cldr-transforms 46.0.0 → 47.0.0-BETA2

package/LICENSE

@@ -2,7 +2,7 @@ UNICODE LICENSE V3
 
 COPYRIGHT AND PERMISSION NOTICE
 
-Copyright © 2004-2024 Unicode, Inc.
+Copyright © 2004-2025 Unicode, Inc.
 
 NOTICE TO USER: Carefully read the following legal agreement. BY
 DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING DATA FILES, AND/OR

package/README.md

@@ -19,7 +19,7 @@ the data contained here, please file a new ticket at [Unicode Jira](https://unic
 
 ## License
 
-Copyright © 1991-2024 Unicode, Inc.
+Copyright © 1991-2025 Unicode, Inc.
 [Terms of Use](http://www.unicode.org/copyright.html)
 
 SPDX-License-Identifier: Unicode-3.0

package/bower.json

@@ -1,8 +1,8 @@
 {
   "name": "cldr-transforms",
-  "version": "46.0.0",
+  "version": "47.0.0-BETA2",
   "dependencies": {
-    "cldr-core": "46.0.0"
+    "cldr-core": "47.0.0-BETA2"
   },
   "main": "transforms/**/*.json",
   "ignore": [

package/package.json

@@ -1,8 +1,8 @@
 {
   "name": "cldr-transforms",
-  "version": "46.0.0",
+  "version": "47.0.0-BETA2",
   "peerDependencies": {
-    "cldr-core": "46.0.0"
+    "cldr-core": "47.0.0-BETA2"
   },
   "description": "Transform data",
   "homepage": "https://cldr.unicode.org",
@@ -24,6 +24,6 @@
   },
   "license": "Unicode-3.0",
   "bugs": "https://cldr.unicode.org/index/bug-reports#TOC-Filing-a-Ticket",
-  "cldrVersion": "46",
+  "cldrVersion": "47",
   "unicodeVersion": "16.0.0"
 }

package/transforms/Arabic-Latin-BGN.txt

@@ -14,7 +14,7 @@
 #
 # MINIMAL FILTER: Arabic-Latin
 #
-:: [[:arabic:][:block=ARABIC:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهوىيًٌٍَُِّْ٠١٢٣٤٥٦٧٨٩ٱ]] ;
+:: [[:Arabic:][:Block=Arabic:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهوىيًٌٍَُِّْ٠١٢٣٤٥٦٧٨٩ٱ]] ;
 :: NFKD (NFC) ;
 #
 #

package/transforms/Arabic-Latin.txt

@@ -10,7 +10,7 @@
 # Does *not* do assimilation of "al", nor hyphenation.
 # While it could be done, we need to determine whether a prefix "al" could
 # occur other than as the definite article (since no space is used).
-:: [[:Arabic:][:block=ARABIC:][‎ⁿ،؛؟ـً-ٕ٠-٬۰-۹﷼ښ][\u0611\u0670]] ;
+:: [[:Arabic:][:Block=Arabic:][‎ⁿ،؛؟ـً-ٕ٠-٬۰-۹﷼ښ][\u0611\u0670]] ;
 :: NFKD (NFC);
 $disambig =  ̱ ;
 $disambig2 =  ̰ ;

package/transforms/Bengali-Latin.txt

@@ -1,4 +1,4 @@
-::[[:script=bengali:][।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ]];
+::[[:Script=Bengali:][।-॥ঁ-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ়-ৄে-ৈো-্ৗড়-ঢ়য়-ৣ০-৺ৎ]];
 ::NFD;
 ::Bengali-InterIndic;
 ::InterIndic-Latin;

