Mihaela Mihaljevic
2eb9f83958
XSD 1.0 (Datatypes Appendix F) defines the regex escape \i as the characters that may begin an XML Name (Letter | '_' | ':') and \c as the characters that may appear in one (NameChar), citing the XML 1.0 Second Edition productions: the enumerated, Unicode-2.0-era character classes of XML 1.0 Appendix B (BaseChar, Ideographic, CombiningChar, Digit, Extender). \i and \c were wired to PureXML.Parsing.XMLCharacter, which correctly implements the Fifth Edition Name production used to parse live XML, but the two genuinely differ: the Fifth Edition admits whole blocks where the Second Edition has gaps, so \c over-accepted, e.g. the combining mark U+0346 (COMBINING BRIDGE ABOVE), which Appendix B's CombiningChar excludes (its first range ends at U+0345). Add XSDNameCharacter, transcribed clean-room from the Appendix B grammar (identical across editions one through four) and stored as sorted, non- overlapping code-point ranges with binary-search membership; the parser's own name check is untouched. The two tables reproduce the W3C XSTS \i/\c enumerations (reZ005, reZ006: 34516 and 35122 code points) exactly and in both directions, so the more restrictive definition rejects no spec-valid input: there is no false-positive surface. Verified over the full W3C XSTS corpus in release: invalid-instances-accepted 12 -> 11 (reZ006i, whose value is U+0346, now rejects), both false-positive buckets at 0. Full suite (1834 tests) green; an adversarial critic brute-forced the binary search over the whole code-point space (0 mismatches), confirmed the tables are sorted and non-overlapping and equal the oracle sets, and that the parser's Fifth Edition path is left intact. Found by triaging the invalid- instance tail to a single boundary code point (U+0345 valid vs U+0346 invalid) and reading the XML 1.0 Appendix B grammar.
148 lines
11 KiB
Swift
148 lines
11 KiB
Swift
extension PureXML.Regex {
|
|
/// The XML 1.0 name-character classes that back the XSD regular-expression
|
|
/// escapes `\i` and `\c` (XSD 1.0 Datatypes Appendix F). XSD 1.0 defines
|
|
/// `\i` as the characters that may begin an XML Name (`Letter | '_' | ':'`)
|
|
/// and `\c` as the characters that may appear in one (`NameChar`), citing the
|
|
/// productions of XML 1.0 Second Edition. Those are the enumerated character
|
|
/// classes of XML 1.0 Appendix B (BaseChar, Ideographic, CombiningChar, Digit,
|
|
/// Extender), a fixed Unicode-2.0-era repertoire, not the broad ranges XML 1.0
|
|
/// Fifth Edition later substituted.
|
|
///
|
|
/// This is deliberately distinct from ``PureXML/Parsing/XMLCharacter``, which
|
|
/// implements the Fifth Edition Name production used to parse live XML: the two
|
|
/// definitions genuinely differ (Fifth Edition admits whole blocks where Second
|
|
/// Edition has gaps, e.g. the combining range is `[#x0300-#x0345]` here but the
|
|
/// entire `0x300...0x36F` block in the parser). Using the parser's check for
|
|
/// `\c` over-accepted, e.g. the combining mark U+0346 (XSTS reZ006i).
|
|
///
|
|
/// The ranges are transcribed clean-room from the XML 1.0 Appendix B grammar
|
|
/// (identical across editions one through four; only the fifth replaced it) and
|
|
/// stored sorted and non-overlapping so membership is a binary search. They are
|
|
/// verified to reproduce the W3C XSTS `\i`/`\c` enumerations (reZ005, reZ006)
|
|
/// exactly, in both directions, by ``XSDNameCharacterTests``.
|
|
enum XSDNameCharacter {
|
|
/// Whether `scalar` may begin an XML Name per XSD `\i` (`Letter | '_' | ':'`).
|
|
static func isNameStart(_ scalar: Unicode.Scalar) -> Bool {
|
|
contains(scalar.value, in: nameStartRanges)
|
|
}
|
|
|
|
/// Whether `scalar` may appear in an XML Name per XSD `\c` (`NameChar`).
|
|
static func isNameChar(_ scalar: Unicode.Scalar) -> Bool {
|
|
contains(scalar.value, in: nameCharRanges)
|
|
}
|
|
|
|
/// Binary search over a sorted, non-overlapping `[lo, hi, lo, hi, ...]`
|
|
/// table; each step compares one range's inclusive bounds.
