organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-10 15:42:14 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 1

ICU-21900 integrate CLDR release-41-alpha1 to ICU main for 71 front-load

Browse source
This commit is contained in:
Peter Edberg 2022-02-11 11:37:47 -08:00 • committed by Peter Edberg
parent e951f4aec4
commit 008fddfaac
61 changed files with 5458 additions and 709 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
icu4c/source/data/cldr-icu-readme.txt
View file

@ -210,21 +210,13 @@ open $ICU4C_DIR/source/data/brkitr/root.txt
Mymr{"Burmese_graphclust_model5_heavy.res"}
}
# 4f. And the time being (a ticket is being filed to generate the below from CLDR data),
# manually re-add the particles/auxVerbs entries in data/brkitr/ja.txt
# 4f. And the time being (work is in progress to generate the below from CLDR data),
# manually re-add the extensions entries in data/brkitr/ja.txt
open $ICU4C_DIR/source/data/brkitr/ja.txt
# paste the following blocks after the boundaries block and before the final closing '}':
particles{
か, かしら, から, が, くらい, けれども, こそ,
さ, さえ, しか, だけ, だに, だの, て, で, でも,
と, ところが, とも, な, など, なり, に, ね, の,
ので, のに, は, ば, ばかり, へ, ほど, まで, も,
や, やら, よ, より, わ, を
}
auxVerbs {
です, でしょ, でし, ます, ませ, まし
}
# copy in the extensions data from the current version...
# and delete any bogus extensions data that ended up in $ICU4C_DIR/source/data/locales/ja.txt
# 5. Check which data files have modifications, which have been added or removed
# (if there are no changes, you may not need to proceed further). Make sure the

1
icu4c/source/data/curr/LOCALE_DEPS.json
View file

@ -176,6 +176,7 @@
"es_VE": "es_419",
"ff_Adlm": "root",
"hi_Latn": "en_IN",
"ks_Deva": "root",
"nb": "no",
"nn": "no",
"pa_Arab": "root",

82
icu4c/source/data/curr/ks_Deva.txt Normal file
View file

@ -0,0 +1,82 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
ks_Deva{
%%Parent{"root"}
Currencies{
BRL{
"R$",
"ब्राज़िली रील",
}
CNY{
"CN¥",
"चीनी युवान",
}
EUR{
"€",
"यूरो",
}
GBP{
"£",
"बरतानवी पूनड",
}
INR{
"₹",
"इंडियन रूपी",
}
JPY{
"JP¥",
"जापानी येन",
}
RUB{
"RUB",
"रूसी रूबल",
}
USD{
"$",
"US डॉलर",
}
XXX{
"¤",
"नामोलुम करन्सी",
}
}
CurrencyPlurals{
BRL{
one{"ब्राज़िली रील"}
other{"ब्राज़िली रीलज़"}
}
CNY{
one{"चीनी युवान"}
other{"चीनी युवान"}
}
EUR{
one{"यूरो"}
other{"यूरोज़"}
}
GBP{
one{"बरतानवी पूनड"}
other{"बरतानवी पूनड"}
}
INR{
one{"इंडियन रूपी"}
other{"इंडियन रुपीज़"}
}
JPY{
one{"जापानी येन"}
other{"जापानी येन"}
}
RUB{
one{"रूसी रूबल"}
other{"रूसी रूबल"}
}
USD{
one{"US डॉलर"}
other{"US डॉलर्ज़"}
}
XXX{
one{"(करन्सी हुंद नामोलुम यूनिट)"}
other{"(नामोलुम करन्सी)"}
}
}
}

3208
icu4c/source/data/dtd/cldr/common/dtd/ldml.dtd Normal file
View file

File diff suppressed because it is too large Load diff

124
icu4c/source/data/dtd/cldr/common/dtd/ldmlICU.dtd Normal file
View file

@ -0,0 +1,124 @@
<!--
Copyright © 1991-2021 Unicode, Inc.
For terms of use, see http://www.unicode.org/copyright.html
SPDX-License-Identifier: Unicode-DFS-2016
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
-->
<!--
NOTE: Unlike the other DTDs, this file is manually maintained.
-->
<!-- ######################################################### -->
<!-- The alias, default, special and cp elements are already defined in ldml.dtd. Defining them here as well would break locale conversion. -->
<!-- ######################################################### -->
<!-- ICU Specific elements -->
<!-- ######################################################### -->
<!ATTLIST special xmlns:icu CDATA #IMPLIED>
<!ATTLIST special icu:version CDATA #IMPLIED>
<!ELEMENT icu:version EMPTY>
<!ATTLIST icu:version icu:specialVersion CDATA #FIXED "41" >
<!ATTLIST icu:version icu:requiredLDMLVersion CDATA #FIXED "41" >
<!-- ICU Scripts -->
<!ELEMENT icu:scripts (alias | icu:script* ) >
<!ATTLIST icu:scripts draft ( true | false ) #IMPLIED >
<!ATTLIST icu:scripts standard CDATA #IMPLIED >
<!ELEMENT icu:script ( #PCDATA ) >
<!ATTLIST icu:script type NMTOKEN #REQUIRED >
<!ATTLIST icu:script draft ( true | false ) #IMPLIED >
<!-- RBNF data -->
<!ELEMENT icu:ruleBasedNumberFormats ( alias | (default?, icu:ruleBasedNumberFormat*)) >
<!-- Either bare data or any number of cp -->
<!ELEMENT icu:ruleBasedNumberFormat (#PCDATA | cp)* >
<!ATTLIST icu:ruleBasedNumberFormat type NMTOKEN #IMPLIED >
<!-- RBBI data -->
<!ELEMENT icu:breakIteratorData (alias | (icu:boundaries?, icu:dictionaries?, icu:extensions?, icu:lstm?)) >
<!ELEMENT icu:boundaries (alias | (icu:grapheme?, icu:word?, icu:line*, icu:sentence?, icu:title?, icu:xgc?)) >
<!ELEMENT icu:dictionaries (alias | (icu:dictionary*)) >
<!ELEMENT icu:extensions (alias | (icu:extension*)) >
<!ELEMENT icu:extension ( #PCDATA ) >
<!ELEMENT icu:lstm (alias | (icu:lstmdata*)) >
<!ELEMENT icu:lstmdata ( #PCDATA ) >
<!ATTLIST icu:lstmdata icu:dependency NMTOKEN #IMPLIED >
<!ATTLIST icu:lstmdata type NMTOKEN #REQUIRED >
<!ELEMENT icu:dictionary ( #PCDATA ) >
<!ATTLIST icu:dictionary icu:dependency NMTOKEN #IMPLIED >
<!ATTLIST icu:dictionary type NMTOKEN #REQUIRED >
<!ELEMENT icu:grapheme ( #PCDATA ) >
<!ATTLIST icu:grapheme icu:class NMTOKEN #IMPLIED >
<!ATTLIST icu:grapheme icu:append NMTOKEN #IMPLIED >
<!ATTLIST icu:grapheme icu:import NMTOKEN #IMPLIED >
<!ATTLIST icu:grapheme icu:dependency NMTOKEN #IMPLIED >
<!ELEMENT icu:word ( #PCDATA ) >
<!ATTLIST icu:word icu:class NMTOKEN #IMPLIED >
<!ATTLIST icu:word icu:append NMTOKEN #IMPLIED >
<!ATTLIST icu:word icu:import NMTOKEN #IMPLIED >
<!ATTLIST icu:word icu:dependency NMTOKEN #IMPLIED >
<!ELEMENT icu:line ( #PCDATA ) >
<!ATTLIST icu:line icu:class NMTOKEN #IMPLIED >
<!ATTLIST icu:line icu:append NMTOKEN #IMPLIED >
<!ATTLIST icu:line icu:import NMTOKEN #IMPLIED >
<!ATTLIST icu:line icu:dependency NMTOKEN #IMPLIED >
<!ATTLIST icu:line alt NMTOKENS #IMPLIED >
<!ELEMENT icu:sentence ( #PCDATA ) >
<!ATTLIST icu:sentence icu:class NMTOKEN #IMPLIED >
<!ATTLIST icu:sentence icu:append NMTOKEN #IMPLIED >
<!ATTLIST icu:sentence icu:import NMTOKEN #IMPLIED >
<!ATTLIST icu:sentence icu:dependency NMTOKEN #IMPLIED >
<!ELEMENT icu:title ( #PCDATA ) >
<!ATTLIST icu:title icu:class NMTOKEN #IMPLIED >
<!ATTLIST icu:title icu:append NMTOKEN #IMPLIED >
<!ATTLIST icu:title icu:import NMTOKEN #IMPLIED >
<!ATTLIST icu:title icu:dependency NMTOKEN #IMPLIED >
<!ELEMENT icu:xgc ( #PCDATA ) >
<!ATTLIST icu:xgc icu:class NMTOKEN #IMPLIED >
<!ATTLIST icu:xgc icu:append NMTOKEN #IMPLIED >
<!ATTLIST icu:xgc icu:import NMTOKEN #IMPLIED >
<!ATTLIST icu:xgc icu:dependency NMTOKEN #IMPLIED >
<!--deprecated -->
<!ELEMENT icu:breakDictionaryData EMPTY >
<!ATTLIST icu:breakDictionaryData icu:class NMTOKEN #IMPLIED >
<!ATTLIST icu:breakDictionaryData icu:import NMTOKEN #IMPLIED >
<!ATTLIST icu:breakDictionaryData icu:importFile CDATA #IMPLIED >
<!-- RBT data -->
<!ELEMENT icu:transforms ( alias | (default?, icu:transform*)) >
<!ELEMENT icu:transform ( #PCDATA |cp )* >
<!ATTLIST icu:transform type NMTOKEN #REQUIRED >
<!-- leap month information, all deprecated -->
<!ELEMENT icu:isLeapMonth ( alias | (icu:nonLeapSymbol?, icu:leapSymbol? ))> <!-- deprecated -->
<!ELEMENT icu:nonLeapSymbol ( #PCDATA ) > <!-- deprecated -->
<!ELEMENT icu:leapSymbol ( #PCDATA ) > <!-- deprecated -->
<!-- UCA Rules -->
<!ELEMENT icu:UCARules EMPTY >
<!ATTLIST icu:UCARules icu:uca_rules CDATA #REQUIRED >
<!-- Dependencies Rules -->
<!ELEMENT icu:depends EMPTY >
<!ATTLIST icu:depends icu:dependency CDATA #REQUIRED >
<!-- ######################################################### -->

1
icu4c/source/data/lang/LOCALE_DEPS.json
View file

@ -176,6 +176,7 @@
"es_VE": "es_419",
"ff_Adlm": "root",
"hi_Latn": "en_IN",
"ks_Deva": "root",
"nb": "no",
"nn": "no",
"pa_Arab": "root",