package/transforms/Cyrillic-Latin.txt

@@ -2,7 +2,7 @@
 # Should add variants for Russian-English, Russian-German
 # Those can use this as a base, and then remap cases
 # like a $hat to ya or ja.
-# :: [\u0000-\u007E ʹ ʺ [:Cyrillic:] [:Latin:] [:nonspacing mark:]] ;
+# :: [\u0000-\u007E ʹ ʺ [:Cyrillic:] [:Latin:] [:Nonspacing_Mark:]] ;
 ### WARNING, ̈ must be added to the generated filters, in both directions ###
 # MINIMAL FILTER
 # Cyrillic-Latin
@@ -267,12 +267,12 @@ $ignore = [[:Mark:]''] * ;
 | K ← Q ;
 | u ← w ;
 | U ← W ;
-| KS ← X } $ignore [:UppercaseLetter:] ;
-| KS ← [:UppercaseLetter:] $ignore { X ;
+| KS ← X } $ignore [:Uppercase_Letter:] ;
+| KS ← [:Uppercase_Letter:] $ignore { X ;
 | Ks ← X ;
 | ks ← x ;
 :: NFC (NFD) ;
 # note: a global filter is more efficient, but MUST include all source chars!!
-# :: ([\u0000-\u007E ʹ ʺ [:Cyrillic:] [:Latin:] [:nonspacing mark:] ‧]);
+# :: ([\u0000-\u007E ʹ ʺ [:Cyrillic:] [:Latin:] [:Nonspacing_Mark:] ‧]);
 # MINIMAL FILTER: Latin-Cyrillic
 :: ( [ḫḪhH‧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] ) ;

package/transforms/Greek-Latin.txt

@@ -1,5 +1,5 @@
 # Rules are predicated on running NFD first, and NFC afterwards
-# :: [\u0000-\u007F \u0370-Ͽ [:Greek:] [:nonspacing mark:]] ;
+# :: [\u0000-\u007F \u0370-Ͽ [:Greek:] [:Nonspacing_Mark:]] ;
 # MINIMAL FILTER GENERATED FOR: Greek-Latin
 :: [΄´;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) ;
@@ -12,9 +12,9 @@
 # ὨΣ ὩΣ ὪΣ ὫΣ
 # Ạ, ạ, Ẹ, ẹ, Ọ, ọ
 # Useful variables
-$lower = [[:latin:][:greek:] & [:Ll:]];
-$glower = [[:greek:] & [:Ll:]];
-$upper = [[:latin:][:greek:] & [:Lu:]] ;
+$lower = [[:Latin:][:Greek:] & [:Ll:]];
+$glower = [[:Greek:] & [:Ll:]];
+$upper = [[:Latin:][:Greek:] & [:Lu:]] ;
 $accent = [:M:] ;
 # NOTE: restrict to just the Greek & Latin accents that we care about
 # TODO: broaden out once interation is fixed
@@ -220,8 +220,8 @@ $ignore = [[:Mark:]''] * ;
 | B ← W  } $vowel ;
 | U ← V ;
 | U ← W ;
-$rough } $ignore [:UppercaseLetter:] → H ;
-$ignore [:UppercaseLetter:] { $rough → H ;
+$rough } $ignore [:Uppercase_Letter:] → H ;
+$ignore [:Uppercase_Letter:] { $rough → H ;
 $rough ← H ;
 $rough ↔ h ;
 # Completeness for Greek
@@ -243,7 +243,7 @@ $rough ↔ h ;
 ← [Ππ] { \' } [Ss] ;
 ← [Νν] { \' } $egammaLike ;
 ::NFC (NFD) ;
-# ([\u0000-\u007F [:Latin:] [:Greek:] [:nonspacing mark:]]) ;
-# ([\u0000-\u007F · [:Latin:] [:nonspacing mark:]]) ;
+# ([\u0000-\u007F [:Latin:] [:Greek:] [:Nonspacing_Mark:]]) ;
+# ([\u0000-\u007F · [:Latin:] [:Nonspacing_Mark:]]) ;
 # MINIMAL FILTER GENERATED FOR: Latin-Greek BACKWARD
 :: ( [':?A-Za-zÀ-ÅÇ-ÏÑ-ÖÙ-Ýà-åç-ïñ-öù-ýÿ-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǰǴ-ǵǸ-țȞ-ȟȦ-ȳ̀-̷̹-ͅ΅-ΆΈ-ΊΌΎ-ΐΪ-ΰϊ-ώϓ-ϔЀ-ЁЃЇЌ-ЎЙйѐ-ёѓїќ-ўѶ-ѷӁ-ӂӐ-ӓӖ-ӗӚ-ӟӢ-ӧӪ-ӵӸ-ӹḀ-ẙẛẠ-ỹἀ-ἕἘ-Ἕἠ-ὅὈ-Ὅὐ-ὗὙὛὝὟ-ώᾀ-ᾴᾶ-ᾼ῁-ῄῆ-ΐῖ-Ί῝-΅ῲ-ῴῶ-ῼK-Å] ) ;

