PureXML/Sources/Schema/SchemaIDAttribute.swift
Mihaela Mihaljevic d2f18a2685 feat(schema): substitution member type must derive from head (e-props-correct.4)
An element declaring substitutionGroup="head" whose own type is unrelated to
the head's type was accepted; XSD 1.0 e-props-correct.4 requires the member's
type be validly derived from the head's. The check runs after named types
resolve and reuses the restriction/extension + built-in-lattice derivation
oracle (an ur-type head admits any member).

It is conservative so it never rejects a valid member: it runs only for a
self-contained schema (no import/include/redefine, where the derivation table
is complete and single-namespace names are unambiguous), reads the member's
type from its own type attribute and the head's from the top-level element
declarations only (so a local element of the same name supplies neither), and
stands down when either type is a list or union (cos-st-derived-ok clauses
2.3/2.4 union-member derivation is not modelled).

The post-namedTypes consistency calls move into a postNamedTypeErrors
aggregator alongside consistencyErrors. XSTS: invalid schemas accepted
480 to 479, no other bucket raised.
2026-06-15 13:08:38 +02:00

73 lines
4.1 KiB
Swift

extension PureXML.Schema.XSDParser {
/// Schema-validity findings for the `id` attributes in a schema document. The
/// `id` attribute on any XSD component is of type `xs:ID`, so each value must
/// be a valid NCName and all values must be unique within the document
/// (XSD Structures: `xs:ID` and the ID/IDREF constraints). The values were
/// never checked, so a malformed (`id=""`, `id="123"`) or duplicated `id` left
/// the schema wrongly accepted.
///
/// Walks the one document rooted at `schema`; an included or imported document
/// keeps its own `id` scope, so cross-document collisions are not flagged here.
static func idAttributeErrors(_ schema: XSDTree) -> [String] {
var errors: [String] = []
var seen: Set<String> = []
collectIDErrors(schema, into: &errors, seen: &seen)
return errors
}
private static func collectIDErrors(_ node: XSDTree, into errors: inout [String], seen: inout Set<String>) {
// `appinfo` and `documentation` hold arbitrary foreign content whose own
// `id` attributes are not xs:ID; do not descend into them.
let local = PureXML.Schema.XSDNode.localName(node)
if local == "appinfo" || local == "documentation" { return }
if let id = unprefixedID(node) {
if !PureXML.Schema.Lexical.isNCName(id) {
errors.append("id attribute value '\(id)' is not a valid NCName")
} else if !seen.insert(id).inserted {
errors.append("duplicate id attribute value '\(id)' in the schema document")
}
}
for child in PureXML.Schema.XSDNode.elementChildren(node) {
collectIDErrors(child, into: &errors, seen: &seen)
}
}
/// The value of the unprefixed, no-namespace `id` attribute (the xs:ID one),
/// or nil. A prefixed attribute such as `xml:id` or a foreign `pre:id` is a
/// different attribute and is not the schema-component identifier.
private static func unprefixedID(_ node: XSDTree) -> String? {
node.attributes.first { $0.name.prefix == nil && $0.name.localName == "id" }?.value
}
/// All compile-time schema-consistency findings, collected together so they are
/// reported in one pass: `id` validity, schema-for-schemas structure, global
/// component-name uniqueness, content-model determinism (UPA), and circular
/// type derivation. The explicit return type keeps the type-checker from
/// inferring a long concatenation.
static func consistencyErrors(_ schema: XSDTree, _ context: PureXML.Schema.XSDContext, _ containers: [XSDTree]) -> [String] {
let structural = idAttributeErrors(schema) + structureErrors(schema) + componentNameErrors(schema)
let determinism = PureXML.Schema.ContentModelDeterminism.violations(in: schema, context: context)
let cycles = derivationCycleErrors(containers, context.namespaceBindings, context.targetNamespace)
+ circularReferenceErrors(containers, context.namespaceBindings, context.targetNamespace)
let placement = allGroupReferencePlacementErrors(containers, context.namespaceBindings, context.targetNamespace)
return structural + determinism + cycles + placement
}
/// Consistency findings that depend on the resolved named types, collected after
/// `namedTypes` has populated them: unresolved references, attribute-use
/// uniqueness and single-ID, ID-typed value constraints, and substitution-group
/// member type derivation (`e-props-correct.4`).
static func postNamedTypeErrors(
_ schema: XSDTree,
_ context: PureXML.Schema.XSDContext,
_ containers: [XSDTree],
_ derivation: DerivationTables,
typeMaps: (global: [String: PureXML.Schema.ElementType], named: [String: PureXML.Schema.ElementType]),
) -> [String] {
referenceErrors(schema, in: context, elements: typeMaps.global)
+ attributeUseErrors(containers, context)
+ idValueConstraintErrors(schema, context)
+ substitutionTypeErrors(schema, derivation, typeMaps.named)
}
}