90
icu4c/source/data/lang/ks_Deva.txt Normal file
View file

@ -0,0 +1,90 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
ks_Deva{
%%Parent{"root"}
Languages{
de{"जर्मन"}
de_AT{"आस्ट्रियन जर्मन"}
de_CH{"स्विस हाई जर्मन"}
en{"अंगरिज़ी"}
en_AU{"आसट्रेलवी अंगरिज़ी"}
en_CA{"कनाडियन अंगरिज़ी"}
en_GB{"बरतानवी अंगरिज़ी"}
en_US{"अमरीकी अंगरिज़ी"}
es{"हसपानवी"}
es_419{"लातिनी अमरीकी हसपानवी"}
es_ES{"यूरपी हसपानवी"}
es_MX{"मेकसिकी हसपानवी"}
fr{"फ्रांसीसी"}
fr_CA{"कनाडियन फ्रांसीसी"}
fr_CH{"स्विस फ्रांसीसी"}
it{"इतालवी"}
ja{"जापानी"}
ks{"कॉशुर"}
pt{"पुरतउगाली"}
pt_BR{"ब्राज़िली पुरतउगाली"}
pt_PT{"यूरपी पुरतउगाली"}
ru{"रूसी"}
und{"नामोलुम ज़बान"}
zh{"चीनी (तरजुम इशार: खास तोर, मैन्डरिन चीनी।)"}
zh_Hans{"आसान चीनी"}
zh_Hant{"रिवायाती चीनी"}
}
Languages%long{
zh_Hans{"आसान मैन्डरिन चीनी"}
zh_Hant{"रिवायाती मैन्डरिन चीनी"}
}
Languages%menu{
zh{"चीनी, मैन्डरिन"}
}
Languages%short{
en_GB{"UK अंगरिज़ी"}
en_US{"US अंगरिज़ी"}
}
Scripts{
Arab{"अरबी"}
Cyrl{"सिरिलिक"}
Deva{"देवनागरी"}
Hans{
"आसान (तरजुम इशार: स्क्रिप्ट नवुक यि वर्ज़न छु चीनी बापथ ज़बान नाव किस मु"
"रकब कि इस्तिमल करान।)"
}
Hant{
"रिवायाती (तरजुम इशार: स्क्रिप्ट नवुक यि वर्ज़न छु चीनी बापथ ज़बान नाव कि"
"स मुरकब कि इस्तिमल करान।)"
}
Latn{"लातिनी"}
Zxxx{"गेर तहरीर"}
Zzzz{"गेर तहरीर स्क्रिप्ट"}
}
Scripts%stand-alone{
Hans{
"आसान हान (तरजुम इशार: स्क्रिप्ट नवुक यि वर्ज़न छु अलग इस्तिमाल सपदन, यि "
"छु नि चीनी ज़बान बापथ ज़बान नवास सीथ मुरकब।)"
}
Hant{
"रिवायाती हान (तरजुम इशार: स्क्रिप्ट नवुक यि वर्ज़न छु अलग इस्तिमाल सपदन,"
" यि छु नि चीनी ज़बान बापथ ज़बान नवास सीथ मुरकब।)"
}
}
Types{
calendar{
gregorian{"ग्रिगोरियन कैलंडर"}
}
collation{
standard{"मियारी तरतीब ऑर्डर"}
}
numbers{
arab{"अरबी-इंडिक हिंदसी"}
arabext{"तोसी शुद अरबी-इंडिक हिंदसी"}
deva{"देवनागरी हिंदसि"}
latn{"यूरपी हिंदसी"}
}
}
codePatterns{
language{"ज़बान: {0}"}
script{"स्क्रिप्ट: {0}"}
territory{"अलाक़: {0}"}
}
}

1
icu4c/source/data/locales/LOCALE_DEPS.json
View file

@ -176,6 +176,7 @@
"es_VE": "es_419",
"ff_Adlm": "root",
"hi_Latn": "en_IN",
"ks_Deva": "root",
"nb": "no",
"nn": "no",
"pa_Arab": "root",

2
icu4c/source/data/locales/en_ZA.txt
View file

@ -4,7 +4,7 @@
en_ZA{
%%Parent{"en_001"}
AuxExemplarCharacters{
"[á à ă â å ä ā æ ç ḓ é è ĕ ê ë ē í ì ĭ î ï ī ḽ ṅ ṋ ñ ó ò ŏ ô ö ø ō œ š ṱ ú ù"
"[á à ă â å ä ā æ ç ḓ é è ĕ ê ë ē í ì ĭ î ï ī ḽ ñ ṅ ṋ ó ò ŏ ô ö ø ō œ š ṱ ú ù"
" ŭ û ü ū ÿ]"
}
ExemplarCharactersNumbers{"[  \\- ‑ , % ‰ + 0 1 2 3 4 5 6 7 8 9]"}

3
icu4c/source/data/locales/es_419.txt
View file

@ -11,15 +11,12 @@ es_419{
patternsLong{
decimalFormat{
1000000000000{
one{"0 billón"}
other{"0 billón"}
}
10000000000000{
one{"00 billones"}
other{"00 billones"}
}
100000000000000{
one{"000 billones"}
other{"000 billones"}
}
}

3
icu4c/source/data/locales/es_MX.txt
View file

@ -9,15 +9,12 @@ es_MX{
patternsLong{
decimalFormat{
1000000000000{
one{"0 billón"}
other{"0 billones"}
}
10000000000000{
one{"00 billones"}
other{"00 billones"}
}
100000000000000{
one{"000 billones"}
other{"000 billones"}
}
}

2
icu4c/source/data/locales/hi.txt
View file

@ -2,7 +2,7 @@
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
hi{
AuxExemplarCharacters{"[\u200C \u200D \u0944]"}
AuxExemplarCharacters{"[\u200C\u200D \u0944]"}
Ellipsis{
final{"{0}…"}
initial{"…{0}"}

2
icu4c/source/data/locales/kea.txt
View file

@ -14,7 +14,7 @@ kea{
word-initial{"… {0}"}
word-medial{"{0} … {1}"}
}
ExemplarCharacters{"[a b d {dj} e f g h i j k l {lh} m n {nh} ñ o p r s t {tx} u v x y z]"}
ExemplarCharacters{"[a b d {dj} e f g h i j k l {lh} m n ñ {nh} o p r s t {tx} u v x y z]"}
ExemplarCharactersIndex{"[A B D E F G H I J K L M N O P R S T U V X Z]"}
ExemplarCharactersNumbers{"[  \\- ‑ , % ‰ + 0 1 2 3 4 5 6 7 8 9]"}
ExemplarCharactersPunctuation{

2
icu4c/source/data/locales/kok.txt
View file

@ -2,7 +2,7 @@
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
kok{
AuxExemplarCharacters{"[\u200C \u200D \u0944]"}
AuxExemplarCharacters{"[\u200C\u200D \u0944]"}
ExemplarCharacters{
"[\u093C ० १ २ ३ ४ ५ ६ ७ ८ ९ ॐ \u0902 \u0901 ः अ आ इ ई उ ऊ ऋ ऌ ऍ ए ऐ ऑ ओ औ क "
"{क\u093C} ख {ख\u093C} ग {ग\u093C} घ ङ च छ ज {ज\u093C} झ ञ ट ठ ड {ड\u093C} ढ "

2
icu4c/source/data/locales/ks.txt
View file

@ -2,7 +2,7 @@
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
ks{
AuxExemplarCharacters{"[\u200E\u200F \u064E \u064F \u0650 \u0654 \u0655 \u065F \u0656 \u0657]"}
AuxExemplarCharacters{"[\u200E\u200F \u064E \u064F \u0650 \u0654 \u0655 \u065F \u0656 \u0657 ئ]"}
ExemplarCharacters{
"[ء آ أ ٲ ؤ ا ب پ ت ث ٹ ج چ ح خ د ذ ڈ ر ز ڑ ژ س ش ص ض ط ظ ع غ ف ق ک گ ل م ن ں"
" ھ ہ و ۄ ۆ ی ۍ ؠ ے]"

339
icu4c/source/data/locales/ks_Deva.txt Normal file
View file

@ -0,0 +1,339 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
ks_Deva{
%%Parent{"root"}
AuxExemplarCharacters{"[\u200C\u200D]"}
ExemplarCharacters{
"[\u093C \u0901 अ आ इ ई उ ऊ ए ऑ ओ क ख ग च {च\u093C} छ {छ\u093C} ज ट ठ ड त थ द"
" न प फ ब म य र ल व श स ह ा ि ी \u0941 \u0942 \u0943 \u0944 \u0945 \u0947 "
"\u0948 ॉ ो ौ \u094D]"
}
ExemplarCharactersNumbers{"[\\- ‑ , . % ‰ + 0 1 2 3 4 5 6 7 8 9]"}
ExemplarCharactersPunctuation{
"[\\- ‐ ‑ – — , ; \\: ! ? . … ' ‘ ’ \u0022 “ ” ( ) \\[ \\] § @ * / \\& # † ‡ "
"′ ″]"
}
MoreInformation{"?"}
calendar{
generic{
DateTimePatterns{
"a h:mm:ss zzzz",
"a h:mm:ss z",
"a h:mm:ss",
"a h:mm",
"G y MMMM d, EEEE",
"G y MMMM d",
"G y MMM d",
"GGGGG y-MM-dd",
"{1} {0}",
"{0} पेठ {1}",
"{0} पेठ {1}",
"{1} {0}",
"{1} {0}",
}
}
gregorian{
DateTimePatterns{
"a h:mm:ss zzzz",
"a h:mm:ss z",
"a h:mm:ss",
"a h:mm",
"EEEE, d MMMM y",
"d MMMM y",
"d MMM y",
"d/M/yy",
"{1}, {0}",
"{0} पेठ {1}",
"{0} पेठ {1}",
"{1}, {0}",
"{1}, {0}",
}
dayNames{
format{
narrow{
"अ",
"च",
"ब",
"ब",
"ब",
"ज",
"ब",
}
wide{
"आथवार",
"चंदिरवार",
"बुवार",
"बोदवार",
"ब्रेसवार",
"जुम्मा",
"बटवार",
}
}
stand-alone{
narrow{
"अ",
"च",
"ब",
"ब",
"ब",
"ज",
"ब",
}
wide{
"आथवार",
"चंदिरवार",
"बुवार",
"बोदवार",
"ब्रेसवार",
"जुम्मा",
"बटवार",
}
}
}
eras{
abbreviated{
"BC",
"AD",
}
}
monthNames{
format{
abbreviated{
"जनवरी",
"फ़रवरी",
"मार्च",
"अप्रैल",
"मे",
"जून",
"जुलाई",
"अगस्त",
"सतुंबर",
"अकतुम्बर",
"नवूमबर",
"दसूमबर",
}
narrow{
"ज",
"फ़",
"म",
"अ",
"म",
"ज",
"ज",
"अ",
"स",
"ओ",
"न",
"द",
}
wide{
"जनवरी",
"फ़रवरी",
"मार्च",
"अप्रैल",
"मे",
"जून",
"जुलाई",
"अगस्त",
"सतुंबर",
"अकतुम्बर",
"नवूमबर",
"दसूमबर",
}
}
stand-alone{
narrow{
"ज",
"फ़",
"म",
"अ",
"म",
"ज",
"ज",
"अ",
"स",
"ओ",
"न",
"द",
}
wide{
"जनवरी",
"फ़रवरी",
"मार्च",
"अप्रैल",
"मे",
"जून",
"जुलाई",
"अगस्त",
"सतुंबर",
"अकतुम्बर",
"नवूमबर",
"दसूमबर",
}
}
}
quarters{
format{
abbreviated{
"Q1",
"Q2",
"Q3",
"Q4",
}
wide{
"1st सह माह",
"2nd सह माह",
"3rd सह माह",
"4th सह माह",
}
}
stand-alone{
abbreviated{
"Q1",
"Q2",
"Q3",
"Q4",
}
wide{
"1st सह माह",
"2nd सह माह",
"3rd सह माह",
"4th सह माह",
}
}
}
}
}
fields{
day{
dn{"दोह"}
relative{
"-1"{"राथ"}
"0"{"अज़"}
"1"{"पगाह"}
}
}
day-narrow{
dn{"दोह"}
relative{
"-1"{"राथ"}
"0"{"अज़"}
"1"{"पगाह"}
}
}
day-short{
dn{"दोह"}
relative{
"-1"{"राथ"}
"0"{"अज़"}
"1"{"पगाह"}
}
}
dayperiod{
dn{"AM/PM"}
}
era{
dn{"दोर"}
}
hour{
dn{"गनटि"}
}
hour-narrow{
dn{"गनटि"}
}
hour-short{
dn{"गनटि"}
}
minute{
dn{"मिनट"}
}
minute-narrow{
dn{"मिनट"}
}
minute-short{
dn{"मिनट"}
}
month{
dn{"माह"}
}
month-narrow{
dn{"माह"}
}
month-short{
dn{"माह"}
}
quarter{
dn{"चूरिम"}
}
quarter-narrow{
dn{"चूरिम"}
}
quarter-short{
dn{"चूरिम"}
}
second{
dn{"सेकंड"}
}
second-narrow{
dn{"सेकंड"}
}
second-short{
dn{"सेकंड"}
}
week{
dn{"हफ़ति"}
}
week-narrow{
dn{"हफ़ति"}
}
week-short{
dn{"हफ़ति"}
}
weekday{
dn{"हफ़तूक दोह"}
}
year{
dn{"वरीह"}
}
year-narrow{
dn{"वरीह"}
}
year-short{
dn{"वरीह"}
}
zone{
dn{"वख ज़ून"}
}
}
listPattern{
standard{
2{"{0} ति {1}"}
end{"{0}, ति {1}"}
}
}
measurementSystemNames{
metric{"मेट्रिक"}
}
parse{
date{
lenient{
"[\\--/]",
"[\\:∶︓﹕：]",
}
}
general{
lenient{
"[.․。︒﹒．｡]",
"['ʼ՚᾽᾿’＇]",
"[%٪﹪％]",
"[؉‰]",
"[\$﹩＄]",
"[£₤￡]",
"[¥￥]",
"[₩￦]",
"[₨₹{Rp}{Rs}]",
}
}
}
}

