mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-05 13:35:32 +00:00
ICU-22922 Integrate CLDR 46.1 beta1 to ICU main, part 2: source data/test generated or copied from CLDR
This commit is contained in:
Peter Edberg
Peter Edberg
parent
c3929d1595
commit
e2581fd1ac
48 changed files with 2511 additions and 2450 deletions
File diff suppressed because it is too large
Load diff
|
|
@ -25,5 +25,5 @@ root{
|
|||
lstm{
|
||||
Thai{"Thai_graphclust_model4_heavy.res"}
|
||||
Mymr{"Burmese_graphclust_model5_heavy.res"}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -42,7 +42,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
|
|||
<!ATTLIST version number CDATA #REQUIRED >
|
||||
<!--@MATCH:regex/\$Revision.*\$-->
|
||||
<!--@METADATA-->
|
||||
<!ATTLIST version cldrVersion CDATA #FIXED "46" >
|
||||
<!ATTLIST version cldrVersion CDATA #FIXED "46.1" >
|
||||
<!--@MATCH:any-->
|
||||
<!--@VALUE-->
|
||||
<!ATTLIST version draft (approved | contributed | provisional | unconfirmed | true | false) #IMPLIED >
|
||||
|
|
|
|||
|
|
@ -283,8 +283,8 @@ ja{
|
|||
"Hmmssz",
|
||||
"Hmmss",
|
||||
"Hmm",
|
||||
"GGGGyMEEEEd",
|
||||
"GGGGyMd",
|
||||
"GGGGyMMMEEEEd",
|
||||
"GGGGyMMMd",
|
||||
"GyMMdd",
|
||||
"GyMMdd",
|
||||
}
|
||||
|
|
@ -761,8 +761,8 @@ ja{
|
|||
"Hmmssz",
|
||||
"Hmmss",
|
||||
"Hmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GGGGGyMMdd",
|
||||
"GGGGGyMd",
|
||||
}
|
||||
|
|
@ -1002,8 +1002,8 @@ ja{
|
|||
"Hmmssz",
|
||||
"Hmmss",
|
||||
"Hmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMdd",
|
||||
"yMMdd",
|
||||
}
|
||||
|
|
@ -1326,8 +1326,8 @@ ja{
|
|||
"Hmmssz",
|
||||
"Hmmss",
|
||||
"Hmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMdd",
|
||||
"GyMMdd",
|
||||
}
|
||||
|
|
@ -1398,8 +1398,8 @@ ja{
|
|||
"Hmmssz",
|
||||
"Hmmss",
|
||||
"Hmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMdd",
|
||||
"GyMMdd",
|
||||
}
|
||||
|
|
@ -1466,10 +1466,10 @@ ja{
|
|||
"Hmmssz",
|
||||
"Hmmss",
|
||||
"Hmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
{
|
||||
"GyMd",
|
||||
"GyMMMd",
|
||||
"y=jpanyear",
|
||||
}
|
||||
"GGGGGyMd",
|
||||
|
|
@ -2005,8 +2005,8 @@ ja{
|
|||
"Hmmssz",
|
||||
"Hmmss",
|
||||
"Hmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMdd",
|
||||
"GyMMdd",
|
||||
}
|
||||
|
|
|
|||
|
|
@ -856,8 +856,8 @@ ko{
|
|||
"ahmsz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
}
|
||||
|
|
@ -1085,8 +1085,8 @@ ko{
|
|||
"ahmsz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMMMMEEEEd",
|
||||
"yMMMMd",
|
||||
"yMd",
|
||||
"yyMd",
|
||||
}
|
||||
|
|
|
|||
|
|
@ -24,8 +24,8 @@ ko_CN{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMMMMEEEEd",
|
||||
"yMMMMd",
|
||||
"yMd",
|
||||
"yyMd",
|
||||
}
|
||||
|
|
|
|||
|
|
@ -770,9 +770,9 @@ yue{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -981,9 +981,9 @@ yue{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMMd",
|
||||
"yMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
|
|||
|
|
@ -206,9 +206,9 @@ yue_Hans{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -766,9 +766,9 @@ yue_Hans{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMMEEEEd",
|
||||
"GyMMd",
|
||||
"GyMMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -972,9 +972,9 @@ yue_Hans{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMdMM",
