You are viewing a plain text version of this content. The canonical link for it is here.
Posted to slide-dev@jakarta.apache.org by lu...@apache.org on 2005/01/14 19:34:14 UTC
cvs commit: jakarta-slide/src/share/org/apache/slide/extractor AbstractContentExtractor.java AbstractPropertyExtractor.java Extractor.java ExtractorManager.java MSExcelExtractor.java MSPowerPointExtractor.java MSWordExtractor.java OfficeExtractor.java PDFExtractor.java SimpleXmlExtractor.java TextContentExtractor.java XmlContentExtractor.java
luetzkendorf 2005/01/14 10:34:14
Modified: src/share/org/apache/slide/extractor
AbstractContentExtractor.java
AbstractPropertyExtractor.java Extractor.java
ExtractorManager.java MSExcelExtractor.java
MSPowerPointExtractor.java MSWordExtractor.java
OfficeExtractor.java PDFExtractor.java
SimpleXmlExtractor.java TextContentExtractor.java
XmlContentExtractor.java
Log:
Improvements by Eirikur S. Hrafnsson for Content-Type handling in
the extractor framework (see Bugzilla 33065)
Revision Changes Path
1.5 +20 -4 jakarta-slide/src/share/org/apache/slide/extractor/AbstractContentExtractor.java
Index: AbstractContentExtractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/AbstractContentExtractor.java,v
retrieving revision 1.4
retrieving revision 1.5
diff -u -r1.4 -r1.5
--- AbstractContentExtractor.java 29 Sep 2004 15:28:06 -0000 1.4
+++ AbstractContentExtractor.java 14 Jan 2005 18:34:13 -0000 1.5
@@ -47,10 +47,26 @@
public abstract Reader extract(InputStream content) throws ExtractorException;
+ /* (non-Javadoc)
+ * @see org.apache.slide.extractor.Extractor#getContentType()
+ */
public String getContentType() {
return contentType;
}
-
+
+ /**
+ * Default implementation returns true if getContentType() contains the fileToIndexContentType<br/>
+ * OR if getContentType() returns null.
+ * @param fileToIndexContentType The content type of the file we want to index.
+ */
+ public boolean isAcceptableContentType(String fileToIndexContentType) {
+ if(getContentType()!=null){
+ //return true if the contentType string contains fileToIndexContentType
+ return (getContentType().indexOf(fileToIndexContentType)>=0);
+ }
+ return true;
+ }
+
public String getUri() {
return uri;
}
1.4 +20 -4 jakarta-slide/src/share/org/apache/slide/extractor/AbstractPropertyExtractor.java
Index: AbstractPropertyExtractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/AbstractPropertyExtractor.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -r1.3 -r1.4
--- AbstractPropertyExtractor.java 29 Sep 2004 15:28:06 -0000 1.3
+++ AbstractPropertyExtractor.java 14 Jan 2005 18:34:13 -0000 1.4
@@ -23,8 +23,8 @@
package org.apache.slide.extractor;
-import java.util.Map;
import java.io.InputStream;
+import java.util.Map;
/**
* The AbstractPropertyExtractor class
@@ -47,6 +47,9 @@
public abstract Map extract(InputStream content) throws ExtractorException;
+ /* (non-Javadoc)
+ * @see org.apache.slide.extractor.Extractor#getContentType()
+ */
public String getContentType() {
return contentType;
}
@@ -58,5 +61,18 @@
public String getNamespace() {
return namespace;
}
+
+ /**
+ * Default implementation returns true if getContentType() contains the fileToIndexContentType<br/>
+ * OR if getContentType() returns null.
+ * @param fileToIndexContentType The content type of the file we want to index.
