Add extra locales to MS-ICU from CLDR-MS from NLS "MS-Only" culture data

icu-patches/patches/017-MSFT-Patch_ICU_test_changes_for_extra_CLDR-MS_locales.patch

@@ -0,0 +1,131 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Jeff Genovy <29107334+jefgen@users.noreply.github.com>
+Date: Wed, 7 Apr 2021 20:47:08 -0700
+Subject: MSFT-PATCH: Modify ICU tests to pass with extra locales from CLDR-MS.
+
+This changes modifies the ICU tests to pass with extra locales from
+CLDR-MS.
+
+diff --git a/icu/icu4c/source/test/cintltst/cldrtest.c b/icu/icu4c/source/test/cintltst/cldrtest.c
+index 179539d5178b5cfd8b5350043c539e89e8740185..bfb35c35a449f60c61c9a8eb6282c307e41fd161 100644
+--- a/icu/icu4c/source/test/cintltst/cldrtest.c
++++ b/icu/icu4c/source/test/cintltst/cldrtest.c
+@@ -970,7 +970,14 @@ static void VerifyTranslation(void) {
+             uprv_strncmp(currLoc, "oc", 2) == 0 || uprv_strncmp(currLoc, "oc_FR", 5) == 0     ||
+             uprv_strncmp(currLoc, "syr", 3) == 0 || uprv_strncmp(currLoc, "syr_SY", 6) == 0   ||
+             uprv_strncmp(currLoc, "tig", 3) == 0 || uprv_strncmp(currLoc, "tig_ER", 6) == 0   ||
+-            uprv_strncmp(currLoc, "wal", 3) == 0 || uprv_strncmp(currLoc, "wal_ET", 6) == 0
++            uprv_strncmp(currLoc, "wal", 3) == 0 || uprv_strncmp(currLoc, "wal_ET", 6) == 0   ||
++            uprv_strncmp(currLoc, "bin", 3) == 0 || uprv_strncmp(currLoc, "bin_NG", 6) == 0   ||
++            uprv_strncmp(currLoc, "la", 2) == 0 || uprv_strncmp(currLoc, "la_VA", 6) == 0    ||
++            uprv_strncmp(currLoc, "jv_Java", 7) == 0 || uprv_strncmp(currLoc, "jv_Java_ID", 10) == 0   ||
++            uprv_strncmp(currLoc, "ks_Deva", 7) == 0 || uprv_strncmp(currLoc, "ks_Deva_IN", 10) == 0   ||
++            uprv_strncmp(currLoc, "pap", 3) == 0 || uprv_strncmp(currLoc, "pap_029", 7) == 0           ||
++            uprv_strncmp(currLoc, "tzm_Arab", 8) == 0 || uprv_strncmp(currLoc, "tzm_Arab_MA", 11) == 0 ||
++            uprv_strncmp(currLoc, "tzm_Tfng", 8) == 0 || uprv_strncmp(currLoc, "tzm_Tfng_MA", 11) == 0
+         ) {
+             log_knownIssue("0", "MSFT Change: skipping test for %s which has issues due to CLDR Seed data.", currLoc);
+         }
+@@ -1110,7 +1117,8 @@ static void VerifyTranslation(void) {
+                if (U_FAILURE(errorCode)) {
+                    log_err("ulocdata_getMeasurementSystem failed for locale %s with error: %s \n", currLoc, u_errorName(errorCode));
+                } else {
+-                   if ( strstr(fullLoc, "_US")!=NULL || strstr(fullLoc, "_LR")!=NULL ) {
++                   /* MSFT Change: CLDR-MS adds 029 region with US measurement */
++                   if ( strstr(fullLoc, "_US")!=NULL || strstr(fullLoc, "_LR")!=NULL || strstr(fullLoc, "_029")!=NULL ) {
+                        if(measurementSystem != UMS_US){
+                             log_err("ulocdata_getMeasurementSystem did not return expected data for locale %s \n", currLoc);
+                        }
+@@ -1128,10 +1136,11 @@ static void VerifyTranslation(void) {
+                if (U_FAILURE(errorCode)) {
+                    log_err("ulocdata_getPaperSize failed for locale %s with error: %s \n", currLoc, u_errorName(errorCode));
+                } else {
++                   /* MSFT Change: CLDR-MS adds 029 region with US paper size */
