PureYAML/Sources/Parsing/LibYAML.Parser.swift

extension PureYAML.Parsing.LibYAML {
    /// A faithful port of libyaml's `parser.c`: a one-event-at-a-time state
    /// machine that consumes the scanner's token stream and produces the YAML
    /// event stream. The token queue is materialized up front by the scanner, so
    /// `peekToken`/`skipToken` index into a fixed array rather than pulling lazily,
    /// which is equivalent because simple-key resolution lives entirely in the
    /// scanner.
    struct Parser {
        let tokens: [Token]
        var cursor = 0
        var state: ParserState = .streamStart
        var states: [ParserState] = []
        var marks: [Mark] = []
        var tagDirectives: [(handle: String, prefix: String)] = []
        /// Whether a bare (implicit) document may begin here: true for the first
        /// document and after an explicit `...` end marker, false otherwise. YAML
        /// 1.2 allows a bare document to follow `...`, which libyaml rejects.
        var allowBareDocument = true

        init(_ input: String = "") throws {
            var scanner = Scanner(input)
            tokens = try scanner.scanAll()
        }

        init(tokens: [Token]) {
            self.tokens = tokens
        }

        /// Drive the state machine until STREAM-END, collecting every event.
        mutating func parse() throws -> [Event] {
            var events: [Event] = []
            while state != .end {
                try events.append(stateMachine())
            }
            return events
        }

        /// The head of the token queue. STREAM-END is always the final token and
        /// the machine halts once it has been consumed, so the clamp is never the
        /// value actually parsed; it only avoids an out-of-range index.
        func peekToken() -> Token {
            tokens[min(cursor, tokens.count - 1)]
        }

        mutating func skipToken() {
            cursor += 1
        }

        /// Port of `yaml_parser_state_machine`: dispatch on the current state. The
        /// flat 24-way switch is split into document/block/flow groups to keep each
        /// dispatcher's branching within the complexity budget.
        mutating func stateMachine() throws -> Event {
            switch state {
            case .streamStart, .implicitDocumentStart, .documentStart, .documentContent, .documentEnd:
                try documentStateMachine()
            case .blockNode, .blockNodeOrIndentlessSequence, .flowNode,
                 .blockSequenceFirstEntry, .blockSequenceEntry, .indentlessSequenceEntry,
                 .blockMappingFirstKey, .blockMappingKey, .blockMappingValue:
                try nodeStateMachine()
            case .flowSequenceFirstEntry, .flowSequenceEntry, .flowSequenceEntryMappingKey,
                 .flowSequenceEntryMappingValue, .flowSequenceEntryMappingEnd,
                 .flowMappingFirstKey, .flowMappingKey, .flowMappingValue, .flowMappingEmptyValue:
                try flowStateMachine()
            case .end:
                throw endError()
            }
        }

        private mutating func documentStateMachine() throws -> Event {
            switch state {
            case .streamStart:
                try parseStreamStart()
            case .implicitDocumentStart:
                try parseDocumentStart()
            case .documentStart:
                try parseDocumentStart()
            case .documentContent:
                try parseDocumentContent()
            default:
                try parseDocumentEnd()
            }
        }

        private mutating func nodeStateMachine() throws -> Event {
            switch state {
            case .blockNode:
                try parseNode(block: true, indentlessSequence: false)
            case .blockNodeOrIndentlessSequence:
                try parseNode(block: true, indentlessSequence: true)
            case .flowNode:
                try parseNode(block: false, indentlessSequence: false)
            case .blockSequenceFirstEntry:
                try parseBlockSequenceEntry(first: true)
            case .blockSequenceEntry:
                try parseBlockSequenceEntry(first: false)
            case .indentlessSequenceEntry:
                try parseIndentlessSequenceEntry()
            case .blockMappingFirstKey:
                try parseBlockMappingKey(first: true)
            case .blockMappingKey:
                try parseBlockMappingKey(first: false)
            default:
                try parseBlockMappingValue()
            }
        }

        private mutating func flowStateMachine() throws -> Event {
            switch state {
            case .flowSequenceFirstEntry:
                try parseFlowSequenceEntry(first: true)
            case .flowSequenceEntry:
                try parseFlowSequenceEntry(first: false)
            case .flowSequenceEntryMappingKey:
                try parseFlowSequenceEntryMappingKey()
            case .flowSequenceEntryMappingValue:
                try parseFlowSequenceEntryMappingValue()
            case .flowSequenceEntryMappingEnd:
                try parseFlowSequenceEntryMappingEnd()
            case .flowMappingFirstKey:
                try parseFlowMappingKey(first: true)
            case .flowMappingKey:
                try parseFlowMappingKey(first: false)
            case .flowMappingValue:
                try parseFlowMappingValue(empty: false)
            default:
                try parseFlowMappingValue(empty: true)
            }
        }

        private func endError() -> ParserError {
            ParserError(context: nil, problem: "parsed past the end of the stream", mark: peekToken().startMark)
        }

        /// Port of `yaml_parser_process_empty_scalar`: an empty plain scalar event
        /// stands in for an absent node.
        func processEmptyScalar(at mark: Mark) -> Event {
            .scalar(value: "", anchor: nil, tag: nil, style: .plain, mark: mark)
        }
    }
}

extension PureYAML.Parsing.LibYAML.Parser {
    typealias Token = PureYAML.Parsing.LibYAML.Token
    typealias Mark = PureYAML.Parsing.Mark
    typealias Event = PureYAML.Parsing.Event
    typealias ParserError = PureYAML.Parsing.LibYAML.ParserError
    typealias ParserState = PureYAML.Parsing.LibYAML.ParserState
}