@longsightgroup/qti3-core 0.10.5 → 0.11.0

package/src/xml-schema-regex-data.ts

@@ -0,0 +1,404 @@
+/** Unicode 17.0.0 blocks, generated from https://www.unicode.org/Public/17.0.0/ucd/Blocks.txt.
+ * Block names retain XML Schema case and hyphens; only spaces are removed.
+ * The data is distributed under the following license.
+ *
+ * UNICODE LICENSE V3
+ *
+ * COPYRIGHT AND PERMISSION NOTICE
+ *
+ * Copyright © 1991-2026 Unicode, Inc.
+ *
+ * NOTICE TO USER: Carefully read the following legal agreement. BY
+ * DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING DATA FILES, AND/OR
+ * SOFTWARE, YOU UNEQUIVOCALLY ACCEPT, AND AGREE TO BE BOUND BY, ALL OF THE
+ * TERMS AND CONDITIONS OF THIS AGREEMENT. IF YOU DO NOT AGREE, DO NOT
+ * DOWNLOAD, INSTALL, COPY, DISTRIBUTE OR USE THE DATA FILES OR SOFTWARE.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of data files and any associated documentation (the "Data Files") or
+ * software and any associated documentation (the "Software") to deal in the
+ * Data Files or Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, and/or sell
+ * copies of the Data Files or Software, and to permit persons to whom the
+ * Data Files or Software are furnished to do so, provided that either (a)
+ * this copyright and permission notice appear with all copies of the Data
+ * Files or Software, or (b) this copyright and permission notice appear in
+ * associated Documentation.
+ *
+ * THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
+ * KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF
+ * THIRD PARTY RIGHTS.
+ *
+ * IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE
+ * BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES,
+ * OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
+ * WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
+ * ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THE DATA
+ * FILES OR SOFTWARE.
+ *
+ * Except as contained in this notice, the name of a copyright holder shall
+ * not be used in advertising or otherwise to promote the sale, use or other
+ * dealings in these Data Files or Software without prior written
+ * authorization of the copyright holder.
+ */
+export const xmlSchemaBlocks: Readonly<Record<string, string>> = {
+  BasicLatin: "\\u{0000}-\\u{007F}",
+  "Latin-1Supplement": "\\u{0080}-\\u{00FF}",
+  "LatinExtended-A": "\\u{0100}-\\u{017F}",
+  "LatinExtended-B": "\\u{0180}-\\u{024F}",
+  IPAExtensions: "\\u{0250}-\\u{02AF}",
+  SpacingModifierLetters: "\\u{02B0}-\\u{02FF}",
+  CombiningDiacriticalMarks: "\\u{0300}-\\u{036F}",
+  GreekandCoptic: "\\u{0370}-\\u{03FF}",
+  Cyrillic: "\\u{0400}-\\u{04FF}",
+  CyrillicSupplement: "\\u{0500}-\\u{052F}",
+  Armenian: "\\u{0530}-\\u{058F}",
+  Hebrew: "\\u{0590}-\\u{05FF}",
+  Arabic: "\\u{0600}-\\u{06FF}",
+  Syriac: "\\u{0700}-\\u{074F}",
+  ArabicSupplement: "\\u{0750}-\\u{077F}",
+  Thaana: "\\u{0780}-\\u{07BF}",
+  NKo: "\\u{07C0}-\\u{07FF}",
+  Samaritan: "\\u{0800}-\\u{083F}",
+  Mandaic: "\\u{0840}-\\u{085F}",
+  SyriacSupplement: "\\u{0860}-\\u{086F}",
+  "ArabicExtended-B": "\\u{0870}-\\u{089F}",
+  "ArabicExtended-A": "\\u{08A0}-\\u{08FF}",
+  Devanagari: "\\u{0900}-\\u{097F}",
+  Bengali: "\\u{0980}-\\u{09FF}",
+  Gurmukhi: "\\u{0A00}-\\u{0A7F}",
+  Gujarati: "\\u{0A80}-\\u{0AFF}",
+  Oriya: "\\u{0B00}-\\u{0B7F}",
+  Tamil: "\\u{0B80}-\\u{0BFF}",
+  Telugu: "\\u{0C00}-\\u{0C7F}",
+  Kannada: "\\u{0C80}-\\u{0CFF}",
+  Malayalam: "\\u{0D00}-\\u{0D7F}",
+  Sinhala: "\\u{0D80}-\\u{0DFF}",
+  Thai: "\\u{0E00}-\\u{0E7F}",
+  Lao: "\\u{0E80}-\\u{0EFF}",
+  Tibetan: "\\u{0F00}-\\u{0FFF}",
+  Myanmar: "\\u{1000}-\\u{109F}",
+  Georgian: "\\u{10A0}-\\u{10FF}",
+  HangulJamo: "\\u{1100}-\\u{11FF}",
+  Ethiopic: "\\u{1200}-\\u{137F}",
+  EthiopicSupplement: "\\u{1380}-\\u{139F}",