5
icu4c/source/data/locales/ks_Deva_IN.txt Normal file
View file

@ -0,0 +1,5 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
ks_Deva_IN{
}

4
icu4c/source/data/locales/ml.txt
View file

@ -2545,8 +2545,8 @@ ml{
or{
2{"{0} അല്ലെങ്കിൽ {1}"}
end{"{0}, അല്ലെങ്കിൽ {1}"}
middle{"{0}, {1} എന്നിവ"}
start{"{0}, {1} എന്നിവ"}
middle{"{0}, {1}"}
start{"{0}, {1}"}
}
standard{
2{"{0} കൂടാതെ {1}"}

2
icu4c/source/data/locales/mr.txt
View file

@ -2,7 +2,7 @@
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
mr{
AuxExemplarCharacters{"[\u200C \u200D \u0944]"}
AuxExemplarCharacters{"[\u200C\u200D \u0944]"}
Ellipsis{
final{"{0}…"}
initial{"…{0}"}

2
icu4c/source/data/locales/ne.txt
View file

@ -2,7 +2,7 @@
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
ne{
AuxExemplarCharacters{"[\u200C \u200D \u0944]"}
AuxExemplarCharacters{"[\u200C\u200D \u0944]"}
Ellipsis{
final{"{0}…"}
initial{"…{0}"}

16
icu4c/source/data/locales/ur_IN.txt
View file

@ -217,20 +217,4 @@ ur_IN{
}
}
}
listPattern{
unit{
2{"{1}، {0}"}
end{"{1}، {0}"}
}
unit-narrow{
2{"{1} {0}"}
end{"{1} {0}"}
middle{"{1} {0}"}
start{"{1} {0}"}
}
unit-short{
2{"{1}، {0}"}
end{"{1}، {0}"}
}
}
}

4
icu4c/source/data/misc/icuver.txt
View file

@ -9,6 +9,6 @@
// ***************************************************************************
icuver:table(nofallback){
CLDRVersion{"41"}
DataVersion{"70.1.0.0"}
ICUVersion{"70.1.0.0"}
DataVersion{"71.0.1.0"}
ICUVersion{"71.0.1.0"}
}

1096
icu4c/source/data/misc/langInfo.txt
View file

File diff suppressed because it is too large Load diff

1
icu4c/source/data/misc/likelySubtags.txt
View file

@ -1078,6 +1078,7 @@ likelySubtags:table(nofallback){
scs{"scs_Latn_CA"}
sd{"sd_Arab_PK"}
sd_Deva{"sd_Deva_IN"}
sd_IN{"sd_Deva_IN"}
sd_Khoj{"sd_Khoj_IN"}
sd_Sind{"sd_Sind_IN"}
sdc{"sdc_Latn_IT"}

2
icu4c/source/data/misc/supplementalData.txt
View file

@ -29675,7 +29675,7 @@ supplementalData:table(nofallback){
}
sd_Deva{
officialStatus{"official_regional"}
populationShareF:int{46260000}
populationShareF:int{47140000}
}
srx{
populationShareF:int{46350000}

1
icu4c/source/data/region/LOCALE_DEPS.json
View file

@ -176,6 +176,7 @@
"es_VE": "es_419",
"ff_Adlm": "root",
"hi_Latn": "en_IN",
"ks_Deva": "root",
"nb": "no",
"nn": "no",
"pa_Arab": "root",

19
icu4c/source/data/region/ks_Deva.txt Normal file
View file

@ -0,0 +1,19 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
ks_Deva{
%%Parent{"root"}
Countries{
BR{"ब्राज़ील"}
CN{"चीन"}
DE{"जर्मन"}
FR{"फ्रांस"}
GB{"मुतहीद बादशाहत"}
IN{"भारत"}
IT{"इटली"}
JP{"जापान"}
RU{"रूस"}
US{"मूतहीद रियासत"}
ZZ{"नामोलुम अलाक़"}
}
}

4
icu4c/source/data/translit/Zawgyi_my.txt
View file

@ -55,14 +55,14 @@ $wspace = [\u0020\u00a0\u1680\u2000-\u200d\u2060\u202f\u205f\u3000\ufeff];
\u1090 → \u101B ;
\u1086 → \u103F ;
# yapin
[\u103A|\u107d] → \u103B ;
[\u103A\u107d] → \u103B ;
# yayit
($zmedialra)+ → \u103C ;
# wasway
\u103C* \u108A → \u103D \u103E; # To avoid duplicate medials
\u103C → \u103D ;
# hatoh
[\u103D|\u1087] → \u103E ;
[\u103D\u1087] → \u103E ;
\u1088 → \u103E \u102F ;
\u1089 → \u103E \u1030 ;
# Vowels

