Docjar: A Java Source and Docuemnt Enginecom.*    java.*    javax.*    org.*    all    new    plug-in

Quick Search    Search Deep

gnu.xml.dom.ls
Class SAXEventSink  view SAXEventSink download SAXEventSink.java

java.lang.Object
  extended bygnu.xml.dom.ls.SAXEventSink
All Implemented Interfaces:
org.xml.sax.ContentHandler, org.xml.sax.ext.DeclHandler, org.xml.sax.DTDHandler, org.xml.sax.ext.LexicalHandler
Direct Known Subclasses:
FilteredSAXEventSink

class SAXEventSink
extends java.lang.Object
implements org.xml.sax.ContentHandler, org.xml.sax.ext.LexicalHandler, org.xml.sax.DTDHandler, org.xml.sax.ext.DeclHandler

A SAX content and lexical handler used to construct a DOM document.


Field Summary
(package private)  boolean coalescing
           
(package private)  org.w3c.dom.Node ctx
           
(package private)  gnu.xml.dom.DomDocument doc
           
(package private)  java.util.LinkedList entityCtx
           
(package private)  boolean expandEntityReferences
           
(package private)  boolean ignoreComments
           
(package private)  boolean ignoreWhitespace
           
(package private)  boolean inCDATA
           
(package private)  boolean inDTD
           
(package private)  boolean interrupted
           
(package private)  org.xml.sax.Locator locator
           
(package private)  boolean namespaceAware
           
(package private)  java.util.List pending
           
private static java.util.HashSet PREDEFINED_ENTITIES
           
(package private)  org.xml.sax.XMLReader reader
           
private static java.lang.String XMLNS_PREFIX
           
private static java.lang.String XMLNS_URI
           
 
Constructor Summary
(package private) SAXEventSink()
           
 
Method Summary
 void attributeDecl(java.lang.String eName, java.lang.String aName, java.lang.String type, java.lang.String mode, java.lang.String value)
          Report an attribute type declaration.
 void characters(char[] c, int off, int len)
          Receive notification of character data.
 void comment(char[] c, int off, int len)
          Report an XML comment anywhere in the document.
protected  org.w3c.dom.Attr createAttr(org.xml.sax.Attributes atts, int index)
           
protected  org.w3c.dom.Node createComment(char[] c, int off, int len)
           
protected  org.w3c.dom.Node createDocumentType(java.lang.String name, java.lang.String publicId, java.lang.String systemId)
           
protected  org.w3c.dom.Element createElement(java.lang.String uri, java.lang.String localName, java.lang.String qName, org.xml.sax.Attributes atts)
           
protected  org.w3c.dom.Node createProcessingInstruction(java.lang.String target, java.lang.String data)
           
protected  org.w3c.dom.Text createText(char[] c, int off, int len)
           
 void elementDecl(java.lang.String name, java.lang.String model)
          Report an element type declaration.
 void endCDATA()
          Report the end of a CDATA section.
 void endDocument()
          Receive notification of the end of a document.
 void endDTD()
          Report the end of DTD declarations.
 void endElement(java.lang.String uri, java.lang.String localName, java.lang.String qName)
          Receive notification of the end of an element.
 void endEntity(java.lang.String name)
          Report the end of an entity.
 void endPrefixMapping(java.lang.String prefix)
          End the scope of a prefix-URI mapping.
 void externalEntityDecl(java.lang.String name, java.lang.String publicId, java.lang.String systemId)
          Report a parsed external entity declaration.
 void ignorableWhitespace(char[] c, int off, int len)
          Receive notification of ignorable whitespace in element content.
 void internalEntityDecl(java.lang.String name, java.lang.String value)
          Report an internal entity declaration.
(package private)  void interrupt()
           
 void notationDecl(java.lang.String name, java.lang.String publicId, java.lang.String systemId)
          Receive notification of a notation declaration event.
 void processingInstruction(java.lang.String target, java.lang.String data)
          Receive notification of a processing instruction.
 void setDocumentLocator(org.xml.sax.Locator locator)
          Receive an object for locating the origin of SAX document events.
 void skippedEntity(java.lang.String name)
          Receive notification of a skipped entity.
 void startCDATA()
          Report the start of a CDATA section.
 void startDocument()
          Receive notification of the beginning of a document.
 void startDTD(java.lang.String name, java.lang.String publicId, java.lang.String systemId)
          Report the start of DTD declarations, if any.
 void startElement(java.lang.String uri, java.lang.String localName, java.lang.String qName, org.xml.sax.Attributes atts)
          Receive notification of the beginning of an element.
 void startEntity(java.lang.String name)
          Report the beginning of some internal and external XML entities.
 void startPrefixMapping(java.lang.String prefix, java.lang.String uri)
          Begin the scope of a prefix-URI Namespace mapping.
 void unparsedEntityDecl(java.lang.String name, java.lang.String publicId, java.lang.String systemId, java.lang.String notationName)
          Receive notification of an unparsed entity declaration event.
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