+ */
+ public boolean isAcceptableContentType(String fileToIndexContentType) {
+ if(getContentType()!=null){
+ //return true if the contentType string contains fileToIndexContentType
+ return (getContentType().indexOf(fileToIndexContentType)>=0);
+ }
+ return true;
+ }
}
1.6 +26 -6 jakarta-slide/src/share/org/apache/slide/extractor/Extractor.java
Index: Extractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/Extractor.java,v
retrieving revision 1.5
retrieving revision 1.6
diff -u -r1.5 -r1.6
--- Extractor.java 29 Sep 2004 15:28:06 -0000 1.5
+++ Extractor.java 14 Jan 2005 18:34:13 -0000 1.6
@@ -24,15 +24,35 @@
package org.apache.slide.extractor;
/**
- * The Extractor interface
- *
+ * The Extractor interface.<br/>
+ * Default init parameters in Domain.xml include:<br/>
+ * <li>"classname" - The extractor class.</li>
+ * <li>"uri" - The URI the extractor handles.</li>
+ * <li>"content-type" - A comma separated list of supported content types</li>
+ * <li>"namespace" - The namespace the extractor handles.</li>
*/
public interface Extractor {
- public String getContentType();
+ /**
+ * @param contentType of the file to index
+ * @return true if this extractor can handle indexing a file of the supplied contentType otherwise false.
+ */
+ public boolean isAcceptableContentType(String contentType);
+ /**
+ * @return a comma separated list of content types this extractor is registered to handle.<br/>
+ * May return null also if it handles any type of file.
+ */
+ public String getContentType();
+
+ /**
+ * @return The URI this extractor is registered to handle.
+ */
public String getUri();
+ /**
+ * @return The namespace this extractor is registered to handle.
+ */
public String getNamespace();
}
1.7 +15 -15 jakarta-slide/src/share/org/apache/slide/extractor/ExtractorManager.java
Index: ExtractorManager.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/ExtractorManager.java,v
retrieving revision 1.6
retrieving revision 1.7
diff -u -r1.6 -r1.7
--- ExtractorManager.java 8 Nov 2004 09:37:43 -0000 1.6
+++ ExtractorManager.java 14 Jan 2005 18:34:13 -0000 1.7
@@ -23,17 +23,20 @@
package org.apache.slide.extractor;
+import java.lang.reflect.Constructor;
+import java.util.ArrayList;
+import java.util.Enumeration;
+import java.util.Iterator;
+import java.util.List;
+import org.apache.slide.content.NodeRevisionDescriptor;
+import org.apache.slide.content.NodeRevisionDescriptors;
import org.apache.slide.util.conf.Configurable;
import org.apache.slide.util.conf.Configuration;
import org.apache.slide.util.conf.ConfigurationException;
-import org.apache.slide.content.NodeRevisionDescriptors;
-import org.apache.slide.content.NodeRevisionDescriptor;
-
-import java.util.*;
-import java.lang.reflect.Constructor;
/**
* The ExtractorManager class
+ *
*/
public class ExtractorManager implements Configurable {
private final static ExtractorManager manager = new ExtractorManager();
@@ -103,8 +106,7 @@
{
for ( Iterator i = extractors.iterator(); i.hasNext(); ) {
Extractor extractor = (Extractor)i.next();
- if ( extractor instanceof ContentExtractor &&
- matches(extractor, namespace, uri, descriptor)) {
+ if ( extractor instanceof ContentExtractor && matches(extractor, namespace, uri, descriptor)) {
return true;
}
}
@@ -113,7 +115,7 @@
static boolean matches(Extractor extractor, String namespace, NodeRevisionDescriptors descriptors, NodeRevisionDescriptor descriptor) {
boolean matching = true;
- if ( descriptor != null && extractor.getContentType() != null && !descriptor.getContentType().equals(extractor.getContentType()) ) {
+ if ( descriptor != null && !extractor.isAcceptableContentType(descriptor.getContentType())) {
matching = false;
}
if ( descriptors != null && extractor.getUri() != null && !descriptors.getUri().startsWith(extractor.getUri()) ) {
