PureYAML/Sources/Parsing/Scanner.Helpers.swift

extension PureYAML.Parsing.Scanner {
    /// A blank line inside a block scalar is preserved as empty content so that
    /// chomping and folding can apply to it. The guard keeps blank lines outside
    /// block scalars unaffected; `isAtLineStart` is true here only when the
    /// previous line already ended, so a content line's own terminating break
    /// does not emit a blank. Blank lines between the header and the first
    /// content line precede the indent token, so they are buffered and emitted
    /// once the content indentation is established.
    func captureBlockScalarBlankLine(_ state: inout State) {
        guard state.isAtLineStart else {
            return
        }
        if state.blockScalarIndentation != nil {
            // The prefix holds any surplus indentation past the block's content level for an
            // otherwise-empty line (see `preserveBlockScalarSurplusOnBlankLine`); empty otherwise.
            state.append(.scalar(value: state.blockScalarContentPrefix, style: .plain))
            state.blockScalarContentPrefix = ""
        } else if state.pendingBlockScalarIndentation {
            state.pendingBlockScalarLeadingBlankWhitespace.append(state.lastLeadingWhitespace)
        }
    }

    func startsWith(
        _ prefix: String,
        _ reader: PureYAML.Parsing.Reader,
    ) -> Bool {
        for (offset, character) in prefix.enumerated() {
            guard reader.peek(offset: offset) == character else {
                return false
            }
        }
        return true
    }

    func isLineBreak(_ character: Character?) -> Bool {
        character == "\n" || character == "\r" || character == "\r\n"
    }

    func isBlockEntry(_ reader: PureYAML.Parsing.Reader) -> Bool {
        reader.peek() == "-" && isIndicatorBoundary(reader.peek(offset: 1))
    }

    func isIndicatorBoundary(_ character: Character?) -> Bool {
        guard let character else {
            return true
        }
        // A tab is separation white space in YAML (only indentation forbids it), so it ends an
        // indicator just as a space does: `---\tscalar`, `-\titem`, `?\tkey`.
        return character == " " || character == "\t" || isLineBreak(character)
    }

    func isMappingValueBoundary(_ character: Character?) -> Bool {
        guard let character else {
            return true
        }
        // A tab is separation white space, so it follows a `:` value indicator as a space does.
        return character == " "
            || character == "\t"
            || isLineBreak(character)
            || character == ","
            || character == "]"
            || character == "}"
    }

    func isBlockMappingValueBoundary(_ character: Character?) -> Bool {
        guard let character else {
            return true
        }
        return character == " " || character == "\t" || isLineBreak(character)
    }

    func isTokenTerminator(_ character: Character) -> Bool {
        character == " "
            || isLineBreak(character)
            || character == ","
            || character == "["
            || character == "]"
            || character == "{"
            || character == "}"
            || character == "#"
    }

    func canStartAnchorName(_ character: Character?) -> Bool {
        guard let character else {
            return false
        }
        return !isTokenTerminator(character)
            && character != "*"
            && character != "&"
            && character != "!"
            && character != "\""
            && character != "'"
    }

    func hasNodeOnSameLine(afterCurrentPositionIn reader: PureYAML.Parsing.Reader) -> Bool {
        var offset = 0
        while reader.peek(offset: offset) == " " {
            offset += 1
        }
        guard let character = reader.peek(offset: offset) else {
            return false
        }
        return !isLineBreak(character) && character != "#"
    }

    func isFlowDelimiter(_ character: Character) -> Bool {
        character == ","
            || character == "["
            || character == "]"
            || character == "{"
            || character == "}"
    }

    func isBlockScalarHeaderCharacter(_ character: Character) -> Bool {
        character == "+"
            || character == "-"
            || character.isNumber
    }

    func trimTrailingSpaces(_ value: String) -> String {
        var end = value.endIndex
        while end > value.startIndex {
            let previous = value.index(before: end)
            guard value[previous] == " " else {
                break
            }
            end = previous
        }
        return String(value[..<end])
    }

    func scanPlainScalarContinuations(
        after firstLine: String,
        firstLineIndent: Int,
        state: inout State,
    ) -> String {
        var value = firstLine
        while true {
            var probe = state.reader
            guard isLineBreak(probe.peek()) else {
                return value
            }

            probe.advance()
            let blankLineCount = consumeBlankLines(&probe)