|
||||
"yMMMd",
|
||||
"yMd",
|
||||
}
|
||||
appendItems{
|
||||
|
|
@ -1287,9 +1287,9 @@ yue_Hans{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
}
|
||||
eras{
|
||||
|
|
@ -1364,9 +1364,9 @@ yue_Hans{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -1446,9 +1446,9 @@ yue_Hans{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMMdd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -1756,9 +1756,9 @@ yue_Hans{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
|
|||
|
|
@ -2,4 +2,33 @@
|
|||
// License & terms of use: http://www.unicode.org/copyright.html
|
||||
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
|
||||
yue_Hant_CN{
|
||||
calendar{
|
||||
gregorian{
|
||||
DateTimePatterns{
|
||||
"HH:mm:ss [zzzz]",
|
||||
"HH:mm:ss [z]",
|
||||
"HH:mm:ss",
|
||||
"HH:mm",
|
||||
"y年M月d日 EEEE",
|
||||
"y年M月d日",
|
||||
"y年M月d日",
|
||||
"y/M/d",
|
||||
"{1} {0}",
|
||||
"{1} {0}",
|
||||
"{1} {0}",
|
||||
"{1} {0}",
|
||||
"{1} {0}",
|
||||
}
|
||||
DateTimeSkeletons{
|
||||
"HHmmsszzzz",
|
||||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMMd",
|
||||
"yMd",
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -677,8 +677,8 @@ zh{
|
|||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
}
|
||||
eras{
|
||||
|
|
@ -744,8 +744,8 @@ zh{
|
|||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
}
|
||||
eras{
|
||||
|
|
@ -821,9 +821,9 @@ zh{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -1022,9 +1022,9 @@ zh{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMMd",
|
||||
"yMd",
|
||||
}
|
||||
appendItems{
|
||||
|
|
@ -1417,9 +1417,9 @@ zh{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMMEEEEd",
|
||||
"GyMMd",
|
||||
"GyMMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -1542,9 +1542,9 @@ zh{
|
|||
"HHmmssz",
|
||||
"HHmmss",
|
||||
"HHmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMMdd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
|
|||
|
|
@ -24,9 +24,9 @@ zh_Hans_HK{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -107,9 +107,9 @@ zh_Hans_HK{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GGGGGyyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -173,9 +173,9 @@ zh_Hans_HK{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMMd",
|
||||
"yyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -240,9 +240,9 @@ zh_Hans_HK{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
}
|
||||
|
|
@ -267,9 +267,9 @@ zh_Hans_HK{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -298,9 +298,9 @@ zh_Hans_HK{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
|
|||
|
|
@ -77,9 +77,9 @@ zh_Hans_MO{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GGGGGyyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -149,9 +149,9 @@ zh_Hans_MO{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMMd",
|
||||
"yyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -224,9 +224,9 @@ zh_Hans_MO{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
}
|
||||
|
|
@ -251,9 +251,9 @@ zh_Hans_MO{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
|
|||
|
|
@ -24,9 +24,9 @@ zh_Hans_MY{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMMd",
|
||||
"yMd",
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -24,9 +24,9 @@ zh_Hans_SG{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
