Package org.apache.tika.parser.microsoft

Class OutlookExtractor

java.lang.Object
org.apache.tika.parser.microsoft.OutlookExtractor
public class OutlookExtractor extends Object
Outlook Message Parser.

  • Nested Class Summary

    Nested Classes
    Modifier and Type
    Class
    Description
    static enum 
    OutlookExtractor.RECIPIENT_TYPE
     

  • Field Summary

    Fields
    Modifier and Type
    Field
    Description
    protected final org.apache.tika.parser.ParseContext
    context
     
    protected final OfficeParserConfig
    officeParserConfig
     
    protected final org.apache.tika.metadata.Metadata
    parentMetadata
     

  • Constructor Summary

    Constructors
    Constructor
    Description
    OutlookExtractor(org.apache.poi.poifs.filesystem.DirectoryNode root, org.apache.tika.metadata.Metadata metadata, org.apache.tika.parser.ParseContext context)
     
    OutlookExtractor(org.apache.poi.poifs.filesystem.DirectoryNode root, org.apache.tika.parser.ParseContext context)
    Deprecated.
    use OutlookExtractor(DirectoryNode, Metadata, ParseContext) Will be removed after 2.4.0
    OutlookExtractor(org.apache.poi.poifs.filesystem.POIFSFileSystem filesystem, org.apache.tika.parser.ParseContext context)
    Deprecated.
    use OutlookExtractor(DirectoryNode, Metadata, ParseContext) Will be removed after 2.4.0

  • Method Summary

    Modifier and Type
    Method
    Description
    static void
    addEvenIfNull(org.apache.tika.metadata.Property property, String value, org.apache.tika.metadata.Metadata metadata)
     
    protected org.apache.tika.detect.Detector
    getDetector()
     
    static String
    getMessageClass(String messageClass)
     
    protected org.apache.tika.mime.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 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.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)
     
    void
    parse(org.apache.tika.sax.XHTMLContentHandler xhtml)
     
    void
    parse(org.apache.tika.sax.XHTMLContentHandler xhtml, org.apache.tika.metadata.Metadata metadata)
    Deprecated.
    use {@link #parse(XHTMLContentHandler), will be removed after 2.4.0}

    Methods inherited from class java.lang.Object

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

  • Field Details

    • parentMetadata

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

    • officeParserConfig

      protected final OfficeParserConfig officeParserConfig

    • context

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

  • Constructor Details

    • OutlookExtractor

      @Deprecated public OutlookExtractor(org.apache.poi.poifs.filesystem.POIFSFileSystem filesystem, org.apache.tika.parser.ParseContext context) throws org.apache.tika.exception.TikaException
      Deprecated.
      use OutlookExtractor(DirectoryNode, Metadata, ParseContext) Will be removed after 2.4.0
      Parameters:
      filesystem -
      context -
      Throws:
      org.apache.tika.exception.TikaException

    • OutlookExtractor

      @Deprecated public OutlookExtractor(org.apache.poi.poifs.filesystem.DirectoryNode root, org.apache.tika.parser.ParseContext context) throws org.apache.tika.exception.TikaException
      Deprecated.
      use OutlookExtractor(DirectoryNode, Metadata, ParseContext) Will be removed after 2.4.0
      Parameters:
      root -
      context -
      Throws:
      org.apache.tika.exception.TikaException

    • OutlookExtractor

      public OutlookExtractor(org.apache.poi.poifs.filesystem.DirectoryNode root, org.apache.tika.metadata.Metadata metadata, org.apache.tika.parser.ParseContext context) throws org.apache.tika.exception.TikaException
      Throws:
      org.apache.tika.exception.TikaException

  • Method Details

    • addEvenIfNull

      public static void addEvenIfNull(org.apache.tika.metadata.Property property, String value, org.apache.tika.metadata.Metadata metadata)

    • getMessageClass

      public static String getMessageClass(String messageClass)

    • parse

      public void parse(org.apache.tika.sax.XHTMLContentHandler xhtml) throws org.apache.tika.exception.TikaException, SAXException, IOException
      Throws:
      org.apache.tika.exception.TikaException
      SAXException
      IOException

    • parse

      @Deprecated public void parse(org.apache.tika.sax.XHTMLContentHandler xhtml, org.apache.tika.metadata.Metadata metadata) throws org.apache.tika.exception.TikaException, SAXException, IOException
      Deprecated.
      use {@link #parse(XHTMLContentHandler), will be removed after 2.4.0}
      Parameters:
      xhtml -
      metadata -
      Throws:
      org.apache.tika.exception.TikaException
      SAXException
      IOException

    • getTikaConfig

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

    • getDetector

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

    • getMimeTypes

      protected org.apache.tika.mime.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(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