Pull Scratchpad Extractor logic to own class

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1752225 13f79535-47bb-0310-9956-ffa450edef68

src/java/org/apache/poi/extractor/OLE2ExtractorFactory.java

@@ -27,14 +27,12 @@ import org.apache.poi.POIOLE2TextExtractor;
 import org.apache.poi.POITextExtractor;
 import org.apache.poi.hssf.extractor.EventBasedExcelExtractor;
 import org.apache.poi.hssf.extractor.ExcelExtractor;
-import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
 import org.apache.poi.poifs.filesystem.DirectoryEntry;
 import org.apache.poi.poifs.filesystem.DirectoryNode;
 import org.apache.poi.poifs.filesystem.Entry;
 import org.apache.poi.poifs.filesystem.NPOIFSFileSystem;
 import org.apache.poi.poifs.filesystem.OPOIFSFileSystem;
 import org.apache.poi.poifs.filesystem.POIFSFileSystem;
-import org.apache.xmlbeans.XmlException;
 
 /**
  * Figures out the correct POIOLE2TextExtractor for your supplied
@@ -104,15 +102,15 @@ public class OLE2ExtractorFactory {
         return threadPreferEventExtractors.get();
     }
 
-    public static POIOLE2TextExtractor createExtractor(POIFSFileSystem fs) throws IOException, OpenXML4JException, XmlException {
+    public static POIOLE2TextExtractor createExtractor(POIFSFileSystem fs) throws IOException {
         // Only ever an OLE2 one from the root of the FS
         return (POIOLE2TextExtractor)createExtractor(fs.getRoot());
     }
-    public static POIOLE2TextExtractor createExtractor(NPOIFSFileSystem fs) throws IOException, OpenXML4JException, XmlException {
+    public static POIOLE2TextExtractor createExtractor(NPOIFSFileSystem fs) throws IOException {
         // Only ever an OLE2 one from the root of the FS
         return (POIOLE2TextExtractor)createExtractor(fs.getRoot());
     }
-    public static POIOLE2TextExtractor createExtractor(OPOIFSFileSystem fs) throws IOException, OpenXML4JException, XmlException {
+    public static POIOLE2TextExtractor createExtractor(OPOIFSFileSystem fs) throws IOException {
         // Only ever an OLE2 one from the root of the FS
         return (POIOLE2TextExtractor)createExtractor(fs.getRoot());
     }
@@ -128,7 +126,7 @@ public class OLE2ExtractorFactory {
      *  {@link org.apache.poi.extractor.ExtractorFactory} for that.
      */
     public static POITextExtractor createExtractor(DirectoryNode poifsDir)
-            throws IOException, OpenXML4JException, XmlException
+            throws IOException
     {
         // Look for certain entries in the stream, to figure it
         // out from
@@ -154,7 +152,7 @@ public class OLE2ExtractorFactory {
      *  {@link POITextExtractor} for each embedded file.
      */
     public static POITextExtractor[] getEmbededDocsTextExtractors(POIOLE2TextExtractor ext)
-            throws IOException, OpenXML4JException, XmlException
+            throws IOException
     {
         // All the embedded directories we spotted
         ArrayList<Entry> dirs = new ArrayList<Entry>();

