saxparser.hpp

开源xml解析库,非常有名

      * @see #setExternalSchemaLocation(const XMLCh* const)
      */
    void setExternalSchemaLocation(const char* const schemaLocation);

    /**
      * This method allows the user to specify the no target namespace XML
      * Schema Location externally.  If specified, the instance document's
      * noNamespaceSchemaLocation attribute will be effectively ignored.
      *
      * If this method is called more than once, only the last one takes effect.
      *
      * The syntax is the same as for the noNamespaceSchemaLocation attribute
      * that may occur in an instance document: e.g."file_name.xsd".
      *
      * @param noNamespaceSchemaLocation the XML Schema Location with no target namespace
      *
      * @see #getExternalNoNamespaceSchemaLocation
      */
    void setExternalNoNamespaceSchemaLocation(const XMLCh* const noNamespaceSchemaLocation);

    /**
      * This method is same as setExternalNoNamespaceSchemaLocation(const XMLCh* const).
      * It takes native char string as parameter
      *
      * @param noNamespaceSchemaLocation the XML Schema Location with no target namespace
      *
      * @see #setExternalNoNamespaceSchemaLocation(const XMLCh* const)
      */
    void setExternalNoNamespaceSchemaLocation(const char* const noNamespaceSchemaLocation);

    /**
      * This allows an application to set a SecurityManager on
      * the parser; this object stores information that various
      * components use to limit their consumption of system
      * resources while processing documents.
      *
      * If this method is called more than once, only the last one takes effect.
      * It may not be reset during a parse.
      *
      *
      * @param securityManager  the SecurityManager instance to
      * be used by this parser
      *
      * @see #getSecurityManager
      */
    void setSecurityManager(SecurityManager* const securityManager);

    /** Set the 'Loading External DTD' flag
      *
      * This method allows users to enable or disable the loading of external DTD.
      * When set to false, the parser will ignore any external DTD completely
      * if the validationScheme is set to Val_Never.
      *
      * The parser's default state is: true.
      *
      * This flag is ignored if the validationScheme is set to Val_Always or Val_Auto.
      *
      * @param newState The value specifying whether external DTD should
      *                 be loaded or not.
      *
      * @see #getLoadExternalDTD
      * @see #setValidationScheme
      */
    void setLoadExternalDTD(const bool newState);

    /** Set the 'Grammar caching' flag
      *
      * This method allows users to enable or disable caching of grammar when
      * parsing XML documents. When set to true, the parser will cache the
      * resulting grammar for use in subsequent parses.
      *
      * If the flag is set to true, the 'Use cached grammar' flag will also be
      * set to true.
      *
      * The parser's default state is: false.
      *
      * @param newState The value specifying whether we should cache grammars
      *                 or not.
      *
      * @see #isCachingGrammarFromParse
      * @see #useCachedGrammarInParse
      */
    void cacheGrammarFromParse(const bool newState);

    /** Set the 'Use cached grammar' flag
      *
      * This method allows users to enable or disable the use of cached
      * grammars.  When set to true, the parser will use the cached grammar,
      * instead of building the grammar from scratch, to validate XML
      * documents.
      *
      * If the 'Grammar caching' flag is set to true, this method ignores the
      * value passed in.
      *
      * The parser's default state is: false.
      *
      * @param newState The value specifying whether we should use the cached
      *                 grammar or not.
      *
      * @see #isUsingCachedGrammarInParse
      * @see #cacheGrammarFromParse
      */
    void useCachedGrammarInParse(const bool newState);

    /** Enable/disable src offset calculation
      *
      * This method allows users to enable/disable src offset calculation.
      * Disabling the calculation will improve performance.
      *
      * The parser's default state is: false.
      *
      * @param newState The value specifying whether we should enable or
      *                 disable src offset calculation
      *
      * @see #getCalculateSrcOfs
      */
    void setCalculateSrcOfs(const bool newState);

    /** Force standard uri
      *
      * This method allows users to tell the parser to force standard uri conformance.
      *
      * The parser's default state is: false.
      *
      * @param newState The value specifying whether the parser should reject malformed URI.
      *
      * @see #getStandardUriConformant
      */
    void setStandardUriConformant(const bool newState);

    /** Set the scanner to use when scanning the XML document
      *
      * This method allows users to set the scanner to use
      * when scanning a given XML document.
      *
      * @param scannerName The name of the desired scanner
      */
    void useScanner(const XMLCh* const scannerName);

    /** Set maximum input buffer size
      *
      * This method allows users to limit the size of buffers used in parsing
      * XML character data. The effect of setting this size is to limit the
      * size of a ContentHandler::characters() call.
      *
      * The parser's default input buffer size is 1 megabyte.
      *
      * @param bufferSize The maximum input buffer size
      */
    void setInputBufferSize(const size_t bufferSize);

    /** Set the 'ignore cached DTD grammar' flag
      *
      * This method gives users the option to ignore a cached DTD grammar, when
      * an XML document contains both an internal and external DTD, and the use
      * cached grammar from parse option is enabled. Currently, we do not allow
      * using cached DTD grammar when an internal subset is present in the
      * document. This option will only affect the behavior of the parser when
      * an internal and external DTD both exist in a document (i.e. no effect
      * if document has no internal subset).
      *
      * The parser's default state is false
      *
      * @param newValue The state to set
      */
    void setIgnoreCachedDTD(const bool newValue);

    /** Set the 'ignore annotation' flag
      *
      * This method gives users the option to not generate XSAnnotations
      * when "traversing" a schema.
      *
      * The parser's default state is false
      *
      * @param newValue The state to set
      */
    void setIgnoreAnnotations(const bool newValue);

    /** Set the 'disable default entity resolution' flag
      *
      * This method gives users the option to not perform default entity
      * resolution.  If the user's resolveEntity method returns NULL the
      * parser will try to resolve the entity on its own.  When this option
      * is set to true, the parser will not attempt to resolve the entity
      * when the resolveEntity method returns NULL.
      *    
      * The parser's default state is false
      *
      * @param newValue The state to set
      *
      * @see #entityResolver
      */
    void setDisableDefaultEntityResolution(const bool newValue);

    /** Set the 'skip DTD validation' flag
      *
      * This method gives users the option to skip DTD validation only when 
      * schema validation is on (i.e. when performing validation,  we will
      * ignore the DTD, except for entities, when schema validation is enabled).
      *
      * NOTE: This option is ignored if schema validation is disabled.
      *
      * The parser's default state is false
      *
      * @param newValue The state to set
      */
    void setSkipDTDValidation(const bool newValue);
    //@}


    // -----------------------------------------------------------------------
    //  Advanced document handler list maintenance methods
    // -----------------------------------------------------------------------

    /** @name Advanced document handler list maintenance methods */
    //@{
    /**
      * This method installs the specified 'advanced' document callback
      * handler, thereby allowing the user to customize the processing,
      * if they choose to do so. Any number of advanced callback handlers
      * maybe installed.
      *
      * <p>The methods in the advanced callback interface represent
      * Xerces-C extensions. There is no specification for this interface.</p>
      *
      * @param toInstall A pointer to the users advanced callback handler.
      *
      * @see #removeAdvDocHandler
      */
    void installAdvDocHandler(XMLDocumentHandler* const toInstall);

    /**
      * This method removes the 'advanced' document handler callback from
      * the underlying parser scanner. If no handler is installed, advanced
      * callbacks are not invoked by the scanner.
      * @param toRemove A pointer to the advanced callback handler which
      *                 should be removed.
      *
      * @see #installAdvDocHandler
      */
    bool removeAdvDocHandler(XMLDocumentHandler* const toRemove);
    //@}


    // -----------------------------------------------------------------------
    //  Progressive scan methods
    // -----------------------------------------------------------------------

    /** @name Progressive scan methods */
    //@{

    /** Begin a progressive parse operation
      *
      * This method is used to start a progressive parse on a XML file.
      * To continue parsing, subsequent calls must be to the parseNext
      * method.
      *
      * It scans through the prolog and returns a token to be used on
      * subsequent scanNext() calls. If the return value is true, then the
      * token is legal and ready for further use. If it returns false, then
      * the scan of the prolog failed and the token is not going to work on
      * subsequent scanNext() calls.
      *
      * @param systemId A pointer to a Unicode string represting the path
      *                 to the XML file to be parsed.
      * @param toFill   A token maintaing state information to maintain
      *                 internal consistency between invocation of 'parseNext'
      *                 calls.
      *
      * @return 'true', if successful in parsing the prolog. It indicates the
      *         user can go ahead with parsing the rest of the file. It
      *         returns 'false' to indicate that the parser could parse the
      *         prolog (which means the token will not be valid.)
      *
      * @see #parseNext
      * @see #parseFirst(char*,...)
      * @see #parseFirst(InputSource&,...)
      */
    bool parseFirst
    (
        const   XMLCh* const    systemId
        ,       XMLPScanToken&  toFill
    );

    /** Begin a progressive parse operation
      *
      * This method is used to start a progressive parse on a XML file.
      * To continue parsing, subsequent calls must be to the parseNext
      * method.
      *
      * It scans through the prolog and returns a token to be used on
      * subsequent scanNext() calls. If the return value is true, then the
      * token is legal and ready for further use. If it returns false, then
      * the scan of the prolog failed and the token is not going to work on
      * subsequent scanNext() calls.
      *
      * @param systemId A pointer to a regular native string represting
      *                 the path to the XML file to be parsed.
      * @param toFill   A token maintaing state information to maintain
      *                 internal consIstency between invocation of 'parseNext'
      *                 calls.
      *
      * @return 'true', if successful in parsing the prolog. It indicates the
      *         user can go ahead with parsing the rest of the file. It
      *         returns 'false' to indicate that the parser could not parse
      *         the prolog.
      *
      * @see #parseNext
      * @see #parseFirst(XMLCh*,...)
      * @see #parseFirst(InputSource&,...)
      */
    bool parseFirst
    (
        const   char* const     systemId
        ,       XMLPScanToken&  toFill
    );

    /** Begin a progressive parse operation
      *
      * This method is used to start a progressive parse on a XML file.
      * To continue parsing, subsequent calls must be to the parseNext
      * method.
      *
      * It scans through the prolog and returns a token to be used on
      * subsequent scanNext() calls. If the return value is true, then the
      * token is legal and ready for further use. If it returns false, then
      * the scan of the prolog failed and the token is not going to work on
      * subsequent scanNext() calls.
      *
      * @param source   A const reference to the InputSource object which
      *                 points to the XML file to be parsed.
      * @param toFill   A token maintaing state information to maintain
      *                 internal consistency between invocation of 'parseNext'
      *                 calls.
      *
      * @return 'true', if successful in parsing the prolog. It indicates the
      *         user can go ahead with parsing the rest of the file. It
      *         returns 'false' to indicate that the parser could not parse
      *         the prolog.
      *
      * @see #parseNext
      * @see #parseFirst(XMLCh*,...)
      * @see #parseFirst(char*,...)
      */
    bool parseFirst