|
|
private static func contains(_ value: UInt32, in ranges: [UInt32]) -> Bool {
|
|
var low = 0
|
|
var high = ranges.count / 2
|
|
while low < high {
|
|
let mid = (low + high) / 2
|
|
if value < ranges[mid * 2] {
|
|
high = mid
|
|
} else if value > ranges[mid * 2 + 1] {
|
|
low = mid + 1
|
|
} else {
|
|
return true
|
|
}
|
|
}
|
|
return false
|
|
}
|
|
}
|
|
}
|
|
|
|
private extension PureXML.Regex.XSDNameCharacter {
|
|
/// Inclusive `[lo, hi]` bounds of the XSD `\i` set: XML 1.0 Appendix B
|
|
/// `Letter` (`BaseChar | Ideographic`) plus `'_'` and `':'`.
|
|
static let nameStartRanges: [UInt32] = [
|
|
0x3A, 0x3A, 0x41, 0x5A, 0x5F, 0x5F, 0x61, 0x7A, 0xC0, 0xD6, 0xD8, 0xF6,
|
|
0xF8, 0x131, 0x134, 0x13E, 0x141, 0x148, 0x14A, 0x17E, 0x180, 0x1C3, 0x1CD, 0x1F0,
|
|
0x1F4, 0x1F5, 0x1FA, 0x217, 0x250, 0x2A8, 0x2BB, 0x2C1, 0x386, 0x386, 0x388, 0x38A,
|
|
0x38C, 0x38C, 0x38E, 0x3A1, 0x3A3, 0x3CE, 0x3D0, 0x3D6, 0x3DA, 0x3DA, 0x3DC, 0x3DC,
|
|
0x3DE, 0x3DE, 0x3E0, 0x3E0, 0x3E2, 0x3F3, 0x401, 0x40C, 0x40E, 0x44F, 0x451, 0x45C,
|
|
0x45E, 0x481, 0x490, 0x4C4, 0x4C7, 0x4C8, 0x4CB, 0x4CC, 0x4D0, 0x4EB, 0x4EE, 0x4F5,
|
|
0x4F8, 0x4F9, 0x531, 0x556, 0x559, 0x559, 0x561, 0x586, 0x5D0, 0x5EA, 0x5F0, 0x5F2,
|
|
0x621, 0x63A, 0x641, 0x64A, 0x671, 0x6B7, 0x6BA, 0x6BE, 0x6C0, 0x6CE, 0x6D0, 0x6D3,
|
|
0x6D5, 0x6D5, 0x6E5, 0x6E6, 0x905, 0x939, 0x93D, 0x93D, 0x958, 0x961, 0x985, 0x98C,
|
|
0x98F, 0x990, 0x993, 0x9A8, 0x9AA, 0x9B0, 0x9B2, 0x9B2, 0x9B6, 0x9B9, 0x9DC, 0x9DD,
|
|
0x9DF, 0x9E1, 0x9F0, 0x9F1, 0xA05, 0xA0A, 0xA0F, 0xA10, 0xA13, 0xA28, 0xA2A, 0xA30,
|
|
0xA32, 0xA33, 0xA35, 0xA36, 0xA38, 0xA39, 0xA59, 0xA5C, 0xA5E, 0xA5E, 0xA72, 0xA74,
|
|
0xA85, 0xA8B, 0xA8D, 0xA8D, 0xA8F, 0xA91, 0xA93, 0xAA8, 0xAAA, 0xAB0, 0xAB2, 0xAB3,
|
|
0xAB5, 0xAB9, 0xABD, 0xABD, 0xAE0, 0xAE0, 0xB05, 0xB0C, 0xB0F, 0xB10, 0xB13, 0xB28,
|
|
0xB2A, 0xB30, 0xB32, 0xB33, 0xB36, 0xB39, 0xB3D, 0xB3D, 0xB5C, 0xB5D, 0xB5F, 0xB61,
|
|