intervalFormats{
|
||||
|
|
@ -102,9 +102,9 @@ zh_Hans_SG{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GGGGGyyMMdd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -171,9 +171,9 @@ zh_Hans_SG{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMMd",
|
||||
"yyMMdd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -244,9 +244,9 @@ zh_Hans_SG{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
}
|
||||
|
|
@ -271,9 +271,9 @@ zh_Hans_SG{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -302,9 +302,9 @@ zh_Hans_SG{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
|
|||
|
|
@ -807,9 +807,9 @@ zh_Hant{
|
|||
"Bhmmssz",
|
||||
"Bhmmss",
|
||||
"Bhmm",
|
||||
"GyMEEEEd",
|
||||
"GyMd",
|
||||
"GyMd",
|
||||
"GyMMMEEEEd",
|
||||
"GyMMMd",
|
||||
"GyMMMd",
|
||||
"GyMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
@ -967,9 +967,9 @@ zh_Hant{
|
|||
"Bhmmssz",
|
||||
"Bhmmss",
|
||||
"Bhmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMMd",
|
||||
"yMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
|
|||
|
|
@ -315,9 +315,9 @@ zh_Hant_HK{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMMd",
|
||||
"yMd",
|
||||
}
|
||||
availableFormats{
|
||||
|
|
|
|||
|
|
@ -24,9 +24,9 @@ zh_Hant_MY{
|
|||
"ahmmssz",
|
||||
"ahmmss",
|
||||
"ahmm",
|
||||
"yMEEEEd",
|
||||
"yMd",
|
||||
"yMd",
|
||||
"yMMMEEEEd",
|
||||
"yMMMd",
|
||||
"yMMMd",
|
||||
"yMd",
|
||||
}
|
||||
}
|
||||
|
|
|
|||
File diff suppressed because it is too large
Load diff
|
|
@ -13324,6 +13324,11 @@ supplementalData:table(nofallback){
|
|||
scripts{"Latn"}
|
||||
}
|
||||
}
|
||||
ecy{
|
||||
secondary{
|
||||
scripts{"Cprt"}
|
||||
}
|
||||
}
|
||||
ee{
|
||||
primary{
|
||||
scripts{"Latn"}
|
||||
|
|
@ -13983,6 +13988,11 @@ supplementalData:table(nofallback){
|
|||
scripts{"Latn"}
|
||||
}
|
||||
}
|
||||
gmy{
|
||||
secondary{
|
||||
scripts{"Linb"}
|
||||
}
|
||||
}
|
||||
gn{
|
||||
primary{
|
||||
scripts{"Latn"}
|
||||
|
|
@ -14030,11 +14040,7 @@ supplementalData:table(nofallback){
|
|||
}
|
||||
grc{
|
||||
secondary{
|
||||
scripts{
|
||||
"Cprt",
|
||||
"Grek",
|
||||
"Linb",
|
||||
}
|
||||
scripts{"Grek"}
|
||||
}
|
||||
}
|
||||
grt{
|
||||
|
|
@ -14572,6 +14578,15 @@ supplementalData:table(nofallback){
|
|||
scripts{"Latn"}
|
||||
}
|
||||
}
|
||||
kaw{
|
||||
secondary{
|
||||
scripts{
|
||||
"Bali",
|
||||
"Java",
|
||||
"Kawi",
|
||||
}
|
||||
}
|
||||
}
|
||||
kbd{
|
||||
primary{
|
||||
scripts{"Cyrl"}
|
||||
|
|
@ -28522,6 +28537,9 @@ supplementalData:table(nofallback){
|
|||
ar{
|
||||
populationShareF:int{46980000}
|
||||
}
|
||||
ecy{
|
||||
populationShareF:int{44100000}
|
||||
}
|
||||
el{
|
||||
officialStatus{"official"}
|
||||
populationShareF:int{49950000}
|
||||
|
|
@ -29490,6 +29508,12 @@ supplementalData:table(nofallback){
|
|||
fr{
|
||||
populationShareF:int{48900000}
|
||||
}
|
||||
gmy{
|
||||
populationShareF:int{0}
|
||||
}
|
||||
grc{
|
||||
populationShareF:int{0}
|
||||
}
|
||||
mk{
|
||||
populationShareF:int{48160000}
|
||||
}
|
||||
|
|
@ -29721,6 +29745,9 @@ supplementalData:table(nofallback){
|
|||
literacyShareF:int{49100000}
|
||||
populationShareF:int{48180000}
|
||||
}
|
||||
ban_Bali{
|
||||
populationShareF:int{0}
|
||||
}
|
||||
bbc{
|
||||
populationShareF:int{47920000}
|
||||
}
|
||||
|
|
