PureYAML/Sources/Parsing/TokenEventParser.Block.swift
Mihaela Mihaljevic cdf5f082f8 fix(parsing): support empty (null) nodes in every position
Compose an empty scalar wherever a node is grammatically required but the next token is a structural indicator or line/stream end, mirroring libyaml's process_empty_scalar: after a tag or anchor property with no node, as an absent mapping value (block and flow), as an absent mapping key (both the plain ': v' form and the explicit '?' form), in flow empty key/value forms ({ : }, { , : v }), and for an indented block node following properties. Also fixes a pre-existing block-sequence bug that nested a sibling '-' as a child when only properties remained on the entry line.

Empty scalars resolve through the existing resolver against the empty string, so !!str yields the empty string, bare empty or !!null yields null, and an empty key yields the empty string.

Flips 20 official YAML test suite cases to passing (270/402). CT4Q no longer false-rejects but still value-mismatches on flow plain-scalar folding (a separate gap), so it is reclassified in the manifest rather than removed. Updates the gap manifest, fixtures, counts, and roadmap.
2026-06-23 20:40:40 +02:00

225 lines
9.2 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
}
// After consuming anchor/tag properties the only content remaining on
// this entry's line may be gone: a `mappingKey` or sibling `-` now on
// the same line opens a nested collection, but one on a later line is
// the next sibling, leaving this entry an empty scalar that carries
// the properties.
if cursor.current?.kind.isMappingKey == true, hasNodeOnSameLine(after: entry) {
endMark = try parseBlockMapping(
properties: properties,
includeIndentedContinuation: true,
minimumColumn: entry.mark.column + 1,
).endMark
} else if cursor.current?.kind.isBlockEntry == true, hasNodeOnSameLine(after: entry) {
endMark = try parseBlockSequence(
properties: properties,
allowMappingKeyTerminator: allowMappingKeyTerminator,
).endMark
} else if canBeginNode(cursor.current), hasNodeOnSameLine(after: entry) {
endMark = try parseNode(properties: properties).endMark
} else {
let mark = properties.mark ?? entry.endMark
try emitEmptyScalar(properties: properties, mark: mark)
endMark = mark
}
} 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
}
}
}