twitter_cldr 6.11.4 → 6.12.0

data/resources/shared/territories_containment.yml

@@ -353,6 +353,7 @@
   : 
     :contains: 
       - AX
+      - CQ
       - DK
       - EE
       - FI

data/resources/shared/timezone_regions.yml

@@ -150,7 +150,7 @@
   :region: ST
   :primary: true
 :Africa/Timbuktu:
-  :region: CI
+  :region: ML
   :primary: true
 :Africa/Tripoli:
   :region: LY
@@ -284,6 +284,9 @@
 :America/Chihuahua:
   :region: MX
   :primary: false
+:America/Ciudad_Juarez:
+  :region: MX
+  :primary: false
 :America/Coral_Harbour:
   :region: CA
   :primary: false
@@ -648,7 +651,7 @@
   :region: CA
   :primary: false
 :America/Virgin:
-  :region: TT
+  :region: VI
   :primary: true
 :America/Whitehorse:
   :region: CA
@@ -687,8 +690,8 @@
   :region: AQ
   :primary: false
 :Antarctica/South_Pole:
-  :region: NZ
-  :primary: true
+  :region: AQ
+  :primary: false
 :Antarctica/Syowa:
   :region: AQ
   :primary: false
@@ -1017,7 +1020,7 @@
   :region: FO
   :primary: true
 :Atlantic/Jan_Mayen:
-  :region: 'NO'
+  :region: SJ
   :primary: true
 :Atlantic/Madeira:
   :region: PT
@@ -1226,6 +1229,9 @@
 :Europe/Kirov:
   :region: RU
   :primary: false
+:Europe/Kyiv:
+  :region: UA
+  :primary: true
 :Europe/Lisbon:
   :region: PT
   :primary: true
@@ -1353,7 +1359,7 @@
   :region: HK
   :primary: true
 :Iceland:
-  :region: IS
+  :region: CI
   :primary: true
 :Indian/Antananarivo:
   :region: MG
@@ -1478,6 +1484,9 @@
 :Pacific/Johnston:
   :region: UM
   :primary: false
+:Pacific/Kanton:
+  :region: KI
+  :primary: false
 :Pacific/Kiritimati:
   :region: KI
   :primary: false

data/resources/shared/transforms/Arabic-Latin.yml

@@ -41,6 +41,9 @@
       - "٧ <> 7 ; # ARABIC-INDIC DIGIT SEVEN"
       - "٨ <> 8 ; # ARABIC-INDIC DIGIT EIGHT"
       - "٩ <> 9 ; # ARABIC-INDIC DIGIT NINE"
+      - "؉ <> ‰ ;	# U+0609	ARABIC-INDIC PER MILLE SIGN"
+      - "؊ <> ‱ ;	 # U+060A	ARABIC-INDIC PER TEN THOUSAND SIGN"
+      - "‎۔‎ <> '.' ; 	# U+06D4	ARABIC FULL STOP"
       - "َا<> ā ; # ARABIC FATHA, ARABIC LETTER ALEF"
       - "ُو <> ū ; # ARABIC DAMMA, ARABIC LETTER WAW"
       - "ِي <> ī ; # ARABIC KASRA, ARABIC LETTER YEH"
@@ -98,6 +101,45 @@
       - "چ <> c h $disambig ; # ARABIC LETTER TCHEH"
       - "ڤ <> v ; # ARABIC LETTER VEH"
       - "گ <> g ; # ARABIC LETTER GAF"
+      - ‎ٺ‎>ṭh;
+      - ‎ٿ‎>th;
+      - ‎ٽ‎>ṭ;
+      - ‎ڙ‎>ṛ;
+      - ‎ڦ‎>ph;
+      - ‎ڻ‎>ṇ;
+      - ‎ڱ‎>ṅ;
+      - ‎ڃ‎>ñ;
+      - ‎ڪ‎>k;
+      - ‎ڄ‎>j̈;
+      - ‎ۃ‎>ẖ;
+      - ‎ڳ‎>g̤;
+      - ‎ڍ‎>ḍh;
+      - ‎ڌ‎>dh;
+      - ‎ڏ‎>d̤;
+      - ‎ڊ‎>ḍ;
+      - ‎ڇ‎>ch;
+      - ‎ڀ‎>bh;
+      - ‎ٻ‎>ḇ;
+      - ‎۽‎>'&';
+      - ‎۾‎>'mn';
+      - "‎ھ‎ > ʱ ;"
+      - "‎ں‎ > ◌̃ ;"
+      - "‎ے‎ > ai ;"
+      - "‎ڈ‎ > ḍ ;"
+      - "‎ڑ‎ > ṛ ;"
+      - "‎ٹ‎ > ṭ ;"
+      - "‎ټ‎ > ṯ ;"
+      - "‎ځ‎ > dz ;"
+      - "‎څ‎ > ts ;"
+      - "‎ډ‎ > ḏ ;"
+      - "‎ړ‎ > ṟ ;"
+      - "‎ږ‎ > z͟h ;"
+      - "‎ګ‎ > g ;"
+      - "‎ڼ‎ > ṉ ;"
+      - "‎ۍ‎ > ạy ;"
+      - "‎ې‎ > e ;"
+      - "‎ہ‎ > ḥ ;"
+      - "‎ە‎ > ĥ ;"
       - "| s < c } [eiy];"
       - "| k < c ;"
       - "| i < e ;"

