PureYAML/Sources/Parsing/LibYAML.Reader.swift

extension PureYAML.Parsing.LibYAML {
    /// Port of libyaml's input buffer and position tracking (the `buffer`/`mark`
    /// fields with the `PEEK`, `SKIP`, and `SKIP_LINE` macros). It iterates
    /// `Unicode.Scalar`s rather than grapheme clusters so a CR and an LF are
    /// distinct, matching libyaml's byte-oriented scanning, and tracks the mark in
    /// libyaml's 0-based line and column convention; conversion to the package's
    /// 1-based `Mark` happens at token emission during integration.
    struct Reader {
        private var scalars: [Unicode.Scalar]
        private(set) var index = 0
        private(set) var line = 0
        private(set) var column = 0
        /// Whether the buffered `scalars` are the complete input. True for every
        /// batch caller (the default), so `ranDry` can never be set and this type's
        /// behavior is unchanged for `scanAll()`. A resumable caller passes `false`
        /// and later calls `markFinal()` once the last chunk has been appended.
        private(set) var isFinal: Bool
        /// Set by `peek(_:)` when it was asked for a position past the buffered
        /// scalars while `!isFinal`: the query is inconclusive, not a real end of
        /// input, and the caller must suspend and retry after `append(_:)`. Batch
        /// callers (`isFinal == true`) never set this, since the guard below is
        /// unreachable when `isFinal` is true.
        private(set) var ranDry = false

        /// The index of the first non-`c-printable` scalar found in `scalars`
        /// (libyaml's reader-level check, `yaml_parser_update_buffer`'s printable
        /// validation), or nil if none has been found yet. Set once, by whichever
        /// of `init`/`append(_:)` first buffers the offending scalar; never
        /// cleared. `fetchNextToken()` checks this once per token and throws,
        /// mirroring libyaml rejecting raw control characters (anything outside
        /// `c-printable`, i.e. not a plain tab/CR/LF and not in the printable
        /// ranges `CharacterClass.isPrintable` implements) wherever they occur in
        /// the stream, not only inside specific constructs like anchor names.
        private(set) var invalidControlCharacterIndex: Int?

        init(_ string: String = "", isFinal: Bool = true) {
            scalars = Array(string.unicodeScalars)
            self.isFinal = isFinal
            recordFirstInvalidControlCharacter(in: 0 ..< scalars.count)
        }

        /// `PEEK_TOKEN` / `CHECK_AT`: the scalar `offset` ahead, or nil past the
        /// end (libyaml's `\0`). Past the buffered end while more chunks may still
        /// arrive, this flags `ranDry` instead of asserting true end of input.
        mutating func peek(_ offset: Int = 0) -> Unicode.Scalar? {
            let position = index + offset
            if position < scalars.count {
                return scalars[position]
            }
            if !isFinal {
                ranDry = true
            }
            return nil
        }

        /// Append a chunk of newly arrived input. Only meaningful before
        /// `markFinal()`. Clears `ranDry`: new data may satisfy whatever `peek(_:)`
        /// call set it, and nothing else ever clears it. The existing
        /// checkpoint-restore path gets this for free (the restored `Reader` is a
        /// copy from before the dry read), but a resumed scan that keeps its
        /// reader position instead of restoring a snapshot (`PlainScalarSuspended`)
        /// has no other point where a stale `true` would ever become false again.
        mutating func append(_ chunk: String) {
            let previousCount = scalars.count
            scalars.append(contentsOf: chunk.unicodeScalars)
            ranDry = false
            recordFirstInvalidControlCharacter(in: previousCount ..< scalars.count)
        }

        /// Declare that no further chunks are coming: a `peek` past the buffered
        /// end is now a real end of input, matching the batch reader's behavior.
        mutating func markFinal() {
            isFinal = true
        }

        var isAtEnd: Bool {
            index >= scalars.count
        }

        /// The current position. Column is 0-based, as in libyaml.
        var mark: PureYAML.Parsing.Mark {
            PureYAML.Parsing.Mark(line: line, column: column, index: index)
        }

        /// `SKIP`: consume one non-break scalar, advancing the column.
        mutating func skip() {
            guard index < scalars.count else {
                return
            }
            index += 1
            column += 1
        }

        /// `SKIP_LINE`: consume a line break and start a new line. A CR+LF pair is
        /// one break, matching libyaml.
        mutating func skipLine() {
            if peek() == "\r", peek(1) == "\n" {
                index += 2
            } else if CharacterClass.isBreak(peek()) {
                index += 1
            } else {
                return
            }
            line += 1
            column = 0
        }

        /// The 0-based line/column of `scalars[index]`, computed by counting line
        /// breaks from the start of the buffer. Not the hot `mark` path (that
        /// tracks `line`/`column` incrementally as scanning consumes characters);
        /// used only once, lazily, when `fetchNextToken()` actually needs to report
        /// `invalidControlCharacterIndex` as a `Mark`, since that index can be
        /// anywhere in the buffer, not necessarily at the reader's current
        /// scanning position.
        func mark(atIndex target: Int) -> PureYAML.Parsing.Mark {
            var line = 0
            var column = 0
            var cursor = 0
            while cursor < target, cursor < scalars.count {
                if scalars[cursor] == "\r", cursor + 1 < scalars.count, scalars[cursor + 1] == "\n" {
                    line += 1
                    column = 0
                    cursor += 2
                } else if CharacterClass.isBreak(scalars[cursor]) {
                    line += 1
                    column = 0
                    cursor += 1
                } else {
                    column += 1
                    cursor += 1
                }
            }
            return PureYAML.Parsing.Mark(line: line, column: column, index: target)
        }

        /// Scans `range` (a slice of `scalars` just buffered by `init`/`append(_:)`)
        /// for the first scalar outside `CharacterClass.isPrintable`, recording its
        /// index if one is found and none was already recorded. Only the first
        /// occurrence overall matters (matching libyaml, which reports the first
        /// invalid byte and stops), so once `invalidControlCharacterIndex` is set
        /// this is a no-op.
        private mutating func recordFirstInvalidControlCharacter(in range: Range<Int>) {
            guard invalidControlCharacterIndex == nil else {
                return
            }
            for index in range where !CharacterClass.isPrintable(scalars[index]) {
                invalidControlCharacterIndex = index
                return
            }
        }
    }
}