|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: INNER | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object | +--org.apache.xerces.util.ParserConfigurationSettings | +--org.cyberneko.html.HTMLConfiguration
An XNI-based parser configuration that can be used to parse HTML documents. This configuration can be used directly in order to parse HTML documents or can be used in conjunction with any XNI based tools, such as the Xerces2 implementation.
This configuration recognizes the following features:
This configuration recognizes the following properties:
For complete usage information, refer to the documentation.
HTMLScanner
,
HTMLTagBalancer
,
HTMLErrorReporter
Inner Class Summary | |
protected class |
HTMLConfiguration.ErrorReporter
Defines an error reporter for reporting HTML errors. |
Field Summary | |
protected static java.lang.String |
AUGMENTATIONS
Include infoset augmentations. |
protected static java.lang.String |
BALANCE_TAGS
Balance tags. |
protected static java.lang.String |
ERROR_DOMAIN
Error domain. |
protected static java.lang.String |
ERROR_REPORTER
Error reporter. |
protected org.apache.xerces.xni.XMLDocumentHandler |
fDocumentHandler
Document handler. |
protected HTMLScanner |
fDocumentScanner
Document scanner. |
protected org.apache.xerces.xni.XMLDTDContentModelHandler |
fDTDContentModelHandler
DTD content model handler. |
protected org.apache.xerces.xni.XMLDTDHandler |
fDTDHandler
DTD handler. |
protected org.apache.xerces.xni.parser.XMLEntityResolver |
fEntityResolver
Entity resolver. |
protected org.apache.xerces.xni.parser.XMLErrorHandler |
fErrorHandler
Error handler. |
protected HTMLErrorReporter |
fErrorReporter
Error reporter. |
protected java.util.Vector |
fHTMLComponents
Components. |
protected static java.lang.String |
FILTERS
Pipeline filters. |
protected java.util.Locale |
fLocale
Locale. |
protected HTMLTagBalancer |
fTagBalancer
HTML tag balancer. |
protected static java.lang.String |
NAMES_ATTRS
Modify HTML attribute names: { "upper", "lower", "default" }. |
protected static java.lang.String |
NAMES_ELEMS
Modify HTML element names: { "upper", "lower", "default" }. |
protected static java.lang.String |
REPORT_ERRORS
Report errors. |
protected static java.lang.String |
SIMPLE_ERROR_FORMAT
Simple report format. |
protected static boolean |
XERCES_2_0_0
Parser version is Xerces 2.0.0. |
protected static boolean |
XERCES_2_0_1
Parser version is Xerces 2.0.1. |
Fields inherited from class org.apache.xerces.util.ParserConfigurationSettings |
fFeatures, fParentSettings, fProperties, fRecognizedFeatures, fRecognizedProperties |
Constructor Summary | |
HTMLConfiguration()
Default constructor. |
Method Summary | |
protected void |
addComponent(HTMLComponent component)
Adds a component. |
org.apache.xerces.xni.XMLDocumentHandler |
getDocumentHandler()
Returns the document handler. |
org.apache.xerces.xni.XMLDTDContentModelHandler |
getDTDContentModelHandler()
Returns the DTD content model handler. |
org.apache.xerces.xni.XMLDTDHandler |
getDTDHandler()
Returns the DTD handler. |
org.apache.xerces.xni.parser.XMLEntityResolver |
getEntityResolver()
Returns the entity resolver. |
org.apache.xerces.xni.parser.XMLErrorHandler |
getErrorHandler()
Returns the error handler. |
java.util.Locale |
getLocale()
Returns the locale. |
void |
parse(org.apache.xerces.xni.parser.XMLInputSource source)
Parses a document. |
void |
pushInputSource(org.apache.xerces.xni.parser.XMLInputSource inputSource)
Pushes an input source onto the current entity stack. |
protected void |
reset()
Resets the parser configuration. |
void |
setDocumentHandler(org.apache.xerces.xni.XMLDocumentHandler handler)
Sets the document handler. |
void |
setDTDContentModelHandler(org.apache.xerces.xni.XMLDTDContentModelHandler handler)
Sets the DTD content model handler. |
void |
setDTDHandler(org.apache.xerces.xni.XMLDTDHandler handler)
Sets the DTD handler. |
void |
setEntityResolver(org.apache.xerces.xni.parser.XMLEntityResolver resolver)
Sets the entity resolver. |
void |
setErrorHandler(org.apache.xerces.xni.parser.XMLErrorHandler handler)
Sets the error handler. |
void |
setFeature(java.lang.String featureId,
boolean state)
Sets a feature. |
void |
setLocale(java.util.Locale locale)
Sets the locale. |
void |
setProperty(java.lang.String propertyId,
java.lang.Object value)
Sets a property. |
Methods inherited from class org.apache.xerces.util.ParserConfigurationSettings |
