PureXML/Sources/Schema/XSDValidations.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

119 lines
6.3 KiB
Swift

public extension PureXML.Validation {
/// The compiled-schema context the XSD validations read: the named-type table
/// a content model resolves against, the identity constraints, and the root
/// element's declared type.
struct XSDContext {
public let types: [String: PureXML.Schema.ElementType]
public let constraints: [String: [PureXML.Schema.IdentityConstraint]]
public let rootDeclaration: PureXML.Schema.ElementType?
public let nillableElements: Set<String>
public let elementConstraints: [String: PureXML.Schema.ValueConstraint]
public let abstractTypes: Set<String>
public let typeBlock: [String: Set<PureXML.Schema.DerivationMethod>]
public let elementBlock: [String: Set<PureXML.Schema.DerivationMethod>]
public let typeDerivation: [String: PureXML.Schema.TypeDerivation]
public let globalAttributes: [String: PureXML.Schema.AttributeUse]
public let identityFieldTypes: [String: PureXML.Schema.SimpleType]
public init(
types: [String: PureXML.Schema.ElementType],
constraints: [String: [PureXML.Schema.IdentityConstraint]],
rootDeclaration: PureXML.Schema.ElementType?,
nillableElements: Set<String> = [],
elementConstraints: [String: PureXML.Schema.ValueConstraint] = [:],
abstractTypes: Set<String> = [],
typeBlock: [String: Set<PureXML.Schema.DerivationMethod>] = [:],
elementBlock: [String: Set<PureXML.Schema.DerivationMethod>] = [:],
typeDerivation: [String: PureXML.Schema.TypeDerivation] = [:],
globalAttributes: [String: PureXML.Schema.AttributeUse] = [:],
identityFieldTypes: [String: PureXML.Schema.SimpleType] = [:],
) {
self.types = types
self.constraints = constraints
self.rootDeclaration = rootDeclaration
self.nillableElements = nillableElements
self.elementConstraints = elementConstraints
self.abstractTypes = abstractTypes
self.typeBlock = typeBlock
self.elementBlock = elementBlock
self.typeDerivation = typeDerivation
self.globalAttributes = globalAttributes
self.identityFieldTypes = identityFieldTypes
}
}
}
public extension PureXML.Validation {
/// ``XSDContext``, in the OpenAPIKit idiom: each rule is a named, removable
/// ``Validation`` value with a positive description, and the ``validator()``
/// composes them; failures are located ``ValidationError``s.
///
/// Scope note (the #101 decision). XSD content validation is *one* recursive
/// ``Validation`` (``contentValidity``) rather than a separate rule per
/// constraint, because XSD is a recursive type system: a child's type is
/// resolved from its parent's content model and position, then rewritten by
/// `xsi:type` and the derivation controls mid-walk. The constraint categories
/// (attributes, content model, derivation, nillability, fixed values) are
/// interdependent through that resolution, so they cannot be split into
/// independent rules without either changing semantics or duplicating the
/// recursion. This is the sanctioned multi-error form (the rule's `check`
/// returns one located error per violation). Each category is isolation-tested
/// through crafted inputs so it is verifiable on its own, which is the
/// testability the idiom asks for. Identity constraints, which *are*
/// independent, are a separate rule (``identityConstraints``).
enum XSD {
/// The document element is valid against its declared XSD type.
static var contentValidity: Validation<PureXML.Model.Node, XSDContext> {
.init(
description: "The document element is valid against its XSD type",
check: { context in
guard case let .element(root) = context.subject, let declaration = context.document.rootDeclaration else {
return []
}
let schema = context.document
let validator = PureXML.Schema.ComplexValidator(
types: schema.types,
globalAttributes: schema.globalAttributes,
nillableElements: schema.nillableElements,
elementConstraints: schema.elementConstraints,
abstractTypes: schema.abstractTypes,
typeBlock: schema.typeBlock,
elementBlock: schema.elementBlock,
typeDerivation: schema.typeDerivation,
)
var errors = validator.validate(root, as: declaration, at: [.element(root.name.description)])
// Document-scoped ID uniqueness and IDREF resolution, gathered
// during the typed walk above, reported once the tree is seen.
errors += validator.idErrors()
return errors
},
when: { $0.codingPath.isEmpty },
)
}
/// The document's XSD identity constraints (`unique`, `key`, `keyref`) hold.
static var identityConstraints: Validation<PureXML.Model.Node, XSDContext> {
.init(
description: "XSD identity constraints hold",
check: { context -> [PureXML.Validation.ValidationError] in
guard case let .element(root) = context.subject else { return [] }
return PureXML.Schema.IdentityValidator(
constraints: context.document.constraints,
fieldTypes: context.document.identityFieldTypes,
types: context.document.types,
).validate(PureXML.Model.TreeNode(context.subject), at: [.element(root.name.description)])
},
when: { $0.codingPath.isEmpty },
)
}
/// A validator combining the content-model and identity-constraint rules.
static func validator() -> Validator<XSDContext> {
Validator<XSDContext>.defaults(
nonReference: [AnyValidation(contentValidity)],
reference: [AnyValidation(identityConstraints)],
)
}
}
}