Package org.apache.tika.parser.microsoft

Class WordExtractor

java.lang.Object

org.apache.tika.parser.microsoft.WordExtractor

public class WordExtractor
extends Object

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	WordExtractor.TagAndStyle

Field Summary

Fields

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

Constructor Summary

Constructors

Constructor	Description
WordExtractor(ParseContext context, Metadata metadata)

Method Summary

Modifier and Type	Method	Description
static WordExtractor.TagAndStyle	buildParagraphTagAndStyle(String styleName, boolean isTable)	Given a style name, return what tag should be used, and what style should be applied to it.
protected Detector	getDetector()
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, Metadata metadata, 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, String filename, String relationshipID, 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, Metadata embeddedMetadata, String filename, String relationshipID, org.apache.poi.hpsf.ClassID storageClassID, 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)
protected void	parseWord6(org.apache.poi.poifs.filesystem.DirectoryNode root, XHTMLContentHandler xhtml)
protected void	parseWord6(org.apache.poi.poifs.filesystem.POIFSFileSystem filesystem, 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 Metadata parentMetadata

officeParserConfig

protected final OfficeParserConfig officeParserConfig

context

protected final ParseContext context

Constructor Detail

WordExtractor

public WordExtractor(ParseContext context,
                     Metadata metadata)

Method Detail

buildParagraphTagAndStyle

public static WordExtractor.TagAndStyle buildParagraphTagAndStyle(String styleName,
                                                                  boolean isTable)

Given a style name, return what tag should be used, and what style should be applied to it.

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

parseWord6

protected void parseWord6(org.apache.poi.poifs.filesystem.POIFSFileSystem filesystem,
                          XHTMLContentHandler xhtml)
                   throws IOException,
                          SAXException,
                          TikaException

Throws:

IOException

SAXException

TikaException

parseWord6

protected void parseWord6(org.apache.poi.poifs.filesystem.DirectoryNode root,
                          XHTMLContentHandler xhtml)
                   throws IOException,
                          SAXException

Throws:

IOException

SAXException

getTikaConfig

protected TikaConfig getTikaConfig()

getDetector

protected 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(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

handleEmbeddedOfficeDoc

protected void handleEmbeddedOfficeDoc(org.apache.poi.poifs.filesystem.DirectoryEntry dir,
                                       Metadata metadata,
                                       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

tryToGetMsgTitle

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