xmlreader.hpp

基于属性证书的访问控制源代码,由c++编写,包括openssl,xercesc等

/*
 * The Apache Software License, Version 1.1
 *
 * Copyright (c) 1999-2001 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Xerces" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact apache\@apache.org.
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation, and was
 * originally based on software copyright (c) 1999, International
 * Business Machines, Inc., http://www.ibm.com .  For more information
 * on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */

/*
 * $Log: XMLReader.hpp,v $
 * Revision 1.15  2004/01/29 11:46:30  cargilld
 * Code cleanup changes to get rid of various compiler diagnostic messages.
 *
 * Revision 1.14  2003/05/16 21:36:58  knoaman
 * Memory manager implementation: Modify constructors to pass in the memory manager.
 *
 * Revision 1.13  2003/05/15 18:26:29  knoaman
 * Partial implementation of the configurable memory manager.
 *
 * Revision 1.12  2003/01/27 16:50:27  knoaman
 * some cleanup.
 *
 * Revision 1.11  2002/12/20 22:09:56  tng
 * XML 1.1
 *
 * Revision 1.10  2002/12/11 22:09:08  knoaman
 * Performance: reduce instructions count.
 *
 * Revision 1.9  2002/12/03 15:31:19  knoaman
 * Enable/disable calculation of src offset.
 *
 * Revision 1.8  2002/12/02 17:20:05  knoaman
 * Remove unused data member.
 *
 * Revision 1.7  2002/11/28 19:19:12  knoaman
 * Performance: remove unnecessary if condition.
 *
 * Revision 1.6  2002/11/28 18:17:22  knoaman
 * Performance: make getNextChar/peekNextChar inline.
 *
 * Revision 1.5  2002/11/25 21:31:08  tng
 * Performance:
 * 1. use XMLRecognizer::Encodings enum to make new transcode, faster than comparing the encoding string every time.
 * 2. Pre uppercase the encodingString before calling encodingForName to avoid calling compareIString
 *
 * Revision 1.4  2002/11/04 14:58:19  tng
 * C++ Namespace Support.
 *
 * Revision 1.3  2002/09/27 12:56:23  tng
 * [Bug 12740] Extra include.  By Peter Volchek.
 *
 * Revision 1.2  2002/05/27 18:42:14  tng
 * To get ready for 64 bit large file, use XMLSSize_t to represent line and column number.
 *
 * Revision 1.1.1.1  2002/02/01 22:22:02  peiyongz
 * sane_include
 *
 * Revision 1.18  2001/12/06 17:47:04  tng
 * Performance Enhancement.  Modify the handling of the fNEL option so that it results in fgCharCharsTable being modified, instead of having all of the low-level routines check the option.  This seemed acceptable because the code appears to only permit the option to be turned on and not turned off again.   By Henry Zongaro.
 *
 * Revision 1.17  2001/07/12 18:50:13  tng
 * Some performance modification regarding standalone check and xml decl check.
 *
 * Revision 1.16  2001/05/11 13:26:17  tng
 * Copyright update.
 *
 * Revision 1.15  2001/05/03 18:42:51  knoaman
 * Added new option to the parsers so that the NEL (0x85) char can be treated as a newline character.
 *
 * Revision 1.14  2001/01/25 19:16:58  tng
 * const should be used instead of static const.  Fixed by Khaled Noaman.
 *
 * Revision 1.13  2000/07/25 22:33:05  aruna1
 * Char definitions in XMLUni moved to XMLUniDefs
 *
 * Revision 1.12  2000/07/08 00:17:13  andyh
 * Cleanup of yesterday's speedup changes.  Merged new bit into the
 * scanner character properties table.
 *
 * Revision 1.11  2000/07/07 01:08:44  andyh
 * Parser speed up in scan of XML content.
 *
 * Revision 1.10  2000/07/06 21:00:52  jpolast
 * inlined getNextCharIfNot() for better performance
 *
 * Revision 1.9  2000/05/11 23:11:33  andyh
 * Add missing validity checks for stand-alone documents, character range
 * and Well-formed parsed entities.  Changes contributed by Sean MacRoibeaird
 * <[e-mail]>
 *
 * Revision 1.8  2000/03/02 19:54:29  roddey
 * This checkin includes many changes done while waiting for the
 * 1.1.0 code to be finished. I can't list them all here, but a list is
 * available elsewhere.
 *
 * Revision 1.7  2000/02/24 20:18:07  abagchi
 * Swat for removing Log from API docs
 *
 * Revision 1.6  2000/02/06 07:47:53  rahulj
 * Year 2K copyright swat.
 *
 * Revision 1.5  2000/01/25 01:04:21  roddey
 * Fixes a bogus error about ]]> in char data.
 *
 * Revision 1.4  2000/01/22 00:01:08  roddey
 * Simple change to get rid of two hard coded 'x' type characters, which won't
 * work on EBCDIC systems.
 *
 * Revision 1.3  1999/12/18 00:20:00  roddey
 * More changes to support the new, completely orthagonal, support for
 * intrinsic encodings.
 *
 * Revision 1.2  1999/12/15 19:48:03  roddey
 * Changed to use new split of transcoder interfaces into XML transcoders and
 * LCP transcoders, and implementation of intrinsic transcoders as pluggable
 * transcoders, and addition of Latin1 intrinsic support.
 *
 * Revision 1.1.1.1  1999/11/09 01:08:22  twl
 * Initial checkin
 *
 * Revision 1.3  1999/11/08 20:44:47  rahul
 * Swat for adding in Product name and CVS comment log variable.
 *
 */

