Add support for 4-character script abbreviations

doc/html/pcre2syntax.html

@@ -207,171 +207,172 @@ at release 5.18.
 </P>
 <br><a name="SEC7" href="#TOC1">SCRIPT MATCHING WITH \p AND \P</a><br>
 <P>
-The following script names are recognized in \p{sc:...} or \p{scx:...} items,
-or on their own with \p (and also \P of course):
+The following script names and their 4-letter abbreviations are recognized in
+\p{sc:...} or \p{scx:...} items, or on their own with \p (and also \P of
+course):
 </P>
 <P>
-Adlam,
-Ahom,
-Anatolian_Hieroglyphs,
-Arabic,
-Armenian,
-Avestan,
-Balinese,
-Bamum,
-Bassa_Vah,
-Batak,
-Bengali,
-Bhaiksuki,
-Bopomofo,
-Brahmi,
-Braille,
-Buginese,
-Buhid,
-Canadian_Aboriginal,
-Carian,
-Caucasian_Albanian,
-Chakma,
-Cham,
-Cherokee,
-Chorasmian,
-Common,
-Coptic,
-Cuneiform,
-Cypriot,
-Cypro_Minoan,
-Cyrillic,
-Deseret,
-Devanagari,
-Dives_Akuru,
-Dogra,
-Duployan,
-Egyptian_Hieroglyphs,
-Elbasan,
-Elymaic,
-Ethiopic,
-Georgian,
-Glagolitic,
-Gothic,
-Grantha,
-Greek,
-Gujarati,
-Gunjala_Gondi,
-Gurmukhi,
-Han,
-Hangul,
-Hanifi_Rohingya,
-Hanunoo,
-Hatran,
-Hebrew,
-Hiragana,
-Imperial_Aramaic,
-Inherited,
-Inscriptional_Pahlavi,
-Inscriptional_Parthian,
-Javanese,
-Kaithi,
-Kannada,
-Katakana,
-Kayah_Li,
-Kharoshthi,
-Khitan_Small_Script,
-Khmer,
-Khojki,
-Khudawadi,
-Lao,
-Latin,
-Lepcha,
-Limbu,
-Linear_A,
-Linear_B,
-Lisu,
-Lycian,
-Lydian,
-Mahajani,
-Makasar,
-Malayalam,
-Mandaic,
-Manichaean,
-Marchen,
-Masaram_Gondi,
-Medefaidrin,
-Meetei_Mayek,
-Mende_Kikakui,
-Meroitic_Cursive,
-Meroitic_Hieroglyphs,
-Miao,
-Modi,
-Mongolian,
-Mro,
-Multani,
-Myanmar,
-Nabataean,
-Nandinagari,
-New_Tai_Lue,
-Newa,
-Nko,
-Nushu,
-Nyakeng_Puachue_Hmong,
-Ogham,
-Ol_Chiki,
-Old_Hungarian,
-Old_Italic,
-Old_North_Arabian,
-Old_Permic,
-Old_Persian,
-Old_Sogdian,
-Old_South_Arabian,
-Old_Turkic,
-Old_Uyghur,
-Oriya,
-Osage,
-Osmanya,
-Pahawh_Hmong,
-Palmyrene,
-Pau_Cin_Hau,
-Phags_Pa,
-Phoenician,
-Psalter_Pahlavi,
-Rejang,
-Runic,
-Samaritan,
-Saurashtra,
-Sharada,
-Shavian,
-Siddham,
-SignWriting,
-Sinhala,
-Sogdian,
-Sora_Sompeng,
-Soyombo,
-Sundanese,
-Syloti_Nagri,
-Syriac,
-Tagalog,
-Tagbanwa,
-Tai_Le,
-Tai_Tham,
-Tai_Viet,
-Takri,
-Tamil,
-Tangsa,
-Tangut,
-Telugu,
-Thaana,
-Thai,
-Tibetan,
-Tifinagh,
-Tirhuta,
-Toto,
-Ugaritic,
-Vai,
-Vithkuqi,
-Wancho,
-Warang_Citi,
-Yezidi,
-Yi,
-Zanabazar_Square.
