class Poco::XML::WhitespaceFilter

Overview

This implementation of the SAX2 XMLFilter interface filters all whitespace-only character data element content. More…

#include <WhitespaceFilter.h>

class WhitespaceFilter:
    public Poco::XML::XMLFilterImpl,
    public Poco::XML::LexicalHandler
{
public:
    // construction

    WhitespaceFilter();
    WhitespaceFilter(XMLReader* pReader);

    // methods

    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
    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
    startDTD(
        const XMLString& name,
        const XMLString& publicId,
        const XMLString& systemId
        );

    virtual
    void
    endDTD();

    virtual
    void
    startEntity(const XMLString& name);

    virtual
    void
    endEntity(const XMLString& name);

    virtual
    void
    startCDATA();

    virtual
    void
    endCDATA();

    virtual
    void
    comment(
        const XMLChar ch [],
        int start,
        int length
        );

protected:
    // methods

    virtual
    void
    setupParse();
};

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;

    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);

    virtual
    void
    startDTD(
        const XMLString& name,
        const XMLString& publicId,
        const XMLString& systemId
        ) = 0;

    virtual
    void
    endDTD() = 0;

    virtual
    void
    startEntity(const XMLString& name) = 0;

    virtual
    void
    endEntity(const XMLString& name) = 0;

    virtual
    void
    startCDATA() = 0;

    virtual
    void
    endCDATA() = 0;

    virtual
    void
    comment(
        const XMLChar ch [],
        int start,
        int length
        ) = 0;

protected:
    // methods

    XMLReader*
    parent() const;

    virtual
    void
    setupParse();

Detailed Documentation

This implementation of the SAX2 XMLFilter interface filters all whitespace-only character data element content.

Construction

WhitespaceFilter()

Creates the WhitespaceFilter, with no parent.

WhitespaceFilter(XMLReader* pReader)

Creates the WhitespaceFilter with the specified parent.

Methods

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
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
startDTD(
    const XMLString& name,
    const XMLString& publicId,
    const XMLString& systemId
    )

Report the start of DTD declarations, if any.

This method is intended to report the beginning of the DOCTYPE declaration; if the document has no DOCTYPE declaration, this method will not be invoked.

All declarations reported through DTDHandler or DeclHandler events must appear between the startDTD and endDTD events. Declarations are assumed to belong to the internal DTD subset unless they appear between startEntity and endEntity events. Comments and processing instructions from the DTD should also be reported between the startDTD and endDTD events, in their original order of (logical) occurrence; they are not required to appear in their correct locations relative to DTDHandler or DeclHandler events, however.

Note that the start/endDTD events will appear within the start/endDocument events from ContentHandler and before the first startElement event.

virtual
void
endDTD()

Report the end of DTD declarations.

This method is intended to report the end of the DOCTYPE declaration; if the document has no DOCTYPE declaration, this method will not be invoked.

virtual
void
startEntity(const XMLString& name)

Report the beginning of some internal and external XML entities.

The reporting of parameter entities (including the external DTD subset) is optional, and SAX2 drivers that report LexicalHandler events may not implement it; you can use the http://xml.org/sax/features/lexical-handler/parameter-entities feature to query or control the reporting of parameter entities.

General entities are reported with their regular names, parameter entities have ‘’ prepended to their names, and the external DTD subset has the pseudo-entity name “[dtd]”.

When a SAX2 driver is providing these events, all other events must be properly nested within start/end entity events. There is no additional requirement that events from DeclHandler or DTDHandler be properly ordered.

Note that skipped entities will be reported through the skippedEntity event, which is part of the ContentHandler interface.

Because of the streaming event model that SAX uses, some entity boundaries cannot be reported under any circumstances:

* general entities within attribute values
* parameter entities within declarations

These will be silently expanded, with no indication of where the original entity boundaries were.

Note also that the boundaries of character references (which are not really entities anyway) are not reported.

All start/endEntity events must be properly nested.

virtual
void
endEntity(const XMLString& name)

Report the end of an entity.

virtual
void
startCDATA()

Report the start of a CDATA section.

The contents of the CDATA section will be reported through the regular characters event; this event is intended only to report the boundary.

virtual
void
endCDATA()

Report the end of a CDATA section.

virtual
void
comment(
    const XMLChar ch [],
    int start,
    int length
    )

Report an XML comment anywhere in the document.

This callback will be used for comments inside or outside the document element, including comments in the external DTD subset (if read). Comments in the DTD must be properly nested inside start/endDTD and start/endEntity events (if used).

virtual
void
setupParse()

Setup the event handlers in the parent reader.