PureYAML/Sources/Parsing/TokenEventParser.Block.swift
Mihaela Mihaljevic 3db3e87d39 fix(parsing): correct block scalar folding and chomping
Rewrite literal (|) and folded (>) block scalar content to YAML 1.2 section 8.1: preserve interior blank lines, apply 8.1.3 line folding (a single break between equally indented non-empty lines folds to a space, while blank lines and more-indented lines keep their breaks), preserve tabs in content (only block-indentation columns are stripped), and support the + keep chomping indicator alongside clip and strip.

The block scalar is now scanned as a single unit (header line plus all content lines) with indentation auto-detection in Scanner.BlockScalar.swift, mirroring the reference scanner, instead of being reassembled from a lossy per-line token array.

Flips 24 official YAML test suite cases to passing (220/402). Updates the gap manifest, vendored fixtures, count assertions, and the conformance roadmap.
2026-06-23 20:01:03 +02:00

216 lines
8.5 KiB
Swift

extension PureYAML.Parsing.TokenEventParser {
mutating func parseBlockSequence(
properties: PureYAML.Parsing.NodeProperties,
allowMappingKeyTerminator: Bool = false,
) throws -> PureYAML.Parsing.NodeResult {
let start = try expect("block sequence entry") { $0.isBlockEntry }
let startMark = properties.mark ?? start.mark
var endMark = start.endMark
try emit(.sequenceStart(
anchor: properties.anchor,
tag: properties.tag,
style: .block,
mark: startMark,
))
try parseBlockSequenceItem(
after: start,
endMark: &endMark,
allowMappingKeyTerminator: allowMappingKeyTerminator,
)
try consumeSequenceItemBoundaryDedent(sequenceIndentWidth: start.mark.column - 1)
try consumeSequenceItemBoundaryIndent(sequenceIndentWidth: start.mark.column - 1)
while cursor.current?.kind.isBlockEntry == true {
let entry = try expect("block sequence entry") { $0.isBlockEntry }
try parseBlockSequenceItem(
after: entry,
endMark: &endMark,
allowMappingKeyTerminator: allowMappingKeyTerminator,
)
try consumeSequenceItemBoundaryDedent(sequenceIndentWidth: entry.mark.column - 1)
try consumeSequenceItemBoundaryIndent(sequenceIndentWidth: entry.mark.column - 1)
}
if let current = cursor.current, current.kind.isMappingKey, !allowMappingKeyTerminator {
throw PureYAML.Parsing.ParseError.mixedCollectionStyles(line: current.mark.line)
}
try emit(.sequenceEnd(mark: endMark))
return PureYAML.Parsing.NodeResult(kind: .sequence, endMark: endMark)
}
mutating func consumeSequenceItemBoundaryDedent(sequenceIndentWidth: Int) throws {
guard dedentWidth(cursor.current) == sequenceIndentWidth,
try cursor.peek()?.kind.isBlockEntry == true
else {
return
}
_ = try expect("dedent") { $0.isDedent }
}
mutating func consumeSequenceItemBoundaryIndent(sequenceIndentWidth: Int) throws {
guard indentWidth(cursor.current) == sequenceIndentWidth,
try cursor.peek()?.kind.isBlockEntry == true
else {
return
}
_ = try expect("indent") { $0.isIndent }
}
mutating func parseBlockSequenceItem(
after entry: PureYAML.Parsing.Token,
endMark: inout PureYAML.Parsing.Mark,
allowMappingKeyTerminator: Bool,
) throws {
if hasNodeOnSameLine(after: entry) {
let properties = try consumeProperties()
if cursor.current?.kind.isIndent == true {
_ = try expect("indent") { $0.isIndent }
endMark = try parseNode(properties: properties).endMark
_ = try expect("dedent") { $0.isDedent }
return
}
if cursor.current?.kind.isMappingKey == true {
endMark = try parseBlockMapping(
properties: properties,
includeIndentedContinuation: true,
minimumColumn: entry.mark.column + 1,
).endMark
} else if cursor.current?.kind.isBlockEntry == true {
endMark = try parseBlockSequence(
properties: properties,
allowMappingKeyTerminator: allowMappingKeyTerminator,
).endMark
} else {
endMark = try parseNode(properties: properties).endMark
}
} else if cursor.current?.kind.isIndent == true {
_ = try expect("indent") { $0.isIndent }
