PureYAML/Sources/Parsing/LibYAML.Scanner.FlowScalar.swift

extension PureYAML.Parsing.LibYAML.Scanner {
    private typealias Classify = PureYAML.Parsing.LibYAML.CharacterClass

    /// The folding state carried through `scan_flow_scalar`, the same shape as the
    /// plain-scalar state.
    private struct FlowState {
        var string = ""
        var leadingBreak = ""
        var trailingBreaks = ""
        var whitespaces = ""
        var leadingBlanks = false
    }

    /// Decoded single-character escapes for double-quoted scalars (libyaml's escape
    /// switch). libyaml emits UTF-8 bytes; here each maps to its Unicode scalar.
    private static let doubleQuotedEscapes: [Unicode.Scalar: Unicode.Scalar] = [
        "0": "\u{0}", "a": "\u{07}", "b": "\u{08}", "t": "\u{09}", "\t": "\u{09}",
        "n": "\u{0A}", "v": "\u{0B}", "f": "\u{0C}", "r": "\u{0D}", "e": "\u{1B}",
        " ": "\u{20}", "\"": "\"", "/": "/", "\\": "\\",
        "N": "\u{85}", "_": "\u{A0}", "L": "\u{2028}", "P": "\u{2029}",
    ]

    /// Port of `yaml_parser_scan_flow_scalar`. Scans a single- or double-quoted
    /// scalar, folding line breaks like a plain scalar and, for double quotes,
    /// decoding escape sequences.
    mutating func scanFlowScalar(single: Bool) throws -> PureYAML.Parsing.LibYAML.Token {
        let startMark = reader.mark
        reader.skip()
        var state = FlowState()
        let quote: Unicode.Scalar = single ? "'" : "\""
        let indent = indentEngine.indent + 1
        // A continuation indented below `indent` is an error, but it is recorded
        // and only raised once the quote is known to close; an unterminated quote
        // reaches end of input first and reports that instead.
        var indentError: PureYAML.Parsing.LibYAML.ScannerError?
        while true {
            if reader.column == 0, documentMarkerAhead() {
                throw flowError("found unexpected document indicator", startMark)
            }
            if reader.peek() == nil {
                throw flowError("found unexpected end of stream", startMark)
            }
            try consumeFlowContent(single: single, &state, startMark: startMark)
            if reader.peek() == quote {
                break
            }
            consumeFlowBreaks(&state, indent: indent, quote: quote, startMark: startMark, error: &indentError)
            foldFlow(&state)
        }
        reader.skip()
        if let indentError {
            throw indentError
        }
        return PureYAML.Parsing.LibYAML.Token(
            type: .scalar(value: state.string, style: single ? .singleQuoted : .doubleQuoted),
            startMark: startMark,
            endMark: reader.mark,
        )
    }

    /// Consume the run of non-blank characters, decoding escapes and stopping at
    /// the closing quote or an escaped line break.
    private mutating func consumeFlowContent(single: Bool, _ state: inout FlowState, startMark: PureYAML.Parsing.Mark) throws {
        state.leadingBlanks = false
        let quote: Unicode.Scalar = single ? "'" : "\""
        while let character = reader.peek(), !Classify.isBlankZ(character) {
            if single, character == "'", reader.peek(1) == "'" {
                state.string.unicodeScalars.append("'")
                reader.skip()
                reader.skip()
            } else if character == quote {
                return
            } else if !single, character == "\\", Classify.isBreak(reader.peek(1)) {
                reader.skip()
                reader.skipLine()
                state.leadingBlanks = true
                return
            } else if !single, character == "\\" {
                try appendEscape(&state, startMark: startMark)
            } else {
                state.string.unicodeScalars.append(character)
                reader.skip()
            }
        }
    }

    /// Decode a double-quoted escape sequence (`\` already at the reader).
    private mutating func appendEscape(_ state: inout FlowState, startMark: PureYAML.Parsing.Mark) throws {
        let escape = reader.peek(1)
        if let escape, let decoded = Self.doubleQuotedEscapes[escape] {
            state.string.unicodeScalars.append(decoded)
            reader.skip()
            reader.skip()
            return
        }
        let codeLength = try hexEscapeLength(escape, startMark: startMark)
        reader.skip()
        reader.skip()
        var value = try readHexEscape(count: codeLength, startMark: startMark)
        if codeLength == 4 {
            value = try combineSurrogateIfNeeded(high: value, startMark: startMark)
        }
        guard let scalar = Unicode.Scalar(value) else {
            throw flowError("found invalid Unicode character escape code", startMark)
        }
        state.string.unicodeScalars.append(scalar)
    }

