organicmaps/icu
13
Fork 0
mirror of https://github.com/unicode-org/icu.git synced 2025-04-04 21:15:35 +00:00
Code Issues 1 Projects Releases Wiki Activity Actions 8

ICU-22520 Replace use of ulocimp_forLanguageTag() in uloc_getVariant().

Browse source 
Originally added by commit 24055f8585
for ICU-7882, converting any language tag with a BCP-47 extension into a
legacy Unicode locale ID was a simple way to make the existing code keep
working unchanged also with BCP-47 extensions.

But the only thing that uloc_getVariant() needs is being able to find
out where variants end and extensions begin, for which converting the
entire language tag is unnecessary, it's much more straightforward to
instead just check for the -t-, -u- or -x- marker that indicates the
start of a BCP-47 extension.
This commit is contained in:
Fredrik Roubert 2024-02-02 23:48:14 +01:00 • committed by Fredrik Roubert
parent 6fa113eaa8
commit 678d5c1273
1 changed files with 27 additions and 24 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

51
icu4c/source/common/uloc.cpp
View file

@ -1103,6 +1103,18 @@ ulocimp_setKeywordValue(const char* keywords,
*/
#define _isTerminator(a) ((a==0)||(a=='.')||(a=='@'))
namespace {
inline bool _isBCP47Extension(const char* p) {
return p[0] == '-' &&
(p[1] == 't' || p[1] == 'T' ||
p[1] == 'u' || p[1] == 'U' ||
p[1] == 'x' || p[1] == 'X') &&
p[2] == '-';
}
} // namespace
/**
* Lookup 'key' in the array 'list'. The array 'list' should contain
* a nullptr entry, followed by more entries, and a second nullptr entry.
@ -1820,61 +1832,52 @@ uloc_getVariant(const char* localeID,
int32_t variantCapacity,
UErrorCode* err)
{
CharString tempBuffer;
const char* tmpLocaleID;
int32_t i=0;
if(err==nullptr || U_FAILURE(*err)) {
return 0;
}
if (_hasBCP47Extension(localeID)) {
CharStringByteSink sink(&tempBuffer);
ulocimp_forLanguageTag(localeID, -1, sink, nullptr, err);
tmpLocaleID = U_SUCCESS(*err) && !tempBuffer.isEmpty() ? tempBuffer.data() : localeID;
} else {
if (localeID==nullptr) {
localeID=uloc_getDefault();
}
tmpLocaleID=localeID;
if (localeID == nullptr) {
localeID = uloc_getDefault();
}
/* Skip the language */
ulocimp_getLanguage(tmpLocaleID, &tmpLocaleID, *err);
ulocimp_getLanguage(localeID, &localeID, *err);
if (U_FAILURE(*err)) {
return 0;
}
if(_isIDSeparator(*tmpLocaleID)) {
if (_isIDSeparator(*localeID)) {
const char *scriptID;
/* Skip the script if available */
ulocimp_getScript(tmpLocaleID+1, &scriptID, *err);
ulocimp_getScript(localeID+1, &scriptID, *err);
if (U_FAILURE(*err)) {
return 0;
}
if(scriptID != tmpLocaleID+1) {
if (scriptID != localeID+1) {
/* Found optional script */
tmpLocaleID = scriptID;
localeID = scriptID;
}
/* Skip the Country */
if (_isIDSeparator(*tmpLocaleID)) {
if (_isIDSeparator(*localeID)) {
const char *cntryID;
ulocimp_getCountry(tmpLocaleID+1, &cntryID, *err);
ulocimp_getCountry(localeID+1, &cntryID, *err);
if (U_FAILURE(*err)) {
return 0;
}
if (cntryID != tmpLocaleID+1) {
if (cntryID != localeID+1) {
/* Found optional country */
tmpLocaleID = cntryID;
localeID = cntryID;
}
if(_isIDSeparator(*tmpLocaleID)) {
if (_isIDSeparator(*localeID) && !_isBCP47Extension(localeID)) {
/* If there was no country ID, skip a possible extra IDSeparator */
if (tmpLocaleID != cntryID && _isIDSeparator(tmpLocaleID[1])) {
tmpLocaleID++;
if (localeID != cntryID && _isIDSeparator(localeID[1])) {
localeID++;
}
CheckedArrayByteSink sink(variant, variantCapacity);
_getVariant(tmpLocaleID+1, *tmpLocaleID, sink, false);
_getVariant(localeID+1, *localeID, sink, false);
i = sink.NumberOfBytesAppended();