Package 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	Description
protected org.apache.tika.parser.ParseContext	context
protected OfficeParserConfig	officeParserConfig
protected org.apache.tika.metadata.Metadata	parentMetadata

Constructor Summary

Constructors

Constructor	Description
HSLFExtractor(org.apache.tika.parser.ParseContext context, org.apache.tika.metadata.Metadata metadata)

Method Summary

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

Methods inherited from class java.lang.Object

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

Field Detail

parentMetadata

protected final org.apache.tika.metadata.Metadata parentMetadata

officeParserConfig

protected final OfficeParserConfig officeParserConfig

context

protected final org.apache.tika.parser.ParseContext context

Constructor Detail

HSLFExtractor

public HSLFExtractor(org.apache.tika.parser.ParseContext context,
                     org.apache.tika.metadata.Metadata metadata)

Method Detail

parse

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

getTikaConfig

protected org.apache.tika.config.TikaConfig getTikaConfig()

getDetector

protected org.apache.tika.detect.Detector getDetector()

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(org.apache.tika.io.TikaInputStream resource,
                                      String filename,
                                      String relationshipID,
                                      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

handleEmbeddedResource

protected void handleEmbeddedResource(org.apache.tika.io.TikaInputStream resource,
                                      String filename,
                                      String relationshipID,
                                      org.apache.poi.hpsf.ClassID storageClassID,
                                      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

handleEmbeddedResource

protected void handleEmbeddedResource(org.apache.tika.io.TikaInputStream resource,
                                      org.apache.tika.metadata.Metadata embeddedMetadata,
                                      String filename,
                                      String relationshipID,
                                      org.apache.poi.hpsf.ClassID storageClassID,
                                      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,
                                       boolean outputHtml)
                                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

handleEmbeddedOfficeDoc

protected void handleEmbeddedOfficeDoc(org.apache.poi.poifs.filesystem.DirectoryEntry dir,
                                       String resourceName,
                                       org.apache.tika.sax.XHTMLContentHandler xhtml,
                                       boolean outputHtml)
                                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

handleEmbeddedOfficeDoc

protected void handleEmbeddedOfficeDoc(org.apache.poi.poifs.filesystem.DirectoryEntry dir,
                                       org.apache.tika.metadata.Metadata metadata,
                                       String resourceName,
                                       org.apache.tika.sax.XHTMLContentHandler xhtml,
                                       boolean outputHtml)
                                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

tryToGetMsgTitle

public static String tryToGetMsgTitle(org.apache.poi.poifs.filesystem.DirectoryEntry node,
                                      String defaultVal)