CLDR-17042 adjust coverage

common/main/yi_001.xml → common/main/yi_UA.xml

@@ -9,6 +9,6 @@ CLDR data files are interpreted according to the LDML specification (http://unic
 	<identity>
 		<version number="$Revision$"/>
 		<language type="yi"/>
-		<territory type="001"/>
+		<territory type="UA"/>
 	</identity>
 </ldml>

common/properties/coverageLevels.txt

@@ -144,6 +144,7 @@ th ;	modern ;	Thai
 ti ;	basic ;	Tigrinya
 tk ;	modern ;	Turkmen
 to ;	basic ;	Tongan
+tok ;	basic ;	Toki Pona
 tr ;	modern ;	Turkish
 tt ;	basic ;	Tatar
 ug ;	basic ;	Uyghur
@@ -164,6 +165,6 @@ yue_Hans ;	modern ;	Cantonese (Simplified)
 za ;	basic ;	Zhuang
 zh ;	modern ;	Chinese
 zh_Hant ;	modern ;	Traditional Chinese
-zu ;	moderate ;	Zulu
+zu ;	modern ;	Zulu
 
 #EOF		

common/supplemental/coverageLevels.xml

@@ -105,8 +105,9 @@ For terms of use, see http://www.unicode.org/copyright.html
 		<coverageVariable key="%language60_GA" value="(fan|mye)"/>
 		<coverageVariable key="%language60_NG" value="(ff|ha|ibb|ig|kr|yo)"/>
 		<coverageVariable key="%language60_TD" value="(shu|dzg|kbl|mde|mua|sba)"/>
-		<!-- See CLDR-16673: All basic+ locales (per coverageLevels.txt) MUST have their language's name at least at level 80 (modern) -->
-		<coverageVariable key="%language80" value="a([bfmvyz]|ce|d[ay]|in|l[et]|np?|r[nps]?|st?|tj|wa)|b([ens]|an?|gc?|ho|in?|l[ao]|rx?|ug|yn)|c([ovy]|ay?|eb|h[kmopry]?|lc|r[gj-mr]|sw?)|d([ev]|a[kr]?|gr|oi|sb|zg)|e([lns-u]|fi|ka)|f([ajy]|il?|on?|rc?)|g([dlnu]|aa?|ez|il|or|wi)|h([ertyz]|a[ix]?|il?|mn|sb|u[pr]?)|i([adgos-u]|b[ab]|kt|lo|nh)|j([av]|bo)|k([jknsvy]|a[cj]?|bd|cg|ea|fo|gp|ha|mb?|ok?|pe|r[clu]?|um?|wk|xv)|l([btv]|ad?|ez|i[jl]?|mo|o[uz]?|sm|u[ans])|m([hklr-t]|a[dgik]|df|en|i[cn]?|ni?|o[ehs]|u[ls]|wl|yv?)|n([glnrvy]|ap?|ew?|i[au]|og?|qo|so)|o([cr]|j[bcsw]|ka)|p([lst]|a[gmpu]?|cm|qm)|qu|r([mo]|a[jpr]|hg|up?)|s([dikmoqsv]|a[dht]?|ba|c[no]?|hn|lh?|nk|rn?|tr?|uk?|wb?|yr|zl)|t([aknos]|ce|e[mt]?|gx?|ht?|ig?|l[hi]|pi|rv?|tm?|um|vl|yv?)|u([gkrz]|dm|mb)|v(ec?|i|mw)|w(a[lr]?|o|uu)|x(al|h|nr)|y(bb|o|rl|ue)|z([ah]|un?|xx|za)"/>
+		<!-- See CLDR-16673: All basic+ locales (per coverageLevels.txt) MUST have their language's name at least at level 80 (modern), except for those on exception list -->
+		<!-- Can use MinimizeRegex.java to "unpack" the compressed lists that are painful to edit -->
+		<coverageVariable key="%language80" value="(ace|ada|ady|ain|ale|alt|anp|arn|arp|ars|ast|atj|awa|ban|bho|bin|bla|brx|bug|byn|cay|ceb|chk|chm|cho|chp|chr|chy|clc|crg|crj|crk|crl|crm|crr|csw|dak|dar|dgr|doi|dsb|dzg|efi|eka|fil|fon|frc|gaa|gez|gil|gor|gwi|hai|hax|hil|hmn|hsb|hup|hur|iba|ibb|ikt|ilo|inh|jbo|kac|kaj|kbd|kcg|kea|kfo|kgp|kha|kmb|kok|kpe|krc|krl|kru|kum|kwk|lad|lez|lil|lou|loz|lsm|lua|lun|lus|mad|mag|mai|mak|mdf|men|mic|min|mni|moe|moh|mos|mul|mus|mwl|myv|nap|new|nia|niu|nog|nqo|nso|ojb|ojc|ojs|ojw|oka|pag|pam|pap|pau|pcm|pqm|rap|rar|rhg|rup|sad|sah|sat|sba|scn|sco|shn|slh|snk|srn|str|suk|swb|syr|tce|tem|tet|tgx|tht|tig|tlh|tli|tpi|trv|ttm|tum|tvl|tyv|udm|umb|wal|war|wuu|xal|ybb|yrl|yue|zun|zxx|zza|ab|af|am|an|ar|as|av|ay|az|ba|be|bg|bi|bn|br|bs|ca|ch|co|cs|cv|cy|da|de|dv|el|en|es|et|eu|fa|fi|fj|fo|fr|fy|ga|gd|gl|gn|gu|ha|he|hi|hr|ht|hu|hy|hz|ia|id|ig|io|is|it|iu|ja|jv|ka|kj|kk|km|kn|ko|kr|ks|ku|kv|ky|la|lb|li|lo|lt|lv|mh|mi|mk|ml|mn|mr|ms|mt|my|na|ne|ng|nl|nn|no|nr|nv|ny|oc|or|pa|pl|ps|pt|qu|rm|ro|ru|sa|sc|sd|si|sk|sl|sm|so|sq|sr|ss|st|su|sv|sw|ta|te|tg|th|ti|tk|tn|to|tr|ts|tt|ty|ug|uk|ur|uz|ve|vi|wa|wo|xh|yo|zh|zu)"/>
 		<coverageVariable key="%languagecomp" value="(gan|hak|hsn|nan)"/> <!-- not currently used, just for reference: the only valid language codes that are not in modern coverage -->
 		<coverageVariable key="%lbTypes80" value="(strict|normal|loose)"/>
 		<coverageVariable key="%lwTypes" value="(normal|breakall|keepall|phrase)"/>

