ICU-22560 Merge ICU 74 maintenance branch to main (#2689)

.github/workflows/icu_ci.yml

@@ -530,10 +530,10 @@ jobs:
  - "-DUCONFIG_NO_FORMATTING=1"
  - "-DUCONFIG_NO_TRANSLITERATION=1"
  - "-DUCONFIG_NO_REGULAR_EXPRESSIONS=1"
- - "-DUCONFIG_NO_SERVICN=1"
+ - "-DUCONFIG_NO_SERVICE=1"
  - "-DUCONFIG_NO_FILTERED_BREAK_ITERATION=1"
  # Turn on all the options in one test.
- - "-DUCONFIG_NO_LEGACY_CONVERSION=1 -DUCONFIG_NO_NORMALIZATION=1 -DUCONFIG_NO_BREAK_ITERATION=1 -DUCONFIG_NO_IDNA=1 -DUCONFIG_NO_COLLATION=1 -DUCONFIG_NO_FORMATTING=1 -DUCONFIG_NO_TRANSLITERATION=1 -DUCONFIG_NO_REGULAR_EXPRESSIONS=1 -DUCONFIG_NO_SERVICN=1 -DUCONFIG_NO_FILTERED_BREAK_ITERATION=1"
+ - "-DUCONFIG_NO_LEGACY_CONVERSION=1 -DUCONFIG_NO_NORMALIZATION=1 -DUCONFIG_NO_BREAK_ITERATION=1 -DUCONFIG_NO_IDNA=1 -DUCONFIG_NO_COLLATION=1 -DUCONFIG_NO_FORMATTING=1 -DUCONFIG_NO_TRANSLITERATION=1 -DUCONFIG_NO_REGULAR_EXPRESSIONS=1 -DUCONFIG_NO_SERVICE=1 -DUCONFIG_NO_FILTERED_BREAK_ITERATION=1"
  steps:
  - name: Checkout
  uses: actions/checkout@v3
@@ -576,10 +576,10 @@ jobs:
  - "-DUCONFIG_NO_FORMATTING=1"
  - "-DUCONFIG_NO_TRANSLITERATION=1"
  - "-DUCONFIG_NO_REGULAR_EXPRESSIONS=1"
- - "-DUCONFIG_NO_SERVICN=1"
+ - "-DUCONFIG_NO_SERVICE=1"
  - "-DUCONFIG_NO_FILTERED_BREAK_ITERATION=1"
  # Turn on all the options in one test.
- - "-DUCONFIG_NO_LEGACY_CONVERSION=1 -DUCONFIG_NO_NORMALIZATION=1 -DUCONFIG_NO_BREAK_ITERATION=1 -DUCONFIG_NO_IDNA=1 -DUCONFIG_NO_COLLATION=1 -DUCONFIG_NO_FORMATTING=1 -DUCONFIG_NO_TRANSLITERATION=1 -DUCONFIG_NO_REGULAR_EXPRESSIONS=1 -DUCONFIG_NO_SERVICN=1 -DUCONFIG_NO_FILTERED_BREAK_ITERATION=1"
+ - "-DUCONFIG_NO_LEGACY_CONVERSION=1 -DUCONFIG_NO_NORMALIZATION=1 -DUCONFIG_NO_BREAK_ITERATION=1 -DUCONFIG_NO_IDNA=1 -DUCONFIG_NO_COLLATION=1 -DUCONFIG_NO_FORMATTING=1 -DUCONFIG_NO_TRANSLITERATION=1 -DUCONFIG_NO_REGULAR_EXPRESSIONS=1 -DUCONFIG_NO_SERVICE=1 -DUCONFIG_NO_FILTERED_BREAK_ITERATION=1"
  steps:
  - name: Checkout
  uses: actions/checkout@v3
@@ -712,7 +712,7 @@ jobs:
  make -j -l2.5 check
  