package/transforms/Greek_Latin_UNGEGN.txt

@@ -6,8 +6,8 @@
 :: [[[:Greek:][:Mn:][:Me:]] [\:-;?·;·]] ;
 ::NFD (NFC) ;
 # Useful variables
-$lower = [[:latin:][:greek:] & [:Ll:]] ;
-$upper = [[:latin:][:greek:] & [:Lu:]] ;
+$lower = [[:Latin:][:Greek:] & [:Ll:]] ;
+$upper = [[:Latin:][:Greek:] & [:Lu:]] ;
 $accent = [[:Mn:][:Me:]] ;
 $macron = ̄ ;
 $ddot = ̈ ;

package/transforms/Han-Latin-Names.txt

@@ -7,7 +7,7 @@
 # Do this before ::Han-Spacedhan() to catch Han after space in original text,
 # and to apply before all other rules.
 $startOfHanMarker = \uFDD1;
-[:^script=Han:] { ([:script=Han:]) → $startOfHanMarker $1;
+[:^Script=Han:] { ([:Script=Han:]) → $startOfHanMarker $1;
 # Need Spacedhan so the name transliterations get spaced properly
 ::Han-Spacedhan();
 # Convert special name readings that depend on next character

package/transforms/Han-Latin.json

@@ -1,7 +1,7 @@
 {
   "_visibility": "external",
-  "_alias": "Han-Latin",
-  "_aliasBcp47": "und-Latn-t-und-hani",
+  "_alias": "Hans-Latn Han-Latin",
+  "_aliasBcp47": "und-Latn-t-und-hans und-Latn-t-und-hani",
   "_source": "Hani",
   "_direction": "forward",
   "_target": "Latn",

package/transforms/Han-Latin.txt

@@ -5,7 +5,7 @@
 # Note that Han-Spacedhan() has already been applied, so there should be spaces between Han characters.
 藏 } \u0020? 文 →zàng;# 藏 is zàng (not cáng) if followed by 文 wén: 藏文 language Zàngwén = Tibetan
 重 } \u0020? 庆 →chóng;# 重 is chóng (not zhòng) if followed by 庆 qìng: 重庆 city Chóngqìng
-沈 } \u0020? 阳 →shěn;# 沈 is shěn (not chén) if followed by 阳 yáng: 沈阳 city Shěnyáng
+# "沈 } \u0020? 阳 →shěn" is obsolete for Hans, the kMandarin entry for 沈 changed from "chén" to "shěn chén" in Unicode 14
 秘 } \u0020? 鲁 →bì;# 秘 is bì (not mì) if followed by 鲁 lǔ: 秘鲁 country Bìlǔ = Peru
 # START AUTOGENERATED Han-Latin.xml ( Unihan kMandarin)
 [吖錒锕阿𠼞𥥩𨉚𱚱]→ā;

package/transforms/Han-Spacedhan.txt

@@ -1,8 +1,8 @@
 # Only intended for internal use
 # Make sure Han are normalized, including characters that contain them.
-# The first set in the filter is computed with http://unicode.org/cldr/utility/list-unicodeset.jsp?a=[:tonfkd:/XXX/:]-[:ideographic:]-[:sc=han:]
-# Where XXX is the resolved [:ideographic:][:sc=han:]. It needs updating with each Unicode release!
-:: [[、。々《-』〜・㆒-㆟㈠-㉇㊀-㊰㋀-㋋ ㍘-㍰㍻-㍿㏠-㏾🈐-🈒🈔-🈺🉀-🉈🉐🉑][:ideographic:][:sc=han:]] nfkc;
+# The first set in the filter is computed with http://unicode.org/cldr/utility/list-unicodeset.jsp?a=[:tonfkd:/XXX/:]-[:Ideographic:]-[:sc=Han:]
+# Where XXX is the resolved [:Ideographic:][:sc=Han:]. It needs updating with each Unicode release!
+:: [[、。々《-』〜・㆒-㆟㈠-㉇㊀-㊰㋀-㋋ ㍘-㍰㍻-㍿㏠-㏾🈐-🈒🈔-🈺🉀-🉈🉐🉑][:Ideographic:][:sc=Han:]] nfkc;
 :: fullwidth-halfwidth;
 ｡ → '.';
 。→ '.';
@@ -23,7 +23,7 @@
 々→ '⓶';
 〜→ '~';
 $terminalPunct = [\.\,\:\;\?\!．，：？！｡、；[:Pe:][:Pf:]];
-$initialPunct = [:Ps:][:Pi:];
+$initialPunct = [[:Ps:][:Pi:]];
 # add space between any Han or terminal punctuation and letters, and
 # between letters and Han or initial punct
 [[:Ideographic:] $terminalPunct] {} [:Letter:] → ' ' ;