@ -29749,6 +29776,9 @@ supplementalData:table(nofallback){
|
|||
literacyShareF:int{49100000}
|
||||
populationShareF:int{49340000}
|
||||
}
|
||||
kaw{
|
||||
populationShareF:int{0}
|
||||
}
|
||||
kge{
|
||||
populationShareF:int{47320000}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@
|
|||
# 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،؛؟ـ\u064B-\u0655٠-٬۰-۹﷼ښ][\u0611\u0670]] ;
|
||||
:: [[:Arabic:][:Block=Arabic:][ⁿ،؛؟ـ\u064B-\u0655٠-٬۰-۹﷼ښ][\u0611\u0670]] ;
|
||||
:: NFKD (NFC);
|
||||
$disambig = \u0331 ;
|
||||
$disambig2 = \u0330 ;
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
# Generated from CLDR
|
||||
#
|
||||
|
||||
::[[:script=bengali:][।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]];
|
||||
::[[:Script=Bengali:][।-॥\u0981-ঃঅ-ঌএ-ঐও-নপ-রলশ-হ\u09BC-\u09C4ে-ৈো-\u09CDৗড়-ঢ়য়-\u09E3০-৺ৎ]];
|
||||
::NFD;
|
||||
::Bengali-InterIndic;
|
||||
::InterIndic-Latin;
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@
|
|||
# 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, \u0308 must be added to the generated filters, in both directions ###
|
||||
# MINIMAL FILTER
|
||||
# Cyrillic-Latin
|
||||
|
|
@ -275,13 +275,13 @@ $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‧ˌ\u0308A-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-ʺ\u0300-\u0302\u0306-\u0307\u030C\u0326\u0331\u0340-\u0341\u0344ʹ΅-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] ) ;
|
||||
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@
|
|||
#
|
||||
|
||||
# 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-ȳ\u0304\u0308\u0313-\u0314\u0342-\u0345ͺ;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) ;
|
||||
|
|
@ -20,9 +20,9 @@
|
|||
# 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
|
||||
|
|
@ -228,8 +228,8 @@ $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
|
||||
|
|
@ -251,8 +251,8 @@ $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-ȳ\u0300-\u0337\u0339-\u0345΅-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] ) ;
|
||||
|
||||
|
|
|
|||
|
|
@ -14,8 +14,8 @@
|
|||
:: [[[: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 = \u0304 ;
|
||||
$ddot = \u0308 ;
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@
|
|||
# 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
|
||||
|
|
|
|||
|
|
@ -8,9 +8,9 @@
|
|||
|
||||
# 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;
|
||||
｡ → '.';
|
||||
。→ '.';
|
||||
|
|
@ -31,7 +31,7 @@
|
|||
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:] → ' ' ;
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@
|
|||
#
|
||||
|
||||
# note: a global filter is more efficient, but MUST include all source chars
|
||||
:: [[\u0000-\u007E 、。 \u3099-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:nonspacing mark:]]-[\u309B \u309C]];
|
||||
:: [[\u0000-\u007E 、。 \u3099-゜ 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
|
||||
|
|
@ -181,6 +181,6 @@ $xo = [
|
|||
お ← $xo {ー};
|
||||
:: NFC (NFKC) ;
|
||||
# note: a global filter is more efficient, but MUST include all source chars!!
|
||||
:: ([[\u0000-\u007E 、。 \u3099-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:nonspacing mark:]]-[\u309B \u309C]]);
|
||||
:: ([[\u0000-\u007E 、。 \u3099-゜ ァ-ー ｡-ﾟー[:Hiragana:] [:Katakana:] [:Nonspacing_Mark:]]-[\u309B \u309C]]);
|
||||
# eof
|
||||
|
