PureYAML/Sources/Parsing/Scanner.State.swift

extension PureYAML.Parsing.Scanner {
    struct State {
        var reader: PureYAML.Parsing.Reader
        var tokens: [PureYAML.Parsing.Token] = []
        var indentation: [Int] = [0]
        var isAtLineStart = true
        var hasDocumentContent = false
        var hasDocumentStartMarker = false
        var isDocumentClosed = false
        var hasYAMLDirective = false
        // The line of a directive awaiting its document. A directive must be followed by an explicit
        // `---`; this is set when one is scanned, cleared at a document start, and checked at a
        // document end and at stream end so a directive with no document is rejected.
        var pendingDirectiveLine: Int?
        var flowDepth = 0
        var flowContexts: [PureYAML.Parsing.ScannerFlowContext] = []
        var validImplicitIndentation: Set<Int> = []
        var pendingBlockScalarIndentation = false
        var pendingBlockScalarIndentationIndicator: Int?
        /// Whether the pending block scalar is the document's own root node (no enclosing collection),
        /// so its content may begin at column 0 (the document parent's indentation being -1).
        var pendingBlockScalarIsRootNode = false
        /// Whether the pending block scalar is an inline mapping value (`- key: |2`), whose parent
        /// mapping sits at an implicit indentation off the main stack, so an explicit indentation
        /// indicator is measured relative to that level rather than the stack's.
        var pendingBlockScalarInlineMappingValue = false
        /// The leading-whitespace characters of each blank line between a block scalar header and its
        /// first content line. Stored verbatim (not just counted) so once the content indentation is
        /// known, any surplus past it, notably a tab on an otherwise-blank line, survives as content.
        var pendingBlockScalarLeadingBlankWhitespace: [String] = []
        /// The widest indentation seen on a block scalar's leading blank lines (before its first
        /// content line). The spec forbids a leading empty line from being more indented than the
        /// content, so this is compared to the content indentation once that is known.
        var pendingBlockScalarMaxBlankIndent = 0
        /// The count of leading space characters (before any tab) from the most recent indentation
        /// scan. Indentation is measured in spaces, so this, not the tab-expanded width, is what the
        /// leading-blank comparison uses: a tab is not indentation.
        var lastLeadingSpaceCount = 0
        // The literal leading-whitespace characters from the most recent indentation scan. Block
        // scalar content keeps tabs beyond its (space-only) indentation verbatim, so the surplus is
        // reconstructed from these characters, not as spaces from the tab-expanded width.
        var lastLeadingWhitespace = ""
        var blockScalarIndentation: Int?
        var blockScalarContentPrefix = ""
        /// Whether a real token has been scanned on the current physical line. Reset when the scan
        /// loop consumes a line break and set as each token is scanned, so the scanner can tell a
        /// comment that opens a line (valid) from one glued to earlier content on it (invalid). A
        /// simple flag, not a token-line comparison, because a blank line inside a block scalar
        /// emits an empty scalar attributed to the next line, which would read as phantom content.
        var sawContentOnLine = false
        /// Like ``sawContentOnLine`` but not set by a node property (an anchor or tag). A `:` whose
        /// only preceding same-line content is a property (`&a :`, `!!str :`) is an empty implicit
        /// key carrying that property, so a null mapping key is synthesized for it exactly as for a
        /// bare `: value`. Reset at each line break.
        var sawNonPropertyContentOnLine = false
        // Whether a block-level mapping-value indicator (`:`) has been emitted on the current line.
        // Once one has, a later scalar followed by `:` is not a new implicit key: block style allows
        // only one mapping pair per line, so the document would be a forbidden inline nested mapping
        // (`a: b: c`). Reset at each line break. Flow `:` do not set it, since flow allows several
        // pairs on a line (`{a: b, c: d}`).
        var sawMappingValueOnLine = false
        /// Whether a flow collection has closed on the current line at the top level. A block
        /// sequence entry cannot follow a flow node on the same line (`{a: b}- x`), unlike a nested
        /// block entry (`- -`), which is not preceded by a flow close. Reset at each line break.
        var sawFlowCloseOnLine = false
        // Whether an explicit `?` mapping key is awaiting its `:` value indicator. A `:` that opens
        // a line is that key's value when one is pending, otherwise it is an implicit null key
        // (`: value`). Only the `?` indicator sets this; a synthesized implicit key does not.
        var pendingExplicitKey = false
        /// The tag handles in scope for the current document. A `%TAG` directive's handle applies
        /// only to the document it precedes (YAML 1.2), so handles are scoped per document, not
        /// accumulated across the stream: `pendingTagHandles` collects a document's directives and is
        /// merged onto the defaults at the document start, then both reset at the document boundary.
        static let defaultTagHandles = [
            "!": "!",
            "!!": "tag:yaml.org,2002:",
        ]
        var tagHandles = Self.defaultTagHandles
        var pendingTagHandles: [String: String] = [:]
        /// Tag shorthands using a handle never declared in their document; collected, not rejected.
        var tagHandleIssues: [PureYAML.Parsing.TagHandleIssue] = []

        mutating func append(_ kind: PureYAML.Parsing.TokenKind) {
            let mark = reader.mark
            tokens.append(PureYAML.Parsing.Token(kind: kind, mark: mark, endMark: mark))
            markDocumentContentIfNeeded(kind)
        }

        mutating func append(
            _ kind: PureYAML.Parsing.TokenKind,
            mark: PureYAML.Parsing.Mark,
            endMark: PureYAML.Parsing.Mark,
        ) {
            tokens.append(PureYAML.Parsing.Token(kind: kind, mark: mark, endMark: endMark))
            markDocumentContentIfNeeded(kind)
        }

        mutating func markDocumentContentIfNeeded(_ kind: PureYAML.Parsing.TokenKind) {
            switch kind {
            case .comment, .dedent, .documentEnd, .documentStart, .indent, .streamEnd, .streamStart:
                return
            default:
                hasDocumentContent = true
            }
        }

        var isExpectingFlowMappingKey: Bool {
            flowContexts.last?.kind == .mapping
                && flowContexts.last?.isExpectingKey == true
        }
    }
}