common/supplemental/likelySubtags.xml

@@ -1586,8 +1586,8 @@ not be patched by hand, as any changes made in that fashion may be lost.
 		<!--{ Yangben; ?; ? } => { Yangben; Latin; Cameroon }-->
 		<likelySubtag from="ybb" to="ybb_Latn_CM"/>
 		<!--{ Yemba; ?; ? } => { Yemba; Latin; Cameroon }-->
-		<likelySubtag from="yi" to="yi_Hebr_001"/>
-		<!--{ Yiddish; ?; ? } => { Yiddish; Hebrew; world }-->
+		<likelySubtag from="yi" to="yi_Hebr_UA"/>
+		<!--{ Yiddish; ?; ? } => { Yiddish; Hebrew; Ukraine }-->
 		<likelySubtag from="yo" to="yo_Latn_NG"/>
 		<!--{ Yoruba; ?; ? } => { Yoruba; Latin; Nigeria }-->
 		<likelySubtag from="yrl" to="yrl_Latn_BR"/>

common/supplemental/supplementalData.xml

@@ -2693,6 +2693,7 @@ XXX Code for transations where no currency is involved
 			<languagePopulation type="crl" populationPercent="0.001" references="R1329"/>	<!--Northern East Cree-->
 			<languagePopulation type="kwk" populationPercent="0.001" references="R1329"/>	<!--Kwakʼwala-->
 			<languagePopulation type="gwi" populationPercent="0.0008" officialStatus="official_regional" references="R1329"/>	<!--Gwichʼin-->
+			<languagePopulation type="tok" populationPercent="0.00000001"/>	<!--Tok Pona-->
 		</territory>
 		<territory type="CC" gdp="29210000" literacyPercent="99" population="596">	<!--Cocos (Keeling) Islands-->
 			<languagePopulation type="ms_Arab" populationPercent="83"/>	<!--Malay (Arabic)-->
@@ -2873,6 +2874,7 @@ XXX Code for transations where no currency is involved
 			<languagePopulation type="frs" populationPercent="0.0025" references="R1300"/>	<!--Eastern Frisian-->
 			<languagePopulation type="stq" populationPercent="0.0012"/>	<!--Saterland Frisian-->
 			<languagePopulation type="pfl" populationPercent="0" references="R1150"/>	<!--Palatine German-->
+			<languagePopulation type="vo" populationPercent="0"/>	<!--Volapük-->
 		</territory>
 		<territory type="DG" gdp="22240000" literacyPercent="99" population="500">	<!--Diego Garcia-->
 			<languagePopulation type="en" populationPercent="99" officialStatus="de_facto_official" references="R1065"/>	<!--English-->