addRecognizedFeatures, addRecognizedProperties, checkFeature, checkProperty, getFeature, getProperty |
Methods inherited from class java.lang.Object |
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Methods inherited from interface org.apache.xerces.xni.parser.XMLParserConfiguration |
addRecognizedFeatures, addRecognizedProperties, getFeature, getProperty |
Field Detail |
protected static final java.lang.String AUGMENTATIONS
protected static final java.lang.String REPORT_ERRORS
protected static final java.lang.String SIMPLE_ERROR_FORMAT
protected static final java.lang.String BALANCE_TAGS
protected static final java.lang.String NAMES_ELEMS
protected static final java.lang.String NAMES_ATTRS
protected static final java.lang.String FILTERS
protected static final java.lang.String ERROR_REPORTER
protected static final java.lang.String ERROR_DOMAIN
protected org.apache.xerces.xni.XMLDocumentHandler fDocumentHandler
protected org.apache.xerces.xni.XMLDTDHandler fDTDHandler
protected org.apache.xerces.xni.XMLDTDContentModelHandler fDTDContentModelHandler
protected org.apache.xerces.xni.parser.XMLErrorHandler fErrorHandler
protected org.apache.xerces.xni.parser.XMLEntityResolver fEntityResolver
protected java.util.Locale fLocale
protected java.util.Vector fHTMLComponents
protected HTMLScanner fDocumentScanner
protected HTMLTagBalancer fTagBalancer
protected HTMLErrorReporter fErrorReporter
protected static boolean XERCES_2_0_0
protected static boolean XERCES_2_0_1
Constructor Detail |
public HTMLConfiguration()
Method Detail |
public void pushInputSource(org.apache.xerces.xni.parser.XMLInputSource inputSource)
Note: This functionality is experimental at this time and is subject to change in future releases of NekoHTML.
inputSource
- The new input source to start scanning.public void setFeature(java.lang.String featureId, boolean state) throws org.apache.xerces.xni.parser.XMLConfigurationException
setFeature
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
setFeature
in class org.apache.xerces.util.ParserConfigurationSettings
public void setProperty(java.lang.String propertyId, java.lang.Object value) throws org.apache.xerces.xni.parser.XMLConfigurationException
setProperty
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
setProperty
in class org.apache.xerces.util.ParserConfigurationSettings
public void setDocumentHandler(org.apache.xerces.xni.XMLDocumentHandler handler)
setDocumentHandler
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public org.apache.xerces.xni.XMLDocumentHandler getDocumentHandler()
getDocumentHandler
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public void setDTDHandler(org.apache.xerces.xni.XMLDTDHandler handler)
setDTDHandler
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public org.apache.xerces.xni.XMLDTDHandler getDTDHandler()
getDTDHandler
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public void setDTDContentModelHandler(org.apache.xerces.xni.XMLDTDContentModelHandler handler)
setDTDContentModelHandler
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public org.apache.xerces.xni.XMLDTDContentModelHandler getDTDContentModelHandler()
getDTDContentModelHandler
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public void setErrorHandler(org.apache.xerces.xni.parser.XMLErrorHandler handler)
setErrorHandler
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public org.apache.xerces.xni.parser.XMLErrorHandler getErrorHandler()
getErrorHandler
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public void setEntityResolver(org.apache.xerces.xni.parser.XMLEntityResolver resolver)
setEntityResolver
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public org.apache.xerces.xni.parser.XMLEntityResolver getEntityResolver()
getEntityResolver
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public void setLocale(java.util.Locale locale)
setLocale
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public java.util.Locale getLocale()
getLocale
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
public void parse(org.apache.xerces.xni.parser.XMLInputSource source) throws org.apache.xerces.xni.XNIException, java.io.IOException
parse
in interface org.apache.xerces.xni.parser.XMLParserConfiguration
protected void addComponent(HTMLComponent component)
protected void reset() throws org.apache.xerces.xni.parser.XMLConfigurationException
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: INNER | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |