CLDR-18129 Investigate and fix (where necessary) invalid codes (#4215)

common/dtd/ldml.dtd

@@ -61,7 +61,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT language ( #PCDATA ) >
 <!ATTLIST language type NMTOKEN #REQUIRED >
-    <!--@MATCH:validity/locale-->
+    <!--@MATCH:validity/locale-for-names-->
 <!ATTLIST language alt NMTOKENS #IMPLIED >
     <!--@MATCH:literal/long, secondary, short, variant, menu, official-->
 <!ATTLIST language draft (approved | contributed | provisional | unconfirmed | true | false) #IMPLIED >
@@ -95,7 +95,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT variant ( #PCDATA ) >
 <!ATTLIST variant type NMTOKEN #REQUIRED >
-    <!--@MATCH:validity/variant-->
+    <!--@MATCH:or/validity/variant||literal/AREVELA, AREVMDA, LAUKIKA, VAIDIKA-->
 <!ATTLIST variant alt NMTOKENS #IMPLIED >
     <!--@MATCH:literal/secondary, variant-->
 <!ATTLIST variant draft (approved | contributed | provisional | unconfirmed | true | false) #IMPLIED >

common/dtd/ldmlSupplemental.dtd

@@ -65,7 +65,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT region ( currency* ) >
 <!ATTLIST region iso3166 NMTOKEN #REQUIRED >
-    <!--@MATCH:validity/region-->
+    <!--@MATCH:validity/region/all-->
 <!ATTLIST region draft (approved | contributed | provisional | unconfirmed | true | false) #IMPLIED >
     <!--@METADATA-->
     <!--@DEPRECATED-->
@@ -113,7 +113,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 <!ATTLIST group type NMTOKEN #REQUIRED >
     <!--@MATCH:validity/region-->
 <!ATTLIST group contains NMTOKENS #IMPLIED >
-    <!--@MATCH:set/validity/region-->
+    <!--@MATCH:set/validity/region/all-->
     <!--@VALUE-->
 <!ATTLIST group grouping (true | false) #IMPLIED >
     <!--@VALUE-->
@@ -284,7 +284,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 <!ELEMENT minDays EMPTY >
 <!ATTLIST minDays count (1 | 2 | 3 | 4 | 5 | 6 | 7) #REQUIRED >
 <!ATTLIST minDays territories NMTOKENS #REQUIRED >
-    <!--@MATCH:set/validity/region-->
+    <!--@MATCH:set/validity/region/all-->
     <!--@VALUE-->
 <!ATTLIST minDays draft (approved | contributed | provisional | unconfirmed | true | false) #IMPLIED >
     <!--@METADATA-->
@@ -297,7 +297,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 <!ELEMENT firstDay EMPTY >
 <!ATTLIST firstDay day (sun | mon | tue | wed | thu | fri | sat) #REQUIRED >
 <!ATTLIST firstDay territories NMTOKENS #REQUIRED >
-    <!--@MATCH:set/validity/region-->
+    <!--@MATCH:set/validity/region/all-->
     <!--@VALUE-->
 <!ATTLIST firstDay draft (approved | contributed | provisional | unconfirmed | true | false) #IMPLIED >
     <!--@METADATA-->
@@ -702,7 +702,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT languageAlias EMPTY >
 <!ATTLIST languageAlias type NMTOKEN #REQUIRED >
-    <!--@MATCH:or/validity/locale||literal/aa_saaho, aar, abk, afr, aka, alb, amh, ara, arg, arm, art_lojban, asm, ava, ave, aym, aze, bak, bam, baq, bel, ben, bih, bis, bod, bos, bre, bul, bur, cat, ces, cha, che, chi, chu, chv, cor, cos, cre, cym, cze, dan, deu, div, dut, dzo, ell, eng, epo, est, eus, ewe, fao, fas, fij, fin, fra, fre, fry, ful, geo, ger, gla, gle, glg, glv, gre, grn, guj, hat, hau, hbs, heb, her, hin, hmo, hrv, hun, hye, i_ami, i_bnn, i_hak, i_klingon, i_lux, i_navajo, i_pwn, i_tao, i_tay, i_tsu, ibo, ice, ido, iii, iku, ile, ina, ind, ipk, isl, ita, jav, jpn, kal, kan, kas, kat, kau, kaz, khm, kik, kin, kir, kom, kon, kor, kua, kur, lao, lat, lav, lim, lin, lit, ltz, lub, lug, mac, mah, mal, mao, mar, may, mkd, mlg, mlt, mol, mon, mri, msa, mya, nau, nav, nbl, nde, ndo, nep, nld, nno, no_bokmal, no_nynorsk, no_bok, no_nyn, nob, nor, nya, oci, oji, ori, orm, oss, pan, per, pli, pol, por, pus, que, roh, ron, rum, run, rus, sag, san, scc, scr, sgn_BE_FR, sgn_BE_NL, sgn_CH_DE, sin, slk, slo, slv, sme, smo, sna, snd, som, sot, spa, sqi, srd, srp, ssw, sun, swa, swe, tah, tam, tat, tel, tgk, tgl, tha, tib, tir, ton, tsn, tso, tuk, tur, twi, uig, ukr, urd, uzb, ven, vie, vol, wel, wln, wol, xho, yid, yor, zh_guoyu, zh_hakka, zh_min_nan, zh_xiang, zha, zho, zul, cel_gaulish, i_default, i_enochian, i_mingo, und_aaland, und_bokmal, und_hakka, und_lojban, und_nynorsk, und_saaho, und_xiang, zh_min, en_GB_oed, zh_cmn, zh_cmn_Hans, zh_cmn_Hant, zh_gan, zh_wuu, zh_yue-->