  # https://unicode-org.github.io/icu/processes/release/tasks/healthy-code.html#test-uconfig_no_conversion
- icu4c-uconfig-no-version:
+ icu4c-uconfig-no-conversion:
  runs-on: ubuntu-latest
  steps:
  - uses: actions/checkout@v3

docs/userguide/datetime/timezone/index.md

@@ -76,7 +76,7 @@ of classes. This protocol includes:
 
 * A programmatic ID, for example, "America/Los_Angeles". This ID is used to
  call up a specific real-world time zone. It corresponds to the IDs defined
- in the [IANA Time Zone datbase](https://www.iana.org/time-zones) used by UNIX
+ in the [IANA Time Zone database](https://www.iana.org/time-zones) used by UNIX
  and other systems, and has the format continent/city or ocean/city.
 * A raw offset. This is the difference, in milliseconds, between a time zone's
  standard time and GMT. Positive raw offsets are east of Greenwich.
@@ -245,7 +245,7 @@ sources for general information on building ICU.
 
 ### Update the time zone data for ICU4J
 
-The [ICU4J Time Zone Update Update
+The [ICU4J Time Zone Update 
 Utility](https://icu.unicode.org/download/icutzu) automates the process of
 updating ICU4J jar files with the latest time zone data. Instructions for use
 are [here](https://htmlpreview.github.io/?https://github.com/unicode-org/icu-data/blob/main/tzdata/tzu/readme.html).

icu4c/source/common/putil.cpp

@@ -1175,6 +1175,21 @@ uprv_tzname(int n)
  if (ret != nullptr && uprv_strcmp(TZDEFAULT, gTimeZoneBuffer) != 0) {
  int32_t tzZoneInfoTailLen = uprv_strlen(TZZONEINFOTAIL);
  const char *tzZoneInfoTailPtr = uprv_strstr(gTimeZoneBuffer, TZZONEINFOTAIL);
+ // MacOS14 has the realpath as something like
+ // /usr/share/zoneinfo.default/Australia/Melbourne
+ // which will not have "/zoneinfo/" in the path.
+ // Therefore if we fail, we fall back to read the link which is
+ // /var/db/timezone/zoneinfo/Australia/Melbourne
+ // We also fall back to reading the link if the realpath leads to something like
+ // /usr/share/zoneinfo/posixrules
+ if (tzZoneInfoTailPtr == nullptr ||
+ uprv_strcmp(tzZoneInfoTailPtr + tzZoneInfoTailLen, "posixrules") == 0) {
+ ssize_t size = readlink(TZDEFAULT, gTimeZoneBuffer, sizeof(gTimeZoneBuffer)-1);
+ if (size > 0) {
+ gTimeZoneBuffer[size] = 0;
+ tzZoneInfoTailPtr = uprv_strstr(gTimeZoneBuffer, TZZONEINFOTAIL);
+ }
+ }
  if (tzZoneInfoTailPtr != nullptr) {
  tzZoneInfoTailPtr += tzZoneInfoTailLen;
  skipZoneIDPrefix(&tzZoneInfoTailPtr);