+  Cherokee: "\\u{13A0}-\\u{13FF}",
+  UnifiedCanadianAboriginalSyllabics: "\\u{1400}-\\u{167F}",
+  Ogham: "\\u{1680}-\\u{169F}",
+  Runic: "\\u{16A0}-\\u{16FF}",
+  Tagalog: "\\u{1700}-\\u{171F}",
+  Hanunoo: "\\u{1720}-\\u{173F}",
+  Buhid: "\\u{1740}-\\u{175F}",
+  Tagbanwa: "\\u{1760}-\\u{177F}",
+  Khmer: "\\u{1780}-\\u{17FF}",
+  Mongolian: "\\u{1800}-\\u{18AF}",
+  UnifiedCanadianAboriginalSyllabicsExtended: "\\u{18B0}-\\u{18FF}",
+  Limbu: "\\u{1900}-\\u{194F}",
+  TaiLe: "\\u{1950}-\\u{197F}",
+  NewTaiLue: "\\u{1980}-\\u{19DF}",
+  KhmerSymbols: "\\u{19E0}-\\u{19FF}",
+  Buginese: "\\u{1A00}-\\u{1A1F}",
+  TaiTham: "\\u{1A20}-\\u{1AAF}",
+  CombiningDiacriticalMarksExtended: "\\u{1AB0}-\\u{1AFF}",
+  Balinese: "\\u{1B00}-\\u{1B7F}",
+  Sundanese: "\\u{1B80}-\\u{1BBF}",
+  Batak: "\\u{1BC0}-\\u{1BFF}",
+  Lepcha: "\\u{1C00}-\\u{1C4F}",
+  OlChiki: "\\u{1C50}-\\u{1C7F}",
+  "CyrillicExtended-C": "\\u{1C80}-\\u{1C8F}",
+  GeorgianExtended: "\\u{1C90}-\\u{1CBF}",
+  SundaneseSupplement: "\\u{1CC0}-\\u{1CCF}",
+  VedicExtensions: "\\u{1CD0}-\\u{1CFF}",
+  PhoneticExtensions: "\\u{1D00}-\\u{1D7F}",
+  PhoneticExtensionsSupplement: "\\u{1D80}-\\u{1DBF}",
+  CombiningDiacriticalMarksSupplement: "\\u{1DC0}-\\u{1DFF}",
+  LatinExtendedAdditional: "\\u{1E00}-\\u{1EFF}",
+  GreekExtended: "\\u{1F00}-\\u{1FFF}",
+  GeneralPunctuation: "\\u{2000}-\\u{206F}",
+  SuperscriptsandSubscripts: "\\u{2070}-\\u{209F}",
+  CurrencySymbols: "\\u{20A0}-\\u{20CF}",
+  CombiningDiacriticalMarksforSymbols: "\\u{20D0}-\\u{20FF}",
+  LetterlikeSymbols: "\\u{2100}-\\u{214F}",
+  NumberForms: "\\u{2150}-\\u{218F}",
+  Arrows: "\\u{2190}-\\u{21FF}",
+  MathematicalOperators: "\\u{2200}-\\u{22FF}",
+  MiscellaneousTechnical: "\\u{2300}-\\u{23FF}",
+  ControlPictures: "\\u{2400}-\\u{243F}",
+  OpticalCharacterRecognition: "\\u{2440}-\\u{245F}",
+  EnclosedAlphanumerics: "\\u{2460}-\\u{24FF}",
+  BoxDrawing: "\\u{2500}-\\u{257F}",
+  BlockElements: "\\u{2580}-\\u{259F}",
+  GeometricShapes: "\\u{25A0}-\\u{25FF}",
+  MiscellaneousSymbols: "\\u{2600}-\\u{26FF}",
+  Dingbats: "\\u{2700}-\\u{27BF}",
+  "MiscellaneousMathematicalSymbols-A": "\\u{27C0}-\\u{27EF}",
+  "SupplementalArrows-A": "\\u{27F0}-\\u{27FF}",
+  BraillePatterns: "\\u{2800}-\\u{28FF}",
+  "SupplementalArrows-B": "\\u{2900}-\\u{297F}",
+  "MiscellaneousMathematicalSymbols-B": "\\u{2980}-\\u{29FF}",
+  SupplementalMathematicalOperators: "\\u{2A00}-\\u{2AFF}",
+  MiscellaneousSymbolsandArrows: "\\u{2B00}-\\u{2BFF}",
+  Glagolitic: "\\u{2C00}-\\u{2C5F}",
+  "LatinExtended-C": "\\u{2C60}-\\u{2C7F}",
+  Coptic: "\\u{2C80}-\\u{2CFF}",
+  GeorgianSupplement: "\\u{2D00}-\\u{2D2F}",
+  Tifinagh: "\\u{2D30}-\\u{2D7F}",
+  EthiopicExtended: "\\u{2D80}-\\u{2DDF}",
+  "CyrillicExtended-A": "\\u{2DE0}-\\u{2DFF}",
+  SupplementalPunctuation: "\\u{2E00}-\\u{2E7F}",
+  CJKRadicalsSupplement: "\\u{2E80}-\\u{2EFF}",
+  KangxiRadicals: "\\u{2F00}-\\u{2FDF}",
+  IdeographicDescriptionCharacters: "\\u{2FF0}-\\u{2FFF}",
+  CJKSymbolsandPunctuation: "\\u{3000}-\\u{303F}",
+  Hiragana: "\\u{3040}-\\u{309F}",
+  Katakana: "\\u{30A0}-\\u{30FF}",
+  Bopomofo: "\\u{3100}-\\u{312F}",
+  HangulCompatibilityJamo: "\\u{3130}-\\u{318F}",
+  Kanbun: "\\u{3190}-\\u{319F}",
+  BopomofoExtended: "\\u{31A0}-\\u{31BF}",
+  CJKStrokes: "\\u{31C0}-\\u{31EF}",
+  KatakanaPhoneticExtensions: "\\u{31F0}-\\u{31FF}",
+  EnclosedCJKLettersandMonths: "\\u{3200}-\\u{32FF}",
+  CJKCompatibility: "\\u{3300}-\\u{33FF}",
+  CJKUnifiedIdeographsExtensionA: "\\u{3400}-\\u{4DBF}",
+  YijingHexagramSymbols: "\\u{4DC0}-\\u{4DFF}",
+  CJKUnifiedIdeographs: "\\u{4E00}-\\u{9FFF}",
+  YiSyllables: "\\u{A000}-\\u{A48F}",
+  YiRadicals: "\\u{A490}-\\u{A4CF}",
+  Lisu: "\\u{A4D0}-\\u{A4FF}",
+  Vai: "\\u{A500}-\\u{A63F}",
