Fix bug #51804 - Include Master Slide text in XSLF text extraction

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@1173749 13f79535-47bb-0310-9956-ffa450edef68

src/documentation/content/xdocs/status.xml

@@ -34,6 +34,7 @@
 
     <changes>
         <release version="3.8-beta5" date="2011-??-??">
+           <action dev="poi-developers" type="add">51804 - include Master Slide text in XSLF text extraction</action>
            <action dev="poi-developers" type="add">New PackagePart method getRelatedPart(PackageRelationship) to simplify navigation of relations between OPC Parts</action>
            <action dev="poi-developers" type="fix">51832 - handle XLS files where the WRITEPROTECT record preceeds the FILEPASS one, rather than following as normal</action>
            <action dev="poi-developers" type="fix">51809 - correct GTE handling in COUNTIF</action>

src/ooxml/java/org/apache/poi/xslf/extractor/XSLFPowerPointExtractor.java

@@ -30,6 +30,7 @@ import org.apache.poi.xslf.usermodel.XSLFCommonSlideData;
 import org.apache.poi.xslf.usermodel.XSLFNotes;
 import org.apache.poi.xslf.usermodel.XSLFRelation;
 import org.apache.poi.xslf.usermodel.XSLFSlide;
+import org.apache.poi.xslf.usermodel.XSLFSlideMaster;
 import org.apache.xmlbeans.XmlException;
 import org.openxmlformats.schemas.presentationml.x2006.main.CTComment;
 import org.openxmlformats.schemas.presentationml.x2006.main.CTCommentAuthor;
@@ -105,13 +106,20 @@ public class XSLFPowerPointExtractor extends POIXMLTextExtractor {
          try {
             XSLFNotes notes = slide.getNotes();
             XSLFComments comments = slide.getComments();
+            XSLFSlideMaster master = slide.getMasterSheet();
 
             // TODO Do the slide's name
+            // (Stored in docProps/app.xml)
 
             // Do the slide's text if requested
             if (slideText) {
                extractText(slide.getCommonSlideData(), text);
                
+               // If there's a master sheet, grab text from there
+               if(master != null) {
+                  extractText(master.getCommonSlideData(), text);
+               }
+
                // If the slide has comments, do those too
                if (comments != null) {
                   for (CTComment comment : comments.getCTCommentsList().getCmList()) {

src/ooxml/testcases/org/apache/poi/xslf/extractor/TestXSLFPowerPointExtractor.java

@@ -26,17 +26,19 @@ import junit.framework.TestCase;
  * Tests for HXFPowerPointExtractor
  */
 public class TestXSLFPowerPointExtractor extends TestCase {
-	/**
+   /**
-	 * A simple file
+    * A simple file
-	 */
+    */
-	private XSLFSlideShow xmlA;
+   private XSLFSlideShow xmlA;
-	private OPCPackage pkg;
+   private OPCPackage pkg;
 	
-	protected void setUp() throws Exception {
+   private POIDataSamples slTests = POIDataSamples.getSlideShowInstance();
-        POIDataSamples slTests = POIDataSamples.getSlideShowInstance();
+
-		pkg = OPCPackage.open(slTests.openResourceAsStream("sample.pptx"));
+   protected void setUp() throws Exception {
-		xmlA = new XSLFSlideShow(pkg);
+      slTests = POIDataSamples.getSlideShowInstance();
-	}
+      pkg = OPCPackage.open(slTests.openResourceAsStream("sample.pptx"));
+      xmlA = new XSLFSlideShow(pkg);
+   }
 
 	/**
 	 * Get text out of the simple file
@@ -54,7 +56,16 @@ public class TestXSLFPowerPointExtractor extends TestCase {
 		
 		// Check Basics
 		assertTrue(text.startsWith("Lorem ipsum dolor sit amet\n"));
-		assertTrue(text.endsWith("amet\n\n"));
+		assertTrue(text.contains("amet\n\n"));
+
+		// Our master text, for tests
+		String masterText =
+         "Click to edit Master title style\n" +
+         "Click to edit Master text styles\n" +
+         "Second level\n" +
+         "Third level\n" +
+         "Fourth level\n" +
+         "Fifth level\n";
 		
 		// Just slides, no notes
 		text = extractor.getText(true, false);
@@ -62,13 +73,18 @@ public class TestXSLFPowerPointExtractor extends TestCase {
 				"Lorem ipsum dolor sit amet\n" +
 				"Nunc at risus vel erat tempus posuere. Aenean non ante.\n" +
 				"\n" +
+				masterText +
+            "\n\n\n" +
 				"Lorem ipsum dolor sit amet\n" +
 				"Lorem\n" +
 				"ipsum\n" +
 				"dolor\n" +
 				"sit\n" +
 				"amet\n" +
-				"\n", text
+				"\n" +
+            masterText +
+				"\n\n\n"
+				, text
 		);
 		
