CLDR-17884 Update CIA Factbook

CLDR-17884 Check alternate country names without parentheses too

CLDR-17884 Regex match

add country note

CLDR-17884 Remove world bank aggregates

tools/cldr-code/src/main/java/org/unicode/cldr/tool/AddPopulationData.java

@@ -85,11 +85,13 @@ static ArrayList<Pair<WBLine, Integer>> parseHeader(final String[] pieces) {
         }
     }
 
-    enum FBLine {
-        Rank,
-        Country,
+    enum FactbookLine {
+        CountryName,
+        CountrySlug,
         Value,
-        Year;
+        DateOfInformation,
+        Ranking,
+        Region;
 
         String get(String[] pieces) {
             return pieces[ordinal()];
@@ -279,16 +281,13 @@ private static void loadFactbookInfo(String filename, final Counter2<String> fac
                 new LineHandler() {
                     @Override
                     public boolean handle(String line) {
-                        if (line.length() == 0
-                                || line.startsWith("This tab")
-                                || line.startsWith("Rank")
-                                || line.startsWith(" This file")) {
+                        String[] pieces = splitCommaSeparated(line);
+                        String countryName =  FactbookLine.CountryName.get(pieces);
+                        if (countryName.equals("name")) {
                             return false;
                         }
-                        String[] pieces = line.split("\\s{2,}");
                         String code =
-                                CountryCodeConverter.getCodeFromName(
-                                        FBLine.Country.get(pieces), true, missing);
+                                CountryCodeConverter.getCodeFromName(countryName, true, missing);
                         if (code == null) {
                             return false;
                         }
@@ -299,7 +298,7 @@ public boolean handle(String line) {
                             return false;
                         }
                         code = code.toUpperCase(Locale.ENGLISH);
-                        String valueString = FBLine.Value.get(pieces).trim();
+                        String valueString = FactbookLine.Value.get(pieces).trim();
                         if (valueString.startsWith("$")) {
                             valueString = valueString.substring(1);
                         }
@@ -539,8 +538,8 @@ static List<Pair<String, Double>> getUnLiteracy(Output<Boolean> hadErr) throws I
             loadFactbookLiteracy();
             loadUnLiteracy();
 
-            loadFactbookInfo("external/factbook_gdp_ppp.txt", factbook_gdp);
-            loadFactbookInfo("external/factbook_population.txt", factbook_population);
+            loadFactbookInfo("external/factbook_gdp_ppp.csv", factbook_gdp);
+            loadFactbookInfo("external/factbook_population.csv", factbook_population);
             CldrUtility.handleFile("external/other_country_data.txt", new MyLineHandler(other));
 
             loadWorldBankInfo();
@@ -581,7 +580,7 @@ static List<Pair<String, Double>> getUnLiteracy(Output<Boolean> hadErr) throws I
             }
             if (myErrors.length() != 0) {
                 throw new IllegalArgumentException(
-                        "Missing Country values, the following and add to external/other_country_data to fix, chaning the 0 to the real value:"
+                        "Missing Country values, the following and add to external/other_country_data to fix, changing the 0 to the real value:"
                                 + myErrors);
             }
         } catch (IOException e) {

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

@@ -142,13 +142,17 @@ SY; Syria; Syrian Arab Republic
 SZ; Eswatini; eSwatini; Swaziland
 SZ; Eswatini;	Swaziland
 
+SH; Saint Helena;	Saint Helena
+SH; Saint Helena;	St. Helena
 SH; Saint Helena; Saint Helena, Ascension, and Tristan da Cunha
+SH; Saint Helena; Saint Helena, Ascension and Tristan da Cunha
 SH; Saint Helena; Saint Helena ex. dep.
 
 TL; East Timor; Timor-Leste
 TL; East Timor; East Timor
 
 TR; Turkey; Turkiye
+TR; Turkey; Turkey (Turkiye)
 TR; ; Turkey
 
 
@@ -198,11 +202,11 @@ RE; ;	Reunion
 PS; ;	Palestinian Territory
 CD; ;	Congo, Democratic Republic
 FX; ;	France, Metropolitan
-SH; ;	St. Helena
 SJ; ;	Svalbard and Jan Mayen Islands
 VA; ;	Vatican
 CW; ;	Netherlands Antilles
 WF; ;	Wallis and Futuna Islands
+WF; ;	Wallis and Futuna
 HM; ;	Heard and McDonald Islands
 PM; ;	St. Pierre and Miquelon
 
@@ -220,34 +224,9 @@ UK;; U.K.
 RS;; Yugoslavia
 KM;; Comros
 
-skip;	skip;	Arab World
-skip;	skip;	Caribbean small states
-skip;	skip;	Country Name
-skip;	skip;	East Asia & Pacific (all income levels)
-skip;	skip;	East Asia & Pacific (developing only)
-skip;	skip;	Euro area
-skip;	skip;	Europe & Central Asia (all income levels)
-skip;	skip;	Europe & Central Asia (developing only)
-skip;	skip;	Heavily indebted poor countries (HIPC)
-skip;	skip;	High income
-skip;	skip;	High income: nonOECD
-skip;	skip;	High income: OECD
-skip;	skip;	Latin America & Caribbean (all income levels)
-skip;	skip;	Latin America & Caribbean (developing only)
-skip;	skip;	Least developed countries: UN classification
-skip;	skip;	Low & middle income
-skip;	skip;	Low income
-skip;	skip;	Lower middle income
-skip;	skip;	Middle East & North Africa (all income levels)
-skip;	skip;	Middle East & North Africa (developing only)
-skip;	skip;	Middle income
-skip;	skip;	OECD members
-skip;	skip;	Other small states
-skip;	skip;	Pacific island small states
-skip;	skip;	Small states
-skip;	skip;	South Asia
-skip;	skip;	Sub-Saharan Africa (all income levels)
-skip;	skip;	Sub-Saharan Africa (developing only)
-skip;	skip;	Sudan (pre-secession)
-skip;	skip;	Upper middle income
-skip;	skip;	Paracel Islands
+419;	Latin America & Caribbean;	Latin America & Caribbean
+419;	Latin America & Caribbean;	Latin America & the Caribbean
+
+# Many of the skipped values below are aggregates from world_bank_data that we can ignore since they don't correspond to UN country groups
+
+skip;	skip;	Paracel Islands