package/transforms/Hant-Latin.json

@@ -0,0 +1,8 @@
+{
+  "_visibility": "external",
+  "_aliasBcp47": "und-Latn-t-und-hant",
+  "_source": "Hant",
+  "_direction": "forward",
+  "_target": "Latn",
+  "_rulesFile": "Hant-Latin.txt"
+}

package/transforms/Hant-Latin.txt

@@ -0,0 +1,100 @@
+# Warning: does not do round-trip mapping!!
+# Convert compounds; these are added individually, not derived from Unihan kMandarin.
+# Here Han-Spacedhan() has not yet been applied.
+# The following was moved from Hans-Latn; in a Hant/Taiwan context, the simplified-form city name 沈阳 should still transform to shěnyáng.
+沈 } 阳 →shěn;# 沈 is shěn (not chén) if followed by 阳 yáng: 沈阳 city Shěnyáng
+# START From Unicode 17, the following should be autogenerated:
+[棓]→bàng;  # U+68D3
+[繃]→bēng;  # U+7E43
+[俾]→bì;    # U+4FFE
+[萹]→biǎn;  # U+8439
+[摽脿蔈麃]→biāo; # U+647D,813F,8508,9E83
+[啵]→bō;    # U+5575
+[柏薄]→bó;   # U+67CF,8584
+[卜]→bǔ;    # U+535C
+[差]→chā;   # U+5DEE
+[沈]→chén;  # U+6C88
+[牚]→chēng; # U+725A
+[埫]→chǒng; # U+57EB
+[槭]→cù;    # U+69ED
+[噠]→dá;    # U+5660
+[蹬]→dèng;  # U+8E6C
+[地]→dì;    # U+5730
+[嗲]→diē;   # U+55F2
+[䏲跌]→dié;  # U+43F2,8DCC
+[町]→dīng;  # U+753A
+[斗]→dǒu;   # U+6597
+[都]→dū;    # U+90FD
+[碡]→dú;    # U+78A1
+[柁]→duò;   # U+67C1
+[嗯]→en;    # U+55EF
+[髪髮]→fǎ;   # U+9AEA,9AEE
+[蕃]→fān;   # U+8543
+[帆]→fán;   # U+5E06
+[氾]→fàn;   # U+6C3E
+[彷]→fǎng;  # U+5F77
+[坋]→fèn;   # U+574B
+[諷讽]→fèng; # U+8AF7,8BBD
+[乾]→gān;   # U+4E7E
+[㪅]→gēng;  # U+3A85
+[蓇]→gǔ;    # U+84C7
+[聒]→guā;   # U+8052
+[氿]→guǐ;   # U+6C3F
+[炔]→guì;   # U+7094
+[欻]→hū;    # U+6B3B
+[砉]→huò;   # U+7809
+[𪟝]→jī;    # U+2A7DD
+[蓻]→jí;    # U+84FB
+[袷]→jiá;   # U+88B7
+[叚]→jiǎ;   # U+53DA
+[菹]→jū;    # U+83F9
+[剋]→kè;    # U+524B
+[框]→kuāng; # U+6846
+[适]→kuò;   # U+9002
+[肋]→lè;    # U+808B
+[釐]→lí;    # U+91D0
+[峛]→lǐ;    # U+5CDB
+[𩷕]→liáng; # U+29DD5
+[瞭]→liǎo;  # U+77AD
+[蹣]→mán;   # U+8E63
+[眄]→miǎn;  # U+7704
+[碈]→mín;   # U+7888
+[万]→mò;    # U+4E07
+[伲]→nǐ;    # U+4F32
+[耙]→pá;    # U+8019
+[芘]→pí;    # U+8298
+[諞]→pián;  # U+8ADE
+[剽]→piào;  # U+527D
+[剖頗]→pǒ;   # U+5256,9817
+[醱]→pò;    # U+91B1
+[呇]→qǐ;    # U+5447
+[癿]→qié;   # U+767F
+[芎]→qiōng; # U+828E
+[杣]→shān;  # U+6763
+[杓]→sháo;  # U+6753
+[舍]→shè;   # U+820D
+[誰]→shéi;  # U+8AB0
+[識识]→shì; # U+8B58,8BC6
+[楯]→shǔn;  # U+696F
+[洓]→suǒ;   # U+6D13
+[沓]→tà;    # U+6C93
+[堤隄]→tí;   # U+5824,9684
+[萎]→wēi;   # U+840E
+[硊]→wěi;   # U+784A
+[筽]→wú;    # U+7B7D
+[嘸]→wǔ;    # U+5638
+[㴔]→xī;    # U+3D14
+[𲆰]→xí;    # U+321B0
+[𲆦]→xì;    # U+321A6
+[呷]→xiá;   # U+5477
+[硍]→xiàn;   # U+784D
+[崾]→yǎo;    # U+5D3E
+[畬]→yú;   # U+756C
+[薁]→yù;   # U+8581
+[嶦]→zhān;   # U+5DA6
+[著]→zhe;   # U+8457
+[徵]→zhēng;   # U+5FB5
+[苧]→zhù;   # U+82E7
+# END From Unicode 17, the above should be autogenerated:
+# Then run the normal Hani-Latn transform for the rest
+::Hani-Latn();

