In perl.git, the branch blead has been updated <https://perl5.git.perl.org/perl.git/commitdiff/3282ee13c09f8fd1009f35571059ec6e8204b2ec?hp=465848b5c535041b50179c7fe361c169bd817143>
- Log ----------------------------------------------------------------- commit 3282ee13c09f8fd1009f35571059ec6e8204b2ec Author: Karl Williamson <[email protected]> Date: Tue Mar 12 11:36:48 2019 -0600 Add tests for wildcards in Unicode property values commit 1532347b696561120241d1e6221c028acedff019 Author: Karl Williamson <[email protected]> Date: Mon Mar 11 17:16:34 2019 -0600 Add Unicode property wildcards commit 2cd613ec5fcf3b5c85fd2752b5871f18b4d33773 Author: Karl Williamson <[email protected]> Date: Mon Mar 11 15:55:54 2019 -0600 regen/mk_invlists.pl: Add tables for Unicode wildcards This supports this new feature. commit 4fa1c4b657de9d7a44e46d8008bf0f11306cf3e8 Author: Karl Williamson <[email protected]> Date: Mon Mar 11 13:14:36 2019 -0600 Add warnings category experimental::uniprop_wildcards ----------------------------------------------------------------------- Summary of changes: charclass_invlists.h | 3475 ++++++++++- lib/unicore/mktables | 49 +- lib/unicore/uni_keywords.pl | 4 +- lib/warnings.pm | 13 +- pod/perldelta.pod | 16 + pod/perldiag.pod | 20 + pod/perlre.pod | 2 +- pod/perlrecharclass.pod | 3 + pod/perlunicode.pod | 146 +- regcharclass.h | 2 +- regcomp.c | 161 + regen/mk_invlists.pl | 132 + regen/warnings.pl | 2 + uni_keywords.h | 14177 +++++++++++++++++++++--------------------- warnings.h | 1 + 15 files changed, 11177 insertions(+), 7026 deletions(-) diff --git a/charclass_invlists.h b/charclass_invlists.h index e2f6796d6e..e08b788b3c 100644 --- a/charclass_invlists.h +++ b/charclass_invlists.h @@ -389989,6 +389989,3477 @@ static const UV * const uni_prop_ptrs[] = { #define UNI_XPERLSPACE UNI_XPOSIXSPACE +static const char * const UNI_age_values[] = { + "1.1", + "2.0", + "2.1", + "3.0", + "3.1", + "3.2", + "4.0", + "4.1", + "5.0", + "5.1", + "5.2", + "6.0", + "6.1", + "6.2", + "6.3", + "7.0", + "8.0", + "9.0", + "10.0", + "11.0", + "12.0", + "NA", + "na", + "Unassigned", + "unassigned", + "V10_0", + "V11_0", + "V12_0", + "V1_1", + "V2_0", + "V2_1", + "V3_0", + "V3_1", + "V3_2", + "V4_0", + "V4_1", + "V5_0", + "V5_1", + "V5_2", + "V6_0", + "V6_1", + "V6_2", + "V6_3", + "V7_0", + "V8_0", + "V9_0", + "v100", + "v11", + "v110", + "v120", + "v20", + "v21", + "v30", + "v31", + "v32", + "v40", + "v41", + "v50", + "v51", + "v52", + "v60", + "v61", + "v62", + "v63", + "v70", + "v80", + "v90", + NULL +}; + +static const char * const UNI_ahex_values[] = { + "F", + "f", + "False", + "false", + "N", + "n", + "No", + "no", + "T", + "t", + "True", + "true", + "Y", + "y", + "Yes", + "yes", + NULL +}; + +static const char * const UNI_bc_values[] = { + "AL", + "al", + "AN", + "an", + "Arabic_Letter", + "arabicletter", + "Arabic_Number", + "arabicnumber", + "B", + "b", + "BN", + "bn", + "Boundary_Neutral", + "boundaryneutral", + "Common_Separator", + "commonseparator", + "CS", + "cs", + "EN", + "en", + "ES", + "es", + "ET", + "et", + "European_Number", + "europeannumber", + "European_Separator", + "europeanseparator", + "European_Terminator", + "europeanterminator", + "First_Strong_Isolate", + "firststrongisolate", + "FSI", + "fsi", + "L", + "l", + "Left_To_Right", + "lefttoright", + "Left_To_Right_Embedding", + "lefttorightembedding", + "Left_To_Right_Isolate", + "lefttorightisolate", + "Left_To_Right_Override", + "lefttorightoverride", + "LRE", + "lre", + "LRI", + "lri", + "LRO", + "lro", + "Nonspacing_Mark", + "nonspacingmark", + "NSM", + "nsm", + "ON", + "on", + "Other_Neutral", + "otherneutral", + "Paragraph_Separator", + "paragraphseparator", + "PDF", + "pdf", + "PDI", + "pdi", + "Pop_Directional_Format", + "popdirectionalformat", + "Pop_Directional_Isolate", + "popdirectionalisolate", + "R", + "r", + "Right_To_Left", + "righttoleft", + "Right_To_Left_Embedding", + "righttoleftembedding", + "Right_To_Left_Isolate", + "righttoleftisolate", + "Right_To_Left_Override", + "righttoleftoverride", + "RLE", + "rle", + "RLI", + "rli", + "RLO", + "rlo", + "S", + "s", + "Segment_Separator", + "segmentseparator", + "White_Space", + "whitespace", + "WS", + "ws", + NULL +}; + +static const char * const UNI_blk_values[] = { + "Adlam", + "adlam", + "Aegean Numbers", + "Aegean_Numbers", + "aegeannumbers", + "Ahom", + "ahom", + "Alchemical", + "alchemical", + "Alchemical