cldr-transforms 46.1.0 → 47.0.0

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": "46.1.0",
+  "version": "47.0.0",
   "dependencies": {
-    "cldr-core": "46.1.0"
+    "cldr-core": "47.0.0"
   },
   "main": "transforms/**/*.json",
   "ignore": [

package/package.json

@@ -1,8 +1,8 @@
 {
   "name": "cldr-transforms",
-  "version": "46.1.0",
+  "version": "47.0.0",
   "peerDependencies": {
-    "cldr-core": "46.1.0"
+    "cldr-core": "47.0.0"
   },
   "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": "46.1",
+  "cldrVersion": "47",
   "unicodeVersion": "16.0.0"
 }

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 阳 →shěn" is obsolete for Hans, the kMandarin entry for 沈 changed from "chén" to "shěn chén" in Unicode 14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/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/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/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",