common/supplemental/supplementalMetadata.xml

@@ -1841,7 +1841,7 @@ For terms of use, see http://www.unicode.org/copyright.html
 			vai_Latn_LR vai_Vaii vai_Vaii_LR ve_ZA vec_IT vi_VN vmw_MZ vo_001 vun_TZ
 			wa_BE wae_CH wal_ET wbp_AU wo_SN
 			xh_ZA xnr_IN xog_UG
-			yav_CM yi_001 yo_NG yrl_BR yue_Hans_CN yue_Hant yue_Hant_HK
+			yav_CM yi_UA yo_NG yrl_BR yue_Hans_CN yue_Hant yue_Hant_HK
 			za_CN zgh_MA zh_Hans zh_Hans_CN zh_Hant_TW zu_ZA"
 		/>
     </metadata>

tools/cldr-code/src/main/java/org/unicode/cldr/util/CoreCoverageInfo.java

@@ -97,6 +97,7 @@ public String toString() {
 
     static UnicodeSet RTL = new UnicodeSet("[[:bc=R:][:bc=AL:]]").freeze();
 
+    /** Only call on L1 locales (parent = root) */
     public static Set<CoreItems> getCoreCoverageInfo(
             CLDRFile resolvedFile, Multimap<CoreItems, String> detailedErrors) {
         detailedErrors.clear();

tools/cldr-code/src/main/java/org/unicode/cldr/util/SupplementalDataInfo.java

@@ -2531,9 +2531,10 @@ public Set<CLDRLocale> getDefaultContentCLDRLocales() {
      * @param language language to search
      * @return default content, or null if none
      */
-    public String getDefaultContentLocale(String language) {
+    public String getDefaultContentLocale(String locale) {
+        CLDRLocale cLocale = CLDRLocale.getInstance(locale);
         for (String dc : defaultContentLocales) {
-            if (dc.startsWith(language + "_")) {
+            if (CLDRLocale.getInstance(dc).getParent() == cLocale) {
                 return dc;
             }
         }

tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/Locales.txt

@@ -305,7 +305,7 @@ Apple	;	sv	;	modern
 Apple	;	ta	;	modern
 Apple	;	te	;	modern
 Apple	;	th	;	modern
-Apple	;	to	;	modern
+Apple	;	to	;	moderate
 Apple	;	tr	;	modern
 Apple	;	uk	;	modern
 Apple	;	ur	;	modern
@@ -533,11 +533,11 @@ Cldr  ; hsb ; modern ; Upper Sorbian
 Cldr  ; dsb ; modern  ; Lower Sorbian
 Cldr  ; gd  ; modern  ; Scottish Gaelic
 Cldr  ; chr ; modern  ; Cherokee
-Cldr	;	to	;	modern ; Tongan
+Cldr	;	to	;	moderate ; Tongan
 Cldr  ; yue_Hans  ; modern  ; Cantonese (Simplified)
 
 Cldr  ; fo  ; moderate  ; Faroese
-Cldr  ; qu  ; modern  ; Quechua
+Cldr  ; qu  ; moderate  ; Quechua
 Cldr  ; br  ; moderate  ; Breton
 Cldr  ; sc  ; moderate  ; Sardinian
 Cldr  ; kgp ; moderate  ; Kaingang
@@ -674,7 +674,6 @@ Microsoft	;	pl	;	modern	;	Polish
 Microsoft	;	ps	;	modern	;	Pashto
 Microsoft	;	pt	;	modern	;	Portuguese (Brazil)
 Microsoft	;	pt_PT	;	modern	;	Portuguese (Portugal)
-Microsoft	;	qu	;	modern	;	Quechua
 Microsoft	;	ro	;	modern	;	Romanian
 Microsoft	;	ru	;	modern	;	Russian
 Microsoft	;	sd	;	modern	;	Sindhi
@@ -918,5 +917,5 @@ special ;	sr_Latn	;	modern	;	Serbian (Latn)
 special ;	yrl	;	moderate	;	Nheengatu
 special ;	yue_Hans	;	modern	;	Cantonese (Simplified)
 special ; uz_Cyrl ; basic ; Uzbek (Cyrillic)
-special	;	to	;	modern ; Tongan
-special  ; qu  ; modern  ; Quechua
+special	;	to	;	moderate ; Tongan
+special  ; qu  ; moderate  ; Quechua

