PureXML/Sources/Parsing/ParseError.swift
Mihaela Mihaljevic 43f82312e6 feat(parser): resolve XML namespaces at the start-element boundary
Add namespace resolution following the XML Namespaces rules, reimplemented in
Swift from libxml2's SAX2 model; no upstream code copied.

- QualifiedName gains an optional resolved namespaceURI (nil for names built
  directly or in no namespace), with a resolved(namespaceURI:) helper.
- NamespaceContext maintains a scope stack of xmlns bindings as elements open
  and close, resolving element and attribute names against it.
- A default namespace applies to unprefixed element names but never to
  attributes; the xml prefix is built in; xmlns declarations are preserved as
  attributes so documents round-trip; an unbound prefix raises
  ParseError.undefinedNamespacePrefix. End-tag matching stays lexical.
- Namespace-free documents are unchanged (URIs remain nil).
- 7 namespace tests; 39 total.
2026-06-08 01:03:29 +02:00

80 lines
3.9 KiB
Swift

public extension PureXML.Parsing {
/// Parser error with source position information when available.
enum ParseError: Swift.Error, Equatable, Sendable, CustomStringConvertible {
case emptyDocument
case unexpectedEndOfInput(Mark)
case unexpectedCharacter(Character, Mark)
case unterminatedTag(Mark)
case unterminatedComment(Mark)
case unterminatedCDATA(Mark)
case mismatchedEndTag(expected: String, found: String, Mark)
case duplicateAttribute(name: String, Mark)
case expectedName(Mark)
case expectedEquals(Mark)
case unquotedAttributeValue(Mark)
case invalidReference(String, Mark)
case unexpectedEndTag(name: String, Mark)
case undefinedNamespacePrefix(prefix: String, Mark)
case junkAfterDocumentElement(Mark)
case nestingTooDeep(limit: Int, Mark)
case nameTooLong(limit: Int, Mark)
case contentTooLong(limit: Int, Mark)
/// A `<!DOCTYPE ...>` declaration was found. DTD processing is disabled by
/// default as a security posture (XXE, entity-expansion DoS); enabling it
/// is a deliberate future opt-in, not silent behavior.
case unsupportedDoctype(Mark)
/// Raised when raw bytes cannot be decoded in the detected encoding (for
/// example an odd-length UTF-16 stream).
case malformedEncoding
/// Raised by entry points whose parsing path is not implemented yet.
case notImplemented(String)
public var description: String {
switch self {
case .emptyDocument:
"document is empty"
case let .unexpectedEndOfInput(mark):
"unexpected end of input at \(mark)"
case let .unexpectedCharacter(character, mark):
"unexpected character '\(character)' at \(mark)"
case let .unterminatedTag(mark):
"unterminated tag starting at \(mark)"
case let .unterminatedComment(mark):
"unterminated comment starting at \(mark)"
case let .unterminatedCDATA(mark):
"unterminated CDATA section starting at \(mark)"
case let .mismatchedEndTag(expected, found, mark):
"expected </\(expected)> but found </\(found)> at \(mark)"
case let .duplicateAttribute(name, mark):
"duplicate attribute '\(name)' at \(mark)"
case let .expectedName(mark):
"expected a name at \(mark)"
case let .expectedEquals(mark):
"expected '=' after attribute name at \(mark)"
case let .unquotedAttributeValue(mark):
"attribute value must be quoted at \(mark)"
case let .invalidReference(reference, mark):
"invalid reference '\(reference)' at \(mark)"
case let .unexpectedEndTag(name, mark):
"unexpected end tag </\(name)> at \(mark)"
case let .undefinedNamespacePrefix(prefix, mark):
"namespace prefix '\(prefix)' is not bound at \(mark)"
case let .junkAfterDocumentElement(mark):
"content after the root element at \(mark)"
case let .nestingTooDeep(limit, mark):
"element nesting exceeds the limit of \(limit) at \(mark)"
case let .nameTooLong(limit, mark):
"name exceeds the length limit of \(limit) at \(mark)"
case let .contentTooLong(limit, mark):
"content exceeds the length limit of \(limit) at \(mark)"
case let .unsupportedDoctype(mark):
"DTD processing is disabled (DOCTYPE at \(mark))"
case .malformedEncoding:
"input bytes are malformed for the detected encoding"
case let .notImplemented(detail):
"not implemented: \(detail)"
}
}
}
}