Mihaela Mihaljevic
5a0c2ec7e4
disable-output-escaping on xsl:value-of and xsl:text (sentinel-marked raw text, unescaped after serialization; string extraction from a fragment drops the markers per 16.4), the html default method for a null-namespace html root (16.1), the spec-default XML declaration for the xml method, META Content-Type injection into head (16.2), case-insensitive raw-text and void element classes, and HTML 4.01 Latin-1 named entities on html output. Whitespace-only stripping now means XML whitespace, so NBSP-only text survives. Conf comparison treats tag-adjacent whitespace as layout outside the canonical path. Xalan baseline 371 -> 352 (output 49 -> 30).
73 lines
2.8 KiB
Swift
73 lines
2.8 KiB
Swift
extension PureXML.XSLT {
|
|
/// `disable-output-escaping`: raw text travels through the result tree
|
|
/// bracketed by private-use sentinels, and after serialization the
|
|
/// escaping applied inside the brackets is undone (XSLT 1.0 section 16.4,
|
|
/// the serializer-flag technique).
|
|
enum RawText {
|
|
static let begin: Character = "\u{E000}"
|
|
static let end: Character = "\u{E001}"
|
|
|
|
static func marked(_ text: String) -> String {
|
|
String(begin) + text + String(end)
|
|
}
|
|
|
|
/// The text with any raw markers removed (escaping re-enabled).
|
|
static func stripped(_ text: String) -> String {
|
|
guard text.contains(begin) || text.contains(end) else { return text }
|
|
return String(text.filter { $0 != begin && $0 != end })
|
|
}
|
|
|
|
/// Removes the sentinels, undoing the serializer's escaping between
|
|
/// them. Text outside sentinel pairs passes through untouched.
|
|
static func resolve(_ serialized: String) -> String {
|
|
guard serialized.contains(begin) else { return serialized }
|
|
var result = ""
|
|
var rawRegion = ""
|
|
var inRaw = false
|
|
for character in serialized {
|
|
switch character {
|
|
case begin:
|
|
inRaw = true
|
|
case end:
|
|
result += unescaped(rawRegion)
|
|
rawRegion = ""
|
|
inRaw = false
|
|
default:
|
|
if inRaw {
|
|
rawRegion.append(character)
|
|
} else {
|
|
result.append(character)
|
|
}
|
|
}
|
|
}
|
|
return result + unescaped(rawRegion)
|
|
}
|
|
|
|
/// The serializer's own escape forms, decoded back.
|
|
private static let escapes: [String: Character] = [
|
|
"quot": "\"", "lt": "<", "gt": ">", "amp": "&",
|
|
"#xD": "\r", "#x9": "\t", "#xA": "\n", "#13": "\r", "#9": "\t", "#10": "\n",
|
|
]
|
|
|
|
/// Undoes the XML/HTML serializer escapes.
|
|
private static func unescaped(_ text: String) -> String {
|
|
guard text.contains("&") else { return text }
|
|
var result = ""
|
|
var index = text.startIndex
|
|
while index < text.endIndex {
|
|
guard text[index] == "&",
|
|
let semicolon = text[index...].firstIndex(of: ";"),
|
|
let decoded = escapes[String(text[text.index(after: index) ..< semicolon])]
|
|
else {
|
|
result.append(text[index])
|
|
index = text.index(after: index)
|
|
continue
|
|
}
|
|
result.append(decoded)
|
|
index = text.index(after: semicolon)
|
|
}
|
|
return result
|
|
}
|
|
}
|
|
}
|