+  "CyrillicExtended-B": "\\u{A640}-\\u{A69F}",
+  Bamum: "\\u{A6A0}-\\u{A6FF}",
+  ModifierToneLetters: "\\u{A700}-\\u{A71F}",
+  "LatinExtended-D": "\\u{A720}-\\u{A7FF}",
+  SylotiNagri: "\\u{A800}-\\u{A82F}",
+  CommonIndicNumberForms: "\\u{A830}-\\u{A83F}",
+  "Phags-pa": "\\u{A840}-\\u{A87F}",
+  Saurashtra: "\\u{A880}-\\u{A8DF}",
+  DevanagariExtended: "\\u{A8E0}-\\u{A8FF}",
+  KayahLi: "\\u{A900}-\\u{A92F}",
+  Rejang: "\\u{A930}-\\u{A95F}",
+  "HangulJamoExtended-A": "\\u{A960}-\\u{A97F}",
+  Javanese: "\\u{A980}-\\u{A9DF}",
+  "MyanmarExtended-B": "\\u{A9E0}-\\u{A9FF}",
+  Cham: "\\u{AA00}-\\u{AA5F}",
+  "MyanmarExtended-A": "\\u{AA60}-\\u{AA7F}",
+  TaiViet: "\\u{AA80}-\\u{AADF}",
+  MeeteiMayekExtensions: "\\u{AAE0}-\\u{AAFF}",
+  "EthiopicExtended-A": "\\u{AB00}-\\u{AB2F}",
+  "LatinExtended-E": "\\u{AB30}-\\u{AB6F}",
+  CherokeeSupplement: "\\u{AB70}-\\u{ABBF}",
+  MeeteiMayek: "\\u{ABC0}-\\u{ABFF}",
+  HangulSyllables: "\\u{AC00}-\\u{D7AF}",
+  "HangulJamoExtended-B": "\\u{D7B0}-\\u{D7FF}",
+  PrivateUseArea: "\\u{E000}-\\u{F8FF}",
+  CJKCompatibilityIdeographs: "\\u{F900}-\\u{FAFF}",
+  AlphabeticPresentationForms: "\\u{FB00}-\\u{FB4F}",
+  "ArabicPresentationForms-A": "\\u{FB50}-\\u{FDFF}",
+  VariationSelectors: "\\u{FE00}-\\u{FE0F}",
+  VerticalForms: "\\u{FE10}-\\u{FE1F}",
+  CombiningHalfMarks: "\\u{FE20}-\\u{FE2F}",
+  CJKCompatibilityForms: "\\u{FE30}-\\u{FE4F}",
+  SmallFormVariants: "\\u{FE50}-\\u{FE6F}",
+  "ArabicPresentationForms-B": "\\u{FE70}-\\u{FEFF}",
+  HalfwidthandFullwidthForms: "\\u{FF00}-\\u{FFEF}",
+  Specials: "\\u{FFF0}-\\u{FFFF}",
+  LinearBSyllabary: "\\u{10000}-\\u{1007F}",
+  LinearBIdeograms: "\\u{10080}-\\u{100FF}",
+  AegeanNumbers: "\\u{10100}-\\u{1013F}",
+  AncientGreekNumbers: "\\u{10140}-\\u{1018F}",
+  AncientSymbols: "\\u{10190}-\\u{101CF}",
+  PhaistosDisc: "\\u{101D0}-\\u{101FF}",
+  Lycian: "\\u{10280}-\\u{1029F}",
+  Carian: "\\u{102A0}-\\u{102DF}",
+  CopticEpactNumbers: "\\u{102E0}-\\u{102FF}",
+  OldItalic: "\\u{10300}-\\u{1032F}",
+  Gothic: "\\u{10330}-\\u{1034F}",
+  OldPermic: "\\u{10350}-\\u{1037F}",
+  Ugaritic: "\\u{10380}-\\u{1039F}",
+  OldPersian: "\\u{103A0}-\\u{103DF}",
+  Deseret: "\\u{10400}-\\u{1044F}",
+  Shavian: "\\u{10450}-\\u{1047F}",
+  Osmanya: "\\u{10480}-\\u{104AF}",
+  Osage: "\\u{104B0}-\\u{104FF}",
+  Elbasan: "\\u{10500}-\\u{1052F}",
+  CaucasianAlbanian: "\\u{10530}-\\u{1056F}",
+  Vithkuqi: "\\u{10570}-\\u{105BF}",
+  Todhri: "\\u{105C0}-\\u{105FF}",
+  LinearA: "\\u{10600}-\\u{1077F}",
+  "LatinExtended-F": "\\u{10780}-\\u{107BF}",
+  CypriotSyllabary: "\\u{10800}-\\u{1083F}",
+  ImperialAramaic: "\\u{10840}-\\u{1085F}",
+  Palmyrene: "\\u{10860}-\\u{1087F}",
+  Nabataean: "\\u{10880}-\\u{108AF}",
+  Hatran: "\\u{108E0}-\\u{108FF}",
+  Phoenician: "\\u{10900}-\\u{1091F}",
+  Lydian: "\\u{10920}-\\u{1093F}",
+  Sidetic: "\\u{10940}-\\u{1095F}",
+  MeroiticHieroglyphs: "\\u{10980}-\\u{1099F}",
+  MeroiticCursive: "\\u{109A0}-\\u{109FF}",
+  Kharoshthi: "\\u{10A00}-\\u{10A5F}",
+  OldSouthArabian: "\\u{10A60}-\\u{10A7F}",
+  OldNorthArabian: "\\u{10A80}-\\u{10A9F}",
+  Manichaean: "\\u{10AC0}-\\u{10AFF}",
+  Avestan: "\\u{10B00}-\\u{10B3F}",
+  InscriptionalParthian: "\\u{10B40}-\\u{10B5F}",
+  InscriptionalPahlavi: "\\u{10B60}-\\u{10B7F}",
+  PsalterPahlavi: "\\u{10B80}-\\u{10BAF}",
+  OldTurkic: "\\u{10C00}-\\u{10C4F}",
+  OldHungarian: "\\u{10C80}-\\u{10CFF}",
+  HanifiRohingya: "\\u{10D00}-\\u{10D3F}",
+  Garay: "\\u{10D40}-\\u{10D8F}",
+  RumiNumeralSymbols: "\\u{10E60}-\\u{10E7F}",
+  Yezidi: "\\u{10E80}-\\u{10EBF}",
+  "ArabicExtended-C": "\\u{10EC0}-\\u{10EFF}",
+  OldSogdian: "\\u{10F00}-\\u{10F2F}",
+  Sogdian: "\\u{10F30}-\\u{10F6F}",
+  OldUyghur: "\\u{10F70}-\\u{10FAF}",
+  Chorasmian: "\\u{10FB0}-\\u{10FDF}",