0xB85, 0xB8A, 0xB8E, 0xB90, 0xB92, 0xB95, 0xB99, 0xB9A, 0xB9C, 0xB9C, 0xB9E, 0xB9F,
|
|
0xBA3, 0xBA4, 0xBA8, 0xBAA, 0xBAE, 0xBB5, 0xBB7, 0xBB9, 0xC05, 0xC0C, 0xC0E, 0xC10,
|
|
0xC12, 0xC28, 0xC2A, 0xC33, 0xC35, 0xC39, 0xC60, 0xC61, 0xC85, 0xC8C, 0xC8E, 0xC90,
|
|
0xC92, 0xCA8, 0xCAA, 0xCB3, 0xCB5, 0xCB9, 0xCDE, 0xCDE, 0xCE0, 0xCE1, 0xD05, 0xD0C,
|
|
0xD0E, 0xD10, 0xD12, 0xD28, 0xD2A, 0xD39, 0xD60, 0xD61, 0xE01, 0xE2E, 0xE30, 0xE30,
|
|
0xE32, 0xE33, 0xE40, 0xE45, 0xE81, 0xE82, 0xE84, 0xE84, 0xE87, 0xE88, 0xE8A, 0xE8A,
|
|
0xE8D, 0xE8D, 0xE94, 0xE97, 0xE99, 0xE9F, 0xEA1, 0xEA3, 0xEA5, 0xEA5, 0xEA7, 0xEA7,
|
|
0xEAA, 0xEAB, 0xEAD, 0xEAE, 0xEB0, 0xEB0, 0xEB2, 0xEB3, 0xEBD, 0xEBD, 0xEC0, 0xEC4,
|
|
0xF40, 0xF47, 0xF49, 0xF69, 0x10A0, 0x10C5, 0x10D0, 0x10F6, 0x1100, 0x1100, 0x1102, 0x1103,
|
|
0x1105, 0x1107, 0x1109, 0x1109, 0x110B, 0x110C, 0x110E, 0x1112, 0x113C, 0x113C, 0x113E, 0x113E,
|
|
0x1140, 0x1140, 0x114C, 0x114C, 0x114E, 0x114E, 0x1150, 0x1150, 0x1154, 0x1155, 0x1159, 0x1159,
|
|
0x115F, 0x1161, 0x1163, 0x1163, 0x1165, 0x1165, 0x1167, 0x1167, 0x1169, 0x1169, 0x116D, 0x116E,
|
|
0x1172, 0x1173, 0x1175, 0x1175, 0x119E, 0x119E, 0x11A8, 0x11A8, 0x11AB, 0x11AB, 0x11AE, 0x11AF,
|
|
0x11B7, 0x11B8, 0x11BA, 0x11BA, 0x11BC, 0x11C2, 0x11EB, 0x11EB, 0x11F0, 0x11F0, 0x11F9, 0x11F9,
|
|
0x1E00, 0x1E9B, 0x1EA0, 0x1EF9, 0x1F00, 0x1F15, 0x1F18, 0x1F1D, 0x1F20, 0x1F45, 0x1F48, 0x1F4D,
|
|
0x1F50, 0x1F57, 0x1F59, 0x1F59, 0x1F5B, 0x1F5B, 0x1F5D, 0x1F5D, 0x1F5F, 0x1F7D, 0x1F80, 0x1FB4,
|
|
0x1FB6, 0x1FBC, 0x1FBE, 0x1FBE, 0x1FC2, 0x1FC4, 0x1FC6, 0x1FCC, 0x1FD0, 0x1FD3, 0x1FD6, 0x1FDB,
|
|
0x1FE0, 0x1FEC, 0x1FF2, 0x1FF4, 0x1FF6, 0x1FFC, 0x2126, 0x2126, 0x212A, 0x212B, 0x212E, 0x212E,
|
|
0x2180, 0x2182, 0x3007, 0x3007, 0x3021, 0x3029, 0x3041, 0x3094, 0x30A1, 0x30FA, 0x3105, 0x312C,
|
|
0x4E00, 0x9FA5, 0xAC00, 0xD7A3,
|
|
]
|
|
|
|
/// Inclusive `[lo, hi]` bounds of the XSD `\c` set: XML 1.0 Appendix B
|
|
/// `NameChar` (`Letter | Digit | '.' | '-' | '_' | ':' | CombiningChar | Extender`).