icu4c/source/common/uloc.cpp

@@ -103,12 +103,12 @@ static const char * const LANGUAGES[] = {
  "ba", "bal", "ban", "bar", "bas", "bax", "bbc", "bbj",
  "be", "bej", "bem", "bew", "bez", "bfd", "bfq", "bg",
  "bgc", "bgn", "bho", "bi", "bik", "bin", "bjn", "bkm", "bla",
- "bm", "bn", "bo", "bpy", "bqi", "br", "bra", "brh",
+ "blo", "bm", "bn", "bo", "bpy", "bqi", "br", "bra", "brh",
  "brx", "bs", "bss", "bua", "bug", "bum", "byn", "byv",
  "ca", "cad", "car", "cay", "cch", "ccp", "ce", "ceb", "cgg",
  "ch", "chb", "chg", "chk", "chm", "chn", "cho", "chp",
  "chr", "chy", "ckb", "co", "cop", "cps", "cr", "crh",
- "cs", "csb", "cu", "cv", "cy",
+ "cs", "csb", "csw", "cu", "cv", "cy",
  "da", "dak", "dar", "dav", "de", "del", "den", "dgr",
  "din", "dje", "doi", "dsb", "dtp", "dua", "dum", "dv",
  "dyo", "dyu", "dz", "dzg",
@@ -135,7 +135,7 @@ static const char * const LANGUAGES[] = {
  "kkj", "kl", "kln", "km", "kmb", "kn", "ko", "koi",
  "kok", "kos", "kpe", "kr", "krc", "kri", "krj", "krl",
  "kru", "ks", "ksb", "ksf", "ksh", "ku", "kum", "kut",
- "kv", "kw", "ky",
+ "kv", "kw", "kxv", "ky",
  "la", "lad", "lag", "lah", "lam", "lb", "lez", "lfn",
  "lg", "li", "lij", "liv", "lkt", "lmo", "ln", "lo",
  "lol", "loz", "lrc", "lt", "ltg", "lu", "lua", "lui",
@@ -169,14 +169,14 @@ static const char * const LANGUAGES[] = {
  "sv", "sw", "swb", "syc", "syr", "szl",
  "ta", "tcy", "te", "tem", "teo", "ter", "tet", "tg",
  "th", "ti", "tig", "tiv", "tk", "tkl", "tkr",
- "tlh", "tli", "tly", "tmh", "tn", "to", "tog", "tpi",
+ "tlh", "tli", "tly", "tmh", "tn", "to", "tog", "tok", "tpi",
  "tr", "tru", "trv", "ts", "tsd", "tsi", "tt", "ttt",
  "tum", "tvl", "tw", "twq", "ty", "tyv", "tzm",
  "udm", "ug", "uga", "uk", "umb", "und", "ur", "uz",
  "vai", "ve", "vec", "vep", "vi", "vls", "vmf", "vmw",
  "vo", "vot", "vro", "vun",
  "wa", "wae", "wal", "war", "was", "wbp", "wo", "wuu",
- "xal", "xh", "xmf", "xog",
+ "xal", "xh", "xmf", "xnr", "xog",
  "yao", "yap", "yav", "ybb", "yi", "yo", "yrl", "yue",
  "za", "zap", "zbl", "zea", "zen", "zgh", "zh", "zu",
  "zun", "zxx", "zza",
@@ -220,12 +220,12 @@ static const char * const LANGUAGES_3[] = {
  "bak", "bal", "ban", "bar", "bas", "bax", "bbc", "bbj",
  "bel", "bej", "bem", "bew", "bez", "bfd", "bfq", "bul",
  "bgc", "bgn", "bho", "bis", "bik", "bin", "bjn", "bkm", "bla",
- "bam", "ben", "bod", "bpy", "bqi", "bre", "bra", "brh",
+ "blo", "bam", "ben", "bod", "bpy", "bqi", "bre", "bra", "brh",
  "brx", "bos", "bss", "bua", "bug", "bum", "byn", "byv",
  "cat", "cad", "car", "cay", "cch", "ccp", "che", "ceb", "cgg",
  "cha", "chb", "chg", "chk", "chm", "chn", "cho", "chp",
  "chr", "chy", "ckb", "cos", "cop", "cps", "cre", "crh",
- "ces", "csb", "chu", "chv", "cym",
+ "ces", "csb", "csw", "chu", "chv", "cym",
  "dan", "dak", "dar", "dav", "deu", "del", "den", "dgr",
  "din", "dje", "doi", "dsb", "dtp", "dua", "dum", "div",
  "dyo", "dyu", "dzo", "dzg",
@@ -252,7 +252,7 @@ static const char * const LANGUAGES_3[] = {
  "kkj", "kal", "kln", "khm", "kmb", "kan", "kor", "koi",
  "kok", "kos", "kpe", "kau", "krc", "kri", "krj", "krl",
  "kru", "kas", "ksb", "ksf", "ksh", "kur", "kum", "kut",
- "kom", "cor", "kir",
+ "kom", "cor", "kxv", "kir",
  "lat", "lad", "lag", "lah", "lam", "ltz", "lez", "lfn",
  "lug", "lim", "lij", "liv", "lkt", "lmo", "lin", "lao",
  "lol", "loz", "lrc", "lit", "ltg", "lub", "lua", "lui",
@@ -286,14 +286,14 @@ static const char * const LANGUAGES_3[] = {
  "swe", "swa", "swb", "syc", "syr", "szl",
  "tam", "tcy", "tel", "tem", "teo", "ter", "tet", "tgk",
  "tha", "tir", "tig", "tiv", "tuk", "tkl", "tkr",
- "tlh", "tli", "tly", "tmh", "tsn", "ton", "tog", "tpi",
+ "tlh", "tli", "tly", "tmh", "tsn", "ton", "tog", "tok", "tpi",
  "tur", "tru", "trv", "tso", "tsd", "tsi", "tat", "ttt",
  "tum", "tvl", "twi", "twq", "tah", "tyv", "tzm",
  "udm", "uig", "uga", "ukr", "umb", "und", "urd", "uzb",
  "vai", "ven", "vec", "vep", "vie", "vls", "vmf", "vmw",
  "vol", "vot", "vro", "vun",
  "wln", "wae", "wal", "war", "was", "wbp", "wol", "wuu",
- "xal", "xho", "xmf", "xog",
+ "xal", "xho", "xmf", "xnr", "xog",
  "yao", "yap", "yav", "ybb", "yid", "yor", "yrl", "yue",
  "zha", "zap", "zbl", "zea", "zen", "zgh", "zho", "zul",
  "zun", "zxx", "zza",