data/resources/shared/transforms/Cyrillic-Latin.yml

@@ -6,7 +6,7 @@
       - und-Latn-t-und-cyrl
     :direction: both
     :rules: 
-      - ":: [Ққ̈Ă-ăĔ-ĕĞ-ğĬ-ĭŎ-ŏŬ-ŭ̆Ѐ-џҐ-ҕҘ-ҙӁ-ӂӐ-ӟӢ-ӧӬ-ӵӸ-ӹḜ-ḝẮ-ặᾰᾸῐῘῠῨ] ;"
+      - ":: [ҺһңҢҰұҮүөӨҚқ̈Ă-ăĔ-ĕĞ-ğĬ-ĭŎ-ŏŬ-ŭ̆Ѐ-џҐ-ҕҘ-ҙӁ-ӂӐ-ӟӢ-ӧӬ-ӵӸ-ӹḜ-ḝẮ-ặᾰᾸῐῘῠῨ] ;"
       - ":: NFD (NFC) ;"
       - "$modprime = ʹ;"
       - "$modprime2 = ʺ;"
@@ -19,6 +19,12 @@
       - "$comma = ̦ ;"
       - "$under = ̱ ;"
       - "$descender = ˌ;"
+      - "$umlaut = \\u0308 ;"
+      - "$macron = \\u0304 ;"
+      - "$breveBelow = \\u032E;"
+      - "$ignoreForCase = [‧[:Mn:][:Me:]] ;"
+      - "$lower = [[:Latin:][:Cyrillic:] & [:Ll:]];"
+      - "$beforeLower = $ignoreForCase * $lower ;"
       - "я <> a  $hat ; # CYRILLIC SMALL LETTER YA"
       - "Я <>  A $hat ; # CYRILLIC CAPITAL LETTER YA"
       - "ч <> c $caron ; # CYRILLIC SMALL LETTER CHE"
@@ -47,6 +53,11 @@
       - "Ћ <> C $acute ; # CYRILLIC CAPITAL LETTER TSHE"
       - "џ <> d $hat ; # CYRILLIC SMALL LETTER DZHE"
       - "Џ <> D $hat ; # CYRILLIC CAPITAL LETTER DZHE"
+      - "х <> kh ; # CYRILLIC SMALL LETTER HA"
+      - "Х } $beforeLower <> Kh ;"
+      - "Х <> KH; # CYRILLIC CAPITAL LETTER HA"
+      - "[Kk] { } [Һһ] > ‧ ;"
+      - "< ‧ ;"
       - "а <> a ; # CYRILLIC SMALL LETTER A"
       - "А <> A ; # CYRILLIC CAPITAL LETTER A"
       - "ә <>  ə ; # CYRILLIC SMALL LETTER SCHWA"
@@ -89,8 +100,12 @@
       - "Л <> L; # CYRILLIC CAPITAL LETTER EL"
       - "м <> m ; # CYRILLIC SMALL LETTER EM"
       - "М <> M ; # CYRILLIC CAPITAL LETTER EM"
+      - "ң <> n$caron ; # CYRILLIC SMALL LETTER EN WITH DESCENDER"
+      - "Ң <> N$caron ; # CYRILLIC CAPITAL LETTER EN WITH DESCENDER"
       - "н <> n ; # CYRILLIC SMALL LETTER EN"
       - "Н <> N; # CYRILLIC CAPITAL LETTER EN"
+      - "ө <> o $umlaut ; # CYRILLIC SMALL LETTER BARRED O"
+      - "Ө <> O $umlaut ; # CYRILLIC CAPITAL LETTER BARRED O"
       - "о <> o ; # CYRILLIC SMALL LETTER O"
       - "О <> O ; # CYRILLIC CAPITAL LETTER O"
       - "п <> p ; # CYRILLIC SMALL LETTER PE"
@@ -101,12 +116,16 @@
       - "С <> S ; # CYRILLIC CAPITAL LETTER ES"
       - "т <> t ; # CYRILLIC SMALL LETTER TE"
       - "Т <> T ; # CYRILLIC CAPITAL LETTER TE"
+      - "ұ <> u$macron ; # CYRILLIC SMALL LETTER STRAIGHT U WITH STROKE"
+      - "Ұ <> U$macron ; # CYRILLIC CAPITAL LETTER STRAIGHT U WITH STROKE"
+      - "ү <> u$umlaut ; # CYRILLIC SMALL LETTER STRAIGHT U"
+      - "Ү <> U$umlaut ; # CYRILLIC CAPITAL LETTER STRAIGHT U"
       - "у <> u ; # CYRILLIC SMALL LETTER U"
       - "У <> U ; # CYRILLIC CAPITAL LETTER U"
       - "ф <> f ; # CYRILLIC SMALL LETTER EF"
       - "Ф <> F ; # CYRILLIC CAPITAL LETTER EF"
-      - "х <> h ; # CYRILLIC SMALL LETTER HA"
-      - "Х <> H; # CYRILLIC CAPITAL LETTER HA"
+      - "һ <> h ; # CYRILLIC SMALL LETTER SHHA"
+      - "Һ <> H ; # CYRILLIC CAPITAL LETTER SHHA"
       - "ц <> c ; # CYRILLIC SMALL LETTER TSE"
       - "Ц <> C; # CYRILLIC CAPITAL LETTER TSE"
       - "Ъ <> $modprime2 $under ; # CYRILLIC CAPITAL LETTER HARD SIGN"
@@ -125,7 +144,7 @@
       - "| Ks < X ;"
       - "| ks < x ;"
       - ":: NFC (NFD) ;"
-      - ":: ( [ˌ̈A-Za-zÀ-ÏÑ-ÖÙ-Ýà-ïñ-öù-ýÿ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƏƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳəʹ-ʺ̀-̂̆-̦̱̇̌̀-́̈́ʹ΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЀЃЌ-ЎЙйѐѓќ-ўӁ-ӂӐ-ӑӖ-ӗḀ-ẙẛẠ-ỹἂ-ἅἊ-Ἅἒ-ἕἚ-Ἕἢ-ἥἪ-Ἥἲ-ἵἺ-Ἵὂ-ὅὊ-Ὅὒ-ὕὛὝὢ-ὥὪ-Ὥὰ-ώᾂ-ᾅᾊ-ᾍᾒ-ᾕᾚ-ᾝᾢ-ᾥᾪ-ᾭᾰᾲᾴᾸᾺ-ΆῂῄῈ-Ή῍-῎ῐῒ-ΐῘῚ-Ί῝-῞ῠῢ-ΰῨῪ-Ύ῭-΅ῲῴῸ-ΏK-Å] ) ;"
+      - ":: ( [‧ˌ̈A-Za-zÀ-ÏÑ-ÖÙ-Ýà-ïñ-öù-ýÿ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƏƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳəʹ-ʺ̀-̂̆-̦̱̇̌̀-́̈́ʹ΅-ΆΈ-ΊΌΎ-ΐά-ΰό-ώϓЀЃЌ-ЎЙйѐѓќ-ўӁ-ӂӐ-ӑӖ-ӗḀ-ẙẛẠ-ỹἂ-ἅἊ-Ἅἒ-ἕἚ-Ἕἢ-ἥἪ-Ἥἲ-ἵἺ-Ἵὂ-ὅὊ-Ὅὒ-ὕὛὝὢ-ὥὪ-Ὥὰ-ώᾂ-ᾅᾊ-ᾍᾒ-ᾕᾚ-ᾝᾢ-ᾥᾪ-ᾭᾰᾲᾴᾸᾺ-ΆῂῄῈ-Ή῍-῎ῐῒ-ΐῘῚ-Ί῝-῞ῠῢ-ΰῨῪ-Ύ῭-΅ῲῴῸ-ΏK-Å] ) ;"
     :source: Cyrl
     :target: Latn
     :variant: ~

