Added a mediafilter to extract text from Word/PowerPoint/Excel includ…

…ing their XML format

dspace-api/src/main/java/org/dspace/app/mediafilter/MSOfficeFilter.java

@@ -0,0 +1,112 @@
+/**
+ * The contents of this file are subject to the license and copyright
+ * detailed in the LICENSE and NOTICE files at the root of the source
+ * tree and available online at
+ *
+ * http://www.dspace.org/license/
+ */
+package org.dspace.app.mediafilter;
+
+import java.io.ByteArrayInputStream;
+import java.io.InputStream;
+import java.io.IOException;
+
+import org.apache.log4j.Logger;
+
+import org.apache.poi.POITextExtractor;
+import org.apache.poi.extractor.ExtractorFactory;
+import org.apache.poi.hslf.extractor.PowerPointExtractor;
+import org.apache.poi.xslf.extractor.XSLFPowerPointExtractor;
+
+/*
+ * 
+ * to do: helpful error messages - can't find mediafilter.cfg - can't
+ * instantiate filter - bitstream format doesn't exist.
+ *  
+ */
+public class MSOfficeFilter extends MediaFilter
+{
+
+    private static Logger log = Logger.getLogger(MSOfficeFilter.class);
+
+    public String getFilteredName(String oldFilename)
+    {
+        return oldFilename + ".txt";
+    }
+
+    /**
+     * @return String bundle name
+     *  
+     */
+    public String getBundleName()
+    {
+        return "TEXT";
+    }
+
+    /**
+     * @return String bitstreamformat
+     */
+    public String getFormatString()
+    {
+        return "Text";
+    }
+
+    /**
+     * @return String description
+     */
+    public String getDescription()
+    {
+        return "Extracted text";
+    }
+
+    /**
+     * @param source
+     *            source input stream
+     * 
+     * @return InputStream the resulting input stream
+     */
+    public InputStream getDestinationStream(InputStream source)
+            throws Exception
+    {
+        // get input stream from bitstream
+        // pass to filter, get string back
+        try  
+        {
+            String extractedText;
+            POITextExtractor extractor = ExtractorFactory.createExtractor(source);
+            if (extractor instanceof PowerPointExtractor)
+            {
+                extractedText = ((PowerPointExtractor) extractor)
+                        .getText(true, true);
+            }
+            else if (extractor instanceof XSLFPowerPointExtractor)
+            {
+                extractedText = ((XSLFPowerPointExtractor) extractor)
+                        .getText(true, true);
+            }
+            else
+            {
+                extractedText = extractor.getText();
+            }
+
+            // if verbose flag is set, print out extracted text
+            // to STDOUT
+            if (MediaFilterManager.isVerbose)
+            {
+                System.out.println(extractedText);
+            }
+
+            // generate an input stream with the extracted text
+            byte[] textBytes = extractedText.getBytes();
+            ByteArrayInputStream bais = new ByteArrayInputStream(textBytes);
+
+            return bais; // will this work? or will the byte array be out of scope?
+        } 
+        catch (Exception e)
+        {
+            System.out.println("MSOfficeFilter Exception");
+            log.error("Error detected : " + e.getMessage(), e);
+            throw e;
+        }
+    }
+}

dspace/config/dspace.cfg

@@ -431,26 +431,23 @@ http.proxy.port = ${http.proxy.port}
 
 #Names of the enabled MediaFilter or FormatFilter plugins
 filter.plugins = PDF Text Extractor, HTML Text Extractor, \
-                                 PowerPoint Text Extractor, \
-                                 Word Text Extractor, JPEG Thumbnail
+                 MSOffice Text Extractor, JPEG Thumbnail
 # [To enable Branded Preview]: remove last line above, and uncomment 2 lines below
-#                        Word Text Extractor, JPEG Thumbnail, \
-#                        Branded Preview JPEG
+#                MSOffice Text Extractor, JPEG Thumbnail, \
+#                Branded Preview JPEG
 
 #Assign 'human-understandable' names to each filter
 plugin.named.org.dspace.app.mediafilter.FormatFilter = \
   org.dspace.app.mediafilter.PDFFilter = PDF Text Extractor, \
   org.dspace.app.mediafilter.HTMLFilter = HTML Text Extractor, \
-  org.dspace.app.mediafilter.WordFilter = Word Text Extractor, \
-  org.dspace.app.mediafilter.PowerPointFilter = PowerPoint Text Extractor, \
+  org.dspace.app.mediafilter.MSOfficeFilter = MSOffice Text Extractor, \
   org.dspace.app.mediafilter.JPEGFilter = JPEG Thumbnail, \
   org.dspace.app.mediafilter.BrandedPreviewJPEGFilter = Branded Preview JPEG
 
 #Configure each filter's input format(s)
 filter.org.dspace.app.mediafilter.PDFFilter.inputFormats = Adobe PDF
 filter.org.dspace.app.mediafilter.HTMLFilter.inputFormats = HTML, Text
-filter.org.dspace.app.mediafilter.WordFilter.inputFormats = Microsoft Word
-filter.org.dspace.app.mediafilter.PowerPointFilter.inputFormats = Microsoft Powerpoint, Microsoft Powerpoint XML
+filter.org.dspace.app.mediafilter.MSOfficeFilter.inputFormats = Microsoft Word, Microsoft Word XML, Microsoft Powerpoint, Microsoft Powerpoint XML, Microsoft Excel, Microsoft Excel XML
 filter.org.dspace.app.mediafilter.JPEGFilter.inputFormats = BMP, GIF, JPEG, image/png
 filter.org.dspace.app.mediafilter.BrandedPreviewJPEGFilter.inputFormats = BMP, GIF, JPEG, image/png
 

pom.xml

@@ -897,17 +897,17 @@
          <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
-           <version>3.6</version>
+           <version>3.10-FINAL</version>
          </dependency>
          <dependency>
             <groupId>org.apache.poi</groupId>
             <artifactId>poi-scratchpad</artifactId>
-            <version>3.6</version>
+            <version>3.10-FINAL</version>
          </dependency>
          <dependency>
             <groupId>org.apache.poi</groupId>
             <artifactId>poi-ooxml</artifactId>
-            <version>3.6</version>
+            <version>3.10-FINAL</version>
          </dependency>
          <dependency>
             <groupId>rome</groupId>