org.egothor.html

Class HTMLPrinter

java.lang.Object

org.cyberneko.html.filters.DefaultFilter

org.egothor.html.HTMLPrinter

All Implemented Interfaces:

org.apache.xerces.xni.parser.XMLComponent, org.apache.xerces.xni.parser.XMLDocumentFilter, org.apache.xerces.xni.parser.XMLDocumentSource, org.apache.xerces.xni.XMLDocumentHandler, org.cyberneko.html.HTMLComponent

public class HTMLPrinter
extends org.cyberneko.html.filters.DefaultFilter

This class reformats HTML documents in our DB to a format that can be used for the science. It was used for a syllable XBW paper.

Field Summary

Fields

Modifier and Type	Field and Description
static String	NOTIFY_CHAR_REFS
static String	NOTIFY_HTML_BUILTIN_REFS

Constructor Summary

Constructors

Constructor and Description
HTMLPrinter(OutputStream outputStream, String encoding)
HTMLPrinter(Writer writer, String encoding, boolean strictScript)

Method Summary

Modifier and Type	Method and Description
void	characters(org.apache.xerces.xni.XMLString text, org.apache.xerces.xni.Augmentations augs)
void	comment(org.apache.xerces.xni.XMLString text, org.apache.xerces.xni.Augmentations augs)
void	emptyElement(org.apache.xerces.xni.QName element, org.apache.xerces.xni.XMLAttributes attributes, org.apache.xerces.xni.Augmentations augs)
void	endElement(org.apache.xerces.xni.QName element, org.apache.xerces.xni.Augmentations augs)
void	endGeneralEntity(String name, org.apache.xerces.xni.Augmentations augs)
static void	filter(String systemId, byte[] file, int file_len, PrintStream ps, String inpEnc, String outEnc)
void	startDocument(org.apache.xerces.xni.XMLLocator locator, String encoding, org.apache.xerces.xni.Augmentations augs)
void	startDocument(org.apache.xerces.xni.XMLLocator locator, String encoding, org.apache.xerces.xni.NamespaceContext nscontext, org.apache.xerces.xni.Augmentations augs)
void	startElement(org.apache.xerces.xni.QName element, org.apache.xerces.xni.XMLAttributes attributes, org.apache.xerces.xni.Augmentations augs)
void	startGeneralEntity(String name, org.apache.xerces.xni.XMLResourceIdentifier id, String encoding, org.apache.xerces.xni.Augmentations augs)

Methods inherited from class org.cyberneko.html.filters.DefaultFilter

doctypeDecl, endCDATA, endDocument, endPrefixMapping, getDocumentHandler, getDocumentSource, getFeatureDefault, getPropertyDefault, getRecognizedFeatures, getRecognizedProperties, ignorableWhitespace, processingInstruction, reset, setDocumentHandler, setDocumentSource, setFeature, setProperty, startCDATA, startPrefixMapping, textDecl, xmlDecl

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

NOTIFY_CHAR_REFS

public static final String NOTIFY_CHAR_REFS

See Also:

Constant Field Values

NOTIFY_HTML_BUILTIN_REFS

public static final String NOTIFY_HTML_BUILTIN_REFS

See Also:

Constant Field Values

Constructor Detail

HTMLPrinter

public HTMLPrinter(OutputStream outputStream,
                   String encoding)
            throws UnsupportedEncodingException

Parameters:

outputStream -

encoding -

Throws:

UnsupportedEncodingException

HTMLPrinter

public HTMLPrinter(Writer writer,
                   String encoding,
                   boolean strictScript)

Parameters:

writer -

encoding -

strictScript -

Method Detail

startDocument

public void startDocument(org.apache.xerces.xni.XMLLocator locator,
                          String encoding,
                          org.apache.xerces.xni.NamespaceContext nscontext,
                          org.apache.xerces.xni.Augmentations augs)
                   throws org.apache.xerces.xni.XNIException

