readermgr.cpp

来自「IBM的解析xml的工具Xerces的源代码」· C++ 代码 · 共 1,112 行 · 第 1/3 页

/*
 * Copyright 1999-2000,2004 The Apache Software Foundation.
 * 
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 * 
 *      http://www.apache.org/licenses/LICENSE-2.0
 * 
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

/*
 * $Id: ReaderMgr.cpp,v 1.28 2004/09/08 13:56:13 peiyongz Exp $
 */

// ---------------------------------------------------------------------------
//  Includes
// ---------------------------------------------------------------------------
#include <xercesc/util/BinMemInputStream.hpp>
#include <xercesc/util/Janitor.hpp>
#include <xercesc/util/PlatformUtils.hpp>
#include <xercesc/util/RuntimeException.hpp>
#include <xercesc/util/UnexpectedEOFException.hpp>
#include <xercesc/util/XMLURL.hpp>
#include <xercesc/util/XMLUniDefs.hpp>
#include <xercesc/util/XMLUni.hpp>
#include <xercesc/util/XMLUri.hpp>
#include <xercesc/sax/InputSource.hpp>
#include <xercesc/framework/LocalFileInputSource.hpp>
#include <xercesc/framework/URLInputSource.hpp>
#include <xercesc/framework/XMLBuffer.hpp>
#include <xercesc/framework/XMLDocumentHandler.hpp>
#include <xercesc/framework/XMLEntityDecl.hpp>
#include <xercesc/framework/XMLEntityHandler.hpp>
#include <xercesc/internal/EndOfEntityException.hpp>
#include <xercesc/internal/ReaderMgr.hpp>
#include <xercesc/util/OutOfMemoryException.hpp>
#include <xercesc/util/XMLResourceIdentifier.hpp>

XERCES_CPP_NAMESPACE_BEGIN

// ---------------------------------------------------------------------------
//  ReaderMgr: Constructors and Destructor
// ---------------------------------------------------------------------------
ReaderMgr::ReaderMgr(MemoryManager* const manager) :

    fCurEntity(0)
    , fCurReader(0)
    , fEntityHandler(0)
    , fEntityStack(0)
    , fNextReaderNum(1)
    , fReaderStack(0)
    , fThrowEOE(false)
    , fXMLVersion(XMLReader::XMLV1_0)
    , fStandardUriConformant(false)
    , fMemoryManager(manager)
{
}

ReaderMgr::~ReaderMgr()
{
    //
    //  Clean up the reader and entity stacks. Note that we don't own the
    //  entities, so we don't delete the current entity (and the entity stack
    //  does not own its elements either, so deleting it will not delete the
    //  entities it still references!)
    //
    delete fCurReader;
    delete fReaderStack;
    delete fEntityStack;
}


// ---------------------------------------------------------------------------
//  ReaderMgr: Getter methods
// ---------------------------------------------------------------------------
bool ReaderMgr::isEmpty() const
{
    return fReaderStack->empty();
}


// ---------------------------------------------------------------------------
//  ReaderMgr: Scanning APIs
// ---------------------------------------------------------------------------
XMLCh ReaderMgr::getNextChar()
{
    XMLCh chRet;
    if (fCurReader->getNextChar(chRet))
        return chRet;

    //
    //  Didn't get anything back so this reader is hosed. So lets move to
    //  the next reader on the stack. If this fails, it will be because
    //  its the end of the original file, and we just return zero.
    //
    //  If its the end of an entity and fThrowEOE is set, it will throw out
    //  of here. Otherwise, it will take us down to the next reader and
    //  we'll have more chars.
    //
    if (!popReader())
        return XMLCh(0);

    // Else try again and return the new character
    fCurReader->getNextChar(chRet);
    return chRet;
}


void ReaderMgr::getSpaces(XMLBuffer& toFill)
{
    // Reset the buffer before we start
    toFill.reset();

    while (true)
    {
        //
        //  Get all the spaces from the current reader. If it returns true,
        //  it hit a non-space and we are done. Else we have to pop a reader
        //  and keep going.
        //
        if (fCurReader->getSpaces(toFill))
            break;

        // We wore that one out, so lets pop a reader and try again
        if (!popReader())
            break;
    }
}


void ReaderMgr::getUpToCharOrWS(XMLBuffer& toFill, const XMLCh toCheck)
{
    // Reset the target buffer before we start
    toFill.reset();

    //
    //  Ok, enter a loop where we ask the current reader to get chars until
    //  it meets the criteria. It returns false if it came back due to eating
    //  up all of its data. Else it returned because something matched, and
    //  we are done.
    //
    while (true)
    {
        if (fCurReader->getUpToCharOrWS(toFill, toCheck))
            break;

        // We ate that one up, lets try to pop another. If not, break out
        if (!popReader())
            break;
    }
}


XMLCh ReaderMgr::peekNextChar()
{
    XMLCh chRet;
    if (fCurReader->peekNextChar(chRet))
        return chRet;

    //
    //  Didn't get anything back so this reader is hosed. So lets move to
    //  the next reader on the stack. If this fails, it will be because
    //  its the end of the original file, and we just return zero.
    //
    if (!popReader())
        return XMLCh(0);

    // Else peek again and return the character
    fCurReader->peekNextChar(chRet);
    return chRet;
}


bool ReaderMgr::skippedChar(const XMLCh toCheck)
{
    while (true)
    {
        // If we get it, then just return true now
        if (fCurReader->skippedChar(toCheck))
            return true;

        //
        //  Check to see if we hit end of input on this reader. If so, then
        //  lets pop and try again. Else, we failed. If we cannot pop another
        //  then we failed.
        //
        if (!fCurReader->getNoMoreFlag())
            break;

        if (!popReader())
            break;
    }
    return false;
}


bool ReaderMgr::skippedSpace()
{
    while (true)
    {
        // If we get it, then just return true now
        if (fCurReader->skippedSpace())
            return true;

        //
        //  Check to see if we hit end of input on this reader. If so, then
        //  lets pop and try again. Else, we failed. If we cannot pop another
        //  then we failed.
        //
        if (!fCurReader->getNoMoreFlag())
            break;

        if (!popReader())
            break;
    }
    return false;
}


bool ReaderMgr::skipIfQuote(XMLCh& chGotten)
{
    while (true)
    {
        // If we get it, then just return true now
        if (fCurReader->skipIfQuote(chGotten))
            return true;

        //
        //  Check to see if we hit end of input on this reader. If so, then
        //  lets pop and try again. Else, we failed. If we cannot pop another
        //  then we failed.
        //
        if (!fCurReader->getNoMoreFlag())
            break;

        if (!popReader())
            break;
    }
    return false;
}


bool ReaderMgr::skipPastSpaces(bool inDecl)
{
    bool skippedSomething = false;
    bool tmpFlag;
    while (true)
    {
        //
        //  Skip all the spaces in the current reader. If it returned because
        //  it hit a non-space, break out. Else we have to pop another entity
        //  and keep going.
        //
        if (fCurReader->skipSpaces(tmpFlag, inDecl))
            break;

        if (tmpFlag)
            skippedSomething = true;

        // Try to pop another enitity. If we can't then we are done
        if (!popReader())
            break;
    }
    return (tmpFlag || skippedSomething);
}

void ReaderMgr::skipQuotedString(const XMLCh quoteCh)
{
    XMLCh nextCh;
    while (true)
    {
        nextCh = getNextChar();

        // If we get an end of file char, then return
        if (!nextCh)
            break;

        // If we get the quote char, then break out
        if (nextCh == quoteCh)
            break;
    }
}


XMLCh ReaderMgr::skipUntilIn(const XMLCh* const listToSkip)
{
    XMLCh nextCh;
    while (true)
    {
        nextCh = peekNextChar();

        if (!nextCh)
            break;

        if (XMLString::indexOf(listToSkip, nextCh) != -1)
            break;

        // Its one of ours so eat it
        getNextChar();
    }
    return nextCh;
}


XMLCh ReaderMgr::skipUntilInOrWS(const XMLCh* const listToSkip)
{
    XMLCh nextCh;
    while (true)
    {
        nextCh = peekNextChar();

        if (!nextCh)
            break;

        if (fCurReader->isWhitespace(nextCh))
            break;

        if (XMLString::indexOf(listToSkip, nextCh) != -1)
            break;

        // Its one of ours, so eat it
        getNextChar();
    }
    return nextCh;
}



// ---------------------------------------------------------------------------
//  ReaderMgr: Control methods
// ---------------------------------------------------------------------------

//
//  If the reader stack is empty, then there is only the original main XML
//  entity left. If its empty, then we have no more input.
//
bool ReaderMgr::atEOF() const
{
    return fReaderStack->empty() && fCurReader->getNoMoreFlag();
}


//
//  This method is called in the case of errors to clean up the stack when
//  entities have been incorrectly left on the stack due to syntax errors.
//  It just cleans back the stack, and sends no entity events.
//
void ReaderMgr::cleanStackBackTo(const unsigned int readerNum)
{
    //
    //  Just start popping readers until we find the one with the indicated
    //  reader number.
    //
    while (true)
    {
        if (fCurReader->getReaderNum() == readerNum)
            break;

        if (fReaderStack->empty())
            ThrowXMLwithMemMgr(RuntimeException, XMLExcepts::RdrMgr_ReaderIdNotFound, fMemoryManager);

        delete fCurReader;
        fCurReader = fReaderStack->pop();
        fCurEntity = fEntityStack->pop();
    }