org.apache.tika.parser.microsoft

Class HSLFExtractor

java.lang.Object

org.apache.tika.parser.microsoft.HSLFExtractor

public class HSLFExtractor
extends Object

Constructor Summary

Constructors

Constructor and Description
HSLFExtractor(ParseContext context)

Method Summary

Methods

Modifier and Type	Method and Description
protected Detector	getDetector()
protected MimeTypes	getMimeTypes()
protected TikaConfig	getTikaConfig()
protected void	handleEmbeddedOfficeDoc(org.apache.poi.poifs.filesystem.DirectoryEntry dir, XHTMLContentHandler xhtml) Handle an office document that's embedded at the POIFS level
protected void	handleEmbeddedResource(TikaInputStream resource, String filename, String relationshipID, String mediaType, XHTMLContentHandler xhtml, boolean outputHtml)
protected void	parse(org.apache.poi.poifs.filesystem.DirectoryNode root, XHTMLContentHandler xhtml)
protected void	parse(org.apache.poi.poifs.filesystem.NPOIFSFileSystem filesystem, XHTMLContentHandler xhtml)

Methods inherited from class java.lang.Object

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

Constructor Detail

HSLFExtractor

public HSLFExtractor(ParseContext context)

Method Detail

parse

protected void parse(org.apache.poi.poifs.filesystem.NPOIFSFileSystem filesystem,
         XHTMLContentHandler xhtml)
              throws IOException,
                     SAXException,
                     TikaException

Throws:

IOException

SAXException

TikaException

parse

protected void parse(org.apache.poi.poifs.filesystem.DirectoryNode root,
         XHTMLContentHandler xhtml)
              throws IOException,
                     SAXException,
                     TikaException

Throws:

IOException

SAXException

TikaException

getTikaConfig

protected TikaConfig getTikaConfig()

getDetector

protected Detector getDetector()

getMimeTypes

protected MimeTypes getMimeTypes()

handleEmbeddedResource

protected void handleEmbeddedResource(TikaInputStream resource,
                          String filename,
                          String relationshipID,
                          String mediaType,
                          XHTMLContentHandler xhtml,
                          boolean outputHtml)
                               throws IOException,
                                      SAXException,
                                      TikaException

Throws:

IOException

SAXException

TikaException

handleEmbeddedOfficeDoc

protected void handleEmbeddedOfficeDoc(org.apache.poi.poifs.filesystem.DirectoryEntry dir,
                           XHTMLContentHandler xhtml)
                                throws IOException,
                                       SAXException,
                                       TikaException

Handle an office document that's embedded at the POIFS level

Throws:

IOException

SAXException

TikaException