@@ -125,10 +127,8 @@
return matching;
}
- static boolean matches(Extractor extractor, String namespace, String uri,
- NodeRevisionDescriptor descriptor)
- {
- if ( descriptor != null && !descriptor.getContentType().equals(extractor.getContentType()) ) {
+ static boolean matches(Extractor extractor, String namespace, String uri, NodeRevisionDescriptor descriptor) {
+ if ( descriptor != null && !extractor.isAcceptableContentType(descriptor.getContentType()) ) {
return false;
}
if ( extractor.getUri() != null && !uri.startsWith(extractor.getUri()) ) {
1.3 +31 -17 jakarta-slide/src/share/org/apache/slide/extractor/MSExcelExtractor.java
Index: MSExcelExtractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/MSExcelExtractor.java,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- MSExcelExtractor.java 29 Sep 2004 15:28:06 -0000 1.2
+++ MSExcelExtractor.java 14 Jan 2005 18:34:13 -0000 1.3
@@ -23,23 +23,27 @@
package org.apache.slide.extractor;
-/**
- * Author: Ryan Rhodes
- * Date: Jun 26, 2004
- * Time: 1:53:31 AM
- */
-
-import java.io.*;
+import java.io.CharArrayReader;
+import java.io.CharArrayWriter;
+import java.io.FileInputStream;
+import java.io.InputStream;
+import java.io.Reader;
import java.util.Iterator;
-
-import org.apache.poi.poifs.filesystem.POIFSFileSystem;
-import org.apache.poi.hssf.usermodel.HSSFWorkbook;
-import org.apache.poi.hssf.usermodel.HSSFSheet;
-import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFCell;
+import org.apache.poi.hssf.usermodel.HSSFRow;
+import org.apache.poi.hssf.usermodel.HSSFSheet;
+import org.apache.poi.hssf.usermodel.HSSFWorkbook;
+import org.apache.poi.poifs.filesystem.POIFSFileSystem;
-public class MSExcelExtractor extends AbstractContentExtractor
-{
+/**
+ * Content extractor for Microsoft Excel documents.
+ */
+public class MSExcelExtractor extends AbstractContentExtractor {
+
+ static final String CONTENT_TYPE_EXCEL_1 = "application/msexcel";
+ static final String CONTENT_TYPE_EXCEL_2 = "application/vnd.ms-excel";
+ static final String CONTENT_TYPE_EXCEL_ALL_CSV = CONTENT_TYPE_EXCEL_1+","+CONTENT_TYPE_EXCEL_2;
+
public MSExcelExtractor(String uri, String contentType, String namespace) {
super(uri, contentType, namespace);
}
@@ -104,4 +108,14 @@
}
while(c != -1);
}
+
+ /* (non-Javadoc)
+ * @see org.apache.slide.extractor.Extractor#getContentType()
+ */
+ public String getContentType() {
+ if(super.getContentType()==null){
+ return CONTENT_TYPE_EXCEL_ALL_CSV;
+ }
+ return super.getContentType();
+ }
}
1.4 +29 -13 jakarta-slide/src/share/org/apache/slide/extractor/MSPowerPointExtractor.java
Index: MSPowerPointExtractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/MSPowerPointExtractor.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -r1.3 -r1.4
--- MSPowerPointExtractor.java 29 Sep 2004 15:28:06 -0000 1.3
+++ MSPowerPointExtractor.java 14 Jan 2005 18:34:13 -0000 1.4
@@ -23,21 +23,27 @@
package org.apache.slide.extractor;
-import org.apache.poi.util.LittleEndian;
-import org.apache.poi.poifs.eventfilesystem.POIFSReaderListener;
-import org.apache.poi.poifs.eventfilesystem.POIFSReaderEvent;
+import java.io.ByteArrayInputStream;
+import java.io.ByteArrayOutputStream;
+import java.io.FileInputStream;
+import java.io.InputStream;
+import java.io.InputStreamReader;
+import java.io.Reader;
import org.apache.poi.poifs.eventfilesystem.POIFSReader;
+import org.apache.poi.poifs.eventfilesystem.POIFSReaderEvent;
+import org.apache.poi.poifs.eventfilesystem.POIFSReaderListener;
import org.apache.poi.poifs.filesystem.DocumentInputStream;
-
-import java.io.*;
+import org.apache.poi.util.LittleEndian;
/**
- * Author: Ryan Rhodes
- * Date: Jun 27, 2004
- * Time: 3:45:39 AM
+ * Content extractor for Microsoft Powerpoint documents.
