PureYAML/Sources/Parsing/Scanner.Scalars.swift
Mihaela M 1d07fce635 fix(parsing): reject a comment glued to earlier content on its line
A '#' that begins a comment must be preceded by whitespace or open the
line; glued to earlier same-line content (e.g. "value"# c, [ a, b ]#c,
>#c, a flow entry then ,#c) it is neither a comment nor, in those
positions, plain-scalar content, so the document is malformed. Such input
was previously accepted as a comment.

A '#' that opens a line, follows a space, or sits inside a plain scalar
(a#b, where it stays literal content and never reaches this check) is
unaffected. The scanner tracks whether a real token has been scanned on
the current physical line, reset on each line break, rather than comparing
token line numbers: the streaming tokenizer drains its token buffer
between scans, and a block scalar's blank line emits an empty scalar
attributed to the next line, either of which would misread as content.

Measured against the official YAML test-suite, parse-level conformance
rises from 243/333 (73.0%) to 247/333 (74.2%): four wrongly-accepted
invalid documents are now rejected, with no valid document regressing.
The scalar-scanning routines move to Scanner.Scalars.swift to keep the
file within the length limit.
2026-06-27 15:53:16 +02:00

155 lines
5.7 KiB
Swift

extension PureYAML.Parsing.Scanner {
func scanComment(_ state: inout State) {
let start = state.reader.mark
state.reader.advance()
if state.reader.peek() == " " {
state.reader.advance()
}
let value = state.reader.consume { character in
!isLineBreak(character)
}
state.append(.comment(value), mark: start, endMark: state.reader.mark)
}
func scanQuotedScalar(
_ style: PureYAML.Parsing.ScalarStyle,
state: inout State,
) throws {
let start = state.reader.mark
let quote: Character = style == .doubleQuoted ? "\"" : "'"
state.reader.advance()
var value = ""
var previousWasEscape = false
while let character = state.reader.peek() {
if style == .singleQuoted, character == quote, state.reader.peek(offset: 1) == quote {
value.append(character)
state.reader.advance()
value.append(character)
state.reader.advance()
continue
}
if character == quote, !previousWasEscape {
break
}
value.append(character)
previousWasEscape = character == "\\" && style == .doubleQuoted && !previousWasEscape
state.reader.advance()
if character != "\\" {
previousWasEscape = false
}
}
guard state.reader.peek() == quote else {
throw PureYAML.Parsing.ParseError.unterminatedQuotedString(line: start.line)
}
state.reader.advance()
// Unlike a plain scalar (which consumes the space before a `:` into itself), a quoted scalar
// stops at its closing quote, so the reader sits at any spaces before a `:`. A space between
// an implicit key and its mapping-value indicator is allowed, so look past them.
if isAtMappingValueIndicatorAfterSpaces(state: state) {
state.append(.mappingKey, mark: start, endMark: start)
}
state.append(.scalar(value: value, style: style), mark: start, endMark: state.reader.mark)
}
func scanBlockScalarHeader(
_ style: PureYAML.Parsing.BlockScalarStyle,
state: inout State,
) {
let start = state.reader.mark
var chomping = PureYAML.Parsing.BlockScalarChomping.clip
var indentationIndicator: Int?
state.reader.advance()
while let character = state.reader.peek(), isBlockScalarHeaderCharacter(character) {
if character == "-" {
chomping = .strip
} else if character == "+" {
chomping = .keep
} else if character.isNumber {
indentationIndicator = Int(String(character))
}
state.reader.advance()
}
state.append(
.blockScalarHeader(style: style, chomping: chomping),
mark: start,
endMark: state.reader.mark,
)
state.pendingBlockScalarIndentation = true
state.pendingBlockScalarIndentationIndicator = indentationIndicator
}
func scanBlockScalarContent(_ state: inout State) {
let start = state.reader.mark
let value = state.blockScalarContentPrefix + state.reader.consume { character in
!isLineBreak(character)
}
state.blockScalarContentPrefix = ""
state.append(.scalar(value: value, style: .plain), mark: start, endMark: state.reader.mark)
}
func scanNamedToken(
kind: (String) -> PureYAML.Parsing.TokenKind,
missingNameError: (Int) -> PureYAML.Parsing.ParseError,
state: inout State,
) throws {
let start = state.reader.mark
state.reader.advance()
let name = state.reader.consume { character in
!isTokenTerminator(character)
}
guard !name.isEmpty else {
throw missingNameError(start.line)
}
state.append(kind(name), mark: start, endMark: state.reader.mark)
}
func scanTag(_ state: inout State) throws {
let start = state.reader.mark
state.reader.advance()
var value = "!"
if state.reader.peek() == "<" {
value.append(state.reader.advance() ?? "<")
var didClose = false
while let character = state.reader.peek() {
value.append(character)
state.reader.advance()
if character == ">" {
didClose = true
break
}
}
guard didClose else {
throw PureYAML.Parsing.ParseError.unterminatedTag(line: start.line)
}
} else {
value += state.reader.consume { character in
!isTokenTerminator(character)
}
value = expandTag(value, state: state)
}
state.append(.tag(value), mark: start, endMark: state.reader.mark)
}
func scanPlainScalar(_ state: inout State) {
let start = state.reader.mark
var value = ""
while let character = state.reader.peek() {
if shouldEndPlainScalar(character, state: state, accumulated: value) {
break
}
value.append(character)
state.reader.advance()
}
var trimmed = trimTrailingSpaces(value)
let isMappingKey = appendMappingKeyIfNeeded(start: start, state: &state)
if !isMappingKey {
trimmed = scanPlainScalarContinuations(
after: trimmed,
firstLineIndent: start.column - 1,
state: &state,
)
}
state.append(.scalar(value: trimmed, style: .plain), mark: start, endMark: state.reader.mark)
}
}