qtextcodec.cpp

doxygen(一个自动从源代码生成文档的工具)的源代码

  inserted, or NULL if there is no such QTextCodec.  Thus,
  codecForIndex(0) returns the most recently created QTextCodec.
*/
QTextCodec* QTextCodec::codecForIndex(int i)
{
    setup();
    return (uint)i >= all->count() ? 0 : all->at(i);
}


/*!
  Returns the QTextCodec which matches the
  \link QTextCodec::mibEnum() MIBenum\endlink \a mib.
*/
QTextCodec* QTextCodec::codecForMib(int mib)
{
    setup();
    QListIterator<QTextCodec> i(*all);
    QTextCodec* result;
    for ( ; (result=i); ++i ) {
        if ( result->mibEnum()==mib )
            break;
    }
    return result;
}





#ifdef _OS_WIN32_
class QWindowsLocalCodec: public QTextCodec
{
public:
    QWindowsLocalCodec();
    ~QWindowsLocalCodec();

    QString toUnicode(const char* chars, int len) const;
    QCString fromUnicode(const QString& uc, int& lenInOut ) const;

    const char* name() const;
    int mibEnum() const;

    int heuristicContentMatch(const char* chars, int len) const;
};

QWindowsLocalCodec::QWindowsLocalCodec()
{
}

QWindowsLocalCodec::~QWindowsLocalCodec()
{
}


QString QWindowsLocalCodec::toUnicode(const char* chars, int len) const
{
    if ( len == 1 && chars ) {          // Optimization; avoids allocation
        char c[2];
        c[0] = *chars;
        c[1] = 0;
        return qt_winMB2QString( c, 2 );
    }
    if ( len < 0 )
        return qt_winMB2QString( chars );
    QCString s(chars,len+1);
    return qt_winMB2QString(s);
}

QCString QWindowsLocalCodec::fromUnicode(const QString& uc, int& lenInOut ) const
{
    QCString r = qt_winQString2MB( uc, lenInOut );
    lenInOut = r.length();
    return r;
}


const char* QWindowsLocalCodec::name() const
{
    return "System";
}

int QWindowsLocalCodec::mibEnum() const
{
    return 0;
}


int QWindowsLocalCodec::heuristicContentMatch(const char* chars, int len) const
{
    // ### Not a bad default implementation?
    QString t = toUnicode(chars,len);
    int l = t.length();
    QCString mb = fromUnicode(t,l);
    int i=0;
    while ( i < len )
        if ( chars[i] == mb[i] )
            i++;
    return i;
}

#else

/* locale names mostly copied from XFree86 */
static const char * const iso8859_2locales[] = {
    "croatian", "cs", "cs_CS", "cs_CZ","cz", "cz_CZ", "czech", "hr",
    "hr_HR", "hu", "hu_HU", "hungarian", "pl", "pl_PL", "polish", "ro",
    "ro_RO", "rumanian", "serbocroatian", "sh", "sh_SP", "sh_YU", "sk",
    "sk_SK", "sl", "sl_CS", "sl_SI", "slovak", "slovene", "sr_SP", 0 };

static const char * const iso8859_3locales[] = {
    "eo", 0 };

static const char * const iso8859_4locales[] = {
    "ee", "ee_EE", "lt", "lt_LT", "lv", "lv_LV", 0 };

static const char * const iso8859_5locales[] = {
    "bg", "bg_BG", "bulgarian", "mk", "mk_MK",
    "sp", "sp_YU", 0 };

static const char * const iso8859_6locales[] = {
    "ar_AA", "ar_SA", "arabic", 0 };

static const char * const iso8859_7locales[] = {
    "el", "el_GR", "greek", 0 };

static const char * const iso8859_8locales[] = {
    "hebrew", "he", "he_IL", "iw", "iw_IL", 0 };

static const char * const iso8859_9locales[] = {
    "tr", "tr_TR", "turkish", 0 };

static const char * const iso8859_15locales[] = {
    "fr", "fi", "french", "finnish", "et", "et_EE", 0 };

static const char * const koi8_ulocales[] = {
    "uk", "uk_UA", "ru_UA", "ukrainian", 0 };

static const char * const tis_620locales[] = {
    "th", "th_TH", "thai", 0 };


static bool try_locale_list( const char * const locale[], const char * lang )
{
    int i;
    for( i=0; locale[i] && qstrcmp(locale[i], lang); i++ )
    { }
    return locale[i] != 0;
}

// For the probably_koi8_locales we have to look. the standard says
// these are 8859-5, but almsot all Russion users uses KOI8-R and
// incorrectly set $LANG to ru_RU. We'll check tolower() to see what
// tolower() thinks ru_RU means.

// If you read the history, it seems that many Russians blame ISO and
// Peristroika for the confusion.
//
// The real bug is that some programs break if the user specifies
// ru_RU.KOI8-R.

static const char * const probably_koi8_rlocales[] = {
    "ru", "ru_SU", "ru_RU", "russian", 0 };

// this means ANY of these locale aliases. if they're aliases for
// different locales, the code breaks.
static QTextCodec * ru_RU_codec = 0;

static QTextCodec * ru_RU_hack( const char * i ) {
    if ( ! ru_RU_codec ) {
        QCString origlocale = setlocale( LC_CTYPE, i );
        // unicode   koi8r   latin5   name
        // 0x044E    0xC0    0xEE     CYRILLIC SMALL LETTER YU
        // 0x042E    0xE0    0xCE     CYRILLIC CAPITAL LETTER YU
        int latin5 = tolower( 0xCE );
        int koi8r = tolower( 0xE0 );
        if ( koi8r == 0xC0 && latin5 != 0xEE ) {
            ru_RU_codec = QTextCodec::codecForName( "KOI8-R" );
        } else if ( koi8r != 0xC0 && latin5 == 0xEE ) {
            ru_RU_codec = QTextCodec::codecForName( "ISO 8859-5" );
        } else {
            // something else again... let's assume... *throws dice*
            ru_RU_codec = QTextCodec::codecForName( "KOI8-R" );
            qWarning( "QTextCodec: using KOI8-R, probe failed (%02x %02x %s)",
                      koi8r, latin5, i );
        }
        setlocale( LC_CTYPE, origlocale.data() );
    }
    return ru_RU_codec;
}