Symbols", + "Alchemical_Symbols", + "alchemicalsymbols", + "Alphabetic_PF", + "alphabeticpf", + "Alphabetic Presentation Forms", + "Alphabetic_Presentation_Forms", + "alphabeticpresentationforms", + "Anatolian Hieroglyphs", + "Anatolian_Hieroglyphs", + "anatolianhieroglyphs", + "Ancient_Greek_Music", + "ancientgreekmusic", + "Ancient Greek Musical Notation", + "Ancient_Greek_Musical_Notation", + "ancientgreekmusicalnotation", + "Ancient Greek Numbers", + "Ancient_Greek_Numbers", + "ancientgreeknumbers", + "Ancient Symbols", + "Ancient_Symbols", + "ancientsymbols", + "Arabic", + "arabic", + "Arabic_Ext_A", + "arabicexta", + "Arabic Extended-A", + "Arabic_Extended_A", + "arabicextendeda", + "Arabic_Math", + "arabicmath", + "Arabic Mathematical Alphabetic Symbols", + "Arabic_Mathematical_Alphabetic_Symbols", + "arabicmathematicalalphabeticsymbols", + "Arabic_PF_A", + "arabicpfa", + "Arabic_PF_B", + "arabicpfb", + "Arabic Presentation Forms-A", + "Arabic_Presentation_Forms_A", + "arabicpresentationformsa", + "Arabic Presentation Forms-B", + "Arabic_Presentation_Forms_B", + "arabicpresentationformsb", + "Arabic_Sup", + "arabicsup", + "Arabic Supplement", + "Arabic_Supplement", + "arabicsupplement", + "Armenian", + "armenian", + "Arrows", + "arrows", + "ASCII", + "ascii", + "Avestan", + "avestan", + "Balinese", + "balinese", + "Bamum", + "bamum", + "Bamum_Sup", + "bamumsup", + "Bamum Supplement", + "Bamum_Supplement", + "bamumsupplement", + "Basic Latin", + "Basic_Latin", + "basiclatin", + "Bassa Vah", + "Bassa_Vah", + "bassavah", + "Batak", + "batak", + "Bengali", + "bengali", + "Bhaiksuki", + "bhaiksuki", + "Block Elements", + "Block_Elements", + "blockelements", + "Bopomofo", + "bopomofo", + "Bopomofo_Ext", + "bopomofoext", + "Bopomofo Extended", + "Bopomofo_Extended", + "bopomofoextended", + "Box Drawing", + "Box_Drawing", + "boxdrawing", + "Brahmi", + "brahmi", + "Braille", + "braille", + "Braille Patterns", + "Braille_Patterns", + "braillepatterns", + "Buginese", + "buginese", + "Buhid", + "buhid", + "Byzantine_Music", + "byzantinemusic", + "Byzantine Musical Symbols", + "Byzantine_Musical_Symbols", + "byzantinemusicalsymbols", + "Canadian_Syllabics", + "canadiansyllabics", + "Carian", + "carian", + "Caucasian Albanian", + "Caucasian_Albanian", + "caucasianalbanian", + "Chakma", + "chakma", + "Cham", + "cham", + "Cherokee", + "cherokee", + "Cherokee_Sup", + "cherokeesup", + "Cherokee Supplement", + "Cherokee_Supplement", + "cherokeesupplement", + "Chess Symbols", + "Chess_Symbols", + "chesssymbols", + "CJK", + "cjk", + "CJK_Compat", + "cjkcompat", + "CJK_Compat_Forms", + "cjkcompatforms", + "CJK Compatibility", + "CJK_Compatibility", + "cjkcompatibility", + "CJK Compatibility Forms", + "CJK_Compatibility_Forms", + "cjkcompatibilityforms", + "CJK Compatibility Ideographs", + "CJK_Compatibility_Ideographs", + "cjkcompatibilityideographs", + "CJK Compatibility Ideographs Supplement", + "CJK_Compatibility_Ideographs_Supplement", + "cjkcompatibilityideographssupplement", + "CJK_Compat_Ideographs", + "cjkcompatideographs", + "CJK_Compat_Ideographs_Sup", + "cjkcompatideographssup", + "CJK_Ext_A", + "cjkexta", + "CJK_Ext_B", + "cjkextb", + "CJK_Ext_C", + "cjkextc", + "CJK_Ext_D", + "cjkextd", + "CJK_Ext_E", + "cjkexte", + "CJK_Ext_F", + "cjkextf", + "CJK_Radicals_Sup", + "cjkradicalssup", + "CJK Radicals Supplement", + "CJK_Radicals_Supplement", + "cjkradicalssupplement", + "CJK Strokes", + "CJK_Strokes", + "cjkstrokes", + "CJK_Symbols", + "cjksymbols", + "CJK Symbols and Punctuation", + "CJK_Symbols_And_Punctuation", + "cjksymbolsandpunctuation", + "CJK Unified Ideographs", + "CJK_Unified_Ideographs", + "cjkunifiedideographs", + "CJK Unified Ideographs Extension A", + "CJK_Unified_Ideographs_Extension_A", + "cjkunifiedideographsextensiona", + "CJK Unified Ideographs Extension B", + "CJK_Unified_Ideographs_Extension_B", + "cjkunifiedideographsextensionb", + "CJK Unified Ideographs Extension C", + "CJK_Unified_Ideographs_Extension_C", + "cjkunifiedideographsextensionc", + "CJK Unified Ideographs Extension D", + "CJK_Unified_Ideographs_Extension_D", + "cjkunifiedideographsextensiond", + "CJK Unified Ideographs Extension E", + "CJK_Unified_Ideographs_Extension_E", + "cjkunifiedideographsextensione", + "CJK Unified Ideographs Extension F", + "CJK_Unified_Ideographs_Extension_F", + "cjkunifiedideographsextensionf", + "Combining Diacritical Marks", + "Combining_Diacritical_Marks", + "combiningdiacriticalmarks", + "Combining Diacritical Marks Extended", + "Combining_Diacritical_Marks_Extended", + "combiningdiacriticalmarksextended", + "Combining Diacritical Marks for Symbols", + "Combining_Diacritical_Marks_For_Symbols", + "combiningdiacriticalmarksforsymbols", + "Combining Diacritical Marks Supplement", + "Combining_Diacritical_Marks_Supplement", + "combiningdiacriticalmarkssupplement", + "Combining Half Marks", + "Combining_Half_Marks", + "combininghalfmarks", + "Combining_Marks_For_Symbols", + "combiningmarksforsymbols", + "Common Indic Number Forms", + "Common_Indic_Number_Forms", + "commonindicnumberforms", + "Compat_Jamo", + "compatjamo", + "Control Pictures", + "Control_Pictures", + "controlpictures", + "Coptic", + "coptic", + "Coptic Epact Numbers", + "Coptic_Epact_Numbers", + "copticepactnumbers", + "Counting_Rod", + "countingrod", + "Counting Rod Numerals", + "Counting_Rod_Numerals", + "countingrodnumerals", + "Cuneiform", + "cuneiform", + "Cuneiform_Numbers", + "cuneiformnumbers", + "Cuneiform Numbers and Punctuation", + "Cuneiform_Numbers_And_Punctuation", + "cuneiformnumbersandpunctuation", + "Currency Symbols", + "Currency_Symbols", + "currencysymbols", + "Cypriot Syllabary", + "Cypriot_Syllabary", + "cypriotsyllabary", + "Cyrillic", + "cyrillic", + "Cyrillic_Ext_A", + "cyrillicexta", + "Cyrillic_Ext_B", + "cyrillicextb", + "Cyrillic_Ext_C", + "cyrillicextc", + "Cyrillic Extended-A", + "Cyrillic_Extended_A", + "cyrillicextendeda", + "Cyrillic Extended-B", + "Cyrillic_Extended_B", + "cyrillicextendedb", + "Cyrillic Extended-C", + "Cyrillic_Extended_C", + "cyrillicextendedc", + "Cyrillic_Sup", + "cyrillicsup", + "Cyrillic Supplement", + "Cyrillic_Supplement", + "cyrillicsupplement", + "Cyrillic_Supplementary", + "cyrillicsupplementary", + "Deseret", + "deseret", + "Devanagari", + "devanagari", + "Devanagari_Ext", + "devanagariext", + "Devanagari Extended", + "Devanagari_Extended", + "devanagariextended", + "Diacriticals", + "diacriticals", + "Diacriticals_Ext", + "diacriticalsext", + "Diacriticals_For_Symbols", + "diacriticalsforsymbols", + "Diacriticals_Sup", + "diacriticalssup", + "Dingbats", + "dingbats", + "Dogra", + "dogra", + "Domino", + "domino", + "Domino Tiles", + "Domino_Tiles", + "dominotiles", + "Duployan", + "duployan", + "Early Dynastic Cuneiform", + "Early_Dynastic_Cuneiform", + "earlydynasticcuneiform", + "Egyptian Hieroglyph Format Controls", + "Egyptian_Hieroglyph_Format_Controls", + "egyptianhieroglyphformatcontrols", + "Egyptian Hieroglyphs", + "Egyptian_Hieroglyphs", + "egyptianhieroglyphs", + "Elbasan", + "elbasan", + "Elymaic", + "elymaic", + "Emoticons", + "emoticons", + "Enclosed_Alphanum", + "enclosedalphanum", + "Enclosed Alphanumerics", + "Enclosed_Alphanumerics", + "enclosedalphanumerics", + "Enclosed Alphanumeric Supplement", + "Enclosed_Alphanumeric_Supplement", + "enclosedalphanumericsupplement", + "Enclosed_Alphanum_Sup", + "enclosedalphanumsup", + "Enclosed_CJK", + "enclosedcjk", + "Enclosed CJK Letters and Months", + "Enclosed_CJK_Letters_And_Months", + "enclosedcjklettersandmonths", + "Enclosed_Ideographic_Sup", + "enclosedideographicsup", + "Enclosed Ideographic Supplement", + "Enclosed_Ideographic_Supplement", + "enclosedideographicsupplement", + "Ethiopic", + "ethiopic", + "Ethiopic_Ext", + "ethiopicext", + "Ethiopic_Ext_A", + "ethiopicexta", + "Ethiopic Extended", + "Ethiopic_Extended", + "ethiopicextended", + "Ethiopic Extended-A", + "Ethiopic_Extended_A", + "ethiopicextendeda", + "Ethiopic_Sup", + "ethiopicsup", + "Ethiopic Supplement", + "Ethiopic_Supplement", + "ethiopicsupplement", + "General Punctuation", + "General_Punctuation", + "generalpunctuation", + "Geometric Shapes", + "Geometric_Shapes", + "geometricshapes", + "Geometric_Shapes_Ext", + "geometricshapesext", + "Geometric Shapes Extended", + "Geometric_Shapes_Extended", + "geometricshapesextended", + "Georgian", + "georgian", + "Georgian_Ext", + "georgianext", + "Georgian Extended", + "Georgian_Extended", + "georgianextended", + "Georgian_Sup", + "georgiansup", + "Georgian Supplement", + "Georgian_Supplement", + "georgiansupplement", + "Glagolitic", + "glagolitic", + "Glagolitic_Sup", + "glagoliticsup", + "Glagolitic Supplement", + "Glagolitic_Supplement", + "glagoliticsupplement", + "Gothic", + "gothic", + "Grantha", + "grantha", + "Greek", + "greek", + "Greek and Coptic", + "Greek_And_Coptic", + "greekandcoptic", + "Greek_Ext", + "greekext", + "Greek Extended", + "Greek_Extended", + "greekextended", + "Gujarati", + "gujarati", + "Gunjala Gondi", + "Gunjala_Gondi", + "gunjalagondi", + "Gurmukhi", + "gurmukhi", + "Half_And_Full_Forms", + "halfandfullforms", + "Half_Marks", + "halfmarks", + "Halfwidth and Fullwidth Forms", + "Halfwidth_And_Fullwidth_Forms", + "halfwidthandfullwidthforms", + "Hangul", + "hangul", + "Hangul Compatibility Jamo", + "Hangul_Compatibility_Jamo", + "hangulcompatibilityjamo", + "Hangul Jamo", + "Hangul_Jamo", + "hanguljamo", + "Hangul Jamo Extended-A", + "Hangul_Jamo_Extended_A", + "hanguljamoextendeda", + "Hangul Jamo Extended-B", + "Hangul_Jamo_Extended_B", + "hanguljamoextendedb", + "Hangul Syllables", + "Hangul_Syllables", + "hangulsyllables", + "Hanifi Rohingya", + "Hanifi_Rohingya", + "hanifirohingya", + "Hanunoo", + "hanunoo", + "Hatran", + "hatran", + "Hebrew", + "hebrew", + "High Private Use Surrogates", + "High_Private_Use_Surrogates", + "highprivateusesurrogates", + "High_PU_Surrogates", + "highpusurrogates", + "High Surrogates", + "High_Surrogates", + "highsurrogates", + "Hiragana", + "hiragana", + "IDC", + "idc", + "Ideographic Description Characters", + "Ideographic_Description_Characters", + "ideographicdescriptioncharacters", + "Ideographic_Symbols", + "ideographicsymbols", + "Ideographic Symbols and Punctuation", + "Ideographic_Symbols_And_Punctuation", + "ideographicsymbolsandpunctuation", + "Imperial Aramaic", + "Imperial_Aramaic", + "imperialaramaic", + "Indic_Number_Forms", + "indicnumberforms", + "Indic Siyaq Numbers", + "Indic_Siyaq_Numbers", + "indicsiyaqnumbers", + "Inscriptional Pahlavi", + "Inscriptional_Pahlavi", + "inscriptionalpahlavi", + "Inscriptional Parthian", + "Inscriptional_Parthian", + "inscriptionalparthian", + "IPA_Ext", + "ipaext", + "IPA Extensions", + "IPA_Extensions", + "ipaextensions", + "Jamo", + "jamo", + "Jamo_Ext_A", + "jamoexta", + "Jamo_Ext_B", + "jamoextb", + "Javanese", + "javanese", + "Kaithi", + "kaithi", + "Kana_Ext_A", + "kanaexta", + "Kana Extended-A", + "Kana_Extended_A", + "kanaextendeda", + "Kana_Sup", + "kanasup", + "Kana Supplement", + "Kana_Supplement", + "kanasupplement", + "Kanbun", + "kanbun", + "Kangxi", + "kangxi", + "Kangxi Radicals", + "Kangxi_Radicals", + "kangxiradicals", + "Kannada", + "kannada", + "Katakana", + "katakana", + "Katakana_Ext", + "katakanaext", + "Katakana Phonetic Extensions", + "Katakana_Phonetic_Extensions", + "katakanaphoneticextensions", + "Kayah Li", + "Kayah_Li", + "kayahli", + "Kharoshthi", + "kharoshthi", + "Khmer", + "khmer", + "Khmer Symbols", + "Khmer_Symbols", + "khmersymbols", + "Khojki", + "khojki", + "Khudawadi", + "khudawadi", + "Lao", + "lao", + "Latin_1", + "latin1", + "Latin_Ext_A", + "latinexta", + "Latin_Ext_Additional", + "latinextadditional", + "Latin_Ext_B", + "latinextb", + "Latin_Ext_C", + "latinextc", + "Latin_Ext_D", + "latinextd", + "Latin_Ext_E", + "latinexte", + "Latin Extended-A", + "Latin_Extended_A", + "latinextendeda", + "Latin Extended Additional", + "Latin_Extended_Additional", + "latinextendedadditional", + "Latin Extended-B", + "Latin_Extended_B", + "latinextendedb", + "Latin Extended-C", + "Latin_Extended_C", + "latinextendedc", + "Latin Extended-D", + "Latin_Extended_D", + "latinextendedd", + "Latin Extended-E", + "Latin_Extended_E", + "latinextendede", + "Latin_1_Sup", + "latin1sup", + "Latin-1 Supplement", + "Latin_1_Supplement", + "latin1supplement", + "Lepcha", + "lepcha", + "Letterlike Symbols", + "Letterlike_Symbols", + "letterlikesymbols", + "Limbu", + "limbu", + "Linear A", + "Linear_A", + "lineara", + "Linear B Ideograms", + "Linear_B_Ideograms", + "linearbideograms", + "Linear B Syllabary", + "Linear_B_Syllabary", + "linearbsyllabary", + "Lisu", + "lisu", + "Low Surrogates", + "Low_Surrogates", + "lowsurrogates", + "Lycian", + "lycian", + "Lydian", + "lydian", + "Mahajani", + "mahajani", + "Mahjong", + "mahjong", + "Mahjong Tiles", + "Mahjong_Tiles", + "mahjongtiles", + "Makasar", + "makasar", + "Malayalam", + "malayalam", + "Mandaic", + "mandaic", + "Manichaean", + "manichaean", + "Marchen", + "marchen", + "Masaram Gondi", + "Masaram_Gondi", + "masaramgondi", + "Math_Alphanum", + "mathalphanum", + "Mathematical Alphanumeric Symbols", + "Mathematical_Alphanumeric_Symbols", + "mathematicalalphanumericsymbols", + "Mathematical Operators", + "Mathematical_Operators", + "mathematicaloperators", + "Math_Operators", + "mathoperators", + "Mayan Numerals", + "Mayan_Numerals", + "mayannumerals", + "Medefaidrin", + "medefaidrin", + "Meetei Mayek", + "Meetei_Mayek", + "meeteimayek", + "Meetei_Mayek_Ext", + "meeteimayekext", + "Meetei Mayek Extensions", + "Meetei_Mayek_Extensions", + "meeteimayekextensions", + "Mende Kikakui", + "Mende_Kikakui", + "mendekikakui", + "Meroitic Cursive", + "Meroitic_Cursive", + "meroiticcursive", + "Meroitic Hieroglyphs", + "Meroitic_Hieroglyphs", + "meroitichieroglyphs", + "Miao", + "miao", + "Misc_Arrows", + "miscarrows", + "Miscellaneous Mathematical Symbols-A", + "Miscellaneous_Mathematical_Symbols_A", + "miscellaneousmathematicalsymbolsa", + "Miscellaneous Mathematical Symbols-B", + "Miscellaneous_Mathematical_Symbols_B", + "miscellaneousmathematicalsymbolsb", + "Miscellaneous Symbols", + "Miscellaneous_Symbols", + "miscellaneoussymbols", + "Miscellaneous Symbols and Arrows", + "Miscellaneous_Symbols_And_Arrows", + "miscellaneoussymbolsandarrows", + "Miscellaneous Symbols and Pictographs", + "Miscellaneous_Symbols_And_Pictographs", + "miscellaneoussymbolsandpictographs", + "Miscellaneous Technical", + "Miscellaneous_Technical", + "miscellaneoustechnical", + "Misc_Math_Symbols_A", + "miscmathsymbolsa", + "Misc_Math_Symbols_B", + "miscmathsymbolsb", + "Misc_Pictographs", + "miscpictographs", + "Misc_Symbols", + "miscsymbols", + "Misc_Technical", + "misctechnical", + "Modi", + "modi", + "Modifier_Letters", + "modifierletters", + "Modifier Tone Letters", + "Modifier_Tone_Letters", + "modifiertoneletters", + "Mongolian", + "mongolian", + "Mongolian_Sup", + "mongoliansup", + "Mongolian Supplement", + "Mongolian_Supplement", + "mongoliansupplement", + "Mro", + "mro", + "Multani", + "multani", + "Music", + "music", + "Musical Symbols", + "Musical_Symbols", + "musicalsymbols", + "Myanmar", + "myanmar", + "Myanmar_Ext_A", + "myanmarexta", + "Myanmar_Ext_B", + "myanmarextb", + "Myanmar Extended-A", + "Myanmar_Extended_A", + "myanmarextendeda", + "Myanmar Extended-B", + "Myanmar_Extended_B", + "myanmarextendedb", + "Nabataean", + "nabataean", + "Nandinagari", + "nandinagari", + "NB", + "nb", + "Newa", + "newa", + "New Tai Lue", + "New_Tai_Lue", + "newtailue", + "NKo", + "nko", + "No_Block", + "noblock", + "Number Forms", + "Number_Forms", + "numberforms", + "Nushu", + "nushu", + "Nyiakeng Puachue Hmong", + "Nyiakeng_Puachue_Hmong", + "nyiakengpuachuehmong", + "OCR", + "ocr", + "Ogham", + "ogham", + "Ol Chiki", + "Ol_Chiki", + "olchiki", + "Old Hungarian", + "Old_Hungarian", + "oldhungarian", + "Old Italic", + "Old_Italic", + "olditalic", + "Old North Arabian", + "Old_North_Arabian", + "oldnortharabian", + "Old Permic", + "Old_Permic", + "oldpermic", + "Old Persian", + "Old_Persian", + "oldpersian", + "Old Sogdian", + "Old_Sogdian", + "oldsogdian", + "Old South Arabian", + "Old_South_Arabian", + "oldsoutharabian", + "Old Turkic", + "Old_Turkic", + "oldturkic", + "Optical Character Recognition", + "Optical_Character_Recognition", + "opticalcharacterrecognition", + "Oriya", + "oriya", + "Ornamental Dingbats", + "Ornamental_Dingbats", + "ornamentaldingbats", + "Osage", + "osage", + "Osmanya", + "osmanya", + "Ottoman Siyaq Numbers", + "Ottoman_Siyaq_Numbers", + "ottomansiyaqnumbers", + "Pahawh Hmong", + "Pahawh_Hmong", + "pahawhhmong", + "Palmyrene", + "palmyrene", + "Pau Cin Hau", + "Pau_Cin_Hau", + "paucinhau", + "Phags-pa", + "Phags_Pa", + "phagspa", + "Phaistos", + "phaistos", + "Phaistos Disc", + "Phaistos_Disc", + "phaistosdisc", + "Phoenician", + "phoenician", + "Phonetic_Ext", + "phoneticext", + "Phonetic Extensions", + "Phonetic_Extensions", + "phoneticextensions", + "Phonetic Extensions Supplement", + "Phonetic_Extensions_Supplement", + "phoneticextensionssupplement", + "Phonetic_Ext_Sup", + "phoneticextsup", + "Playing Cards", + "Playing_Cards", + "playingcards", + "Private_Use", + "privateuse", + "Private Use Area", + "Private_Use_Area", + "privateusearea", + "Psalter Pahlavi", + "Psalter_Pahlavi", + "psalterpahlavi", + "PUA", + "pua", + "Punctuation", + "punctuation", + "Rejang", + "rejang", + "Rumi", + "rumi", + "Rumi Numeral