File: JSONWriter.swift

package info (click to toggle)
swiftlang 6.2.3-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 2,856,264 kB
  • sloc: cpp: 9,995,718; ansic: 2,234,019; asm: 1,092,167; python: 313,940; objc: 82,726; f90: 80,126; lisp: 38,373; pascal: 25,580; sh: 20,378; ml: 5,058; perl: 4,751; makefile: 4,725; awk: 3,535; javascript: 3,018; xml: 918; fortran: 664; cs: 573; ruby: 396
file content (352 lines) | stat: -rw-r--r-- 12,779 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
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
//===----------------------------------------------------------------------===//
//
// This source file is part of the Swift.org open source project
//
// Copyright (c) 2023 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
//
//===----------------------------------------------------------------------===//

internal struct JSONWriter {

    // Structures with container nesting deeper than this limit are not valid.
    private static let maximumRecursionDepth = 512

    private var indent = 0
    private let pretty: Bool
    private let sortedKeys: Bool
    private let withoutEscapingSlashes: Bool

    var bytes = [UInt8]()

    init(options: JSONEncoder.OutputFormatting) {
        pretty = options.contains(.prettyPrinted)
        sortedKeys = options.contains(.sortedKeys)
        withoutEscapingSlashes = options.contains(.withoutEscapingSlashes)
    }

    mutating func serializeJSON(_ value: JSONEncoderValue, depth: Int = 0) throws {
        switch value {
        case .string(let str):
            serializeString(str)
        case .bool(let boolValue):
            writer(boolValue ? "true" : "false")
        case .number(let numberStr):
            writer(contentsOf: numberStr.utf8)
        case .array(let array):
            try serializeArray(array, depth: depth + 1)
        case .nonPrettyDirectArray(let arrayRepresentation):
            writer(contentsOf: arrayRepresentation)
        case let .directArray(bytes, lengths):
            try serializePreformattedByteArray(bytes, lengths, depth: depth + 1)
        case .object(let object):
            try serializeObject(object, depth: depth + 1)
        case .null:
            writer("null")
        }
    }

    @inline(__always)
    mutating func writer(_ string: StaticString) {
        writer(pointer: string.utf8Start, count: string.utf8CodeUnitCount)
    }

    @inline(__always)
    mutating func writer<S: Sequence>(contentsOf sequence: S) where S.Element == UInt8 {
        bytes.append(contentsOf: sequence)
    }

    @inline(__always)
    mutating func writer(ascii: UInt8) {
        bytes.append(ascii)
    }

    @inline(__always)
    mutating func writer(pointer: UnsafePointer<UInt8>, count: Int) {
        bytes.append(contentsOf: UnsafeBufferPointer(start: pointer, count: count))
    }

    // Shortcut for strings known not to require escapes, like numbers.
    @inline(__always)
    mutating func serializeSimpleStringContents(_ str: String) -> Int {
        let stringStart = self.bytes.endIndex
        var mutStr = str
        mutStr.withUTF8 {
            writer(contentsOf: $0)
        }
        let length = stringStart.distance(to: self.bytes.endIndex)
        return length
    }

    // Shortcut for strings known not to require escapes, like numbers.
    @inline(__always)
    mutating func serializeSimpleString(_ str: String) -> Int {
        writer(ascii: ._quote)
        defer {
            writer(ascii: ._quote)
        }
        return self.serializeSimpleStringContents(str) + 2 // +2 for quotes.
    }

    @inline(__always)
    mutating func serializeStringContents(_ str: String) -> Int {
        let unquotedStringStart = self.bytes.endIndex
        var mutStr = str
        mutStr.withUTF8 {

            @inline(__always)
            func appendAccumulatedBytes(from mark: UnsafePointer<UInt8>, to cursor: UnsafePointer<UInt8>, followedByContentsOf sequence: [UInt8]) {
                if cursor > mark {
                    writer(pointer: mark, count: cursor-mark)
                }
                writer(contentsOf: sequence)
            }

            @inline(__always)
            func valueToASCII(_ value: UInt8) -> UInt8 {
                switch value {
                case 0 ... 9:
                    return value &+ UInt8(ascii: "0")
                case 10 ... 15:
                    return value &- 10 &+ UInt8(ascii: "a")
                default:
                    preconditionFailure()
                }
            }

            var cursor = $0.baseAddress!
            let end = $0.baseAddress! + $0.count
            var mark = cursor
            while cursor < end {
                switch cursor.pointee {
                case ._quote:
                    appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [._backslash, ._quote])
                case ._backslash:
                    appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [._backslash, ._backslash])
                case ._slash where !withoutEscapingSlashes:
                    appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [._backslash, ._forwardslash])
                case 0x8:
                    appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [._backslash, UInt8(ascii: "b")])
                case 0xc:
                    appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [._backslash, UInt8(ascii: "f")])
                case ._newline:
                    appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [._backslash, UInt8(ascii: "n")])
                case ._return:
                    appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [._backslash, UInt8(ascii: "r")])
                case ._tab:
                    appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [._backslash, UInt8(ascii: "t")])
                case 0x0...0xf:
                    appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [._backslash, UInt8(ascii: "u"), UInt8(ascii: "0"), UInt8(ascii: "0"), UInt8(ascii: "0")])
                    writer(ascii: valueToASCII(cursor.pointee))
                case 0x10...0x1f:
                    appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [._backslash, UInt8(ascii: "u"), UInt8(ascii: "0"), UInt8(ascii: "0")])
                    writer(ascii: valueToASCII(cursor.pointee / 16))
                    writer(ascii: valueToASCII(cursor.pointee % 16))
                default:
                    // Accumulate this byte
                    cursor += 1
                    continue
                }

                cursor += 1
                mark = cursor // Start accumulating bytes starting after this escaped byte.
            }

            appendAccumulatedBytes(from: mark, to: cursor, followedByContentsOf: [])
        }
        let unquotedStringLength = unquotedStringStart.distance(to: self.bytes.endIndex)
        return unquotedStringLength
    }

    @discardableResult
    mutating func serializeString(_ str: String) -> Int {
        writer(ascii: ._quote)
        defer {
            writer(ascii: ._quote)
        }
        return self.serializeStringContents(str) + 2 // +2 for quotes.

