update dictionary + genc fixes

NEWS.md

@@ -3,6 +3,7 @@
 ## development
 
 * The `simplify` argument in `apply` was introduced in R 4.1.0. We used it, which broke usage of countrycode on older versions of R.
+* `genc` code improvements.
 
 ## countrycode 1.6.0
 

dictionary/codelist_without_cldr.csv

@@ -279,7 +279,7 @@ OECD1990,.va,Europe,Vatikanstaat,vatikan|heilig.*stuhl,Vatican City,holy.?see|va
 LAM,.ve,Americas,Venezuela,venezuela,Venezuela,venezuela,Venezuela,venezuela|vénézuélien,Venezuela,venezuela,Venezuela,VEN,101,Bolívar Soberano,,VE,,Southern America,South-Atlantic,VE,236,VE,263,VE,VEN,862,VEN,101,CARSAM,299,VEN,Venezuela (Bolivarian Republic of),Venezuela (République bolivarienne du),VE,VEN,862,VED,926,Venezuela,VEN,101,VEN,101,Latin America & Caribbean,South America,862,فنزويلا (جمهورية - البوليفارية),Venezuela (Bolivarian Republic of),Venezuela (República Bolivariana de),Venezuela (République bolivarienne du),Венесуэла (Боливарианская Республика),委内瑞拉（玻利瓦尔共和国）,19,Americas,5,South America,419,Latin America and the Caribbean,VEN,The Americas,🇻🇪,862,51,Venezuela,VEN,VE,VEN,862
 ASIA,.vn,Asia,Vietnam,^(?!.*republik).*viet.?nam|^(?=.*sozialist).*viet.?nam,Vietnam,^(?!south)(?!republic).*viet.?nam(?!.*south)|democratic.republic.of.vietnam|socialist.republic.of.viet.?nam|north.viet.?nam|viet.?nam.north,Vietnam,^(?!.*republique).*viet.?nam|^(?=.*socialist).*viet.?nam,Vietnam,^(?!.*republik).*viet.?nam|^(?=.*sozialist).*viet.?nam,Vietnam,DRV,816,Dong,VN,VN,,Asia,Asia/Pacific,VN,237,VM,264,VN,VNM,704,RVN,817,ASIAPAC,582,VIE,Viet Nam,Viet Nam (le),VN,VNM,704,VND,704,Vietnam,VIE,818,VIE,818,East Asia & Pacific,South-Eastern Asia,704,فييت نام,Viet Nam,Viet Nam,Viet Nam,Вьетнам,越南,142,Asia,,,35,South-eastern Asia,SRV,Asia and the Pacific,🇻🇳,704,34,Vietnam,VNM,VN,VNM,704
 ASIA,.wf,Oceania,Wallis und Futuna,futuna|wallis,Wallis & Futuna,futuna|wallis,Wallis-et-Futuna,futuna|wallis,Wallis e Futuna,futuna|wallis,,,,CFP Franc,,WF,,Asia,Asia/Pacific,WF,243,WF,266,WF,WLF,876,,,,,,Wallis and Futuna,Wallis-et-Futuna,WF,WLF,876,XPF,953,,,,,,,Polynesia,876,,,,,,,9,Oceania,,,61,Polynesia,,,🇼🇫,876,,,,,,
-MAF,.eh,Africa,Westsahara,west.*sahara,Western Sahara,western.sahara,Sahara occidental,west.*sahara|sahara.*(occidental|ouest),Sahara occidentale,west.*sahara|sahara.*occidentale,,,,Moroccan Dirham,,EH,,Africa,Southern Africa,EH,205,WI,268,EH,ESH,732,,,AFI,,,Western Sahara,Sahara occidental (le),EH,ESH,732,MAD,504,,,,,,,Northern Africa,732,,,,,,,2,Africa,,,15,Northern Africa,WSH,Middle East and North Africa,🇪🇭,732,,,,,,
+MAF,.eh,Africa,Westsahara,west.*sahara,Western Sahara,western.sahara,Sahara occidental,west.*sahara|sahara.*(occidental|ouest),Sahara occidentale,west.*sahara|sahara.*occidentale,,,,Moroccan Dirham,,EH,,Africa,Southern Africa,EH,205,WI,268,,,,,,AFI,,,Western Sahara,Sahara occidental (le),EH,ESH,732,MAD,504,,,,,,,Northern Africa,732,,,,,,,2,Africa,,,15,Northern Africa,WSH,Middle East and North Africa,🇪🇭,732,,,,,,
 ,,,Württemberg,w(ue|ü)rttemberg,Wuerttemburg,w(ue|ü)rttemburg,,w.rt.?emberg,,w.rt.?emberg,Wuerttemburg,WRT,271,,,,,,,,,,,,,,,,,,,,,,,,,,Wuerttemburg,WRT,271,WRT,271,Europe & Central Asia,,,,,,,,,,,,,,,,,,,,,,,,
 ,,,,,Würtemberg,w.rtemberg,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,Europe & Central Asia,,,,,,,,,,,,,,,,,,,355,Würtemberg,,,,
 MAF,.ye,Asia,Jemen,^(?!.*arab)(?!.*nord)(?!.*sana)(?!.*peo)(?!.*dem)(?!.*süd)(?!.*aden)(?!.*\bp\.?d\.?r).*jemen,Yemen,^(?!.*arab)(?!.*north)(?!.*sana)(?!.*peo)(?!.*dem)(?!.*south)(?!.*aden)(?!.*\bp\.?d\.?r).*yemen,Yémen,y(e|é)men,Yemen,yemen,Yemen,YEM,679,Yemeni Rial,YE,YE,,Middle East,Middle-East,YE,249,YM,269,YE,YEM,887,,,MID,474,YEM,Yemen,Yémen (le),YE,YEM,887,YER,886,Yemen,YEM,679,YEM,679,Middle East & North Africa,Western Asia,887,اليمن,Yemen,Yemen,Yémen,Йемен,也门,142,Asia,,,145,Western Asia,YEM,Middle East and North Africa,🇾🇪,887,14,Yemen,YEM,YE,YEM,887

dictionary/data_genc.csv

@@ -1,8 +1,5 @@
 country,genc2c,genc3c,genc3n
-ABU MUSA AND TUNB ISLANDS,AA,XAA,935
-ABYEI,QN,XQN,936
 AFGHANISTAN,AF,AFG,004
-AKSAI CHIN AND OTHER AREAS,QO,XQO,937
 ALBANIA,AL,ALB,008
 ALGERIA,DZ,DZA,012
 AMERICAN SAMOA,AS,ASM,016
@@ -32,7 +29,6 @@ BOSNIA AND HERZEGOVINA,BA,BIH,070
 BOTSWANA,BW,BWA,072
 BOUVET ISLAND,BV,BVT,074
 BRAZIL,BR,BRA,076
-BRAZILIAN ISLAND,QP,XQP,938
 BRITISH INDIAN OCEAN TERRITORY,IO,IOT,086
 BRUNEI,BN,BRN,096
 BULGARIA,BG,BGR,100
@@ -53,12 +49,9 @@ CHRISTMAS ISLAND,CX,CXR,162
 COCOS (KEELING) ISLANDS,CC,CCK,166
 COLOMBIA,CO,COL,170
 COMOROS,KM,COM,174
-CONEJO ISLAND,QQ,XQQ,939
 CONGO (BRAZZAVILLE),CG,COG,178
 CONGO (KINSHASA),CD,COD,180
-CONGO RIVER ISLANDS,QR,XQR,940
 COOK ISLANDS,CK,COK,184
-CORISCO BAY ISLANDS,QT,XQT,941
 COSTA RICA,CR,CRI,188
 CÔTE D’IVOIRE,CI,CIV,384
 CROATIA,HR,HRV,191
@@ -70,8 +63,6 @@ DENMARK,DK,DNK,208
 DJIBOUTI,DJ,DJI,262
 DOMINICA,DM,DMA,212
 DOMINICAN REPUBLIC,DO,DOM,214
-DOUMEIRA ISLANDS,QV,XQV,942
-DRAMANA AND SHAKHATOE,QY,XQY,943
 ECUADOR,EC,ECU,218
 EGYPT,EG,EGY,818
 EL SALVADOR,SV,SLV,222
@@ -92,7 +83,6 @@ GABON,GA,GAB,266
 "GAMBIA, THE",GM,GMB,270
 GEORGIA,GE,GEO,268
 GERMANY,DE,DEU,276
-GEYSER REEF,XF,XXF,944
 GHANA,GH,GHA,288
 GIBRALTAR,GI,GIB,292
 GREECE,GR,GRC,300
@@ -106,9 +96,7 @@ GUINEA,GN,GIN,324
 GUINEA-BISSAU,GW,GNB,624
 GUYANA,GY,GUY,328
 HAITI,HT,HTI,332
-HANS ISLAND,XI,XXI,945
 HEARD ISLAND AND MCDONALD ISLANDS,HM,HMD,334
-HEIPETHES ISLANDS,XN,XXN,946
 HONDURAS,HN,HND,340
 HONG KONG,HK,HKG,344
 HUNGARY,HU,HUN,348
@@ -125,11 +113,9 @@ JAMAICA,JM,JAM,388
 JAPAN,JP,JPN,392
 JERSEY,JE,JEY,832
 JORDAN,JO,JOR,400
-KALAPANI,XO,XXO,947
 KAZAKHSTAN,KZ,KAZ,398
 KENYA,KE,KEN,404
 KIRIBATI,KI,KIR,296
-KOALOU / KOUROU,XX,XXX,948
 "KOREA, NORTH",KP,PRK,408
 "KOREA, SOUTH",KR,KOR,410
 KOSOVO,XK,XKS,901
@@ -158,7 +144,6 @@ MAURITIUS,MU,MUS,480
 MAYOTTE,YT,MYT,175
 MEXICO,MX,MEX,484
 "MICRONESIA, FEDERATED STATES OF",FM,FSM,583
-MINERVA REEFS,XY,XXY,949
 MOLDOVA,MD,MDA,498
 MONACO,MC,MCO,492
 MONGOLIA,MN,MNG,496
@@ -186,7 +171,6 @@ PALAU,PW,PLW,585
 PANAMA,PA,PAN,591
 PAPUA NEW GUINEA,PG,PNG,598
 PARAGUAY,PY,PRY,600
-PARSLEY ISLAND,XZ,XXZ,950
 PERU,PE,PER,604
 PHILIPPINES,PH,PHL,608
 PITCAIRN ISLANDS,PN,PCN,612
@@ -207,12 +191,10 @@ SAINT VINCENT AND THE GRENADINES,VC,VCT,670
 SAMOA,WS,WSM,882
 SAN MARINO,SM,SMR,674
 SAO TOME AND PRINCIPE,ST,STP,678
-SAPODILLA CAYES,ZZ,XZZ,951
 SAUDI ARABIA,SA,SAU,682
 SENEGAL,SN,SEN,686
 SERBIA,RS,SRB,688
 SEYCHELLES,SC,SYC,690
-SIACHEN,SQ,XSQ,952
 SIERRA LEONE,SL,SLE,694
 SINGAPORE,SG,SGP,702
 SINT MAARTEN,SX,SXM,534

