xmlreader.hpp

来自「IBM的解析xml的工具Xerces的源代码」· HPP 代码 · 共 954 行 · 第 1/3 页

inline unsigned long XMLReader::charsLeftInBuffer() const
{
    return fCharsAvail - fCharIndex;
}


// ---------------------------------------------------------------------------
//  XMLReader: Getter methods
// ---------------------------------------------------------------------------
inline XMLSSize_t XMLReader::getColumnNumber() const
{
    return fCurCol;
}

inline const XMLCh* XMLReader::getEncodingStr() const
{
    return fEncodingStr;
}

inline XMLSSize_t XMLReader::getLineNumber() const
{
    return fCurLine;
}

inline bool XMLReader::getNoMoreFlag() const
{
    return fNoMore;
}

inline const XMLCh* XMLReader::getPublicId() const
{
    return fPublicId;
}

inline unsigned int XMLReader::getReaderNum() const
{
    return fReaderNum;
}

inline XMLReader::RefFrom XMLReader::getRefFrom() const
{
    return fRefFrom;
}

inline XMLReader::Sources XMLReader::getSource() const
{
    return fSource;
}

inline const XMLCh* XMLReader::getSystemId() const
{
    return fSystemId;
}

inline bool XMLReader::getThrowAtEnd() const
{
    return fThrowAtEnd;
}

inline XMLReader::Types XMLReader::getType() const
{
    return fType;
}

// ---------------------------------------------------------------------------
//  XMLReader: Setter methods
// ---------------------------------------------------------------------------
inline void XMLReader::setReaderNum(const unsigned int newNum)
{
    fReaderNum = newNum;
}

inline void XMLReader::setThrowAtEnd(const bool newValue)
{
    fThrowAtEnd = newValue;
}

inline void XMLReader::setXMLVersion(const XMLVersion version)
{
    fXMLVersion = version;
    if (version == XMLV1_1) {
        fNEL = true;
        fgCharCharsTable = XMLChar1_1::fgCharCharsTable1_1;
    }
    else {
        fNEL = XMLChar1_0::enableNEL;
        fgCharCharsTable = XMLChar1_0::fgCharCharsTable1_0;
    }

}



// ---------------------------------------------------------------------------
//
//  XMLReader: movePlainContentChars()
//
//       Move as many plain (no special handling of any sort required) content
//       characters as possible from this reader to the supplied destination buffer.
//
//       This is THE hottest performance spot in the parser.
//
// ---------------------------------------------------------------------------
inline void XMLReader::movePlainContentChars(XMLBuffer &dest)
{
    unsigned int count = fCharIndex;

    while (fCharIndex < fCharsAvail)
    {
        if (!isPlainContentChar(fCharBuf[fCharIndex]))
            break;
        fCharIndex++;
    }

    if (count != fCharIndex)
    {
        fCurCol    += (fCharIndex - count);
        dest.append(&fCharBuf[count], fCharIndex - count);
    }
}


// ---------------------------------------------------------------------------
//  XMLReader: getNextCharIfNot() method inlined for speed
// ---------------------------------------------------------------------------
inline bool XMLReader::getNextCharIfNot(const XMLCh chNotToGet, XMLCh& chGotten)
{
    //
    //  See if there is at least a char in the buffer. Else, do the buffer
    //  reload logic.
    //
    if (fCharIndex >= fCharsAvail)
    {
        // If fNoMore is set, then we have nothing else to give
        if (fNoMore)
            return false;

        // Try to refresh
        if (!refreshCharBuffer())
            return false;
    }

    // Check the next char
    if (fCharBuf[fCharIndex] == chNotToGet)
        return false;

    // Its not the one we want to skip so bump the index
    chGotten = fCharBuf[fCharIndex++];

    // Handle end of line normalization and line/col member maintenance.
    handleEOL(chGotten, false);

    return true;
}

// ---------------------------------------------------------------------------
//  XMLReader: getNextChar() method inlined for speed
// ---------------------------------------------------------------------------
inline bool XMLReader::getNextChar(XMLCh& chGotten)
{
    //
    //  See if there is at least a char in the buffer. Else, do the buffer
    //  reload logic.
    //
    if (fCharIndex >= fCharsAvail)
    {
        // If fNoMore is set, then we have nothing else to give
        if (fNoMore)
            return false;

