diff --git a/src/xml/sax/qxml.cpp b/src/xml/sax/qxml.cpp
index 1898f4fbe8a..d1af7e42daf 100644
--- a/src/xml/sax/qxml.cpp
+++ b/src/xml/sax/qxml.cpp
@@ -244,9 +244,7 @@ public:
int pos;
int length;
bool nextReturnedEndOfData;
-#if QT_CONFIG(textcodec)
- QTextDecoder *encMapper;
-#endif
+ QStringDecoder toUnicode;
QByteArray encodingDeclBytes;
QString encodingDeclChars;
@@ -1090,9 +1088,6 @@ void QXmlInputSource::init()
d->inputStream = nullptr;
setData(QString());
-#if QT_CONFIG(textcodec)
- d->encMapper = nullptr;
-#endif
d->nextReturnedEndOfData = true; // first call to next() will call fetchData()
d->encodingDeclBytes.clear();
@@ -1136,9 +1131,6 @@ QXmlInputSource::QXmlInputSource(QIODevice *dev)
QXmlInputSource::~QXmlInputSource()
{
// ### close the input device.
-#if QT_CONFIG(textcodec)
- delete d->encMapper;
-#endif
delete d;
}
@@ -1356,77 +1348,47 @@ QString QXmlInputSource::fromRawData(const QByteArray &data, bool beginning)
{
if (data.size() == 0)
return QString();
- if (beginning) {
- delete d->encMapper;
- d->encMapper = nullptr;
- }
- int mib = 106; // UTF-8
+ if (beginning)
+ d->toUnicode = QStringDecoder();
// This is the initial UTF codec we will read the encoding declaration with
- if (d->encMapper == nullptr) {
+ if (!d->toUnicode.isValid()) {
d->encodingDeclBytes.clear();
d->encodingDeclChars.clear();
d->lookingForEncodingDecl = true;
- // look for byte order mark and read the first 5 characters
- if (data.size() >= 4) {
- uchar ch1 = data.at(0);
- uchar ch2 = data.at(1);
- uchar ch3 = data.at(2);
- uchar ch4 = data.at(3);
-
- if ((ch1 == 0 && ch2 == 0 && ch3 == 0xfe && ch4 == 0xff) ||
- (ch1 == 0xff && ch2 == 0xfe && ch3 == 0 && ch4 == 0))
- mib = 1017; // UTF-32 with byte order mark
- else if (ch1 == 0x3c && ch2 == 0x00 && ch3 == 0x00 && ch4 == 0x00)
- mib = 1019; // UTF-32LE
- else if (ch1 == 0x00 && ch2 == 0x00 && ch3 == 0x00 && ch4 == 0x3c)
- mib = 1018; // UTF-32BE
+ auto encoding = QStringConverter::encodingForData(data.constData(), data.size(), char16_t('<'));
+ if (encoding) {
+ d->lookingForEncodingDecl = false;
+ d->toUnicode = QStringDecoder(*encoding);
+ } else {
+ d->toUnicode = QStringDecoder(QStringDecoder::Utf8);
}
- if (mib == 106 && data.size() >= 2) {
- uchar ch1 = data.at(0);
- uchar ch2 = data.at(1);
-
- if ((ch1 == 0xfe && ch2 == 0xff) || (ch1 == 0xff && ch2 == 0xfe))
- mib = 1015; // UTF-16 with byte order mark
- else if (ch1 == 0x3c && ch2 == 0x00)
- mib = 1014; // UTF-16LE
- else if (ch1 == 0x00 && ch2 == 0x3c)
- mib = 1013; // UTF-16BE
- }
-
- QTextCodec *codec = QTextCodec::codecForMib(mib);
- Q_ASSERT(codec);
-
- d->encMapper = codec->makeDecoder();
}
- QString input = d->encMapper->toUnicode(data.constData(), data.size());
+ QString input = d->toUnicode(data.constData(), data.size());
if (d->lookingForEncodingDecl) {
d->encodingDeclChars += input;
bool needMoreText;
- QString encoding = extractEncodingDecl(d->encodingDeclChars, &needMoreText);
