PureYAML/Sources/Parsing/Scanner.Directives.swift

extension PureYAML.Parsing.Scanner {
    func scanDirectiveOrDocumentMarker(_ state: inout State) throws -> Bool {
        guard state.indentation.last == 0 else {
            return false
        }
        if state.reader.peek() == "%" {
            try scanDirective(&state)
            return true
        }
        if state.reader.peek() == "#" {
            return false
        }
        if startsWith("---", state.reader), isIndicatorBoundary(state.reader.peek(offset: 3)) {
            try scanDocumentMarker(.documentStart, state: &state)
            resetForDocumentStart(&state)
            return true
        }
        if startsWith("...", state.reader), isIndicatorBoundary(state.reader.peek(offset: 3)) {
            guard !state.isDocumentClosed else {
                throw PureYAML.Parsing.ParseError.unsupportedMultiDocumentStream(line: state.reader.mark.line)
            }
            // A `...` ends a document, so a directive still awaiting its `---` never gets one.
            try enforceDirectiveHasDocument(state)
            try scanDocumentMarker(.documentEnd, state: &state)
            resetForDocumentEnd(&state)
            return true
        }
        guard !state.isDocumentClosed else {
            throw PureYAML.Parsing.ParseError.unsupportedMultiDocumentStream(line: state.reader.mark.line)
        }
        return false
    }

    func scanDocumentMarker(
        _ kind: PureYAML.Parsing.TokenKind,
        state: inout State,
    ) throws {
        let start = state.reader.mark
        state.reader.advance()
        state.reader.advance()
        state.reader.advance()
        state.append(kind, mark: start, endMark: state.reader.mark)
        while state.reader.peek() == " " {
            state.reader.advance()
        }
        if let next = state.reader.peek(), !isLineBreak(next), next != "#" {
            // The marker's own line carries real content. A document start may carry the root node
            // here (e.g. `--- >`, `--- foo`, `--- {a: 1}`), so leave it for the main loop to scan.
            if case .documentStart = kind {
                state.isAtLineStart = false
                return
            }
            // A document end (`...`) takes no same-line node; only a comment or blank may follow it.
            throw PureYAML.Parsing.ParseError.contentAfterDocumentEnd(line: state.reader.mark.line)
        }
        skipLine(&state)
    }

    func resetForDocumentStart(_ state: inout State) {
        state.hasDocumentContent = false
        state.hasDocumentStartMarker = true
        state.isDocumentClosed = false
        state.hasYAMLDirective = false
        state.pendingDirectiveLine = nil
    }

    /// A directive must be followed by an explicit `---` document start. Called at a document end
    /// and at stream end, where a still-pending directive means none ever came.
    func enforceDirectiveHasDocument(_ state: State) throws {
        if let line = state.pendingDirectiveLine {
            throw PureYAML.Parsing.ParseError.directiveWithoutDocument(line: line)
        }
    }

    func resetForDocumentEnd(_ state: inout State) {
        state.hasDocumentContent = false
        state.hasDocumentStartMarker = false
        state.isDocumentClosed = true
        state.hasYAMLDirective = false
    }

    func scanDirective(_ state: inout State) throws {
        let start = state.reader.mark
        let line = state.reader.consume { character in
            !isLineBreak(character)
        }
        let parts = line.split(separator: " ").map(String.init)
        guard let name = parts.first else {
            return
        }
        guard !state.hasDocumentContent, !state.hasDocumentStartMarker, !state.isDocumentClosed else {
            throw PureYAML.Parsing.ParseError.unsupportedDirective(name: name, line: start.line)
        }
        // Every directive must be followed by an explicit `---`; record that one is now awaiting it.
        state.pendingDirectiveLine = start.line
        switch name {
        case "%YAML":
            guard parts.indices.contains(1), parts[1] == "1.1" || parts[1] == "1.2" else {
                throw PureYAML.Parsing.ParseError.incompatibleYAMLDirective(line: start.line)
            }
            // `%YAML` takes exactly one parameter, the version; only a comment may follow it.
            guard parts.count == 2 || parts[2].hasPrefix("#") else {
                throw PureYAML.Parsing.ParseError.malformedDirective(name: name, line: start.line)
            }
            // At most one `%YAML` directive is allowed per document.
            guard !state.hasYAMLDirective else {
                throw PureYAML.Parsing.ParseError.duplicateDirective(name: name, line: start.line)
            }
            state.hasYAMLDirective = true
        case "%TAG":
            guard parts.count >= 3 else {
                return
            }
            state.tagHandles[parts[1]] = parts[2]
        default:
            // A YAML processor ignores a directive it does not recognize (the spec calls for a
            // warning and otherwise no effect), rather than rejecting the document. The line has
            // already been consumed, so there is nothing more to do.
            return
        }
    }
}