+                    if ( strstr(fullLoc, "_US")!=NULL || strstr(fullLoc, "_BZ")!=NULL || strstr(fullLoc, "_CA")!=NULL || strstr(fullLoc, "_CL")!=NULL ||
+                         strstr(fullLoc, "_CO")!=NULL || strstr(fullLoc, "_CR")!=NULL || strstr(fullLoc, "_GT")!=NULL || strstr(fullLoc, "_MX")!=NULL ||
+                         strstr(fullLoc, "_NI")!=NULL || strstr(fullLoc, "_PA")!=NULL || strstr(fullLoc, "_PH")!=NULL || strstr(fullLoc, "_PR")!=NULL ||
+-                        strstr(fullLoc, "_SV")!=NULL || strstr(fullLoc, "_VE")!=NULL ) {
++                        strstr(fullLoc, "_SV")!=NULL || strstr(fullLoc, "_VE")!=NULL || strstr(fullLoc, "_029")!=NULL ) {
+                        if (height != 279 || width != 216) {
+                             log_err("ulocdata_getPaperSize did not return expected data for locale %s \n", currLoc);
+                        }
+@@ -1251,8 +1260,14 @@ static void TestExemplarSet(void){
+
+             if (existsInScript == FALSE){
+                 /* MSFT Change */
+-                if (uprv_strncmp(locale, "oc", 2) == 0 || uprv_strncmp(locale, "oc_FR", 5) == 0) {
+-                    log_knownIssue("0", "MSFT Change: oc and oc_FR have ExemplarSet issues.");
++                if (uprv_strncmp(locale, "oc", 2) == 0 || uprv_strncmp(locale, "oc_FR", 5) == 0 ||
++                    uprv_strncmp(locale, "jv_Java", 7) == 0 || uprv_strncmp(locale, "jv_Java_ID", 10) == 0 ||
++                    uprv_strncmp(locale, "la", 2) == 0 || uprv_strncmp(locale, "la_VA", 6) == 0 ||
++                    uprv_strncmp(locale, "pap", 3) == 0 || uprv_strncmp(locale, "pap_029", 7) == 0 ||
++                    uprv_strncmp(locale, "tzm_Arab", 8) == 0 || uprv_strncmp(locale, "tzm_Arab_MA", 11) == 0 ||
++                    uprv_strncmp(locale, "tzm_Tfng", 8) == 0 || uprv_strncmp(locale, "tzm_Tfng_MA", 11) == 0
++                ) {
++                    log_knownIssue("0", "MSFT Change: skipping test for %s which has issue due to CLDR seed data.", locale);
+                     continue;
+                 } else {
+                     log_err("ExemplarSet containment failed for locale : %s\n", locale);
+diff --git a/icu/icu4c/source/test/cintltst/cnmdptst.c b/icu/icu4c/source/test/cintltst/cnmdptst.c
+index 99a9ce23be7ef93923493b2b8312a254706c3f2d..a319b99e3faf6f6fc749e70852a298ce42268696 100644
+--- a/icu/icu4c/source/test/cintltst/cnmdptst.c
++++ b/icu/icu4c/source/test/cintltst/cnmdptst.c
+@@ -811,7 +811,8 @@ static void TestGetKeywordValuesForLocale(void) {
+             { "und",                "USD", "USN", NULL },
+  /*           { "und_ZZ",             "USD", NULL, NULL },  -- temporarily remove as this locale now has 15 entries */
+             { "en_US",              "USD", "USN", NULL },
+-            { "en_029",             "USD", "USN", NULL },
++        /* MSFT Change: CLDR-MS adds en_029 locale with XCD currency */
++            { "en_029",             "XCD", NULL, NULL },
+             { "en_TH",              "THB", NULL, NULL },
+             { "de",                 "EUR", NULL, NULL },
+             { "de_DE",              "EUR", NULL, NULL },
+@@ -825,11 +826,13 @@ static void TestGetKeywordValuesForLocale(void) {
+             { "en_US@currency=CAD;rg=THZZZZ", "THB", NULL, NULL },
+     };
+     const int32_t EXPECTED_SIZE[PREFERRED_SIZE] = {