+  Elymaic: "\\u{10FE0}-\\u{10FFF}",
+  Brahmi: "\\u{11000}-\\u{1107F}",
+  Kaithi: "\\u{11080}-\\u{110CF}",
+  SoraSompeng: "\\u{110D0}-\\u{110FF}",
+  Chakma: "\\u{11100}-\\u{1114F}",
+  Mahajani: "\\u{11150}-\\u{1117F}",
+  Sharada: "\\u{11180}-\\u{111DF}",
+  SinhalaArchaicNumbers: "\\u{111E0}-\\u{111FF}",
+  Khojki: "\\u{11200}-\\u{1124F}",
+  Multani: "\\u{11280}-\\u{112AF}",
+  Khudawadi: "\\u{112B0}-\\u{112FF}",
+  Grantha: "\\u{11300}-\\u{1137F}",
+  "Tulu-Tigalari": "\\u{11380}-\\u{113FF}",
+  Newa: "\\u{11400}-\\u{1147F}",
+  Tirhuta: "\\u{11480}-\\u{114DF}",
+  Siddham: "\\u{11580}-\\u{115FF}",
+  Modi: "\\u{11600}-\\u{1165F}",
+  MongolianSupplement: "\\u{11660}-\\u{1167F}",
+  Takri: "\\u{11680}-\\u{116CF}",
+  "MyanmarExtended-C": "\\u{116D0}-\\u{116FF}",
+  Ahom: "\\u{11700}-\\u{1174F}",
+  Dogra: "\\u{11800}-\\u{1184F}",
+  WarangCiti: "\\u{118A0}-\\u{118FF}",
+  DivesAkuru: "\\u{11900}-\\u{1195F}",
+  Nandinagari: "\\u{119A0}-\\u{119FF}",
+  ZanabazarSquare: "\\u{11A00}-\\u{11A4F}",
+  Soyombo: "\\u{11A50}-\\u{11AAF}",
+  "UnifiedCanadianAboriginalSyllabicsExtended-A": "\\u{11AB0}-\\u{11ABF}",
+  PauCinHau: "\\u{11AC0}-\\u{11AFF}",
+  "DevanagariExtended-A": "\\u{11B00}-\\u{11B5F}",
+  SharadaSupplement: "\\u{11B60}-\\u{11B7F}",
+  Sunuwar: "\\u{11BC0}-\\u{11BFF}",
+  Bhaiksuki: "\\u{11C00}-\\u{11C6F}",
+  Marchen: "\\u{11C70}-\\u{11CBF}",
+  MasaramGondi: "\\u{11D00}-\\u{11D5F}",
+  GunjalaGondi: "\\u{11D60}-\\u{11DAF}",
+  TolongSiki: "\\u{11DB0}-\\u{11DEF}",
+  Makasar: "\\u{11EE0}-\\u{11EFF}",
+  Kawi: "\\u{11F00}-\\u{11F5F}",
+  LisuSupplement: "\\u{11FB0}-\\u{11FBF}",
+  TamilSupplement: "\\u{11FC0}-\\u{11FFF}",
+  Cuneiform: "\\u{12000}-\\u{123FF}",
+  CuneiformNumbersandPunctuation: "\\u{12400}-\\u{1247F}",
+  EarlyDynasticCuneiform: "\\u{12480}-\\u{1254F}",
+  "Cypro-Minoan": "\\u{12F90}-\\u{12FFF}",
+  EgyptianHieroglyphs: "\\u{13000}-\\u{1342F}",
+  EgyptianHieroglyphFormatControls: "\\u{13430}-\\u{1345F}",
+  "EgyptianHieroglyphsExtended-A": "\\u{13460}-\\u{143FF}",
+  AnatolianHieroglyphs: "\\u{14400}-\\u{1467F}",
+  GurungKhema: "\\u{16100}-\\u{1613F}",
+  BamumSupplement: "\\u{16800}-\\u{16A3F}",
+  Mro: "\\u{16A40}-\\u{16A6F}",
+  Tangsa: "\\u{16A70}-\\u{16ACF}",
+  BassaVah: "\\u{16AD0}-\\u{16AFF}",
+  PahawhHmong: "\\u{16B00}-\\u{16B8F}",
+  KiratRai: "\\u{16D40}-\\u{16D7F}",
+  Medefaidrin: "\\u{16E40}-\\u{16E9F}",
+  BeriaErfe: "\\u{16EA0}-\\u{16EDF}",
+  Miao: "\\u{16F00}-\\u{16F9F}",
+  IdeographicSymbolsandPunctuation: "\\u{16FE0}-\\u{16FFF}",
+  Tangut: "\\u{17000}-\\u{187FF}",
+  TangutComponents: "\\u{18800}-\\u{18AFF}",
+  KhitanSmallScript: "\\u{18B00}-\\u{18CFF}",
+  TangutSupplement: "\\u{18D00}-\\u{18D7F}",
+  TangutComponentsSupplement: "\\u{18D80}-\\u{18DFF}",
+  "KanaExtended-B": "\\u{1AFF0}-\\u{1AFFF}",
+  KanaSupplement: "\\u{1B000}-\\u{1B0FF}",
+  "KanaExtended-A": "\\u{1B100}-\\u{1B12F}",
+  SmallKanaExtension: "\\u{1B130}-\\u{1B16F}",
+  Nushu: "\\u{1B170}-\\u{1B2FF}",
+  Duployan: "\\u{1BC00}-\\u{1BC9F}",
+  ShorthandFormatControls: "\\u{1BCA0}-\\u{1BCAF}",
+  SymbolsforLegacyComputingSupplement: "\\u{1CC00}-\\u{1CEBF}",
+  MiscellaneousSymbolsSupplement: "\\u{1CEC0}-\\u{1CEFF}",
+  ZnamennyMusicalNotation: "\\u{1CF00}-\\u{1CFCF}",
+  ByzantineMusicalSymbols: "\\u{1D000}-\\u{1D0FF}",
+  MusicalSymbols: "\\u{1D100}-\\u{1D1FF}",
+  AncientGreekMusicalNotation: "\\u{1D200}-\\u{1D24F}",
+  KaktovikNumerals: "\\u{1D2C0}-\\u{1D2DF}",
+  MayanNumerals: "\\u{1D2E0}-\\u{1D2FF}",
+  TaiXuanJingSymbols: "\\u{1D300}-\\u{1D35F}",
+  CountingRodNumerals: "\\u{1D360}-\\u{1D37F}",
+  MathematicalAlphanumericSymbols: "\\u{1D400}-\\u{1D7FF}",
+  SuttonSignWriting: "\\u{1D800}-\\u{1DAAF}",
+  "LatinExtended-G": "\\u{1DF00}-\\u{1DFFF}",
+  GlagoliticSupplement: "\\u{1E000}-\\u{1E02F}",