 		// Just notes, no slides
@@ -82,14 +98,19 @@ public class TestXSLFPowerPointExtractor extends TestCase {
 		assertEquals(
 				"Lorem ipsum dolor sit amet\n" +
 				"Nunc at risus vel erat tempus posuere. Aenean non ante.\n" +
-				"\n\n\n" +
+            "\n" +
+            masterText +
+				"\n\n\n\n\n" +
 				"Lorem ipsum dolor sit amet\n" +
 				"Lorem\n" +
 				"ipsum\n" +
 				"dolor\n" +
 				"sit\n" +
 				"amet\n" +
-				"\n\n\n", text
+				"\n" +
+            masterText +
+            "\n\n\n\n\n"
+				, text
 		);
 		
 		// Via set defaults
@@ -101,28 +122,41 @@ public class TestXSLFPowerPointExtractor extends TestCase {
 		);
 	}
 	
-	public void testGetComments() throws Exception {
+   public void testGetComments() throws Exception {
-        POIDataSamples slTests = POIDataSamples.getSlideShowInstance();
+      XSLFSlideShow xml = 
-		xmlA = new XSLFSlideShow(OPCPackage.open(slTests.openResourceAsStream("45545_Comment.pptx")));
+         new XSLFSlideShow(OPCPackage.open(slTests.openResourceAsStream("45545_Comment.pptx")));
-		XSLFPowerPointExtractor extractor = 
+      XSLFPowerPointExtractor extractor = 
-			new XSLFPowerPointExtractor(xmlA);
+         new XSLFPowerPointExtractor(xml);
 
-		String text = extractor.getText();
+      String text = extractor.getText();
-		assertTrue(text.length() > 0);
+      assertTrue(text.length() > 0);
 
-		// Check comments are there
+      // Check comments are there
-		assertTrue("Unable to find expected word in text\n" + text, text.contains("testdoc"));
+      assertTrue("Unable to find expected word in text\n" + text, text.contains("testdoc"));
       assertTrue("Unable to find expected word in text\n" + text, text.contains("test phrase"));
 
-		// Check the authors came through too
+      // Check the authors came through too
       assertTrue("Unable to find expected word in text\n" + text, text.contains("XPVMWARE01"));
+   }
+	
+	public void testGetMasterText() throws Exception {
+      XSLFSlideShow xml = 
+         new XSLFSlideShow(OPCPackage.open(slTests.openResourceAsStream("WithMaster.pptx")));
+      XSLFPowerPointExtractor extractor = 
+         new XSLFPowerPointExtractor(xml);
+      
+      String text = extractor.getText();
+      assertTrue(text.length() > 0);
+
+      // Check master text is there
+      assertTrue("Unable to find expected word in text\n" + text, text.contains("Master footer is here"));
 	}
 
     public void testTable() throws Exception {
-        POIDataSamples slTests = POIDataSamples.getSlideShowInstance();
+        XSLFSlideShow xml = 
-        xmlA = new XSLFSlideShow(OPCPackage.open(slTests.openResourceAsStream("present1.pptx")));
+           new XSLFSlideShow(OPCPackage.open(slTests.openResourceAsStream("present1.pptx")));
         XSLFPowerPointExtractor extractor =
-            new XSLFPowerPointExtractor(xmlA);
+            new XSLFPowerPointExtractor(xml);
 
         String text = extractor.getText();
         assertTrue(text.length() > 0);
@@ -137,7 +171,6 @@ public class TestXSLFPowerPointExtractor extends TestCase {
      *  well as from the normal file
      */
     public void testDifferentSubformats() throws Exception {
-       POIDataSamples slTests = POIDataSamples.getSlideShowInstance();
        String[] extensions = new String[] {
              "pptx", "pptm", "ppsm", "ppsx",
              "thmx", 
@@ -145,9 +178,10 @@ public class TestXSLFPowerPointExtractor extends TestCase {
        };
        for(String extension : extensions) {
           String filename = "testPPT." + extension;
-          xmlA = new XSLFSlideShow(OPCPackage.open(slTests.openResourceAsStream(filename)));
+          XSLFSlideShow xml = 
+             new XSLFSlideShow(OPCPackage.open(slTests.openResourceAsStream(filename)));
           XSLFPowerPointExtractor extractor =
-             new XSLFPowerPointExtractor(xmlA);
+             new XSLFPowerPointExtractor(xml);
 
          String text = extractor.getText();
          if(extension.equals("thmx")) {