package/transforms/Hiragana-Katakana.txt

@@ -1,5 +1,5 @@
 # note: a global filter is more efficient, but MUST include all source chars
-:: [[\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:nonspacing mark:]]-[\u309B \u309C]];
+:: [[\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:Nonspacing_Mark:]]-[\u309B \u309C]];
 :: NFKC (NFC);
 # Hiragana-Katakana
 # This is largely a one-to-one mapping, but it has a
@@ -173,5 +173,5 @@ $xo = [
 お ← $xo {ー};
 :: NFC (NFKC) ;
 # note: a global filter is more efficient, but MUST include all source chars!!
-:: ([[\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:nonspacing mark:]]-[\u309B \u309C]]);
+:: ([[\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:Nonspacing_Mark:]]-[\u309B \u309C]]);
 # eof

package/transforms/Latin-Jamo.txt

@@ -1,5 +1,5 @@
-::[[:script=Latin:][:M:]-];
+::[[:Script=Latin:][:M:]-];
 ::NFD;
 ::Lower;
 ::Latin-ConjoiningJamo;
-::[[:script=Latin:][:M:]] NFC;
+::[[:Script=Latin:][:M:]] NFC;

package/transforms/Latin-Katakana.txt

@@ -1,5 +1,5 @@
 # note: a global filter is more efficient, but MUST include all source chars
-#:: [\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟ [:Latin:][:Katakana:] [:nonspacing mark:]] ;
+#:: [\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟ [:Latin:][:Katakana:] [:Nonspacing_Mark:]] ;
 # MINIMAL FILTER GENERATED FOR: Latin-Katakana
 ### WARNING -- must add width filter, both here and below!!! ###
 :: [[ᄀ-ᄒᄚᄡ\u1160-ᅵᆪᆬ-ᆭᆰ-ᆵ←-↓│■○\u3000-。「-」゙-゚ァ-ロワヲ-ヴヷヺ-ー！-～￠-￦][',.A-Za-z~À-ÖØ-öø-ďĒ-ĥĨ-İĴ-ķĹ-ľŃ-ňŌ-őŔ-ťŨ-žƠ-ơƯ-ưǍ-ǜǞ-ǣǦ-ǭǰǴ-ǵǸ-țȞ-ȟȦ-ȳ̄Ӣ-ӣӮ-ӯḀ-ẙẠ-ỹᾱᾹῑῙῡῩK-Å]] ;
@@ -370,11 +370,11 @@ x → | ks ;
 # Final cleanup
 '~' → ; # delete stray tildes between letters
 [:Katakana:] { '' } [:Latin:] → ; # delete stray quotes between letters
-# [ʾ[:Nonspacing Mark:]-[゙-゜]] → ; # delete any non-spacing marks that we didn't use
+# [ʾ[:Nonspacing_Mark:]-[゙-゜]] → ; # delete any non-spacing marks that we didn't use
 :: NFC (NFD) ;
 :: ([[:Katakana:][\u309B\u309C\u30A0\u30FC\uFF70\uFF9E\uFF9F]] halfwidth-fullwidth);
 # note: a global filter is more efficient, but MUST include all source chars!!
-#:: ([\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟ [:Latin:][:Katakana:] [:nonspacing mark:]]);
+#:: ([\u0000-\u007E 、。 ゙-゜ ァ-ー ｡-ﾟ [:Latin:][:Katakana:] [:Nonspacing_Mark:]]);
 # MINIMAL FILTER GENERATED FOR: Latin-Katakana BACKWARD
 :: ( [[\ -~¢-£¥-¦¬̄₩｡-ﾾￂ-ￇￊ-ￏￒ-ￗￚ-ￜ￨-￮][~、-。がぎぐげござじずぜぞだぢづでどば-ぱび-ぴぶ-ぷべ-ぺぼ-ぽゔ゙-゛ゞァ-ヺー-ヾ][\u309B\u309C\u30A0\u30FC\uFF70\uFF9E\uFF9F]] ) ;
 # eof