tools/cldr-code/src/test/java/org/unicode/cldr/unittest/LocaleMatcherTest.java

@@ -681,7 +681,7 @@ public void testPerf() {
                         "af, am, ar, az, be, bg, bn, bs, ca, cs, cy, cy, da, de, el, en, en-GB, es, es-419, et, eu, fa, fi, fil, fr, ga, gl, gu, hi, hr, hu, hy, id, is, it, iw, ja, ka, kk, km, kn, ko, ky, lo, lt, lv, mk, ml, mn, mr, ms, my, ne, nl, no, pa, pl, pt, pt-PT, ro, ru, si, sk, sl, sq, sr, sr-Latn, sv, sw, ta, te, th, tr, uk, ur, uz, vi, zh-CN, zh-TW, zu");
         final LocaleMatcher matcherVeryLong =
                 newLocaleMatcher(
-                        "af, af_NA, af_ZA, agq, agq_CM, ak, ak_GH, am, am_ET, ar, ar_001, ar_AE, ar_BH, ar_DJ, ar_DZ, ar_EG, ar_EH, ar_ER, ar_IL, ar_IQ, ar_JO, ar_KM, ar_KW, ar_LB, ar_LY, ar_MA, ar_MR, ar_OM, ar_PS, ar_QA, ar_SA, ar_SD, ar_SO, ar_SS, ar_SY, ar_TD, ar_TN, ar_YE, as, as_IN, asa, asa_TZ, ast, ast_ES, az, az_Cyrl, az_Cyrl_AZ, az_Latn, az_Latn_AZ, bas, bas_CM, be, be_BY, bem, bem_ZM, bez, bez_TZ, bg, bg_BG, bm, bm_ML, bn, bn_BD, bn_IN, bo, bo_CN, bo_IN, br, br_FR, brx, brx_IN, bs, bs_Cyrl, bs_Cyrl_BA, bs_Latn, bs_Latn_BA, ca, ca_AD, ca_ES, ca_ES_VALENCIA, ca_FR, ca_IT, ce, ce_RU, cgg, cgg_UG, chr, chr_US, ckb, ckb_IQ, ckb_IR, cs, cs_CZ, cu, cu_RU, cy, cy_GB, da, da_DK, da_GL, dav, dav_KE, de, de_AT, de_BE, de_CH, de_DE, de_LI, de_LU, dje, dje_NE, dsb, dsb_DE, dua, dua_CM, dyo, dyo_SN, dz, dz_BT, ebu, ebu_KE, ee, ee_GH, ee_TG, el, el_CY, el_GR, en, en_001, en_150, en_AG, en_AI, en_AS, en_AT, en_AU, en_BB, en_BE, en_BI, en_BM, en_BS, en_BW, en_BZ, en_CA, en_CC, en_CH, en_CK, en_CM, en_CX, en_CY, en_DE, en_DG, en_DK, en_DM, en_ER, en_FI, en_FJ, en_FK, en_FM, en_GB, en_GD, en_GG, en_GH, en_GI, en_GM, en_GU, en_GY, en_HK, en_IE, en_IL, en_IM, en_IN, en_IO, en_JE, en_JM, en_KE, en_KI, en_KN, en_KY, en_LC, en_LR, en_LS, en_MG, en_MH, en_MO, en_MP, en_MS, en_MT, en_MU, en_MW, en_MY, en_NA, en_NF, en_NG, en_NL, en_NR, en_NU, en_NZ, en_PG, en_PH, en_PK, en_PN, en_PR, en_PW, en_RW, en_SB, en_SC, en_SD, en_SE, en_SG, en_SH, en_SI, en_SL, en_SS, en_SX, en_SZ, en_TC, en_TK, en_TO, en_TT, en_TV, en_TZ, en_UG, en_UM, en_US, en_US_POSIX, en_VC, en_VG, en_VI, en_VU, en_WS, en_ZA, en_ZM, en_ZW, eo, eo_001, es, es_419, es_AR, es_BO, es_CL, es_