84
icu4c/source/data/translit/my_Zawgyi.txt
View file

@ -17,7 +17,7 @@
# The transform is done in two main stages:
# (1) Map all Unicode codepoints to their Zawgyi counterparts.
# (2) Perform reordering.
# Modern Burmese digits & Unicode code points.
# Modern Burmese digits and Unicode code points.
$nondigits = [^\u1040-\u1049];
$consonant = [\u1000-\u1021];
$narrowconsonant = [\u1001\u1002\u1004\u1005\u1007\u100b-\u100e\u1012\u1013\u1015-\u1017\u1019\u101d\u1020\u1025\u1026\u108f];
@ -28,8 +28,8 @@ $vowelsign = [\u102B-\u1030\u1032];
$vowelmedial = [\u102B-\u1030\u1032\u103c-\u103F];
$ukinzi = [\u1004\u101b\u105a]\u103A\u1039;
$medialraZ = [\u103b\u107e-\u1084];
$lowsignZ = [\u102f\u1030\u1037\u103a\u103c\u103d\u1087-\u108a];
$highsignZ = [\u102d\u102e\u1032\u1036\u1039\u103d-\u103e\u1064];
$lowsignZ = [\u102f\u1030\u1037\u103c\u103d\u1087-\u108a];
$highsignZ = [\u102d\u102e\u1032\u1036\u1039\u1064];
$subscriptitem = [\u1060-\u1063\u1064-\u1068\u106c\u106d\u1070-\u107c\u1085\u1093\u1096];
$vowelsAndConsonants = [\u1000-\u102a];
#### Phase 0: CODEPOINT MAPPING FROM UNICODE TO ZAWGYI
@ -75,9 +75,6 @@ $ukinzi ($consonant) > $1 \u1064 ;
\u1039 \u1008 > \u1069 ;
\u1039 \u100B > \u106C ;
\u1039 \u100C > \u106D ;
\u1039 \u100D > \u106E ;
\u100d \u1039 \u100E > \u106F ;
\u1039 \u100E > \u106F ;
\u1039 \u100F > \u1070 ;
\u1039 \u1010 > \u1072 ;
\u1039 \u1011 > \u1074 ;
@ -91,22 +88,27 @@ $ukinzi ($consonant) > $1 \u1064 ;
\u1039 \u1019 > \u107C ;
\u1039 \u101C > \u1085 ;
\u100d\u1039\u100D > \u106E ;
\u100d\u1039\u100E > \u106F ;
\u100F\u1039\u100D > \u1091 ;
\u100B\u1039\u100C > \u1092 ;
\u100B\u1039\u100B > \u1097 ;
\u104E\u1004\u103A\u1038 > \u104E ;
#### PHASE 1: Everything is now in Zawgyi code points. REORDERING RULES.
::Null;
# Handle Na with lower modifiers, medial ra.
\u1014 ($subscriptitem) ($highsignZ*) \u103b > \u103b \u108f $1 $2;
\u1014 \u103b ([\u103c\u103d]*) (\u1031*) > $2 \u103b \u108f $1;
# E Vowel + medial ra. Move the e vowel
($consonant) \u103b \u1031 > \u1031 \u103b $1 ;
($consonant) \u103b ([\u103c\u103d]*) \u1031 > \u1031 \u103b $1 $2;
($consonant) \u103b > \u103b $1 ;
($consonant) \u103d \u1031 \u1037 > \u1031 $1 \u1094 \u103D ;
($consonant) (\u108a) \u1031 > \u1031 $1 $2 ;
($consonant) ([\u103a\u103d\u103e]+) \u1031 > \u1031 $1 $2 ;
# Ra + kinzi
($consonant) \u1064 \u103b > \u103b $1 \u1064 ;
# E vowel plus medials
($consonant) ([\u103a\u103c-\u103d]) \u1031 > \u1031 $1 $2 ;
($consonant) ([\u103a\u103c-\u103d]+) \u1031 > \u1031 $1 $2 ;
# Handle consonant, subscripted consonant, medial ra
($consonant) ($subscriptitem) ($highsignZ*) \u103b > \u103b $1 $2 $3 ;
# No medials intervening.
($vowelsAndConsonants) \u1031 > \u1031 $1 ;
# Handle Na with lower modifiers.
@ -114,8 +116,6 @@ $ukinzi ($consonant) > $1 \u1064 ;
\u1014 ($lowsignZ) ($highsignZ) \u1037 > \u108f $1 $2 \u1094;
\u1014 ($highsignZ) ($lowsignZ) \u1037 > \u108f $1 $2 \u1094;
\u1014 ($highsignZ) \u1037 > \u1014 $1 \u1094;
# Two medials
\u103a \u103c > \u107d \u103c;
# a special case
\u1014 \u1032 \u1037 > \u1014 \u1032 \u1094;
\u1014 \u1037 > \u1014 \u1094;
@ -134,29 +134,34 @@ $ukinzi ($consonant) > $1 \u1064 ;
\u1025 \u102E > \u1026;
\u1037 \u103A > \u103A \u1037;
([\u102B\u102C\u102F\u1030]) ([\u102D\u102E\u1032]) > $2 $1;
# Medial plus vowel sign U
($medialraZ) ($consonant) \u102f > $1 $2 \u1033;
## Phase 2: Further adjustments
::Null;
# Handle consonant, subscripted consonant, medial ra
($narrowconsonant) ($subscriptitem) ($highsignZ) $medialraZ > \u1083 $1 $2 $3 ;
($wideconsonant) ($subscriptitem) ($highsignZ) $medialraZ > \u1084 $1 $2 ;
($narrowconsonant) ($subscriptitem) $medialraZ > \u1081 $1 $2 ;
($wideconsonant) ($subscriptitem) $medialraZ > \u1082 $1 $2 ;
# Two medials
\u103a \u103c > \u103c \u107d;
\u103c \u1094 > \u103c \u1095 ;
# Medial ra variations, context dependent
$medialraZ ($narrowconsonant) \u102d \u103d \u102f > \u107f $1 \u102d \u1087 \u1083 ;
$medialraZ ($wideconsonant) \u102d \u103d \u102f > \u1080 $1 \u102d \u1087 \u1083 ;
$medialraZ ($narrowconsonant) ($lowsignZ) ($highsignZ) > \u1083 $1 $2 $3 ;
$medialraZ ($wideconsonant) ($lowsignZ) ($highsignZ) > \u1084 $1 $2 $3 ;
$medialraZ ($narrowconsonant) ($highsignZ) > \u107f $1 $2 ;
$medialraZ ($wideconsonant) ($highsignZ) > \u1080 $1 $2 ;
$medialraZ ($narrowconsonant) \u1030 > \u103b $1 \u1034 ;
$medialraZ ($wideconsonant) \u1030 > \u107e $1 \u1034 ;
$medialraZ ($narrowconsonant) (\u102f) > \u103b $1 \u1033 ;
$medialraZ ($wideconsonant) (\u102f) > \u107e $1 \u1033 ;
$medialraZ ($narrowconsonant) ($lowsignZ) > \u1081 $1 $2 ;
$medialraZ ($wideconsonant) ($lowsignZ) > \u1082 $1 $2 ;
$medialraZ ($narrowconsonant) ($subscriptitem) ($highsignZ) > \u1083 $1 $2 $3 ;
$medialraZ ($wideconsonant) ($subscriptitem) ($highsignZ) > \u1084 $1 $2 $3;
$medialraZ ($narrowconsonant) ($subscriptitem) > \u1081 $1 $2 ;
$medialraZ ($wideconsonant) ($subscriptitem) > \u1082 $1 $2 ;
$medialraZ ($narrowconsonant) ([\u103c\u108a]) ($highsignZ) > \u1083 $1 $2 $3 ;
$medialraZ ($wideconsonant) ([\u103c\u108a]) ($highsignZ) > \u1084 $1 $2 $3 ;
$medialraZ ($narrowconsonant) \u103d ($highsignZ) > \u107f $1 \u1087 $2;
$medialraZ ($wideconsonant) \u103d ($highsignZ) > \u1080 $1 \u1087 $2;
$medialraZ ($narrowconsonant) \u102f ($highsignZ) > \u107f $1 \u1033 $2;
$medialraZ ($wideconsonant) \u102f ($highsignZ) > \u1080 $1 \u1033 $2;
$medialraZ ($narrowconsonant) \u1030 ($highsignZ) > \u107f $1 \u1034 $2;
$medialraZ ($wideconsonant) \u1030 ($highsignZ) > \u1080 $1 \u1034 $2;
$medialraZ ($narrowconsonant) ($lowsignZ*) ($highsignZ) > \u107f $1 $2 $3;
$medialraZ ($wideconsonant) ($lowsignZ*) ($highsignZ) > \u1080 $1 $2 $3;
$medialraZ ($narrowconsonant) ([\u103c\u108a]) > \u1081 $1 $2 ;
$medialraZ ($wideconsonant) ([\u103c\u108a]) > \u1082 $1 $2 ;
$medialraZ ($narrowconsonant) \u103d > \u103b $1 \u1087;
$medialraZ ($wideconsonant) \u103d > \u107e $1 \u1087;
$medialraZ ($narrowconsonant) \u102f > \u103b $1 \u1033;
$medialraZ ($wideconsonant) \u102f > \u107e $1 \u1033;
$medialraZ ($narrowconsonant) \u1030 > \u103b $1 \u1034;
$medialraZ ($wideconsonant) \u1030 > \u107e $1 \u1034;
$medialraZ ($widenya) > \u1082 $1 ;
$medialraZ ($othernya) > \u103b \u106a ;
$medialraZ ($narrowconsonant) > \u103b $1 ;
@ -171,22 +176,21 @@ $medialraZ ($wideconsonant) > \u107e $1 ;
\u1064 \u102e > \u108c ;
##### Phase 3
::Null;
([\u103C\u103D\u103E]+) \u103B > \u103B $1;
([\u103D\u103E]+) \u103C > \u103C $1;
\u103E\u103D > \u103D\u103E ;
\u1037 ([\u102D-\u1030\u1032\u1036]) > $1 \u1037;
($consonant) ([\u102B-\u1032\u1036\u103B-\u103E]) \u103A ($consonant)> $1 \u103A $2 $3;
# Combine vowel and consonant signs
\u103d \u102f > \u1088;
\u1033 \u1094 > \u1033 \u1095; # Wider spacing on lower dot
($medialraZ) ($consonant) ($highsignZ) \u102f > $1 $2 $3 \u1033;
($medialraZ) ($narrowconsonant) ($lowsignZ*) ($highsignZ*) \u102f > $1 $2 $3 $4 \u1033;
($medialraZ) ($wideconsonant) ($lowsignZ*) ($highsignZ*) \u102f > $1 $2 $3 $4 \u1033;
($medialraZ) ($narrowconsonant) ($lowsignZ*) ($highsignZ*) \u1030 > $1 $2 $3 $4 \u1034;
($medialraZ) ($wideconsonant) ($lowsignZ*) ($highsignZ*) \u1030 > $1 $2 $3 $4 \u1034;
##### Phase 4. More reorderings of medials
::Null;
([\u103D\u103E]) \u103C > \u103C $1;
\u103E\u103D > \u103D\u103E ;
\u1038 ($vowelmedial) > $1 \u1038;
\u1038 ([\u1036\u1037\u103A]) > $1 \u1038;
\u1036 \u102f > \u102f \u1036;
\u103a ([\u1064\u108b-\u108e]) \u102d \u102f > \u103a $1 \u102d \u1033;
\u103a \u102d \u102f > \u103a \u102d \u1033;
#### Phase 5
@ -216,10 +220,10 @@ $medialraZ ($wideconsonant) > \u107e $1 ;
\u103D \u103D+ > \u103D;
\u103E \u103E+ > \u103E;
# Visually identical orderings - standardize
\u102f \u102D > \u102D \u102f ;
\u102f \u1036 > \u1036 \u102f ;
\u1039 \u1037 > \u1037 \u1039 ;
\u103c \u1032 > \u1032 \u103c ;
\u103c \u102e > \u102e \u103c ;
([\u102f\u1033]) \u102D > \u102D $1 ;
([\u102f\u1033]) \u1036 > \u1036 $1 ;
\u1037 \u1039 > \u1039 \u1037;
\u1032 \u103c > \u103c \u1032 ;
\u102e \u103c > \u103c \u102e ;
\u103d \u1088 > \u1088 ;

1
icu4c/source/data/unit/LOCALE_DEPS.json
View file

@ -176,6 +176,7 @@
"es_VE": "es_419",
"ff_Adlm": "root",
"hi_Latn": "en_IN",
"ks_Deva": "root",
"nb": "no",
"nn": "no",
"pa_Arab": "root",

6
icu4c/source/data/unit/ks_Deva.txt Normal file
View file

@ -0,0 +1,6 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
ks_Deva{
%%Parent{"root"}
}

