QFileSystemIterator/Unix: use QStringDecoder

The end result is a QFileInfo constructed from the QFileSystemEntry;
QFileSystemEntry's API will at some point convert the NativePath (QBA on
Unix) to a QString, e.g. when it calls findLastSeparator().

So instead of converting the parent dir path from Utf8 to Utf16 multiple
times, store the dir path as a QString once in the constructor.

Use QStringDecoder to convert the dirent->d_name to Utf16 and check the
decoder's hasError(); which as Thiago pointed out, is more efficient
than using isValidUtf8(), throwing away the results, then converting to
unicode anyway later on in QDirIteratorPrivate::advance().

(Ironically) `QFileSystemEntry::NativePath nativePath` is still used on
Windows.

Change-Id: Icd2b130103640b502862d210d64926b99c499a01
Reviewed-by: Thiago Macieira <thiago.macieira@intel.com>

src/corelib/io/qfilesystemiterator_p.h

@@ -26,6 +26,10 @@
 #include <QtCore/private/qfilesystementry_p.h>
 #include <QtCore/private/qfilesystemmetadata_p.h>
 
+#if !defined(Q_OS_WIN)
+#include <private/qstringconverter_p.h>
+#endif
+
 #include <memory>
 
 QT_BEGIN_NAMESPACE
@@ -39,11 +43,11 @@ public:
     bool advance(QFileSystemEntry &fileEntry, QFileSystemMetaData &metaData);
 
 private:
-    QFileSystemEntry::NativePath nativePath;
+    QString dirPath;
 
     // Platform-specific data
 #if defined(Q_OS_WIN)
-    QString dirPath;
+    QFileSystemEntry::NativePath nativePath;
     HANDLE findFileHandle;
     QStringList uncShares;
     bool uncFallback;
@@ -58,6 +62,7 @@ private:
 
     QT_DIRENT *dirEntry = nullptr;
     int lastError = 0;
+    QStringDecoder toUtf16;
 #endif
 
     Q_DISABLE_COPY_MOVE(QFileSystemIterator)

src/corelib/io/qfilesystemiterator_unix.cpp

@@ -4,10 +4,10 @@
 #include "qplatformdefs.h"
 #include "qfilesystemiterator_p.h"
 
-#include <private/qstringconverter_p.h>
-
 #ifndef QT_NO_FILESYSTEMITERATOR
 
+#include <qvarlengtharray.h>
+
 #include <memory>
 
 #include <stdlib.h>
@@ -15,20 +15,13 @@
 
 QT_BEGIN_NAMESPACE
 
-static bool checkNameDecodable(const char *d_name, qsizetype len)
-{
-    // This function is called in a loop from advance() below, but the loop is
-    // usually run only once.
-
-    return QUtf8::isValidUtf8(QByteArrayView(d_name, len)).isValidUtf8;
-}
-
 /*
     Native filesystem iterator, which uses ::opendir()/readdir()/dirent from the system
     libraries to iterate over the directory represented by \a entry.
 */
 QFileSystemIterator::QFileSystemIterator(const QFileSystemEntry &entry, QDir::Filters filters)
-    : nativePath(entry.nativeFilePath())
+    : dirPath(entry.filePath()),
+      toUtf16(QStringDecoder::Utf8)
 {
     Q_UNUSED(filters);
 
@@ -36,8 +29,8 @@ QFileSystemIterator::QFileSystemIterator(const QFileSystemEntry &entry, QDir::Fi
     if (!dir) {
         lastError = errno;
     } else {
-        if (!nativePath.endsWith('/'))
-            nativePath.append('/');
+        if (!dirPath.endsWith(u'/'))
+            dirPath.append(u'/');
     }
 }
 
@@ -58,9 +51,18 @@ bool QFileSystemIterator::advance(QFileSystemEntry &fileEntry, QFileSystemMetaDa
         dirEntry = QT_READDIR(dir.get());
 
         if (dirEntry) {
-            qsizetype len = strlen(dirEntry->d_name);
-            if (checkNameDecodable(dirEntry->d_name, len)) {
-                fileEntry = QFileSystemEntry(nativePath + QByteArray(dirEntry->d_name, len), QFileSystemEntry::FromNativePath());
+            // POSIX allows readdir() to return a file name in struct dirent that
+            // extends past the end of the d_name array (it's a char[1] array on QNX, for
+            // example). Therefore, we *must* call strlen() on it to get the actual length
+            // of the file name. See:
+            // https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/dirent.h.html#tag_13_07_05
+            QByteArrayView name(dirEntry->d_name, strlen(dirEntry->d_name));
+            // name.size() is sufficient here, see QUtf8::convertToUnicode() for details
+            QVarLengthArray<char16_t> buffer(name.size());
+            auto *end = toUtf16.appendToBuffer(buffer.data(), name);
+            buffer.resize(end - buffer.constData());
+            if (!toUtf16.hasError()) {
+                fileEntry = {dirPath + QStringView(buffer), QFileSystemEntry::FromInternalPath()};
                 metaData.fillFromDirEnt(*dirEntry);
                 return true;
             } else {

src/corelib/io/qfilesystemiterator_win.cpp

@@ -15,8 +15,8 @@ using namespace Qt::StringLiterals;
 bool done = true;
 
 QFileSystemIterator::QFileSystemIterator(const QFileSystemEntry &entry, QDir::Filters filters)
-    : nativePath(entry.nativeFilePath())
-    , dirPath(entry.filePath())
+    : dirPath(entry.filePath())
+    , nativePath(entry.nativeFilePath())
     , findFileHandle(INVALID_HANDLE_VALUE)
     , uncFallback(false)
     , uncShareIndex(0)