+    <!--@MATCH:or/validity/bcp47-wellformed||literal/aa_saaho, art_lojban, cel_gaulish, en_GB_oed, hy_arevmda, i_ami, i_bnn, i_default, i_enochian, i_hak, i_klingon, i_lux, i_mingo, i_navajo, i_pwn, i_tao, i_tay, i_tsu, no_bok, no_bokmal, no_nyn, no_nynorsk, sgn_BE_FR, sgn_BE_NL, sgn_BR, sgn_CH_DE, sgn_CO, sgn_DE, sgn_DK, sgn_ES, sgn_FR, sgn_GB, sgn_GR, sgn_IE, sgn_IT, sgn_JP, sgn_MX, sgn_NI, sgn_NL, sgn_NO, sgn_PT, sgn_SE, sgn_US, sgn_ZA, und_aaland, und_arevela, und_arevmda, und_bokmal, und_hakka, und_hepburn_heploc, und_lojban, und_nynorsk, und_saaho, und_xiang, zh_cmn, zh_cmn_Hans, zh_cmn_Hant, zh_gan, zh_guoyu, zh_hakka, zh_min, zh_min_nan, zh_wuu, zh_xiang, zh_yue-->
 <!ATTLIST languageAlias replacement NMTOKEN #REQUIRED >
     <!--@MATCH:or/validity/locale||literal/en_x_i_default, nan_x_zh_min, see_x_i_mingo, und_x_i_enochian, xtg_x_cel_gaulish-->
     <!--@VALUE-->
@@ -711,7 +711,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT scriptAlias EMPTY >
 <!ATTLIST scriptAlias type NMTOKEN #REQUIRED >
-    <!--@MATCH:validity/script-->
+    <!--@MATCH:validity/script/all-->
 <!ATTLIST scriptAlias replacement NMTOKEN #REQUIRED >
     <!--@MATCH:validity/script-->
     <!--@VALUE-->
@@ -720,9 +720,9 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT territoryAlias EMPTY >
 <!ATTLIST territoryAlias type NMTOKEN #REQUIRED >
-    <!--@MATCH:set/or/validity/region||regex/[0-9]{3}|[A-Z]{3}||literal/CT, DY, FQ, HV, JT, MI, NH, NQ, PC, PU, PZ, RH, UK, VD, WK-->
+    <!--@MATCH:set/or/validity/region/all||regex/[0-9]{3}|[A-Z]{3}||literal/CT, DY, FQ, HV, JT, MI, NH, NQ, PC, PU, PZ, RH, UK, VD, WK-->
 <!ATTLIST territoryAlias replacement NMTOKENS #REQUIRED >
-    <!--@MATCH:set/validity/region-->
+    <!--@MATCH:set/validity/region/all-->
     <!--@VALUE-->
 <!ATTLIST territoryAlias reason (deprecated | overlong) #IMPLIED >
     <!--@VALUE-->
@@ -738,7 +738,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT variantAlias EMPTY >
 <!ATTLIST variantAlias type NMTOKEN #REQUIRED >
-    <!--@MATCH:or/validity/variant||literal/aaland, polytoni-->
+    <!--@MATCH:or/validity/variant/all||literal/aaland, polytoni-->
 <!ATTLIST variantAlias replacement NMTOKEN #REQUIRED >
     <!--@MATCH:or/validity/variant||validity/region||literal/hy, hyw-->
     <!--@VALUE-->
@@ -914,7 +914,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT territoryCodes EMPTY >
 <!ATTLIST territoryCodes type NMTOKEN #REQUIRED >
-    <!--@MATCH:validity/region-->
+    <!--@MATCH:validity/region/all-->
 <!ATTLIST territoryCodes numeric NMTOKEN #IMPLIED >
     <!--@MATCH:range/1~999-->
     <!--@VALUE-->
@@ -962,9 +962,9 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT likelySubtag EMPTY >
 <!ATTLIST likelySubtag from NMTOKEN #REQUIRED >
-    <!--@MATCH:validity/locale-->
+    <!--@MATCH:validity/locale-for-likely-->
 <!ATTLIST likelySubtag to NMTOKEN #REQUIRED >
-    <!--@MATCH:validity/locale-->
+    <!--@MATCH:validity/locale-for-likely-->
     <!--@VALUE-->
 <!ATTLIST likelySubtag origin NMTOKENS #IMPLIED >
     <!--@MATCH:set/literal/sil1, wikidata, special-->
@@ -996,7 +996,7 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 
 <!ELEMENT pluralRules ( pluralRule* ) >
 <!ATTLIST pluralRules locales NMTOKENS #REQUIRED >
-    <!--@MATCH:set/validity/locale-->
+    <!--@MATCH:set/or/validity/locale-for-likely||literal/sh-->
 <!ATTLIST pluralRules draft (approved | contributed | provisional | unconfirmed) #IMPLIED >
     <!--@METADATA-->
     <!--@DEPRECATED-->

