Merged revisions 638786-638802,638805-638811,638813-638814,638816-639230,639233-639241,639243-639253,639255-639486,639488-639601,639603-639835,639837-639917,639919-640056,640058-640710,640712-641156,641158-641184,641186-641795,641797-641798,641800-641933,641935-641963,641965-641966,641968-641995,641997-642230,642232-642562,642564-642565,642568-642570,642572-642573,642576-642736,642739-642877,642879,642881-642890,642892-642903,642905-642945,642947-643624,643626-643653,643655-643669,643671,643673-643830,643832-643833,643835-644342,644344-644472,644474-644508,644510-645347,645349-645351,645353-645559,645561-645565,645568-645951,645953-646193,646195-646313 via svnmerge from

https://svn.apache.org:443/repos/asf/poi/trunk

........
  r646312 | nick | 2008-04-09 13:46:42 +0100 (Wed, 09 Apr 2008) | 1 line
  
  Provide a common ole2 implementation of POITextExtractor, which gives access to the document metadata
........


git-svn-id: https://svn.apache.org/repos/asf/poi/branches/ooxml@646818 13f79535-47bb-0310-9956-ffa450edef68

build.xml

@@ -220,6 +220,7 @@ under the License.
     <path id="ooxml.classpath">
         <path refid="main.classpath"/>
         <path refid="scratchpad.classpath"/>
+        <pathelement location="${scratchpad.output.dir}"/>
         <fileset dir="${ooxml.lib}">
 			<include name="*.jar" />
 		</fileset>

src/java/org/apache/poi/POIOLE2TextExtractor.java

@@ -0,0 +1,53 @@
+/* ====================================================================
+   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;
+
+import org.apache.poi.hpsf.DocumentSummaryInformation;
+import org.apache.poi.hpsf.SummaryInformation;
+
+/**
+ * Common Parent for OLE2 based Text Extractors
+ *  of POI Documents, such as .doc, .xls
+ * You will typically find the implementation of
+ *  a given format's text extractor under
+ *  org.apache.poi.[format].extractor .
+ * @see org.apache.poi.hssf.extractor.ExcelExtractor
+ * @see org.apache.poi.hslf.extractor.PowerPointExtractor
+ * @see org.apache.poi.hdgf.extractor.VisioTextExtractor
+ * @see org.apache.poi.hwpf.extractor.WordExtractor
+ */
+public abstract class POIOLE2TextExtractor extends POITextExtractor {
+	/**
+	 * Creates a new text extractor for the given document
+	 */
+	public POIOLE2TextExtractor(POIDocument document) {
+		super(document);
+	}
+	
+	/**
+	 * Returns the document information metadata for the document
+	 */
+	public DocumentSummaryInformation getDocSummaryInformation() {
+		return document.getDocumentSummaryInformation();
+	}
+	/**
+	 * Returns the summary information metadata for the document
+	 */
+	public SummaryInformation getSummaryInformation() {
+		return document.getSummaryInformation();
+	}
+}

src/java/org/apache/poi/hssf/extractor/ExcelExtractor.java

@@ -18,7 +18,7 @@ package org.apache.poi.hssf.extractor;
 
 import java.io.IOException;
 
-import org.apache.poi.POITextExtractor;
+import org.apache.poi.POIOLE2TextExtractor;
 import org.apache.poi.hssf.usermodel.HSSFCell;
 import org.apache.poi.hssf.usermodel.HSSFRichTextString;
 import org.apache.poi.hssf.usermodel.HSSFRow;
@@ -35,7 +35,7 @@ import org.apache.poi.poifs.filesystem.POIFSFileSystem;
  *  the XLS2CSVmra example
  * @see org.apache.poi.hssf.eventusermodel.examples.XLS2CSVmra
  */
-public class ExcelExtractor extends POITextExtractor{
+public class ExcelExtractor extends POIOLE2TextExtractor {
 	private HSSFWorkbook wb;
 	private boolean includeSheetNames = true;
 	private boolean formulasNotResults = false;

src/ooxml/java/org/apache/poi/extractor/ExtractorFactory.java

@@ -29,6 +29,7 @@ import org.openxml4j.opc.Package;
 import org.openxml4j.opc.PackagePart;
 import org.openxml4j.opc.PackageRelationshipCollection;
 
