Author: nick
Date: Fri Nov 1 19:43:46 2013
New Revision: 1538044
URL: http://svn.apache.org/r1538044
Log:
Fix bug #55733 - XWPFWordExtractor need
s to handle .docx files with neither headers nor footers
Added:
poi/trunk/test-data/document/55733.docx (with props)
Modified:
poi/trunk/src/ooxml/java/org/apache/poi/xwpf/extractor/XWPFWordExtractor.java
poi/trunk/src/ooxml/testcases/org/apache/poi/xwpf/extractor/TestXWPFWordExtractor.java
poi/trunk/src/scratchpad/testcases/org/apache/poi/hwpf/extractor/TestWordExtractorBugs.java
Modified:
poi/trunk/src/ooxml/java/org/apache/poi/xwpf/extractor/XWPFWordExtractor.java
URL:
http://svn.apache.org/viewvc/poi/trunk/src/ooxml/java/org/apache/poi/xwpf/extractor/XWPFWordExtractor.java?rev=1538044&r1=1538043&r2=1538044&view=diff
==============================================================================
---
poi/trunk/src/ooxml/java/org/apache/poi/xwpf/extractor/XWPFWordExtractor.java
(original)
+++
poi/trunk/src/ooxml/java/org/apache/poi/xwpf/extractor/XWPFWordExtractor.java
Fri Nov 1 19:43:46 2013
@@ -17,7 +17,6 @@
package org.apache.poi.xwpf.extractor;
import java.io.IOException;
-import java.util.Iterator;
import java.util.List;
import org.apache.poi.POIXMLDocument;
@@ -34,7 +33,6 @@ import org.apache.poi.xwpf.usermodel.XWP
import org.apache.poi.xwpf.usermodel.XWPFHyperlinkRun;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRelation;
-import org.apache.poi.xwpf.usermodel.XWPFRun;
import org.apache.poi.xwpf.usermodel.XWPFSDT;
import org.apache.poi.xwpf.usermodel.XWPFTable;
import org.apache.poi.xwpf.usermodel.XWPFTableCell;
@@ -85,24 +83,24 @@ public class XWPFWordExtractor extends P
System.out.println(extractor.getText());
}
- public String getText() {
- StringBuffer text = new StringBuffer();
- XWPFHeaderFooterPolicy hfPolicy =
document.getHeaderFooterPolicy();
+ public String getText() {
+ StringBuffer text = new StringBuffer();
+ XWPFHeaderFooterPolicy hfPolicy = document.getHeaderFooterPolicy();
+
+ // Start out with all headers
+ extractHeaders(text, hfPolicy);
+
+ // Process all body elements
+ for (IBodyElement e : document.getBodyElements()){
+ appendBodyElementText(text, e);
+ text.append('\n');
+ }
- // Start out with all headers
- extractHeaders(text, hfPolicy);
-
- // body elements
- for (IBodyElement e : document.getBodyElements()){
- appendBodyElementText(text, e);
- text.append('\n');
- }
-
- // Finish up with all the footers
- extractFooters(text, hfPolicy);
-
- return text.toString();
- }
+ // Finish up with all the footers
+ extractFooters(text, hfPolicy);
+
+ return text.toString();
+ }
public void appendBodyElementText(StringBuffer text, IBodyElement e){
if (e instanceof XWPFParagraph){
@@ -178,6 +176,8 @@ public class XWPFWordExtractor extends P
}
private void extractFooters(StringBuffer text, XWPFHeaderFooterPolicy
hfPolicy) {
+ if (hfPolicy == null) return;
+
if(hfPolicy.getFirstPageFooter() != null) {
text.append( hfPolicy.getFirstPageFooter().getText() );
}
@@ -190,6 +190,8 @@ public class XWPFWordExtractor extends P
}
private void extractHeaders(StringBuffer text, XWPFHeaderFooterPolicy
hfPolicy) {
+ if (hfPolicy == null) return;
+
if(hfPolicy.getFirstPageHeader() != null) {
text.append( hfPolicy.getFirstPageHeader().getText() );
}
Modified:
poi/trunk/src/ooxml/testcases/org/apache/poi/xwpf/extractor/TestXWPFWordExtractor.java
URL:
http://svn.apache.org/viewvc/poi/trunk/src/ooxml/testcases/org/apache/poi/xwpf/extractor/TestXWPFWordExtractor.java?rev=1538044&r1=1538043&r2=1538044&view=diff
==============================================================================
---
poi/trunk/src/ooxml/testcases/org/apache/poi/xwpf/extractor/TestXWPFWordExtractor.java
(original)
+++
poi/trunk/src/ooxml/testcases/org/apache/poi/xwpf/extractor/TestXWPFWordExtractor.java
Fri Nov 1 19:43:46 2013
@@ -351,5 +351,16 @@ public class TestXWPFWordExtractor exten
assertEquals("controlled content loading-"+targ, true, hit);
}
assertEquals("controlled content loading hit count", targs.length,
hits);
+ ex.close();
+ }
+
+ /** No Header or Footer in document */
+ public void testBug55733() throws Exception {
+ XWPFDocument doc =
XWPFTestDataSamples.openSampleDocument("55733.docx");
+ XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
+
+ // Check it gives text without error
+ extractor.getText();
+ extractor.close();
}
}
Modified:
poi/trunk/src/scratchpad/testcases/org/apache/poi/hwpf/extractor/TestWordExtractorBugs.java
URL:
http://svn.apache.org/viewvc/poi/trunk/src/scratchpad/testcases/org/apache/poi/hwpf/extractor/TestWordExtractorBugs.java?rev=1538044&r1=1538043&r2=1538044&view=diff
==============================================================================
---
poi/trunk/src/scratchpad/testcases/org/apache/poi/hwpf/extractor/TestWordExtractorBugs.java
(original)
+++
poi/trunk/src/scratchpad/testcases/org/apache/poi/hwpf/extractor/TestWordExtractorBugs.java
Fri Nov 1 19:43:46 2013
@@ -45,5 +45,4 @@ public final class TestWordExtractorBugs
// Check it gives text without error
extractor.getText();
}
-
}
Added: poi/trunk/test-data/document/55733.docx
URL:
http://svn.apache.org/viewvc/poi/trunk/test-data/document/55733.docx?rev=1538044&view=auto
==============================================================================
Binary file - no diff available.
Propchange: poi/trunk/test-data/document/55733.docx
------------------------------------------------------------------------------
svn:mime-type = application/octet-stream
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
