Fix bug #45538 - Include excel headers and footers in the output of ExcelExtractor

git-svn-id: https://svn.apache.org/repos/asf/poi/trunk@682511 13f79535-47bb-0310-9956-ffa450edef68

src/documentation/content/xdocs/changes.xml

@@ -37,6 +37,7 @@
 
 		<!-- Don't forget to update status.xml too! -->
         <release version="3.1.1-alpha1" date="2008-??-??">
+           <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>
            <action dev="POI-DEVELOPERS" type="fix">44953 - Extensive fixes for data validation</action>

src/documentation/content/xdocs/status.xml

@@ -34,6 +34,7 @@
 	<!-- Don't forget to update changes.xml too! -->
     <changes>
         <release version="3.1.1-alpha1" date="2008-??-??">
+           <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>
            <action dev="POI-DEVELOPERS" type="fix">44953 - Extensive fixes for data validation</action>

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

@@ -19,8 +19,11 @@ package org.apache.poi.hssf.extractor;
 import java.io.IOException;
 
 import org.apache.poi.POIOLE2TextExtractor;
+import org.apache.poi.hssf.usermodel.HeaderFooter;
 import org.apache.poi.hssf.usermodel.HSSFCell;
 import org.apache.poi.hssf.usermodel.HSSFComment;
+import org.apache.poi.hssf.usermodel.HSSFFooter;
+import org.apache.poi.hssf.usermodel.HSSFHeader;
 import org.apache.poi.hssf.usermodel.HSSFRichTextString;
 import org.apache.poi.hssf.usermodel.HSSFRow;
 import org.apache.poi.hssf.usermodel.HSSFSheet;
@@ -89,6 +92,13 @@ public class ExcelExtractor extends POIOLE2TextExtractor {
 				}
 			}
 			
+			// Header text, if there is any
+			if(sheet.getHeader() != null) {
+				text.append(
+						extractHeaderFooter(sheet.getHeader())
+				);
+			}
+			
 			int firstRow = sheet.getFirstRowNum();
 			int lastRow = sheet.getLastRowNum();
 			for(int j=firstRow;j<=lastRow;j++) {
@@ -154,8 +164,37 @@ public class ExcelExtractor extends POIOLE2TextExtractor {
 				// Finish off the row
 				text.append("\n");
 			}
+			
+			// Finally Feader text, if there is any
+			if(sheet.getFooter() != null) {
+				text.append(
+						extractHeaderFooter(sheet.getFooter())
+				);
+			}
 		}
 		
 		return text.toString();
 	}
+	
+	private String extractHeaderFooter(HeaderFooter hf) {
+		StringBuffer text = new StringBuffer();
+		
+		if(hf.getLeft() != null) {
+			text.append(hf.getLeft());
+		}
+		if(hf.getCenter() != null) {
+			if(text.length() > 0)
+				text.append("\t");
+			text.append(hf.getCenter());
+		}
+		if(hf.getRight() != null) {
+			if(text.length() > 0)
+				text.append("\t");
+			text.append(hf.getRight());
+		}
+		if(text.length() > 0)
+			text.append("\n");
+		
+		return text.toString();
+	}
 }

src/java/org/apache/poi/hssf/usermodel/HSSFFooter.java

@@ -32,7 +32,7 @@ import org.apache.poi.hssf.record.FooterRecord;
  * <P>
  * @author Shawn Laubach (slaubach at apache dot org)
  */
-public class HSSFFooter extends Object {
+public class HSSFFooter extends Object implements HeaderFooter {
 
     FooterRecord footerRecord;
     String left;

src/java/org/apache/poi/hssf/usermodel/HSSFHeader.java

@@ -32,7 +32,7 @@ import org.apache.poi.hssf.record.HeaderRecord;
  *
  * @author Shawn Laubach (slaubach at apache dot org)
  */
-public class HSSFHeader
+public class HSSFHeader implements HeaderFooter
 {
 
     HeaderRecord headerRecord;

src/java/org/apache/poi/hssf/usermodel/HeaderFooter.java

@@ -0,0 +1,33 @@
+/* ====================================================================
+   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.hssf.usermodel;
+
+/**
+ * Common interface for {@link HSSFHeader} and
+ *  {@link HSSFFooter}.
+ */
+public interface HeaderFooter {
+    public String getLeft();
+    public void setLeft( String newLeft );
+
+    public String getCenter();
+    public void setCenter( String newCenter );
+
+    public String getRight();
+    public void setRight( String newRight );
+
+}

src/testcases/org/apache/poi/hssf/extractor/TestExcelExtractor.java

@@ -255,4 +255,20 @@ public final class TestExcelExtractor extends TestCase {
 				ex.getText());
 		assertEquals("Excel With Embeded", ex.getSummaryInformation().getTitle());
 	}
+	
+	/**
+	 * Test that we get text from headers and footers
+	 */
+	public void test45538() throws Exception {
+		String[] files = new String[] {
+			"45538_classic_Footer.xls", "45538_form_Footer.xls",    
+			"45538_classic_Header.xls", "45538_form_Header.xls"
+		};
+		for(int i=0; i<files.length; i++) {
+			ExcelExtractor extractor = createExtractor(files[i]);
+			String text = extractor.getText();
+			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"));
+		}
+	}
 }