PureXML/Sources/Schema/ComplexValidatorDerivation.swift
Mihaela Mihaljevic 94e16b1d7d
fix(schema): block an xsi:type that reaches a union declared type through a member (#277)
cvc-elt.4.3 defers to cos-st-derived-OK, whose clause 2.2.4 makes a type
validly derived from a union when it is validly derived from one of the
union's member types. The block check followed only the named base chain,
so when the declared type was a union and the substitute reached it through
a member by a blocked derivation method, the check found no path and stayed
silent, wrongly accepting the substitution (W3C XSTS elemT074: block on the
element is restriction and the xsi:type restricts a union member).

Record a union's direct member types during schema compilation and follow a
derivation through a member when the base chain does not reach the union.
The member clause is existential: bar the substitution only when every
confirmed derivation path to a member is blocked, so a substitute that is
itself a member (its self-membership path uses no method) or reaches one
member by an unblocked method is accepted whatever other members it reaches
by a blocked method. The check adds a rejection only on a positively
confirmed path, so an unresolved, inline-anonymous, or nested-union member
leaves it silent: a bounded, disclosed under-rejection, never a false
positive.

Drops XSTS invalid-instances-accepted 15 to 14 with valid-schemas-rejected
and valid-instances-rejected held at 0 over the full archive. An adversarial
over-rejection review caught a first cut that order-shadowed the
self-membership path; the existential form rules it out and the case is a
regression test.
2026-06-24 21:12:35 +02:00

333 lines
18 KiB
Swift

extension PureXML.Schema.ComplexValidator {
/// The first `xsi:type` override error for `child`, if any: a substitution
/// blocked by `block`, a substitute not validly derived from the declared type
/// (cvc-elt.4.3.2.1), or a missing `xsi:type` on an abstract declared type.
///
/// The derivation backbone (`typeDerivation`), `block` tables, and abstract-type
/// set are keyed by namespaced identity (`{ns}local`), so two imported types
/// sharing a local name in different namespaces do not collide. The declared
/// type's reference (`type:{ns}local`) and the instance `xsi:type` (resolved
/// through the element's prefix bindings) are both reduced to that key.
func xsiTypeOverrideError(
declared: PureXML.Schema.ElementType,
child: PureXML.Model.Element,
at path: [PureXML.Validation.PathKey],
namespaceBindings: [String: String],
) -> PureXML.Validation.ValidationError? {
if let blocked = blockedSubstitutionError(declared: declared, child: child, at: path, namespaceBindings: namespaceBindings) { return blocked }
if let notDerived = notDerivedSubstitutionError(declared: declared, child: child, at: path, namespaceBindings: namespaceBindings) { return notDerived }
if let anyTypeSub = anyTypeForAnySimpleTypeError(declared: declared, child: child, at: path, namespaceBindings: namespaceBindings) { return anyTypeSub }
if let listUnion = listUnionSubstitutionError(declared: declared, child: child, at: path, namespaceBindings: namespaceBindings) { return listUnion }
if let abstractType = abstractXsiTypeError(child: child, at: path, namespaceBindings: namespaceBindings) { return abstractType }
if case let .typeReference(name) = declared { return abstractTypeError(named: name, child: child, at: path) }
return nil
}
/// The error when an instance `xsi:type` names an ABSTRACT type: an abstract
/// type cannot be the type of an instance element (cvc-elt.4.3.2), so it may not
/// be used as a substitution. Distinct from ``abstractTypeError``, which covers
/// an abstract DECLARED type with no `xsi:type`.
func abstractXsiTypeError(
child: PureXML.Model.Element,
at path: [PureXML.Validation.PathKey],
namespaceBindings: [String: String],
) -> PureXML.Validation.ValidationError? {
guard let label = Self.xsiTypeName(child),
let reference = Self.xsiTypeReference(child, namespaceBindings: namespaceBindings),
abstractTypes.contains(Self.derivationKey(fromReference: reference))
else { return nil }
return PureXML.Validation.ValidationError(
reason: "xsi:type '\(label)' names an abstract type and may not be used as a substitution",
at: path,
)
}
/// cvc-elt.4.3.2.1 for a list or union `xsi:type`: a list or union simple type
/// is derived only from `anySimpleType`, so it can validly stand in only for an
/// element whose declared type is a ur-type (`anySimpleType`/`anyType`). Naming a
/// list or union type on an element of any more specific atomic or complex type
/// is not a valid derivation. When the declared type is itself a list or union
/// the check stays silent (an inline list/union identity cannot be matched), so
/// it biases to under-reject and never over-rejects.
