xmlscanner.cpp

来自「IBM的解析xml的工具Xerces的源代码」· C++ 代码 · 共 1,855 行 · 第 1/5 页

            bbTarget.append(nextCh);
        }
    }
    else
    {
        // No target, but make sure its terminated ok
        if (!fReaderMgr.skippedChar(chQuestion))
        {
            emitError(XMLErrs::UnterminatedPI);
            fReaderMgr.skipPastChar(chCloseAngle);
            return;
        }

        if (!fReaderMgr.skippedChar(chCloseAngle))
        {
            emitError(XMLErrs::UnterminatedPI);
            fReaderMgr.skipPastChar(chCloseAngle);
            return;
        }
    }

    // Point the target pointer at the raw data
    targetPtr = bbTarget.getRawBuffer();

    // If we have a handler, then call it
    if (fDocHandler)
    {
        fDocHandler->docPI
        (
            namePtr
            , targetPtr
       );
    }

    //mark PI is seen within the current element
    if (! fElemStack.isEmpty())
        fElemStack.setCommentOrPISeen();

}

//  Scans all the input from the start of the file to the root element.
//  There does not have to be anything in the prolog necessarily, but usually
//  there is at least an XMLDecl.
//
//  On exit from here we are either at the end of the file or about to read
//  the opening < of the root element.
void XMLScanner::scanProlog()
{
    // Get a buffer for whitespace processing
    XMLBufBid bbCData(&fBufMgr);

    //  Loop through the prolog. If there is no content, this could go all
    //  the way to the end of the file.
    try
    {
        while (true)
        {
            const XMLCh nextCh = fReaderMgr.peekNextChar();

            if (nextCh == chOpenAngle)
            {
                //  Ok, it could be the xml decl, a comment, the doc type line,
                //  or the start of the root element.
                if (checkXMLDecl(true))
                {
                    // There shall be at lease --ONE-- space in between
                    // the tag '<?xml' and the VersionInfo.
                    //
                    //  If we are not at line 1, col 6, then the decl was not
                    //  the first text, so its invalid.
                    const XMLReader* curReader = fReaderMgr.getCurrentReader();
                    if ((curReader->getLineNumber() != 1)
                    ||  (curReader->getColumnNumber() != 7))
                    {
                        emitError(XMLErrs::XMLDeclMustBeFirst);
                    }

                    scanXMLDecl(Decl_XML);
                }
                else if (fReaderMgr.skippedString(XMLUni::fgPIString))
                {
                    scanPI();
                }
                 else if (fReaderMgr.skippedString(XMLUni::fgCommentString))
                {
                    scanComment();
                }
                 else if (fReaderMgr.skippedString(XMLUni::fgDocTypeString))
                {
                    scanDocTypeDecl();

                    // if reusing grammar, this has been validated already in first scan
                    // skip for performance
                    if (fValidate && !fGrammar->getValidated()) {
                        //  validate the DTD scan so far
                        fValidator->preContentValidation(fUseCachedGrammar, true);
                    }
                }
                else
                {
                    // Assume its the start of the root element
                    return;
                }
            }
            else if (fReaderMgr.getCurrentReader()->isWhitespace(nextCh))
            {
                //  If we have a document handler then gather up the
                //  whitespace and call back. Otherwise just skip over spaces.
                if (fDocHandler)
                {
                    fReaderMgr.getSpaces(bbCData.getBuffer());
                    fDocHandler->ignorableWhitespace
                    (
                        bbCData.getRawBuffer()
                        , bbCData.getLen()
                        , false
                    );
                }
                 else
                {
                    fReaderMgr.skipPastSpaces();
                }
            }
             else
            {
                emitError(XMLErrs::InvalidDocumentStructure);

                // Watch for end of file and break out
                if (!nextCh)
                    break;
                else
                    fReaderMgr.skipPastChar(chCloseAngle);
            }

        }
    }
    catch(const EndOfEntityException&)
    {
        //  We should never get an end of entity here. They should only
        //  occur within the doc type scanning method, and not leak out to
        //  here.
        emitError
        (
            XMLErrs::UnexpectedEOE
            , "in prolog"
        );
    }
}