*/
-public class MSPowerPointExtractor extends AbstractContentExtractor implements POIFSReaderListener
-{
+public class MSPowerPointExtractor extends AbstractContentExtractor implements POIFSReaderListener{
+
+ static final String CONTENT_TYPE_POWERPOINT_1 = "application/mspowerpoint";
+ static final String CONTENT_TYPE_POWERPOINT_2 = "application/vnd.ms-powerpoint";
+ static final String CONTENT_TYPE_POWERPOINT_ALL_CSV = CONTENT_TYPE_POWERPOINT_1+","+CONTENT_TYPE_POWERPOINT_2;
+
private ByteArrayOutputStream writer = new ByteArrayOutputStream();
public MSPowerPointExtractor(String uri, String contentType, String namespace) {
@@ -104,4 +110,14 @@
}
while( c != -1 );
}
+
+ /* (non-Javadoc)
+ * @see org.apache.slide.extractor.Extractor#getContentType()
+ */
+ public String getContentType() {
+ if(super.getContentType()==null){
+ return CONTENT_TYPE_POWERPOINT_ALL_CSV;
+ }
+ return super.getContentType();
+ }
}
1.3 +26 -13 jakarta-slide/src/share/org/apache/slide/extractor/MSWordExtractor.java
Index: MSWordExtractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/MSWordExtractor.java,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- MSWordExtractor.java 29 Sep 2004 15:28:06 -0000 1.2
+++ MSWordExtractor.java 14 Jan 2005 18:34:13 -0000 1.3
@@ -23,17 +23,20 @@
package org.apache.slide.extractor;
-/**
- * Author: Ryan Rhodes
- * Date: Jun 26, 2004
- * Time: 12:34:29 AM
- */
-
-import java.io.*;
-
+import java.io.FileInputStream;
+import java.io.InputStream;
+import java.io.Reader;
+import java.io.StringReader;
import org.textmining.text.extraction.WordExtractor;
+/**
+ * Content extractor for Microsoft Word documents.
+ */
public class MSWordExtractor extends AbstractContentExtractor {
+
+ static final String CONTENT_TYPE_WORD_1 = "application/msword";
+ static final String CONTENT_TYPE_WORD_2 = "application/vnd.ms-word";
+ static final String CONTENT_TYPE_WORD_ALL_CSV = CONTENT_TYPE_WORD_1+","+CONTENT_TYPE_WORD_2;
public MSWordExtractor(String uri, String contentType, String namespace) {
super(uri, contentType, namespace);
@@ -41,8 +44,7 @@
public Reader extract(InputStream content) throws ExtractorException {
try {
- WordExtractor extractor =
- new WordExtractor();
+ WordExtractor extractor = new WordExtractor();
String text = extractor.extractText(content);
StringReader reader = new StringReader(text);
@@ -70,4 +72,15 @@
}
while( c != -1 );
}
+
+ /* (non-Javadoc)
+ * @see org.apache.slide.extractor.Extractor#getContentType()
+ */
+ public String getContentType() {
+ if(super.getContentType()==null){
+ return CONTENT_TYPE_WORD_ALL_CSV;
+ }
+ return super.getContentType();
+ }
+
}
1.4 +27 -6 jakarta-slide/src/share/org/apache/slide/extractor/OfficeExtractor.java
Index: OfficeExtractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/OfficeExtractor.java,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -r1.3 -r1.4
--- OfficeExtractor.java 29 Sep 2004 15:28:06 -0000 1.3
+++ OfficeExtractor.java 14 Jan 2005 18:34:13 -0000 1.4
@@ -1,21 +1,31 @@
package org.apache.slide.extractor;
import java.io.InputStream;
-import java.util.*;
-
-import org.apache.poi.hpsf.*;
-import org.apache.poi.poifs.eventfilesystem.*;
+import java.util.ArrayList;
+import java.util.Enumeration;
+import java.util.HashMap;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
+import org.apache.poi.hpsf.NoPropertySetStreamException;
+import org.apache.poi.hpsf.Property;
+import org.apache.poi.hpsf.PropertySet;
+import org.apache.poi.hpsf.PropertySetFactory;
+import org.apache.poi.hpsf.Section;
+import org.apache.poi.poifs.eventfilesystem.POIFSReader;
+import org.apache.poi.poifs.eventfilesystem.POIFSReaderEvent;
+import org.apache.poi.poifs.eventfilesystem.POIFSReaderListener;
import org.apache.slide.util.conf.Configurable;
import org.apache.slide.util.conf.Configuration;
import org.apache.slide.util.conf.ConfigurationException;
/**
- * The OfficeExtractor class
- *
+ * Property extractor for Microsoft office documents.