+-            2, 2, 2, 2, 1, 1, 1, 1, 2, 2, 1, 1, 1, 2, 1
++        /* MSFT Change: CLDR-MS adds en_029 locale with XCD currency */
++            2, 2, 2, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 2, 1
+     };
+     /* ucurr_forLocale results for same locales; "" if no result expected */
+     const char *FORLOCALE[PREFERRED_SIZE] = {
+-            "",    "",    "USD", "",
++        /* MSFT Change: CLDR-MS adds en_029 locale with XCD currency */
++            "",    "",    "USD", "XCD",
+             "THB", "",    "EUR", "",
+             "ILS", "CAD", "ZZZ", "DEM",
+             "THB", "USD", "CAD"
+diff --git a/icu/icu4c/source/test/intltest/dtptngts.cpp b/icu/icu4c/source/test/intltest/dtptngts.cpp
+index dc86355f93fa68f509a0023dc95fc17a548170c1..c83e27bb68c212c3e9569c71ed5b417a96b7f9de 100644
+--- a/icu/icu4c/source/test/intltest/dtptngts.cpp
++++ b/icu/icu4c/source/test/intltest/dtptngts.cpp
+@@ -1408,7 +1408,8 @@ void IntlTestDateTimePatternGeneratorAPI::testJjMapping() {
+                         uprv_strncmp(localeID, "ssy_ER", 6) == 0 || uprv_strncmp(localeID, "st_LS", 5) == 0   ||
+                         uprv_strncmp(localeID, "syr", 3) == 0 || uprv_strncmp(localeID, "syr_SY", 6) == 0   ||
+                         uprv_strncmp(localeID, "tig", 3) == 0 || uprv_strncmp(localeID, "tig_ER", 6) == 0   ||
+-                        uprv_strncmp(localeID, "wal", 3) == 0 || uprv_strncmp(localeID, "wal_ET", 6) == 0
++                        uprv_strncmp(localeID, "wal", 3) == 0 || uprv_strncmp(localeID, "wal_ET", 6) == 0  ||
++                        uprv_strncmp(localeID, "ks_Deva", 7) == 0 || uprv_strncmp(localeID, "ks_Deva_IN", 10) == 0
+                      ) {
+                          logKnownIssue("0", "MSFT Change: skipping test for %s which has issues due to CLDR Seed data.", localeID);
+                      }
+diff --git a/icu/icu4c/source/test/intltest/numfmtst.cpp b/icu/icu4c/source/test/intltest/numfmtst.cpp
+index bc072bd8e3775554b8a8f96a81baf850b5e8feb7..a63c329c8eabf287512b9c152ac91d862d333264 100644
+--- a/icu/icu4c/source/test/intltest/numfmtst.cpp
++++ b/icu/icu4c/source/test/intltest/numfmtst.cpp
+@@ -8094,10 +8094,12 @@ void NumberFormatTest::TestAccountingCurrency() {
+         (Formattable)(double)-1000.5, UnicodeString("(\\uFFE51,000)").unescape(), FALSE, status);
+     expect(NumberFormat::createInstance("de_DE", style, status),
+         (Formattable)(double)-23456.7, UnicodeString("-23.456,70\\u00A0\\u20AC").unescape(), TRUE, status);
++    /* MSFT Change: We add a CLDR-MS locale en_ID */
+     expect(NumberFormat::createInstance("en_ID", style, status),
+-        (Formattable)(double)0, UnicodeString("IDR\\u00A00.00").unescape(), TRUE, status);
++        (Formattable)(double)0, UnicodeString("IDR\\u00A00,00").unescape(), TRUE, status);
+     expect(NumberFormat::createInstance("en_ID", style, status),
+-        (Formattable)(double)-0.2, UnicodeString("(IDR\\u00A00.20)").unescape(), TRUE, status);
++        (Formattable)(double)-0.2, UnicodeString("(IDR\\u00A00,20)").unescape(), TRUE, status);
++    /* MSFT Change: End */
+     expect(NumberFormat::createInstance("sh_ME", style, status),
+         (Formattable)(double)0, UnicodeString("0,00\\u00A0\\u20AC").unescape(), TRUE, status);
+     expect(NumberFormat::createInstance("sh_ME", style, status),