package/transforms/Latin-NumericPinyin.txt

@@ -23,5 +23,5 @@ $digit = [1-5];
 $1 &NumericPinyin-Pinyin($3) $2 ← ([aAeE]) ($vowel* $consonant*) ($digit);
 $1 &NumericPinyin-Pinyin($3) $2 ← ([oO]) ([$vowel-[aeAE]]* $consonant*) ($digit);
 $1 &NumericPinyin-Pinyin($3) $2 ← ($vowel) ($consonant*) ($digit);
-&NumericPinyin-Pinyin($1) ← [:letter:] {($digit)};
+&NumericPinyin-Pinyin($1) ← [:Letter:] {($digit)};
 ::NFC (NFD);

package/transforms/Maldivian-Latin-BGN.txt

@@ -10,7 +10,7 @@
 # In our rules, we also convert Arabic punctuation characters to Latin.
 # These appears to be used in Maldivian text, for example in the Universal
 # Declaration of Human Rights.
-::[[:block=thaana:][،؛؟٪٫٬]\uFDF2] ;
+::[[:Block=Thaana:][،؛؟٪٫٬]\uFDF2] ;
 ::NFD;
 $wordBoundary = [^[:L:][:M:][:N:]] ;
 $vowel = [\u07A6-\u07AF] ;

package/transforms/Persian-Latin-BGN.txt

@@ -11,7 +11,7 @@
 #
 # MINIMAL FILTER: Persian-Latin
 #
-:: [[:arabic:][:block=ARABIC:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهویيَُِّْ٠١٢٣٤٥٦٧٨٩پچژگی]] ;
+:: [[:Arabic:][:Block=Arabic:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهویيَُِّْ٠١٢٣٤٥٦٧٨٩پچژگی]] ;
 :: NFKD (NFC) ;
 #
 #

package/transforms/Thai-Latin.txt

@@ -1,4 +1,4 @@
-::[[:thai:] ก-ฺเ-๛];
+::[[:Thai:] ก-ฺเ-๛];
 ::NFD;
 ::Thai-ThaiSemi;
 ::Any-BreakInternal;

package/transforms/Thai-ThaiLogical.txt

@@ -1,7 +1,7 @@
 # This reverses the Thai LogicalOrderException vowels, and does (part of) spaces
 # The rules that convert space into semicolon are in another file;
 # since they have to come BEFORE the break iterator
-$thai = [[:thai:] ก-ฺเ-๛] ;
+$thai = [[:Thai:] ก-ฺเ-๛] ;
 # First convert the semicolon back
 ' '  ← $thai { '; '  } $thai;
 # Remove any other spaces between thai letters

package/transforms/Thai-ThaiSemi.txt

@@ -1,4 +1,4 @@
 # The rules that convert space into semicolon are in this file;
 # since they have to come BEFORE the break iterator.
-$thai = [[:thai:] ก-ฺเ-๛] ;
+$thai = [[:Thai:] ก-ฺเ-๛] ;
 $thai { ' ' } $thai → '; ' ;

package/transforms/ThaiLogical-Latin.txt

@@ -18,8 +18,8 @@
 #{ ( $consonant ) } [^$vowel \uE000] → | $1 \uE000 ;
 #\uE000 → ọ ;
 # ← ọ ;
-$notAbove = [^\p{ccc=0}\p{ccc=above}] ;
-$notBelow = [^\p{ccc=0}\p{ccc=below}] ;
+$notAbove = [^\p{ccc=0}\p{ccc=Above}] ;
+$notBelow = [^\p{ccc=0}\p{ccc=Below}] ;
 # Consonants
 # Warning: the 'h's need to be handled carefully!
 # What we really want to say is the following, but we can't

