class Poco::XML::XMLFilterImpl
Overview
Base class for deriving an XML filter. More…
#include <XMLFilterImpl.h> class XMLFilterImpl: public Poco::XML::XMLFilter, public Poco::XML::EntityResolver, public Poco::XML::DTDHandler, public Poco::XML::ContentHandler, public Poco::XML::ErrorHandler { public: // construction XMLFilterImpl(); XMLFilterImpl(XMLReader* pParent); // methods virtual XMLReader* getParent() const; virtual void setParent(XMLReader* pParent); virtual void setEntityResolver(EntityResolver* pResolver); virtual EntityResolver* getEntityResolver() const; virtual void setDTDHandler(DTDHandler* pDTDHandler); virtual DTDHandler* getDTDHandler() const; virtual void setContentHandler(ContentHandler* pContentHandler); virtual ContentHandler* getContentHandler() const; virtual void setErrorHandler(ErrorHandler* pErrorHandler); virtual ErrorHandler* getErrorHandler() const; virtual void setFeature( const XMLString& featureId, bool state ); virtual bool getFeature(const XMLString& featureId) const; virtual void setProperty( const XMLString& propertyId, const XMLString& value ); virtual void setProperty( const XMLString& propertyId, void* value ); virtual void* getProperty(const XMLString& propertyId) const; virtual void parse(InputSource* pSource); virtual void parse(const XMLString& systemId); virtual void parseMemoryNP( const char* xml, std::size_t size ); virtual InputSource* resolveEntity( const XMLString* publicId, const XMLString& systemId ); virtual void releaseInputSource(InputSource* pSource); virtual void notationDecl( const XMLString& name, const XMLString* publicId, const XMLString* systemId ); virtual void unparsedEntityDecl( const XMLString& name, const XMLString* publicId, const XMLString& systemId, const XMLString& notationName ); virtual void setDocumentLocator(const Locator* loc); virtual void startDocument(); virtual void endDocument(); virtual void startElement( const XMLString& uri, const XMLString& localName, const XMLString& qname, const Attributes& attrList ); virtual void endElement( const XMLString& uri, const XMLString& localName, const XMLString& qname ); virtual void characters( const XMLChar ch [], int start, int length ); virtual void ignorableWhitespace( const XMLChar ch [], int start, int length ); virtual void processingInstruction( const XMLString& target, const XMLString& data ); virtual void startPrefixMapping( const XMLString& prefix, const XMLString& uri ); virtual void endPrefixMapping(const XMLString& prefix); virtual void skippedEntity(const XMLString& name); virtual void warning(const SAXException& exc); virtual void error(const SAXException& exc); virtual void fatalError(const SAXException& exc); protected: // methods XMLReader* parent() const; virtual void setupParse(); }; // direct descendants class WhitespaceFilter;
Inherited Members
public: // fields static const XMLString FEATURE_VALIDATION; static const XMLString FEATURE_NAMESPACES; static const XMLString FEATURE_NAMESPACE_PREFIXES; static const XMLString FEATURE_EXTERNAL_GENERAL_ENTITIES; static const XMLString FEATURE_EXTERNAL_PARAMETER_ENTITIES; static const XMLString FEATURE_STRING_INTERNING; static const XMLString PROPERTY_DECLARATION_HANDLER; static const XMLString PROPERTY_LEXICAL_HANDLER; // methods virtual void setEntityResolver(EntityResolver* pResolver) = 0; virtual EntityResolver* getEntityResolver() const = 0; virtual void setDTDHandler(DTDHandler* pDTDHandler) = 0; virtual DTDHandler* getDTDHandler() const = 0; virtual void setContentHandler(ContentHandler* pContentHandler) = 0; virtual ContentHandler* getContentHandler() const = 0; virtual void setErrorHandler(ErrorHandler* pErrorHandler) = 0; virtual ErrorHandler* getErrorHandler() const = 0; virtual void setFeature( const XMLString& featureId, bool state ) = 0; virtual bool getFeature(const XMLString& featureId) const = 0; virtual void setProperty( const XMLString& propertyId, const XMLString& value ) = 0; virtual void setProperty( const XMLString& propertyId, void* value ) = 0; virtual void* getProperty(const XMLString& propertyId) const = 0; virtual void parse(InputSource* pSource) = 0; virtual void parse(const XMLString& systemId) = 0; virtual void parseMemoryNP( const char* xml, std::size_t size ) = 0; virtual XMLReader* getParent() const = 0; virtual void setParent(XMLReader* pParent) = 0; virtual InputSource* resolveEntity( const XMLString* publicId, const XMLString& systemId ) = 0; virtual void releaseInputSource(InputSource* pSource) = 0; virtual void notationDecl( const XMLString& name, const XMLString* publicId, const XMLString* systemId ) = 0; virtual void unparsedEntityDecl( const XMLString& name, const XMLString* publicId, const XMLString& systemId, const XMLString& notationName ) = 0; virtual void setDocumentLocator(const Locator* loc) = 0; virtual void startDocument() = 0; virtual void endDocument() = 0; virtual void startElement( const XMLString& uri, const XMLString& localName, const XMLString& qname, const Attributes& attrList ) = 0; virtual void endElement( const XMLString& uri, const XMLString& localName, const XMLString& qname ) = 0; virtual void characters( const XMLChar ch [], int start, int length ) = 0; virtual void ignorableWhitespace( const XMLChar ch [], int start, int length ) = 0; virtual void processingInstruction( const XMLString& target, const XMLString& data ) = 0; virtual void startPrefixMapping( const XMLString& prefix, const XMLString& uri ) = 0; virtual void endPrefixMapping(const XMLString& prefix) = 0; virtual void skippedEntity(const XMLString& name) = 0; virtual void warning(const SAXException& exc) = 0; virtual void error(const SAXException& exc) = 0; virtual void fatalError(const SAXException& exc) = 0;
Detailed Documentation
Base class for deriving an XML filter.
This class is designed to sit between an XMLReader and the client application’s event handlers. By default, it does nothing but pass requests up to the reader and events on to the handlers unmodified, but subclasses can override specific methods to modify the event stream or the configuration requests as they pass through.
Construction
XMLFilterImpl()
Construct an empty XML filter, with no parent.
This filter will have no parent: you must assign a parent before you start a parse or do any configuration with setFeature or setProperty, unless you use this as a pure event consumer rather than as an XMLReader.
XMLFilterImpl(XMLReader* pParent)
Construct an XML filter with the specified parent.
Methods
virtual XMLReader* getParent() const
Set the parent reader.
This method allows the application to link the filter to a parent reader (which may be another filter). The argument may not be null.
virtual void setParent(XMLReader* pParent)
Get the parent reader.
This method allows the application to query the parent reader (which may be another filter). It is generally a bad idea to perform any operations on the parent reader directly: they should all pass through this filter.
virtual void setEntityResolver(EntityResolver* pResolver)
Allow an application to register an entity resolver.
If the application does not register an entity resolver, the XMLReader will perform its own default resolution.
Applications may register a new or different resolver in the middle of a parse, and the SAX parser must begin using the new resolver immediately.
virtual EntityResolver* getEntityResolver() const
Return the current entity resolver.
virtual void setDTDHandler(DTDHandler* pDTDHandler)
Allow an application to register a DTD event handler.
If the application does not register a DTD handler, all DTD events reported by the SAX parser will be silently ignored.
Applications may register a new or different handler in the middle of a parse, and the SAX parser must begin using the new handler immediately.
virtual DTDHandler* getDTDHandler() const
Return the current DTD handler.
virtual void setContentHandler(ContentHandler* pContentHandler)
Allow an application to register a content event handler.
If the application does not register a content handler, all content events reported by the SAX parser will be silently ignored.
Applications may register a new or different handler in the middle of a parse, and the SAX parser must begin using the new handler immediately.
virtual ContentHandler* getContentHandler() const
Return the current content handler.
virtual void setErrorHandler(ErrorHandler* pErrorHandler)
Allow an application to register an error event handler.
If the application does not register an error handler, all error events reported by the SAX parser will be silently ignored; however, normal processing may not continue. It is highly recommended that all SAX applications implement an error handler to avoid unexpected bugs.
Applications may register a new or different handler in the middle of a parse, and the SAX parser must begin using the new handler immediately.
virtual ErrorHandler* getErrorHandler() const
Return the current error handler.
virtual void setFeature( const XMLString& featureId, bool state )
Set the state of a feature.
The feature name is any fully-qualified URI. It is possible for an XMLReader to expose a feature value but to be unable to change the current value. Some feature values may be immutable or mutable only in specific contexts, such as before, during, or after a parse.
All XMLReaders are required to support setting http://xml.org/sax/features/namespaces to true and http://xml.org/sax/features/namespace-prefixes to false.
virtual bool getFeature(const XMLString& featureId) const
Look up the value of a feature.
The feature name is any fully-qualified URI. It is possible for an XMLReader to recognize a feature name but temporarily be unable to return its value. Some feature values may be available only in specific contexts, such as before, during, or after a parse. Also, some feature values may not be programmatically accessible. (In the case of an adapter for SAX1 Parser, there is no implementation-independent way to expose whether the underlying parser is performing validation, expanding external entities, and so forth.)
All XMLReaders are required to recognize the http://xml.org/sax/features/namespaces and the http://xml.org/sax/features/namespace-prefixes feature names. Implementors are free (and encouraged) to invent their own features, using names built on their own URIs.
virtual void setProperty( const XMLString& propertyId, const XMLString& value )
Set the value of a property.
The property name is any fully-qualified URI. It is possible for an XMLReader to recognize a property name but to be unable to change the current value. Some property values may be immutable or mutable only in specific contexts, such as before, during, or after a parse.
XMLReaders are not required to recognize setting any specific property names, though a core set is defined by SAX2.
This method is also the standard mechanism for setting extended handlers.
virtual void setProperty( const XMLString& propertyId, void* value )
Set the value of a property.
See also setProperty(const XMLString&, const XMLString&).
virtual void* getProperty(const XMLString& propertyId) const
Look up the value of a property.
String values are returned as XMLChar* The property name is any fully-qualified URI. It is possible for an XMLReader to recognize a property name but temporarily be unable to return its value. Some property values may be available only in specific contexts, such as before, during, or after a parse.
XMLReaders are not required to recognize any specific property names, though an initial core set is documented for SAX2.
Implementors are free (and encouraged) to invent their own properties, using names built on their own URIs.
virtual void parse(InputSource* pSource)
Parse an XML document.
The application can use this method to instruct the XML reader to begin parsing an XML document from any valid input source (a character stream, a byte stream, or a URI).
Applications may not invoke this method while a parse is in progress (they should create a new XMLReader instead for each nested XML document). Once a parse is complete, an application may reuse the same XMLReader object, possibly with a different input source. Configuration of the XMLReader object (such as handler bindings and values established for feature flags and properties) is unchanged by completion of a parse, unless the definition of that aspect of the configuration explicitly specifies other behavior. (For example, feature flags or properties exposing characteristics of the document being parsed.)
During the parse, the XMLReader will provide information about the XML document through the registered event handlers.
This method is synchronous: it will not return until parsing has ended. If a client application wants to terminate parsing early, it should throw an exception.
virtual void parse(const XMLString& systemId)
Parse an XML document from a system identifier.
See also parse(InputSource*).
virtual void parseMemoryNP( const char* xml, std::size_t size )
Parse an XML document from memory.
See also parse(InputSource*).
virtual InputSource* resolveEntity( const XMLString* publicId, const XMLString& systemId )
Allow the application to resolve external entities.
The parser will call this method before opening any external entity except the top-level document entity. Such entities include the external DTD subset and external parameter entities referenced within the DTD (in either case, only if the parser reads external parameter entities), and external general entities referenced within the document element (if the parser reads external general entities). The application may request that the parser locate the entity itself, that it use an alternative URI, or that it use data provided by the application (as a character or byte input stream).
Application writers can use this method to redirect external system identifiers to secure and/or local URIs, to look up public identifiers in a catalogue, or to read an entity from a database or other input source (including, for example, a dialog box). Neither XML nor SAX specifies a preferred policy for using public or system IDs to resolve resources. However, SAX specifies how to interpret any InputSource returned by this method, and that if none is returned, then the system ID will be dereferenced as a URL.
If the system identifier is a URL, the SAX parser must resolve it fully before reporting it to the application.
Note that publicId maybe null, therefore we pass a pointer rather than a reference.
virtual void releaseInputSource(InputSource* pSource)
This is a non-standard extension to SAX! Called by the parser when the input source returned by ResolveEntity is no longer needed.
Should free any resources used by the input source.
virtual void notationDecl( const XMLString& name, const XMLString* publicId, const XMLString* systemId )
Receive notification of a notation declaration event.
It is up to the application to record the notation for later reference, if necessary; notations may appear as attribute values and in unparsed entity declarations, and are sometime used with processing instruction target names.
At least one of publicId and systemId must be non-null. If a system identifier is present, and it is a URL, the SAX parser must resolve it fully before passing it to the application through this event.
There is no guarantee that the notation declaration will be reported before any unparsed entities that use it.
Note that publicId and systemId maybe null, therefore we pass a pointer rather than a reference.
virtual void unparsedEntityDecl( const XMLString& name, const XMLString* publicId, const XMLString& systemId, const XMLString& notationName )
Receive notification of an unparsed entity declaration event.
Note that the notation name corresponds to a notation reported by the notationDecl event. It is up to the application to record the entity for later reference, if necessary; unparsed entities may appear as attribute values.
If the system identifier is a URL, the parser must resolve it fully before passing it to the application.
Note that publicId maybe null, therefore we pass a pointer rather than a reference.
virtual void setDocumentLocator(const Locator* loc)
Receive an object for locating the origin of SAX document events.
SAX parsers are strongly encouraged (though not absolutely required) to supply a locator: if it does so, it must supply the locator to the application by invoking this method before invoking any of the other methods in the ContentHandler interface.
The locator allows the application to determine the end position of any document-related event, even if the parser is not reporting an error. Typically, the application will use this information for reporting its own errors (such as character content that does not match an application’s business rules). The information returned by the locator is probably not sufficient for use with a search engine.
Note that the locator will return correct information only during the invocation SAX event callbacks after startDocument returns and before endDocument is called. The application should not attempt to use it at any other time.
virtual void startDocument()
Receive notification of the beginning of a document.
The SAX parser calls this function one time before calling all other functions of this class (except SetDocumentLocator).
virtual void endDocument()
Receive notification of the end of a document.
The SAX parser will invoke this method only once, and it will be the last method invoked during the parse. The parser shall not invoke this method until it has either abandoned parsing (because of an unrecoverable error) or reached the end of input.
virtual void startElement( const XMLString& uri, const XMLString& localName, const XMLString& qname, const Attributes& attrList )
Receive notification of the beginning of an element.
The Parser will invoke this method at the beginning of every element in the XML document; there will be a corresponding endElement event for every startElement event (even when the element is empty). All of the element’s content will be reported, in order, before the corresponding endElement event.
This event allows up to three name components for each element:
1. the Namespace URI; 2. the local name; and 3. the qualified (prefixed) name.
Any or all of these may be provided, depending on the values of the http://xml.org/sax/features/namespaces and the http://xml.org/sax/features/namespace-prefixes properties:
* the Namespace URI and local name are required when the namespaces property is true (the default), and are optional when the namespaces property is false (if one is specified, both must be); * the qualified name is required when the namespace-prefixes property is true, and is optional when the namespace-prefixes property is false (the default).
Note that the attribute list provided will contain only attributes with explicit values (specified or defaulted): #IMPLIED attributes will be omitted. The attribute list will contain attributes used for Namespace declarations (xmlns* attributes) only if the http://xml.org/sax/features/namespace-prefixes property is true (it is false by default, and support for a true value is optional).
Like characters(), attribute values may have characters that need more than one char value.
virtual void endElement( const XMLString& uri, const XMLString& localName, const XMLString& qname )
Receive notification of the end of an element.
The SAX parser will invoke this method at the end of every element in the XML document; there will be a corresponding startElement event for every endElement event (even when the element is empty).
For information on the names, see startElement.
virtual void characters( const XMLChar ch [], int start, int length )
Receive notification of character data.
The Parser will call this method to report each chunk of character data. SAX parsers may return all contiguous character data in a single chunk, or they may split it into several chunks; however, all of the characters in any single event must come from the same external entity so that the Locator provides useful information.
The application must not attempt to read from the array outside of the specified range.
Individual characters may consist of more than one XMLChar value. There are three important cases where this happens, because characters can’t be represented in just sixteen bits. In one case, characters are represented in a Surrogate Pair, using two special Unicode values. Such characters are in the so-called “Astral Planes”, with a code point above U+FFFF. A second case involves composite characters, such as a base character combining with one or more accent characters. And most important, if XMLChar is a plain char, characters are encoded in UTF-8.
Your code should not assume that algorithms using char-at-a-time idioms will be working in character units; in some cases they will split characters. This is relevant wherever XML permits arbitrary characters, such as attribute values, processing instruction data, and comments as well as in data reported from this method. It’s also generally relevant whenever C++ code manipulates internationalized text; the issue isn’t unique to XML.
Note that some parsers will report whitespace in element content using the ignorableWhitespace method rather than this one (validating parsers must do so).
virtual void ignorableWhitespace( const XMLChar ch [], int start, int length )
Receive notification of ignorable whitespace in element content.
Validating Parsers must use this method to report each chunk of whitespace in element content (see the W3C XML 1.0 recommendation, section 2.10): non-validating parsers may also use this method if they are capable of parsing and using content models.
SAX parsers may return all contiguous whitespace in a single chunk, or they may split it into several chunks; however, all of the characters in any single event must come from the same external entity, so that the Locator provides useful information.
The application must not attempt to read from the array outside of the specified range.
virtual void processingInstruction( const XMLString& target, const XMLString& data )
Receive notification of a processing instruction.
The Parser will invoke this method once for each processing instruction found: note that processing instructions may occur before or after the main document element.
A SAX parser must never report an XML declaration (XML 1.0, section 2.8) or a text declaration (XML 1.0, section 4.3.1) using this method.
Like characters(), processing instruction data may have characters that need more than one char value.
virtual void startPrefixMapping( const XMLString& prefix, const XMLString& uri )
Begin the scope of a prefix-URI Namespace mapping.
The information from this event is not necessary for normal Namespace processing: the SAX XML reader will automatically replace prefixes for element and attribute names when the http://xml.org/sax/features/namespaces feature is true (the default).
There are cases, however, when applications need to use prefixes in character data or in attribute values, where they cannot safely be expanded automatically; the start/endPrefixMapping event supplies the information to the application to expand prefixes in those contexts itself, if necessary.
Note that start/endPrefixMapping events are not guaranteed to be properly nested relative to each other: all startPrefixMapping events will occur immediately before the corresponding startElement event, and all endPrefixMapping events will occur immediately after the corresponding endElement event, but their order is not otherwise guaranteed.
There should never be start/endPrefixMapping events for the “xml” prefix, since it is predeclared and immutable.
virtual void endPrefixMapping(const XMLString& prefix)
End the scope of a prefix-URI mapping.
See startPrefixMapping for details. These events will always occur immediately after the corresponding endElement event, but the order of endPrefixMapping events is not otherwise guaranteed.
virtual void skippedEntity(const XMLString& name)
Receive notification of a skipped entity.
This is not called for entity references within markup constructs such as element start tags or markup declarations. (The XML recommendation requires reporting skipped external entities. SAX also reports internal entity expansion/non-expansion, except within markup constructs.)
The Parser will invoke this method each time the entity is skipped. Non-validating processors may skip entities if they have not seen the declarations (because, for example, the entity was declared in an external DTD subset). All processors may skip external entities, depending on the values of the http://xml.org/sax/features/external-general-entities and the http://xml.org/sax/features/external-parameter-entities properties.
virtual void warning(const SAXException& exc)
Receive notification of a warning.
SAX parsers will use this method to report conditions that are not errors or fatal errors as defined by the XML recommendation. The default behaviour is to take no action.
The SAX parser must continue to provide normal parsing events after invoking this method: it should still be possible for the application to process the document through to the end.
Filters may use this method to report other, non-XML warnings as well.
virtual void error(const SAXException& exc)
Receive notification of a recoverable error.
This corresponds to the definition of “error” in section 1.2 of the W3C XML 1.0 Recommendation. For example, a validating parser would use this callback to report the violation of a validity constraint. The default behaviour is to take no action.
The SAX parser must continue to provide normal parsing events after invoking this method: it should still be possible for the application to process the document through to the end. If the application cannot do so, then the parser should report a fatal error even if the XML recommendation does not require it to do so.
Filters may use this method to report other, non-XML errors as well.
virtual void fatalError(const SAXException& exc)
Receive notification of a non-recoverable error.
The application must assume that the document is unusable after the parser has invoked this method, and should continue (if at all) only for the sake of collecting additional error messages: in fact, SAX parsers are free to stop reporting any other events once this method has been invoked.
XMLReader* parent() const
Return a pointer to the parent reader.
Subclasses can use this method instead of getParent() for better performance - this method is non-virtual and implemented as inline.
virtual void setupParse()
Setup the event handlers in the parent reader.