File: SyntaxHighlightingTokenParser.swift

package info (click to toggle)
swiftlang 6.0.3-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 2,519,992 kB
  • sloc: cpp: 9,107,863; ansic: 2,040,022; asm: 1,135,751; python: 296,500; objc: 82,456; f90: 60,502; lisp: 34,951; pascal: 19,946; sh: 18,133; perl: 7,482; ml: 4,937; javascript: 4,117; makefile: 3,840; awk: 3,535; xml: 914; fortran: 619; cs: 573; ruby: 573
file content (237 lines) | stat: -rw-r--r-- 7,496 bytes parent folder | download
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
//===----------------------------------------------------------------------===//
//
// This source file is part of the Swift.org open source project
//
// Copyright (c) 2014 - 2021 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
// See https://swift.org/CONTRIBUTORS.txt for the list of Swift project authors
//
//===----------------------------------------------------------------------===//

import LSPLogging
import LanguageServerProtocol
import SourceKitD

/// Parses tokens from sourcekitd response dictionaries.
struct SyntaxHighlightingTokenParser {
  private let sourcekitd: SourceKitD

  init(sourcekitd: SourceKitD) {
    self.sourcekitd = sourcekitd
  }

  private func parseTokens(
    _ response: SKDResponseDictionary,
    in snapshot: DocumentSnapshot,
    into tokens: inout SyntaxHighlightingTokens
  ) {
    let keys = sourcekitd.keys

    if let offset: Int = response[keys.offset],
      var length: Int = response[keys.length],
      let skKind: sourcekitd_api_uid_t = response[keys.kind],
      case (let kind, var modifiers)? = parseKindAndModifiers(skKind)
    {

      // If the name is escaped in backticks, we need to add two characters to the
      // length for the backticks.
      if modifiers.contains(.declaration),
        snapshot.text[snapshot.indexOf(utf8Offset: offset)] == "`"
      {
        length += 2
      }

      if let isSystem: Bool = response[keys.isSystem], isSystem {
        modifiers.insert(.defaultLibrary)
      }

      let multiLineRange = snapshot.positionOf(utf8Offset: offset)..<snapshot.positionOf(utf8Offset: offset + length)
      let ranges = multiLineRange.splitToSingleLineRanges(in: snapshot)

      tokens.tokens += ranges.map {
        SyntaxHighlightingToken(
          range: $0,
          kind: kind,
          modifiers: modifiers
        )
      }
    }

    if let substructure: SKDResponseArray = response[keys.subStructure] {
      parseTokens(substructure, in: snapshot, into: &tokens)
    }
  }

  private func parseTokens(
    _ response: SKDResponseArray,
    in snapshot: DocumentSnapshot,
    into tokens: inout SyntaxHighlightingTokens
  ) {
    response.forEach { (_, value) in
      parseTokens(value, in: snapshot, into: &tokens)
      return true
    }
  }

  func parseTokens(_ response: SKDResponseArray, in snapshot: DocumentSnapshot) -> SyntaxHighlightingTokens {
    var tokens: SyntaxHighlightingTokens = SyntaxHighlightingTokens(tokens: [])
    parseTokens(response, in: snapshot, into: &tokens)
    return tokens
  }

