1berry/qtbase
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Rework QLocale::uiLanguages() to be a bit more straigthforward

Browse Source 
Skip duplicates as a separate step, to save some complications. Other
than that, achieve the same results by post-processing the list,
instead of trying to integrate the finding of fallbacks into the main
iteration. This makes the code easier to think about and cope with
further complications as we come to them.

Change-Id: If06eae5fd1e91e88b52b3d32ccaba8cbb8e3c8af
Reviewed-by: Thiago Macieira <thiago.macieira@intel.com>
(cherry picked from commit 2c39365aad957aea7ca9c9c861665391edf7ef23)
This commit is contained in:
Edward Welbourne 2024-12-12 16:01:39 +01:00
parent e149129954
commit e7cc3ccf1d
2 changed files with 81 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

131
src/corelib/text/qlocale.cpp
View File

@ -27,6 +27,7 @@ QT_WARNING_DISABLE_GCC("-Wfree-nonheap-object") // false positive tracking
#include "qcalendar.h"
#include "qdatastream.h"
#include "qdebug.h"
#include "private/qduplicatetracker_p.h"
#include "qhashfunctions.h"
#include "qstring.h"
#include "qlocale.h"
@ -5047,24 +5048,6 @@ QStringList QLocale::uiLanguages(TagSeparator separator) const
localeIds.append(d->m_data->id());
}
// Warning: this processing is quadratic in the length of the final list.
// Hopefully that list isn't too long, though.
QStringList fallbacks;
auto gatherTruncations = [&fallbacks, cut = QLatin1Char(sep)](const QString &name) {
fallbacks.removeAll(name);
for (qsizetype at = name.indexOf(cut); at >= 0; at = name.indexOf(cut, at + 1)) {
Q_ASSERT(at > 1); // First sub-tag length is >= 2 (C is handled separately).
// We find shorter entries before fuller ones; we want the long ones
// earlier, the short ones later, but all before any entries from
// later in the localeIds list (already present in fallbacks because
// of the reverse traversal). However, that can still leave a
// shorter truncation of a long name before some truncations of
// shorter names of which the shorter one is a prefix; that's
// handled in the final appending to uiLanguages; see exclude.
fallbacks.insert(0, name.first(at));
}
};
for (qsizetype i = localeIds.size(); i-- > 0; ) {
QLocaleId id = localeIds.at(i);
qsizetype j;
@ -5094,23 +5077,17 @@ QStringList QLocale::uiLanguages(TagSeparator separator) const
const QLocaleId min = max.withLikelySubtagsRemoved();
// Include minimal version (last) unless it's what our locale is derived from:
if (const QByteArray name = min.name(sep); name != prior) {
QString sName = QString::fromLatin1(name);
uiLanguages.insert(j, sName);
gatherTruncations(sName);
} else if (!isSystem && min == id) {
if (const QByteArray name = min.name(sep); name != prior)
uiLanguages.insert(j, QString::fromLatin1(name));
else if (!isSystem && min == id)
--j; // Put more specific forms *before* minimal entry.
}
if (id.script_id) {
// Include scriptless version if likely-equivalent and distinct:
id.script_id = 0;
if (id != min && id.withLikelySubtagsAdded() == max) {
if (const QByteArray name = id.name(sep); name != prior) {
auto sName = QString::fromLatin1(name);
uiLanguages.insert(j, sName);
gatherTruncations(sName);
}
if (const QByteArray name = id.name(sep); name != prior)
uiLanguages.insert(j, QString::fromLatin1(name));
}
}
@ -5120,52 +5097,80 @@ QStringList QLocale::uiLanguages(TagSeparator separator) const
// Include version with territory if likely-equivalent and distinct:
id.territory_id = max.territory_id;
if (id != max && id.withLikelySubtagsAdded() == max) {
if (const QByteArray name = id.name(sep); name != prior) {
auto sName = QString::fromLatin1(name);
uiLanguages.insert(j, sName);
gatherTruncations(sName);
if (const QByteArray name = id.name(sep); name != prior)
uiLanguages.insert(j, QString::fromLatin1(name));
}
}
}
gatherTruncations(QString::fromLatin1(prior)); // After trimmed forms, before max.
// Include version with all likely sub-tags (first) if distinct from the rest:
if (max != min && max != id) {
if (const QByteArray name = max.name(sep); name != prior) {
auto sName = QString::fromLatin1(name);
uiLanguages.insert(j, sName);
gatherTruncations(sName);
}
if (const QByteArray name = max.name(sep); name != prior)
uiLanguages.insert(j, QString::fromLatin1(name));
}
}
auto exclude = [fallbacks, cut = QLatin1Char(sep)](QStringList::const_iterator entry,
const QStringList &uiLanguages) {
// If this entry in fallbacks reappears later, after one of which it is
// a prefix, that's not yet in uiLanguages, leave it for the later entry
// to take care of.
const QString &name = *entry;
// entry < constEnd(), so found < constEnd()
auto found = entry;
// Initial found < constEnd(), so found + 1 is at worst constEnd(), not beyond it.
while ((found = std::find(found + 1, fallbacks.constEnd(), name)) != fallbacks.constEnd()) {
// entry < returned found < constEnd()
// *found is a repeat of name
// entry < found, so found - 1 is at worst entry
const QString &prev = *(found - 1);
if (uiLanguages.contains(prev))
continue;
if (prev.size() > name.size() && prev.startsWith(name) && prev[name.size()] == cut)
return true;
// Second pass: deduplicate.
QDuplicateTracker<QString> known(uiLanguages.size());
for (qsizetype i = 0; i < uiLanguages.size();) {
if (known.hasSeen(uiLanguages.at(i)))
uiLanguages.remove(i);
else
++i;
}
return false;
// Third pass: add truncations, when not already present.
// Cubic in list length, but hopefully that's at most a dozen or so.
const QLatin1Char cut(sep);
const auto hasPrefix = [cut](QStringView name, QStringView stem) {
// A prefix only counts if it's either full or followed by a separator.
return name.startsWith(stem)
&& (name.size() == stem.size() || name.at(stem.size()) == cut);
};
for (auto it = fallbacks.constBegin(); it < fallbacks.constEnd(); ++it) {
const QString &name = *it;
if (uiLanguages.contains(name) || exclude(it, uiLanguages))
for (qsizetype i = 0; i < uiLanguages.size(); ++i) {
const QString entry = uiLanguages.at(i);
if (hasPrefix(entry, u"C") || hasPrefix(entry, u"und"))
continue;
uiLanguages.append(name);
const qsizetype stopAt = uiLanguages.size();
QString prefix = entry;
qsizetype at = 0;
while ((at = prefix.lastIndexOf(cut)) > 0) {
prefix = prefix.first(at);
// Don't test with hasSeen() as we might defer adding to later, when
// we'll need known to see the later entry's offering of this prefix
// as a new entry.
bool found = known.contains(prefix);
for (qsizetype j = i + 1; !found && j < stopAt; ++j) {
QString later = uiLanguages.at(j);
if (!later.startsWith(prefix))
continue;
// The duplicate tracker would already have spotted if equal:
Q_ASSERT(later.size() > prefix.size());
if (later.at(prefix.size()) == cut) {
// Prefix match. Shall produce the same prefix, but possibly
// after prefixes of other entries in the list. If later has
// a longer prefix not yet in the list, we want that before
// this shorter prefix, so leave this for later, otherwise,
// we include this prefix right away.
QStringView head{later};
for (qsizetype as = head.lastIndexOf(cut);
!found && as > prefix.size(); as = head.lastIndexOf(cut)) {
head = head.first(as);
bool seen = false;
for (qsizetype k = j + 1; !seen && k < uiLanguages.size(); ++k)
seen = uiLanguages.at(k) == head;
if (!seen)
found = true;
}
}
}
if (found) // Don't duplicate.
break; // any further truncations of prefix would also be found.
// Now we're committed to adding it, get it into known:
(void) known.hasSeen(prefix);
uiLanguages.append(entry.first(prefix.size()));
}
}
return uiLanguages;
}

