Include likely-adjusted uiLanguages for the system locale

QLocale::uiLanguages() on the system locale uses whatever the system
locale's query(QSystemLocale::UILanguages,...) returns. On Android,
this is just a list of locales. However, for non-system locales, we
also include some results of removing likely sub-tags from the locale
name, where equivalent. Thus zh-CN would also get zh and zh-Hans-CN
added to it; however, if the system locale is zh-Hans-CN, the shorter
forms are omitted. So post-process the system locale list in the same
way, albeit tweaked to avoid duplicates and rearranged so that we can
insert likely-adjusted entries between what they adjust and what
followed it.

Added QLocalePrivate::rawName() in the process, since it looks likely
to be useful in other contexts (and I needed its value): it just joins
such tags as are non-Any. This, however, uses QByteArrayList, so added
that (it's small) to the bootstrap library and qmake.

This follows up on commit 8796e3016fae1672e727e2fa4e48f671a0c667ba.

[ChangeLog][QtCore][QLocale] The system locale's UI languages list now
includes, as for that of an ordinary locale, the results of adding
likely sub-tags from each locale name, and of removing some, where
this doesn't change which locale is specified. This gives searches for
translation files a better chance of finding a suitable file.

Fixes: QTBUG-75413
Change-Id: Iaafd79aac6a0fdd5f44aed16e445e84a2267c9da
Reviewed-by: Paul Wicking <paul.wicking@qt.io>
Reviewed-by: Qt CI Bot <qt_ci_bot@qt-project.org>
Reviewed-by: Thiago Macieira <thiago.macieira@intel.com>

2 files changed, 67 insertions, 16 deletions

diff --git a/src/corelib/text/qlocale.cpp b/src/corelib/text/qlocale.cpp
index 48d57e5e6e..75a5bc802e 100644
--- a/src/corelib/text/qlocale.cpp
+++ b/src/corelib/text/qlocale.cpp
@@ -345,6 +345,23 @@ QByteArray QLocalePrivate::bcp47Name(char separator) const
     return localeId.withLikelySubtagsRemoved().name(separator);
 }
 
+/*!
+  \internal
+ */
+QByteArray QLocalePrivate::rawName(char separator) const
+{
+    QByteArrayList parts;
+    if (m_data->m_language_id != QLocale::AnyLanguage)
+        parts.append(languageCode().latin1());
+    if (m_data->m_script_id != QLocale::AnyScript)
+        parts.append(scriptCode().latin1());
+    if (m_data->m_country_id != QLocale::AnyCountry)
+        parts.append(countryCode().latin1());
+
+    return parts.join(separator);
+}
+
+
 static const QLocaleData *findLocaleDataById(const QLocaleId &lid)
 {
     QLocaleId localeId = lid.withLikelySubtagsAdded();
@@ -4367,30 +4384,63 @@ QString QLocale::formattedDataSize(qint64 bytes, int precision, DataSizeFormats
 */
 QStringList QLocale::uiLanguages() const
 {
+    QStringList uiLanguages;
+    QVector<QLocale> locales;
 #ifndef QT_NO_SYSTEMLOCALE
     if (d->m_data == systemData()) {
         QVariant res = systemLocale()->query(QSystemLocale::UILanguages, QVariant());
         if (!res.isNull()) {
-            QStringList result = res.toStringList();
-            if (!result.isEmpty())
-                return result;
+            uiLanguages = res.toStringList();
+            // ... but we need to include likely-adjusted forms of each of those, too:
+            for (const auto entry : qAsConst(uiLanguages))
+                locales.append(QLocale(entry));
         }
-    }
+    } else
 #endif
-    QLocaleId id = QLocaleId::fromIds(d->m_data->m_language_id, d->m_data->m_script_id,
-                                      d->m_data->m_country_id);
-    const QLocaleId max = id.withLikelySubtagsAdded();
-    const QLocaleId min = max.withLikelySubtagsRemoved();
+    {
+        locales.append(*this);
+    }
+    for (int i = locales.size(); i-- > 0; ) {
+        const QLocale &locale = locales.at(i);
+        int j;
+        QByteArray prior;
+        if (i < uiLanguages.size()) {
+            // Adding likely-adjusted forms to system locale's list.
+            // Name the locale is derived from:
+            const QString &name = uiLanguages.at(i);
+            prior = name.toLatin1();
+            // Don't try to likely-adjust if construction's likely-adjustments
+            // were so drastic the result doesn't match the prior name:
+            if (locale.name() != name && locale.d->rawName() != prior)
+                continue;
+            // Insert just after prior:
+            j = i + 1;
+        } else {
+            // Plain locale, not system locale; just append.
+            j = uiLanguages.size();
+        }
+        const auto data = locale.d->m_data;
+
+        QLocaleId id
+            = QLocaleId::fromIds(data->m_language_id, data->m_script_id, data->m_country_id);
+        const QLocaleId max = id.withLikelySubtagsAdded();
+        const QLocaleId min = max.withLikelySubtagsRemoved();
+        id.script_id = 0; // For re-use as script-less variant.
+
+        // Include version with all likely sub-tags (last) if distinct from the rest:
+        if (max != min && max != id && max.name() != prior)
+            uiLanguages.insert(j, QString::fromLatin1(max.name()));
+
+        // Include scriptless version if likely-equivalent and distinct:
+        if (data->m_script_id && id != min && id.name() != prior
+            && id.withLikelySubtagsAdded() == max) {
+            uiLanguages.insert(j, QString::fromLatin1(id.name()));
+        }
 
-    QStringList uiLanguages;
-    uiLanguages.append(QString::fromLatin1(min.name()));
-    if (id.script_id) {
-        id.script_id = 0;
-        if (id != min && id.withLikelySubtagsAdded() == max)
-            uiLanguages.append(QString::fromLatin1(id.name()));
+        // Include minimal version (first) unless it's what our locale is derived from:
+        if (min.name() != prior)
+            uiLanguages.insert(j, QString::fromLatin1(min.name()));
     }
-    if (max != min && max != id)
-        uiLanguages.append(QString::fromLatin1(max.name()));
     return uiLanguages;
 }
 
diff --git a/src/corelib/text/qlocale_p.h b/src/corelib/text/qlocale_p.h
index 5ebed9b385..edee3a89c7 100644
--- a/src/corelib/text/qlocale_p.h
+++ b/src/corelib/text/qlocale_p.h
@@ -359,6 +359,7 @@ public:
     quint16 countryId() const { return m_data->m_country_id; }
 
     QByteArray bcp47Name(char separator = '-') const;
+    QByteArray rawName(char separator = '-') const;
 
     inline QLatin1String languageCode() const { return languageToCode(QLocale::Language(m_data->m_language_id)); }
     inline QLatin1String scriptCode() const { return scriptToCode(QLocale::Script(m_data->m_script_id)); }