XMLNS_URI

private static final java.lang.String XMLNS_URI
See Also:
Constant Field Values

XMLNS_PREFIX

private static final java.lang.String XMLNS_PREFIX
See Also:
Constant Field Values

PREDEFINED_ENTITIES

private static final java.util.HashSet PREDEFINED_ENTITIES

namespaceAware

boolean namespaceAware

ignoreWhitespace

boolean ignoreWhitespace

expandEntityReferences

boolean expandEntityReferences

ignoreComments

boolean ignoreComments

coalescing

boolean coalescing

reader

org.xml.sax.XMLReader reader

doc

gnu.xml.dom.DomDocument doc

ctx

org.w3c.dom.Node ctx

entityCtx

java.util.LinkedList entityCtx

pending

java.util.List pending

locator

org.xml.sax.Locator locator

inCDATA

boolean inCDATA

inDTD

boolean inDTD

interrupted

boolean interrupted
Constructor Detail

SAXEventSink

SAXEventSink()
Method Detail

interrupt

void interrupt()

setDocumentLocator

public void setDocumentLocator(org.xml.sax.Locator locator)
Description copied from interface: org.xml.sax.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 startDocument 55 returns and before endDocument 55 is called. The application should not attempt to use it at any other time.

Specified by:
setDocumentLocator in interface org.xml.sax.ContentHandler

startDocument

public void startDocument()
                   throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ContentHandler
Receive notification of the beginning of a document.

The SAX parser will invoke this method only once, before any other event callbacks (except for setDocumentLocator 55 ).

Specified by:
startDocument in interface org.xml.sax.ContentHandler

endDocument

public void endDocument()
                 throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ContentHandler
Receive notification of the end of a document.

There is an apparent contradiction between the documentation for this method and the documentation for ErrorHandler.fatalError(org.xml.sax.SAXParseException)>ErrorHandler.fatalError(org.xml.sax.SAXParseException) 55 . 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.

Specified by:
endDocument in interface org.xml.sax.ContentHandler

startPrefixMapping

public void startPrefixMapping(java.lang.String prefix,
                               java.lang.String uri)
                        throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ContentHandler
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 55 event, and all endPrefixMapping 55 events will occur immediately after the corresponding endElement 55 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.

Specified by:
startPrefixMapping in interface org.xml.sax.ContentHandler

endPrefixMapping

public void endPrefixMapping(java.lang.String prefix)
                      throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ContentHandler
End the scope of a prefix-URI mapping.

See startPrefixMapping 55 for details. These events will always occur immediately after the corresponding endElement 55 event, but the order of endPrefixMapping 55 events is not otherwise guaranteed.

Specified by:
endPrefixMapping in interface org.xml.sax.ContentHandler

startElement

public void startElement(java.lang.String uri,
                         java.lang.String localName,
                         java.lang.String qName,
                         org.xml.sax.Attributes atts)
                  throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ContentHandler
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 55 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() 55 , attribute values may have characters that need more than one char value.

Specified by:
startElement in interface org.xml.sax.ContentHandler

createElement

protected org.w3c.dom.Element createElement(java.lang.String uri,
                                            java.lang.String localName,
                                            java.lang.String qName,
                                            org.xml.sax.Attributes atts)
                                     throws org.xml.sax.SAXException

createAttr

protected org.w3c.dom.Attr createAttr(org.xml.sax.Attributes atts,
                                      int index)

endElement

public void endElement(java.lang.String uri,
                       java.lang.String localName,
                       java.lang.String qName)
                throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ContentHandler
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 55 event for every endElement event (even when the element is empty).

For information on the names, see startElement.

Specified by:
endElement in interface org.xml.sax.ContentHandler

characters

public void characters(char[] c,
                       int off,
                       int len)
                throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ContentHandler
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 ignorableWhitespace 55 method rather than this one (validating parsers must do so).

Specified by:
characters in interface org.xml.sax.ContentHandler

createText

protected org.w3c.dom.Text createText(char[] c,
                                      int off,
                                      int len)
                               throws org.xml.sax.SAXException

ignorableWhitespace

public void ignorableWhitespace(char[] c,
                                int off,
                                int len)
                         throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ContentHandler
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.

Specified by:
ignorableWhitespace in interface org.xml.sax.ContentHandler

processingInstruction

public void processingInstruction(java.lang.String target,
                                  java.lang.String data)
                           throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ContentHandler
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() 55 , processing instruction data may have characters that need more than one char value.

Specified by:
processingInstruction in interface org.xml.sax.ContentHandler

createProcessingInstruction

protected org.w3c.dom.Node createProcessingInstruction(java.lang.String target,
                                                       java.lang.String data)

skippedEntity

public void skippedEntity(java.lang.String name)
                   throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ContentHandler
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.