common/main/en.xml

@@ -139,6 +139,7 @@ annotations.
 			<language type="cop">Coptic</language>
 			<language type="cps">Capiznon</language>
 			<language type="cr">Cree</language>
+			<language type="cr" alt="long">Woods Cree</language>
 			<language type="crg">Michif</language>
 			<language type="crh">Crimean Tatar</language>
 			<language type="crj">Southern East Cree</language>
@@ -152,7 +153,6 @@ annotations.
 			<language type="csw">Swampy Cree</language>
 			<language type="cu">Church Slavic</language>
 			<language type="cv">Chuvash</language>
-			<language type="cwd">Woods Cree</language>
 			<language type="cy">Welsh</language>
 			<language type="da">Danish</language>
 			<language type="dak">Dakota</language>
@@ -256,7 +256,6 @@ annotations.
 			<language type="hak">Hakka Chinese</language>
 			<language type="haw">Hawaiian</language>
 			<language type="hax">Southern Haida</language>
-			<language type="hdn">Northern Haida</language>
 			<language type="he">Hebrew</language>
 			<language type="hi">Hindi</language>
 			<language type="hi_Latn">Hindi (Latin)</language>
@@ -284,7 +283,6 @@ annotations.
 			<language type="ig">Igbo</language>
 			<language type="ii">Sichuan Yi</language>
 			<language type="ik">Inupiaq</language>
-			<language type="ike">Eastern Canadian Inuktitut</language>
 			<language type="ikt">Western Canadian Inuktitut</language>
 			<language type="ilo">Iloko</language>
 			<language type="inh">Ingush</language>
@@ -474,7 +472,6 @@ annotations.
 			<language type="oj">Ojibwa</language>
 			<language type="ojb">Northwestern Ojibwa</language>
 			<language type="ojc">Central Ojibwa</language>
-			<language type="ojg">Eastern Ojibwa</language>
 			<language type="ojs">Oji-Cree</language>
 			<language type="ojw">Western Ojibwa</language>
 			<language type="oka">Okanagan</language>