CO, es_CR, es_CU, es_DO, es_EA, es_EC, es_ES, es_GQ, es_GT, es_HN, es_IC, es_MX, es_NI, es_PA, es_PE, es_PH, es_PR, es_PY, es_SV, es_US, es_UY, es_VE, et, et_EE, eu, eu_ES, ewo, ewo_CM, fa, fa_AF, fa_IR, ff, ff_CM, ff_GN, ff_MR, ff_SN, fi, fi_FI, fil, fil_PH, fo, fo_DK, fo_FO, fr, fr_BE, fr_BF, fr_BI, fr_BJ, fr_BL, fr_CA, fr_CD, fr_CF, fr_CG, fr_CH, fr_CI, fr_CM, fr_DJ, fr_DZ, fr_FR, fr_GA, fr_GF, fr_GN, fr_GP, fr_GQ, fr_HT, fr_KM, fr_LU, fr_MA, fr_MC, fr_MF, fr_MG, fr_ML, fr_MQ, fr_MR, fr_MU, fr_NC, fr_NE, fr_PF, fr_PM, fr_RE, fr_RW, fr_SC, fr_SN, fr_SY, fr_TD, fr_TG, fr_TN, fr_VU, fr_WF, fr_YT, fur, fur_IT, fy, fy_NL, ga, ga_IE, gd, gd_GB, gl, gl_ES, gsw, gsw_CH, gsw_FR, gsw_LI, gu, gu_IN, guz, guz_KE, gv, gv_IM, ha, ha_GH, ha_NE, ha_NG, haw, haw_US, he, he_IL, hi, hi_IN, hr, hr_BA, hr_HR, hsb, hsb_DE, hu, hu_HU, hy, hy_AM, id, id_ID, ig, ig_NG, ii, ii_CN, is, is_IS, it, it_CH, it_IT, it_SM, ja, ja_JP, jgo, jgo_CM, jmc, jmc_TZ, ka, ka_GE, kab, kab_DZ, kam, kam_KE, kde, kde_TZ, kea, kea_CV, khq, khq_ML, ki, ki_KE, kk, kk_KZ, kkj, kkj_CM, kl, kl_GL, kln, kln_KE, km, km_KH, kn, kn_IN, ko, ko_KP, ko_KR, kok, kok_IN, ks, ks_IN, ksb, ksb_TZ, ksf, ksf_CM, ksh, ksh_DE, kw, kw_GB, ky, ky_KG, lag, lag_TZ, lb, lb_LU, lg, lg_UG, lkt, lkt_US, ln, ln_AO, ln_CD, ln_CF, ln_CG, lo, lo_LA, lrc, lrc_IQ, lrc_IR, lt, lt_LT, lu, lu_CD, luo, luo_KE, luy, luy_KE, lv, lv_LV, mas, mas_KE, mas_TZ, mer, mer_KE, mfe, mfe_MU, mg, mg_MG, mgh, mgh_MZ, mgo, mgo_CM, mk, mk_MK, ml, ml_IN, mn, mn_MN, mr, mr_IN, ms, ms_BN, ms_MY, ms_SG, mt, mt_MT, mua, mua_CM, my, my_MM, mzn, mzn_IR, naq, naq_NA, nb, nb_NO, nb_SJ, nd, nd_ZW, ne, ne_IN, ne_NP, nl, nl_AW, nl_BE, nl_BQ, nl_CW, nl_NL, nl_SR, nl_SX, nmg, nmg_CM, nn, nn_NO, nnh, nnh_CM, no, nus, nus_SS, nyn, nyn_UG, om, om_ET, om_KE, or, or_IN, os, os_GE, os_RU, pa, pa_Arab, pa_Arab_PK, pa_Guru, pa_Guru_IN, pl, pl_PL, prg, prg_001, ps, ps_AF, pt, pt_AO, pt_BR, pt_CV, pt_GW, pt_MO, pt_MZ, pt_PT, pt_ST, pt_TL, qu, qu_BO, qu_EC, qu_PE, rm, rm_CH, rn, rn_BI, ro, ro_MD, ro_RO, rof, rof_TZ, root, ru, ru_BY, ru_KG, ru_KZ, ru_MD, ru_RU, ru_UA, rw, rw_RW, rwk, rwk_TZ, sah, sah_RU, saq, saq_KE, sbp, sbp_TZ, se, se_FI, se_NO, se_SE, seh, seh_MZ, ses, ses_ML, sg, sg_CF, shi, shi_Latn, shi_Latn_MA, shi_Tfng, shi_Tfng_MA, si, si_LK, sk, sk_SK, sl, sl_SI, smn, smn_FI, sn, sn_ZW, so, so_DJ, so_ET, so_KE, so_SO, sq, sq_AL, sq_MK, sq_XK, sr, sr_Cyrl, sr_Cyrl_BA, sr_Cyrl_ME, sr_Cyrl_RS, sr_Cyrl_XK, sr_Latn, sr_Latn_BA, sr_Latn_ME, sr_Latn_RS, sr_Latn_XK, sv, sv_AX, sv_FI, sv_SE, sw, sw_CD, sw_KE, sw_TZ, sw_UG, ta, ta_IN, ta_LK, ta_MY, ta_SG, te, te_IN, teo, teo_KE, teo_UG, th, th_TH, ti, ti_ER, ti_ET, tk, tk_TM, to, to_TO, tr, tr_CY, tr_TR, twq, twq_NE, tzm, tzm_MA, ug, ug_CN, uk, uk_UA, ur, ur_IN, ur_PK, uz, uz_Arab, uz_Arab_AF, uz_Cyrl, uz_Cyrl_UZ, uz_Latn, uz_Latn_UZ, vai, vai_Latn, vai_Latn_LR, vai_Vaii, vai_Vaii_LR, vi, vi_VN, vo, vo_001, vun, vun_TZ, wae, wae_CH, xog, xog_UG, yav, yav_CM, yi, yi_001, yo, yo_BJ, yo_NG, zgh, zgh_MA, zh, zh_Hans, zh_Hans_CN, zh_Hans_HK, zh_Hans_MO, zh_Hans_SG, zh_Hant, zh_Hant_HK, zh_Hant_MO, zh_Hant_TW, zu, zu_ZA");
+                        "af, af_NA, af_ZA, agq, agq_CM, ak, ak_GH, am, am_ET, ar, ar_001, ar_AE, ar_BH, ar_DJ, ar_DZ, ar_EG, ar_EH, ar_ER, ar_IL, ar_IQ, ar_JO, ar_KM, ar_KW, ar_LB, ar_LY, ar_MA, ar_MR, ar_OM, ar_PS, ar_QA, ar_SA, ar_SD, ar_SO, ar_SS, ar_SY, ar_TD, ar_TN, ar_YE, as, as_IN, asa, asa_TZ, ast, ast_ES, az, az_Cyrl, az_Cyrl_AZ, az_Latn, az_Latn_AZ, bas, bas_CM, be, be_BY, bem, bem_ZM, bez, bez_TZ, bg, bg_BG, bm, bm_ML, bn, bn_BD, bn_IN, bo, bo_CN, bo_IN, br, br_FR, brx, brx_IN, bs, bs_Cyrl, bs_Cyrl_BA, bs_Latn, bs_Latn_BA, ca, ca_AD, ca_ES, ca_ES_VALENCIA, ca_FR, ca_IT, ce, ce_RU, cgg, cgg_UG, chr, chr_US, ckb, ckb_IQ, ckb_IR, cs, cs_CZ, cu, cu_RU, cy, cy_GB, da, da_DK, da_GL, dav, dav_KE, de, de_AT, de_BE, de_CH, de_DE, de_LI, de_LU, dje, dje_NE, dsb, dsb_DE, dua, dua_CM, dyo, dyo_SN, dz, dz_BT, ebu, ebu_KE, ee, ee_GH, ee_TG, el, el_CY, el_GR, en, en_001, en_150, en_AG, en_AI, en_AS, en_AT, en_AU, en_BB, en_BE, en_BI, en_BM, en_BS, en_BW, en_BZ, en_CA, en_CC, en_CH, en_CK, en_CM, en_CX, en_CY, en_DE, en_DG, en_DK, en_DM, en_ER, en_FI, en_FJ, en_FK, en_FM, en_GB, en_GD, en_GG, en_GH, en_GI, en_GM, en_GU, en_GY, en_HK, en_IE, en_IL, en_IM, en_IN, en_IO, en_JE, en_JM, en_KE, en_KI, en_KN, en_KY, en_LC, en_LR, en_LS, en_MG, en_MH, en_MO, en_MP, en_MS, en_MT, en_MU, en_MW, en_MY, en_NA, en_NF, en_NG, en_NL, en_NR, en_NU, en_NZ, en_PG, en_PH, en_PK, en