package/transforms/am-Ethi-t-d0-morse.txt

@@ -12,7 +12,7 @@
 #
 # MINIMAL FILTER: Ethiopic-Morse Code
 #
-:: [[:Zs:]0-9!\?\+/@()\[\]_:;,\.'"$=\-[:Ethiopic:]] ;
+:: [[:Zs:]0-9!\?\+/@()\[\]_:;,\.'"\$=\-[:Ethiopic:]] ;
 ([:Lo:])([:Zs:]+)([:Lo:]) → | $1⁄⁂⁄$2$3 ;  # ⁄⁂⁄ is assumed to be a sufficiently weird enough sequence that won't naturally appear in any normal content
 #
 ########################################################################

package/transforms/az-Title.txt

@@ -1,8 +1,8 @@
 # I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
 # Make any string of letters after a cased letter be lower, with rules for i
-[:cased:] [:case-ignorable:]* { İ → i;
-[:cased:] [:case-ignorable:]* { I → ı;
-[:cased:] [:case-ignorable:]* { (.) → &Any-Lower($1) ;
+[:Cased:] [:Case_Ignorable:]* { İ → i;
+[:Cased:] [:Case_Ignorable:]* { I → ı;
+[:Cased:] [:Case_Ignorable:]* { (.) → &Any-Lower($1) ;
 # Otherwise all lowercase go to upper (titlecase stay as is)
 i→İ ;
 ([:Lowercase:]) → &Any-Upper($1) ;

package/transforms/byn-Ethi-t-byn-latn-m0-xaleget.txt

@@ -747,16 +747,16 @@ $wordBoundary{ኦ → $ኦ ; # ETHIOPIC SYLLABLE GLOTTAL O
 # Convert to dot to dot if dot is followed by a number, ellipsis, or another dot.
 \. $1 ← \.([0-9….]) ;
 # Convert to Ethiopic Fullstop if dot is not followed by a number or another dot.
-። $1 ↔ \.([^0-9.]) ;
+። $1 ← \.([^0-9.]) ;
 \, $1 ← \,([0-9]) ;
-# ፣ $1 ↔ \,([^0-9]) ;
+# ፣ $1 ← \,([^0-9]) ;
 ፤ ↔ \;    ;
 ፦ ↔ \:\-  ;
 # ፥ ↔ \:  ;
 # ፨ → "#" ;
 # ፠ → \+  ;
 ፧ → \?  ;
-፡ $1 ↔ \,([^0-9])   ;
+፡ $1 ← \,([^0-9])   ;
 ::Null ;
 $1 $ጥበቅ ← $ጥበቅ ([ሀ-ፖ]) ;
 ########################################################################

package/transforms/chr-chr_FONIPA.txt

@@ -106,4 +106,4 @@ e e+ → eː;
 i i+ → iː;
 o o+ → oː;
 u u+ → uː;
-ə̃ {ə̃}+ → ə̃;
+ə̃ ə̃+ → ə̃;

package/transforms/de-ASCII.txt

@@ -10,4 +10,4 @@ $UE = [Ü {U \u0308}];
 $AE → AE;
 $OE → OE;
 $UE → UE;
-::Any-ASCII;
+::Latin-ASCII;

package/transforms/el-Lower.txt

@@ -4,7 +4,7 @@
 # and C is not followed by a sequence consisting of zero or more case-ignorable characters and then a cased letter.
 # 03A3; 03C2; 03A3; 03A3; Final_Sigma; # GREEK CAPITAL LETTER SIGMA
 # With translit rules, easiest is to handle the negative condition first, mapping in that case to the regular sigma.
-Σ } [:case-ignorable:]* [:cased:] → σ;
-[:cased:] [:case-ignorable:]* { Σ → ς;
+Σ } [:Case_Ignorable:]* [:Cased:] → σ;
+[:Cased:] [:Case_Ignorable:]* { Σ → ς;
 ::Any-Lower;
 ::NFC();