data/resources/shared/transforms/Devanagari-InterIndic.yml

@@ -110,6 +110,7 @@
       - "९>\\uE06F;  # DIGIT NINE"
       - "॰>\\uE070;  # Devanagari-InterIndic: ABBREVIATION SIGN"
       - "ॽ>\\uE082;  # Devanagari Glottal Stop"
+      - "ॲ>\\uE084; # https://en.wiktionary.org/wiki/%E0%A5%B2"
     :source: Devanagari
     :target: InterIndic
     :variant: ~

data/resources/shared/transforms/Devanagari-Latin.yml

@@ -6,7 +6,7 @@
       - und-Latn-t-und-deva
     :direction: forward
     :rules: 
-      - "::[ँ-ःऄअ-ह़-्ॐ-॔क़-९ॽ];"
+      - "::[॑ ॒ ॔ ॓ ़ ँ-ः । ॥ ॰ ०-९ ॐ ॲ ऄ-ऋ ॠ ऌ ॡ ऍ-कक़ खख़ गग़ घ-जज़ झ-डड़ ढढ़ ण-फफ़ ब-यय़ र-ह ऽ ॽ ा-ॄ ॢ ॣ ॅ-्];"
       - "::NFD;"
       - "::Devanagari-InterIndic;"
       - "::InterIndic-Latin;"

data/resources/shared/transforms/Greek-Latin.yml

@@ -6,7 +6,7 @@
       - und-Latn-t-und-grek
     :direction: both
     :rules: 
-      - ":: [;µ·ÄËÏÖÜäëïöüÿ-āĒ-ēĪ-īŌ-ōŪ-ūŸǕ-ǜǞ-ǣǬ-ǭȪ-ȭȰ-ȳ̄̈̓-̔͂-ͅͺ;Ά-ΊΌΎ-ΡΣ-ώϐ-ϗϛϝϟϡϣϥϧϩϫϭϯ-ϵϷ-\\u07FBЁЇёїӒ-ӓӚ-ӟӢ-ӧӪ-ӱӴ-ӵӸ-ӹḔ-ḗḠ-ḡḦ-ḧḮ-ḯḸ-ḹṎ-ṓṜ-ṝṺ-ṻẄ-ẅẌ-ẍẗἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼι῁-ῄῆ-ῌ῏-ΐῖ-Ί῟-Ῥῲ-ῴῶ-ῼΩϹ] ;"
+      - ":: [΄´;µ·ÄËÏÖÜäëïöüÿ-āĒ-ēĪ-īŌ-ōŪ-ūŸǕ-ǜǞ-ǣǬ-ǭȪ-ȭȰ-ȳ̄̈̓-̔͂-ͅͺ;Ά-ΊΌΎ-ΡΣ-ώϐ-ϗϛϝϟϡϣϥϧϩϫϭϯ-ϵϷ-\\u07FBЁЇёїӒ-ӓӚ-ӟӢ-ӧӪ-ӱӴ-ӵӸ-ӹḔ-ḗḠ-ḡḦ-ḧḮ-ḯḸ-ḹṎ-ṓṜ-ṝṺ-ṻẄ-ẅẌ-ẍẗἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼι῁-ῄῆ-ῌ῏-ΐῖ-Ί῟-Ῥῲ-ῴῶ-ῼΩϹ] ;"
       - ":: NFD (NFC) ;"
       - "$lower = [[:latin:][:greek:] & [:Ll:]];"
       - "$glower = [[:greek:] & [:Ll:]];"
@@ -40,6 +40,7 @@
       - "\\? <> \\? $under ;"
       - "\\; <> \\? ;"
       - "· <> \\: ;"
+      - "΄ <> ´;"
       - "͂ <> ̂ ;"
       - "$accent_minus = [[$accent]-[$iotasub$macron]];"
       - "Α } $accent_minus * $iotasub > | Α $macron ;"

