PureXML/Sources/Schema/ComplexType.swift
Mihaela Mihaljevic be8a39394d fix(schema): advance XSTS valid-instances-rejected to 4 (#146)
Consolidates the in-progress #146 work; valid-instances-rejected reaches 4
on the 2006-11-06 XSTS archive (buckets now 1/262/4/147).

Regex: match Unicode scalars rather than grapheme clusters; the empty
pattern matches only the empty string; pin the category repertoire to
Unicode 3.2, the version the corpus is consistent at, so code points added
in 3.2 (Tagalog, Cyrillic Komi) are word characters while later additions
(the Tamil digit zero) stay unassigned and match \D. New XSDCategory and a
3.2 assignment table derived from DerivedAge, replacing the old Unicode31
files.

Content model: assess each child against the particle the content automaton
matched, not a by-name lookup (#180). Two same-named particles keep their
own fixed values, and an element matching a skip wildcard is no longer
validated against its global declaration. Selection is made reproducible
when an ambiguous schema slips past the UPA check.

XSTS runner: compile and merge every schemaDocument in a schemaTest, not
just the first; this also surfaced one previously-masked invalid-instance
acceptance (recorded in the baselines).

Also folds in attribute-group anyAttribute inheritance, extension wildcard
union, namespace-qualified type tables for multi-document
xsi:schemaLocation, per-container elementFormDefault, strict and lax
attribute wildcard validation, built-in type resolution, and xs:redefine
simpleType overrides.
2026-06-16 22:22:05 +02:00