|
|
static let nameCharRanges: [UInt32] = [
|
|
0x2D, 0x2E, 0x30, 0x3A, 0x41, 0x5A, 0x5F, 0x5F, 0x61, 0x7A, 0xB7, 0xB7,
|
|
0xC0, 0xD6, 0xD8, 0xF6, 0xF8, 0x131, 0x134, 0x13E, 0x141, 0x148, 0x14A, 0x17E,
|
|
0x180, 0x1C3, 0x1CD, 0x1F0, 0x1F4, 0x1F5, 0x1FA, 0x217, 0x250, 0x2A8, 0x2BB, 0x2C1,
|
|
0x2D0, 0x2D1, 0x300, 0x345, 0x360, 0x361, 0x386, 0x38A, 0x38C, 0x38C, 0x38E, 0x3A1,
|
|
0x3A3, 0x3CE, 0x3D0, 0x3D6, 0x3DA, 0x3DA, 0x3DC, 0x3DC, 0x3DE, 0x3DE, 0x3E0, 0x3E0,
|
|
0x3E2, 0x3F3, 0x401, 0x40C, 0x40E, 0x44F, 0x451, 0x45C, 0x45E, 0x481, 0x483, 0x486,
|
|
0x490, 0x4C4, 0x4C7, 0x4C8, 0x4CB, 0x4CC, 0x4D0, 0x4EB, 0x4EE, 0x4F5, 0x4F8, 0x4F9,
|
|
0x531, 0x556, 0x559, 0x559, 0x561, 0x586, 0x591, 0x5A1, 0x5A3, 0x5B9, 0x5BB, 0x5BD,
|
|
0x5BF, 0x5BF, 0x5C1, 0x5C2, 0x5C4, 0x5C4, 0x5D0, 0x5EA, 0x5F0, 0x5F2, 0x621, 0x63A,
|
|
0x640, 0x652, 0x660, 0x669, 0x670, 0x6B7, 0x6BA, 0x6BE, 0x6C0, 0x6CE, 0x6D0, 0x6D3,
|
|
0x6D5, 0x6E8, 0x6EA, 0x6ED, 0x6F0, 0x6F9, 0x901, 0x903, 0x905, 0x939, 0x93C, 0x94D,
|
|
0x951, 0x954, 0x958, 0x963, 0x966, 0x96F, 0x981, 0x983, 0x985, 0x98C, 0x98F, 0x990,
|
|
0x993, 0x9A8, 0x9AA, 0x9B0, 0x9B2, 0x9B2, 0x9B6, 0x9B9, 0x9BC, 0x9BC, 0x9BE, 0x9C4,
|
|
0x9C7, 0x9C8, 0x9CB, 0x9CD, 0x9D7, 0x9D7, 0x9DC, 0x9DD, 0x9DF, 0x9E3, 0x9E6, 0x9F1,
|
|
0xA02, 0xA02, 0xA05, 0xA0A, 0xA0F, 0xA10, 0xA13, 0xA28, 0xA2A, 0xA30, 0xA32, 0xA33,
|
|
0xA35, 0xA36, 0xA38, 0xA39, 0xA3C, 0xA3C, 0xA3E, 0xA42, 0xA47, 0xA48, 0xA4B, 0xA4D,
|
|
0xA59, 0xA5C, 0xA5E, 0xA5E, 0xA66, 0xA74, 0xA81, 0xA83, 0xA85, 0xA8B, 0xA8D, 0xA8D,
|
|
0xA8F, 0xA91, 0xA93, 0xAA8, 0xAAA, 0xAB0, 0xAB2, 0xAB3, 0xAB5, 0xAB9, 0xABC, 0xAC5,
|
|
0xAC7, 0xAC9, 0xACB, 0xACD, 0xAE0, 0xAE0, 0xAE6, 0xAEF, 0xB01, 0xB03, 0xB05, 0xB0C,
|
|
0xB0F, 0xB10, 0xB13, 0xB28, 0xB2A, 0xB30, 0xB32, 0xB33, 0xB36, 0xB39, 0xB3C, 0xB43,
|
|
0xB47, 0xB48, 0xB4B, 0xB4D, 0xB56, 0xB57, 0xB5C, 0xB5D, 0xB5F, 0xB61, 0xB66, 0xB6F,
|
|
0xB82, 0xB83, 0xB85, 0xB8A, 0xB8E, 0xB90, 0xB92, 0xB95, 0xB99, 0xB9A, 0xB9C, 0xB9C,
|
|
0xB9E, 0xB9F, 0xBA3, 0xBA4, 0xBA8, 0xBAA, 0xBAE, 0xBB5, 0xBB7, 0xBB9, 0xBBE, 0xBC2,
|
|
0xBC6, 0xBC8, 0xBCA, 0xBCD, 0xBD7, 0xBD7, 0xBE7, 0xBEF, 0xC01, 0xC03, 0xC05, 0xC0C,
|
|
0xC0E, 0xC10, 0xC12, 0xC28, 0xC2A, 0xC33, 0xC35, 0xC39, 0xC3E, 0xC44, 0xC46, 0xC48,