func listUnionSubstitutionError(
declared: PureXML.Schema.ElementType,
child: PureXML.Model.Element,
at path: [PureXML.Validation.PathKey],
namespaceBindings: [String: String],
) -> PureXML.Validation.ValidationError? {
guard let label = Self.xsiTypeName(child),
let reference = Self.xsiTypeReference(child, namespaceBindings: namespaceBindings),
case let .simple(substitute)? = Self.resolveNamedType(reference, in: types),
Self.isListOrUnion(substitute),
!declaredAdmitsAnySimpleType(declared)
else { return nil }
return PureXML.Validation.ValidationError(
reason: "xsi:type '\(label)' is a list or union type not validly derived from the declared type of '\(child.name.localName)'",
at: path,
)
}
/// cvc-elt.4.3.2.1 for an `anyType` `xsi:type`: `anyType` is the ur-supertype of
/// every type, so it is never DERIVED from `anySimpleType` (its own subtype). An
/// `anyType` override on an `anySimpleType`-declared element is therefore invalid.
/// The general not-derived check stays silent on ur-type declared types to avoid
/// false positives; this rejects only the provably-invalid anyType-for-anySimpleType
/// pairing. `anyType` still validly substitutes for an `anyType`-declared element,
/// which `declaredIsAnySimpleType` excludes (that resolves to a complex ur-type).
func anyTypeForAnySimpleTypeError(
declared: PureXML.Schema.ElementType,
child: PureXML.Model.Element,
at path: [PureXML.Validation.PathKey],
namespaceBindings: [String: String],
) -> PureXML.Validation.ValidationError? {
guard let label = Self.xsiTypeName(child),
let reference = Self.xsiTypeReference(child, namespaceBindings: namespaceBindings),
case let .complex(substitute)? = Self.resolveNamedType(reference, in: types),
Self.isUrType(substitute),
declaredIsAnySimpleType(declared)
else { return nil }
return PureXML.Validation.ValidationError(
reason: "xsi:type '\(label)' is not validly derived from the anySimpleType declared type of '\(child.name.localName)'",
at: path,
)
}
/// Whether `declared` resolves to the simple ur-type `anySimpleType` itself, not
/// `anyType` (a complex ur-type), a list/union, or any more specific type.
private func declaredIsAnySimpleType(_ declared: PureXML.Schema.ElementType) -> Bool {
let resolved: PureXML.Schema.ElementType? = switch declared {
case .simple, .complex: declared
case let .typeReference(reference): resolvedDeclaredType(reference)
}
if case let .simple(type)? = resolved { return type.isAnySimpleType }
return false
}
/// Whether a list or union substitute may validly stand in for `declared`: only
/// the ur-types (`anySimpleType`/`anyType`) admit one. A declared type that is
/// itself a list or union, or an unresolvable reference, is also treated as
/// admitting, so the list/union check stays silent rather than risk a false
/// positive on an inline or unknown declared type.
private func declaredAdmitsAnySimpleType(_ declared: PureXML.Schema.ElementType) -> Bool {
let resolved: PureXML.Schema.ElementType? = switch declared {
case .simple, .complex: declared
case let .typeReference(reference): resolvedDeclaredType(reference)
}
switch resolved {
case let .simple(type): return type.isAnySimpleType || Self.isListOrUnion(type)
case let .complex(type): return Self.isUrType(type)
default: return true
}
}
/// Follows an element-ref / type-reference chain (`element:foo` -> concrete type)
/// to the concrete declared type (a `.simple` or `.complex`), or nil when the
/// chain does not resolve. The name-returning ``resolvedDeclaredTypeName`` walks
/// the same chain for the backbone key.
private func resolvedDeclaredType(_ reference: String) -> PureXML.Schema.ElementType? {
var key = reference
var resolved = types[key] ?? Self.resolveNamedType(key, in: types)
var steps = 0
while case let .typeReference(next)? = resolved, steps <= types.count {
key = next
resolved = types[key] ?? Self.resolveNamedType(key, in: types)
steps += 1
}
return resolved
}
/// Whether a simple type is a list or union (deriving only from `anySimpleType`).
