extension PureYAML.Parsing.LibYAML.Scanner { private typealias Classify = PureYAML.Parsing.LibYAML.CharacterClass private typealias Token = PureYAML.Parsing.LibYAML.Token private typealias ScannerError = PureYAML.Parsing.LibYAML.ScannerError /// Produce every token for the input, mirroring repeated calls to libyaml's /// `yaml_parser_fetch_next_token` until STREAM-END. Tokens are never dequeued, /// so `tokens_parsed` stays 0 and `QUEUE_INSERT` positions are absolute, which /// matches the simple-key splice. mutating func scanAll() throws -> [PureYAML.Parsing.LibYAML.Token] { while !streamEndProduced { try fetchNextToken() } return indentEngine.tokens } /// Port of `yaml_parser_scan_to_next_token`: skip a leading BOM, spaces and /// tabs, a comment, and a single line break, which re-allows a simple key in /// the block context. A tab is valid in-line separation, so it is skipped /// here; `tabbedSeparation` records when one preceded the token so a block /// indicator or implicit key (where the tab would be indentation) can reject. private mutating func scanToNextToken() { while true { tabbedSeparation = false if reader.column == 0, reader.peek() == "\u{FEFF}" { reader.skip() } while reader.peek() == " " || Classify.isTab(reader.peek()) { if Classify.isTab(reader.peek()), flowLevel == 0, simpleKeyAllowed { tabbedSeparation = true } reader.skip() } // YAML 1.2: a line containing only whitespace is blank even when that // whitespace includes tabs. libyaml leaves a leading tab in place and // later rejects it; instead consume the trailing blanks so the line // break below is reached and the blank line is skipped. if blankLineAhead() { while reader.peek() == " " || Classify.isTab(reader.peek()) { reader.skip() } } if reader.peek() == "#" { while !Classify.isBreakZ(reader.peek()) { reader.skip() } } if Classify.isBreak(reader.peek()) { reader.skipLine() if flowLevel == 0 { simpleKeyAllowed = true } } else { break } } } /// Port of `yaml_parser_fetch_next_token`: emit STREAM-START first, otherwise /// skip to the next token, expire stale simple keys, unroll the indentation to /// the current column, and dispatch on the leading character. Constructs not /// yet ported throw an explicit error rather than mis-scan. mutating func fetchNextToken() throws { if !streamStartProduced { fetchStreamStart() return } scanToNextToken() mark = reader.mark try staleSimpleKeys() indentEngine.unrollIndent(column: reader.column, mark: reader.mark) mark = reader.mark try dispatchToken() } /// Dispatch on the leading character: stream end, directives and document /// markers at column 0, then the indicators. private mutating func dispatchToken() throws { let character = reader.peek() if Classify.isZ(character) { fetchStreamEnd() return } if reader.column == 0, character == "%" { try fetchDirective() return } if reader.column == 0, isDocumentMarker("-") { fetchDocumentIndicator(.documentStart) return } if reader.column == 0, isDocumentMarker(".") { fetchDocumentIndicator(.documentEnd) return } guard let character else { return } try dispatchIndicator(character) } /// Dispatch the block-structure indicators and plain scalars; unported /// constructs throw an explicit error. private mutating func dispatchIndicator(_ character: Unicode.Scalar) throws { if try fetchFlowToken(character) { return } if try fetchNodeToken(character) { return } switch character { case "-" where Classify.isBlankZ(reader.peek(1)): try fetchBlockEntry() case "?" where Classify.isBlankZ(reader.peek(1)) || (flowLevel > 0 && Classify.isFlowIndicator(reader.peek(1))): // In flow context libyaml treats every `?` as a key indicator, but per // `ns-plain-first` a `?