icu4c/source/common/unicode/rbbi.h

@@ -45,7 +45,6 @@ class UStack;
 
 
 #ifndef U_HIDE_DRAFT_API
-#if !UCONFIG_NO_SERVICE
 /**
  * The ExternalBreakEngine class define an abstract interface for the host environment
  * to provide a low level facility to break text for unicode text in script that the text boundary
@@ -104,7 +103,6 @@ class ExternalBreakEngine : public UObject {
  int32_t* foundBreaks, int32_t foundBreaksCapacity,
  UErrorCode& status) const = 0;
 };
-#endif /* UCONFIG_NO_SERVICE */
 #endif /* U_HIDE_DRAFT_API */
 
 
@@ -802,7 +800,6 @@ class U_COMMON_API RuleBasedBreakIterator /*final*/ : public BreakIterator {
 #endif /* U_HIDE_INTERNAL_API */
 
 #ifndef U_HIDE_DRAFT_API
-#if !UCONFIG_NO_SERVICE
  /**
  * Register a new external break engine. The external break engine will be adopted.
  * Because ICU may choose to cache break engine internally, this must
@@ -814,7 +811,6 @@ class U_COMMON_API RuleBasedBreakIterator /*final*/ : public BreakIterator {
  */
  static void U_EXPORT2 registerExternalBreakEngine(
  ExternalBreakEngine* toAdopt, UErrorCode& status);
-#endif /* UCONFIG_NO_SERVICE */
 #endif /* U_HIDE_DRAFT_API */
 
 };

icu4c/source/data/curr/LOCALE_DEPS.json

@@ -179,6 +179,9 @@
  "ff_Adlm": "root",
  "hi_Latn": "en_IN",
  "ks_Deva": "root",
+ "kxv_Deva": "root",
+ "kxv_Orya": "root",
+ "kxv_Telu": "root",
  "nb": "no",
  "nn": "no",
  "pa_Arab": "root",