Symbols", + "Rumi_Numeral_Symbols", + "ruminumeralsymbols", + "Runic", + "runic", + "Samaritan", + "samaritan", + "Saurashtra", + "saurashtra", + "Sharada", + "sharada", + "Shavian", + "shavian", + "Shorthand Format Controls", + "Shorthand_Format_Controls", + "shorthandformatcontrols", + "Siddham", + "siddham", + "Sinhala", + "sinhala", + "Sinhala Archaic Numbers", + "Sinhala_Archaic_Numbers", + "sinhalaarchaicnumbers", + "Small_Forms", + "smallforms", + "Small Form Variants", + "Small_Form_Variants", + "smallformvariants", + "Small_Kana_Ext", + "smallkanaext", + "Small Kana Extension", + "Small_Kana_Extension", + "smallkanaextension", + "Sogdian", + "sogdian", + "Sora Sompeng", + "Sora_Sompeng", + "sorasompeng", + "Soyombo", + "soyombo", + "Spacing Modifier Letters", + "Spacing_Modifier_Letters", + "spacingmodifierletters", + "Specials", + "specials", + "Sundanese", + "sundanese", + "Sundanese_Sup", + "sundanesesup", + "Sundanese Supplement", + "Sundanese_Supplement", + "sundanesesupplement", + "Sup_Arrows_A", + "suparrowsa", + "Sup_Arrows_B", + "suparrowsb", + "Sup_Arrows_C", + "suparrowsc", + "Super_And_Sub", + "superandsub", + "Superscripts and Subscripts", + "Superscripts_And_Subscripts", + "superscriptsandsubscripts", + "Sup_Math_Operators", + "supmathoperators", + "Supplemental Arrows-A", + "Supplemental_Arrows_A", + "supplementalarrowsa", + "Supplemental Arrows-B", + "Supplemental_Arrows_B", + "supplementalarrowsb", + "Supplemental Arrows-C", + "Supplemental_Arrows_C", + "supplementalarrowsc", + "Supplemental Mathematical Operators", + "Supplemental_Mathematical_Operators", + "supplementalmathematicaloperators", + "Supplemental Punctuation", + "Supplemental_Punctuation", + "supplementalpunctuation", + "Supplemental Symbols and Pictographs", + "Supplemental_Symbols_And_Pictographs", + "supplementalsymbolsandpictographs", + "Supplementary Private Use Area-A", + "Supplementary_Private_Use_Area_A", + "supplementaryprivateuseareaa", + "Supplementary Private Use Area-B", + "Supplementary_Private_Use_Area_B", + "supplementaryprivateuseareab", + "Sup_PUA_A", + "suppuaa", + "Sup_PUA_B", + "suppuab", + "Sup_Punctuation", + "suppunctuation", + "Sup_Symbols_And_Pictographs", + "supsymbolsandpictographs", + "Sutton SignWriting", + "Sutton_SignWriting", + "suttonsignwriting", + "Syloti Nagri", + "Syloti_Nagri", + "sylotinagri", + "Symbols_And_Pictographs_Ext_A", + "symbolsandpictographsexta", + "Symbols and Pictographs Extended-A", + "Symbols_And_Pictographs_Extended_A", + "symbolsandpictographsextendeda", + "Syriac", + "syriac", + "Syriac_Sup", + "syriacsup", + "Syriac Supplement", + "Syriac_Supplement", + "syriacsupplement", + "Tagalog", + "tagalog", + "Tagbanwa", + "tagbanwa", + "Tags", + "tags", + "Tai Le", + "Tai_Le", + "taile", + "Tai Tham", + "Tai_Tham", + "taitham", + "Tai Viet", + "Tai_Viet", + "taiviet", + "Tai_Xuan_Jing", + "taixuanjing", + "Tai Xuan Jing Symbols", + "Tai_Xuan_Jing_Symbols", + "taixuanjingsymbols", + "Takri", + "takri", + "Tamil", + "tamil", + "Tamil_Sup", + "tamilsup", + "Tamil Supplement", + "Tamil_Supplement", + "tamilsupplement", + "Tangut", + "tangut", + "Tangut Components", + "Tangut_Components", + "tangutcomponents", + "Telugu", + "telugu", + "Thaana", + "thaana", + "Thai", + "thai", + "Tibetan", + "tibetan", + "Tifinagh", + "tifinagh", + "Tirhuta", + "tirhuta", + "Transport_And_Map", + "transportandmap", + "Transport and Map Symbols", + "Transport_And_Map_Symbols", + "transportandmapsymbols", + "UCAS", + "ucas", + "UCAS_Ext", + "ucasext", + "Ugaritic", + "ugaritic", + "Unified Canadian Aboriginal Syllabics", + "Unified_Canadian_Aboriginal_Syllabics", + "unifiedcanadianaboriginalsyllabics", + "Unified Canadian Aboriginal Syllabics Extended", + "Unified_Canadian_Aboriginal_Syllabics_Extended", + "unifiedcanadianaboriginalsyllabicsextended", + "Vai", + "vai", + "Variation Selectors", + "Variation_Selectors", + "variationselectors", + "Variation Selectors Supplement", + "Variation_Selectors_Supplement", + "variationselectorssupplement", + "Vedic_Ext", + "vedicext", + "Vedic Extensions", + "Vedic_Extensions", + "vedicextensions", + "Vertical Forms", + "Vertical_Forms", + "verticalforms", + "VS", + "vs", + "VS_Sup", + "vssup", + "Wancho", + "wancho", + "Warang Citi", + "Warang_Citi", + "warangciti", + "Yijing", + "yijing", + "Yijing Hexagram Symbols", + "Yijing_Hexagram_Symbols", + "yijinghexagramsymbols", + "Yi Radicals", + "Yi_Radicals", + "yiradicals", + "Yi