static func isListOrUnion(_ type: PureXML.Schema.SimpleType) -> Bool {
switch type.variety {
case .atomic: false
case .list, .union: true
}
}
/// Whether a substitute type participates in the not-derived check: a complex
/// type, or an ATOMIC simple type. A list or union substitute is excluded here
/// (it is handled by ``listUnionSubstitutionError``).
static func isAtomicOrComplex(_ type: PureXML.Schema.ElementType) -> Bool {
switch type {
case .complex: true
case let .simple(simple): !isListOrUnion(simple)
case .typeReference: false
}
}
/// Whether an element type resolves to a complex type.
static func isComplexType(_ type: PureXML.Schema.ElementType) -> Bool {
if case .complex = type { return true }
return false
}
/// The error when an element's declared type is an abstract complex type and
/// the element supplies no `xsi:type` to name a concrete derived type. An
/// abstract type cannot itself be the type of an instance element.
func abstractTypeError(
named name: String,
child: PureXML.Model.Element,
at path: [PureXML.Validation.PathKey],
) -> PureXML.Validation.ValidationError? {
guard abstractTypes.contains(resolvedDeclaredTypeName(name)),
Self.xsiTypeName(child) == nil
else { return nil }
let bare = PureXML.Schema.XSDParser.bareTypeLocalName(name)
return PureXML.Validation.ValidationError(
reason: "element '\(child.name.localName)' has abstract type '\(bare)' and requires an xsi:type naming a concrete derived type",
at: path,
)
}
/// The error when an `xsi:type` substitution is forbidden by `block` on the
/// declared type: the substituted type reaches the declared type by a method
/// the declared type lists in `block`. Returns nil when there is no named
/// declared type, no `block`, or the substitution is permitted.
func blockedSubstitutionError(
declared: PureXML.Schema.ElementType,
child: PureXML.Model.Element,
at path: [PureXML.Validation.PathKey],
namespaceBindings: [String: String],
) -> PureXML.Validation.ValidationError? {
guard case let .typeReference(reference) = declared,
let substituteLabel = Self.xsiTypeName(child),
let substituteRef = Self.xsiTypeReference(child, namespaceBindings: namespaceBindings),
Self.resolveNamedType(substituteRef, in: types) != nil
else {
return nil
}
let substituteKey = Self.derivationKey(fromReference: substituteRef)
let declaredName = resolvedDeclaredTypeName(reference)
// The substitution is blocked when the derivation method is disallowed by
// either the declared type's `block` or the element declaration's own
// `block`, both keyed by namespaced identity.
let blocked = (typeBlock[declaredName] ?? []).union(elementBlock[Self.key(child.name)] ?? [])
guard isSubstitutionBlocked(from: substituteKey, to: declaredName, by: blocked) else {
return nil
}
return PureXML.Validation.ValidationError(
reason: "xsi:type '\(substituteLabel)' is blocked: substitution by this derivation is disallowed",
at: path,
)
}
/// Whether the `block` set bars deriving `substitute` from `declared`. The
/// derivation is along the base chain, or, when `declared` is a union, through
/// any one of its members (cos-st-derived-OK 2.2.4). That member clause is
/// EXISTENTIAL: the substitution is valid as long as ONE member yields an
/// unblocked derivation, so a substitute that IS a member (the empty-method
/// self-membership path) or reaches one member by an unblocked method is never
/// blocked, whatever other members it also reaches by a blocked method. With no
/// confirmed path at all the check stays silent (under-reject) rather than risk
/// a false positive.
private func isSubstitutionBlocked(
from substitute: String,
to declared: String,
by blocked: Set<PureXML.Schema.DerivationMethod>,
) -> Bool {
if let direct = PureXML.Schema.XSDParser.derivationMethods(from: substitute, to: declared, typeDerivation) {
return !direct.isDisjoint(with: blocked)
}
// `unionMembers` records a union's DIRECT members only, not flattened, so a
// path reaching `declared` through a member that is itself a union is not
// modeled: that member yields no base-chain derivation here, leaving the
// check silent. A bounded, disclosed under-rejection, never an over-rejection.
guard let members = unionMembers[declared] else { return false }
var anyConfirmedPath = false
for member in members {
// The substitute IS a member: derived with no method of its own, so
// this path is unblocked and the substitution is permitted outright.