endMark = try parseNode().endMark
_ = try expect("dedent") { $0.isDedent }
} else {
let mark = entry.endMark
try emit(.scalar(value: "", anchor: nil, tag: nil, style: .plain, mark: mark))
endMark = mark
}
}
mutating func parseBlockMapping(
properties: PureYAML.Parsing.NodeProperties,
includeIndentedContinuation: Bool,
minimumColumn: Int? = nil,
) throws -> PureYAML.Parsing.NodeResult {
let startMark = properties.mark ?? cursor.current?.mark ?? .start
let tokenColumn = cursor.current?.mark.column ?? startMark.column
let contentColumn = min(startMark.column, tokenColumn)
let boundaryColumn = minimumColumn ?? contentColumn
var endMark = startMark
try emit(.mappingStart(
anchor: properties.anchor,
tag: properties.tag,
style: .block,
mark: startMark,
))
try parseBlockMappingPairs(
boundaryColumn: boundaryColumn,
includeIndentedContinuation: includeIndentedContinuation,
endMark: &endMark,
)
if let current = cursor.current, !canEndBlockMapping(at: current, minimumColumn: boundaryColumn) {
throw PureYAML.Parsing.ParseError.unexpectedToken(
expected: "mapping key",
actual: current.kind.description,
line: current.mark.line,
column: current.mark.column,
)
}
try emit(.mappingEnd(mark: endMark))
return PureYAML.Parsing.NodeResult(kind: .mapping, endMark: endMark)
}
mutating func parseBlockMappingPairs(
boundaryColumn: Int,
includeIndentedContinuation: Bool,
endMark: inout PureYAML.Parsing.Mark,
) throws {
while canContinueBlockMapping(minimumColumn: boundaryColumn) {
endMark = try parseMappingPairAndBoundaries(
boundaryColumn: boundaryColumn,
includeIndentedContinuation: includeIndentedContinuation,
).endMark
}
while includeIndentedContinuation, cursor.current?.kind.isIndent == true {
endMark = try parseIndentedBlockMappingPairs(boundaryColumn: boundaryColumn).endMark
}
}
mutating func parseIndentedBlockMappingPairs(
boundaryColumn: Int,
) throws -> PureYAML.Parsing.NodeResult {
_ = try expect("indent") { $0.isIndent }
guard cursor.current?.kind.isMappingKey == true else {
throw unexpectedToken(expected: "mapping key")
}
var endMark = cursor.current?.mark ?? .start
while canContinueBlockMapping(minimumColumn: boundaryColumn) {
endMark = try parseMappingPairAndBoundaries(
boundaryColumn: boundaryColumn,
includeIndentedContinuation: true,
).endMark
}
if !canEndBlockMapping(at: cursor.current, minimumColumn: boundaryColumn) {
_ = try expect("dedent") { $0.isDedent }
}
return PureYAML.Parsing.NodeResult(kind: .mapping, endMark: endMark)
}
mutating func parseMappingPairAndBoundaries(
boundaryColumn: Int,
includeIndentedContinuation: Bool,
) throws -> PureYAML.Parsing.NodeResult {
let result = try parseMappingPair()
try consumeMappingSiblingBoundaryDedents(minimumColumn: boundaryColumn)
try consumeMappingSiblingBoundaryReindent(minimumColumn: boundaryColumn)
if includeIndentedContinuation {
try consumeDedents(atOrAbove: boundaryColumn)
try consumeMappingSiblingBoundaryDedents(minimumColumn: boundaryColumn)
try consumeMappingSiblingBoundaryReindent(minimumColumn: boundaryColumn)
}
return result
}
mutating func parseBlockScalar(
properties: PureYAML.Parsing.NodeProperties,
) throws -> PureYAML.Parsing.NodeResult {
let header = try expect("block scalar header") { kind in
if case .blockScalarHeader = kind {
return true
}
return false
}
guard case let .blockScalarHeader(_, _, value) = header.kind else {
throw unexpectedToken(expected: "block scalar header")
}
let mark = properties.mark ?? header.mark
try emit(.scalar(
value: value,
anchor: properties.anchor,
tag: properties.tag,
style: scalarStyle(for: header.kind),
mark: mark,
))
return PureYAML.Parsing.NodeResult(kind: .scalar, endMark: header.endMark)
}
func scalarStyle(for kind: PureYAML.Parsing.TokenKind) -> PureYAML.Parsing.ScalarStyle {
switch kind {
case .blockScalarHeader(.folded, _, _):
.folded
case .blockScalarHeader(.literal, _, _):
.literal
default:
.plain
}
}
}