KDECore
kencodingdetector.cpp
Go to the documentation of this file.
58};
107 KEncodingDetectorPrivate(QTextCodec* codec,KEncodingDetector::EncodingChoiceSource source, KEncodingDetector::AutoDetectScript script)
129 return m_source != KEncodingDetector::DefaultEncoding && m_source != KEncodingDetector::AutoDetectedEncoding;
392 if ( ptr[ i ] == 0x80 || ( ptr[ i ] >= 0x82 && ptr[ i ] <= 0x87 ) || ptr[ i ] == 0x89 || ptr[ i ] == 0x8B
654KEncodingDetector::KEncodingDetector(QTextCodec* codec, EncodingChoiceSource source, AutoDetectScript script) :
870 kWarning() << "KEncodingDetector:flush() "<< d->m_bufferForDefferedEncDetection.length()<<" bytes "<< d->m_codec->name();
877 // Check for UTF-16 or UTF-8 BOM mark at the beginning, which is a sure sign of a Unicode encoding.
1069 kDebug( 6005 ) << "KEncodingDetector: found charset in <meta>: " << str.mid(pos,endpos-pos).data();
1092 return setEncoding(automaticDetectionForArabic( (const unsigned char*) data, len ), AutoDetectedEncoding);
1095 return setEncoding(automaticDetectionForBaltic( (const unsigned char*) data, len ), AutoDetectedEncoding);
1098 return setEncoding(automaticDetectionForCentralEuropean( (const unsigned char*) data, len ), AutoDetectedEncoding);
1101 return setEncoding(automaticDetectionForCyrillic( (const unsigned char*) data, len), AutoDetectedEncoding);
1104 return setEncoding(automaticDetectionForGreek( (const unsigned char*) data, len ), AutoDetectedEncoding);
1107 return setEncoding(automaticDetectionForHebrew( (const unsigned char*) data, len ), AutoDetectedEncoding);
1110 return setEncoding(automaticDetectionForJapanese( (const unsigned char*) data, len ), AutoDetectedEncoding);
1113 return setEncoding(automaticDetectionForTurkish( (const unsigned char*) data, len ), AutoDetectedEncoding);
1116 if (setEncoding(automaticDetectionForWesternEuropean( (const unsigned char*) data, len ), AutoDetectedEncoding))
QTextCodec * codecForName(const QString &name) const
Provided for compatibility.
Definition kcharsets.cpp:696
static AutoDetectScript scriptForName(const QString &lang)
Takes lang name after it were i18n()'ed.
Definition kencodingdetector.cpp:1145
QString decodeWithBuffering(const char *data, int len)
Convenience method that uses buffering.
Definition kencodingdetector.cpp:796
bool errorsIfUtf8(const char *data, int length)
Check if we are really utf8.
Definition kencodingdetector.cpp:585
QString flush()
Convenience method to be used with decodeForHtml.
Definition kencodingdetector.cpp:861
static QString nameForScript(AutoDetectScript)
Definition kencodingdetector.cpp:1207
KEncodingDetector()
Default codec is latin1 (as html spec says), EncodingChoiceSource is default, AutoDetectScript=Semiau...
Definition kencodingdetector.cpp:650
static bool hasAutoDetectionForScript(AutoDetectScript)
Definition kencodingdetector.cpp:1173
void setAutoDetectLanguage(AutoDetectScript)
Definition kencodingdetector.cpp:664
bool decodedInvalidCharacters() const
This method checks whether invalid characters were found during a decoding operation.
Definition kencodingdetector.cpp:856
EncodingChoiceSource encodingChoiceSource() const
Definition kencodingdetector.cpp:673
bool processNull(char *data, int length)
This nice method will kill all 0 bytes (or double bytes) and remember if this was a binary or not ;)
Definition kencodingdetector.cpp:556
bool setEncoding(const char *encoding, EncodingChoiceSource type)
Definition kencodingdetector.cpp:712
AutoDetectScript autoDetectLanguage() const
Definition kencodingdetector.cpp:668
Definition kaboutdata.h:33
Definition guess_ja_p.h:86
enum Type guess_jp(const char *buf, int buflen)
Definition guess_ja.cpp:305
static QByteArray automaticDetectionForHebrew(const unsigned char *ptr, int size)
Definition kencodingdetector.cpp:402
static void skipComment(const char *&ptr, const char *pEnd)
Definition kencodingdetector.cpp:478
static QByteArray automaticDetectionForBaltic(const unsigned char *ptr, int size)
Definition kencodingdetector.cpp:148
static QByteArray automaticDetectionForCyrillic(const unsigned char *ptr, int size)
Definition kencodingdetector.cpp:193
static QByteArray automaticDetectionForGreek(const unsigned char *ptr, int size)
Definition kencodingdetector.cpp:389
static QByteArray automaticDetectionForCentralEuropean(const unsigned char *ptr, int size)
Definition kencodingdetector.cpp:161
static QByteArray automaticDetectionForJapanese(const unsigned char *ptr, int size)
Definition kencodingdetector.cpp:418
static QByteArray automaticDetectionForTurkish(const unsigned char *ptr, int size)
Definition kencodingdetector.cpp:438
static QByteArray automaticDetectionForArabic(const unsigned char *ptr, int size)
Definition kencodingdetector.cpp:134
static int findXMLEncoding(const QByteArray &str, int &encodingLength)
Definition kencodingdetector.cpp:512
static QByteArray automaticDetectionForWesternEuropean(const unsigned char *ptr, int size)
Definition kencodingdetector.cpp:449
QString i18nc(const char *ctxt, const char *text)
Returns a localized version of a string and a context.
Definition klocalizedstring.h:797
This file is part of the KDE documentation.
Documentation copyright © 1996-2024 The KDE developers.
Generated on Wed Jan 24 2024 00:00:00 by doxygen 1.10.0 written by Dimitri van Heesch, © 1997-2006
Documentation copyright © 1996-2024 The KDE developers.
Generated on Wed Jan 24 2024 00:00:00 by doxygen 1.10.0 written by Dimitri van Heesch, © 1997-2006
KDE's Doxygen guidelines are available online.