data/resources/shared/transforms/Han-Latin.yml

@@ -21,7 +21,7 @@
       - "[㛺㞄㫨㸩䀂䅖䢿侒媕安峖庵桉氨痷盦盫腤菴萻葊蓭誝諳谙鞌鞍韽馣鵪鶕鹌𠽪𡯏𢰍𣚖𧩸𧫥𧫧𧮍𩽾𪁟𪘒𬸝]>ān;"
       - "[䜙儑啽玵雸𡪁𡽜𣵱]>án;"
       - "[㜝㽢俺唵垵埯揞罯銨铵隌𠉬𤃷𤜁𥦍𦺽𩅝𩈴]>ǎn;"
-      - "[㟁㱘䅁䬓䮗䯥堓婩岸按晻暗案洝犴胺荌豻貋錌闇鮟黯𠰑𡎑𡪙𡹼𣆛𣣚𣽥𤞿𤟉𥏮𥳬𧖮𨲊𩓤𩭢𩹎𫗊𬮴𬴁]>àn;"
+      - "[㟁㱘䅁䬓䮗䯥堓婩岸按晻暗案洝犴胺荌豻貋錌闇鮟黯鿷𠰑𡎑𡪙𡹼𣆛𣣚𣽥𤞿𤟉𥏮𥳬𧖮𨲊𩓤𩭢𩹎𫗊𬮴𬴁]>àn;"
       - "[肮骯𠵫𡕉]>āng;"
       - "[㭿䀚䒢䩕䭹卬岇昂昻𤭒𩑝𩔘]>áng;"
       - "[䇦䭺𦫫]>ǎng;"
@@ -271,7 +271,7 @@
       - "[㫀㴿奵嵿濎薡鐤頂顶鼎鼑𢑅𣆍𤐣𤛙𧇷𩠑𪔂𰛽𰾸]>dǐng;"
       - "[㝎啶定忊椗矴碇碠磸聢腚萣蝊訂订鋌錠铤锭顁飣饤𣢳𥇓𥯢𥳰𥸧𦩘𩜦𩠆𩸎𬱫]>dìng;"
       - "[丟丢銩铥𠲍𢒝]>diū;"
-      - "[㚵䍶䰤东倲冬咚埬娻岽崠崬徚昸東氡氭涷笗苳菄蝀鮗鯟鶇鶫鸫鼕𢔅𢛔𣱝𤤮𤦪𤲚𤷆𧓕𧯾𧲴𧼓𨩧𨿢𩂓𩜍𩣳𪣆𫹼𬟽𰎏𰛒]>dōng;"
+      - "[㚵䍶䰤东倲冬咚埬娻岽崠崬徚昸東氡氭涷笗苳菄蝀鮗鯟鶇鶫鸫鼕鿴𢔅𢛔𣱝𤤮𤦪𤲚𤷆𧓕𧯾𧲴𧼓𨩧𨿢𩂓𩜍𩣳𪣆𫹼𬟽𰎏𰛒]>dōng;"
       - "[㖦㨂䂢䵔墥嬞懂箽董蕫諌𣿅𥳘𦡂𧄓𧳣𪐈𰇎]>dǒng;"
       - "[㑈㓊㢥㼯䞒侗働冻凍动動垌姛峒恫戙挏栋棟洞湩硐絧胨胴腖迵霘駧𠄉𢳾𥫎𧡍𧽿𩐤𩐵𩧲𩭩𪔦𫄡𫢙𬢈]>dòng;"
       - "[㨮兜兠吺唗橷篼蔸都𠍄𠱑𠾇𣂮𣘛𤝈𤾒𥆖𥉝𦄓𦆘𧡸𧯠𧯤𨁋𩔡𩮷𩳈𰴛]>dōu;"
@@ -595,7 +595,7 @@
       - "[㛦㧛㨫㩜㰖䌫囕壈嬾孄孏懒懶揽擥攬榄欖浨漤灠爦纜缆罱覧覽览醂顲𠓭𡒄𡓔𡽳𤑸𤣟𥦝𧮤𨎹𨣸𩟺𫝮𫶊𰈆𰌙𰜐]>lǎn;"
       - "[㜮㱫䃹嚂滥濫烂燗爁爛爤瓓糷鑭𢒞𢹙𤂺𤃨𥗺𧸦𨣨𩉀𫱕𬊶𬎑𬒇𬥾𰈓𰫖𰼏]>làn;"
       - "[啷]>lāng;"
-      - "[㝗㟍㢃㱢㾿䆡䡙䯖䱶勆嫏廊斏桹榔欴狼琅瑯硠稂筤艆蓈蜋螂躴郎郒郞鋃鎯锒阆駺𢽂𥍫𥧫𦵧𨞿𨱍𩛡𩷕𪁜𫗨𬴀𬸏]>láng;"
+      - "[㝗㟍㢃㱢㾿䆡䡙䯖䱶勆嫏廊斏桹榔欴狼琅瑯硠稂筤艆蓈蜋螂躴郎郒郞鋃鎯锒阆駺鿶𢽂𥍫𥧫𦵧𨞿𨱍𩛡𩷕𪁜𫗨𬴀𬸏]>láng;"
       - "[㓪㙟㮾塱朖朗朤樃烺蓢誏𠻴𣊧𥇑𧚅𬣼]>lǎng;"
       - "[㫰䍚䕞埌崀浪莨蒗閬𠺘𢳑𣻡𦺫𧻴𨶗𩲒𩳤]>làng;"
       - "[唥]>lang;"
@@ -683,7 +683,7 @@
       - "[亇吗嗎嘛嫲]>ma;"
       - "[㜥㦟䁲䚑䨪埋薶霾𢙑𢠼𨤢𩍃𫰨]>mái;"
       - "[买嘪荬蕒買鷶𠿆𧹒𪡃𱉳]>mǎi;"
-      - "[⻨䘑䜕䨫䮮佅劢勱卖売脈脉衇賣迈邁霡霢麥麦鿏𥇯𥌚𦏢𦙻𧱘𩈗𩊍𪄳𪒪𬑙]>mài;"
+      - "[⻨䘑䜕䨫䮮佅劢勱卖売脈脉衇賣迈邁霡霢麥麦鿏鿺𥇯𥌚𦏢𦙻𧱘𩈗𩊍𪄳𪒪𬑙]>mài;"
       - "[嫚颟]>mān;"
       - "[㒼㙢䅼䊡䐽䒥䛲䟂䯶䰋僈姏悗慲樠瞒瞞蛮蠻謾谩蹒鞔顢饅馒鬗鬘鰻鳗𢦈𣗊𤜘𥊑𥧭𥲑𦔔𧜞𧱼𨲛𨲾𩆓𩮉𪈿𪍩𪑪𰊟𰒆𰯎𱆆]>mán;"
       - "[㛧䜱屘満满滿睌矕螨蟎襔鏋𥬈𥲈𦎌𧆏𧖵𩈦𩛎𬲴𰥠]>mǎn;"
@@ -905,7 +905,7 @@
       - "[拤𡘧]>qiá;"
       - "[峠跒酠鞐]>qiǎ;"
       - "[㓞㓣㓤㡊䁍䂒䨐䯊䶝冾圶帢恰愘殎洽硈髂𠕣𠜤𠝘𠳌𢼣𣁴𣨄𤫶𤵹𥎸𥦞𥴭𦝣𦸉𧩶𩥌𩩱𩮁𩷻𪘺𫈰]>qià;"
-      - "[㗔㩃㩷㪠䀒䇂䉦䙴䞿仟佥僉兛千圱圲奷婜孅孯岍悭愆慳扦拪掔搴撁攐攑攓杄檶櫏欦汘汧牵牽瓩竏签箞簽籤粁臤芊茾蚈褰諐謙谦谸迁遷釺鈆鉛钎铅阡雃韆顅騫骞鬜鬝鵮鹐𠑲𠔺𠠃𠬾𢃥𢋔𢌍𢍱𢜩𢧥𣘝𣟋𣢬𣢲𤠿𤿷𥏥𥜴𥱺𥲢𦖎𧘜𧛓𧟑𧢞𧮮𧲀𧽐𨐋𨐩𨓲𨝍𨦄𨨘𩋆𩨓𩪢𪇇𪉻𫓪𫖶𫣛𫽥𰔲𰗬𱁶𱆀𱆁]>qiān;"
+      - "[㗔㩃㩷㪠䀒䇂䉦䙴䞿仟佥僉兛千圱圲奷婜孅孯岍悭愆慳扦拪掔搴撁攐攑攓杄檶櫏欦汘汧牵牽瓩竏签箞簽籤粁臤芊茾蚈褰諐謙谦谸迁遷釺鈆鉛钎铅阡雃韆顅騫骞鬜鬝鵮鹐𠑲𠔺𠠃𠬾𢃥𢋔𢌍𢍱𢜩𢧥𣘝𣟋𣢬𣢲𤠿𤿷𥏥𥜴𥱺𥲢𦖎𧘜𧛓𧟑𧢞𧮮𧲀𧽐𨐋𨐩𨓲𨝍𨦄𨨘𩋆𩨓𩪢𪇇𪉻𫓪𫖶𫣛𫽥𰀡𰔲𰗬𱁶𱆀𱆁]>qiān;"
       - "[㦮㨜㩮㸫䁮䈤䕭䖍乾仱偂前墘媊岒忴扲拑掮揵榩橬歬潛潜濳灊箝羬蕁虔軡鈐鉗銭錢钤钱钳靬騚騝鰬黔黚𠀼𠢍𠷁𢁮𣖳𥔮𥮒𥴤𥷪𦂒𦴑𦼓𧃑𧣑𨜻𨥞𨱫𨺩𨽨𩨃𩨊𩬚𪈇𱈉]>qián;"
       - "[㦿㧄㹂䇜䭤凵嗛嵰槏浅淺繾缱肷脥膁蜸譴谴遣鑓𠊭𠋵𠳋𡒌𢮄𣍰𣓅𥦃𥧬𥳐𦅋𧥛𧪯𨗦𨺫𩑳𩒣𪘦𬙃𰲮]>qiǎn;"
       - "[㐸㜞㟻㯠䈴䊴䑶䥅䪈䵖䵛俔倩傔儙刋堑塹壍嬱嵌悓慊棈椠槧欠歉皘篏篟綪縴芡茜蒨蔳輤鰜𢂺𢃘𣢖𣹥𧚫𧮽𨰂𬘬𰊢𰌆𰬮𰺉]>qiàn;"
@@ -955,7 +955,7 @@
       - "[㪊㿏䭽宭帬羣群裙裠𣀄𤛭𤸷𨞗]>qún;"
       - "[𦃢]>qǔn;"
       - "[㜣㲯㸐㾆䔳䕼䖄䫇䳿呥嘫然燃繎肰蚦蚺衻袇袡髥髯𠊌𠤀𠯍𡖝𢓒𣰦𤙼𤡮𤱋𥳚𦫉𪓘𪓚𪚮𬊾𬙇𬝴𰚪𱍄]>rán;"