||||
|
|
|
|||
|
|
@ -31,6 +31,6 @@ $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);
|
||||
|
||||
|
|
|
|||
|
|
@ -6,9 +6,9 @@
|
|||
# Generated from CLDR
|
||||
#
|
||||
|
||||
::[[:script=Latin:][:M:]-];
|
||||
::[[:Script=Latin:][:M:]-];
|
||||
::NFD;
|
||||
::Lower;
|
||||
::Latin-ConjoiningJamo;
|
||||
::[[:script=Latin:][:M:]] NFC;
|
||||
::[[:Script=Latin:][:M:]] NFC;
|
||||
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@
|
|||
#
|
||||
|
||||
# note: a global filter is more efficient, but MUST include all source chars
|
||||
#:: [\u0000-\u007E 、。 \u3099-゜ ァ-ー ｡-ﾟ [:Latin:][:Katakana:] [:nonspacing mark:]] ;
|
||||
#:: [\u0000-\u007E 、。 \u3099-゜ 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-。「-」\u3099-\u309A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-ȳ\u0304Ӣ-ӣӮ-ӯḀ-ẙẠ-ỹᾱᾹῑῙῡῩK-Å]] ;
|
||||
|
|
@ -378,11 +378,11 @@ x → | ks ;
|
|||
# Final cleanup
|
||||
'~' → ; # delete stray tildes between letters
|
||||
[:Katakana:] { '' } [:Latin:] → ; # delete stray quotes between letters
|
||||
# [ʾ[:Nonspacing Mark:]-[\u3099-゜]] → ; # delete any non-spacing marks that we didn't use
|
||||
# [ʾ[:Nonspacing_Mark:]-[\u3099-゜]] → ; # 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 、。 \u3099-゜ ァ-ー ｡-ﾟ [:Latin:][:Katakana:] [:nonspacing mark:]]);
|
||||
#:: ([\u0000-\u007E 、。 \u3099-゜ ァ-ー ｡-ﾟ [:Latin:][:Katakana:] [:Nonspacing_Mark:]]);
|
||||
# MINIMAL FILTER GENERATED FOR: Latin-Katakana BACKWARD
|
||||
:: ( [[\ -~¢-£¥-¦¬\u0304₩｡-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\u3099-゛ゞァ-ヺー-ヾ][\u309B\u309C\u30A0\u30FC\uFF70\uFF9E\uFF9F]] ) ;
|
||||
# eof
|
||||
|
|
|
|||
|
|
@ -26,8 +26,8 @@
|
|||
#{ ( $consonant ) } [^$vowel \uE000] → | $1 \uE000 ;
|
||||
#\uE000 → o\u0323 ;
|
||||
# ← o\u0323 ;
|
||||
$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
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
# Generated from CLDR
|
||||
#
|
||||
|
||||
::[[:thai:] ก-\u0E3Aเ-๛];
|
||||
::[[:Thai:] ก-\u0E3Aเ-๛];
|
||||
::NFD;
|
||||
::Thai-ThaiSemi;
|
||||
::Any-BreakInternal;
|
||||
|
|
|
|||
|
|
@ -9,7 +9,7 @@
|
|||
# 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-\u0E3Aเ-๛] ;
|
||||
$thai = [[:Thai:] ก-\u0E3Aเ-๛] ;
|
||||
# First convert the semicolon back
|
||||
' ' ← $thai { '; ' } $thai;
|
||||
# Remove any other spaces between thai letters
|
||||
|
|
|
|||
|
|
@ -8,6 +8,6 @@
|
|||
|
||||
# The rules that convert space into semicolon are in this file;
|
||||
# since they have to come BEFORE the break iterator.
|
||||
$thai = [[:thai:] ก-\u0E3Aเ-๛] ;
|
||||
$thai = [[:Thai:] ก-\u0E3Aเ-๛] ;
|
||||
$thai { ' ' } $thai → '; ' ;
|
||||
|
||||
|
|
|
|||
|
|
@ -20,7 +20,7 @@
|
|||
#
|
||||
# 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
|
||||
#
|
||||
########################################################################
|
||||
|
|
|
|||
|
|
@ -22,7 +22,7 @@
|
|||
#
|
||||
# MINIMAL FILTER: Arabic-Latin
|
||||
#
|
||||
:: [[:arabic:][:block=ARABIC:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهوىي\u064B\u064C\u064D\u064E\u064F\u0650\u0651\u0652٠١٢٣٤٥٦٧٨٩ٱ]] ;
|
||||
:: [[:Arabic:][:Block=Arabic:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهوىي\u064B\u064C\u064D\u064E\u064F\u0650\u0651\u0652٠١٢٣٤٥٦٧٨٩ٱ]] ;
|
||||
:: NFKD (NFC) ;
|
||||
#
|
||||
#
|
||||
|
|
|
|||
|
|
@ -8,9 +8,9 @@