        // Try to refresh
        if (!refreshCharBuffer())
            return false;
    }

    chGotten = fCharBuf[fCharIndex++];

    // Handle end of line normalization and line/col member maintenance.
    handleEOL(chGotten, false);

    return true;
}


// ---------------------------------------------------------------------------
//  XMLReader: peekNextChar() method inlined for speed
// ---------------------------------------------------------------------------
inline bool XMLReader::peekNextChar(XMLCh& chGotten)
{
    //
    //  If there is something still in the buffer, get it. Else do the reload
    //  scenario.
    //
    if (fCharIndex >= fCharsAvail)
    {
        // Try to refresh the buffer
        if (!refreshCharBuffer())
        {
            chGotten = chNull;
            return false;
        }
    }

    chGotten = fCharBuf[fCharIndex];

    //
    //  Even though we are only peeking, we have to act the same as the
    //  normal char get method in regards to newline normalization, though
    //  its not as complicated as the actual character getting method's.
    //
    if ((chGotten == chCR || ((chGotten == chNEL || chGotten == chLineSeparator) && fNEL))
        && (fSource == Source_External))
        chGotten = chLF;

    return true;
}

/***
 *
 * XML1.1
 *
 * 2.11 End-of-Line Handling
 *
 *    XML parsed entities are often stored in computer files which, for editing 
 *    convenience, are organized into lines. These lines are typically separated 
 *    by some combination of the characters CARRIAGE RETURN (#xD) and LINE FEED (#xA).
 *
 *    To simplify the tasks of applications, the XML processor MUST behave as if 
 *    it normalized all line breaks in external parsed entities (including the document 
 *    entity) on input, before parsing, by translating all of the following to a single 
 *    #xA character:
 *
 *  1. the two-character sequence #xD #xA
 *  2. the two-character sequence #xD #x85
 *  3. the single character #x85
 *  4. the single character #x2028
 *  5. any #xD character that is not immediately followed by #xA or #x85.
 *
 *
 ***/
inline void XMLReader::handleEOL(XMLCh& curCh, bool inDecl)
{
    // 1. the two-character sequence #xD #xA
    // 2. the two-character sequence #xD #x85
    // 5. any #xD character that is not immediately followed by #xA or #x85.
    if (curCh == chCR)
    {
        fCurCol = 1;
        fCurLine++;

        //
        //  If not already internalized, then convert it to an
        //  LF and eat any following LF.
        //
        if (fSource == Source_External)
        {
            if ((fCharIndex < fCharsAvail) || refreshCharBuffer())
            {
                if ( fCharBuf[fCharIndex] == chLF              || 
                    ((fCharBuf[fCharIndex] == chNEL) && fNEL)  )
                {
                    fCharIndex++;
                }
            }
            curCh = chLF;
        }
    }
    else if (curCh == chLF)                   
    {
        fCurCol = 1;
        fCurLine++;
    }
    // 3. the single character #x85
    // 4. the single character #x2028
    else if (curCh == chNEL || curCh == chLineSeparator)
    {
        if (inDecl && fXMLVersion == XMLV1_1)
        {

        /***
         * XML1.1
         *
         * 2.11 End-of-Line Handling
         *  ...
         *   The characters #x85 and #x2028 cannot be reliably recognized and translated 
         *   until an entity's encoding declaration (if present) has been read. 
         *   Therefore, it is a fatal error to use them within the XML declaration or 
         *   text declaration. 
         *
         ***/
            ThrowXMLwithMemMgr1
                (
                TranscodingException
                , XMLExcepts::Reader_NelLsepinDecl
                , fSystemId
                , fMemoryManager
                );
        }

        if (fNEL && fSource == Source_External)
        {
            fCurCol = 1;
            fCurLine++;
            curCh = chLF;
        }
    }
    else
    {
        fCurCol++;
    }

    return;
}

XERCES_CPP_NAMESPACE_END

#endif