-      - "[㒄㚩㿵䎃䒣䣸䤡冄冉姌媣染橪珃苒蒅𠱞𡜉𡜫𤲗𥀭𥬕𨹌𩃵𩢡𩧬𩶎𫝜]>rǎn;"
+      - "[㒄㚩㿵䎃䒣䣸䤡冄冉姌媣染橪珃苒蒅𠱞𡜉𡜫𤲗𥀭𥬕𨹌𩃵𩢡𩧬𩶎]>rǎn;"
       - "[𥣺]>ràn;"
       - "[䉴儴勷瀼獽瓤禳穣穰蘘躟鬤𣰶𤬥𤰂𧟄𨟚𩆶]>ráng;"
       - "[䑋嚷壌壤攘爙纕𣩽𤅑𥗝𨏛]>rǎng;"
@@ -1280,7 +1280,7 @@
       - "[㔵㧋㾌䠣咺晅烜癣癬选選顈𢈋𣉖𣎓𥥾𥶷𦌔𧡚𧡢𩘒]>xuǎn;"
       - "[㧦㯀㳙䀏䃠䍗䍻䝮䧎䩙䩰怰昡楥楦泫渲炫琄眩眴碹絢縼繏绚蔙衒袨讂贙鉉鏇铉镟鞙颴𠵷𢂄𢳄𤂿𥌭𦈝𦛔𧾆𨁁𨊼𨹆𩃚𩉥𩋢𩋫𩑹𪍧𬱽𰬵𰶍𰷮]>xuàn;"
       - "[㗾㻡削疶蒆薛辥辪靴鞾𢪎𥄒𪃅𫖇]>xuē;"
-      - "[㖸㰒㶅㿱䋉䱑乴壆学學岤峃嶨斈泶澩燢穴茓袕觷踅雤鷽鸴𢯳𢼺𥀣𦥯𧉢𧸗𰴣]>xué;"
+      - "[㖸㰒㶅㿱䋉䱑乴壆学學岤峃嶨斈泶澩燢穴茓袕觷踅雤鷽鸴𢯳𢼺𥀣𦥯𧉢𧸗𰃮𰴣]>xué;"
       - "[䨮樰膤艝轌雪鱈鳕]>xuě;"
       - "[㕰㞽䆝䆷䎀䒸䛎䤕䦑䫼䬂䭥吷坹桖瀥狘血謔谑趐𣧌𣧡𣧵𣪨𣺭𤀰𥄎𥄴𥅧𦐍𦰾𧔗𧮞𨑣𨭁𩌊𩖱𩖶𬱷𬱸]>xuè;"
       - "[䗼䠝䵫勋勛勲勳嚑坃埙塤壎壦曛焄熏燻爋獯矄窨纁臐蔒薫薰蘍醺駨𡑎𡺕𤑕𦘶𧰣𩪱𫄸𫭯]>xūn;"
@@ -1321,7 +1321,7 @@
       - "[㡕䁐䓨䣐䦫䧹䪯䴍偀啨嘤嚶婴媖嫈嬰孆孾应応愥應撄攖朠桜樱櫻渶煐珱瑛璎瓔甇甖碤礯緓纓绬缨罂罃罌膺英莺蘡蝧蠳褮譍譻賏軈鍈鑍锳霙韺鴬鶑鶧鶯鷪鷹鸎鸚鹦鹰𠠜𠮳𠸄𡎘𢄋𤜉𤣎𤭫𥌽𥌾𥍼𥐑𦔃𦦿𧓀𧕄𧢛𧮆𧯀𨍞𨟙𨵛𩄪𩹅𪧀𫝭𬢯𬤚𬸕𮐨𰌀𰡢𰢤𰳗]>yīng;"
       - "[㨕㵬㶈㹚㿘䁝䃷䊔䑉䕦䤰僌営塋嬴攍楹櫿溁溋滢潆濙濚濴瀅瀛瀠瀯瀴灐灜熒營瑩盁盈籝籯縈茔荧莹萤-萦萾蓥藀蛍蝇蝿螢蠅覮謍贏赢迎鎣𡃅𡺡𢥏𣲜𤟣𤹜𦖽𦝚𧅋𧕍𧭓𨜏𩸥𩻷𰜳𰝅𰥞𰪣𰴯]>yíng;"
       - "[㢍㲟㹵䀴䚆䨍䬬䭊䭗䭘巊廮影摬梬浧潁瘿癭矨穎郢鐛頴颍颕颖𠝟𡂚𣟤𣤵𤁽𤌌𥏎𦡺𦢆𨠸𩖍𩘑𩳍𪊵𪩎𫷾𬑏𬢑𬳑𱃵]>yǐng;"
-      - "[㑞䙬䤝䵴噟媵映暎硬膡鞕鱦𠊶𡀘𡁊𡄖𢣙𣈣𣋋𤇾𤹥𥚿𦩩𨪄𩋹𫜙𭈉𱇸]>yìng;"
+      - "[㑞䙬䤝䵴噟媵映暎硬膡鞕鱦𠊶𡀘𡁊𡄖𢣙𣈣𣋋𤇾𤹥𥚿𦩩𨪄𩋹𫇦𫜙𭈉𱇸]>yìng;"
       - "[哟唷喲]>yō;"
       - "[㐯㜉㟾㴩㻾㽫䗸䧡佣傭嗈噰墉壅嫞庸廱慵拥擁槦滽澭灉牅痈癕癰臃邕郺鄘鏞镛雍雝饔鱅鳙鷛𠆌𢀍𢢓𢧳𣋿𤛑𥑿𥧱𦃽𦤘𧝸𧴄𧴗𩍓𩟀𩟷𪄉𪇛𪪝𬳓𱊤]>yōng;"