580
icu4c/source/data/unit/sr_Latn.txt
View file

@ -29,8 +29,17 @@ sr_Latn{
other{"{0} ge sila"}
}
meter-per-square-second{
case{
genitive{
one{"{0} metra u sekundi na kvadrat"}
}
instrumental{
one{"{0} metrom u sekundi na kvadrat"}
}
}
dnam{"metri u sekundi na kvadrat"}
few{"{0} metra u sekundi na kvadrat"}
gender{"inanimate"}
one{"{0} metar u sekundi na kvadrat"}
other{"{0} metara u sekundi na kvadrat"}
}
@ -159,8 +168,17 @@ sr_Latn{
other{"{0} hektara"}
}
square-centimeter{
case{
genitive{
one{"{0} kvadratnog centimetra"}
}
instrumental{
one{"{0} kvadratnim centimetrom"}
}
}
dnam{"kvadratni centimetri"}
few{"{0} kvadratna centimetra"}
gender{"inanimate"}
one{"{0} kvadratni centimetar"}
other{"{0} kvadratnih centimetara"}
per{"{0}/cm²"}
@ -179,15 +197,33 @@ sr_Latn{
per{"{0}/in²"}
}
square-kilometer{
case{
genitive{
one{"{0} kvadratna kilometra"}
}
instrumental{
one{"{0} kvadratnim kilometrom"}
}
}
dnam{"kvadratni kilometri"}
few{"{0} kvadratna kilometra"}
gender{"inanimate"}
one{"{0} kvadratni kilometar"}
other{"{0} kvadratnih kilometara"}
per{"{0} po kvadratnom kilometru"}
}
square-meter{
case{
genitive{
one{"{0} kvadratna metra"}
}
instrumental{
one{"{0} kvadratnim metrom"}
}
}
dnam{"kvadratni metri"}
few{"{0} kvadratna metra"}
gender{"inanimate"}
one{"{0} kvadratni metar"}
other{"{0} kvadratnih metara"}
per{"{0}/m²"}
@ -274,8 +310,20 @@ sr_Latn{
}
concentr{
item{
case{
accusative{
one{"{0} stavku"}
}
genitive{
one{"{0} stavke"}
}
instrumental{
one{"{0} stavkom"}
}
}
dnam{"stavke"}
few{"{0} stavke"}
gender{"feminine"}
one{"{0} stavka"}
other{"{0} stavki"}
}
@ -304,8 +352,17 @@ sr_Latn{
other{"{0} miligrama po decilitru"}
}
millimole-per-liter{
case{
genitive{
one{"{0} milimola po litri"}
}
instrumental{
one{"{0} milimolom po litri"}
}
}
dnam{"milimol po litri"}
few{"{0} milimola po litri"}
gender{"inanimate"}
one{"{0} milimol po litri"}
other{"{0} milimola po litri"}
}
@ -396,14 +453,32 @@ sr_Latn{
}
consumption{
liter-per-100-kilometer{
case{
genitive{
one{"{0} litra na 100 kilometara"}
}
instrumental{
one{"{0} litrom na 100 kilometara"}
}
}
dnam{"litri na 100 kilometara"}
few{"{0} litra na 100 kilometara"}
gender{"inanimate"}
one{"{0} litar na 100 kilometara"}
other{"{0} litara na 100 kilometara"}
}
liter-per-kilometer{
case{
genitive{
one{"{0} litra po kilometru"}
}
instrumental{
one{"{0} litrom po kilometru"}
}
}
dnam{"litri po kilometru"}
few{"{0} litra po kilometru"}
gender{"inanimate"}
one{"{0} litar po kilometru"}
other{"{0} litara po kilometru"}
}
@ -465,56 +540,142 @@ sr_Latn{
other{"{0} bajtova"}
}
gigabit{
case{
genitive{
one{"{0} gigabita"}
}
instrumental{
one{"{0} gigabitom"}
}
}
dnam{"gigabitovi"}
few{"{0} gigabita"}
gender{"inanimate"}
one{"{0} gigabit"}
other{"{0} gigabitova"}
}
gigabyte{
case{
genitive{
one{"{0} gigabajta"}
}
instrumental{
one{"{0} gigabajtom"}
}
}
dnam{"gigabajti"}
few{"{0} gigabajta"}
gender{"inanimate"}
one{"{0} gigabajt"}
other{"{0} gigabajtova"}
}
kilobit{
case{
genitive{
one{"{0} kilobita"}
}
instrumental{
one{"{0} kilobitom"}
}
}
dnam{"kilobitovi"}
few{"{0} kilobita"}
gender{"inanimate"}
one{"{0} kilobit"}
other{"{0} kilobitova"}
}
kilobyte{
case{
genitive{
one{"{0} kilobajta"}
}
instrumental{
one{"{0} kilobajtom"}
}
}
dnam{"kilobajti"}
few{"{0} kilobajta"}
gender{"inanimate"}
one{"{0} kilobajt"}
other{"{0} kilobajtova"}
}
megabit{
case{
genitive{
one{"{0} megabita"}
}
instrumental{
one{"{0} megabitom"}
}
}
dnam{"megabitovi"}
few{"{0} megabita"}
gender{"inanimate"}
one{"{0} megabit"}
other{"{0} megabitova"}
}
megabyte{
case{
genitive{
one{"{0} megabajta"}
}
instrumental{
one{"{0} megabajtom"}
}
}
dnam{"megabajti"}
few{"{0} megabajta"}
gender{"inanimate"}
one{"{0} megabajt"}
other{"{0} megabajtova"}
}
petabyte{
case{
genitive{
one{"{0} petabajta"}
}
instrumental{
one{"{0} petabajtom"}
}
}
dnam{"petabajti"}
few{"{0} petabajta"}
gender{"inanimate"}
one{"{0} petabajt"}
other{"{0} petabajtova"}
}
terabit{
case{
genitive{
one{"{0} terabita"}
}
instrumental{
one{"{0} terabitom"}
}
}
dnam{"terabitovi"}
few{"{0} terabita"}
gender{"inanimate"}
one{"{0} terabit"}
other{"{0} terabitova"}
}
terabyte{
case{
accusative{
other{"{0} terabajtova"}
}
genitive{
one{"{0} terabajta"}
other{"{0} terabajtova"}
}
instrumental{
one{"{0} terabajtom"}
other{"{0} terabajtova"}
}
}
dnam{"terabajti"}
few{"{0} terabajta"}
gender{"inanimate"}
one{"{0} terabajt"}
other{"{0} terabajta"}
}
@ -598,14 +759,35 @@ sr_Latn{
per{"{0}/sat"}
}
microsecond{
case{
accusative{
one{"{0} mikrosekundu"}
}
genitive{
one{"{0} mikrosekunde"}
}
instrumental{
one{"{0} mikrosekundom"}
}
}
dnam{"mikrosekunde"}
few{"{0} mikrosekunde"}
gender{"feminine"}
one{"{0} mikrosekunda"}
other{"{0} mikrosekundi"}
}
millisecond{
case{
genitive{
one{"{0} milisekunde"}
}
instrumental{
one{"{0} milisekundom"}
}
}
dnam{"milisekunde"}
few{"{0} milisekunde"}
gender{"feminine"}
one{"{0} milisekunda"}
other{"{0} milisekundi"}
}
@ -648,8 +830,20 @@ sr_Latn{
per{"{0} mesečno"}
}
nanosecond{
case{
accusative{
one{"{0} nanosekunde"}
}
genitive{
one{"{0} nanosekunde"}
}
instrumental{
one{"{0} nanosekundom"}
}
}
dnam{"nanosekunde"}
few{"{0} nanosekunde"}
gender{"feminine"}
one{"{0} nanosekunda"}
other{"{0} nanosekundi"}
}
@ -731,8 +925,17 @@ sr_Latn{
other{"{0} ampera"}
}
milliampere{
case{
genitive{
one{"{0} miliampera"}
}
instrumental{
one{"{0} miliamperom"}
}
}
dnam{"miliamperi"}
few{"{0} miliampera"}
gender{"inanimate"}
one{"{0} miliamper"}
other{"{0} miliampera"}
}
@ -832,14 +1035,32 @@ sr_Latn{
other{"{0} kilokalorija"}
}
kilojoule{
case{
genitive{
one{"{0} kilodžula"}
}
instrumental{
one{"{0} kilodžulom"}
}
}
dnam{"kilodžuli"}
few{"{0} kilodžula"}
gender{"inanimate"}
one{"{0} kilodžul"}
other{"{0} kilodžula"}
}
kilowatt-hour{
case{
genitive{
one{"{0} kilovat-sata"}
}
instrumental{
one{"{0} kilovat-satom"}
}
}
dnam{"kilovat-sati"}
few{"{0} kilovat-sata"}
gender{"inanimate"}
one{"{0} kilovat-sat"}
other{"{0} kilovat-sati"}
}
@ -851,6 +1072,9 @@ sr_Latn{
}
}
force{
kilowatt-hour-per-100-kilometer{
gender{"inanimate"}
}
newton{
case{
accusative{
@ -878,8 +1102,17 @@ sr_Latn{
}
frequency{
gigahertz{
case{
genitive{
one{"{0} gigaherca"}
}
instrumental{
one{"{0} gigahercom"}
}
}
dnam{"gigaherci"}
few{"{0} gigaherca"}
gender{"inanimate"}
one{"{0} gigaherc"}
other{"{0} gigaherca"}
}
@ -902,14 +1135,32 @@ sr_Latn{
other{"{0} herca"}
}
kilohertz{
case{
genitive{
one{"{0} kiloherca"}
}
instrumental{
one{"{0} kilohercom"}
}
}
dnam{"kiloherci"}
few{"{0} kiloherca"}
gender{"inanimate"}
one{"{0} kiloherc"}
other{"{0} kiloherca"}
}
megahertz{
case{
genitive{
one{"{0} megaherca"}
}
instrumental{
one{"{0} megahercom"}
}
}
dnam{"megaherci"}
few{"{0} megaherca"}
gender{"inanimate"}
one{"{0} megaherc"}
other{"{0} megaherca"}
}
@ -922,11 +1173,76 @@ sr_Latn{
}
em{
gender{"inanimate"}
one{"{0} em"}
}
megapixel{
case{
accusative{
few{"{0} megapiksela"}
one{"{0} megapiksel"}
other{"{0} megapiksela"}
}
genitive{
few{"{0} megapiksela"}
one{"{0} megapiksela"}
other{"{0} megapiksela"}
}
instrumental{
few{"{0} megapiksela"}
one{"{0} megapikselom"}
other{"{0} megapiksela"}
}
}
dnam{"megapikseli"}
few{"{0} megapiksela"}
gender{"inanimate"}
one{"{0} megapiksel"}
other{"{0} megapiksela"}
}
pixel{
case{
accusative{
few{"{0} piksela"}
one{"{0} piksel"}
other{"{0} piksela"}
}
genitive{
few{"{0} piksela"}
one{"{0} piksela"}
other{"{0} piksela"}
}
instrumental{
few{"{0} piksela"}
one{"{0} pikselom"}
other{"{0} piksela"}
}
}
few{"{0} piksela"}
gender{"inanimate"}
one{"{0} px"}
one{"{0} piksel"}
other{"{0} piksela"}
}
pixel-per-centimeter{
