Merged revisions 638786-638802,638805-638811,638813-638814,638816-639230,639233-639241,639243-639253,639255-639486,639488-639601,639603-639835,639837-639917,639919-640056,640058-640710,640712-641156,641158-641184,641186-641795,641797-641798,641800-641933,641935-641963,641965-641966,641968-641995,641997-642230,642232-642562,642564-642565,642568-642570,642572-642573,642576-642736,642739-642877,642879,642881-642890,642892-642903,642905-642945,642947-643624,643626-643653,643655-643669,643671,643673-643830,643832-643833,643835-644342,644344-644472,644474-644508,644510-645347,645349-645351,645353-645559,645561-645565,645568-645951,645953-646193,646195-646311,646313-646404,646406-646665,646667-646853,646855-646869,646871-647151,647153-647185,647187-647277,647279-647566,647568-647573,647575,647578-647711,647714-647737,647739-647823,647825-648155,648157-648202,648204-648273,648275,648277-648302,648304-648333,648335-648588,648590-648622,648625-648673,648675-649141,649144,649146-649556,649558-649795,649799,649801-649910,649912-649913,649915-650128,650131-650132,650134-650137,650140-650914,650916-651991,651993-652284,652286-652287,652289,652291,652293-652297,652299-652328,652330-652425,652427-652445,652447-652560,652562-652933,652935,652937-652993,652995-653116,653118-653124,653126-653483,653487-653519,653522-653550,653552-653607,653609-653667,653669-653674,653676-653814,653817-653830,653832-653891,653893-653944,653946-654055,654057-654355,654357-654365,654367-654648,654651-655215,655217-655277,655279-655281,655283-655911,655913-656212,656214,656216-656251,656253-656698,656700-656756,656758-656892,656894-657135,657137-657165,657168-657179,657181-657354,657356-657357,657359-657701,657703-657874,657876-658032,658034-658284,658286,658288-658301,658303-658307,658309-658321,658323-658335,658337-658348,658351,658353-658832,658834-658983,658985,658987-659066,659068-659402,659404-659428,659430-659451,659453-659454,659456-659461,659463-659477,659479-659524,659526-659571,659574,659576-660255,660257-660262,660264-660279,660281-660343,660345-660473,660475-660827,660829-660833,660835-660888,660890-663321,663323-663435,663437-663764,663766-663854,663856-664219,664221-664489,664494-664514,664516-668013,668015-668142,668144-668152,668154,668156-668256,668258,668260-669139,669141-669455,669457-669657,669659-669808,669810-670189,670191-671321,671323-672229,672231-672549,672551-672552,672554-672561,672563-672566,672568,672571-673049,673051-673852,673854-673862,673864-673986,673988-673996,673998-674347,674349-674890,674892-674910,674912-674936,674938-674952,674954-675078,675080-675085,675087-675217,675219-675660,675662-675670,675672-675716,675718-675726,675728-675733,675735-675775,675777-675782,675784,675786-675791,675794-675852,675854-676200,676202,676204,676206-676220,676222-676309,676311-676456,676458-676994,676996-677027,677030-677040,677042-677056,677058-677375,677377-677968,677970-677971,677973,677975-677994,677996-678286,678288-678538,678540-680393,680395-680469,680471-680529,680531-680852,680854-681529,681531-681571,681573-682224,682226,682228,682231-682281,682283-682335,682337-682507,682509,682512-682517,682519-682533 via svnmerge from

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

........
  r682533 | nick | 2008-08-04 23:48:39 +0100 (Mon, 04 Aug 2008) | 1 line
  
  Fix bug #45543 - Optionally extract comment text with PowerPointExtractor, and initial hslf model support for comments
........


git-svn-id: https://svn.apache.org/repos/asf/poi/branches/ooxml@682535 13f79535-47bb-0310-9956-ffa450edef68

src/documentation/content/xdocs/changes.xml

@@ -52,6 +52,7 @@
            <action dev="POI-DEVELOPERS" type="add">Created a common interface for handling Excel files, irrespective of if they are .xls or .xlsx</action>
         </release>
         <release version="3.1.1-alpha1" date="2008-??-??">
+           <action dev="POI-DEVELOPERS" type="add">45543 - Optionally extract comment text with PowerPointExtractor, and initial hslf model support for comments</action>
            <action dev="POI-DEVELOPERS" type="fix">45538 - Include excel headers and footers in the output of ExcelExtractor</action>
            <action dev="POI-DEVELOPERS" type="fix">44894 - refactor duplicate logic from EventRecordFactory to RecordFactory</action>
            <action dev="POI-DEVELOPERS" type="add">Support for Headers / Footers in HSLF</action>