#endif

static QTextCodec * localeMapper = 0;

void qt_set_locale_codec( QTextCodec *codec )
{
    localeMapper = codec;
}

/*!  Returns a pointer to the codec most suitable for this locale. */

QTextCodec* QTextCodec::codecForLocale()
{
    if ( localeMapper )
        return localeMapper;

    setup();

#ifdef _OS_WIN32_
    localeMapper = new QWindowsLocalCodec;
#else
    // Very poorly defined and followed standards causes lots of code
    // to try to get all the cases...

    char * lang = qstrdup( getenv("LANG") );

    char * p = lang ? strchr( lang, '.' ) : 0;
    if ( !p || *p != '.' ) {
        // Some versions of setlocale return encoding, others not.
        char *ctype = qstrdup( setlocale( LC_CTYPE, 0 ) );
        // Some Linux distributions have broken locales which will return
        // "C" for LC_CTYPE
        if ( qstrcmp( ctype, "C" ) == 0 ) {
            delete [] ctype;
        } else {
            if ( lang )
                delete [] lang;
            lang = ctype;
            p = lang ? strchr( lang, '.' ) : 0;
        }
    }

    if( p && *p == '.' ) {
        // if there is an encoding and we don't know it, we return 0
        // User knows what they are doing.  Codecs will believe them.
        localeMapper = codecForName( lang );
        if ( !localeMapper ) {
            // Use or codec disagree.
            localeMapper = codecForName( p+1 );
        }
    }
    if ( !localeMapper || !(p && *p == '.') ) {
        // if there is none, we default to 8859-1
        // We could perhaps default to 8859-15.
        if ( try_locale_list( iso8859_2locales, lang ) )
            localeMapper = codecForName( "ISO 8859-2" );
        else if ( try_locale_list( iso8859_3locales, lang ) )
            localeMapper = codecForName( "ISO 8859-3" );
        else if ( try_locale_list( iso8859_4locales, lang ) )
            localeMapper = codecForName( "ISO 8859-4" );
        else if ( try_locale_list( iso8859_5locales, lang ) )
            localeMapper = codecForName( "ISO 8859-5" );
        else if ( try_locale_list( iso8859_6locales, lang ) )
            localeMapper = codecForName( "ISO 8859-6-I" );
        else if ( try_locale_list( iso8859_7locales, lang ) )
            localeMapper = codecForName( "ISO 8859-7" );
        else if ( try_locale_list( iso8859_8locales, lang ) )
            localeMapper = codecForName( "ISO 8859-8-I" );
        else if ( try_locale_list( iso8859_9locales, lang ) )
            localeMapper = codecForName( "ISO 8859-9" );
        else if ( try_locale_list( iso8859_15locales, lang ) )
            localeMapper = codecForName( "ISO 8859-15" );
        else if ( try_locale_list( tis_620locales, lang ) )
            localeMapper = codecForName( "ISO 8859-11" );
        else if ( try_locale_list( koi8_ulocales, lang ) )
            localeMapper = codecForName( "KOI8-U" );
         else if ( try_locale_list( probably_koi8_rlocales, lang ) )
            localeMapper = ru_RU_hack( lang );
        else if (!lang || !(localeMapper = codecForName(lang) ))
            localeMapper = codecForName( "ISO 8859-1" );
    }
    delete[] lang;
#endif

    return localeMapper;
}


/*!
  Searches all installed QTextCodec objects, returning the one
  which best matches given name.  Returns NULL if no codec has
  a match closeness above \a accuracy.

  \sa heuristicNameMatch()
*/
QTextCodec* QTextCodec::codecForName(const char* hint, int accuracy)
{
    setup();
    QListIterator<QTextCodec> i(*all);
    QTextCodec* result = 0;
    int best=accuracy;
    for ( QTextCodec* cursor; (cursor=i); ++i ) {
        int s = cursor->heuristicNameMatch(hint);
        if ( s > best ) {
            best = s;
            result = cursor;
        }
    }
    return result;
}


/*!
  Searches all installed QTextCodec objects, returning the one
  which most recognizes the given content.  May return 0.

  Note that this is often a poor choice, since character
  encodings often use most of the available character sequences,
  and so only by linguistic analysis could a true match be made.

  \sa heuristicContentMatch()
*/
QTextCodec* QTextCodec::codecForContent(const char* chars, int len)
{
    setup();
    QListIterator<QTextCodec> i(*all);
    QTextCodec* result = 0;
    int best=0;
    for ( QTextCodec* cursor; (cursor=i); ++i ) {
        int s = cursor->heuristicContentMatch(chars,len);
        if ( s > best ) {
            best = s;
            result = cursor;
        }
    }
    return result;
}


/*!
  \fn const char* QTextCodec::name() const
  Subclasses of QTextCodec must reimplement this function.  It returns
  the name of the encoding supported by the subclass.  When choosing
  a name for an encoding, consider these points:
  <ul>
    <li>On X11, heuristicNameMatch( const char * hint )
        is used to test if a the QTextCodec
        can convert between Unicode and the encoding of a font