+import org.apache.poi.POIOLE2TextExtractor;
 import org.apache.poi.POITextExtractor;
 import org.apache.poi.POIXMLDocument;
 import org.apache.poi.POIXMLTextExtractor;
@@ -104,7 +105,7 @@ public class ExtractorFactory {
 		throw new IllegalArgumentException("No supported documents found in the OOXML package");
 	}
 	
-	public static POITextExtractor createExtractor(POIFSFileSystem fs) throws IOException {
+	public static POIOLE2TextExtractor createExtractor(POIFSFileSystem fs) throws IOException {
 		// Look for certain entries in the stream, to figure it
 		//  out from
 		for(Iterator entries = fs.getRoot().getEntries(); entries.hasNext(); ) {

src/scratchpad/src/org/apache/poi/hdgf/extractor/VisioTextExtractor.java

@@ -21,7 +21,7 @@ import java.io.IOException;
 import java.io.InputStream;
 import java.util.ArrayList;
 
-import org.apache.poi.POITextExtractor;
+import org.apache.poi.POIOLE2TextExtractor;
 import org.apache.poi.hdgf.HDGFDiagram;
 import org.apache.poi.hdgf.chunks.Chunk;
 import org.apache.poi.hdgf.chunks.Chunk.Command;
@@ -35,7 +35,7 @@ import org.apache.poi.poifs.filesystem.POIFSFileSystem;
  * Can opperate on the command line (outputs to stdout), or
  *  can return the text for you (eg for use with Lucene).
  */
-public class VisioTextExtractor extends POITextExtractor {
+public class VisioTextExtractor extends POIOLE2TextExtractor {
 	private HDGFDiagram hdgf;
 	private POIFSFileSystem fs;
 

src/scratchpad/src/org/apache/poi/hslf/extractor/PowerPointExtractor.java

@@ -23,7 +23,7 @@ package org.apache.poi.hslf.extractor;
 import java.io.*;
 import java.util.HashSet;
 
-import org.apache.poi.POITextExtractor;
+import org.apache.poi.POIOLE2TextExtractor;
 import org.apache.poi.poifs.filesystem.POIFSFileSystem;
 import org.apache.poi.hslf.*;
 import org.apache.poi.hslf.model.*;
@@ -36,7 +36,7 @@ import org.apache.poi.hslf.usermodel.*;
  * @author Nick Burch
  */
 
-public class PowerPointExtractor extends POITextExtractor
+public class PowerPointExtractor extends POIOLE2TextExtractor
 {
 	private HSLFSlideShow _hslfshow;
 	private SlideShow _show;

src/scratchpad/src/org/apache/poi/hwpf/extractor/WordExtractor.java

@@ -22,7 +22,7 @@ import java.io.FileInputStream;
 import java.io.UnsupportedEncodingException;
 import java.util.Iterator;
 
-import org.apache.poi.POITextExtractor;
+import org.apache.poi.POIOLE2TextExtractor;
 import org.apache.poi.hwpf.HWPFDocument;
 import org.apache.poi.hwpf.model.TextPiece;
 import org.apache.poi.hwpf.usermodel.Paragraph;
@@ -37,7 +37,7 @@ import org.apache.poi.poifs.filesystem.POIFSFileSystem;
  *
  * @author Nick Burch (nick at torchbox dot com)
  */
-public class WordExtractor extends POITextExtractor {
+public class WordExtractor extends POIOLE2TextExtractor {
 	private POIFSFileSystem fs;
 	private HWPFDocument doc;