src/scratchpad/src/org/apache/poi/extractor/OLE2ScrachpadExtractorFactory.java

@@ -0,0 +1,149 @@
+/* ====================================================================
+   Licensed to the Apache Software Foundation (ASF) under one or more
+   contributor license agreements.  See the NOTICE file distributed with
+   this work for additional information regarding copyright ownership.
+   The ASF licenses this file to You under the Apache License, Version 2.0
+   (the "License"); you may not use this file except in compliance with
+   the License.  You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+==================================================================== */
+package org.apache.poi.extractor;
+
+import java.io.ByteArrayInputStream;
+import java.io.FileNotFoundException;
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.Iterator;
+
+import org.apache.poi.POIOLE2TextExtractor;
+import org.apache.poi.POITextExtractor;
+import org.apache.poi.hdgf.extractor.VisioTextExtractor;
+import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
+import org.apache.poi.hslf.extractor.PowerPointExtractor;
+import org.apache.poi.hsmf.MAPIMessage;
+import org.apache.poi.hsmf.datatypes.AttachmentChunks;
+import org.apache.poi.hsmf.extractor.OutlookTextExtactor;
+import org.apache.poi.hwpf.OldWordFileFormatException;
+import org.apache.poi.hwpf.extractor.Word6Extractor;
+import org.apache.poi.hwpf.extractor.WordExtractor;
+import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
+import org.apache.poi.poifs.filesystem.DirectoryEntry;
+import org.apache.poi.poifs.filesystem.DirectoryNode;
+import org.apache.poi.poifs.filesystem.Entry;
+import org.apache.xmlbeans.XmlException;
+
+/**
+ * Scratchpad-specific logic for {@link OLE2ExtractorFactory} and
+ *  {@link ExtractorFactory}, which permit the other two to run with
+ *  no Scratchpad jar (though without functionality!)
+ * <p>Note - should not be used standalone, always use via the other
+ *  two classes</p>
+ */
+@SuppressWarnings("WeakerAccess")
+public class OLE2ScrachpadExtractorFactory {
+    /**
+     * Look for certain entries in the stream, to figure it
+     * out what format is desired
+     * Note - doesn't check for core-supported formats!
+     * Note - doesn't check for OOXML-supported formats
+     */
+    public static POITextExtractor createExtractor(DirectoryNode poifsDir) throws IOException,
+            OpenXML4JException, XmlException
+    {
+        if (poifsDir.hasEntry("WordDocument")) {
+            // Old or new style word document?
+            try {
+                return new WordExtractor(poifsDir);
+            } catch (OldWordFileFormatException e) {
+                return new Word6Extractor(poifsDir);
+            }
+        }
+
+        if (poifsDir.hasEntry("PowerPoint Document")) {
+            return new PowerPointExtractor(poifsDir);
+        }
+
+        if (poifsDir.hasEntry("VisioDocument")) {
+            return new VisioTextExtractor(poifsDir);
+        }
+
+        if (poifsDir.hasEntry("Quill")) {
+            return new PublisherTextExtractor(poifsDir);
+        }
+
+        final String[] outlookEntryNames = new String[] {
+                // message bodies, saved as plain text (PtypString)
+                // The first short (0x1000, 0x0047, 0x0037) refer to the Property ID (see [MS-OXPROPS].pdf)
+                // the second short (0x001e, 0x001f, 0x0102) refer to the type of data stored in this entry
+                // https://msdn.microsoft.com/endatatypes.Ex-us/library/cc433490(v=exchg.80).aspx
+                // @see org.apache.poi.hsmf.Types.MAPIType
+                "__substg1.0_1000001E", //PidTagBody ASCII
+                "__substg1.0_1000001F", //PidTagBody Unicode
+                "__substg1.0_0047001E", //PidTagMessageSubmissionId ASCII
+                "__substg1.0_0047001F", //PidTagMessageSubmissionId Unicode
+                "__substg1.0_0037001E", //PidTagSubject ASCII
+                "__substg1.0_0037001F", //PidTagSubject Unicode
+        };
+        for (String entryName : outlookEntryNames) {
+            if (poifsDir.hasEntry(entryName)) {
+                return new OutlookTextExtactor(poifsDir);
+            }
+        }
+
+        throw new IllegalArgumentException("No supported documents found in the OLE2 stream");
+    }
+
+	/**
+	 * Returns an array of text extractors, one for each of
+	 *  the embedded documents in the file (if there are any).
+	 * If there are no embedded documents, you'll get back an
+	 *  empty array. Otherwise, you'll get one open
+	 *  {@link POITextExtractor} for each embedded file.
+	 */
+	public static void identifyEmbeddedResources(POIOLE2TextExtractor ext, ArrayList<Entry> dirs, ArrayList<InputStream> nonPOIFS) throws IOException {
+      // Find all the embedded directories
+		DirectoryEntry root = ext.getRoot();
+		if(root == null) {
+			throw new IllegalStateException("The extractor didn't know which POIFS it came from!");
+		}
+
+		if(ext instanceof WordExtractor) {
+		    // These are in ObjectPool -> _... under the root
+		    try {
+		        DirectoryEntry op = (DirectoryEntry)
+		                root.getEntry("ObjectPool");
+		        Iterator<Entry> it = op.getEntries();
+		        while(it.hasNext()) {
+		            Entry entry = it.next();
+		            if(entry.getName().startsWith("_")) {
+		                dirs.add(entry);
+		            }
+		        }
+		    } catch(FileNotFoundException e) {
+		        // ignored here
+		    }
+		    //} else if(ext instanceof PowerPointExtractor) {
+		    // Tricky, not stored directly in poifs
+		    // TODO
+		} else if(ext instanceof OutlookTextExtactor) {
+		    // Stored in the Attachment blocks
+		    MAPIMessage msg = ((OutlookTextExtactor)ext).getMAPIMessage();
+		    for(AttachmentChunks attachment : msg.getAttachmentFiles()) {
+		        if(attachment.attachData != null) {
+		            byte[] data = attachment.attachData.getValue();
+		            nonPOIFS.add( new ByteArrayInputStream(data) );
+		        } else if(attachment.attachmentDirectory != null) {
+		            dirs.add(attachment.attachmentDirectory.getDirectory());
+		        }
+		    }
+		}
+	}
+}