case{
accusative{
few{"{0} piksela na centimetar"}
one{"{0} piksel na centimetar"}
other{"{0} piksela na centimetar"}
}
genitive{
few{"{0} piksela na centimetar"}
one{"{0} piksela na centimetar"}
other{"{0} piksela na centimetar"}
}
instrumental{
few{"{0} piksela na centimetar"}
one{"{0} pikselom na centimetar"}
other{"{0} piksela na centimetar"}
}
}
few{"{0} piksela na centimetar"}
gender{"inanimate"}
one{"{0} piksel na centimetar"}
other{"{0} piksela na centimetar"}
}
}
length{
@ -937,20 +1253,44 @@ sr_Latn{
other{"{0} astronomskih jedinica"}
}
centimeter{
case{
accusative{
few{"{0} centimetra"}
}
genitive{
few{"{0} centimetra"}
one{"{0} centimetra"}
}
instrumental{
few{"{0} centimetra"}
one{"{0} centimetrom"}
}
}
dnam{"centimetri"}
few{"{0} centimentra"}
few{"{0} centimetra"}
gender{"inanimate"}
one{"{0} centimetar"}
other{"{0} centimetara"}
per{"{0}/cm"}
}
decimeter{
case{
genitive{
one{"{0} decimetra"}
}
instrumental{
one{"{0} decimetrom"}
}
}
dnam{"decimetri"}
few{"{0} decimetra"}
gender{"inanimate"}
one{"{0} decimetar"}
other{"{0} decimetara"}
}
earth-radius{
dnam{"poluprečnik Zemlje"}
few{"{0} poluprečnik Zemlje"}
one{"{0} poluprečnik Zemlje"}
other{"{0} poluprečnika Zemlje"}
}
@ -981,8 +1321,17 @@ sr_Latn{
per{"{0}/in"}
}
kilometer{
case{
genitive{
one{"{0} kilometra"}
}
instrumental{
one{"{0} kilometrom"}
}
}
dnam{"kilometri"}
few{"{0} kilometra"}
gender{"inanimate"}
one{"{0} kilometar"}
other{"{0} kilometara"}
per{"{0}/km"}
@ -1013,8 +1362,17 @@ sr_Latn{
per{"{0}/m"}
}
micrometer{
case{
genitive{
one{"{0} mikrometra"}
}
instrumental{
one{"{0} mikrometrom"}
}
}
dnam{"mikrometri"}
few{"{0} mikrometra"}
gender{"inanimate"}
one{"{0} mikrometar"}
other{"{0} mikrometara"}
}
@ -1043,14 +1401,32 @@ sr_Latn{
other{"{0} skandinavskih milja"}
}
millimeter{
case{
genitive{
one{"{0} milimetra"}
}
instrumental{
one{"{0} milimetrom"}
}
}
dnam{"milimetri"}
few{"{0} milimetra"}
gender{"inanimate"}
one{"{0} milimetar"}
other{"{0} milimetara"}
}
nanometer{
case{
genitive{
one{"{0} nanometra"}
}
instrumental{
one{"{0} nanometrom"}
}
}
dnam{"nanometri"}
few{"{0} nanometra"}
gender{"inanimate"}
one{"{0} nanometar"}
other{"{0} nanometara"}
}
@ -1067,8 +1443,17 @@ sr_Latn{
other{"{0} parseka"}
}
picometer{
case{
genitive{
one{"{0} pikometra"}
}
instrumental{
one{"{0} pikometrom"}
}
}
dnam{"pikometri"}
few{"{0} pikometra"}
gender{"inanimate"}
one{"{0} pikometar"}
other{"{0} pikometara"}
}
@ -1241,14 +1626,32 @@ sr_Latn{
other{"{0} metričkih tona"}
}
microgram{
case{
genitive{
one{"{0} mikrograma"}
}
instrumental{
one{"{0} mikrogramom"}
}
}
dnam{"mikrogrami"}
few{"{0} mikrograma"}
gender{"inanimate"}
one{"{0} mikrogram"}
other{"{0} mikrograma"}
}
milligram{
case{
genitive{
one{"{0} miligrama"}
}
instrumental{
one{"{0} miligramom"}
}
}
dnam{"miligrami"}
few{"{0} miligrama"}
gender{"inanimate"}
one{"{0} miligram"}
other{"{0} miligrama"}
}
@ -1293,8 +1696,17 @@ sr_Latn{
}
power{
gigawatt{
case{
genitive{
one{"{0} gigavata"}
}
instrumental{
one{"{0} gigavatom"}
}
}
dnam{"gigavati"}
few{"{0} gigavata"}
gender{"inanimate"}
one{"{0} gigavat"}
other{"{0} gigavati"}
}
@ -1305,20 +1717,47 @@ sr_Latn{
other{"{0} konjskih snaga"}
}
kilowatt{
case{
genitive{
one{"{0} kilovata"}
}
instrumental{
one{"{0} kilovatom"}
}
}
dnam{"kilovati"}
few{"{0} kilovata"}
gender{"inanimate"}
one{"{0} kilovat"}
other{"{0} kilovati"}
}
megawatt{
case{
genitive{
one{"{0} megavata"}
}
instrumental{
one{"{0} megavatom"}
}
}
dnam{"megavati"}
few{"{0} megavata"}
gender{"inanimate"}
one{"{0} megavat"}
other{"{0} megavati"}
}
milliwatt{
case{
genitive{
one{"{0} milivata"}
}
instrumental{
one{"{0} milivatom"}
}
}
dnam{"milivati"}
few{"{0} milivata"}
gender{"inanimate"}
one{"{0} milivat"}
other{"{0} milivati"}
}
@ -1379,8 +1818,17 @@ sr_Latn{
other{"{0} bara"}
}
hectopascal{
case{
genitive{
one{"{0} hektopaskala"}
}
instrumental{
one{"{0} hektopaskalom"}
}
}
dnam{"hektopaskali"}
few{"{0} hektopaskala"}
gender{"inanimate"}
one{"{0} hektopaskal"}
other{"{0} hektopaskala"}
}
@ -1391,20 +1839,47 @@ sr_Latn{
other{"{0} inča živinog stuba"}
}
kilopascal{
case{
genitive{
one{"{0} kilopaskala"}
}
instrumental{
one{"{0} kilopaskalom"}
}
}
dnam{"kilopaskali"}
few{"{0} kilopaskala"}
gender{"inanimate"}
one{"{0} kilopaskal"}
other{"{0} kilopaskala"}
}
megapascal{
case{
genitive{
one{"{0} megapaskala"}
}
instrumental{
one{"{0} megapaskalom"}
}
}
dnam{"megapaskali"}
few{"{0} megapaskala"}
gender{"inanimate"}
one{"{0} megapaskal"}
other{"{0} megapaskala"}
}
millibar{
case{
genitive{
one{"{0} milibara"}
}
instrumental{
one{"{0} milibarom"}
}
}
dnam{"milibari"}
few{"{0} milibara"}
gender{"inanimate"}
one{"{0} milibar"}
other{"{0} milibara"}
}
@ -1441,8 +1916,17 @@ sr_Latn{
}
speed{
kilometer-per-hour{
case{
genitive{
one{"{0} kilometra na sat"}
}
instrumental{
one{"{0} kilometrom na sat"}
}
}
dnam{"kilometri na sat"}
few{"{0} kilometra na sat"}
gender{"inanimate"}
one{"{0} kilometar na sat"}
other{"{0} kilometara na sat"}
}
@ -1453,8 +1937,17 @@ sr_Latn{
other{"{0} čvorova"}
}
meter-per-second{
case{
genitive{
one{"{0} metra u sekundi"}
}
instrumental{
one{"{0} metrom u sekundi"}
}
}
dnam{"metri u sekundi"}
few{"{0} metra u sekundi"}
gender{"inanimate"}
one{"{0} metar u sekundi"}
other{"{0} metara u sekundi"}
}
@ -1518,8 +2011,17 @@ sr_Latn{
}
torque{
newton-meter{
case{
genitive{
one{"{0} njutn-metra"}
}
instrumental{
one{"{0} njutn-metrom"}
}
}
dnam{"njutn-metri"}
few{"{0} njutn-metra"}
gender{"inanimate"}
one{"{0} njutn-metar"}
other{"{0} njutn-metara"}
}
@ -1550,14 +2052,32 @@ sr_Latn{
other{"{0} bušela"}
}
centiliter{
case{
genitive{
one{"{0} centilitra"}
}
instrumental{
one{"{0} centilitrom"}
}
}
dnam{"centilitri"}
few{"{0} centilitra"}
gender{"inanimate"}
one{"{0} centilitar"}
other{"{0} centilitara"}
}
cubic-centimeter{
case{
genitive{
one{"{0} kubnog centimetra"}
}
instrumental{
one{"{0} kubnim centimetrom"}
}
}
dnam{"kubni centimetri"}
few{"{0} kubna centimetra"}
gender{"inanimate"}
one{"{0} kubni centimetar"}
other{"{0} kubnih centimetara"}
per{"{0}/cm³"}
@ -1575,14 +2095,32 @@ sr_Latn{
other{"{0} kubnih inča"}
}
cubic-kilometer{
case{
genitive{
one{"{0} kubnog kilometra"}
}
instrumental{
one{"{0} kubnim kilometrom"}
}
}
dnam{"kubni kilometri"}
few{"{0} kubna kilometra"}
gender{"inanimate"}
one{"{0} kubni kilometar"}
other{"{0} kubnih kilometara"}
}
cubic-meter{
case{
genitive{
one{"{0} kubnog metra"}
}
instrumental{
one{"{0} kubnim metrom"}
}
}
dnam{"kubni metri"}
few{"{0} kubna metra"}
gender{"inanimate"}
one{"{0} kubni metar"}
other{"{0} kubnih metara"}
per{"{0}/m³"}
@ -1624,8 +2162,17 @@ sr_Latn{
other{"{0} metričkih šolja"}
}
deciliter{
case{
genitive{
one{"{0} decilitra"}
}
instrumental{
one{"{0} decilitrom"}
}
}
dnam{"decilitri"}
few{"{0} decilitra"}
gender{"inanimate"}
one{"{0} decilitar"}
other{"{0} decilitara"}
}
@ -1680,8 +2227,17 @@ sr_Latn{
per{"{0} po imp. galonu"}
}
hectoliter{
case{
genitive{
one{"{0} hektolitra"}
}
instrumental{
one{"{0} hektolitrom"}
}
}
dnam{"hektolitri"}
few{"{0} hektolitra"}
gender{"inanimate"}
one{"{0} hektolitar"}
other{"{0} hektolitara"}
}
@ -1711,14 +2267,32 @@ sr_Latn{
per{"{0} po litri"}
}
megaliter{
case{
genitive{
one{"{0} megalitra"}
}
instrumental{
one{"{0} megalitrom"}
}
}
dnam{"megalitri"}
few{"{0} megalitra"}
gender{"inanimate"}
one{"{0} megalitar"}
other{"{0} megalitara"}
}
milliliter{
case{
genitive{
one{"{0} mililitra"}
}
instrumental{
one{"{0} mililitrom"}
}
}
dnam{"mililitri"}
few{"{0} mililitra"}
gender{"inanimate"}
one{"{0} mililitar"}
other{"{0} mililitara"}
}