common/main/fi.xml

@@ -31,7 +31,7 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 			<language type="afh">afrihili</language>
 			<language type="agq">aghem</language>
 			<language type="ain">ainu</language>
-			<language type="ajp">urduni</language>
+			<language type="apc">urduni</language>
 			<language type="ak">akan</language>
 			<language type="akk">akkadi</language>
 			<language type="akz">alabama</language>

common/main/la.xml

@@ -24,7 +24,6 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 			<language type="az" draft="provisional">Atropatenica</language>
 			<language type="be" draft="provisional">Ruthenica Alba</language>
 			<language type="bg" draft="provisional">Bulgarica</language>
-			<language type="bh" draft="provisional">Bihari</language>
 			<language type="bn" draft="provisional">Bengalica</language>
 			<language type="bo" draft="provisional">Tibetana</language>
 			<language type="br" draft="provisional">Britonica</language>
@@ -66,12 +65,12 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 			<language type="ia" draft="provisional">Interlingua</language>
 			<language type="ie" draft="provisional">Interlingue</language>
 			<language type="ig" draft="provisional">Igbonica</language>
-			<language type="in" draft="provisional">Indonesia</language>
+			<language type="id" draft="provisional">Indonesia</language>
 			<language type="is" draft="provisional">Islandica</language>
 			<language type="it" draft="provisional">Italiana</language>
-			<language type="iw" draft="provisional">Hebraica</language>
+			<language type="he" draft="provisional">Hebraica</language>
 			<language type="ja" draft="provisional">Iaponica</language>
-			<language type="ji" draft="provisional">Iudaeogermanica</language>
+			<language type="yi" draft="provisional">Iudaeogermanica</language>
 			<language type="jv" draft="provisional">Iavensis</language>
 			<language type="ka" draft="provisional">Georgiana</language>
 			<language type="kk" draft="provisional">Cazachica</language>
@@ -213,7 +212,6 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 			<territory type="BR" draft="provisional">Brasilia</territory>
 			<territory type="BS" draft="provisional">Insulae Bahamenses</territory>
 			<territory type="BT" draft="provisional">Butania</territory>
-			<territory type="BU" draft="provisional">Birmania</territory>
 			<territory type="BV" draft="provisional">Insula Bouvet</territory>
 			<territory type="BW" draft="provisional">Botswana</territory>
 			<territory type="BY" draft="provisional">Ruthenia Alba</territory>
@@ -237,7 +235,6 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 			<territory type="CX" draft="provisional">Insula Christi Natalis</territory>
 			<territory type="CY" draft="provisional">Cyprus</territory>
 			<territory type="CZ" draft="provisional">Cechia</territory>
-			<territory type="DD" draft="provisional">Res publica Democratica Germanica</territory>
 			<territory type="DE" draft="provisional">Germania</territory>
 			<territory type="DJ" draft="provisional">Gibutum</territory>
 			<territory type="DK" draft="provisional">Dania</territory>
@@ -421,7 +418,6 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 			<territory type="XK" draft="provisional">Kosovia</territory>
 			<territory type="YE" draft="provisional">Iemenia</territory>
 			<territory type="YT" draft="provisional">Maiotta</territory>
-			<territory type="YU" draft="provisional">Iugoslavia</territory>
 			<territory type="ZA" draft="provisional">Africa Australis</territory>
 			<territory type="ZM" draft="provisional">Zambia</territory>
 			<territory type="ZW" draft="provisional">Zimbabua</territory>

common/main/nl.xml

@@ -31,7 +31,6 @@ Warnings: All cp values have U+FE0F characters removed. See /annotationsDerived/
 			<language type="afh">Afrihili</language>
 			<language type="agq">Aghem</language>
 			<language type="ain">Aino</language>
-			<language type="ajp" draft="contributed">Zuid-Levantijns-Arabisch</language>
 			<language type="ak">Akan</language>
 			<language type="akk">Akkadisch</language>
 			<language type="akz">Alabama</language>