*/
public class OfficeExtractor extends AbstractPropertyExtractor implements Configurable {
protected List instructions = new ArrayList();
protected Map propertyMap = new HashMap();
+ static final String CONTENT_TYPE_MS_OFFICE_ALL_CSV = MSWordExtractor.CONTENT_TYPE_WORD_ALL_CSV+","+MSExcelExtractor.CONTENT_TYPE_EXCEL_ALL_CSV+","+MSPowerPointExtractor.CONTENT_TYPE_POWERPOINT_ALL_CSV;
public OfficeExtractor(String uri, String contentType, String namespace) {
super(uri, contentType, namespace);
@@ -81,4 +91,15 @@
propertyMap.put(id, property);
}
}
+
+ /* (non-Javadoc)
+ * @see org.apache.slide.extractor.Extractor#getContentType()
+ */
+ public String getContentType() {
+ if(super.getContentType()==null){
+ return CONTENT_TYPE_MS_OFFICE_ALL_CSV;
+ }
+ return super.getContentType();
+ }
+
}
1.3 +27 -11 jakarta-slide/src/share/org/apache/slide/extractor/PDFExtractor.java
Index: PDFExtractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/PDFExtractor.java,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- PDFExtractor.java 29 Sep 2004 15:28:06 -0000 1.2
+++ PDFExtractor.java 14 Jan 2005 18:34:13 -0000 1.3
@@ -23,19 +23,24 @@
package org.apache.slide.extractor;
-import org.pdfbox.util.PDFTextStripper;
+import java.io.CharArrayReader;
+import java.io.CharArrayWriter;
+import java.io.FileInputStream;
+import java.io.InputStream;
+import java.io.Reader;
import org.pdfbox.pdfparser.PDFParser;
import org.pdfbox.pdmodel.PDDocument;
-
-import java.io.*;
+import org.pdfbox.util.PDFTextStripper;
/**
- * Author: Ryan Rhodes
- * Date: Jun 26, 2004
- * Time: 4:03:00 AM
+ * Content extractor for PDF documents.
*/
-public class PDFExtractor extends AbstractContentExtractor
-{
+public class PDFExtractor extends AbstractContentExtractor{
+
+ private static final String CONTENT_TYPE_PDF_1 = "application/pdf";
+ private static final String CONTENT_TYPE_PDF_2 = "application/x-pdf";
+ private static final String CONTENT_TYPE_PDF_ALL_CSV = CONTENT_TYPE_PDF_1+","+CONTENT_TYPE_PDF_2;
+
public PDFExtractor(String uri, String contentType, String namespace)
{
@@ -84,4 +89,15 @@
}
while(c != -1);
}
+
+ /* (non-Javadoc)
+ * @see org.apache.slide.extractor.Extractor#getContentType()
+ */
+ public String getContentType() {
+ if(super.getContentType()==null){
+ return CONTENT_TYPE_PDF_ALL_CSV;
+ }
+ return super.getContentType();
+ }
+
}
1.11 +28 -8 jakarta-slide/src/share/org/apache/slide/extractor/SimpleXmlExtractor.java
Index: SimpleXmlExtractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/SimpleXmlExtractor.java,v
retrieving revision 1.10
retrieving revision 1.11
diff -u -r1.10 -r1.11
--- SimpleXmlExtractor.java 29 Nov 2004 18:44:30 -0000 1.10
+++ SimpleXmlExtractor.java 14 Jan 2005 18:34:13 -0000 1.11
@@ -23,6 +23,14 @@
package org.apache.slide.extractor;
+import java.io.IOException;
+import java.io.InputStream;
+import java.util.ArrayList;
+import java.util.Enumeration;
+import java.util.HashMap;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
import org.apache.slide.common.PropertyName;
import org.apache.slide.util.conf.Configurable;
import org.apache.slide.util.conf.Configuration;
