org.apache.tika.parser.microsoft

Class HSLFExtractor

java.lang.Object

org.apache.tika.parser.microsoft.HSLFExtractor

public class HSLFExtractor
extends Object

Field Summary

Fields

Modifier and Type	Field and Description
protected ParseContext	context
protected OfficeParserConfig	officeParserConfig
protected Metadata	parentMetadata

Constructor Summary

Constructors

Constructor and Description
HSLFExtractor(ParseContext context, Metadata metadata)

Method Summary

Modifier and Type	Method and Description
protected Detector	getDetector()
protected MimeTypes	getMimeTypes() Deprecated. use embeddedDocumentUtil
protected String	getPassword() Returns the password to be used for this file, or null if no / default password should be used
protected TikaConfig	getTikaConfig()
protected void	handleEmbeddedOfficeDoc(org.apache.poi.poifs.filesystem.DirectoryEntry dir, String resourceName, XHTMLContentHandler xhtml, boolean outputHtml) Handle an office document that's embedded at the POIFS level
protected void	handleEmbeddedOfficeDoc(org.apache.poi.poifs.filesystem.DirectoryEntry dir, XHTMLContentHandler xhtml, boolean outputHtml) Handle an office document that's embedded at the POIFS level
protected void	handleEmbeddedResource(TikaInputStream resource, Metadata embeddedMetadata, String filename, String relationshipID, org.apache.poi.hpsf.ClassID storageClassID, String mediaType, XHTMLContentHandler xhtml, boolean outputHtml)
protected void	handleEmbeddedResource(TikaInputStream resource, String filename, String relationshipID, org.apache.poi.hpsf.ClassID storageClassID, String mediaType, XHTMLContentHandler xhtml, boolean outputHtml)
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.POIFSFileSystem filesystem, XHTMLContentHandler xhtml)

Methods inherited from class java.lang.Object

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

Field Detail

parentMetadata

protected final Metadata parentMetadata

officeParserConfig

protected final OfficeParserConfig officeParserConfig

context

protected final ParseContext context

Constructor Detail

HSLFExtractor

public HSLFExtractor(ParseContext context,
                     Metadata metadata)

Method Detail

parse

protected void parse(org.apache.poi.poifs.filesystem.POIFSFileSystem 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()

Deprecated. use embeddedDocumentUtil

Returns:

mimetypes

getPassword

protected String getPassword()

Returns the password to be used for this file, or null if no / default password should be used

handleEmbeddedResource

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

Throws:

IOException

SAXException

TikaException

handleEmbeddedResource

protected void handleEmbeddedResource(TikaInputStream resource,
                                      String filename,
                                      String relationshipID,
                                      org.apache.poi.hpsf.ClassID storageClassID,
                                      String mediaType,
                                      XHTMLContentHandler xhtml,
                                      boolean outputHtml)
                               throws IOException,
                                      SAXException,
                                      TikaException

Throws:

IOException

SAXException

TikaException

handleEmbeddedResource

protected void handleEmbeddedResource(TikaInputStream resource,
                                      Metadata embeddedMetadata,
                                      String filename,
                                      String relationshipID,
                                      org.apache.poi.hpsf.ClassID storageClassID,
                                      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,
                                       boolean outputHtml)
                                throws IOException,
                                       SAXException,
                                       TikaException

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

Throws:

IOException

SAXException

TikaException

handleEmbeddedOfficeDoc

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

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

Throws:

IOException

SAXException

TikaException