//  Scans the <?xml .... ?> line. This stuff is all sequential so we don't
//  do any state machine loop here. We just bull straight through it. It ends
//  past the closing bracket. If there is a document handler, then its called
//  on the XMLDecl callback.
//
//  On entry, the <?xml has been scanned, and we pick it up from there.
//
//  NOTE: In order to provide good recovery from bad XML here, we try to be
//  very flexible. No matter what order the stuff is in, we'll keep going
//  though we'll issue errors.
//
//  The parameter tells us which type of decl we should expect, Text or XML.
//    [23] XMLDecl ::= '<?xml' VersionInfo EncodingDecl? SDDecl? S? '?>'
//    [77] TextDecl::= '<?xml' VersionInfo? EncodingDecl S? '?>'
void XMLScanner::scanXMLDecl(const DeclTypes type)
{
    // Get us some buffers to use
    XMLBufBid bbVersion(&fBufMgr);
    XMLBufBid bbEncoding(&fBufMgr);
    XMLBufBid bbStand(&fBufMgr);
    XMLBufBid bbDummy(&fBufMgr);
    XMLBufBid bbName(&fBufMgr);

    //  We use this little enum and array to keep up with what we found
    //  and what order we found them in. This lets us get them free form
    //  without too much overhead, but still know that they were in the
    //  wrong order.
    enum Strings
    {
        VersionString
        , EncodingString
        , StandaloneString
        , UnknownString

        , StringCount
    };
    int flags[StringCount] = { -1, -1, -1, -1 };

    //  Also set up a list of buffers in the right order so that we know
    //  where to put stuff.
    XMLBuffer* buffers[StringCount] ;
    buffers[0] = &bbVersion.getBuffer();
    buffers[1] = &bbEncoding.getBuffer();
    buffers[2] = &bbStand.getBuffer();
    buffers[3] = &bbDummy.getBuffer();

    int curCount = 0;
    Strings curString;
    XMLBuffer& nameBuf = bbName.getBuffer();
    while (true)
    {
        // Skip any spaces
        const unsigned int spaceCount = fReaderMgr.skipPastSpaces(true);

        // If we are looking at a question mark, then break out
        if (fReaderMgr.lookingAtChar(chQuestion))
            break;

        // If this is not the first string, then we require the spaces
        if (!spaceCount && curCount)
            emitError(XMLErrs::ExpectedWhitespace);

        //  Get characters up to the next whitespace or equal's sign.
        if (!scanUpToWSOr(nameBuf, chEqual))
            emitError(XMLErrs::ExpectedDeclString);

        // See if it matches any of our expected strings
        if (XMLString::equals(nameBuf.getRawBuffer(), XMLUni::fgVersionString))
            curString = VersionString;
        else if (XMLString::equals(nameBuf.getRawBuffer(), XMLUni::fgEncodingString))
            curString = EncodingString;
        else if (XMLString::equals(nameBuf.getRawBuffer(), XMLUni::fgStandaloneString))
            curString = StandaloneString;
        else
            curString = UnknownString;

        //  If its an unknown string, then give that error. Else check to
        //  see if this one has been done already and give that error.
        if (curString == UnknownString)
            emitError(XMLErrs::ExpectedDeclString, nameBuf.getRawBuffer());
        else if (flags[curString] != -1)
            emitError(XMLErrs::DeclStringRep, nameBuf.getRawBuffer());
        else if (flags[curString] == -1)
            flags[curString] = ++curCount;

        //  Scan for an equal's sign. If we don't find it, issue an error
        //  but keep trying to go on.
        if (!scanEq(true))
            emitError(XMLErrs::ExpectedEqSign);

        //  Get a quote string into the buffer for the string that we are
        //  currently working on.
        if (!getQuotedString(*buffers[curString]))
        {
            emitError(XMLErrs::ExpectedQuotedString);
            fReaderMgr.skipPastChar(chCloseAngle);
            return;
        }

        // And validate the value according which one it was
        const XMLCh* rawValue = buffers[curString]->getRawBuffer();
        if (curString == VersionString)
        {
            if (XMLString::equals(rawValue, XMLUni::fgVersion1_1)) {
                if (type == Decl_XML) {
                	fXMLVersion = XMLReader::XMLV1_1;
                    fReaderMgr.setXMLVersion(XMLReader::XMLV1_1);
                }
                else {
            	    if (fXMLVersion != XMLReader::XMLV1_1)
            	        emitError(XMLErrs::UnsupportedXMLVersion, rawValue);                
            	}
            }
            else if (XMLString::equals(rawValue, XMLUni::fgVersion1_0)) {
                if (type == Decl_XML) {
                	fXMLVersion = XMLReader::XMLV1_0;
                    fReaderMgr.setXMLVersion(XMLReader::XMLV1_0);                    
                }
            }
            else
                emitError(XMLErrs::UnsupportedXMLVersion, rawValue);
        }
         else if (curString == EncodingString)
        {
            if (!XMLString::isValidEncName(rawValue))
                emitError(XMLErrs::BadXMLEncoding, rawValue);
        }
         else if (curString == StandaloneString)
        {
            if (XMLString::equals(rawValue, XMLUni::fgYesString))
                fStandalone = true;
            else if (XMLString::equals(rawValue, XMLUni::fgNoString))
                fStandalone = false;
            else
            {
                emitError(XMLErrs::BadStandalone);
                if (!XMLString::compareIString(rawValue, XMLUni::fgYesString))
                    fStandalone = true;
                else if (!XMLString::compareIString(rawValue, XMLUni::fgNoString))
                    fStandalone = false;
            }
        }
    }

    //  Make sure that the strings present are in order. We don't care about
    //  which ones are present at this point, just that any there are in the
    //  right order.
    int curTop = 0;
    for (int index = VersionString; index < StandaloneString; index++)
    {
        if (flags[index] != -1)
        {
            if (flags[index] !=  curTop + 1)
            {
                emitError(XMLErrs::DeclStringsInWrongOrder);
                break;
            }
            curTop = flags[index];
        }
    }

    //  If its an XML decl, the version must be present.
    //  If its a Text decl, then encoding must be present AND standalone must not be present.
    if ((type == Decl_XML) && (flags[VersionString] == -1))
        emitError(XMLErrs::XMLVersionRequired);
    else if (type == Decl_Text) {
        if (flags[StandaloneString] != -1)
            emitError(XMLErrs::StandaloneNotLegal);
        if (flags[EncodingString] == -1)
            emitError(XMLErrs::EncodingRequired);
    }

    if (!fReaderMgr.skippedChar(chQuestion))
    {
        emitError(XMLErrs::UnterminatedXMLDecl);
        fReaderMgr.skipPastChar(chCloseAngle);
    }
     else if (!fReaderMgr.skippedChar(chCloseAngle))
    {
        emitError(XMLErrs::UnterminatedXMLDecl);
        fReaderMgr.skipPastChar(chCloseAngle);
    }

    //  Do this before we possibly update the reader with the
    //  actual encoding string. Otherwise, we will pass the wrong thing
    //  for the last parameter!
    const XMLCh* actualEnc = fReaderMgr.getCurrentEncodingStr();

    //  Ok, we've now seen the real encoding string, if there was one, so
    //  lets call back on the current reader and tell it what the real
    //  encoding string was. If it fails, that's because it represents some
    //  sort of contradiction with the autosensed format, and it keeps the
    //  original encoding.
    //
    //  NOTE: This can fail for a number of reasons, such as a bogus encoding
    //  name or because its in flagrant contradiction of the auto-sensed
    //  format.
    if (flags[EncodingString] != -1)
    {
        if (!fReaderMgr.getCurrentReader()->setEncoding(bbEncoding.getRawBuffer()))
            emitError(XMLErrs::ContradictoryEncoding, bbEncoding.getRawBuffer());
        else
            actualEnc = bbEncoding.getRawBuffer();
    }

    //  If we have a document handler then call the XML Decl callback.
    if (type == Decl_XML)
    {
        if (fDocHandler)
            fDocHandler->XMLDecl
            (
                bbVersion.getRawBuffer()
                , bbEncoding.getRawBuffer()
                , bbStand.getRawBuffer()
                , actualEnc
            );
    }
    else if (type == Decl_Text)
    {
        if (fDocTypeHandler)
            fDocTypeHandler->TextDecl