+  "CyrillicExtended-D": "\\u{1E030}-\\u{1E08F}",
+  NyiakengPuachueHmong: "\\u{1E100}-\\u{1E14F}",
+  Toto: "\\u{1E290}-\\u{1E2BF}",
+  Wancho: "\\u{1E2C0}-\\u{1E2FF}",
+  NagMundari: "\\u{1E4D0}-\\u{1E4FF}",
+  OlOnal: "\\u{1E5D0}-\\u{1E5FF}",
+  TaiYo: "\\u{1E6C0}-\\u{1E6FF}",
+  "EthiopicExtended-B": "\\u{1E7E0}-\\u{1E7FF}",
+  MendeKikakui: "\\u{1E800}-\\u{1E8DF}",
+  Adlam: "\\u{1E900}-\\u{1E95F}",
+  IndicSiyaqNumbers: "\\u{1EC70}-\\u{1ECBF}",
+  OttomanSiyaqNumbers: "\\u{1ED00}-\\u{1ED4F}",
+  ArabicMathematicalAlphabeticSymbols: "\\u{1EE00}-\\u{1EEFF}",
+  MahjongTiles: "\\u{1F000}-\\u{1F02F}",
+  DominoTiles: "\\u{1F030}-\\u{1F09F}",
+  PlayingCards: "\\u{1F0A0}-\\u{1F0FF}",
+  EnclosedAlphanumericSupplement: "\\u{1F100}-\\u{1F1FF}",
+  EnclosedIdeographicSupplement: "\\u{1F200}-\\u{1F2FF}",
+  MiscellaneousSymbolsandPictographs: "\\u{1F300}-\\u{1F5FF}",
+  Emoticons: "\\u{1F600}-\\u{1F64F}",
+  OrnamentalDingbats: "\\u{1F650}-\\u{1F67F}",
+  TransportandMapSymbols: "\\u{1F680}-\\u{1F6FF}",
+  AlchemicalSymbols: "\\u{1F700}-\\u{1F77F}",
+  GeometricShapesExtended: "\\u{1F780}-\\u{1F7FF}",
+  "SupplementalArrows-C": "\\u{1F800}-\\u{1F8FF}",
+  SupplementalSymbolsandPictographs: "\\u{1F900}-\\u{1F9FF}",
+  ChessSymbols: "\\u{1FA00}-\\u{1FA6F}",
+  "SymbolsandPictographsExtended-A": "\\u{1FA70}-\\u{1FAFF}",
+  SymbolsforLegacyComputing: "\\u{1FB00}-\\u{1FBFF}",
+  CJKUnifiedIdeographsExtensionB: "\\u{20000}-\\u{2A6DF}",
+  CJKUnifiedIdeographsExtensionC: "\\u{2A700}-\\u{2B73F}",
+  CJKUnifiedIdeographsExtensionD: "\\u{2B740}-\\u{2B81F}",
+  CJKUnifiedIdeographsExtensionE: "\\u{2B820}-\\u{2CEAF}",
+  CJKUnifiedIdeographsExtensionF: "\\u{2CEB0}-\\u{2EBEF}",
+  CJKUnifiedIdeographsExtensionI: "\\u{2EBF0}-\\u{2EE5F}",
+  CJKCompatibilityIdeographsSupplement: "\\u{2F800}-\\u{2FA1F}",
+  CJKUnifiedIdeographsExtensionG: "\\u{30000}-\\u{3134F}",
+  CJKUnifiedIdeographsExtensionH: "\\u{31350}-\\u{323AF}",
+  CJKUnifiedIdeographsExtensionJ: "\\u{323B0}-\\u{3347F}",
+  Tags: "\\u{E0000}-\\u{E007F}",
+  VariationSelectorsSupplement: "\\u{E0100}-\\u{E01EF}",
+  "SupplementaryPrivateUseArea-A": "\\u{F0000}-\\u{FFFFF}",
+  "SupplementaryPrivateUseArea-B": "\\u{100000}-\\u{10FFFF}",
+  Greek: "\\u{0370}-\\u{03FF}",
+  CombiningMarksforSymbols: "\\u{20D0}-\\u{20FF}",
+  PrivateUse: "\\u{E000}-\\u{F8FF}",
+};
+// XML 1.0 (Second Edition), productions 85–89:
+// https://www.w3.org/TR/2000/REC-xml-20001006#CharClasses
+export const xmlNameInitial =
+  "_:" +
+  "\\u{0041}-\\u{005A}\\u{0061}-\\u{007A}\\u{00C0}-\\u{00D6}\\u{00D8}-\\u{00F6}\\u{00F8}-\\u{00FF}\\u{0100}-\\u{0131}\\u{0134}-\\u{013E}\\u{0141}-\\u{0148}\\u{014A}-\\u{017E}\\u{0180}-\\u{01C3}\\u{01CD}-\\u{01F0}\\u{01F4}-\\u{01F5}\\u{01FA}-\\u{0217}\\u{0250}-\\u{02A8}\\u{02BB}-\\u{02C1}\\u{0386}\\u{0388}-\\u{038A}\\u{038C}\\u{038E}-\\u{03A1}\\u{03A3}-\\u{03CE}\\u{03D0}-\\u{03D6}\\u{03DA}\\u{03DC}\\u{03DE}\\u{03E0}\\u{03E2}-\\u{03F3}\\u{0401}-\\u{040C}\\u{040E}-\\u{044F}\\u{0451}-\\u{045C}\\u{045E}-\\u{0481}\\u{0490}-\\u{04C4}\\u{04C7}-\\u{04C8}\\u{04CB}-\\u{04CC}\\u{04D0}-\\u{04EB}\\u{04EE}-\\u{04F5}\\u{04F8}-\\u{04F9}\\u{0531}-\\u{0556}\\u{0559}\\u{0561}-\\u{0586}\\u{05D0}-\\u{05EA}\\u{05F0}-\\u{05F2}\\u{0621}-\\u{063A}\\u{0641}-\\u{064A}\\u{0671}-\\u{06B7}\\u{06BA}-\\u{06BE}\\u{06C0}-\\u{06CE}\\u{06D0}-\\u{06D3}\\u{06D5}\\u{06E5}-\\u{06E6}\\u{0905}-\\u{0939}\\u{093D}\\u{0958}-\\u{0961}\\u{0985}-\\u{098C}\\u{098F}-\\u{0990}\\u{0993}-\\u{09A8}\\u{09AA}-\\u{09B0}\\u{09B2}\\u{09B6}-\\u{09B9}\\u{09DC}-\\u{09DD}\\u{09DF}-\\u{09E1}\\u{09F0}-\\u{09F1}\\u{0A05}-\\u{0A0A}\\u{0A0F}-\\u{0A10}\\u{0A13}-\\u{0A28}\\u{0A2A}-\\u{0A30}\\u{0A32}-\\u{0A33}\\u{0A35}-\\u{0A36}\\u{0A38}-\\u{0A39}\\u{0A59}-\\u{0A5C}\\u{0A5E}\\u{0A72}-\\u{0A74}\\u{0A85}-\\u{0A8B}\\u{0A8D}\\u{0A8F}-\\u{0A91