Syllables", + "Yi_Syllables", + "yisyllables", + "Zanabazar Square", + "Zanabazar_Square", + "zanabazarsquare", + NULL +}; + +static const char * const UNI_bpt_values[] = { + "c", + "Close", + "close", + "n", + "None", + "none", + "o", + "Open", + "open", + NULL +}; + +static const char * const UNI_ccc_values[] = { + "0", + "1", + "7", + "8", + "9", + "10", + "11", + "12", + "13", + "14", + "15", + "16", + "17", + "18", + "19", + "20", + "21", + "22", + "23", + "24", + "25", + "26", + "27", + "28", + "29", + "30", + "31", + "32", + "33", + "34", + "35", + "36", + "84", + "91", + "103", + "107", + "118", + "122", + "129", + "130", + "132", + "133", + "200", + "202", + "214", + "216", + "218", + "220", + "222", + "224", + "226", + "228", + "230", + "232", + "233", + "234", + "240", + "A", + "a", + "Above", + "above", + "Above_Left", + "aboveleft", + "Above_Right", + "aboveright", + "AL", + "al", + "AR", + "ar", + "ATA", + "ata", + "ATAR", + "atar", + "ATB", + "atb", + "ATBL", + "atbl", + "Attached_Above", + "attachedabove", + "Attached_Above_Right", + "attachedaboveright", + "Attached_Below", + "attachedbelow", + "Attached_Below_Left", + "attachedbelowleft", + "B", + "b", + "Below", + "below", + "Below_Left", + "belowleft", + "Below_Right", + "belowright", + "BL", + "bl", + "BR", + "br", + "CCC10", + "CCC103", + "CCC107", + "CCC11", + "CCC118", + "CCC12", + "CCC122", + "CCC129", + "CCC13", + "CCC130", + "CCC132", + "CCC133", + "CCC14", + "CCC15", + "CCC16", + "CCC17", + "CCC18", + "CCC19", + "CCC20", + "CCC21", + "CCC22", + "CCC23", + "CCC24", + "CCC25", + "CCC26", + "CCC27", + "CCC28", + "CCC29", + "CCC30", + "CCC31", + "CCC32", + "CCC33", + "CCC34", + "CCC35", + "CCC36", + "CCC84", + "CCC91", + "ccc10", + "ccc103", + "ccc107", + "ccc11", + "ccc118", + "ccc12", + "ccc122", + "ccc129", + "ccc13", + "ccc130", + "ccc132", + "ccc133", + "ccc14", + "ccc15", + "ccc16", + "ccc17", + "ccc18", + "ccc19", + "ccc20", + "ccc21", + "ccc22", + "ccc23", + "ccc24", + "ccc25", + "ccc26", + "ccc27", + "ccc28", + "ccc29", + "ccc30", + "ccc31", + "ccc32", + "ccc33", + "ccc34", + "ccc35", + "ccc36", + "ccc84", + "ccc91", + "DA", + "da", + "DB", + "db", + "Double_Above", + "doubleabove", + "Double_Below", + "doublebelow", + "Iota_Subscript", + "iotasubscript", + "IS", + "is", + "Kana_Voicing", + "kanavoicing", + "KV", + "kv", + "L", + "l", + "Left", + "left", + "NK", + "nk", + "Not_Reordered", + "notreordered", + "NR", + "nr", + "Nukta", + "nukta", + "OV", + "ov", + "Overlay", + "overlay", + "R", + "r", + "Right", + "right", + "Virama", + "virama", + "VR", + "vr", + NULL +}; + +static const char * const UNI_dt_values[] = { + "Can", + "can", + "Canonical", + "canonical", + "Circle", + "circle", + "Com", + "com", + "Compat", + "compat", + "Enc", + "enc", + "Fin", + "fin", + "Final", + "final", + "Font", + "font", + "Fra", + "fra", + "Fraction", + "fraction", + "Init", + "init", + "Initial", + "initial", + "Iso", + "iso", + "Isolated", + "isolated", + "Med", + "med", + "Medial", + "medial", + "Nar", + "nar", + "Narrow", + "narrow", + "Nb", + "nb", + "Nobreak", + "nobreak", + "Non_Canon", + "noncanon", + "Non_Canonical", + "noncanonical", + "None", + "none", + "Small", + "small", + "Sml", + "sml", + "Sqr", + "sqr", + "Square", + "square", + "Sub", + "sub", + "Sup", + "sup", + "Super", + "super", + "Vert", + "vert", + "Vertical", + "vertical", + "Wide", + "wide", + NULL +}; + +static const char * const UNI_ea_values[] = { + "A", + "a", + "Ambiguous", + "ambiguous", + "F", + "f", + "Fullwidth", + "fullwidth", + "H", + "h", + "Halfwidth", + "halfwidth", + "N", + "n", + "Na", + "na", + "Narrow", + "narrow", + "Neutral", + "neutral", + "W", + "w", + "Wide", + "wide", + NULL +}; + +static const char * const UNI_gc_values[] = { + "C", + "c", + "Cased_Letter", + "casedletter", + "Cc", + "cc", + "Cf", + "cf", + "Close_Punctuation", + "closepunctuation", + "Cn", + "cn", + "Cntrl", + "cntrl", + "Co", + "co", + "Combining_Mark", + "combiningmark", + "Connector_Punctuation", + "connectorpunctuation", + "Control", + "control", + "Cs", + "cs", + "Currency_Symbol", + "currencysymbol", + "Dash_Punctuation", + "dashpunctuation", + "Decimal_Number", + "decimalnumber", + "Digit", + "digit", + "Enclosing_Mark", + "enclosingmark", + "Final_Punctuation", + "finalpunctuation", + "Format", + "format", + "Initial_Punctuation", + "initialpunctuation", + "L", + "l", + "LC", + "lc", + "