            _ = probe.consume { character in
                character == " "
            }
            let indentationWidth = probe.mark.column - 1

            guard !probe.isAtEnd, !isLineBreak(probe.peek()), probe.peek() != "#" else {
                return value
            }

            // A plain scalar never spans a document marker (`---` / `...`); stop the continuation at
            // one so it begins (or ends) the document rather than folding into the scalar's value.
            if indentationWidth == 0, isAtDocumentMarker(probe) {
                return value
            }

            let baseIndentation = plainScalarContinuationBaseIndentation(state: state, firstLineIndent: firstLineIndent)
            guard indentationWidth > baseIndentation else {
                return value
            }
            if isBlockEntry(probe), state.validImplicitIndentation.contains(indentationWidth) {
                return value
            }

            var continuationState = state
            continuationState.reader = probe
            let continuation = scanPlainScalarContinuationLine(&continuationState)
            if isAtMappingValueIndicator(state: continuationState) {
                // A continuation line ending at `:` is normally a new implicit key, so the scalar
                // stops before it. Two cases keep folding instead, with the `:` left to be scanned as
                // the value indicator: a block explicit key (`? foo` then `bar :`), where the line is
                // still the key's content, and any flow scalar, since a flow key may span lines
                // (`{ multi`/`line: v }`) where a block implicit key may not.
                let foldsAcrossMappingValue = state.flowDepth > 0 || state.pendingExplicitKey
                guard foldsAcrossMappingValue else {
                    return value
                }
                state = continuationState
                value += blankLineCount == 0 ? " " : String(repeating: "\n", count: blankLineCount)
                value += continuation
                return value
            }

            state = continuationState
            if blankLineCount == 0 {
                value += " "
            } else {
                value += String(repeating: "\n", count: blankLineCount)
            }
            value += continuation
        }
    }

    /// Advance `probe` over a run of blank lines (lines that are empty or only spaces), returning
    /// how many were consumed; the probe is left at the start of the next non-blank line.
    func consumeBlankLines(_ probe: inout PureYAML.Parsing.Reader) -> Int {
        var count = 0
        while true {
            var blankProbe = probe
            // A line of only white space is empty for folding, including one that holds a tab: a tab
            // is not indentation, but a whitespace-only line is still blank, so consume it here.
            _ = blankProbe.consume { character in
                character == " " || character == "\t"
            }
            guard isLineBreak(blankProbe.peek()) else {
                break
            }
            blankProbe.advance()
            probe = blankProbe
            count += 1
        }
        return count
    }

    /// Whether the reader is positioned at a document marker (`---` or `...`) followed by an
    /// indicator boundary, i.e. the marker that starts or ends a document.
    func isAtDocumentMarker(_ reader: PureYAML.Parsing.Reader) -> Bool {
        (startsWith("---", reader) || startsWith("...", reader)) && isIndicatorBoundary(reader.peek(offset: 3))
    }

    func plainScalarContinuationBaseIndentation(state: State, firstLineIndent: Int) -> Int {
        // When the scalar begins exactly at the current indentation top, it is a block value on its
        // own line, so its own indent was pushed onto the stack; its continuation lines sit at that
        // same indent, and the level they must exceed is the enclosing block's: the indent below on
        // the stack, or -1 at the document root, where nothing encloses the scalar and a
        // continuation may sit at column 1. For an inline value the top of the stack already is the
        // enclosing block's indent, so it is used directly.
        if state.indentation.last == firstLineIndent {
            return state.indentation.count >= 2 ? state.indentation[state.indentation.count - 2] : -1
        }
        return state.indentation.last ?? 0
    }

    func scanPlainScalarContinuationLine(_ state: inout State) -> String {
        // Leading white space beyond the line's indentation folds away in a plain scalar. A tab is
        // not indentation, so the indentation scan leaves it here; skip it (and any spaces after it)
        // so a continuation line like `\t3rd` joins as `3rd`, not `\t3rd`.
        while let character = state.reader.peek(), character == " " || character == "\t" {
            state.reader.advance()
        }
        var value = ""
        while let character = state.reader.peek(), !isLineBreak(character) {
            if character == " ", state.reader.peek(offset: 1) == "#" {
                break
            }
            if character == "#", value.isEmpty || value.last == " " {
                break
            }
            if character == ":", shouldEndPlainScalarAtMappingValue(state: state) {
                break
            }
            if state.flowDepth > 0, isFlowDelimiter(character) {
                break
            }
            value.append(character)
            state.reader.advance()
        }
        return trimTrailingSpaces(value)
    }