}\\u{0A93}-\\u{0AA8}\\u{0AAA}-\\u{0AB0}\\u{0AB2}-\\u{0AB3}\\u{0AB5}-\\u{0AB9}\\u{0ABD}\\u{0AE0}\\u{0B05}-\\u{0B0C}\\u{0B0F}-\\u{0B10}\\u{0B13}-\\u{0B28}\\u{0B2A}-\\u{0B30}\\u{0B32}-\\u{0B33}\\u{0B36}-\\u{0B39}\\u{0B3D}\\u{0B5C}-\\u{0B5D}\\u{0B5F}-\\u{0B61}\\u{0B85}-\\u{0B8A}\\u{0B8E}-\\u{0B90}\\u{0B92}-\\u{0B95}\\u{0B99}-\\u{0B9A}\\u{0B9C}\\u{0B9E}-\\u{0B9F}\\u{0BA3}-\\u{0BA4}\\u{0BA8}-\\u{0BAA}\\u{0BAE}-\\u{0BB5}\\u{0BB7}-\\u{0BB9}\\u{0C05}-\\u{0C0C}\\u{0C0E}-\\u{0C10}\\u{0C12}-\\u{0C28}\\u{0C2A}-\\u{0C33}\\u{0C35}-\\u{0C39}\\u{0C60}-\\u{0C61}\\u{0C85}-\\u{0C8C}\\u{0C8E}-\\u{0C90}\\u{0C92}-\\u{0CA8}\\u{0CAA}-\\u{0CB3}\\u{0CB5}-\\u{0CB9}\\u{0CDE}\\u{0CE0}-\\u{0CE1}\\u{0D05}-\\u{0D0C}\\u{0D0E}-\\u{0D10}\\u{0D12}-\\u{0D28}\\u{0D2A}-\\u{0D39}\\u{0D60}-\\u{0D61}\\u{0E01}-\\u{0E2E}\\u{0E30}\\u{0E32}-\\u{0E33}\\u{0E40}-\\u{0E45}\\u{0E81}-\\u{0E82}\\u{0E84}\\u{0E87}-\\u{0E88}\\u{0E8A}\\u{0E8D}\\u{0E94}-\\u{0E97}\\u{0E99}-\\u{0E9F}\\u{0EA1}-\\u{0EA3}\\u{0EA5}\\u{0EA7}\\u{0EAA}-\\u{0EAB}\\u{0EAD}-\\u{0EAE}\\u{0EB0}\\u{0EB2}-\\u{0EB3}\\u{0EBD}\\u{0EC0}-\\u{0EC4}\\u{0F40}-\\u{0F47}\\u{0F49}-\\u{0F69}\\u{10A0}-\\u{10C5}\\u{10D0}-\\u{10F6}\\u{1100}\\u{1102}-\\u{1103}\\u{1105}-\\u{1107}\\u{1109}\\u{110B}-\\u{110C}\\u{110E}-\\u{1112}\\u{113C}\\u{113E}\\u{1140}\\u{114C}\\u{114E}\\u{1150}\\u{1154}-\\u{1155}\\u{1159}\\u{115F}-\\u{1161}\\u{1163}\\u{1165}\\u{1167}\\u{1169}\\u{116D}-\\u{116E}\\u{1172}-\\u{1173}\\u{1175}\\u{119E}\\u{11A8}\\u{11AB}\\u{11AE}-\\u{11AF}\\u{11B7}-\\u{11B8}\\u{11BA}\\u{11BC}-\\u{11C2}\\u{11EB}\\u{11F0}\\u{11F9}\\u{1E00}-\\u{1E9B}\\u{1EA0}-\\u{1EF9}\\u{1F00}-\\u{1F15}\\u{1F18}-\\u{1F1D}\\u{1F20}-\\u{1F45}\\u{1F48}-\\u{1F4D}\\u{1F50}-\\u{1F57}\\u{1F59}\\u{1F5B}\\u{1F5D}\\u{1F5F}-\\u{1F7D}\\u{1F80}-\\u{1FB4}\\u{1FB6}-\\u{1FBC}\\u{1FBE}\\u{1FC2}-\\u{1FC4}\\u{1FC6}-\\u{1FCC}\\u{1FD0}-\\u{1FD3}\\u{1FD6}-\\u{1FDB}\\u{1FE0}-\\u{1FEC}\\u{1FF2}-\\u{1FF4}\\u{1FF6}-\\u{1FFC}\\u{2126}\\u{212A}-\\u{212B}\\u{212E}\\u{2180}-\\u{2182}\\u{3041}-\\u{3094}\\u{30A1}-\\u{30FA}\\u{3105}-\\u{312C}\\u{AC00}-\\u{D7A3}" +
+  "\\u{4E00}-\\u{9FA5}\\u{3007}\\u{3021}-\\u{3029}";
+export const xmlNameCharacters =
+  xmlNameInitial +
+  "\\u{2D}." +
+  "\\u{0030}-\\u{0039}\\u{0660}-\\u{0669}\\u{06F0}-\\u{06F9}\\u{0966}-\\u{096F}\\u{09E6}-\\u{09EF}\\u{0A66}-\\u{0A6F}\\u{0AE6}-\\u{0AEF}\\u{0B66}-\\u{0B6F}\\u{0BE7}-\\u{0BEF}\\u{0C66}-\\u{0C6F}\\u{0CE6}-\\u{0CEF}\\u{0D66}-\\u{0D6F}\\u{0E50}-\\u{0E59}\\u{0ED0}-\\u{0ED9}\\u{0F20}-\\u{0F29}" +
+  "\\u{0300}-\\u{0345}\\u{0360}-\\u{0361}\\u{0483}-\\u{0486}\\u{0591}-\\u{05A1}\\u{05A3}-\\u{05B9}\\u{05BB}-\\u{05BD}\\u{05BF}\\u{05C1}-\\u{05C2}\\u{05C4}\\u{064B}-\\u{0652}\\u{0670}\\u{06D6}-\\u{06DC}\\u{06DD}-\\u{06DF}\\u{06E0}-\\u{06E4}\\u{06E7}-\\u{06E8}\\u{06EA}-\\u{06ED}\\u{0901}-\\u{0903}\\u{093C}\\u{093E}-\\u{094C}\\u{094D}\\u{0951}-\\u{0954}\\u{0962}-\\u{0963}\\u{0981}-\\u{0983}\\u{09BC}\\u{09BE}\\u{09BF}\\u{09C0}-\\u{09C4}\\u{09C7}-\\u{09C8}\\u{09CB}-\\u{09CD}\\u{09D7}\\u{09E2}-\\u{09E3}\\u{0A02}\\u{0A3C}\\u{0A3E}\\u{0A3F}\\u{0A40}-\\u{0A42}\\u{0A47}-\\u{0A48}\\u{0A4B}-\\u{0A4D}\\u{0A70}-\\u{0A71}\\u{0A81}-\\u{0A83}\\u{0ABC}\\u{0ABE}-\\u{0AC5}\\u{0AC7}-\\u{0AC9}\\u{0ACB}-\\u{0ACD}\\u{0B01}-\\u{0B03}\\u{0B3C}\\u{0B3E}-\\u{0B43}\\u{0B47}-\\u{0B48}\\u{0B4B}-\\u{0B4D}\\u{0B56}-\\u{0B57}\\u{0B82}-\\u{0B83}\\u{0BBE}-\\u{0BC2}\\u{0BC6}-\\u{0BC8}\\u{0BCA}-\\u{0BCD}\\u{0BD7}\\u{0C01}-\\u{0C03}\\u{0C3E}-\\u{0C44}\\u{0C46}-\\u{0C48}\\u{0C4A}-\\u{0C4D}\\u{0C55}-\\u{0C56}\\u{0C82}-\\u{0C83}\\u{0CBE}-\\u{0CC4}\\u{0CC6}-\\u{0CC8}\\u{0CCA}-\\u{0CCD}\\u{0CD5}-\\u{0CD6}\\u{0D02}-\\u{0D03}\\u{0D3E}-\\u{0D43}\\u{0D46}-\\u{0D48}\\u{0D4A}-\\u{0D4D}\\u{0D57}\\u{0E31}\\u{0E34}-\\u{0E3A}\\u{0E47}-\\u{0E4E}\\u{0EB1}\\u{0EB4}-\\u{0EB9}\\u{0EBB}-\\u{0EBC}\\u{0EC8}-\\u{0ECD}\\u{0F18}-\\u{0F19}\\u{0F35}\\u{0F37}\\u{0F39}\\u{0F3E}\\u{0F3F}\\u{0F71}-\\u{0F84}\\u{0F86}-\\u{0F8B}\\u{0F90}-\\u{0F95}\\u{0F97}\\u{0F99}-\\u{0FAD}\\u{0FB1}-\\u{0FB7}\\u{0FB9}\\u{20D0}-\\u{20DC}\\u{20E1}\\u{302A}-\\u{302F}\\u{3099}\\u{309A}" +