+Adlam (Adlm),
+Ahom (Ahom),
+Anatolian_Hieroglyphs (Hluw),
+Arabic (Arab),
+Armenian (Armn),
+Avestan (Avst),
+Balinese (Bali),
+Bamum (Bamu),
+Bassa_Vah (Bass),
+Batak (Batk),
+Bengali (Beng),
+Bhaiksuki (Bhks),
+Bopomofo (Bopo),
+Brahmi (Brah),
+Braille (Brai),
+Buginese (Bugi),
+Buhid (Buhd),
+Canadian_Aboriginal (Cans),
+Carian (Cari),
+Caucasian_Albanian (Aghb),
+Chakma (Cakm),
+Cham (Cham),
+Cherokee (Cher),
+Chorasmian (Chrs),
+Common (Zyyy),
+Coptic (Copt),
+Cuneiform (Xsux),
+Cypriot (Cprt),
+Cypro_Minoan (Cpmn),
+Cyrillic (Cyrl),
+Deseret (Dsrt),
+Devanagari (Deva),
+Dives_Akuru (Diak),
+Dogra (Dogr),
+Duployan (Dupl),
+Egyptian_Hieroglyphs (Egyp),
+Elbasan (Elba),
+Elymaic (Elym),
+Ethiopic (Ethi),
+Georgian (Geor),
+Glagolitic (Glag),
+Gothic (Goth),
+Grantha (Gran),
+Greek (Grek),
+Gujarati (Gujr),
+Gunjala_Gondi (Gong),
+Gurmukhi (Guru),
+Han (Hani),
+Hangul (Hang),
+Hanifi_Rohingya (Rohg),
+Hanunoo (Hano),
+Hatran (Hatr),
+Hebrew (Hebr),
+Hiragana (Hira),
+Imperial_Aramaic (Armi),
+Inherited (Zinh),
+Inscriptional_Pahlavi (Phli),
+Inscriptional_Parthian (Prti),
+Javanese (Java),
+Kaithi (Kthi),
+Kannada (Knda),
+Katakana (Kana),
+Kayah_Li (Kali),
+Kharoshthi (Khar),
+Khitan_Small_Script (Kits),
+Khmer (Khmr),
+Khojki (Khoj),
+Khudawadi (Sind),
+Lao (Laoo),
+Latin (Latn),
+Lepcha (Lepc),
+Limbu (Limb),
+Linear_A (Lina),
+Linear_B (Linb),
+Lisu (Lisu),
+Lycian (Lyci),
+Lydian (Lydi),
+Mahajani (Majh),
+Makasar (Maka),
+Malayalam (Mlym),
+Mandaic (Mand),
+Manichaean (Mani),
+Marchen (Marc),
+Masaram_Gondi (Gonm),
+Medefaidrin (Medf),
+Meetei_Mayek (Mtei),
+Mende_Kikakui (Mend),
+Meroitic_Cursive (Merc),
+Meroitic_Hieroglyphs (Mero),
+Miao (Miao),
+Modi (Modi),
+Mongolian (Mong),
+Mro (Mroo),
+Multani (Mult),
+Myanmar (Mymr),
+Nabataean (Nbar),
+Nandinagari (Nand),
+New_Tai_Lue (Talu),
+Newa (Newa),
+Nko (Nkoo),
+Nushu (Nshu),
+Nyiakeng_Puachue_Hmong (Hmnp),
+Ogham (Ogam),
+Ol_Chiki (Olck),
+Old_Hungarian (Hung),
+Old_Italic (Olck),
+Old_North_Arabian (Narb),
+Old_Permic (Perm),
+Old_Persian (Orkh),
+Old_Sogdian (Sogo),
+Old_South_Arabian (Sarb),
+Old_Turkic (Orkh),
+Old_Uyghur (Ougr),
+Oriya (Orya),
+Osage (Osge),
+Osmanya (Osma),
+Pahawh_Hmong (Hmng),
+Palmyrene (Palm),
+Pau_Cin_Hau (Pauc),
+Phags_Pa (Phag),
+Phoenician (Phnx),
+Psalter_Pahlavi (Phli),
+Rejang (Rjng),
+Runic (Runr),
+Samaritan (Samr),
+Saurashtra (Saur),
+Sharada (Shrd),
+Shavian (Shaw),
+Siddham (Sidd),
+SignWriting (Sgnw),
+Sinhala (Sinh),
+Sogdian (Sogd),
+Sora_Sompeng (Sora),
+Soyombo (Soyo),
+Sundanese (Sund),
+Syloti_Nagri (Sylo),
+Syriac (Syrc),
+Tagalog (Tglg),
+Tagbanwa (Tagb),
+Tai_Le (Tale),
+Tai_Tham (Lana),
+Tai_Viet (Tavt),
+Takri (Takr),
+Tamil (Taml),
+Tangsa (Tngs),
+Tangut (Tang),
+Telugu (Telu),
+Thaana (Thaa),
+Thai (Thai),
+Tibetan (Tibt),
+Tifinagh (Tfng),
+Tirhuta (Tirh),
+Toto (Toto),
+Ugaritic (Ugar),
+Vai (Vaii),
+Vithkuqi (Vith),
+Wancho (Wcho),
+Warang_Citi (Wara),
+Yezidi (Yezi),
+Yi (Yiii),
+Zanabazar_Square (Zanb).
 </P>
 <br><a name="SEC8" href="#TOC1">BIDI_PROPERTIES FOR \p AND \P</a><br>
 <P>
@@ -743,7 +744,7 @@ Cambridge, England.
 </P>
 <br><a name="SEC30" href="#TOC1">REVISION</a><br>
 <P>
-Last updated: 22 December 2021
+Last updated: 28 December 2021
 <br>
 Copyright &copy; 1997-2021 University of Cambridge.
 <br>