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
|
//===----------------------------------------------------------------------===//
//
// This source file is part of the Swift.org open source project
//
// Copyright (c) 2021-2022 Apple Inc. and the Swift project authors
// Licensed under Apache License v2.0 with Runtime Library Exception
//
// See https://swift.org/LICENSE.txt for license information
//
//===----------------------------------------------------------------------===//
extension AST {
/// An option, written in source, that changes matching semantics.
public struct MatchingOption: Hashable {
public enum Kind: Hashable {
// PCRE options
case caseInsensitive // i
case allowDuplicateGroupNames // J
case multiline // m
case namedCapturesOnly // n
case singleLine // s
case reluctantByDefault // U
case extended // x
case extraExtended // xx
// ICU options
case unicodeWordBoundaries // w
// Oniguruma options
case asciiOnlyDigit // D
case asciiOnlyPOSIXProps // P
case asciiOnlySpace // S
case asciiOnlyWord // W
// Oniguruma text segment options (these are mutually exclusive and cannot
// be unset, only flipped between)
case textSegmentGraphemeMode // y{g}
case textSegmentWordMode // y{w}
// Swift semantic matching level
case graphemeClusterSemantics // X
case unicodeScalarSemantics // u
case byteSemantics // b
// Swift-only default possessive quantifier
case possessiveByDefault // t.b.d.
// NSRegularExpression compatibility special-case
case nsreCompatibleDot // no AST representation
}
public var kind: Kind
public var location: SourceLocation
public init(_ kind: Kind, location: SourceLocation) {
self.kind = kind
self.location = location
}
/// If this is either the regular or extra extended syntax option.
public var isAnyExtended: Bool {
switch kind {
case .extended, .extraExtended:
return true
default:
return false
}
}
public var isTextSegmentMode: Bool {
switch kind {
case .textSegmentGraphemeMode, .textSegmentWordMode:
return true
default:
return false
}
}
public var isSemanticMatchingLevel: Bool {
switch kind {
case .graphemeClusterSemantics, .unicodeScalarSemantics, .byteSemantics:
return true
default:
return false
}
}
}
/// A sequence of matching options, written in source.
public struct MatchingOptionSequence: Hashable {
/// If the sequence starts with a caret '^', its source location, or nil
/// otherwise. If this is set, it indicates that all the matching options
/// are unset, except the ones in `adding`.
public var caretLoc: SourceLocation?
/// The options to add.
public var adding: [MatchingOption]
/// The location of the '-' between the options to add and options to
/// remove.
public var minusLoc: SourceLocation?
/// The options to remove.
public var removing: [MatchingOption]
public init(caretLoc: SourceLocation?, adding: [MatchingOption],
minusLoc: SourceLocation?, removing: [MatchingOption]) {
self.caretLoc = caretLoc
self.adding = adding
self.minusLoc = minusLoc
self.removing = removing
}
/// Whether this set of matching options first resets the options before
/// adding onto them.
public var resetsCurrentOptions: Bool { caretLoc != nil }
}
}
extension AST.MatchingOptionSequence {
public init(adding: [AST.MatchingOption]) {
self.init(caretLoc: nil, adding: adding, minusLoc: nil, removing: [])
}
public init(removing: [AST.MatchingOption]) {
self.init(caretLoc: nil, adding: [], minusLoc: nil, removing: removing)
}
}
extension AST.MatchingOption: _ASTPrintable {
public var _dumpBase: String { "\(kind)" }
}
extension AST.MatchingOptionSequence: _ASTPrintable {
public var _dumpBase: String {
"""
adding: \(adding), removing: \(removing), \
resetsCurrentOptions: \(resetsCurrentOptions)
"""
}
}
extension AST {
/// Global matching option specifiers.
///
/// Unlike `MatchingOptionSequence`,
/// these options must appear at the start of the pattern,
/// and they apply to the entire pattern.
public struct GlobalMatchingOption: _ASTNode, Hashable {
/// Determines the definition of a newline for the '.' character class and
/// when parsing end-of-line comments.
public enum NewlineMatching: Hashable {
/// (*CR*)
case carriageReturnOnly
/// (*LF)
case linefeedOnly
/// (*CRLF)
case carriageAndLinefeedOnly
/// (*ANYCRLF)
case anyCarriageReturnOrLinefeed
/// (*ANY)
case anyUnicode
/// (*NUL)
case nulCharacter
}
/// Determines what `\R` matches.
public enum NewlineSequenceMatching: Hashable {
/// (*BSR_ANYCRLF)
case anyCarriageReturnOrLinefeed
/// (*BSR_UNICODE)
case anyUnicode
}
public enum Kind: Hashable {
/// (*LIMIT_DEPTH=d)
case limitDepth(AST.Atom.Number)
/// (*LIMIT_HEAP=d)
case limitHeap(AST.Atom.Number)
/// (*LIMIT_MATCH=d)
case limitMatch(AST.Atom.Number)
/// (*NOTEMPTY)
case notEmpty
/// (*NOTEMPTY_ATSTART)
case notEmptyAtStart
/// (*NO_AUTO_POSSESS)
case noAutoPossess
/// (*NO_DOTSTAR_ANCHOR)
case noDotStarAnchor
/// (*NO_JIT)
case noJIT
/// (*NO_START_OPT)
case noStartOpt
/// (*UTF)
case utfMode
/// (*UCP)
case unicodeProperties
case newlineMatching(NewlineMatching)
case newlineSequenceMatching(NewlineSequenceMatching)
}
public var kind: Kind
public var location: SourceLocation
public init(_ kind: Kind, _ location: SourceLocation) {
self.kind = kind
self.location = location
}
}
}
|