11
tests/auto/corelib/text/qlocale/tst_qlocale.cpp
View File

@ -4094,6 +4094,8 @@ public:
return QVariant(QStringList{u"en-DK"_s, u"en-GB"_s, u"fo-FO"_s,
u"da-FO"_s, u"da-DK"_s});
}
if (m_name == u"en-NL-GB") // Netherlander at work for a GB-ish employer:
return QVariant(QStringList{u"en-NL"_s, u"nl-NL"_s, u"en-GB"_s});
if (m_name == u"de-CA") { // Imagine a 2nd generation Canadian of de-AT ancestry ...
return QVariant(QStringList{u"en-CA"_s, u"fr-CA"_s, u"de-AT"_s,
u"en-GB"_s, u"fr-FR"_s});
@ -4152,12 +4154,19 @@ void tst_QLocale::mySystemLocale_data()
QTest::addRow("no") // QTBUG-131127
<< u"no"_s << QLocale::NorwegianBokmal
<< QStringList{u"no"_s, u"nb-Latn-NO"_s, u"nb-NO"_s, u"en-US"_s, u"en-Latn-US"_s, u"en"_s,
u"nb"_s, u"nb-Latn-NO"_s, u"nb-NO"_s, u"nb-Latn"_s, u"en-Latn"_s};
u"nb"_s, u"nb-Latn"_s, u"en-Latn"_s};
QTest::addRow("en-Latn") // Android crash
<< u"en-Latn"_s << QLocale::English
<< QStringList{u"en-Latn"_s, u"en-Latn-US"_s, u"en-US"_s, u"en"_s,
u"en-NO"_s, u"en-Latn-NO"_s};
QTest::addRow("anglo-dutch-GB")
<< u"en-NL-GB"_s << QLocale::English
<< QStringList{u"en-NL"_s, u"en-Latn-NL"_s,
u"nl-NL"_s, u"nl-Latn-NL"_s, u"nl"_s,
u"en-GB"_s, u"en-Latn-GB"_s,
u"en-Latn"_s, u"en"_s, u"nl-Latn"_s};
QTest::addRow("catalan")
<< u"ca"_s << QLocale::Catalan
<< QStringList{u"ca"_s, u"ca-Latn-ES"_s, u"ca-ES"_s, u"ca-Latn"_s};