222 lines
8.4 KiB
Swift

public extension PureXML.Schema {
/// A model-group compositor.
enum Compositor: Sendable {
/// An ordered list (`xs:sequence`).
case sequence
/// One of the alternatives (`xs:choice`).
case choice
/// Each member once, in any order (`xs:all`).
case all
}
/// The namespace constraint of a wildcard (`xs:any`/`xs:anyAttribute`).
enum WildcardNamespace: Sendable, Equatable {
/// `##any`: a name in any namespace, or none.
case any
/// `##other`: a name in any namespace other than the target, and not in no
/// namespace.
case other
/// A specific set of namespace URIs; the empty string stands for no
/// namespace (`##local`).
case enumerated(Set<String>)
}
/// How a wildcard-matched item is validated: `skip` (no validation), `lax`
/// (validate if a declaration is found), or `strict` (a declaration is
/// required).
enum ProcessContents: Sendable, Equatable {
case skip
case lax
case strict
}
/// An element or attribute wildcard (`xs:any`/`xs:anyAttribute`): which
/// namespaces it admits, and how matched items are validated.
struct Wildcard: Sendable, Equatable {
public var namespace: WildcardNamespace
public var processContents: ProcessContents
/// The schema's target namespace, needed to resolve `##other`.
public var targetNamespace: String?
public init(
namespace: WildcardNamespace = .any,
processContents: ProcessContents = .strict,
targetNamespace: String? = nil,
) {
self.namespace = namespace
self.processContents = processContents
self.targetNamespace = targetNamespace
}
/// Whether `name` is admitted by this wildcard's namespace constraint.
public func admits(_ name: PureXML.Model.QualifiedName) -> Bool {
let namespaceURI = name.namespaceURI ?? ""
switch namespace {
case .any:
return true
case .other:
return !namespaceURI.isEmpty && namespaceURI != (targetNamespace ?? "")
case let .enumerated(uris):
return uris.contains(namespaceURI)
}
}
/// The union of two wildcard constraints (XSD 1.0 `cos-aw-union`), used when
/// a complexContent extension adds its own `anyAttribute`.
func union(with other: Wildcard) -> Wildcard {
Wildcard(
namespace: Self.unionNamespace(namespace, other.namespace),
processContents: Self.unionProcessContents(processContents, other.processContents),
targetNamespace: targetNamespace ?? other.targetNamespace,
)
}
/// Combines optional wildcards from a base type and a derivation.
static func union(_ left: Wildcard?, _ right: Wildcard?) -> Wildcard? {
switch (left, right) {
case (nil, nil): nil
case (let left?, nil): left
case (nil, let right?): right
case let (left?, right?): left.union(with: right)
}
}
private static func unionNamespace(_ left: WildcardNamespace, _ right: WildcardNamespace) -> WildcardNamespace {
switch (left, right) {
case (.any, _), (_, .any): .any
case (.other, .other): .other
case let (.enumerated(lhs), .enumerated(rhs)): .enumerated(lhs.union(rhs))
case (.other, _), (_, .other): .any
}
}
private static func unionProcessContents(_ left: ProcessContents, _ right: ProcessContents) -> ProcessContents {
if left == .strict || right == .strict { return .strict }
if left == .lax || right == .lax { return .lax }
return .skip
}
}
/// The term of a particle: an element declaration, a nested model group, or a
/// wildcard.
indirect enum Term: Sendable {
/// `typeName` is the resolved local name of the element's `type` reference
/// (a built-in, a user type, or `anyType` for an absent type), or nil when
/// the type is an inline anonymous definition. It preserves the derivation
/// identity the flattened `type` (`ElementType`) loses, for NameAndTypeOK.
case element(name: PureXML.Model.QualifiedName, type: ElementType?, typeName: String?, valueConstraint: ValueConstraint? = nil)
case group(Group)
case wildcard(Wildcard)
}
/// A particle: a term with an occurrence range. `maxOccurs` nil means
/// unbounded.
struct Particle: Sendable {
public var minOccurs: Int
public var maxOccurs: Int?
public var term: Term
public init(minOccurs: Int = 1, maxOccurs: Int? = 1, term: Term) {
self.minOccurs = minOccurs
self.maxOccurs = maxOccurs
self.term = term
}
}
/// A model group: a compositor over particles.
struct Group: Sendable {
public var compositor: Compositor
public var particles: [Particle]
public init(compositor: Compositor, particles: [Particle]) {
self.compositor = compositor
self.particles = particles
}
}
/// The declared type of an element: a simple type (text only), a complex one,
/// or a named reference resolved against the schema's type table (which lets
/// recursive schemas be represented without an infinite value).
indirect enum ElementType: Sendable {
case simple(SimpleType)
case complex(ComplexType)
case typeReference(String)
}
/// A value constraint on an attribute or element: a default value supplied
/// when the item is absent, or a fixed value the item must equal.
enum ValueConstraint: Sendable, Equatable {
case `default`(String)
case fixed(String)
/// The fixed value, when this is a `fixed` constraint.
public var fixedValue: String? {
if case let .fixed(value) = self { return value }
return nil
}
/// The constraint's value, whether `default` or `fixed`: the value an
/// empty element or absent attribute takes.
public var value: String {
switch self {
case let .default(value), let .fixed(value): value
}
}
}
/// An attribute use on a complex type.
struct AttributeUse: Sendable {
public var name: PureXML.Model.QualifiedName
public var type: SimpleType
public var required: Bool
public var valueConstraint: ValueConstraint?
/// When true, an unprefixed instance attribute may match this use if the
/// element is in the same namespace (chameleon include only).
public var chameleonUnprefixed: Bool
public init(
name: PureXML.Model.QualifiedName,
type: SimpleType,
required: Bool = false,
valueConstraint: ValueConstraint? = nil,
chameleonUnprefixed: Bool = false,
) {
self.name = name
self.type = type
self.required = required
self.valueConstraint = valueConstraint
self.chameleonUnprefixed = chameleonUnprefixed
}
}
/// The content of a complex type.
indirect enum ContentType: Sendable {
/// No child elements or non-whitespace text.
case empty
/// Character data validated against a simple type, no child elements.
case simpleContent(SimpleType)
/// Child elements matching the particle; no non-whitespace text.
case elementOnly(Particle)
/// Child elements matching the particle, with text allowed between them.
case mixed(Particle)
}
/// A complex type: its attribute uses, an optional attribute wildcard
/// (`xs:anyAttribute`) admitting further attributes, and its content model.
struct ComplexType: Sendable {
public var attributes: [AttributeUse]
public var attributeWildcard: Wildcard?
public var content: ContentType
public init(
attributes: [AttributeUse] = [],
attributeWildcard: Wildcard? = nil,
content: ContentType = .empty,
) {
self.attributes = attributes
self.attributeWildcard = attributeWildcard
self.content = content
}
}
}