|
|||
|
||||
# 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) ;
|
||||
|
|
|
|||
|
|
@ -18,5 +18,5 @@ $UE = [Ü {U \u0308}];
|
|||
$AE → AE;
|
||||
$OE → OE;
|
||||
$UE → UE;
|
||||
::Any-ASCII;
|
||||
::Latin-ASCII;
|
||||
|
||||
|
|
|
|||
|
|
@ -18,7 +18,7 @@
|
|||
# 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] ;
|
||||
|
|
|
|||
|
|
@ -12,8 +12,8 @@
|
|||
# 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();
|
||||
|
||||
|
|
|
|||
|
|
@ -10,9 +10,9 @@
|
|||
# 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();
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@
|
|||
#
|
||||
# MINIMAL FILTER: Persian-Latin
|
||||
#
|
||||
:: [[:arabic:][:block=ARABIC:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهویي\u064E\u064F\u0650\u0651\u0652٠١٢٣٤٥٦٧٨٩پچژگی]] ;
|
||||
:: [[:Arabic:][:Block=Arabic:][ءآابةتثجحخدذرزسشصضطظعغفقكلمنهویي\u064E\u064F\u0650\u0651\u0652٠١٢٣٤٥٦٧٨٩پچژگی]] ;
|
||||
:: NFKD (NFC) ;
|
||||
#
|
||||
#
|
||||
|
|
|
|||
|
|
@ -259,6 +259,6 @@ y → | i;
|
|||
z → ዝ;
|
||||
#
|
||||
#
|
||||
[:nonspacing mark:] → ;
|
||||
[:Nonspacing_Mark:] → ;
|
||||
::NFC(NFD);
|
||||
|
||||
|
|
|
|||
|
|
@ -261,6 +261,6 @@ z → ツ;
|
|||
\- → ＝;
|
||||
#
|
||||
#
|
||||
[:nonspacing mark:] → ;
|
||||
[:Nonspacing_Mark:] → ;
|
||||
::NFC(NFD);
|
||||
|
||||
|
|
|
|||
|
|
@ -8,13 +8,13 @@
|
|||
|
||||
# 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) ;
|
||||
|
|
|
|||
|
|
@ -8,9 +8,9 @@
|
|||
|
||||
# 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) ;
|
||||
|
|
|
|||
|
|
@ -318,7 +318,7 @@ class LocaleFallbackData {
|
|||
t.put("gon", "Deva");
|
||||
t.put("got", "Goth");
|
||||
t.put("gra", "Deva");
|
||||
t.put("grc", "Cprt");
|
||||
t.put("grc", "Grek");
|
||||
t.put("grt", "Beng");
|
||||
t.put("gru", "Ethi");
|
||||
t.put("gu", "Gujr");
|
||||
|
|
@ -409,7 +409,7 @@ class LocaleFallbackData {
|
|||
t.put("ka", "Geor");
|
||||
t.put("kaa", "Cyrl");
|
||||
t.put("kap", "Cyrl");
|
||||
t.put("kaw", "Kawi");
|
||||
t.put("kaw", "Bali");
|
||||
t.put("kbd", "Cyrl");
|
||||
t.put("kbg", "Tibt");
|
||||
t.put("kbu", "Arab");
|
||||
|
|
|
|||
|
|
@ -151,6 +151,7 @@ mass ; ton ; kilogram ; 907.18474 * x ; 907184.7
|
|||
mass ; tonne ; kilogram ; 1,000 * x ; 1000000.0
|
||||
mass ; earth-mass ; kilogram ; 5,972,200,000,000,000,000,000,000 * x ; 5.9722E27
|
||||
mass ; solar-mass ; kilogram ; 1,988,470,000,000,000,000,000,000,000,000 * x ; 1.98847E33
|
||||
night-duration ; night ; night ; 1 * x ; 1,000.00
|
||||
portion ; permillion ; portion ; 0.000001 * x ; 0.001
|
||||
portion ; permyriad ; portion ; 0.0001 * x ; 0.1
|
||||
portion ; permille ; portion ; 0.001 * x ; 1.0
|
||||
|
|
@ -187,6 +188,7 @@ speed ; kilometer-per-hour ; meter-per-second ; 2.5/9 * x ; 277.7778
|
|||
speed ; mile-per-hour ; meter-per-second ; 0.44704 * x ; 447.04
|
||||
speed ; knot ; meter-per-second ; 4.63/9 * x ; 514.4444
|
||||
speed ; meter-per-second ; meter-per-second ; 1 * x ; 1,000.00
|
||||
speed ; light-speed ; meter-per-second ; 299,792,458 * x ; 2.997925E11
|
||||
substance-amount ; item ; item ; 1 * x ; 1,000.00
|
||||
substance-amount ; mole ; item ; 602,214,076,000,000,000,000,000 * x ; 6.022141E26
|
||||
temperature ; rankine ; kelvin ; 5/9 * x ; 555.5556
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue