PureYAML/Sources/Parsing/LibYAML.Scanner.swift
Mihaela Mihaljevic d9bf2bda26 feat(parsing): support multi-line flow mapping keys
YAML 1.2 lets a flow-context key be separated from its ':' value indicator
by line breaks, so a flow-level simple key must survive a new line (it is
still bounded to 1024 characters). libyaml invalidates every simple key on
a new line, which wrongly rejects keys like `{"foo"\n: "bar"}` and
multi-line quoted keys.

Canonical event conformance: 259 -> 268 of 308 (4MUZ/00-02, 5MUD, 9SA2,
K3WX, NJ66, UT92, VJP3/01). This passes the hand-rolled parser's 267 and
exceeds libyaml's own 252. 333 tests pass.
2026-06-24 17:46:16 +02:00

113 lines
4.8 KiB
Swift

extension PureYAML.Parsing.LibYAML {
/// Aggregate scanner state, mirroring the fields of `yaml_parser_t` that the
/// ported functions read and write. It is built up as the port proceeds;
/// currently it holds the indentation engine and the simple-key mechanism.
/// Column values follow libyaml's 0-based convention internally; conversion to
/// the package's 1-based `Mark` happens at token emission during integration.
struct Scanner {
/// The input buffer and position (`parser->buffer` / `parser->mark`).
var reader: Reader
/// The indentation stack and `roll_indent` / `unroll_indent` (also the
/// owner of `flow_level` and the token queue).
var indentEngine = IndentEngine()
/// `parser->simple_keys`. Always holds at least the block-context level.
var simpleKeys: [SimpleKey] = [.empty]
/// `parser->simple_key_allowed`. True at stream start.
var simpleKeyAllowed = true
/// `parser->mark`, kept in sync with the reader at each fetch step.
var mark: PureYAML.Parsing.Mark = .start
/// `parser->stream_start_produced`.
var streamStartProduced = false
/// `parser->stream_end_produced`.
var streamEndProduced = false
init(_ input: String = "") {
reader = Reader(input)
}
/// `parser->flow_level`, kept on the indent engine.
var flowLevel: Int {
indentEngine.flowLevel
}
/// Port of `yaml_parser_stale_simple_keys`. A potential simple key is
/// invalid once it is on an earlier line or more than 1024 characters back
/// (a simple key is single-line and bounded); a required one going stale is
/// an error.
mutating func staleSimpleKeys() throws {
for index in simpleKeys.indices {
let key = simpleKeys[index]
guard key.possible else {
continue
}
// A block-context key (index 0) is single-line. A flow-context key
// (index >= 1) may be separated from its ':' by line breaks under
// YAML 1.2, so a new line alone does not invalidate it; both remain
// bounded to 1024 characters. libyaml invalidates every key on a new
// line, which wrongly rejects multi-line flow keys.
let tooFarBack = key.mark.index + 1024 < mark.index
let stale = index == 0 ? (key.mark.line < mark.line || tooFarBack) : tooFarBack
guard stale else {
continue
}
if key.required {
throw ScannerError(
context: "while scanning a simple key",
problem: "could not find expected ':'",
mark: key.mark,
)
}
simpleKeys[index].possible = false
}
}
/// Port of `yaml_parser_save_simple_key`. Record the current position as a
/// potential simple key for this flow level when one is allowed. A key is
/// required (a `:` must follow) when it sits exactly at the block indent.
mutating func saveSimpleKey() throws {
let required = flowLevel == 0 && indentEngine.indent == mark.column
guard simpleKeyAllowed else {
return
}
let key = SimpleKey(
possible: true,
required: required,
tokenNumber: indentEngine.tokensParsed + indentEngine.tokens.count,
mark: mark,
)
try removeSimpleKey()
simpleKeys[simpleKeys.count - 1] = key
}
/// Port of `yaml_parser_remove_simple_key`. Drop the potential key at the
/// current flow level; removing a required key is an error.
mutating func removeSimpleKey() throws {
let top = simpleKeys.count - 1
if simpleKeys[top].possible, simpleKeys[top].required {
throw ScannerError(
context: "while scanning a simple key",
problem: "could not find expected ':'",
mark: simpleKeys[top].mark,
)
}
simpleKeys[top].possible = false
}
/// Port of `yaml_parser_increase_flow_level`. Push an empty simple key for
/// the new flow level.
mutating func increaseFlowLevel() {
simpleKeys.append(.empty)
indentEngine.flowLevel += 1
}
/// Port of `yaml_parser_decrease_flow_level`. Pop the flow level's simple
/// key.
mutating func decreaseFlowLevel() {
if indentEngine.flowLevel > 0 {
indentEngine.flowLevel -= 1
simpleKeys.removeLast()
}
}
}
}