4
icu4c/source/data/xml/brkitr/de.xml
View file

@ -6,9 +6,9 @@
See comments on https://unicode-org.atlassian.net/browse/ICU-10750 - this file is needed to emit break iterator rules properly.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/el.xml
View file

@ -4,9 +4,9 @@
License & terms of use: http://www.unicode.org/copyright.html
Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/en.xml
View file

@ -4,9 +4,9 @@
License & terms of use: http://www.unicode.org/copyright.html
Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/en_US.xml
View file

@ -4,9 +4,9 @@
License & terms of use: http://www.unicode.org/copyright.html
Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/en_US_POSIX.xml
View file

@ -4,9 +4,9 @@
License & terms of use: http://www.unicode.org/copyright.html
Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/es.xml
View file

@ -6,9 +6,9 @@
See comments on https://unicode-org.atlassian.net/browse/ICU-10750 - this file is needed to emit break iterator rules properly.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/fr.xml
View file

@ -6,9 +6,9 @@
See comments on https://unicode-org.atlassian.net/browse/ICU-10750 - this file is needed to emit break iterator rules properly.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/it.xml
View file

@ -6,9 +6,9 @@
See comments on https://unicode-org.atlassian.net/browse/ICU-10750 - this file is needed to emit break iterator rules properly.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

230
icu4c/source/data/xml/brkitr/ja.xml
View file

@ -4,9 +4,9 @@
License & terms of use: http://www.unicode.org/copyright.html
Copyright (c) 2006-2015 International Business Machines Corporation and others. All rights reserved.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>
@ -27,6 +27,232 @@
<icu:line alt="strict_phrase" icu:dependency="line_phrase_cj.brk"/>
<icu:line alt="phrase" icu:dependency="line_phrase_cj.brk"/>
</icu:boundaries>
<icu:extensions>
<!--
Entries in cjdict.txt categorized as particles (助詞), auxiliary verbs (助動詞),
conjugations (活用) and prefix of them.
These entries are connected to the previous words for phrase based line breaking.
https://ja.wikipedia.org/wiki/助詞
https://ja.wikipedia.org/wiki/助動詞_(国文法)
https://ja.wikipedia.org/wiki/活用
-->
<icu:extension>かい</icu:extension>
<icu:extension>かしら</icu:extension>
<icu:extension>から</icu:extension>
<icu:extension>きり</icu:extension>
<icu:extension>くらい</icu:extension>
<icu:extension>ぐらい</icu:extension>
<icu:extension>けれど</icu:extension>
<icu:extension>けれども</icu:extension>
<icu:extension>こそ</icu:extension>
<icu:extension>さえ</icu:extension>
<icu:extension>しか</icu:extension>
<icu:extension>した</icu:extension>
<icu:extension>ずつ</icu:extension>
<icu:extension>せる</icu:extension>
<icu:extension>せん</icu:extension>
<icu:extension>たい</icu:extension>
<icu:extension>たがる</icu:extension>
<icu:extension>たく</icu:extension>
<icu:extension>たら</icu:extension>
<icu:extension>たり</icu:extension>
<icu:extension>だけ</icu:extension>
<icu:extension>だに</icu:extension>
<icu:extension>だの</icu:extension>
<icu:extension>だり</icu:extension>
<icu:extension>つつ</icu:extension>
<icu:extension>てる</icu:extension>
<icu:extension>です</icu:extension>
<icu:extension>でも</icu:extension>
<icu:extension>ところが</icu:extension>
<icu:extension>ところで</icu:extension>
<icu:extension>とも</icu:extension>
<icu:extension>ない</icu:extension>
<icu:extension>なか</icu:extension>
<icu:extension>ながら</icu:extension>
<icu:extension>なく</icu:extension>
<icu:extension>なし</icu:extension>
<icu:extension>なぞ</icu:extension>
<icu:extension>など</icu:extension>
<icu:extension>なら</icu:extension>
<icu:extension>なり</icu:extension>
<icu:extension>なんぞ</icu:extension>
<icu:extension>ねる</icu:extension>
<icu:extension>ので</icu:extension>
<icu:extension>のに</icu:extension>
<icu:extension>のみ</icu:extension>
<icu:extension>ばかり</icu:extension>
<icu:extension>へる</icu:extension>
<icu:extension>ほど</icu:extension>
<icu:extension>まい</icu:extension>
<icu:extension>まう</icu:extension>
<icu:extension>まし</icu:extension>
<icu:extension>ます</icu:extension>
<icu:extension>まっ</icu:extension>
<icu:extension>まで</icu:extension>
<icu:extension>まま</icu:extension>
<icu:extension>もん</icu:extension>
<icu:extension>やら</icu:extension>
<icu:extension>よう</icu:extension>
<icu:extension>より</icu:extension>
<icu:extension>らしい</icu:extension>
<icu:extension>られる</icu:extension>
<icu:extension>れる</icu:extension>
<icu:extension>ろう</icu:extension>
<icu:extension>わっ</icu:extension>
<icu:extension>わな</icu:extension>
<icu:extension>わら</icu:extension>
<icu:extension>わり</icu:extension>
<icu:extension>わる</icu:extension>
<icu:extension>われ</icu:extension>
<icu:extension>わん</icu:extension>
<!--
Entries added for technical reasons (particle + others).
Entries in cjdict.txt, which are compound words starting from the above categories
(i.e. particles, auxiliary verbs and conjunctions).
These entries are connected to the previous words for phrase based line breaking.
-->
<icu:extension>えたい</icu:extension>
<icu:extension>えて</icu:extension>
<icu:extension>える</icu:extension>
<icu:extension>けた</icu:extension>
<icu:extension>けたい</icu:extension>
<icu:extension>ける</icu:extension>
<icu:extension>させる</icu:extension>
<icu:extension>そうだ</icu:extension>
<icu:extension>っきゃ</icu:extension>
<icu:extension>っきり</icu:extension>
<icu:extension>っけ</icu:extension>
<icu:extension>っす</icu:extension>
<icu:extension>ったらしい</icu:extension>
<icu:extension>っちゅう</icu:extension>
<icu:extension>って</icu:extension>
<icu:extension>っていう</icu:extension>
<icu:extension>ってか</icu:extension>
<icu:extension>ってな</icu:extension>
<icu:extension>っと</icu:extension>
<icu:extension>っぱなし</icu:extension>
<icu:extension>っぷり</icu:extension>
<icu:extension>っぽい</icu:extension>
<icu:extension>にあう</icu:extension>
<icu:extension>にあがる</icu:extension>
<icu:extension>にあたって</icu:extension>
<icu:extension>にあたり</icu:extension>
<icu:extension>にあたりまして</icu:extension>
<icu:extension>にあたります</icu:extension>
<icu:extension>にあたる</icu:extension>
<icu:extension>において</icu:extension>
<icu:extension>におきまして</icu:extension>
<icu:extension>における</icu:extension>
<icu:extension>にかけ</icu:extension>
<icu:extension>にかけて</icu:extension>
<icu:extension>にかけまして</icu:extension>
<icu:extension>にたいして</icu:extension>
<icu:extension>にたいしまして</icu:extension>
<icu:extension>にたいします</icu:extension>
<icu:extension>にたいする</icu:extension>
<icu:extension>について</icu:extension>
<icu:extension>につき</icu:extension>
<icu:extension>につきまして</icu:extension>
<icu:extension>につけ</icu:extension>
<icu:extension>につれ</icu:extension>
<icu:extension>につれて</icu:extension>
<icu:extension>にて</icu:extension>
<icu:extension>にとって</icu:extension>
<icu:extension>にとり</icu:extension>
<icu:extension>にとりまして</icu:extension>
<icu:extension>にまつわります</icu:extension>
<icu:extension>にまつわる</icu:extension>
<icu:extension>にもかかわらず</icu:extension>
<icu:extension>にゃ</icu:extension>
<icu:extension>によって</icu:extension>
<icu:extension>により</icu:extension>
<icu:extension>によりまして</icu:extension>
<icu:extension>によります</icu:extension>
<icu:extension>による</icu:extension>
<icu:extension>にわたって</icu:extension>
<icu:extension>にわたり</icu:extension>
<icu:extension>にわたりまして</icu:extension>
<icu:extension>にわたります</icu:extension>
<icu:extension>にわたる</icu:extension>
<icu:extension>に対し</icu:extension>
<icu:extension>に対して</icu:extension>
<icu:extension>に対しまして</icu:extension>
<icu:extension>に対します</icu:extension>
<icu:extension>に対する</icu:extension>
<icu:extension>に当たって</icu:extension>
<icu:extension>に当たり</icu:extension>
<icu:extension>に当たりまして</icu:extension>
<icu:extension>に当たります</icu:extension>
<icu:extension>に当たる</icu:extension>
<icu:extension>に従い</icu:extension>
<icu:extension>に従いまして</icu:extension>
<icu:extension>に従います</icu:extension>
<icu:extension>に従う</icu:extension>
<icu:extension>に従って</icu:extension>
<icu:extension>に関し</icu:extension>
<icu:extension>に関して</icu:extension>
<icu:extension>に関しまして</icu:extension>
<icu:extension>に関します</icu:extension>
<icu:extension>に関する</icu:extension>
<icu:extension>に際し</icu:extension>
<icu:extension>に際して</icu:extension>
<icu:extension>ものの</icu:extension>
<icu:extension>ろうし</icu:extension>
<icu:extension>ろうと</icu:extension>
<icu:extension>われと</icu:extension>
<icu:extension>をの</icu:extension>
<icu:extension>をめぐって</icu:extension>
<icu:extension>をめぐりまして</icu:extension>
<icu:extension>をめぐります</icu:extension>
<icu:extension>をめぐる</icu:extension>
<icu:extension>をもちまして</icu:extension>
<icu:extension>をもって</icu:extension>
<icu:extension>を以て</icu:extension>
<icu:extension>を通して</icu:extension>
<icu:extension>を通しまして</icu:extension>
<icu:extension>を通じ</icu:extension>
<icu:extension>を通じて</icu:extension>
<icu:extension>を通じまして</icu:extension>
<icu:extension>んじゃ</icu:extension>
<icu:extension>んで</icu:extension>
<!--
Entries added for technical reasons (noun suffix).
Entries in cjdict.txt, which are suffixes of nouns.
These entries should be connected to the previous (noun) words.
-->
<icu:extension>々宮</icu:extension>
<icu:extension>々家</icu:extension>
<icu:extension>え目</icu:extension>
<icu:extension>が丘</icu:extension>
<icu:extension>が台</icu:extension>
<icu:extension>が床</icu:extension>
<icu:extension>が浜</icu:extension>
<icu:extension>ヵ国</icu:extension>
<icu:extension>ヵ年</icu:extension>
<icu:extension>ヵ所</icu:extension>
<icu:extension>ヵ月</icu:extension>
<icu:extension>ヵ村</icu:extension>
<icu:extension>ヵ条</icu:extension>
<icu:extension>ヶ丘</icu:extension>
<icu:extension>ヶ国</icu:extension>
<icu:extension>ヶ島</icu:extension>
<icu:extension>ヶ年</icu:extension>
<icu:extension>ヶ所</icu:extension>
<icu:extension>ヶ月</icu:extension>
<icu:extension>ヶ村</icu:extension>
<icu:extension>ヶ条</icu:extension>
<icu:extension>ージ</icu:extension>
<icu:extension>ーズ</icu:extension>
<icu:extension>ータ</icu:extension>
<icu:extension>ード</icu:extension>
<icu:extension>ーニャ</icu:extension>
<icu:extension>ープランス</icu:extension>
<icu:extension>ーユ</icu:extension>
<icu:extension>ーランド</icu:extension>
<icu:extension>ーリンズ</icu:extension>
<icu:extension>ーン</icu:extension>
</icu:extensions>
</icu:breakIteratorData>
</special>
</ldml>

4
icu4c/source/data/xml/brkitr/pt.xml
View file

@ -6,9 +6,9 @@
See comments on https://unicode-org.atlassian.net/browse/ICU-10750 - this file is needed to emit break iterator rules properly.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/root.xml
View file

@ -4,9 +4,9 @@
License & terms of use: http://www.unicode.org/copyright.html
Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/ru.xml
View file

@ -6,9 +6,9 @@
See comments on https://unicode-org.atlassian.net/browse/ICU-10750 - this file is needed to emit break iterator rules properly.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/zh.xml
View file

@ -4,9 +4,9 @@
License & terms of use: http://www.unicode.org/copyright.html
Copyright (c) 2006-2015 International Business Machines Corporation and others. All rights reserved.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/brkitr/zh_Hant.xml
View file

@ -4,9 +4,9 @@
License & terms of use: http://www.unicode.org/copyright.html
Copyright (c) 2006-2015 International Business Machines Corporation and others. All rights reserved.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/collation/root.xml
View file

@ -4,9 +4,9 @@
License & terms of use: http://www.unicode.org/copyright.html
Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

4
icu4c/source/data/xml/main/root.xml
View file

@ -4,9 +4,9 @@
License & terms of use: http://www.unicode.org/copyright.html
Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
-->
<!DOCTYPE ldml SYSTEM "../../dtd/cldr-40/common/dtd/ldml.dtd"
<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
[
<!ENTITY % icu SYSTEM "../../dtd/cldr-40/common/dtd/ldmlICU.dtd">
<!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
%icu;
]
>

1
icu4c/source/data/zone/LOCALE_DEPS.json
View file

@ -176,6 +176,7 @@
"es_VE": "es_419",
"ff_Adlm": "root",
"hi_Latn": "en_IN",
"ks_Deva": "root",
"nb": "no",
"nn": "no",
"pa_Arab": "root",

60
icu4c/source/data/zone/ks_Deva.txt Normal file
View file

@ -0,0 +1,60 @@
// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
ks_Deva{
%%Parent{"root"}
zoneStrings{
"Etc:UTC"{
ls{"कोऑर्डनैटिड यूनवर्सल वख"}
}
"Etc:Unknown"{
ec{"नमोलुम शहर"}
}
"meta:America_Central"{
ld{"सेंट्रल डे लाइट वख"}
lg{"सेंट्रल वख"}
ls{"सेंट्रल स्टैन्डर्ड वख"}
}
"meta:America_Eastern"{
ld{"मशरिकी डे लाइट वख"}
lg{"मशरिकी वख"}
ls{"मशरिकी स्टैन्डर्ड वख"}
}
"meta:America_Mountain"{
ld{"माउंटेन डे लाइट वख"}
lg{"माउंटेन वख"}
ls{"माउंटेन स्टैन्डर्ड वख"}
}
"meta:America_Pacific"{
ld{"पेसिफिक डे लाइट वख"}
lg{"पेसिफिक वख"}
ls{"पेसिफिक स्टैन्डर्ड वख"}
}
"meta:Atlantic"{
ld{"अटलांटिक डे लाइट वख"}
lg{"अटलांटिक वख"}
ls{"अटलांटिक स्टैन्डर्ड वख"}
}
"meta:Europe_Central"{
ld{"मरकज़ी यूरपी समर वख"}
lg{"मरकज़ी यूरपी वख"}
ls{"मरकज़ी यूरपी स्टैन्डर्ड वख"}
}
"meta:Europe_Eastern"{
ld{"मशरिकी यूरपी समर वख"}
lg{"मशरिकी यूरपी वख"}
ls{"मशरिकी यूरपी स्टैन्डर्ड वख"}
}
"meta:Europe_Western"{
ld{"मगरीबी यूरपी समर वख"}
lg{"मगरीबी यूरपी वख"}
ls{"मगरीबी यूरपी स्टैन्डर्ड वख"}
}
"meta:GMT"{
ls{"ग्रीनविच मीन वख"}
}
regionFormat{"{0} वख"}
regionFormatDaylight{"{0} डे लाइट वख"}
regionFormatStandard{"{0} स्टैन्डर्ड वख"}
}
}

3
icu4c/source/data/zone/sr_Latn.txt
View file

@ -1224,6 +1224,9 @@ sr_Latn{
"Pacific:Johnston"{
ec{"Džonston"}
}
"Pacific:Kanton"{
ec{"Kanton"}
}
"Pacific:Kiritimati"{
ec{"Kiritimati"}
}

8
icu4c/source/test/cintltst/cldrtest.c
View file

@ -1002,6 +1002,10 @@ static void VerifyTranslation(void) {
log_knownIssue("cldrbug:14995", "mai/sd_Deva day names use chars not in exemplars")) {
end = 0;
}
if (uprv_strncmp(currLoc,"ks_Deva",7) == 0 &&
log_knownIssue("cldrbug:15355", "ks_Deva day names use chars not in exemplars")) {
end = 0;
}
for (idx = 0; idx < end; idx++) {
const UChar *fromBundleStr = ures_getStringByIndex(resArray, idx, &langSize, &errorCode);
@ -1035,8 +1039,8 @@ static void VerifyTranslation(void) {
log_knownIssue("cldrbug:14995", "sd_Deva month names use chars not in exemplars")) {
end = 0;
}
if (uprv_strncmp(currLoc,"ks",2) == 0 &&
log_knownIssue("cldrbug:15341", "ks month names use chars not in exemplars")) {
if (uprv_strncmp(currLoc,"ks_Deva",7) == 0 &&
log_knownIssue("cldrbug:15355", "ks_Deva month names use chars not in exemplars")) {
end = 0;
}