_PN, en_PR, en_PW, en_RW, en_SB, en_SC, en_SD, en_SE, en_SG, en_SH, en_SI, en_SL, en_SS, en_SX, en_SZ, en_TC, en_TK, en_TO, en_TT, en_TV, en_TZ, en_UG, en_UM, en_US, en_US_POSIX, en_VC, en_VG, en_VI, en_VU, en_WS, en_ZA, en_ZM, en_ZW, eo, eo_001, es, es_419, es_AR, es_BO, es_CL, es_CO, es_CR, es_CU, es_DO, es_EA, es_EC, es_ES, es_GQ, es_GT, es_HN, es_IC, es_MX, es_NI, es_PA, es_PE, es_PH, es_PR, es_PY, es_SV, es_US, es_UY, es_VE, et, et_EE, eu, eu_ES, ewo, ewo_CM, fa, fa_AF, fa_IR, ff, ff_CM, ff_GN, ff_MR, ff_SN, fi, fi_FI, fil, fil_PH, fo, fo_DK, fo_FO, fr, fr_BE, fr_BF, fr_BI, fr_BJ, fr_BL, fr_CA, fr_CD, fr_CF, fr_CG, fr_CH, fr_CI, fr_CM, fr_DJ, fr_DZ, fr_FR, fr_GA, fr_GF, fr_GN, fr_GP, fr_GQ, fr_HT, fr_KM, fr_LU, fr_MA, fr_MC, fr_MF, fr_MG, fr_ML, fr_MQ, fr_MR, fr_MU, fr_NC, fr_NE, fr_PF, fr_PM, fr_RE, fr_RW, fr_SC, fr_SN, fr_SY, fr_TD, fr_TG, fr_TN, fr_VU, fr_WF, fr_YT, fur, fur_IT, fy, fy_NL, ga, ga_IE, gd, gd_GB, gl, gl_ES, gsw, gsw_CH, gsw_FR, gsw_LI, gu, gu_IN, guz, guz_KE, gv, gv_IM, ha, ha_GH, ha_NE, ha_NG, haw, haw_US, he, he_IL, hi, hi_IN, hr, hr_BA, hr_HR, hsb, hsb_DE, hu, hu_HU, hy, hy_AM, id, id_ID, ig, ig_NG, ii, ii_CN, is, is_IS, it, it_CH, it_IT, it_SM, ja, ja_JP, jgo, jgo_CM, jmc, jmc_TZ, ka, ka_GE, kab, kab_DZ, kam, kam_KE, kde, kde_TZ, kea, kea_CV, khq, khq_ML, ki, ki_KE, kk, kk_KZ, kkj, kkj_CM, kl, kl_GL, kln, kln_KE, km, km_KH, kn, kn_IN, ko, ko_KP, ko_KR, kok, kok_IN, ks, ks_IN, ksb, ksb_TZ, ksf, ksf_CM, ksh, ksh_DE, kw, kw_GB, ky, ky_KG, lag, lag_TZ, lb, lb_LU, lg, lg_UG, lkt, lkt_US, ln, ln_AO, ln_CD, ln_CF, ln_CG, lo, lo_LA, lrc, lrc_IQ, lrc_IR, lt, lt_LT, lu, lu_CD, luo, luo_KE, luy, luy_KE, lv, lv_LV, mas, mas_KE, mas_TZ, mer, mer_KE, mfe, mfe_MU, mg, mg_MG, mgh, mgh_MZ, mgo, mgo_CM, mk, mk_MK, ml, ml_IN, mn, mn_MN, mr, mr_IN, ms, ms_BN, ms_MY, ms_SG, mt, mt_MT, mua, mua_CM, my, my_MM, mzn, mzn_IR, naq, naq_NA, nb, nb_NO, nb_SJ, nd, nd_ZW, ne, ne_IN, ne_NP, nl, nl_AW, nl_BE, nl_BQ, nl_CW, nl_NL, nl_SR, nl_SX, nmg, nmg_CM, nn, nn_NO, nnh, nnh_CM, no, nus, nus_SS, nyn, nyn_UG, om, om_ET, om_KE, or, or_IN, os, os_GE, os_RU, pa, pa_Arab, pa_Arab_PK, pa_Guru, pa_Guru_IN, pl, pl_PL, prg, prg_001, ps, ps_AF, pt, pt_AO, pt_BR, pt_CV, pt_GW, pt_MO, pt_MZ, pt_PT, pt_ST, pt_TL, qu, qu