common/supplemental/supplementalData.xml

@@ -4930,7 +4930,7 @@ XXX Code for transations where no currency is involved
 		<weekOfPreference ordering="weekOfYear weekOfInterval" locales="zu"/>
 		<weekOfPreference ordering="weekOfDate" locales="ca es fr gl"/>
 		<weekOfPreference ordering="weekOfDate weekOfMonth" locales="en bn ja ka"/>
-		<weekOfPreference ordering="weekOfDate weekOfMonth weekOfInterval" locales="bg de iw pt ur zh"/>
+		<weekOfPreference ordering="weekOfDate weekOfMonth weekOfInterval" locales="bg de he pt ur zh"/>
 		<weekOfPreference ordering="weekOfDate weekOfYear weekOfMonth" locales="nl"/>
 		<weekOfPreference ordering="weekOfDate weekOfInterval weekOfMonth" locales="af"/>
 		<weekOfPreference ordering="weekOfMonth" locales="ar fil gu hu hy id kk ko"/>

common/supplemental/supplementalMetadata.xml

@@ -179,7 +179,7 @@ For terms of use, see http://www.unicode.org/copyright.html
 			<languageAlias type="mof" replacement="xnt" reason="deprecated"/>  <!-- Mohegan-Montauk-Narragansett -->
 			<languageAlias type="mwd" replacement="dmw" reason="deprecated"/>  <!-- Mudbura -->
 			<languageAlias type="nbf" replacement="nru" reason="deprecated"/>  <!-- Naxi -->
-			<languageAlias type="nbx" replacement="ekc" reason="deprecated"/>  <!-- Ngura -->
+			<languageAlias type="nbx" replacement="gll" reason="deprecated"/>  <!-- Ngura -->
 			<languageAlias type="nln" replacement="azd" reason="deprecated"/>  <!-- Durango Nahuatl -->
 			<languageAlias type="nlr" replacement="nrk" reason="deprecated"/>  <!-- Ngarla -->
 			<languageAlias type="noo" replacement="dtd" reason="deprecated"/>  <!-- Nootka -->
@@ -306,6 +306,9 @@ For terms of use, see http://www.unicode.org/copyright.html
 			<languageAlias type="him" replacement="srx" reason="macrolanguage"/> <!-- Himachali ⇒ Sirmauri (= Pahari, Himachali) -->
 			<languageAlias type="mnk" replacement="man" reason="macrolanguage"/> <!-- Mandinka ⇒ Mandingo -->
 			<languageAlias type="bh" replacement="bho" reason="macrolanguage"/> <!-- Bihari ⇒ Bhojpuri -->
+			<languageAlias type="cls" replacement="sa" reason="macrolanguage"/> <!-- Classical Sanskrit ⇒ Sanskrit -->
+			<!-- Special case <languageAlias type="nb" replacement="no" reason="macrolanguage"/> <! - - Norwegian Bokmål ⇒ Norwegian -->
+			<!-- Special case <languageAlias type="sr" replacement="sh" reason="macrolanguage"/> <! - - Serbian ⇒ Serbo-Croatian -->
 
 			<languageAlias type="prs" replacement="fa_AF" reason="overlong"/> <!-- Dari ⇒ Farsi (Afganistan) -->
 			<languageAlias type="swc" replacement="sw_CD" reason="overlong"/> <!-- Congo Swahili ⇒ Swahili (Congo - Kinshasa) -->

common/validity/language.xml

@@ -76,7 +76,7 @@
 			cia~e cih cik cim~n cip cir ciw ciy
 			cja cje cjh~i cjk cjm~p cjs cjv cjy
 			ckb ckh ckl~o ckq~v ckx~z
-			cla clc cle clh~m clo cls~u clw cly
+			cla clc cle clh~m clo clt~u clw cly
 			cma cmc cme cmg cmi cml~m cmo cmr~t
 			cna~c cng~i cnk~l cno~q cns~u cnw~x
 			co coa~h coj~q cot~x coz
@@ -628,7 +628,7 @@
 		<id type='language' idStatus='deprecated'>		<!-- 296 items -->
 			aam adp agp ais ajp ajt~u als aoh arb asd aue ayr ayx~y azj
 			baz bbz bcc bcl bgm bh bhk bic bij bjd bjq bkb blg bmy bpb btb btl bxk bxr bxx byy
-			cbe cbh cca ccq cdg cjr cka cld cmk cmn cnr coy cqu cug cum cwd
+			cbe cbh cca ccq cdg cjr cka cld cls cmk cmn cnr coy cqu cug cum cwd
 			daf dap dgo dgu dha dhd dik diq dit djl dkl drh drr drw dud duj dwl
 			ekc ekk elp emk emo esk
 			fat fuc