       - "[㝘䗤喁揘顒颙鰫𧲤𧺸𨦡𩔔𩤛𪅟𫚦𰽽]>yóng;"
@@ -1411,7 +1411,7 @@
       - "[㩼㯄㲍㴯㸟㽻䓋䓜䓡䝷䞠䟡䣽䧴䵹之倁卮吱坧巵戠搘支枝栀梔椥榰汁汥泜疷知祗祬禔秓秖秪稙綕織织肢胑胝脂臸芝蘵蜘衼隻馶鳷鴲鼅𠦧𠰅𢎈𤵋𤽁𥃫𥇭𥘡𥝑𥝮𥻬𥾣𦏤𦝔𦭜𦯫𦴀𧌔𧐉𧱒𧹛𧽦𨌌𨕕𨜎𨟾𨢮𩍲𩍵𩙾𪂅𪉆𪒊𫛛𬘨𰱲𱌄]>zhī;"
       - "[㙷㜼㥀䐈䟈䵂侄値值嗭埴執墌妷姪嬂慹执摭植樴殖淔漐犆瓡直禃絷縶聀职職膱蟙跖踯蹠躑軄釞鉄馽𡁉𡂣𡈊𡌴𡏀𡖻𡰹𡸜𢃜𣖭𣖿𣳀𣽚𤃲𥏅𥮖𦳮𧀿𧃐𧏸𧓸𧾂𨂂𨤱𨼓𩯈𪗨𪙹𰑔𰛣𱅁𱋪]>zhí;"
       - "[㕄㡳㡶㫑㮹㲛䅩䇛䛗䤠䳅凪劧只咫址坁夂帋徵怾恉扺抧指旨枳止汦沚洔淽疻砋祉紙纸芷茋藢衹襧訨趾軹轵酯阯黹𠮡𠼠𡙑𡱔𢇨𢛍𢰙𢷸𢽃𢽗𢾫𣔐𣖌𣚠𣲵𤶓𤸓𥒗𥔊𦐖𦰘𧊙𧛢𧜚𧝉𧠴𧸅𧸕𨎌𨬚𨰛𨵂𩬺𪑜𫐋𫟞𰽠𱉙]>zhǐ;"
-      - "[㗌㗧㘉㛿㜱㝂㣥㨁㨖㴛㿃䄺䆈䇧䉅䉜䎺䏯䐭䑇䓌䕌䘭䚦䚳䝰䞃䡹䥍䦯䩢䬹䭁䱃䱥䲀乿俧偫傂儨制劕厔垁墆娡寘峙崻帙帜幟庢庤廌彘徏徝志忮憄懥懫扻挃挚掷搱摯擲擳旘晊智柣栉桎梽楖櫍櫛治洷滍滞滯潌瀄炙熫狾猘瓆畤疐痔痣礩祑秩秲秷稚稺穉窒筫紩緻置翐膣至致芖蛭螲袟袠製覟觗觯觶誌豑豒豸貭質贄质贽跱踬躓軽輊轾迣郅銍鋕鑕铚锧阤陟隲雉駤騭騺驇骘鯯鴙鷙鸷𠊤𠊷𠋤𠍜𠓶𠘖𠚅𡀹𡂒𡍶𡏚𡑘𡖧𡠗𡠹𡮞𡽆𢄢𢄱𢅁𢊁𢍧𢐂𢕞𢖇𢖿𢙺𢚨𢡒𢧤𢯶𢴠𢴧𢻙𣗻𣥰𣨋𤆒𤓕𤖞𤛱𤞂𤞌𤦄𤦮𤧜𤴛𤴟𤴢𤿙𥇕𥍭𥎹𥏄𥏊𥏰𥏷𥒓𥠈𥠽𥣮𥭡𥴒𥹩𥿮𦃘𦛧𦜋𦟔𦤻𦥎-𦥐𦭮𦯯𧙁𧠫𧣭𧣾𧤡𧨰𧫡𧸲𨁷𨃯𨆧𨎉𨑨𨒉𨖹𨟊𨡐𨧵𨫔𨻆𨿛𩊝𩊴𩋩𩧄𩷓𩹈𩻼𪁊𪁓𪁩𪏀𪗻𫔵𫘠𫞢𫟬𫪪𬃊𬘽𬢌𬣛𬺁𮉢𰊂𰑬𰓜𰛤𰧉𰬫𰵧𱀑𱃸𱅊𱇹𱉛]>zhì;"
+      - "[㗌㗧㘉㛿㜱㝂㣥㨁㨖㴛㿃䄺䆈䇧䉅䉜䎺䏯䐭䑇䓌䕌䘭䚦䚳䝰䞃䡹䥍䦯䩢䬹䭁䱃䱥䲀乿俧偫傂儨制劕厔垁墆娡寘峙崻帙帜幟庢庤廌彘徏徝志忮憄懥懫扻挃挚掷搱摯擲擳旘晊智柣栉桎梽楖櫍櫛治洷滍滞滯潌瀄炙熫狾猘瓆畤疐痔痣礩祑秩秲秷稚稺穉窒筫紩緻置翐膣至致芖蛭螲袟袠製覟觗觯觶誌豑豒豸貭質贄质贽跱踬躓軽輊轾迣郅銍鋕鑕铚锧阤陟隲雉駤騭騺驇骘鯯鴙鷙鸷鿵𠊤𠊷𠋤𠍜𠓶𠘖𠚅𡀹𡂒𡍶𡏚𡑘𡖧𡠗𡠹𡮞𡽆𢄢𢄱𢅁𢊁𢍧𢐂𢕞𢖇𢖿𢙺𢚨𢡒𢧤𢯶𢴠𢴧𢻙𣗻𣥰𣨋𤆒𤓕𤖞𤛱𤞂𤞌𤦄𤦮𤧜𤴛𤴟𤴢𤿙𥇕𥍭𥎹𥏄𥏊𥏰𥏷𥒓𥠈𥠽𥣮𥭡𥴒𥹩𥿮𦃘𦛧𦜋𦟔𦤻𦥎-𦥐𦭮𦯯𧙁𧠫𧣭𧣾𧤡𧨰𧫡𧸲𨁷𨃯𨆧𨎉𨑨𨒉𨖹𨟊𨡐𨧵𨫔𨻆𨿛𩊝𩊴𩋩𩧄𩷓𩹈𩻼𪁊𪁓𪁩𪏀𪗻𫔵𫘠𫞢𫟬𫪪𬃊𬘽𬢌𬣛𬺁𮉢𰊂𰑬𰓜𰛤𰧉𰬫𰵧𱀑𱃸𱅊𱇹𱉛]>zhì;"
       - "[徔]>zhi;"
       - "[㹣䇗䈺䝦中伀刣妐幒彸忠柊汷泈炂盅籦終终舯蔠螤螽衳衷蹱鈡銿鍾鐘钟锺鴤鼨𠛀𡖌𢁷𢃭𢨱𣷡𤝅𤯚𥗦𥷈𦉂𦬕𧆼𧑆𨳗𩅞𩅧𰪊𰱛]>zhōng;"
       - "[㣫冢喠塚塜尰歱煄瘇种種穜肿腫踵𠊥𡰒𡻑𣹞𤺄]>zhǒng;"