    /// The hex digit count for `\x` (2), `\u` (4), and `\U` (8) escapes.
    private func hexEscapeLength(_ escape: Unicode.Scalar?, startMark: PureYAML.Parsing.Mark) throws -> Int {
        switch escape {
        case "x": 2
        case "u": 4
        case "U": 8
        default: throw flowError("found unknown escape character", startMark)
        }
    }

    /// Read and consume `count` hexadecimal digits, returning their value.
    private mutating func readHexEscape(count: Int, startMark: PureYAML.Parsing.Mark) throws -> UInt32 {
        var value: UInt32 = 0
        for _ in 0 ..< count {
            guard let digit = reader.peek(), Classify.isHex(digit) else {
                throw flowError("did not find expected hexdecimal number", startMark)
            }
            value = (value << 4) + hexValue(digit)
            reader.skip()
        }
        return value
    }

    /// Combine a UTF-16 surrogate pair (a high surrogate `\u` escape immediately
    /// followed by a low surrogate `\u` escape) into a single astral code point,
    /// for JSON compatibility. A lone high surrogate is left for the scalar check.
    private mutating func combineSurrogateIfNeeded(high: UInt32, startMark: PureYAML.Parsing.Mark) throws -> UInt32 {
        guard (0xD800 ... 0xDBFF).contains(high), reader.peek() == "\\", reader.peek(1) == "u" else {
            return high
        }
        reader.skip()
        reader.skip()
        let low = try readHexEscape(count: 4, startMark: startMark)
        guard (0xDC00 ... 0xDFFF).contains(low) else {
            throw flowError("found invalid Unicode character escape code", startMark)
        }
        return 0x10000 + ((high - 0xD800) << 10) + (low - 0xDC00)
    }

    /// Consume blanks and line breaks between content, recording pending
    /// whitespace and folded breaks.
    private mutating func consumeFlowBreaks(
        _ state: inout FlowState,
        indent: Int,
        quote: Unicode.Scalar,
        startMark: PureYAML.Parsing.Mark,
        error: inout PureYAML.Parsing.LibYAML.ScannerError?,
    ) {
        while Classify.isBlank(reader.peek()) || Classify.isBreak(reader.peek()) {
            if Classify.isBlank(reader.peek()) {
                if error == nil, state.leadingBlanks, reader.column < indent, Classify.isTab(reader.peek()), !blankLineAhead() {
                    error = flowError("found a tab character that violates indentation", startMark)
                }
                if !state.leadingBlanks, let blank = reader.peek() {
                    state.whitespaces.unicodeScalars.append(blank)
                }
                reader.skip()
            } else if !state.leadingBlanks {
                state.whitespaces = ""
                reader.skipLine()
                state.leadingBreak = "\n"
                state.leadingBlanks = true
            } else {
                reader.skipLine()
                state.trailingBreaks += "\n"
            }
        }
        // The continuation content must be indented at least `indent`; a less
        // indented (non-closing, non-empty) line is malformed.
        if error == nil, state.leadingBlanks, let next = reader.peek(), next != quote, !Classify.isBreakZ(next), reader.column < indent {
            error = flowError("found wrong indentation in a multi-line quoted scalar", startMark)
        }
    }

    /// Fold the pending breaks or whitespace into the value.
    private func foldFlow(_ state: inout FlowState) {
        guard state.leadingBlanks else {
            state.string += state.whitespaces
            state.whitespaces = ""
            return
        }
        if state.leadingBreak.first == "\n" {
            if state.trailingBreaks.isEmpty {
                state.string += " "
            } else {
                state.string += state.trailingBreaks
                state.trailingBreaks = ""
            }
            state.leadingBreak = ""
        } else {
            state.string += state.leadingBreak
            state.string += state.trailingBreaks
            state.leadingBreak = ""
            state.trailingBreaks = ""
        }
    }

    private func hexValue(_ scalar: Unicode.Scalar) -> UInt32 {
        switch scalar {
        case "0" ... "9": scalar.value - Unicode.Scalar("0").value
        case "A" ... "F": scalar.value - Unicode.Scalar("A").value + 10
        default: scalar.value - Unicode.Scalar("a").value + 10
        }
    }

    private func flowError(_ problem: String, _ mark: PureYAML.Parsing.Mark) -> PureYAML.Parsing.LibYAML.ScannerError {
        PureYAML.Parsing.LibYAML.ScannerError(context: "while scanning a quoted scalar", problem: problem, mark: mark)
    }

    private mutating func documentMarkerAhead() -> Bool {
        let first = reader.peek()
        guard first == "-" || first == "." else {
            return false
        }
        return reader.peek(1) == first && reader.peek(2) == first && Classify.isBlankZ(reader.peek(3))
    }
}