+ QByteArray encoding = extractEncodingDecl(d->encodingDeclChars, &needMoreText).toLatin1();
if (!encoding.isEmpty()) {
- if (QTextCodec *codec = QTextCodec::codecForName(std::move(encoding).toLatin1())) {
- /* If the encoding is the same, we don't have to do toUnicode() all over again. */
- if(codec->mibEnum() != mib) {
- delete d->encMapper;
- d->encMapper = codec->makeDecoder();
+ auto e = QStringDecoder::encodingForData(encoding.constData(), encoding.size());
+ if (e && *e != QStringDecoder::Utf8) {
+ d->toUnicode = QStringDecoder(*e);
- /* The variable input can potentially be large, so we deallocate
- * it before calling toUnicode() in order to avoid having two
- * large QStrings in memory simultaneously. */
- input.clear();
+ /* The variable input can potentially be large, so we deallocate
+ * it before calling toUnicode() in order to avoid having two
+ * large QStrings in memory simultaneously. */
+ input.clear();
- // prime the decoder with the data so far
- d->encMapper->toUnicode(d->encodingDeclBytes.constData(), d->encodingDeclBytes.size());
- // now feed it the new data
- input = d->encMapper->toUnicode(data.constData(), data.size());
- }
+ // prime the decoder with the data so far
+ d->toUnicode(d->encodingDeclBytes.constData(), d->encodingDeclBytes.size());
+ // now feed it the new data
+ input = d->toUnicode(data.constData(), data.size());
}
}
diff --git a/tests/auto/xml/sax/qxmlsimplereader/encodings/doc_euc-jp.xml b/tests/auto/xml/sax/qxmlsimplereader/encodings/doc_euc-jp.xml
deleted file mode 100644
index 887ab5ec30d..00000000000
--- a/tests/auto/xml/sax/qxmlsimplereader/encodings/doc_euc-jp.xml
+++ /dev/null
@@ -1,78 +0,0 @@
-
-
-
-<週報>
- <年月週>
- <年度>1997
- <月度>1
- <週>1
-
-
- <氏名>
- <氏>山田
- <名>太郎
-
-
- <業務報告リスト>
- <業務報告>
- <業務名>XMLエディターの作成
- <業務コード>X3355-23
- <工数管理>
- <見積もり工数>1600
- <実績工数>320
- <当月見積もり工数>160
- <当月実績工数>24
-
- <予定項目リスト>
- <予定項目>
- XMLエディターの基本仕様の作成
-
-
- <実施事項リスト>
- <実施事項>
- XMLエディターの基本仕様の作成
-
- <実施事項>
- 競合他社製品の機能調査
-
-
- <上長への要請事項リスト>
- <上長への要請事項>
- 特になし
-
-
- <問題点対策>
- XMLとは何かわからない。
-
-
-
- <業務報告>
- <業務名>検索エンジンの開発
- <業務コード>S8821-76
- <工数管理>
- <見積もり工数>120
- <実績工数>6
- <当月見積もり工数>32
- <当月実績工数>2
-
- <予定項目リスト>
- <予定項目>
- gooの機能を調べてみる
-
-
- <実施事項リスト>
- <実施事項>
- 更に、どういう検索エンジンがあるか調査する
-
-
- <上長への要請事項リスト>
- <上長への要請事項>
- 開発をするのはめんどうなので、Yahoo!を買収して下さい。
-
-
- <問題点対策>
- 検索エンジンで車を走らせることができない。（要調査）
-
-
-
-
diff --git a/tests/auto/xml/sax/qxmlsimplereader/encodings/doc_iso-2022-jp.xml.ref b/tests/auto/xml/sax/qxmlsimplereader/encodings/doc_iso-2022-jp.xml.ref
deleted file mode 100644
index 28dcdd98c4f..00000000000
--- a/tests/auto/xml/sax/qxmlsimplereader/encodings/doc_iso-2022-jp.xml.ref
+++ /dev/null
@@ -1,4 +0,0 @@
-setDocumentLocator(locator={columnNumber=1, lineNumber=1})
-startDocument()
- processingInstruction(target="xml", data="version='1.0' encoding='iso-2022-jp'")
- fatalError(exception={columnNumber=11, lineNumber=2, publicId="", systemId="", message="letter is expected"})