src/documentation/content/xdocs/status.xml

@@ -49,6 +49,7 @@
            <action dev="POI-DEVELOPERS" type="add">Created a common interface for handling Excel files, irrespective of if they are .xls or .xlsx</action>
         </release>
         <release version="3.1.1-alpha1" date="2008-??-??">
+           <action dev="POI-DEVELOPERS" type="add">45543 - Optionally extract comment text with PowerPointExtractor, and initial hslf model support for comments</action>
            <action dev="POI-DEVELOPERS" type="fix">45538 - Include excel headers and footers in the output of ExcelExtractor</action>
            <action dev="POI-DEVELOPERS" type="fix">44894 - refactor duplicate logic from EventRecordFactory to RecordFactory</action>
            <action dev="POI-DEVELOPERS" type="add">Support for Headers / Footers in HSLF</action>

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

@@ -27,6 +27,8 @@ import org.apache.poi.POIOLE2TextExtractor;
 import org.apache.poi.poifs.filesystem.POIFSFileSystem;
 import org.apache.poi.hslf.*;
 import org.apache.poi.hslf.model.*;
+import org.apache.poi.hslf.record.Comment2000;
+import org.apache.poi.hslf.record.Record;
 import org.apache.poi.hslf.usermodel.*;
 
 /**
@@ -44,6 +46,7 @@ public class PowerPointExtractor extends POIOLE2TextExtractor
 	
 	private boolean slidesByDefault = true;
 	private boolean notesByDefault = false;
+	private boolean commentsByDefault = false;
 
   /**
    * Basic extractor. Returns all the text, and optionally all the notes
@@ -57,16 +60,20 @@ public class PowerPointExtractor extends POIOLE2TextExtractor
 	}
 
 	boolean notes = false;
+	boolean comments = false;
 	String file;
 	if(args.length > 1) {
 		notes = true;
 		file = args[1];
+		if(args.length > 2) {
+			comments = true;
+		}
 	} else {
 		file = args[0];
 	}
 
 	PowerPointExtractor ppe = new PowerPointExtractor(file);
-	System.out.println(ppe.getText(true,notes));
+	System.out.println(ppe.getText(true,notes,comments));
 	ppe.close();
   }
 
@@ -127,6 +134,13 @@ public class PowerPointExtractor extends POIOLE2TextExtractor
 	public void setNotesByDefault(boolean notesByDefault) {
 		this.notesByDefault = notesByDefault;
 	}
+	/**
+	 * Should a call to getText() return comments text?
+	 * Default is no
+	 */
+	public void setCommentsByDefault(boolean commentsByDefault) {
+		this.commentsByDefault = commentsByDefault;
+	}
 
 	/**
 	 * Fetches all the slide text from the slideshow, 
@@ -135,7 +149,7 @@ public class PowerPointExtractor extends POIOLE2TextExtractor
 	 *  to change this
 	 */
 	public String getText() {
-		return getText(slidesByDefault,notesByDefault);
+		return getText(slidesByDefault,notesByDefault,commentsByDefault);
 	}
 
 	/**
@@ -153,6 +167,9 @@ public class PowerPointExtractor extends POIOLE2TextExtractor
    * @param getNoteText fetch note text
    */
   public String getText(boolean getSlideText, boolean getNoteText) {
+	  return getText(getSlideText, getNoteText, commentsByDefault);
+  }
+  public String getText(boolean getSlideText, boolean getNoteText, boolean getCommentText) {
 	StringBuffer ret = new StringBuffer(); 
 
 	if(getSlideText) {
@@ -169,6 +186,18 @@ public class PowerPointExtractor extends POIOLE2TextExtractor
 					}
 				}
 			}
+			
+			if(getCommentText) {
+				Comment[] comments = slide.getComments();
+				for(int j=0; j<comments.length; j++) {
+					ret.append(
+							comments[j].getAuthor() + 
+							" - " +
+							comments[j].getText() + 
+							"\n"
+					);
+				}
+			}
 		}
 		if(getNoteText) {
 			ret.append("\n");

