CLDR-17349 Fix special cases

unicode-org · May 8, 2024 · f47dbe7 · f47dbe7
1 parent 43482a5
commit f47dbe7
Show file tree

Hide file tree

Showing 4 changed files with 23 additions and 20 deletions.
diff --git a/common/annotations/en.xml b/common/annotations/en.xml
@@ -3907,21 +3907,21 @@ annotations.
 		<annotation cp="³" type="tts">superscript three</annotation>
 		<annotation cp="µ">measure | micro sign</annotation>
 		<annotation cp="µ" type="tts">micro sign</annotation>
-		<!--  start hand-generated lines from E16 -->
-		<annotation cp='🪉' type='tts'>harp</annotation>
-		<annotation cp='🪉'>music | instrument | love | cupid | orchestra</annotation>
-		<annotation cp='🪏' type='tts'>shovel</annotation>
-		<annotation cp='🪏'>dig | spade | hole | scoop</annotation>
-		<annotation cp='🪾' type='tts'>leafless tree</annotation>
-		<annotation cp='🪾'>winter | barren | drought</annotation>
-		<annotation cp='🫆' type='tts'>fingerprint</annotation>
-		<annotation cp='🫆'>forensics | identity | safety</annotation>
-		<annotation cp='🫜' type='tts'>root vegetable</annotation>
-		<annotation cp='🫜'>root | vegetable | garden | beet | turnip</annotation>
-		<annotation cp='🫟' type='tts'>splatter</annotation>
-		<annotation cp='🫟'>paint | holi | spill | stain</annotation>
-		<annotation cp='🫩' type='tts'>face with bags under eyes</annotation>
-		<annotation cp='🫩'>tired | sleepy | exhausted</annotation>
-		<!--  end hand-generated lines from E16 -->
+		<!-- start hand-generated lines from E16 -->
+		<annotation cp="🪉">music | instrument | love | cupid | orchestra</annotation>
+		<annotation cp="🪉" type="tts">harp</annotation>
+		<annotation cp="🪏">dig | spade | hole | scoop</annotation>
+		<annotation cp="🪏" type="tts">shovel</annotation>
+		<annotation cp="🪾">winter | barren | drought</annotation>
+		<annotation cp="🪾" type="tts">leafless tree</annotation>
+		<annotation cp="🫆">forensics | identity | safety</annotation>
+		<annotation cp="🫆" type="tts">fingerprint</annotation>
+		<annotation cp="🫜">root | vegetable | garden | beet | turnip</annotation>
+		<annotation cp="🫜" type="tts">root vegetable</annotation>
+		<annotation cp="🫟">paint | holi | spill | stain</annotation>
+		<annotation cp="🫟" type="tts">splatter</annotation>
+		<annotation cp="🫩">tired | sleepy | exhausted</annotation>
+		<annotation cp="🫩" type="tts">face with bags under eyes</annotation>
+		<!-- end hand-generated lines from E16 -->
 	</annotations>
 </ldml>
diff --git a/common/annotations/he.xml b/common/annotations/he.xml
@@ -2868,7 +2868,7 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🃏">ג׳וקר | משחק | קלף</annotation>
 		<annotation cp="🃏" type="tts">ג׳וקר</annotation>
 		<annotation cp="🀄">אדום | דרקון | דרקון אדום במה-ג׳ונג | מה-ג׳ונג | משחק</annotation>
-		<annotation cp="🀄" type="tts">דרקון אדום ‎מה-ג׳ונג</annotation>
+		<annotation cp="🀄" type="tts">דרקון אדום מה-ג׳ונג</annotation>
 		<annotation cp="🎴">יפני | משחק | קלף | קלפי פרחים</annotation>
 		<annotation cp="🎴" type="tts">קלפי פרחים</annotation>
 		<annotation cp="🎭" draft="contributed">אמנויות הבמה | במה | דרמה | מסיכות | משחק | תיאטרון | פורים</annotation>

diff --git a/common/annotations/ur.xml b/common/annotations/ur.xml
@@ -2129,7 +2129,7 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🫔" type="tts">ٹمالے</annotation>
 		<annotation cp="🥙" draft="contributed">بھری ہوئی | بھری ہوئی چپاتی | چپاتی | خوراک | کباب | فلافل | روٹی | نان | روٹ | جائرو</annotation>
 		<annotation cp="🥙" type="tts">بھری ہوئی چپاتی</annotation>
-		<annotation cp="🧆" draft="contributed">چنا | فلافل | کوفتہ | سفید چنا | کھانا | ‏‏‏غذا</annotation>
+		<annotation cp="🧆" draft="contributed">چنا | فلافل | کوفتہ | سفید چنا | کھانا | غذا</annotation>
 		<annotation cp="🧆" type="tts">فلافل</annotation>
 		<annotation cp="🥚" draft="contributed">انڈا | خوراک | بیضہ | مرغ | آملیٹ | کیک | نانختائی</annotation>
 		<annotation cp="🥚" type="tts">انڈا</annotation>
@@ -2205,7 +2205,7 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 		<annotation cp="🍨" type="tts">آئس کریم</annotation>
 		<annotation cp="🍩" draft="contributed">ڈونٹ | میٹھا | شیریں | خوراک | شیرینی | کھانا</annotation>
 		<annotation cp="🍩" type="tts">ڈونٹ</annotation>
-		<annotation cp="🍪" draft="contributed">کوکی | میٹھا | شیرینی | ‫نان ختایی‬‎ | میٹھاس | چاکلیٹ والی نان ختایی</annotation>
+		<annotation cp="🍪" draft="contributed">کوکی | میٹھا | شیرینی | نان ختایی | میٹھاس | چاکلیٹ والی نان ختایی</annotation>
 		<annotation cp="🍪" type="tts">کوکی</annotation>
 		<annotation cp="🎂" draft="contributed">پیسٹری | جشن | سالگرہ کا کیک | کیک | میٹھا | سالگرہ مبارک | سالگرہ | ہیپی برتھ ڈے | برتھ ڈے | پیدائش | شیرینی | برتھ ڈے کیک</annotation>
 		<annotation cp="🎂" type="tts">سالگرہ کا کیک</annotation>

diff --git a/common/transforms/Arabic-Latin.xml b/common/transforms/Arabic-Latin.xml
@@ -22,7 +22,7 @@ For terms of use, see http://www.unicode.org/copyright.html
 # 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]] ;
+:: [[:Arabic:][:block=ARABIC:][‎ⁿ،؛؟ـً-ٕ٠-٬۰-۹﷼ښ][\u0611\u0670]] ;
 :: NFKD (NFC);
 $disambig =  ̱ ;
 $disambig2 =  ̰ ;
@@ -190,6 +190,9 @@ $notAbove = [[:^ccc=0:] & [:^ccc=230:]];
 ‎ہ‎ → ḥ ;
 ‎ە‎ → ĥ ;
 
+# Delete marks without correspondants
+[\u0611\u0670] → ;
+
 # fallbacks
 | s ← c } [eiy];
 | k ← c ;