org.apache.tika.parser.microsoft
Class HSLFExtractor

java.lang.Object
  org.apache.tika.parser.microsoft.HSLFExtractor

public class HSLFExtractor
extends Object

Constructor Summary

HSLFExtractor(org.apache.tika.parser.ParseContext context)

Method Summary

protected void	handleEmbeddedOfficeDoc(org.apache.poi.poifs.filesystem.DirectoryEntry dir, org.apache.tika.sax.XHTMLContentHandler xhtml) Handle an office document that's embedded at the POIFS level
protected void	handleEmbeddedResource(org.apache.tika.io.TikaInputStream resource, String filename, String mediaType, org.apache.tika.sax.XHTMLContentHandler xhtml, boolean outputHtml)
protected void	parse(org.apache.poi.poifs.filesystem.DirectoryNode root, org.apache.tika.sax.XHTMLContentHandler xhtml)
protected void	parse(org.apache.poi.poifs.filesystem.NPOIFSFileSystem filesystem, org.apache.tika.sax.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(org.apache.tika.parser.ParseContext context)

Method Detail

parse

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

Throws:

IOException

SAXException

org.apache.tika.exception.TikaException

parse

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

Throws:

IOException

SAXException

org.apache.tika.exception.TikaException

handleEmbeddedResource

protected void handleEmbeddedResource(org.apache.tika.io.TikaInputStream resource,
                                      String filename,
                                      String mediaType,
                                      org.apache.tika.sax.XHTMLContentHandler xhtml,
                                      boolean outputHtml)
                               throws IOException,
                                      SAXException,
                                      org.apache.tika.exception.TikaException

Throws:

IOException

SAXException

org.apache.tika.exception.TikaException

handleEmbeddedOfficeDoc

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

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

Throws:

IOException

SAXException

org.apache.tika.exception.TikaException