src/scratchpad/src/org/apache/poi/hslf/model/Comment.java

@@ -0,0 +1,54 @@
+package org.apache.poi.hslf.model;
+
+import org.apache.poi.hslf.record.Comment2000;
+
+public class Comment {
+	private Comment2000 comment2000;
+	
+	public Comment(Comment2000 comment2000) {
+		this.comment2000 = comment2000;
+	}
+	
+	protected Comment2000 getComment2000() {
+		return comment2000;
+	}
+	
+	/**
+	 * Get the Author of this comment
+	 */
+	public String getAuthor() {
+		return comment2000.getAuthor();
+	}
+	/**
+	 * Set the Author of this comment
+	 */
+	public void setAuthor(String author) {
+		comment2000.setAuthor(author);
+	}
+
+	/**
+	 * Get the Author's Initials of this comment
+	 */
+	public String getAuthorInitials() {
+		return comment2000.getAuthorInitials();
+	}
+	/**
+	 * Set the Author's Initials of this comment
+	 */
+	public void setAuthorInitials(String initials) {
+		comment2000.setAuthorInitials(initials);
+	}
+
+	/**
+	 * Get the text of this comment
+	 */
+	public String getText() {
+		return comment2000.getText();
+	}
+	/**
+	 * Set the text of this comment
+	 */
+	public void setText(String text) {
+		comment2000.setText(text);
+	}
+}

src/scratchpad/src/org/apache/poi/hslf/model/Slide.java

@@ -361,6 +361,59 @@ public class Slide extends Sheet
         }
         return super.getColorScheme();
     }
+    
+    /**
+     * Get the comment(s) for this slide.
+     * Note - for now, only works on PPT 2000 and 
+     *  PPT 2003 files. Doesn't work for PPT 97
+     *  ones, as they do their comments oddly.
+     */
+    public Comment[] getComments() {
+    	// If there are any, they're in
+    	//  ProgTags -> ProgBinaryTag -> BinaryTagData
+    	RecordContainer progTags = (RecordContainer)
+    			getSheetContainer().findFirstOfType(
+    						RecordTypes.ProgTags.typeID
+    	);
+    	if(progTags != null) {
+    		RecordContainer progBinaryTag = (RecordContainer)
+    			progTags.findFirstOfType(
+    					RecordTypes.ProgBinaryTag.typeID
+    		);
+    		if(progBinaryTag != null) {
+    			RecordContainer binaryTags = (RecordContainer)
+    				progBinaryTag.findFirstOfType(
+    						RecordTypes.BinaryTagData.typeID
+    			);
+    			if(binaryTags != null) {
+    				// This is where they'll be
+    				int count = 0;
+    				for(int i=0; i<binaryTags.getChildRecords().length; i++) {
+    					if(binaryTags.getChildRecords()[i] instanceof Comment2000) {
+    						count++;
+    					}
+    				}
+    				
+    				// Now build
+    				Comment[] comments = new Comment[count];
+    				count = 0;
+    				for(int i=0; i<binaryTags.getChildRecords().length; i++) {
+    					if(binaryTags.getChildRecords()[i] instanceof Comment2000) {
+    						comments[i] = new Comment(
+    								(Comment2000)binaryTags.getChildRecords()[i]
+    						);
+    						count++;
+    					}
+    				}
+    				
+    				return comments;
+    			}
+    		}
+    	}
+    	
+    	// None found
+    	return new Comment[0];
+    }
 
     public void draw(Graphics2D graphics){
         MasterSheet master = getMasterSheet();

src/scratchpad/src/org/apache/poi/hslf/record/RecordContainer.java

@@ -123,6 +123,20 @@ public abstract class RecordContainer extends Record
 	}
 	
 	
+	/**
+	 * Finds the first child record of the given type,
+	 *  or null if none of the child records are of the
+	 *  given type. Does not descend.
+	 */
+	public Record findFirstOfType(long type) {
+		for(int i=0; i<_children.length; i++) {
+			if(_children[i].getRecordType() == type) {
+				return _children[i];
+			}
+		}
+		return null;
+	}
+	
 	/* ===============================================================
 	 *                   External Move Methods
 	 * ===============================================================

src/scratchpad/testcases/org/apache/poi/hslf/extractor/TextExtractor.java

@@ -216,4 +216,36 @@ public class TextExtractor extends TestCase {
 				ppe.getText(true, false)
 		);
     }
+    
+    /**
+     * From bug #45543
+     */
+    public void testWithComments() throws Exception {
+		String filename;
+		
+		// New file
+		filename = dirname + "/WithComments.ppt";
+		ppe = new PowerPointExtractor(filename);
+
+		String text = ppe.getText();
+		assertFalse("Comments not in by default", text.contains("This is a test comment"));
+		
+		ppe.setCommentsByDefault(true);
+		
+		text = ppe.getText();
+		assertTrue("Unable to find expected word in text\n" + text, text.contains("This is a test comment"));
+
+		
+		// And another file
+		filename = dirname + "/45543.ppt";
+		ppe = new PowerPointExtractor(filename);
+
+		text = ppe.getText();
+		assertFalse("Comments not in by default", text.contains("testdoc"));
+		
+		ppe.setCommentsByDefault(true);
+		
+		text = ppe.getText();
+		assertTrue("Unable to find expected word in text\n" + text, text.contains("testdoc"));
+    }
 }