/** * Checks whether all content within the given HTML element should be discarded instead of * including it in the parse output. Subclasses can override this method to customize the set of * discarded elements. * * @param name HTML element name (upper case) * @return <code>true</code> if content inside the named element should be ignored, <code>false * </code> otherwise * @since Apache Tika 0.5 * @deprecated Use the {@link HtmlMapper} mechanism to customize the HTML mapping. This method * will be removed in Tika 1.0. */ protected boolean isDiscardElement(String name) { return DefaultHtmlMapper.INSTANCE.isDiscardElement(name); }
/** * @deprecated Use the {@link HtmlMapper} mechanism to customize the HTML mapping. This method * will be removed in Tika 1.0. */ public String mapSafeAttribute(String elementName, String attributeName) { return DefaultHtmlMapper.INSTANCE.mapSafeAttribute(elementName, attributeName); }
/** * Maps "safe" HTML element names to semantic XHTML equivalents. If the given element is unknown * or deemed unsafe for inclusion in the parse output, then this method returns <code>null</code> * and the element will be ignored but the content inside it is still processed. See the {@link * #isDiscardElement(String)} method for a way to discard the entire contents of an element. * * <p>Subclasses can override this method to customize the default mapping. * * @param name HTML element name (upper case) * @return XHTML element name (lower case), or <code>null</code> if the element is unsafe * @since Apache Tika 0.5 * @deprecated Use the {@link HtmlMapper} mechanism to customize the HTML mapping. This method * will be removed in Tika 1.0. */ protected String mapSafeElement(String name) { return DefaultHtmlMapper.INSTANCE.mapSafeElement(name); }