#if !defined(XMLREADER_HPP)
#define XMLREADER_HPP

#include <xercesc/util/XMLChar.hpp>
#include <xercesc/framework/XMLRecognizer.hpp>
#include <xercesc/framework/XMLBuffer.hpp>

XERCES_CPP_NAMESPACE_BEGIN

class InputSource;
class BinInputStream;
class ReaderMgr;
class XMLScanner;
class XMLTranscoder;


// ---------------------------------------------------------------------------
//  Instances of this class are used to manage the content of entities. The
//  scanner maintains a stack of these, one for each entity (this means entity
//  in the sense of any parsed file or internal entity) currently being
//  scanned. This class, given a binary input stream will handle reading in
//  the data and decoding it from its external decoding into the internal
//  Unicode format. Once internallized, this class provides the access
//  methods to read in the data in various ways, maintains line and column
//  information, and provides high performance character attribute checking
//  methods.
//
//  This is NOT to be derived from.
//
// ---------------------------------------------------------------------------
class XMLPARSER_EXPORT XMLReader : public XMemory
{
public:
    // -----------------------------------------------------------------------
    //  Public types
    // -----------------------------------------------------------------------
    enum Types
    {
        Type_PE
        , Type_General
    };

    enum Sources
    {
        Source_Internal
        , Source_External
    };

    enum RefFrom
    {
        RefFrom_Literal
        , RefFrom_NonLiteral
    };

    enum XMLVersion
    {
        XMLV1_0
        , XMLV1_1
        , XMLV_Unknown
    };


    // -----------------------------------------------------------------------
    //  Public, query methods
    // -----------------------------------------------------------------------
    bool isAllSpaces
    (
        const   XMLCh* const    toCheck
        , const unsigned int    count
    );

    bool containsWhiteSpace
    (
        const   XMLCh* const    toCheck
        , const unsigned int    count
    );


    bool isXMLLetter(const XMLCh toCheck);
    bool isFirstNameChar(const XMLCh toCheck);
    bool isNameChar(const XMLCh toCheck);
    bool isPlainContentChar(const XMLCh toCheck);
    bool isSpecialStartTagChar(const XMLCh toCheck);
    bool isXMLChar(const XMLCh toCheck);
    bool isWhitespace(const XMLCh toCheck);
    bool isControlChar(const XMLCh toCheck);
    bool isPublicIdChar(const XMLCh toCheck);

    // -----------------------------------------------------------------------
    //  Constructors and Destructor
    // -----------------------------------------------------------------------
    XMLReader
    (
        const   XMLCh* const          pubId
        , const XMLCh* const          sysId
        ,       BinInputStream* const streamToAdopt
        , const RefFrom               from
        , const Types                 type
        , const Sources               source
        , const bool                  throwAtEnd = false
        , const bool                  calculateSrcOfs = true
        , const XMLVersion            xmlVersion = XMLV1_0
        ,       MemoryManager* const  manager = XMLPlatformUtils::fgMemoryManager
    );

    XMLReader
    (
        const   XMLCh* const          pubId
        , const XMLCh* const          sysId
        ,       BinInputStream* const streamToAdopt
        , const XMLCh* const          encodingStr
        , const RefFrom               from
        , const Types                 type
        , const Sources               source
        , const bool                  throwAtEnd = false
        , const bool                  calculateSrcOfs = true
        , const XMLVersion            xmlVersion = XMLV1_0
        ,       MemoryManager* const  manager = XMLPlatformUtils::fgMemoryManager
    );

    XMLReader
    (
        const   XMLCh* const          pubId
        , const XMLCh* const          sysId
        ,       BinInputStream* const streamToAdopt
        , XMLRecognizer::Encodings    encodingEnum
        , const RefFrom               from
        , const Types                 type
        , const Sources               source
        , const bool                  throwAtEnd = false
        , const bool                  calculateSrcOfs = true
        , const XMLVersion            xmlVersion = XMLV1_0
        ,       MemoryManager* const  manager = XMLPlatformUtils::fgMemoryManager
    );

    ~XMLReader();


    // -----------------------------------------------------------------------
    //  Character buffer management methods
    // -----------------------------------------------------------------------
    unsigned long charsLeftInBuffer() const;
    bool refreshCharBuffer();


    // -----------------------------------------------------------------------
    //  Scanning methods
    // -----------------------------------------------------------------------
    bool getName(XMLBuffer& toFill, const bool token);
    bool getNextChar(XMLCh& chGotten);