org.apache.tika.parser.microsoft
Class OutlookExtractor

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

public class OutlookExtractor
extends Object

Outlook Message Parser.

Constructor Summary

OutlookExtractor(org.apache.poi.poifs.filesystem.DirectoryNode root, ParseContext context)

OutlookExtractor(org.apache.poi.poifs.filesystem.NPOIFSFileSystem filesystem, ParseContext context)

Method Summary

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 mediaType, XHTMLContentHandler xhtml, boolean outputHtml)
void	parse(XHTMLContentHandler xhtml, Metadata metadata)

Methods inherited from class java.lang.Object

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

Constructor Detail

OutlookExtractor

public OutlookExtractor(org.apache.poi.poifs.filesystem.NPOIFSFileSystem filesystem,
                        ParseContext context)
                 throws TikaException

Throws:

TikaException

OutlookExtractor

public OutlookExtractor(org.apache.poi.poifs.filesystem.DirectoryNode root,
                        ParseContext context)
                 throws TikaException

Throws:

TikaException

Method Detail

parse

public void parse(XHTMLContentHandler xhtml,
                  Metadata metadata)
           throws TikaException,
                  SAXException,
                  IOException

Throws:

TikaException

SAXException

IOException

getTikaConfig

protected TikaConfig getTikaConfig()

getDetector

protected Detector getDetector()

getMimeTypes

protected MimeTypes getMimeTypes()

handleEmbeddedResource

protected void handleEmbeddedResource(TikaInputStream resource,
                                      String filename,
                                      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