Specified by:
skippedEntity in interface org.xml.sax.ContentHandler

startDTD

public void startDTD(java.lang.String name,
                     java.lang.String publicId,
                     java.lang.String systemId)
              throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.LexicalHandler
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 55 events. Declarations are assumed to belong to the internal DTD subset unless they appear between startEntity 55 and endEntity 55 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 55 event.

Specified by:
startDTD in interface org.xml.sax.ext.LexicalHandler

createDocumentType

protected org.w3c.dom.Node createDocumentType(java.lang.String name,
                                              java.lang.String publicId,
                                              java.lang.String systemId)

endDTD

public void endDTD()
            throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.LexicalHandler
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.

Specified by:
endDTD in interface org.xml.sax.ext.LexicalHandler

startEntity

public void startEntity(java.lang.String name)
                 throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.LexicalHandler
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 55 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.

Specified by:
startEntity in interface org.xml.sax.ext.LexicalHandler

endEntity

public void endEntity(java.lang.String name)
               throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.LexicalHandler
Report the end of an entity.

Specified by:
endEntity in interface org.xml.sax.ext.LexicalHandler

startCDATA

public void startCDATA()
                throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.LexicalHandler
Report the start of a CDATA section.

The contents of the CDATA section will be reported through the regular characters 55 event; this event is intended only to report the boundary.

Specified by:
startCDATA in interface org.xml.sax.ext.LexicalHandler

endCDATA

public void endCDATA()
              throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.LexicalHandler
Report the end of a CDATA section.

Specified by:
endCDATA in interface org.xml.sax.ext.LexicalHandler

comment

public void comment(char[] c,
                    int off,
                    int len)
             throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.LexicalHandler
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).

Specified by:
comment in interface org.xml.sax.ext.LexicalHandler

createComment

protected org.w3c.dom.Node createComment(char[] c,
                                         int off,
                                         int len)

notationDecl

public void notationDecl(java.lang.String name,
                         java.lang.String publicId,
                         java.lang.String systemId)
                  throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.DTDHandler
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.

Specified by:
notationDecl in interface org.xml.sax.DTDHandler

unparsedEntityDecl

public void unparsedEntityDecl(java.lang.String name,
                               java.lang.String publicId,
                               java.lang.String systemId,
                               java.lang.String notationName)
                        throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.DTDHandler
Receive notification of an unparsed entity declaration event.

Note that the notation name corresponds to a notation reported by the notationDecl 55 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.

Specified by:
unparsedEntityDecl in interface org.xml.sax.DTDHandler

elementDecl

public void elementDecl(java.lang.String name,
                        java.lang.String model)
                 throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.DeclHandler
Report an element type declaration.

The content model will consist of the string "EMPTY", the string "ANY", or a parenthesised group, optionally followed by an occurrence indicator. The model will be normalized so that all parameter entities are fully resolved and all whitespace is removed,and will include the enclosing parentheses. Other normalization (such as removing redundant parentheses or simplifying occurrence indicators) is at the discretion of the parser.

Specified by:
elementDecl in interface org.xml.sax.ext.DeclHandler

attributeDecl

public void attributeDecl(java.lang.String eName,
                          java.lang.String aName,
                          java.lang.String type,
                          java.lang.String mode,
                          java.lang.String value)
                   throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.DeclHandler
Report an attribute type declaration.

Only the effective (first) declaration for an attribute will be reported. The type will be one of the strings "CDATA", "ID", "IDREF", "IDREFS", "NMTOKEN", "NMTOKENS", "ENTITY", "ENTITIES", a parenthesized token group with the separator "|" and all whitespace removed, or the word "NOTATION" followed by a space followed by a parenthesized token group with all whitespace removed.

The value will be the value as reported to applications, appropriately normalized and with entity and character references expanded.

Specified by:
attributeDecl in interface org.xml.sax.ext.DeclHandler

internalEntityDecl

public void internalEntityDecl(java.lang.String name,
                               java.lang.String value)
                        throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.DeclHandler
Report an internal entity declaration.

Only the effective (first) declaration for each entity will be reported. All parameter entities in the value will be expanded, but general entities will not.

Specified by:
internalEntityDecl in interface org.xml.sax.ext.DeclHandler

externalEntityDecl

public void externalEntityDecl(java.lang.String name,
                               java.lang.String publicId,
                               java.lang.String systemId)
                        throws org.xml.sax.SAXException
Description copied from interface: org.xml.sax.ext.DeclHandler
Report a parsed external entity declaration.

Only the effective (first) declaration for each entity will be reported.

If the system identifier is a URL, the parser must resolve it fully before passing it to the application.

Specified by:
externalEntityDecl in interface org.xml.sax.ext.DeclHandler