Letter", + "letter", + "Letter_Number", + "letternumber", + "Line_Separator", + "lineseparator", + "Ll", + "ll", + "Lm", + "lm", + "Lo", + "lo", + "Lowercase_Letter", + "lowercaseletter", + "Lt", + "lt", + "Lu", + "lu", + "M", + "m", + "Mark", + "mark", + "Math_Symbol", + "mathsymbol", + "Mc", + "mc", + "Me", + "me", + "Mn", + "mn", + "Modifier_Letter", + "modifierletter", + "Modifier_Symbol", + "modifiersymbol", + "N", + "n", + "Nd", + "nd", + "Nl", + "nl", + "No", + "no", + "Nonspacing_Mark", + "nonspacingmark", + "Number", + "number", + "Open_Punctuation", + "openpunctuation", + "Other", + "other", + "Other_Letter", + "otherletter", + "Other_Number", + "othernumber", + "Other_Punctuation", + "otherpunctuation", + "Other_Symbol", + "othersymbol", + "P", + "p", + "Paragraph_Separator", + "paragraphseparator", + "Pc", + "pc", + "Pd", + "pd", + "Pe", + "pe", + "Pf", + "pf", + "Pi", + "pi", + "Po", + "po", + "Private_Use", + "privateuse", + "Ps", + "ps", + "Punct", + "punct", + "Punctuation", + "punctuation", + "S", + "s", + "Sc", + "sc", + "Separator", + "separator", + "Sk", + "sk", + "Sm", + "sm", + "So", + "so", + "Space_Separator", + "spaceseparator", + "Spacing_Mark", + "spacingmark", + "Surrogate", + "surrogate", + "Symbol", + "symbol", + "Titlecase_Letter", + "titlecaseletter", + "Unassigned", + "unassigned", + "Uppercase_Letter", + "uppercaseletter", + "Z", + "z", + "Zl", + "zl", + "Zp", + "zp", + "Zs", + "zs", + NULL +}; + +static const char * const UNI_gcb_values[] = { + "CN", + "cn", + "Control", + "control", + "CR", + "cr", + "EB", + "eb", + "E_Base", + "ebase", + "E_Base_GAZ", + "ebasegaz", + "EBG", + "ebg", + "EM", + "em", + "E_Modifier", + "emodifier", + "EX", + "ex", + "Extend", + "extend", + "GAZ", + "gaz", + "Glue_After_Zwj", + "glueafterzwj", + "L", + "l", + "LF", + "lf", + "LV", + "lv", + "LVT", + "lvt", + "Other", + "other", + "PP", + "pp", + "Prepend", + "prepend", + "Regional_Indicator", + "regionalindicator", + "RI", + "ri", + "SM", + "sm", + "SpacingMark", + "spacingmark", + "T", + "t", + "V", + "v", + "XX", + "xx", + "ZWJ", + "zwj", + NULL +}; + +static const char * const UNI_hst_values[] = { + "L", + "l", + "Leading_Jamo", + "leadingjamo", + "LV", + "lv", + "LV_Syllable", + "lvsyllable", + "LVT", + "lvt", + "LVT_Syllable", + "lvtsyllable", + "NA", + "na", + "Not_Applicable", + "notapplicable", + "T", + "t", + "Trailing_Jamo", + "trailingjamo", + "V", + "v", + "Vowel_Jamo", + "voweljamo", + NULL +}; + +static const char * const UNI_in_values[] = { + "1.1", + "2.0", + "2.1", + "3.0", + "3.1", + "3.2", + "4.0", + "4.1", + "5.0", + "5.1", + "5.2", + "6.0", + "6.1", + "6.2", + "6.3", + "7.0", + "8.0", + "9.0", + "10.0", + "11.0", + "12.0", + "Unassigned", + "unassigned", + "V10_0", + "V11_0", + "V12_0", + "V2_0", + "V2_1", + "V3_0", + "V3_1", + "V3_2", + "V4_0", + "V4_1", + "V5_0", + "V5_1", + "V5_2", + "V6_0", + "V6_1", + "V6_2", + "V6_3", + "V7_0", + "V8_0", + "V9_0", + "v100", + "v110", + "v120", + "v20", + "v21", + "v30", + "v31", + "v32", + "v40", + "v41", + "v50", + "v51", + "v52", + "v60", + "v61", + "v62", + "v63", + "v70", + "v80", + "v90", + NULL +}; + +static const char * const UNI_inpc_values[] = { + "Bottom", + "bottom", + "Bottom_And_Left", + "bottomandleft", + "Bottom_And_Right", + "bottomandright", + "Left", + "left", + "Left_And_Right", + "leftandright", + "NA", + "na", + "Overstruck", + "overstruck", + "Right", + "right", + "Top", + "top", + "Top_And_Bottom", + "topandbottom", + "Top_And_Bottom_And_Right", + "topandbottomandright", + "Top_And_Left", + "topandleft", + "Top_And_Left_And_Right", + "topandleftandright", + "Top_And_Right", + "topandright", + "Visual_Order_Left", + "visualorderleft", + NULL +}; + +static const char * const UNI_insc_values[] = { + "Avagraha", + "avagraha", + "Bindu", + "bindu", + "Brahmi_Joining_Number", + "brahmijoiningnumber", + "Cantillation_Mark", + "cantillationmark", + "Consonant", + "consonant", + "Consonant_Dead", + "consonantdead", + "Consonant_Final", + "consonantfinal", + "Consonant_Head_Letter", + "consonantheadletter", + "Consonant_Initial_Postfixed", + "consonantinitialpostfixed", + "Consonant_Killer", + "consonantkiller", + "Consonant_Medial", + "consonantmedial", + "Consonant_Placeholder", + "consonantplaceholder", + "Consonant_Preceding_Repha", + "consonantprecedingrepha", ... 16576 lines suppressed ... -- Perl5 Master Repository