icu-patches/patches/018-MSFT-Patch_ICU_toolutil_increase_string_store_for_extra_locales.patch

@@ -0,0 +1,19 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Jeff Genovy <29107334+jefgen@users.noreply.github.com>
+Date: Wed, 7 Apr 2021 20:47:31 -0700
+Subject: MSFT-PATCH: Increase the STRING_STORE_SIZE due to extra locales from CLDR-MS
+
+
+diff --git a/icu/icu4c/source/tools/toolutil/package.h b/icu/icu4c/source/tools/toolutil/package.h
+index ea60c13a74a57b94057882e39b6aa05314c4ca1f..6c411ae5fd04c8463a089307efc056f4d2f622f9 100644
+--- a/icu/icu4c/source/tools/toolutil/package.h
++++ b/icu/icu4c/source/tools/toolutil/package.h
+@@ -27,7 +27,7 @@
+
+ // .dat package file representation ---------------------------------------- ***
+
+-#define STRING_STORE_SIZE 100000
++#define STRING_STORE_SIZE 120000
+ #define MAX_PKG_NAME_LENGTH 64
+
+ typedef void CheckDependency(void *context, const char *itemName, const char *targetName);

icu/icu4c/source/data/curr/LOCALE_DEPS.json

@@ -21,6 +21,10 @@
         "ff_GN": "ff_Latn_GN",
         "ff_MR": "ff_Latn_MR",
         "ff_SN": "ff_Latn_SN",
+        "ha_Latn": "ha",
+        "ha_Latn_GH": "ha_GH",
+        "ha_Latn_NE": "ha_NE",
+        "ha_Latn_NG": "ha_NG",
         "in": "id",
         "in_ID": "id_ID",
         "iu_Cans": "iu",
@@ -75,6 +79,9 @@
         "su_ID": "su_Latn_ID",
         "tl": "fil",
         "tl_PH": "fil_PH",
+        "tzm_Latn": "tzm",
+        "tzm_Latn_DZ": "tzm_DZ",
+        "tzm_Latn_MA": "tzm_MA",
         "uz_AF": "uz_Arab_AF",
         "uz_UZ": "uz_Latn_UZ",
         "vai_LR": "vai_Vaii_LR",
@@ -204,6 +211,7 @@
         "es_VE": "es_419",
         "ff_Adlm": "root",
         "iu_Latn": "root",
+        "ks_Deva": "root",
         "mn_Mong": "root",
         "pa_Arab": "root",
         "pt_AO": "pt_PT",

icu/icu4c/source/data/curr/bin.txt

@@ -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
+bin{
+}

icu/icu4c/source/data/curr/en_029.txt

@@ -0,0 +1,11 @@
+// © 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
+en_029{
+    Currencies{
+        XCD{
+            "EC$",
+            "East Caribbean Dollar",
+        }
+    }
+}

icu/icu4c/source/data/curr/en_ID.txt

@@ -0,0 +1,11 @@
+// © 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
+en_ID{
+    Currencies{
+        IDR{
+            "IDR",
+            "Rupiah",
+        }
+    }
+}

icu/icu4c/source/data/curr/fr_029.txt

@@ -0,0 +1,11 @@
+// © 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
+fr_029{
+    Currencies{
+        XCD{
+            "EC$",
+            "dollar des Caraïbes orientales",
+        }
+    }
+}

icu/icu4c/source/data/curr/ha_Latn.txt

@@ -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
+ha_Latn{
+    "%%ALIAS"{"ha"}
+}

icu/icu4c/source/data/curr/ha_Latn_GH.txt

@@ -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
+ha_Latn_GH{
+    "%%ALIAS"{"ha_GH"}
+}

icu/icu4c/source/data/curr/ha_Latn_NE.txt

@@ -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
+ha_Latn_NE{
+    "%%ALIAS"{"ha_NE"}
+}

icu/icu4c/source/data/curr/ha_Latn_NG.txt

@@ -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
+ha_Latn_NG{
+    "%%ALIAS"{"ha_NG"}
+}

icu/icu4c/source/data/curr/ha_NE.txt

@@ -0,0 +1,9 @@
+// © 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
+/**
+ * generated alias target
+ */
+ha_NE{
+    ___{""}
+}

icu/icu4c/source/data/curr/ha_NG.txt

@@ -0,0 +1,9 @@
+// © 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
+/**
+ * generated alias target
+ */
+ha_NG{
+    ___{""}
+}

icu/icu4c/source/data/curr/ibb.txt

@@ -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
+ibb{
+}

icu/icu4c/source/data/curr/kr.txt

@@ -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
+kr{
+}

icu/icu4c/source/data/curr/ks_Deva.txt

@@ -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"}
+}

icu/icu4c/source/data/curr/la.txt

@@ -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
+la{
+}

icu/icu4c/source/data/curr/pap.txt

@@ -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
+pap{
+}

icu/icu4c/source/data/curr/supplementalData.txt

@@ -3,6 +3,15 @@
 // Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
 supplementalData:table(nofallback){
     CurrencyMap{
+        029{
+            {
+                from:intvector{
+                    -507,
+                    95619072,
+                }
+                id{"XCD"}
+            }
+        }
         AC{
             {
                 from:intvector{

icu/icu4c/source/data/curr/tzm_DZ.txt

@@ -0,0 +1,11 @@
+// © 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
+tzm_DZ{
+    Currencies{
+        DZD{
+            "DA",
+            "Dinar",
+        }
+    }
+}

icu/icu4c/source/data/curr/tzm_Latn.txt

@@ -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
+tzm_Latn{
+    "%%ALIAS"{"tzm"}
+}

icu/icu4c/source/data/curr/tzm_Latn_DZ.txt

@@ -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
+tzm_Latn_DZ{
+    "%%ALIAS"{"tzm_DZ"}
+}

icu/icu4c/source/data/curr/tzm_Latn_MA.txt

@@ -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
+tzm_Latn_MA{
+    "%%ALIAS"{"tzm_MA"}
+}

icu/icu4c/source/data/curr/tzm_MA.txt

@@ -0,0 +1,9 @@
+// © 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
+/**
+ * generated alias target
+ */
+tzm_MA{
+    ___{""}
+}

icu/icu4c/source/data/curr/tzm_Tfng.txt

@@ -0,0 +1,11 @@
+// © 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
+tzm_Tfng{
+    Currencies{
+        MAD{
+            "ⴷⵔ",
+            "ⴷⵔⵀⵎ ⴰⵎⵖⵔⴰⴱⵉ",
+        }
+    }
+}