package/transforms/el-Title.txt

@@ -2,9 +2,9 @@
 # Remove \0301 following Greek, with possible intervening 0308 marks.
 # [[:Greek:] & [:Ll:]] [\u0308]? { \u0301 → ;
 # Make any string of letters after a cased letter be lower, with rules for sigma
-[:cased:] [:case-ignorable:]* { Σ } [:case-ignorable:]* [:cased:] → σ;
-[:cased:] [:case-ignorable:]* { Σ → ς;
-[:cased:] [:case-ignorable:]* { (.) → &Any-Lower($1) ;
+[:Cased:] [:Case_Ignorable:]* { Σ } [:Case_Ignorable:]* [:Cased:] → σ;
+[:Cased:] [:Case_Ignorable:]* { Σ → ς;
+[:Cased:] [:Case_Ignorable:]* { (.) → &Any-Lower($1) ;
 # Otherwise all lowercase go to upper (titlecase stay as is)
 ([:Lowercase:]) → &Any-Title($1) ;
 ::NFC();

package/transforms/it-am.txt

@@ -251,5 +251,5 @@ y → | i;
 z → ዝ;
 #
 #
-[:nonspacing mark:] → ;
+[:Nonspacing_Mark:] → ;
 ::NFC(NFD);

package/transforms/it-ja.txt

@@ -253,5 +253,5 @@ z → ツ;
 \- → ＝;
 #
 #
-[:nonspacing mark:] → ;
+[:Nonspacing_Mark:] → ;
 ::NFC(NFD);

package/transforms/lt-Title.txt

@@ -1,12 +1,12 @@
 # Make any string of letters after a cased letter be lower
 ::NFD();
-[:cased:] [:case-ignorable:]* {I } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → i \u0307;
-[:cased:] [:case-ignorable:]* {J } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → j \u0307;
-[:cased:] [:case-ignorable:]* {I \u0328 } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → i \u0328 \u0307;
-[:cased:] [:case-ignorable:]* {I \u0300 → i \u0307 \u0300;
-[:cased:] [:case-ignorable:]* {I \u0301 → i \u0307 \u0301;
-[:cased:] [:case-ignorable:]* {I \u0303 → i \u0307 \u0303;
-[:cased:] [:case-ignorable:]* { (.) → &Any-Lower($1) ;
+[:Cased:] [:Case_Ignorable:]* {I } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → i \u0307;
+[:Cased:] [:Case_Ignorable:]* {J } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → j \u0307;
+[:Cased:] [:Case_Ignorable:]* {I \u0328 } [^[:ccc=Not_Reordered:][:ccc=Above:]]* [:ccc=Above:] → i \u0328 \u0307;
+[:Cased:] [:Case_Ignorable:]* {I \u0300 → i \u0307 \u0300;
+[:Cased:] [:Case_Ignorable:]* {I \u0301 → i \u0307 \u0301;
+[:Cased:] [:Case_Ignorable:]* {I \u0303 → i \u0307 \u0303;
+[:Cased:] [:Case_Ignorable:]* { (.) → &Any-Lower($1) ;
 # Otherwise all lowercase go to upper (titlecase stay as is)
 [:Soft_Dotted:] [^[:ccc=Not_Reordered:][:ccc=Above:]]* { \u0307 → ;
 ([:Lowercase:]) → &Any-Upper($1) ;

package/transforms/tr-Title.txt

@@ -1,8 +1,8 @@
 # I and i-dotless; I-dot and i are case pairs in Turkish and Azeri
 # Make any string of letters after a cased letter be lower, with rules for i
-[:cased:] [:case-ignorable:]* { İ → i;
-[:cased:] [:case-ignorable:]* { I → ı;
-[:cased:] [:case-ignorable:]* { (.) → &Any-Lower($1) ;
+[:Cased:] [:Case_Ignorable:]* { İ → i;
+[:Cased:] [:Case_Ignorable:]* { I → ı;
+[:Cased:] [:Case_Ignorable:]* { (.) → &Any-Lower($1) ;
 # Otherwise all lowercase go to upper (titlecase stay as is)
 i→İ ;
 ([:Lowercase:]) → &Any-Upper($1) ;

package/transforms/und-Ethi-t-und-latn-m0-beta_metsehaf-geminate.txt

@@ -12,6 +12,6 @@
 ########################################################################
 #
 :: Amharic-Amharic/Geminate ;
-:: Ethiopic-Latin/BetaMetsehaf ;
+:: Ethiopic-Latin/Beta_Metsehaf ;
 #
 ########################################################################

package/transforms.json

@@ -71,6 +71,7 @@
       "Han-Latin-Names",
       "Han-Spacedhan",
       "Hangul-Latin",
+      "Hant-Latin",
       "Hebrew-Latin",
       "Hebrew-Latin-BGN",
       "Hiragana-Katakana",