|
|
0xC4A, 0xC4D, 0xC55, 0xC56, 0xC60, 0xC61, 0xC66, 0xC6F, 0xC82, 0xC83, 0xC85, 0xC8C,
|
|
0xC8E, 0xC90, 0xC92, 0xCA8, 0xCAA, 0xCB3, 0xCB5, 0xCB9, 0xCBE, 0xCC4, 0xCC6, 0xCC8,
|
|
0xCCA, 0xCCD, 0xCD5, 0xCD6, 0xCDE, 0xCDE, 0xCE0, 0xCE1, 0xCE6, 0xCEF, 0xD02, 0xD03,
|
|
0xD05, 0xD0C, 0xD0E, 0xD10, 0xD12, 0xD28, 0xD2A, 0xD39, 0xD3E, 0xD43, 0xD46, 0xD48,
|
|
0xD4A, 0xD4D, 0xD57, 0xD57, 0xD60, 0xD61, 0xD66, 0xD6F, 0xE01, 0xE2E, 0xE30, 0xE3A,
|
|
0xE40, 0xE4E, 0xE50, 0xE59, 0xE81, 0xE82, 0xE84, 0xE84, 0xE87, 0xE88, 0xE8A, 0xE8A,
|
|
0xE8D, 0xE8D, 0xE94, 0xE97, 0xE99, 0xE9F, 0xEA1, 0xEA3, 0xEA5, 0xEA5, 0xEA7, 0xEA7,
|
|
0xEAA, 0xEAB, 0xEAD, 0xEAE, 0xEB0, 0xEB9, 0xEBB, 0xEBD, 0xEC0, 0xEC4, 0xEC6, 0xEC6,
|
|
0xEC8, 0xECD, 0xED0, 0xED9, 0xF18, 0xF19, 0xF20, 0xF29, 0xF35, 0xF35, 0xF37, 0xF37,
|
|
0xF39, 0xF39, 0xF3E, 0xF47, 0xF49, 0xF69, 0xF71, 0xF84, 0xF86, 0xF8B, 0xF90, 0xF95,
|
|
0xF97, 0xF97, 0xF99, 0xFAD, 0xFB1, 0xFB7, 0xFB9, 0xFB9, 0x10A0, 0x10C5, 0x10D0, 0x10F6,
|
|
0x1100, 0x1100, 0x1102, 0x1103, 0x1105, 0x1107, 0x1109, 0x1109, 0x110B, 0x110C, 0x110E, 0x1112,
|
|
0x113C, 0x113C, 0x113E, 0x113E, 0x1140, 0x1140, 0x114C, 0x114C, 0x114E, 0x114E, 0x1150, 0x1150,
|
|
0x1154, 0x1155, 0x1159, 0x1159, 0x115F, 0x1161, 0x1163, 0x1163, 0x1165, 0x1165, 0x1167, 0x1167,
|
|
0x1169, 0x1169, 0x116D, 0x116E, 0x1172, 0x1173, 0x1175, 0x1175, 0x119E, 0x119E, 0x11A8, 0x11A8,
|
|
0x11AB, 0x11AB, 0x11AE, 0x11AF, 0x11B7, 0x11B8, 0x11BA, 0x11BA, 0x11BC, 0x11C2, 0x11EB, 0x11EB,
|
|
0x11F0, 0x11F0, 0x11F9, 0x11F9, 0x1E00, 0x1E9B, 0x1EA0, 0x1EF9, 0x1F00, 0x1F15, 0x1F18, 0x1F1D,
|
|
0x1F20, 0x1F45, 0x1F48, 0x1F4D, 0x1F50, 0x1F57, 0x1F59, 0x1F59, 0x1F5B, 0x1F5B, 0x1F5D, 0x1F5D,
|
|
0x1F5F, 0x1F7D, 0x1F80, 0x1FB4, 0x1FB6, 0x1FBC, 0x1FBE, 0x1FBE, 0x1FC2, 0x1FC4, 0x1FC6, 0x1FCC,
|
|
0x1FD0, 0x1FD3, 0x1FD6, 0x1FDB, 0x1FE0, 0x1FEC, 0x1FF2, 0x1FF4, 0x1FF6, 0x1FFC, 0x20D0, 0x20DC,
|
|
0x20E1, 0x20E1, 0x2126, 0x2126, 0x212A, 0x212B, 0x212E, 0x212E, 0x2180, 0x2182, 0x3005, 0x3005,
|
|
0x3007, 0x3007, 0x3021, 0x302F, 0x3031, 0x3035, 0x3041, 0x3094, 0x3099, 0x309A, 0x309D, 0x309E,
|
|
0x30A1, 0x30FA, 0x30FC, 0x30FE, 0x3105, 0x312C, 0x4E00, 0x9FA5, 0xAC00, 0xD7A3,
|
|
]
|
|
}
|