if member == substitute { return false }
guard let toMember = PureXML.Schema.XSDParser.derivationMethods(from: substitute, to: member, typeDerivation) else {
continue
}
anyConfirmedPath = true
// An unblocked path to any member makes the whole substitution valid.
if toMember.isDisjoint(with: blocked) { return false }
}
// Every confirmed member path is blocked (and at least one exists): bar it.
return anyConfirmedPath
}
/// cvc-elt.4.3.2.1: an `xsi:type` must resolve to a type DERIVED from the
/// element's declared type. This flags the case where both the declared type and
/// the substitute resolve to complex or atomic-simple types recorded in the
/// derivation backbone and there is no derivation path between them (a different
/// branch of the hierarchy, including a substitute that is the declared type's
/// own ancestor). A list or union substitute is handled separately by
/// ``listUnionSubstitutionError``; a substitute or declared type ABSENT from the
/// backbone (a built-in, or the ur-types) leaves the relationship unconfirmable,
/// so the rule stays silent (under-reject) rather than risk a false positive.
func notDerivedSubstitutionError(
declared: PureXML.Schema.ElementType,
child: PureXML.Model.Element,
at path: [PureXML.Validation.PathKey],
namespaceBindings: [String: String],
) -> PureXML.Validation.ValidationError? {
guard case let .typeReference(reference) = declared,
let substituteLabel = Self.xsiTypeName(child),
let substituteRef = Self.xsiTypeReference(child, namespaceBindings: namespaceBindings),
let substituteType = Self.resolveNamedType(substituteRef, in: types),
Self.isAtomicOrComplex(substituteType)
else { return nil }
let substituteKey = Self.derivationKey(fromReference: substituteRef)
let declaredName = resolvedDeclaredTypeName(reference)
// A complex substitute is in scope even when it records no base of its own:
// a baseless complex type derives only from `anyType`, so it cannot derive
// from the declared (non-ur) type and is correctly flagged. An atomic
// substitute must be in the backbone, so a built-in (which derives by the
// primitive hierarchy the backbone does not record) stays silent.
let substituteInScope = Self.isComplexType(substituteType) || typeDerivation[substituteKey] != nil
guard substituteKey != declaredName,
substituteInScope,
typeDerivation[declaredName] != nil || isComplexBackboneRoot(declaredName),
PureXML.Schema.XSDParser.derivationMethods(from: substituteKey, to: declaredName, typeDerivation) == nil
else { return nil }
return PureXML.Validation.ValidationError(
reason: "xsi:type '\(substituteLabel)' is not validly derived from the declared type of '\(child.name.localName)'",
at: path,
)
}
/// A complex type that heads a derivation backbone (some recorded type derives
/// from it) even though it records no base of its own, so it is a legitimate
/// declared-type target for the not-derived check.
private func isComplexBackboneRoot(_ name: String) -> Bool {
let local = PureXML.Schema.XSDParser.unpackElementName(name).0
guard local != "anyType", local != "anySimpleType" else { return false }
return typeDerivation.values.contains { $0.base == name }
}
/// Follows an element-ref / type-reference chain (`element:foo` -> concrete type)
/// to the declared type's namespaced derivation key (`{ns}local`), which the
/// derivation backbone is keyed by.
private func resolvedDeclaredTypeName(_ reference: String) -> String {
var key = reference
var name = Self.derivationKey(fromReference: reference)
var steps = 0
while steps <= types.count {
guard let resolved = types[key] ?? Self.resolveNamedType(key, in: types),
case let .typeReference(next) = resolved
else { break }
key = next
name = Self.derivationKey(fromReference: next)
steps += 1
}
return name
}
/// The namespaced derivation key (`{ns}local`) a type-table reference reduces
/// to. A `type:{ns}local` key has its `type:` prefix stripped to leave the
/// `{ns}local` identity. A bare reference (an unprefixed `xsi:type` resolved in
/// no namespace, or a built-in name) is normalized to `{}local`, matching the
/// no-namespace key the backbone records for an unqualified component. An
/// `element:`/other-keyed reference is left as-is, where it will not match the
/// namespaced backbone and the check stays silent rather than risk a false
/// positive.
static func derivationKey(fromReference reference: String) -> String {
if reference.hasPrefix("type:") { return String(reference.dropFirst("type:".count)) }
if reference.hasPrefix("{") || reference.contains(":") { return reference }
return key(PureXML.Model.QualifiedName(localName: reference, namespaceURI: nil))
}
}