` followed by a flow-safe character (anything but // whitespace, end, or a flow indicator) begins a plain scalar (`?foo`). try fetchKey() case ":" where Classify.isBlankZ(reader.peek(1)) || (flowLevel > 0 && (Classify.isFlowIndicator(reader.peek(1)) || flowKeyIsJSON)): // In flow context libyaml makes every `:` a value indicator. Per the // spec a `:` only ends a node when followed by whitespace, end of // input, or a flow indicator, except an adjacent `:` after a JSON // (quoted) key. Otherwise the `:` is plain-scalar content (`:x`). try fetchValue() default: // A plain scalar may begin with any non-blank character; a blank (a // tab here, since spaces and breaks were already consumed) cannot // start a token, matching libyaml's final guard in fetch_next_token. guard !Classify.isBlankZ(character) else { throw ScannerError( context: "while scanning for the next token", problem: "found character that cannot start any token", mark: reader.mark, ) } try fetchPlainScalar() } } /// The error raised when a tab is used where indentation is required (before a /// block indicator or an implicit mapping key). A tab is valid separation but /// never indentation. private func tabIndentationError() -> PureYAML.Parsing.LibYAML.ScannerError { ScannerError( context: "while scanning for the next token", problem: "found a tab character where an indentation space is expected", mark: reader.mark, ) } /// Whether this flow level's pending simple key is a JSON (quoted) node, which /// lets an adjacent `:` open its value without a separating space. private var flowKeyIsJSON: Bool { let key = simpleKeys[simpleKeys.count - 1] return key.possible && key.isJSON } /// Fetch a flow-collection indicator (`[` `]` `{` `}` `,`); returns false /// otherwise. private mutating func fetchFlowToken(_ character: Unicode.Scalar) throws -> Bool { switch character { case "[": fetchFlowCollectionStart(.flowSequenceStart) case "{": fetchFlowCollectionStart(.flowMappingStart) case "]": try fetchFlowCollectionEnd(.flowSequenceEnd) case "}": try fetchFlowCollectionEnd(.flowMappingEnd) case ",": try fetchFlowEntry() default: return false } return true } /// Fetch a quoted scalar, an anchor/alias, or a block scalar; returns false /// otherwise. private mutating func fetchNodeToken(_ character: Unicode.Scalar) throws -> Bool { switch character { case "'": try fetchFlowScalar(single: true) case "\"": try fetchFlowScalar(single: false) case "&": try fetchAnchor(isAnchor: true) case "*": try fetchAnchor(isAnchor: false) case "!": try fetchTag() case "|" where flowLevel == 0: try fetchBlockScalar(literal: true) case ">" where flowLevel == 0: try fetchBlockScalar(literal: false) default: return false } return true } /// Port of `yaml_parser_fetch_tag`. private mutating func fetchTag() throws { mark = reader.mark try saveSimpleKey() simpleKeyAllowed = false let token = try scanTag() indentEngine.enqueue(token) } /// Port of `yaml_parser_fetch_block_scalar`. private mutating func fetchBlockScalar(literal: Bool) throws { try removeSimpleKey() simpleKeyAllowed = true let token = try scanBlockScalar(literal: literal) indentEngine.enqueue(token) } /// Port of `yaml_parser_fetch_flow_scalar`. private mutating func fetchFlowScalar(single: Bool) throws { mark = reader.mark let saved = simpleKeyAllowed try saveSimpleKey() // A quoted scalar that became this level's simple key is a JSON node, so a // later adjacent `:` (no space) still opens its value. if saved { simpleKeys[simpleKeys.count - 1].isJSON = true } simpleKeyAllowed = false let token = try scanFlowScalar(single: single) indentEngine.enqueue(token) } /// Port of `yaml_parser_fetch_anchor`. private mutating func fetchAnchor(isAnchor: Bool) throws { mark = reader.mark try saveSimpleKey() simpleKeyAllowed = false let token = try scanAnchor(isAnchor: isAnchor) indentEngine.enqueue(token) } /// Port of `yaml_parser_fetch_flow_collection_start`. private mutating func fetchFlowCollectionStart(_ type: PureYAML.Parsing.LibYAML.TokenType) { // saveSimpleKey cannot throw in flow: a required key needs block context. let saved = simpleKeyAllowed try? saveSimpleKey() // A flow collection is a JSON node, so when it is this level's simple key // an adjacent `:` after its closing `]`/`}` still opens its value. if saved { simpleKeys[simpleKeys.count - 1].isJSON = true } increaseFlowLevel() simpleKeyAllowed = true let startMark = reader.mark reader.skip() indentEngine.enqueue(Token(type: type, startMark: startMark, endMark: reader.mark)) } /// Port of `yaml_parser_fetch_flow_collection_end`. private mutating func fetchFlowCollectionEnd(_ type: PureYAML.Parsing.LibYAML.TokenType) throws { try removeSimpleKey() decreaseFlowLevel() simpleKeyAllowed = false let startMark = reader.mark reader.skip() indentEngine.enqueue(Token(type: type, startMark: startMark, endMark: reader.mark)) } /// Port of `yaml_parser_fetch_flow_entry`. private