dictionary/get_genc.R

@@ -10,14 +10,8 @@ tmp <- tempfile()
 httr::GET(url, write_disk(tmp, overwrite=TRUE))
 genc <- readxl::read_excel(tmp, sheet = 'Codes_for_GE_Names', skip = 2)
 
-bad <- c('AKROTIRI', 'ASHMORE AND CARTIER ISLANDS', 'BAKER ISLAND',
-         'CLIPPERTON ISLAND', 'CORAL SEA ISLANDS', 'DHEKELIA', 'DIEGO GARCIA',
-         'ENTITY 1', 'ENTITY 2', 'ENTITY 3', 'ENTITY 4', 'ENTITY 5', 'ENTITY 6',
-         'EUROPA ISLAND', 'GLORIOSO ISLANDS', 'GUANTANAMO BAY NAVAL BASE',
-         'HOWLAND ISLAND', 'JAN MAYEN', 'JARVIS ISLAND', 'JOHNSTON ATOLL',
-         'JUAN DE NOVA ISLAND', 'KINGMAN REEF', 'MIDWAY ISLANDS',
-         'NAVASSA ISLAND', 'PALMYRA ATOLL', 'PARACEL ISLANDS', 'SAINT MARTIN',
-         'SPRATLY ISLANDS', 'TROMELIN ISLAND', 'UNKNOWN', 'WAKE ISLAND', 'BASSAS DA INDIA', 'GAZA STRIP')
+bad <- c('AKROTIRI', 'ASHMORE AND CARTIER ISLANDS', 'BAKER ISLAND', 'CLIPPERTON ISLAND', 'CORAL SEA ISLANDS', 'DHEKELIA', 'DIEGO GARCIA', 'ENTITY 1', 'ENTITY 2', 'ENTITY 3', 'ENTITY 4', 'ENTITY 5', 'ENTITY 6', 'EUROPA ISLAND', 'GLORIOSO ISLANDS', 'GUANTANAMO BAY NAVAL BASE', 'HOWLAND ISLAND', 'JAN MAYEN', 'JARVIS ISLAND', 'JOHNSTON ATOLL', 'JUAN DE NOVA ISLAND', 'KINGMAN REEF', 'MIDWAY ISLANDS', 'NAVASSA ISLAND', 'PALMYRA ATOLL', 'PARACEL ISLANDS', 'SAINT MARTIN', 'SPRATLY ISLANDS', 'TROMELIN ISLAND', 'UNKNOWN', 'WAKE ISLAND', 'BASSAS DA INDIA', 'GAZA STRIP', "ABU MUSA AND TUNB ISLANDS", "ABYEI", "AKSAI CHIN AND OTHER AREAS", "CONEJO ISLAND", "CORISCO BAY ISLANDS", "DOUMEIRA ISLANDS", "DRAMANA AND SHAKHATOE", "GEYSER REEF", "HANS ISLAND", "HEIPETHES ISLANDS", "KALAPANI", "KOALOU / KOUROU", "MINERVA REEFS", "PARSLEY ISLAND", "SAPODILLA CAYES", "SIACHEN", "BRAZILIAN ISLAND", "CONGO RIVER ISLANDS")
+
 genc <-
     genc %>%
     dplyr::select(country = Name, genc2c = `2-character Code`,