Mihaela Mihaljevic
56e889f790
Add EUC-TW for the whole-buffer and streaming decoders: ASCII, a two-byte plane-1 pair, and a 0x8E four-byte plane selector plus a pair. CNS planes 1 and 2, which carry essentially all real-world EUC-TW text, are vendored from the ICU euc-tw-2014 mapping (private-use fallbacks dropped); planes 3-15 are a documented follow-up. Tested for plane 1 (two-byte and four-byte forms), plane 2, and streaming. The streaming method moved to its own file to stay under the type-body cap. Closes #108
26 lines
1.1 KiB
Swift
26 lines
1.1 KiB
Swift
extension PureXML.Parsing.StreamingDecoder {
|
|
/// Streams one EUC-TW character: ASCII, a two-byte plane-1 pair, or a `0x8E`
|
|
/// four-byte plane selector plus a pair.
|
|
mutating func nextEUCTW() -> Character? {
|
|
guard let lead = nextByte() else {
|
|
finished = true
|
|
return nil
|
|
}
|
|
if lead <= 0x7F { return Character(Unicode.Scalar(lead)) }
|
|
if lead == 0x8E {
|
|
guard let plane = nextByte(), let byte1 = nextByte(), let byte2 = nextByte() else {
|
|
finished = true
|
|
return Self.replacement
|
|
}
|
|
return PureXML.Parsing.ByteDecoder.EUCTW.fourByteScalar(plane, byte1, byte2).map(Character.init) ?? Self.replacement
|
|
}
|
|
guard (0xA1 ... 0xFE).contains(lead) else { return Self.replacement }
|
|
guard let trail = nextByte() else {
|
|
finished = true
|
|
return Self.replacement
|
|
}
|
|
let table = PureXML.Parsing.ByteDecoder.eucTWPlane1
|
|
return PureXML.Parsing.ByteDecoder.EUCTW.planeScalar(table, lead, trail).map(Character.init) ?? Self.replacement
|
|
}
|
|
}
|