@@ -34,16 +42,18 @@
import org.jdom.input.SAXBuilder;
import org.jdom.xpath.XPath;
-import java.io.IOException;
-import java.io.InputStream;
-import java.util.*;
-
/**
* The SimpleXmlExtractor class
*
*/
public class SimpleXmlExtractor extends AbstractPropertyExtractor implements Configurable {
-
+
+ static final String CONTENT_TYPE_XML = "text/xml";
+ static final String CONTENT_TYPE_XHTML = "application/xhtml+xml";
+ //html also because xhtml can and most often has the html content type
+ static final String CONTENT_TYPE_HTML = "text/html";
+ static final String CONTENT_TYPE_XML_ALL_CSV = CONTENT_TYPE_XML+","+CONTENT_TYPE_XHTML+","+CONTENT_TYPE_HTML;
+
protected List instructions = new ArrayList();
public SimpleXmlExtractor(String uri, String contentType, String namespace) {
@@ -133,4 +143,14 @@
return propertyName;
}
}
+
+ /* (non-Javadoc)
+ * @see org.apache.slide.extractor.Extractor#getContentType()
+ */
+ public String getContentType() {
+ if(super.getContentType()==null){
+ return CONTENT_TYPE_XML_ALL_CSV;
+ }
+ return super.getContentType();
+ }
}
1.3 +16 -5 jakarta-slide/src/share/org/apache/slide/extractor/TextContentExtractor.java
Index: TextContentExtractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/TextContentExtractor.java,v
retrieving revision 1.2
retrieving revision 1.3
diff -u -r1.2 -r1.3
--- TextContentExtractor.java 29 Nov 2004 18:43:09 -0000 1.2
+++ TextContentExtractor.java 14 Jan 2005 18:34:13 -0000 1.3
@@ -30,8 +30,9 @@
/**
* Content extractor that simply returns the content.
*/
-public class TextContentExtractor extends AbstractContentExtractor
-{
+public class TextContentExtractor extends AbstractContentExtractor{
+
+ private static final String CONTENT_TYPE_TEXT = "text/plain";
public TextContentExtractor(String uri, String contentType)
{
@@ -46,5 +47,15 @@
{
return new InputStreamReader(content);
}
+
+ /* (non-Javadoc)
+ * @see org.apache.slide.extractor.Extractor#getContentType()
+ */
+ public String getContentType() {
+ if(super.getContentType()==null){
+ return CONTENT_TYPE_TEXT;
+ }
+ return super.getContentType();
+ }
}
1.2 +13 -3 jakarta-slide/src/share/org/apache/slide/extractor/XmlContentExtractor.java
Index: XmlContentExtractor.java
===================================================================
RCS file: /home/cvs/jakarta-slide/src/share/org/apache/slide/extractor/XmlContentExtractor.java,v
retrieving revision 1.1
retrieving revision 1.2
diff -u -r1.1 -r1.2
--- XmlContentExtractor.java 29 Nov 2004 18:43:21 -0000 1.1
+++ XmlContentExtractor.java 14 Jan 2005 18:34:13 -0000 1.2
@@ -124,4 +124,14 @@
return new InputSource(new StringReader(""));
}
}
+
+ /* (non-Javadoc)
+ * @see org.apache.slide.extractor.Extractor#getContentType()
+ */
+ public String getContentType() {
+ if(super.getContentType()==null){
+ return SimpleXmlExtractor.CONTENT_TYPE_XML_ALL_CSV;
+ }
+ return super.getContentType();
+ }
}
---------------------------------------------------------------------
To unsubscribe, e-mail: slide-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: slide-dev-help@jakarta.apache.org