    func skipLine(_ state: inout State) {
        _ = state.reader.consume { character in
            !isLineBreak(character)
        }
    }

    func expandTag(
        _ tag: String,
        state: State,
    ) -> String {
        let handles = state.tagHandles.keys.sorted { first, second in
            first.count > second.count
        }
        for handle in handles where tag.hasPrefix(handle) {
            let suffix = tag.dropFirst(handle.count)
            return (state.tagHandles[handle] ?? handle) + suffix
        }
        return tag
    }

    func shouldEndPlainScalar(
        _ character: Character,
        state: State,
        accumulated: String,
    ) -> Bool {
        if isLineBreak(character) {
            return true
        }
        // A comment opens after white space, a tab as well as a space, so a `#` preceded by either
        // ends the plain scalar: `d\t#X` is the value `d` with a trailing comment.
        if character == " " || character == "\t", state.reader.peek(offset: 1) == "#" {
            return true
        }
        if character == "#", accumulated.isEmpty || accumulated.last == " " || accumulated.last == "\t" {
            return true
        }
        if character == ":", shouldEndPlainScalarAtMappingValue(state: state) {
            return true
        }
        if state.flowDepth > 0, isFlowDelimiter(character) {
            return true
        }
        return false
    }

    func shouldEndPlainScalarAtMappingValue(state: State) -> Bool {
        if state.flowDepth > 0 {
            return state.isExpectingFlowMappingKey
                || isMappingValueBoundary(state.reader.peek(offset: 1))
        }
        return isBlockMappingValueBoundary(state.reader.peek(offset: 1))
    }

    func isAtMappingValueIndicator(state: State) -> Bool {
        state.reader.peek() == ":" && shouldEndPlainScalarAtMappingValue(state: state)
    }

    /// Whether a mapping-value indicator (`: ` or `:` at line end) follows, allowing spaces before
    /// the colon. Used after a quoted scalar, where the reader stops at the closing quote and any
    /// separating spaces remain, unlike a plain scalar that ends at the colon itself.
    func isAtMappingValueIndicatorAfterSpaces(state: State) -> Bool {
        var offset = 0
        while state.reader.peek(offset: offset) == " " {
            offset += 1
        }
        return state.reader.peek(offset: offset) == ":"
            && isBlockMappingValueBoundary(state.reader.peek(offset: offset + 1))
    }

    @discardableResult
    func appendMappingKeyIfNeeded(
        start: PureYAML.Parsing.Mark,
        state: inout State,
    ) -> Bool {
        guard isAtMappingValueIndicator(state: state), canSynthesizeImplicitBlockKey(state) else {
            return false
        }
        state.append(.mappingKey, mark: start, endMark: start)
        return true
    }

    /// Whether a scalar followed by `:` may start an implicit mapping key here. In block style a
    /// line holds at most one mapping pair, so once a block-level `:` has appeared on the line a
    /// further key would form a forbidden inline nested mapping; in flow style several pairs per
    /// line are allowed, so that restriction does not apply. In flow a scalar that is the content of
    /// an open explicit key (`?`) is the key itself, not a new implicit key.
    /// Records the implicit indentation levels a block entry with an inline node introduces: the
    /// node's own indent (one past the dash), and the dash's indent as a sibling level so an inline
    /// item's plain value stops folding at a later entry that returns to it (`: -␣b` then `  - - c`).
    /// The sibling level is skipped under a pending explicit key (`? - x`), whose sequence key drives
    /// implicit indentation itself.
    func recordBlockEntryImplicitIndentation(start: PureYAML.Parsing.Mark, state: inout State) {
        guard hasNodeOnSameLine(afterCurrentPositionIn: state.reader) else {
            return
        }
        state.validImplicitIndentation.insert(start.column + 1)
        if !state.pendingExplicitKey {
            state.validImplicitIndentation.insert(start.column - 1)
        }
    }

    func canSynthesizeImplicitBlockKey(_ state: State) -> Bool {
        if state.flowDepth > 0 {
            return state.flowContexts.last?.hasExplicitKey != true
        }
        return !state.sawMappingValueOnLine
    }
}