org.xml.sax.ContentHandler Maven / Gradle / Ivy
// ContentHandler.java - handle main document content.
// http://www.saxproject.org
// Written by David Megginson
// NO WARRANTY! This class is in the public domain.
// $Id: ContentHandler.java,v 1.13 2004/04/26 17:50:49 dmegginson Exp $
package org.xml.sax;
/**
* Receive notification of the logical content of a document.
*
*
* This module, both source code and documentation, is in the
* Public Domain, and comes with NO WARRANTY.
* See http://www.saxproject.org
* for further information.
*
*
* This is the main interface that most SAX applications
* implement: if the application needs to be informed of basic parsing
* events, it implements this interface and registers an instance with
* the SAX parser using the {@link org.xml.sax.XMLReader#setContentHandler
* setContentHandler} method. The parser uses the instance to report
* basic document-related events like the start and end of elements
* and character data.
*
* The order of events in this interface is very important, and
* mirrors the order of information in the document itself. For
* example, all of an element's content (character data, processing
* instructions, and/or subelements) will appear, in order, between
* the startElement event and the corresponding endElement event.
*
* This interface is similar to the now-deprecated SAX 1.0
* DocumentHandler interface, but it adds support for Namespaces
* and for reporting skipped entities (in non-validating XML
* processors).
*
* Implementors should note that there is also a
* ContentHandler class in the java.net
* package; that means that it's probably a bad idea to do
*
* import java.net.*;
* import org.xml.sax.*;
*
*
* In fact, "import ...*" is usually a sign of sloppy programming
* anyway, so the user should consider this a feature rather than a
* bug.
*
* @since SAX 2.0
* @author David Megginson
* @version 2.0.1+ (sax2r3pre1)
* @see org.xml.sax.XMLReader
* @see org.xml.sax.DTDHandler
* @see org.xml.sax.ErrorHandler
*/
public interface ContentHandler
{
/**
* 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
* {@link #startDocument startDocument} returns and before
* {@link #endDocument endDocument} is called. The
* application should not attempt to use it at any other time.
*
* @param locator an object that can return the location of
* any SAX document event
* @see org.xml.sax.Locator
*/
public void setDocumentLocator (Locator locator);
/**
* Receive notification of the beginning of a document.
*
* The SAX parser will invoke this method only once, before any
* other event callbacks (except for {@link #setDocumentLocator
* setDocumentLocator}).
*
* @throws org.xml.sax.SAXException any SAX exception, possibly
* wrapping another exception
* @see #endDocument
*/
public void startDocument ()
throws SAXException;
/**
* Receive notification of the end of a document.
*
* There is an apparent contradiction between the
* documentation for this method and the documentation for {@link
* org.xml.sax.ErrorHandler#fatalError}. Until this ambiguity is
* resolved in a future major release, clients should make no
* assumptions about whether endDocument() will or will not be
* invoked when the parser has reported a fatalError() or thrown
* an exception.
*
* 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.
*
* @throws org.xml.sax.SAXException any SAX exception, possibly
* wrapping another exception
* @see #startDocument
*/
public void endDocument()
throws SAXException;
/**
* 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 {@link #startElement startElement} event,
* and all {@link #endPrefixMapping endPrefixMapping}
* events will occur immediately after the corresponding
* {@link #endElement 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.
*
* @param prefix the Namespace prefix being declared.
* An empty string is used for the default element namespace,
* which has no prefix.
* @param uri the Namespace URI the prefix is mapped to
* @throws org.xml.sax.SAXException the client may throw
* an exception during processing
* @see #endPrefixMapping
* @see #startElement
*/
public void startPrefixMapping (String prefix, String uri)
throws SAXException;
/**
* End the scope of a prefix-URI mapping.
*
* See {@link #startPrefixMapping startPrefixMapping} for
* details. These events will always occur immediately after the
* corresponding {@link #endElement endElement} event, but the order of
* {@link #endPrefixMapping endPrefixMapping} events is not otherwise
* guaranteed.
*
* @param prefix the prefix that was being mapped.
* This is the empty string when a default mapping scope ends.
* @throws org.xml.sax.SAXException the client may throw
* an exception during processing
* @see #startPrefixMapping
* @see #endElement
*/
public void endPrefixMapping (String prefix)
throws SAXException;
/**
* 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
* {@link #endElement 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:
*
*
* - the Namespace URI;
* - the local name; and
* - 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 {@link #characters characters()}, attribute values may have
* characters that need more than one char value.
*
* @param uri the Namespace URI, or the empty string if the
* element has no Namespace URI or if Namespace
* processing is not being performed
* @param localName the local name (without prefix), or the
* empty string if Namespace processing is not being
* performed
* @param qName the qualified name (with prefix), or the
* empty string if qualified names are not available
* @param atts the attributes attached to the element. If
* there are no attributes, it shall be an empty
* Attributes object. The value of this object after
* startElement returns is undefined
* @throws org.xml.sax.SAXException any SAX exception, possibly
* wrapping another exception
* @see #endElement
* @see org.xml.sax.Attributes
* @see org.xml.sax.helpers.AttributesImpl
*/
public void startElement (String uri, String localName,
String qName, Attributes atts)
throws SAXException;
/**
* 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
* {@link #startElement startElement} event for every endElement
* event (even when the element is empty).
*
* For information on the names, see startElement.
*
* @param uri the Namespace URI, or the empty string if the
* element has no Namespace URI or if Namespace
* processing is not being performed
* @param localName the local name (without prefix), or the
* empty string if Namespace processing is not being
* performed
* @param qName the qualified XML name (with prefix), or the
* empty string if qualified names are not available
* @throws org.xml.sax.SAXException any SAX exception, possibly
* wrapping another exception
*/
public void endElement (String uri, String localName,
String qName)
throws SAXException;
/**
* 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 Java
* char value. There are two 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.
*
* 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 Java code
* manipulates internationalized text; the issue isn't unique to XML.
*
* Note that some parsers will report whitespace in element
* content using the {@link #ignorableWhitespace ignorableWhitespace}
* method rather than this one (validating parsers must
* do so).
*
* @param ch the characters from the XML document
* @param start the start position in the array
* @param length the number of characters to read from the array
* @throws org.xml.sax.SAXException any SAX exception, possibly
* wrapping another exception
* @see #ignorableWhitespace
* @see org.xml.sax.Locator
*/
public void characters (char ch[], int start, int length)
throws SAXException;
/**
* 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.
*
* @param ch the characters from the XML document
* @param start the start position in the array
* @param length the number of characters to read from the array
* @throws org.xml.sax.SAXException any SAX exception, possibly
* wrapping another exception
* @see #characters
*/
public void ignorableWhitespace (char ch[], int start, int length)
throws SAXException;
/**
* 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 {@link #characters characters()}, processing instruction
* data may have characters that need more than one char
* value.
*
* @param target the processing instruction target
* @param data the processing instruction data, or null if
* none was supplied. The data does not include any
* whitespace separating it from the target
* @throws org.xml.sax.SAXException any SAX exception, possibly
* wrapping another exception
*/
public void processingInstruction (String target, String data)
throws SAXException;
/**
* 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.
*
* @param name the name of the skipped entity. If it is a
* parameter entity, the name will begin with '%', and if
* it is the external DTD subset, it will be the string
* "[dtd]"
* @throws org.xml.sax.SAXException any SAX exception, possibly
* wrapping another exception
*/
public void skippedEntity (String name)
throws SAXException;
}
// end of ContentHandler.java