data/resources/shared/transforms/Han-Spacedhan.yml

@@ -4,9 +4,26 @@
     :aliases: ~
     :direction: both
     :rules: 
-      - ":: [[㆒-㆟㈠-㉇㊀-㊰㋀-㋋㍘-㍰㍻-㍿㏠-㏾ 🈐-🈒🈔-🈺🉀-🉈🉐🉑][:ideographic:][:sc=han:]] nfkc;"
+      - ":: [[、。々《-』〜・㆒-㆟㈠-㉇㊀-㊰㋀-㋋ ㍘-㍰㍻-㍿㏠-㏾🈐-🈒🈔-🈺🉀-🉈🉐🉑][:ideographic:][:sc=han:]] nfkc;"
       - ":: fullwidth-halfwidth;"
       - "｡ > '.';"
+      - "。> '.';"
+      - "、> ',';"
+      - "､> ',';"
+      - "《> '«';"
+      - "》> '»';"
+      - "〈 > '‹';"
+      - "〉> '›';"
+      - "「> '‘';"
+      - "」> '’';"
+      - "｢> '‘';"
+      - "｣> '’';"
+      - "『> '“';"
+      - "』> '”';"
+      - "・> '‧';"
+      - "･ > '‧';"
+      - "々> '⓶';"
+      - "〜> '~';"
       - "$terminalPunct = [\\.\\,\\:\\;\\?\\!．，：？！｡、；[:Pe:][:Pf:]];"
       - "$initialPunct = [:Ps:][:Pi:];"
       - "[[:Ideographic:] $terminalPunct] {} [:Letter:] > ' ' ;"

data/resources/shared/transforms/Hebrew-Latin.yml

@@ -6,8 +6,11 @@
       - und-Latn-t-und-hebr
     :direction: both
     :rules: 
-      - ":: [[:Hebrew:] [:^ccc=0:] [ְ-ֹֻ-ּׁ-ׂℵ-ℸֿ̄] - [ֽ]] ;"
+      - ":: [[־׳״][:Hebrew:] [:^ccc=0:] [ְ-ֹֻ-ּׁ-ׂℵ-ℸֿ̄] - [ֽ]] ;"
       - ":: nfkd (nfc) ;"
+      - "׳ <> '′';"
+      - "״ <> '″';"
+      - "־ <> '-';"
       - "$letterAfter = [:M:]* [:L:] ;"
       - "ח <> ẖ ;"
       - "צ <> ẕ } $letterAfter;"
@@ -69,7 +72,7 @@
       - "כס < x ;"
       - ":: (lower);"
       - ":: nfc (nfd) ;"
-      - ":: ([[:Latin:] [:^ccc=0:] [ʻ-ʼ̀-̧̱̂̇̌̀-́    ̄ ]]);"
+      - ":: ([[-′″][:Latin:] [:^ccc=0:] [ʻ-ʼ̀-̧̱̂̇̌̀-́    ̄ ]]);"
     :source: Hebr
     :target: Latn
     :variant: ~

data/resources/shared/transforms/InterIndic-Latin.yml

@@ -435,7 +435,7 @@
       - $kta>ṯ;
       - $danda>'.';
       - $doubleDanda>'.';
-      - "\\uE070>;       # ABBREVIATION SIGN"
+      - "\\uE070>'.';       # ABBREVIATION SIGN"
       - "\\uE071}$x>ra;"
       - \uE071$virama>r;
       - \uE071>ra;
@@ -457,6 +457,9 @@
       - "\\uE07F>;       # URA"
       - "\\uE080>;       # EK ONKAR"
       - "\\uE004>;       # DEVANAGARI VOWEL SIGN SHORT A"
+      - "$virama>; # remove remaining viramas"
+      - "$nukta>\\u0323 ;  # combining dot below"
+      - "\\uE084>æ;       # DEVANAGARI VOWEL SIGN SHORT A"
     :source: InterIndic
     :target: Latin
     :variant: ~