+  "\\u{00B7}\\u{02D0}\\u{02D1}\\u{0387}\\u{0640}\\u{0E46}\\u{0EC6}\\u{3005}\\u{3031}-\\u{3035}\\u{309D}-\\u{309E}\\u{30FC}-\\u{30FE}";

package/src/xml-schema-regex-parser.ts

@@ -0,0 +1,234 @@
+import { xmlNameCharacters, xmlNameInitial, xmlSchemaBlocks } from "./xml-schema-regex-data.js";
+
+export type XmlRegexNode =
+  | { type: "character"; matcher: RegExp }
+  | { type: "sequence" | "choice"; children: XmlRegexNode[] }
+  | { type: "repeat"; child: XmlRegexNode; minimum: number; maximum: number };
+export interface XmlRegexProblem {
+  code: "syntax" | "limit";
+  message: string;
+}
+export type XmlRegexParseResult =
+  | { ok: true; expression: XmlRegexNode }
+  | { ok: false; problem: XmlRegexProblem };
+interface CharacterToken {
+  source: string;
+  point?: number;
+}
+
+export const XML_REGEX_MAX_PATTERN_LENGTH = 16_384;
+export const XML_REGEX_MAX_DEPTH = 64;
+const categories = /^(?:L[ultmo]?|M[nce]?|N[dlo]?|P[cdseifo]?|Z[slp]?|S[mcko]?|C[cfon]?)$/;
+const singleEscapes: Readonly<Record<string, string>> = { n: "\n", r: "\r", t: "\t" };
+const multiEscapes: Readonly<Record<string, string>> = {
+  s: "[ \\t\\n\\r]",
+  S: "[^ \\t\\n\\r]",
+  d: "\\p{Nd}",
+  D: "\\P{Nd}",
+  w: "[^\\p{P}\\p{Z}\\p{C}]",
+  W: "[\\p{P}\\p{Z}\\p{C}]",
+  i: `[${xmlNameInitial}]`,
+  I: `[^${xmlNameInitial}]`,
+  c: `[${xmlNameCharacters}]`,
+  C: `[^${xmlNameCharacters}]`,
+};
+
+/** Parses Appendix F syntax; native regexes only classify one code point at a time. */
+export function parseXmlSchemaRegex(pattern: string): XmlRegexParseResult {
+  if (pattern.length > XML_REGEX_MAX_PATTERN_LENGTH)
+    return {
+      ok: false,
+      problem: { code: "limit", message: "Pattern exceeds 16384 UTF-16 code units." },
+    };
+  let offset = 0;
+  let problem: XmlRegexProblem | undefined;
+  const peek = () => pattern[offset];
+  const hasProblem = () => problem !== undefined;
+  const fail = (message: string, code: XmlRegexProblem["code"] = "syntax"): undefined => {
+    problem ??= { code, message: `${message} At pattern offset ${offset}.` };
+    return undefined;
+  };
+  function literal(character: string): CharacterToken | undefined {
+    if (!isXmlRegexCharacter(character)) return fail("Pattern contains a non-XML character.");
+    const point = character.codePointAt(0) ?? 0;
+    return { source: `\\u{${point.toString(16)}}`, point };
+  }
+  function escape(): CharacterToken | undefined {
+    offset += 1;
+    const character = peek();
+    if (character === undefined) return fail("Incomplete escape.");
+    offset += 1;
+    if (Object.hasOwn(singleEscapes, character)) return literal(singleEscapes[character] ?? "");
+    if ("\\|.?*+(){}-[]^".includes(character)) return literal(character);
+    if (Object.hasOwn(multiEscapes, character)) return { source: multiEscapes[character] ?? "" };
+    if (character !== "p" && character !== "P") return fail("Unknown XML Schema escape.");
+    if (peek() !== "{") return fail("Expected a Unicode property in braces.");
+    offset += 1;
+    const end = pattern.indexOf("}", offset);
+    if (end < 0) return fail("Unclosed Unicode property.");
+    const property = pattern.slice(offset, end);
+    offset = end + 1;
+    if (categories.test(property)) return { source: `\\${character}{${property}}` };
+    const block = property.startsWith("Is") ? property.slice(2) : "";
+    if (!Object.hasOwn(xmlSchemaBlocks, block)) return fail("Unknown XML Schema Unicode property.");
+    const ranges = xmlSchemaBlocks[block];
+    // Preserve the Appendix F Specials block's legacy BOM member as well.