    }

    mutating func serializeArray(_ array: [JSONEncoderValue], depth: Int) throws {
        guard depth < Self.maximumRecursionDepth else {
            throw JSONError.tooManyNestedArraysOrDictionaries()
        }

        writer(ascii: ._openbracket)
        if pretty {
            writer(ascii: ._newline)
            incIndent()
        }

        var first = true
        for elem in array {
            if first {
                first = false
            } else if pretty {
                writer(contentsOf: [._comma, ._newline])
            } else {
                writer(ascii: ._comma)
            }
            if pretty {
                writeIndent()
            }
            try serializeJSON(elem, depth: depth)
        }
        if pretty {
            writer(ascii: ._newline)
            decAndWriteIndent()
        }
        writer(ascii: ._closebracket)
    }
    
    mutating func serializePreformattedByteArray(_ bytes: [UInt8], _ lengths: [Int], depth: Int) throws {
        guard depth < Self.maximumRecursionDepth else {
            throw JSONError.tooManyNestedArraysOrDictionaries()
        }

        writer(ascii: ._openbracket)
        if pretty {
            writer(ascii: ._newline)
            incIndent()
        }

        var lowerBound: [UInt8].Index = bytes.startIndex

        var first = true
        for length in lengths {
            if first {
                first = false
            } else if pretty {
                writer(contentsOf: [._comma, ._newline])
            } else {
                writer(ascii: ._comma)
            }
            if pretty {
                writeIndent()
            }

            // Do NOT call `serializeString` here! The input strings have already been formatted exactly as they need to be for direct JSON output, including any requisite quotes or escaped characters for strings.
            let upperBound = lowerBound + length
            writer(contentsOf: bytes[lowerBound ..< upperBound])
            lowerBound = upperBound
        }
        if pretty {
            writer(ascii: ._newline)
            decAndWriteIndent()
        }
        writer(ascii: ._closebracket)
    }

    mutating func serializeObject(_ dict: [String:JSONEncoderValue], depth: Int) throws {
        guard depth < Self.maximumRecursionDepth else {
            throw JSONError.tooManyNestedArraysOrDictionaries()
        }

        writer(ascii: ._openbrace)
        if pretty {
            writer(ascii: ._newline)
            incIndent()
            if dict.count > 0 {
                writeIndent()
            }
        }

        var first = true

        func serializeObjectElement(key: String, value: JSONEncoderValue, depth: Int) throws {
            if first {
                first = false
            } else if pretty {
                writer(contentsOf: [._comma, ._newline])
                writeIndent()
            } else {
                writer(ascii: ._comma)
            }
            serializeString(key)
            pretty ? writer(contentsOf: [._space, ._colon, ._space]) : writer(ascii: ._colon)
            try serializeJSON(value, depth: depth)
        }

        if sortedKeys {
            #if FOUNDATION_FRAMEWORK
            var compatibilitySorted = false
            if JSONEncoder.compatibility1 {
                // If applicable, use the old NSString-based sorting with appropriate options
                compatibilitySorted = true
                let nsKeysAndValues = dict.map {
                    (key: $0.key as NSString, value: $0.value)
                }
                let elems = nsKeysAndValues.sorted(by: { a, b in
                    let options: String.CompareOptions = [.numeric, .caseInsensitive, .forcedOrdering]
                    let range = NSMakeRange(0, a.key.length)
                    let locale = Locale.system
                    return a.key.compare(b.key as String, options: options, range: range, locale: locale) == .orderedAscending
                })
                for elem in elems {
                    try serializeObjectElement(key: elem.key as String, value: elem.value, depth: depth)
                }
            }
            #else
            let compatibilitySorted = false
            #endif
            
            // If we didn't use the NSString-based compatibility sorting, sort lexicographically by the UTF-8 view
            if !compatibilitySorted {
                let elems = dict.sorted { a, b in
                    a.key.utf8.lexicographicallyPrecedes(b.key.utf8)
                }
                for elem in elems {
                    try serializeObjectElement(key: elem.key as String, value: elem.value, depth: depth)
                }
            }
        } else {
            for (key, value) in dict {
                try serializeObjectElement(key: key, value: value, depth: depth)
            }
        }

        if pretty {
            writer("\n")
            decAndWriteIndent()
        }
        writer("}")
    }

    mutating func incIndent() {
        indent += 1
    }

    mutating func incAndWriteIndent() {
        indent += 1
        writeIndent()
    }

    mutating func decAndWriteIndent() {
        indent -= 1
        writeIndent()
    }

    mutating func writeIndent() {
        switch indent {
        case 0:  break
        case 1:  writer("  ")
        case 2:  writer("    ")
        case 3:  writer("      ")
        case 4:  writer("        ")
        case 5:  writer("          ")
        case 6:  writer("            ")
        case 7:  writer("              ")
        case 8:  writer("                ")
        case 9:  writer("                  ")
        case 10: writer("                    ")
        default:
            for _ in 0..<indent {
                writer("  ")
            }
        }
    }
}