Mihaela Mihaljevic
dd0ff5d086
Make the DTD declaration grammar strict: <!ENTITY> requires its whitespace (after the keyword, around %, after the name), a real name (not #DEFAULT), nothing but '>' after the value, NDATA preceded by whitespace and forbidden on parameter entities; entity-value literals are validated (XML Chars only, every & a complete reference); SYSTEM/PUBLIC external identifiers parse strictly (PUBLIC needs both literals for entities and the DOCTYPE, public-only stays legal for notations) with PubidChar validation; <!ATTLIST> bodies are validated against XML 1.0 productions 52-60 via a new DTDAttListGrammar (spacing, attribute types, enumerations, quoted defaults); the reserved xml PI target is rejected inside the subset. Also: strict UTF-8 decoding (no silent replacement of malformed sequences), XML Char checks in attribute values and CDATA, the declaration's version/encoding value grammar, and required whitespace between pseudo-attributes. The strict machinery lives in DoctypeScannerStrict/DTDAttListGrammar to stay under the length caps. W3C xmltest: not-wf/sa 162/186 rejected (from 129; 80 at first contact), valid/sa 118/119, zero false positives across all 846 tests at every step. The remaining 24-case baseline is exactly: the entity replacement-text class (19) and the deliberate internal-subset extensions this package supports as features (conditional sections, PEs in the internal subset: 5). Part of #120, #105
63 lines
2.8 KiB
Swift
63 lines
2.8 KiB
Swift
/// The start-tag attribute scanners, in their own file to keep the reader's
|
|
/// type body under the length cap. Behavior is part of EventReader proper.
|
|
extension PureXML.Parsing.EventReader {
|
|
mutating func scanAttributes() throws -> [PureXML.Model.Attribute] {
|
|
var attributes: [PureXML.Model.Attribute] = []
|
|
var seen: Set<String> = []
|
|
while true {
|
|
reader.skipSpace()
|
|
guard let next = reader.peek(), next != ">", next != "/" else {
|
|
return attributes
|
|
}
|
|
let mark = reader.mark
|
|
let name = try scanName()
|
|
reader.skipSpace()
|
|
guard reader.consume("=") else {
|
|
throw PureXML.Parsing.ParseError.expectedEquals(reader.mark)
|
|
}
|
|
reader.skipSpace()
|
|
let value = try scanAttributeValue()
|
|
guard seen.insert(name.description).inserted else {
|
|
if recovering {
|
|
// Keep the element: record the duplicate and drop the later
|
|
// occurrence rather than failing the whole start tag.
|
|
diagnostics.append(PureXML.Parsing.Diagnostic(PureXML.Parsing.ParseError.duplicateAttribute(name: name.description, mark)))
|
|
continue
|
|
}
|
|
throw PureXML.Parsing.ParseError.duplicateAttribute(name: name.description, mark)
|
|
}
|
|
attributes.append(PureXML.Model.Attribute(name: name, value: value))
|
|
// A following attribute needs whitespace before it.
|
|
if let next = reader.peek(), next != ">", next != "/", next != "?", !next.isWhitespace {
|
|
throw PureXML.Parsing.ParseError.missingSpaceBeforeAttribute(reader.mark)
|
|
}
|
|
}
|
|
}
|
|
|
|
mutating func scanAttributeValue() throws -> String {
|
|
let mark = reader.mark
|
|
guard let quote = reader.peek(), quote == "\"" || quote == "'" else {
|
|
throw PureXML.Parsing.ParseError.unquotedAttributeValue(reader.mark)
|
|
}
|
|
reader.advance()
|
|
var raw = ""
|
|
var length = 0
|
|
while let character = reader.peek(), character != quote {
|
|
length += 1
|
|
try checkContent(length, mark)
|
|
if character == "<" {
|
|
throw PureXML.Parsing.ParseError.rawLessThanInAttribute(reader.mark)
|
|
}
|
|
guard character.unicodeScalars.allSatisfy(PureXML.Parsing.XMLCharacter.isChar) else {
|
|
throw PureXML.Parsing.ParseError.invalidCharacter(reader.mark)
|
|
}
|
|
raw.append(character)
|
|
reader.advance()
|
|
}
|
|
guard reader.consume(String(quote)) else {
|
|
throw PureXML.Parsing.ParseError.unexpectedEndOfInput(reader.mark)
|
|
}
|
|
return try PureXML.Parsing.EntityDecoder.decode(raw, entities: documentType.entities, budget: &entityBudget, at: mark)
|
|
}
|
|
}
|