  private func parseKindAndModifiers(
    _ uid: sourcekitd_api_uid_t
  ) -> (SemanticTokenTypes, SemanticTokenModifiers)? {
    let api = sourcekitd.api
    let values = sourcekitd.values
    switch uid {
    case values.completionKindKeyword, values.keyword:
      return (.keyword, [])
    case values.attributeBuiltin:
      return (.modifier, [])
    case values.declModule:
      return (.namespace, [])
    case values.declClass:
      return (.class, [.declaration])
    case values.refClass:
      return (.class, [])
    case values.declActor:
      return (.actor, [.declaration])
    case values.refActor:
      return (.actor, [])
    case values.declStruct:
      return (.struct, [.declaration])
    case values.refStruct:
      return (.struct, [])
    case values.declEnum:
      return (.enum, [.declaration])
    case values.refEnum:
      return (.enum, [])
    case values.declEnumElement:
      return (.enumMember, [.declaration])
    case values.refEnumElement:
      return (.enumMember, [])
    case values.declProtocol:
      return (.interface, [.declaration])
    case values.refProtocol:
      return (.interface, [])
    case values.declAssociatedType,
      values.declTypeAlias,
      values.declGenericTypeParam:
      return (.typeParameter, [.declaration])
    case values.refAssociatedType,
      values.refTypeAlias,
      values.refGenericTypeParam:
      return (.typeParameter, [])
    case values.declFunctionFree:
      return (.function, [.declaration])
    case values.declMethodStatic,
      values.declMethodClass,
      values.declConstructor:
      return (.method, [.declaration, .static])
    case values.declMethodInstance,
      values.declDestructor,
      values.declSubscript:
      return (.method, [.declaration])
    case values.refFunctionFree:
      return (.function, [])
    case values.refMethodStatic,
      values.refMethodClass,
      values.refConstructor:
      return (.method, [.static])
    case values.refMethodInstance,
      values.refDestructor,
      values.refSubscript:
      return (.method, [])
    case values.operator:
      return (.operator, [])
    case values.declFunctionPrefixOperator,
      values.declFunctionPostfixOperator,
      values.declFunctionInfixOperator:
      return (.operator, [.declaration])
    case values.refFunctionPrefixOperator,
      values.refFunctionPostfixOperator,
      values.refFunctionInfixOperator:
      return (.operator, [])
    case values.declVarStatic,
      values.declVarClass,
      values.declVarInstance:
      return (.property, [.declaration])
    case values.declVarParam:
      // SourceKit seems to use these to refer to parameter labels,
      // therefore we don't use .parameter here (which LSP clients like
      // VSCode seem to interpret as variable identifiers, however
      // causing a 'wrong highlighting' e.g. of `x` in `f(x y: Int) {}`)
      return (.function, [.declaration])
    case values.refVarStatic,
      values.refVarClass,
      values.refVarInstance:
      return (.property, [])
    case values.declVarLocal,
      values.declVarGlobal:
      return (.variable, [.declaration])
    case values.refVarLocal,
      values.refVarGlobal:
      return (.variable, [])
    case values.comment,
      values.commentMarker,
      values.commentURL:
      return (.comment, [])
    case values.docComment,
      values.docCommentField:
      return (.comment, [.documentation])
    case values.typeIdentifier:
      return (.type, [])
    case values.number:
      return (.number, [])
    case values.string:
      return (.string, [])
    case values.identifier:
      return (.identifier, [])
    default:
      let ignoredKinds: Set<sourcekitd_api_uid_t> = [
        values.stringInterpolation
      ]
      if !ignoredKinds.contains(uid) {
        let name = api.uid_get_string_ptr(uid).map(String.init(cString:))
        logger.error("Unknown token kind: \(name ?? "?", privacy: .public)")
      }
      return nil
    }
  }
}

extension Range<Position> {
  /// Splits a potentially multi-line range to multiple single-line ranges.
  @_spi(Testing) public func splitToSingleLineRanges(in snapshot: DocumentSnapshot) -> [Self] {
    if isEmpty {
      return []
    }

    if lowerBound.line == upperBound.line {
      return [self]
    }

    let text = snapshot.text[snapshot.indexRange(of: self)]
    let lines = text.split(separator: "\n", omittingEmptySubsequences: false)

    return
      lines
      .enumerated()
      .lazy
      .map { (i, content) in
        let start = Position(
          line: lowerBound.line + i,
          utf16index: i == 0 ? lowerBound.utf16index : 0
        )
        let end = Position(
          line: start.line,
          utf16index: start.utf16index + content.utf16.count
        )
        return start..<end
      }
      .filter { !$0.isEmpty }
  }
}