mutating func fetchFlowEntry() throws { try removeSimpleKey() simpleKeyAllowed = true let startMark = reader.mark reader.skip() indentEngine.enqueue(Token(type: .flowEntry, startMark: startMark, endMark: reader.mark)) } /// Port of `yaml_parser_fetch_stream_start`. private mutating func fetchStreamStart() { // indent is already -1 and simpleKeys already holds the block-context slot. simpleKeyAllowed = true streamStartProduced = true indentEngine.enqueue(Token(type: .streamStart, startMark: reader.mark, endMark: reader.mark)) } /// Port of `yaml_parser_fetch_stream_end`. private mutating func fetchStreamEnd() { if reader.column != 0 { // Force a new line in the mark, as libyaml does. mark = PureYAML.Parsing.Mark(line: reader.line + 1, column: 0, index: reader.index) } indentEngine.unrollIndent(column: -1, mark: mark) // remove_simple_key cannot throw here: a required key would already have // been resolved before stream end in the block + plain core. simpleKeys[simpleKeys.count - 1].possible = false simpleKeyAllowed = false streamEndProduced = true indentEngine.enqueue(Token(type: .streamEnd, startMark: mark, endMark: mark)) } /// Port of `yaml_parser_fetch_document_indicator`. private mutating func fetchDocumentIndicator(_ type: PureYAML.Parsing.LibYAML.TokenType) { indentEngine.unrollIndent(column: -1, mark: reader.mark) simpleKeys[simpleKeys.count - 1].possible = false simpleKeyAllowed = false let startMark = reader.mark reader.skip() reader.skip() reader.skip() indentEngine.enqueue(Token(type: type, startMark: startMark, endMark: reader.mark)) } /// Port of `yaml_parser_fetch_block_entry`. private mutating func fetchBlockEntry() throws { if tabbedSeparation { throw tabIndentationError() } if flowLevel == 0 { indentEngine.rollIndent(column: reader.column, number: -1, type: .blockSequenceStart, mark: reader.mark) } simpleKeys[simpleKeys.count - 1].possible = false simpleKeyAllowed = true let startMark = reader.mark reader.skip() indentEngine.enqueue(Token(type: .blockEntry, startMark: startMark, endMark: reader.mark)) } /// Port of `yaml_parser_fetch_key`. private mutating func fetchKey() throws { if tabbedSeparation { throw tabIndentationError() } if flowLevel == 0 { indentEngine.rollIndent(column: reader.column, number: -1, type: .blockMappingStart, mark: reader.mark) } simpleKeys[simpleKeys.count - 1].possible = false simpleKeyAllowed = flowLevel == 0 let startMark = reader.mark reader.skip() indentEngine.enqueue(Token(type: .key, startMark: startMark, endMark: reader.mark)) } /// Port of `yaml_parser_fetch_value`, including the simple-key splice: a /// possible simple key inserts its `KEY` token at the recorded position and /// rolls the block mapping indent to the key's column. private mutating func fetchValue() throws { let top = simpleKeys.count - 1 if simpleKeys[top].possible { if simpleKeys[top].tabbed { throw tabIndentationError() } let key = simpleKeys[top] indentEngine.insert(Token(type: .key, startMark: key.mark, endMark: key.mark), atTokenNumber: key.tokenNumber) indentEngine.rollIndent(column: key.mark.column, number: key.tokenNumber, type: .blockMappingStart, mark: key.mark) simpleKeys[top].possible = false simpleKeyAllowed = false } else { if flowLevel == 0 { indentEngine.rollIndent(column: reader.column, number: -1, type: .blockMappingStart, mark: reader.mark) } simpleKeyAllowed = flowLevel == 0 } let startMark = reader.mark reader.skip() indentEngine.enqueue(Token(type: .value, startMark: startMark, endMark: reader.mark)) } /// Port of `yaml_parser_fetch_plain_scalar`. private mutating func fetchPlainScalar() throws { mark = reader.mark try saveSimpleKey() simpleKeyAllowed = false let token = try scanPlainScalar() indentEngine.enqueue(token) } /// Whether the rest of the current line, from the current position, is only /// spaces and tabs up to a line break or end of stream (a blank line). private func blankLineAhead() -> Bool { var offset = 0 while let character = reader.peek(offset), character == " " || Classify.isTab(character) { offset += 1 } return Classify.isBreakZ(reader.peek(offset)) } private func isDocumentMarker(_ character: Unicode.Scalar) -> Bool { reader.peek(0) == character && reader.peek(1) == character && reader.peek(2) == character && Classify.isBlankZ(reader.peek(3)) } }