+    return {
+      source: `[${character === "P" ? "^" : ""}${ranges}${block === "Specials" ? "\\u{FEFF}" : ""}]`,
+    };
+  }
+  function classToken(): CharacterToken | undefined {
+    const character = peek();
+    if (character === "\\") return escape();
+    if (character === undefined || character === "[" || character === "]")
+      return fail("Expected a character in the class.");
+    const code = pattern.codePointAt(offset);
+    if (code === undefined) return fail("Expected a character.");
+    const value = String.fromCodePoint(code);
+    offset += value.length;
+    return literal(value);
+  }
+  function characterClass(depth: number): string | undefined {
+    if (depth > XML_REGEX_MAX_DEPTH) return fail("Character-class nesting exceeds 64.", "limit");
+    offset += 1;
+    const negative = peek() === "^";
+    if (negative) offset += 1;
+    const members: string[] = [];
+    let subtraction: string | undefined;
+    while (!hasProblem() && peek() !== "]") {
+      if (members.length > 0 && pattern.slice(offset, offset + 2) === "-[") {
+        offset += 1;
+        subtraction = characterClass(depth + 1);
+        if (peek() !== "]") return fail("Subtraction must end the character class.");
+        break;
+      }
+      const wasDash = peek() === "-";
+      if (wasDash && members.length > 0 && pattern[offset + 1] !== "]")
+        return fail("An unescaped dash must begin or end a class.");
+      const first = classToken();
+      if (!first) return undefined;
+      if (
+        !wasDash &&
+        peek() === "-" &&
+        pattern[offset + 1] !== "[" &&
+        pattern[offset + 1] !== "]"
+      ) {
+        offset += 1;
+        if (peek() === "-") return fail("Escape a dash used as a range endpoint.");
+        const last = classToken();
+        if (!last) return undefined;
+        if (first.point === undefined || last.point === undefined || first.point > last.point)
+          return fail("Invalid character range.");
+        members.push(`[${first.source}-${last.source}]`);
+      } else members.push(first.source);
+    }
+    if (problem) return undefined;
+    if (peek() !== "]" || members.length === 0) return fail("Unclosed or empty character class.");
+    offset += 1;
+    const union = `(?:${members.join("|")})`;
+    const base = negative ? `(?!${union})[\\s\\S]` : union;
+    return subtraction === undefined ? base : `(?!${subtraction})${base}`;
+  }
+  function characterNode(source: string): XmlRegexNode | undefined {
+    try {
+      return { type: "character", matcher: new RegExp(`^(?:${source})$`, "u") };
+    } catch {
+      return fail("Unable to compile the character class.");
+    }
+  }
+  function atom(depth: number): XmlRegexNode | undefined {
+    if (depth > XML_REGEX_MAX_DEPTH) return fail("Group nesting exceeds 64.", "limit");
+    const token = peek();
+    if (token === "(") {
+      offset += 1;
+      const expression = expressionAt(depth + 1);
+      if (peek() !== ")") return fail("Unclosed group.");
+      offset += 1;
+      return expression;
+    }
+    if (token === "[") {
+      const source = characterClass(depth + 1);
+      return source === undefined ? undefined : characterNode(source);
+    }
+    if (token === ".") {
+      offset += 1;
+      return characterNode("[^\\n\\r]");
+    }
+    if (token === "\\") {
+      const escaped = escape();
+      return escaped ? characterNode(escaped.source) : undefined;
+    }
+    if (token === undefined || "?*+{}]|)".includes(token)) return fail("Unexpected metacharacter.");
+    const value = classToken();
+    return value ? characterNode(value.source) : undefined;
+  }
+  function piece(depth: number): XmlRegexNode | undefined {
+    const child = atom(depth);
+    if (!child) return undefined;
+    const quantifier = peek();
+    if (quantifier === "?" || quantifier === "*" || quantifier === "+") {
+      offset += 1;
+      return {
+        type: "repeat",
+        child,
+        minimum: quantifier === "+" ? 1 : 0,
+        maximum: quantifier === "?" ? 1 : Infinity,
+      };
+    }
+    if (quantifier !== "{") return child;
+    const match = /^\{([0-9]+)(?:,([0-9]*))?\}/.exec(pattern.slice(offset));
+    if (!match || match[1] === undefined) return fail("Malformed quantifier.");
+    offset += match[0].length;
+    const minimum = Number(match[1]);
+    const maximum =
+      match[2] === undefined ? minimum : match[2] === "" ? Infinity : Number(match[2]);
+    if (!Number.isSafeInteger(minimum) || (maximum !== Infinity && !Number.isSafeInteger(maximum)))
+      return fail("Quantifier exceeds the safe integer range.", "limit");
+    if (maximum < minimum) return fail("Quantifier maximum is smaller than its minimum.");
+    return { type: "repeat", child, minimum, maximum };
+  }
+  function expressionAt(depth: number): XmlRegexNode | undefined {
+    const branches: XmlRegexNode[] = [];
+    while (!hasProblem()) {
+      const children: XmlRegexNode[] = [];
+      while (peek() !== undefined && peek() !== "|" && peek() !== ")" && !hasProblem()) {
+        const node = piece(depth);
+        if (!node) return undefined;
+        children.push(node);
+      }
+      branches.push({ type: "sequence", children });
+      if (peek() !== "|") break;
+      offset += 1;
+    }
+    return { type: "choice", children: branches };
+  }
+  const expression = expressionAt(0);
+  if (!problem && offset !== pattern.length) fail("Unexpected closing delimiter.");
+  if (problem) return { ok: false, problem };
+  return expression
+    ? { ok: true, expression }
+    : { ok: false, problem: { code: "syntax", message: "Invalid pattern." } };
+}
+
+/** QTI StringOrVariableRef uses braces, so bare identifiers remain literal patterns. */
+export function patternVariableIdentifier(pattern: string): string | undefined {
+  if (!pattern.startsWith("{") || !pattern.endsWith("}")) return undefined;
+  const identifier = pattern.slice(1, -1);
+  const initial = `[${xmlNameInitial}]`;
+  const rest = `[${xmlNameCharacters}]`;
+  return !identifier.includes(":") && new RegExp(`^${initial}${rest}*$`, "u").test(identifier)
+    ? identifier
+    : undefined;
+}
+
+export function isXmlRegexCharacter(value: string): boolean {
+  const point = value.codePointAt(0) ?? 0;
+  return (
+    point === 9 ||
+    point === 10 ||
+    point === 13 ||
+    (point >= 0x20 && point <= 0xd7ff) ||
+    (point >= 0xe000 && point <= 0xfffd) ||
+    (point >= 0x10000 && point <= 0x10ffff)
+  );
+}