// followed by two-byte offset
Branch,
// followed by two-byte offset
TestCharGroup,
// anchoring expression
// followed by offset of tail and offset
Anchor,
AnchorReverse,
// repetition support
// followed by min, max ints
Repeat,
RepeatLazy,
Until,
FastRepeat,
FastRepeatLazy,
// followed by min byte
RepeatInfinite,
RepeatInfiniteLazy,
}
}
|