32
icu4c/source/test/intltest/listformattertest.cpp
View file

@ -276,7 +276,7 @@ void ListFormatterTest::RunTestFieldPositionIteratorWithNItemsPatternShift(
const char* testName) {
IcuTestErrorCode errorCode(*this, testName);
LocalPointer<ListFormatter> formatter(ListFormatter::createInstance(
Locale("ur", "IN"),
Locale("ur", "IN"), // in CLDR 41 alpha1 the "backwards order" patterns in this and other locales were removed.
ULISTFMT_TYPE_UNITS,
ULISTFMT_WIDTH_NARROW,
errorCode));
@ -329,21 +329,21 @@ void ListFormatterTest::TestFieldPositionIteratorWith3Items() {
}
void ListFormatterTest::TestFieldPositionIteratorWith3ItemsPatternShift() {
// 0 1
// 012345678901234
// "cc bbb a"
// Note: In CLDR 41 alpha1 the "backwards order" patterns in ur_IN (and one or two
// other locales) were removed, ur_IN now just inherits list patterns from ur.
// So this test may no longer be interesting.
UnicodeString data[3] = {"a", "bbb", "cc"};
int32_t expected[] = {
ULISTFMT_ELEMENT_FIELD, 7, 8,
ULISTFMT_LITERAL_FIELD, 6, 7,
ULISTFMT_ELEMENT_FIELD, 0, 1,
ULISTFMT_LITERAL_FIELD, 1, 3,
ULISTFMT_ELEMENT_FIELD, 3, 6,
ULISTFMT_LITERAL_FIELD, 2, 3,
ULISTFMT_ELEMENT_FIELD, 0, 2
ULISTFMT_LITERAL_FIELD, 6, 12,
ULISTFMT_ELEMENT_FIELD, 12, 14
};
int32_t tupleCount = sizeof(expected)/(3 * sizeof(*expected));
RunTestFieldPositionIteratorWithNItemsPatternShift(
data, 3, expected, tupleCount,
u"cc bbb a",
u"a، bbb، اور cc",
"TestFieldPositionIteratorWith3ItemsPatternShift");
}
@ -365,19 +365,19 @@ void ListFormatterTest::TestFieldPositionIteratorWith2Items() {
}
void ListFormatterTest::TestFieldPositionIteratorWith2ItemsPatternShift() {
// 0 1
// 01234567890
// "cc bbb"
// Note: In CLDR 41 alpha1 the "backwards order" patterns in ur_IN (and one or two
// other locales) were removed, ur_IN now just inherits list patterns from ur.
// So this test may no longer be interesting.
UnicodeString data[2] = {"bbb", "cc"};
int32_t expected[] = {
ULISTFMT_ELEMENT_FIELD, 3, 6,
ULISTFMT_LITERAL_FIELD, 2, 3,
ULISTFMT_ELEMENT_FIELD, 0, 2
ULISTFMT_ELEMENT_FIELD, 0, 3,
ULISTFMT_LITERAL_FIELD, 3, 8,
ULISTFMT_ELEMENT_FIELD, 8, 10
};
int32_t tupleCount = sizeof(expected)/(3 * sizeof(*expected));
RunTestFieldPositionIteratorWithNItemsPatternShift(
data, 2, expected, tupleCount,
u"cc bbb",
u"bbb اور cc",
"TestFieldPositionIteratorWith2ItemsPatternShift");
}

30
icu4c/source/test/intltest/transtst.cpp
View file

@ -3654,19 +3654,35 @@ void TransliteratorTest::TestIncrementalProgress(void) {
// 1. Devanagari-Arabic
// 2. Any-*/BGN
// 2a. Any-*/BGN_1981
// 3. Any-*/UNGEGN
// 4. Any-*/MNS
// If UCONFIG_NO_BREAK_ITERATION is on, Latin-Thai is also not expected to work.
// 3. Any-*/MNS
//
// 4. If UCONFIG_NO_BREAK_ITERATION is on, Latin-Thai is also not expected to work.
//
// The following are direction="both" transforms with variants, inverting the Any-Xxxx/Variant for
// any of these does not work; see ICU-21911 (not sure whether this is intentional or an ICU bug).
// Unfortunately we do not easily have the info at this point as to whether the original transform
// had direction="both" specified.
// 5. Any-*/UNGEGN
// 6. Any-Ethiopic/*
// 7. Any-Braille/*
// 8. Any-*/Gurage_2013
// 9. Any-*/Gutgarts
// 10. Any-*/Tekie_Alibekit
// 11. Any-*/Xaleget
//
if ( id.compare((UnicodeString)"Devanagari-Arabic/") != 0
&& !(id.startsWith((UnicodeString)"Any-") &&
(id.endsWith((UnicodeString)"/BGN") || id.endsWith((UnicodeString)"/BGN_1981") || id.endsWith((UnicodeString)"/UNGEGN") || id.endsWith((UnicodeString)"/MNS"))
(id.endsWith((UnicodeString)"/BGN") || id.endsWith((UnicodeString)"/BGN_1981") || id.endsWith((UnicodeString)"/MNS"))
)
#if UCONFIG_NO_BREAK_ITERATION
&& id.compare((UnicodeString)"Latin-Thai/") != 0
#endif
&& !(logKnownIssue("15337", "Ethiopic transforms new in CLDR 41 fail inverse test ") &&
(id.startsWith((UnicodeString)"Any-Ethiopic/") || id.startsWith((UnicodeString)"Any-byn_") || id.startsWith((UnicodeString)"Any-Braille/") ||
id.endsWith((UnicodeString)"/Gurage_2013") || id.endsWith((UnicodeString)"/Gutgarts")))
&& !(logKnownIssue("21911", "ICU4C cannot create inverse of Any-Xxxx/Variant transform created from both-direction transform") &&
id.startsWith((UnicodeString)"Any-") &&
(id.endsWith((UnicodeString)"/UNGEGN") || id.startsWith((UnicodeString)"Any-Ethiopic/") || id.startsWith((UnicodeString)"Any-Braille/") ||
id.endsWith((UnicodeString)"/Gurage_2013") || id.endsWith((UnicodeString)"/Gutgarts") || id.endsWith((UnicodeString)"/Tekie_Alibekit") ||
id.endsWith((UnicodeString)"/Xaleget"))
)
)
{
errln((UnicodeString)"FAIL: Could not create inverse of " + id + ", status " + u_errorName(status));

4
icu4j/main/shared/data/icudata.jar
View file

@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2023c8c2492957393643b34d6b9396060acb3dd8d66d28bf023d118ea03eab7
size 13867661
oid sha256:62f6bb6255440bed5ea35dd659ba59dc4d3034ecfd53fae6790be0fcbc3f9eff
size 13873153

4
icu4j/main/shared/data/icutzdata.jar
View file

@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1bbf45782f7b1026b5ead53ffa5c1d77bb2dc8e45bdf8774be2dae31855a6e63
size 96440
oid sha256:379538ae9348bb63b1a4f1c1314f1513acadd72c6b9630af8dc9e4cc0465ea57
size 96439

4
icu4j/main/shared/data/testdata.jar
View file

@ -1,3 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:26b283b1ea008e2750b1dfcfc1150fce21dc5fcbdcb4f79b1a9148e18ce926f1
size 826064
oid sha256:67aa8c24114eb601f3fa722c490dd07fe236a1205591e6672706e7d93c5e4767
size 826063

6
tools/cldr/cldr-to-icu/build-icu-data.xml
View file

@ -47,10 +47,10 @@
<property name="specialsDir" value="${basedir}/../../../icu4c/source/data/xml"/>
<!-- Default value for ICU version (icuver.txt). Update this for each release. -->
<property name="icuVersion" value="70.1.0.0"/>
<property name="icuVersion" value="71.0.1.0"/>
<!-- Default value for ICU data version (icuver.txt). Update this for each release. -->
<property name="icuDataVersion" value="70.1.0.0"/>
<property name="icuDataVersion" value="71.0.1.0"/>
<!-- An override for the CLDR version string (icuver.txt and others). This will be
extracted from the CLDR library used for building the data if not set here. -->
@ -187,7 +187,7 @@
// K
ka, kab, kam, kde, kea, kgp, khq, ki, kk, kkj, kl, kln, km, kn, ko, kok, ks
ks_IN, ksb, ksf, ksh, ku, kw, ky
ks_Deva, ks_IN, ksb, ksf, ksh, ku, kw, ky
// L
lag, lb, lg, lkt, ln, lo, lrc, lt, lu, luo, luy, lv

2
tools/cldr/cldr-to-icu/pom.xml
View file

@ -83,7 +83,7 @@
<dependency>
<groupId>com.ibm.icu</groupId>
<artifactId>icu4j-for-cldr</artifactId>
<version>70.0.1-SNAPSHOT-cldr-2021-08-11</version>
<version>70.1-cldr-2022-02-08</version>
<!-- Note: see https://github.com/unicode-org/icu/packages/411079/versions
for the icu4j-for-cldr version tag to use -->
</dependency>

2
tools/cldr/cldr-to-icu/src/main/java/org/unicode/icu/tool/cldrtoicu/LdmlConverter.java
View file

@ -662,6 +662,8 @@ public final class LdmlConverter {
.put("boundaries", BRKITR)
.put("dictionaries", BRKITR)
.put("exceptions", BRKITR)
.put("extensions", BRKITR)
.put("lstm", BRKITR)
// COLL
.put("collations", COLL)
.put("depends", COLL)

14
tools/cldr/cldr-to-icu/src/main/java/org/unicode/icu/tool/cldrtoicu/mapper/BreakIteratorMapper.java
View file

@ -43,6 +43,8 @@ public final class BreakIteratorMapper {
specials.addValueAction("icu:boundaries/*", BreakIteratorMapper::addBoundary);
specials.addValueAction(
"icu:dictionaries/icu:dictionary", BreakIteratorMapper::addDictionary);
specials.addValueAction(
"icu:extensions/icu:extension", BreakIteratorMapper::addExtension);
specials.addValueAction(
"icu:lstm/icu:lstmdata", BreakIteratorMapper::addLstmdata);
CLDR_PROCESSOR = processor.build();
@ -80,6 +82,7 @@ public final class BreakIteratorMapper {
}
private void addSuppression(CldrValue v) {
//System.out.println("addSegmentation: " + v.toString()); // debug
String type = SEGMENTATION_TYPE.valueFrom(v);
// TODO: Understand and document why we escape values here, but not for collation data.
icuData.add(
@ -87,19 +90,26 @@ public final class BreakIteratorMapper {
}
private void addBoundary(CldrValue v) {
//System.out.println("addBoundary: " + v.toString()); // debug
addDependency(getDependencyName(v), getBoundaryType(v), getBoundaryDependency(v));
}
private void addDictionary(CldrValue v) {
//System.out.println("addDictionary: " + v.toString());
//System.out.println("addDictionary: " + v.toString()); // debug
addDependency(
getDependencyName(v),
DICTIONARY_TYPE.valueFrom(v),
DICTIONARY_DEP.optionalValueFrom(v));
}
private void addExtension(CldrValue v) {
//System.out.println("addExtension: " + v.toString()); // debug
icuData.add(
RbPath.of("extensions"), v.getValue());
}
private void addLstmdata(CldrValue v) {
//System.out.println("addLstmdata: " + v.toString());
//System.out.println("addLstmdata: " + v.toString()); // debug
addDependency(
getDependencyName(v),
LSTMDATA_TYPE.valueFrom(v),