Specified by:

startDocument in interface org.apache.xerces.xni.XMLDocumentHandler

Overrides:

startDocument in class org.cyberneko.html.filters.DefaultFilter

Parameters:

locator -

encoding -

nscontext -

augs -

Throws:

org.apache.xerces.xni.XNIException

startDocument

public void startDocument(org.apache.xerces.xni.XMLLocator locator,
                          String encoding,
                          org.apache.xerces.xni.Augmentations augs)
                   throws org.apache.xerces.xni.XNIException

Overrides:

startDocument in class org.cyberneko.html.filters.DefaultFilter

Parameters:

locator -

encoding -

augs -

Throws:

org.apache.xerces.xni.XNIException

comment

public void comment(org.apache.xerces.xni.XMLString text,
                    org.apache.xerces.xni.Augmentations augs)
             throws org.apache.xerces.xni.XNIException

Specified by:

comment in interface org.apache.xerces.xni.XMLDocumentHandler

Overrides:

comment in class org.cyberneko.html.filters.DefaultFilter

Parameters:

text -

augs -

Throws:

org.apache.xerces.xni.XNIException

startElement

public void startElement(org.apache.xerces.xni.QName element,
                         org.apache.xerces.xni.XMLAttributes attributes,
                         org.apache.xerces.xni.Augmentations augs)
                  throws org.apache.xerces.xni.XNIException

Specified by:

startElement in interface org.apache.xerces.xni.XMLDocumentHandler

Overrides:

startElement in class org.cyberneko.html.filters.DefaultFilter

Parameters:

element -

attributes -

augs -

Throws:

org.apache.xerces.xni.XNIException

emptyElement

public void emptyElement(org.apache.xerces.xni.QName element,
                         org.apache.xerces.xni.XMLAttributes attributes,
                         org.apache.xerces.xni.Augmentations augs)
                  throws org.apache.xerces.xni.XNIException

Specified by:

emptyElement in interface org.apache.xerces.xni.XMLDocumentHandler

Overrides:

emptyElement in class org.cyberneko.html.filters.DefaultFilter

Parameters:

element -

attributes -

augs -

Throws:

org.apache.xerces.xni.XNIException

characters

public void characters(org.apache.xerces.xni.XMLString text,
                       org.apache.xerces.xni.Augmentations augs)
                throws org.apache.xerces.xni.XNIException

Specified by:

characters in interface org.apache.xerces.xni.XMLDocumentHandler

Overrides:

characters in class org.cyberneko.html.filters.DefaultFilter

Parameters:

text -

augs -

Throws:

org.apache.xerces.xni.XNIException

endElement

public void endElement(org.apache.xerces.xni.QName element,
                       org.apache.xerces.xni.Augmentations augs)
                throws org.apache.xerces.xni.XNIException

Specified by:

endElement in interface org.apache.xerces.xni.XMLDocumentHandler

Overrides:

endElement in class org.cyberneko.html.filters.DefaultFilter

Parameters:

element -

augs -

Throws:

org.apache.xerces.xni.XNIException

startGeneralEntity

public void startGeneralEntity(String name,
                               org.apache.xerces.xni.XMLResourceIdentifier id,
                               String encoding,
                               org.apache.xerces.xni.Augmentations augs)
                        throws org.apache.xerces.xni.XNIException

Specified by:

startGeneralEntity in interface org.apache.xerces.xni.XMLDocumentHandler

Overrides:

startGeneralEntity in class org.cyberneko.html.filters.DefaultFilter

Parameters:

name -

id -

encoding -

augs -

Throws:

org.apache.xerces.xni.XNIException

endGeneralEntity

public void endGeneralEntity(String name,
                             org.apache.xerces.xni.Augmentations augs)
                      throws org.apache.xerces.xni.XNIException

Specified by:

endGeneralEntity in interface org.apache.xerces.xni.XMLDocumentHandler

Overrides:

endGeneralEntity in class org.cyberneko.html.filters.DefaultFilter

Parameters:

name -

augs -

Throws:

org.apache.xerces.xni.XNIException

filter

public static void filter(String systemId,
                          byte[] file,
                          int file_len,
                          PrintStream ps,
                          String inpEnc,
                          String outEnc)
                   throws Exception

Parameters:

systemId -

file -

file_len -

ps -

inpEnc -

outEnc -

Throws:

Exception