_BO, qu_EC, qu_PE, rm, rm_CH, rn, rn_BI, ro, ro_MD, ro_RO, rof, rof_TZ, root, ru, ru_BY, ru_KG, ru_KZ, ru_MD, ru_RU, ru_UA, rw, rw_RW, rwk, rwk_TZ, sah, sah_RU, saq, saq_KE, sbp, sbp_TZ, se, se_FI, se_NO, se_SE, seh, seh_MZ, ses, ses_ML, sg, sg_CF, shi, shi_Latn, shi_Latn_MA, shi_Tfng, shi_Tfng_MA, si, si_LK, sk, sk_SK, sl, sl_SI, smn, smn_FI, sn, sn_ZW, so, so_DJ, so_ET, so_KE, so_SO, sq, sq_AL, sq_MK, sq_XK, sr, sr_Cyrl, sr_Cyrl_BA, sr_Cyrl_ME, sr_Cyrl_RS, sr_Cyrl_XK, sr_Latn, sr_Latn_BA, sr_Latn_ME, sr_Latn_RS, sr_Latn_XK, sv, sv_AX, sv_FI, sv_SE, sw, sw_CD, sw_KE, sw_TZ, sw_UG, ta, ta_IN, ta_LK, ta_MY, ta_SG, te, te_IN, teo, teo_KE, teo_UG, th, th_TH, ti, ti_ER, ti_ET, tk, tk_TM, to, to_TO, tr, tr_CY, tr_TR, twq, twq_NE, tzm, tzm_MA, ug, ug_CN, uk, uk_UA, ur, ur_IN, ur_PK, uz, uz_Arab, uz_Arab_AF, uz_Cyrl, uz_Cyrl_UZ, uz_Latn, uz_Latn_UZ, vai, vai_Latn, vai_Latn_LR, vai_Vaii, vai_Vaii_LR, vi, vi_VN, vo, vo_001, vun, vun_TZ, wae, wae_CH, xog, xog_UG, yav, yav_CM, yi, yi_UA, yo, yo_BJ, yo_NG, zgh, zgh_MA, zh, zh_Hans, zh_Hans_CN, zh_Hans_HK, zh_Hans_MO, zh_Hans_SG, zh_Hant, zh_Hant_HK, zh_Hant_MO, zh_Hant_TW, zu, zu_ZA");
 
         // LocaleMatcher.DEBUG = true;
         ULocale expected = new ULocale("sv");

tools/cldr-code/src/test/java/org/unicode/cldr/unittest/TestCLDRLocaleCoverage.java

@@ -246,6 +246,11 @@ public void TestLanguageNameCoverage() {
                         "zun",
                         "zza");
 
+        Set<String> removalsForLateBasics =
+                Set.of(
+                        "blo", "eo", "ie", "kxv", "lij", "lmo", "nds", "prg", "szl", "tok", "vec",
+                        "vmw", "xnr", "za");
+
         warnln(
                 "Locale names added for translation; revisit each release:\n"
                         + Joiner.on("\n")
@@ -283,6 +288,7 @@ public void TestLanguageNameCoverage() {
         Set<String> localesForNames = new TreeSet<>();
         localesForNames.addAll(mainLocales);
         localesForNames.addAll(additionsToTranslate);
+        localesForNames.removeAll(removalsForLateBasics);
         localesForNames = ImmutableSet.copyOf(localesForNames);
 
         assertContains("regularPlus.containsAll(mainLocales)", regularPlus, localesForNames);