Author: nick
Date: Fri Jan 13 15:01:54 2012
New Revision: 1231117
URL: http://svn.apache.org/viewvc?rev=1231117&view=rev
Log:
TIKA-840 Update the OOXML parsers, so that rather than hard coding the content
type, the file specific one is feteched and set
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java?rev=1231117&r1=1231116&r2=1231117&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/AbstractOOXMLExtractor.java
Fri Jan 13 15:01:54 2012
@@ -64,11 +64,8 @@ public abstract class AbstractOOXMLExtra
private final EmbeddedDocumentExtractor embeddedExtractor;
- private final String type;
-
- public AbstractOOXMLExtractor(ParseContext context, POIXMLTextExtractor
extractor, String type) {
+ public AbstractOOXMLExtractor(ParseContext context, POIXMLTextExtractor
extractor) {
this.extractor = extractor;
- this.type = type;
EmbeddedDocumentExtractor ex =
context.get(EmbeddedDocumentExtractor.class);
@@ -91,7 +88,7 @@ public abstract class AbstractOOXMLExtra
* @see
org.apache.tika.parser.microsoft.ooxml.OOXMLExtractor#getMetadataExtractor()
*/
public MetadataExtractor getMetadataExtractor() {
- return new MetadataExtractor(extractor, type);
+ return new MetadataExtractor(extractor);
}
/**
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java?rev=1231117&r1=1231116&r2=1231117&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/MetadataExtractor.java
Fri Jan 13 15:01:54 2012
@@ -44,16 +44,11 @@ public class MetadataExtractor {
private final POIXMLTextExtractor extractor;
- private final String type;
-
- public MetadataExtractor(POIXMLTextExtractor extractor, String type) {
+ public MetadataExtractor(POIXMLTextExtractor extractor) {
this.extractor = extractor;
- this.type = type;
}
public void extract(Metadata metadata) throws TikaException {
- addProperty(metadata, Metadata.CONTENT_TYPE, type);
-
if (extractor.getDocument() != null ||
(extractor instanceof XSSFEventBasedExcelExtractor &&
extractor.getPackage() != null)) {
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java?rev=1231117&r1=1231116&r2=1231117&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLExtractorFactory.java
Fri Jan 13 15:01:54 2012
@@ -35,7 +35,10 @@ import org.apache.tika.exception.TikaExc
import org.apache.tika.io.CloseShieldInputStream;
import org.apache.tika.io.TikaInputStream;
import org.apache.tika.metadata.Metadata;
+import org.apache.tika.mime.MediaType;
+import org.apache.tika.parser.EmptyParser;
import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.pkg.ZipContainerDetector;
import org.apache.tika.sax.EndDocumentShieldingContentHandler;
import org.apache.xmlbeans.XmlException;
import org.xml.sax.ContentHandler;
@@ -56,21 +59,31 @@ public class OOXMLExtractorFactory {
try {
OOXMLExtractor extractor;
+ OPCPackage pkg;
- POIXMLTextExtractor poiExtractor;
+ // Open the OPCPackage for the file
TikaInputStream tis = TikaInputStream.cast(stream);
if (tis != null && tis.getOpenContainer() instanceof OPCPackage) {
- poiExtractor = ExtractorFactory.createExtractor(
- (OPCPackage) tis.getOpenContainer());
+ pkg = (OPCPackage) tis.getOpenContainer();
} else if (tis != null && tis.hasFile()) {
- poiExtractor = (POIXMLTextExtractor)
- ExtractorFactory.createExtractor(tis.getFile());
+ pkg = OPCPackage.open( tis.getFile().getPath() );
} else {
InputStream shield = new CloseShieldInputStream(stream);
- poiExtractor = (POIXMLTextExtractor)
- ExtractorFactory.createExtractor(shield);
+ pkg = OPCPackage.open(shield);
}
+
+ // Get the type, and ensure it's one we handle
+ MediaType type = ZipContainerDetector.detectOfficeOpenXML(pkg);
+ if (type != null &&
OOXMLParser.UNSUPPORTED_OOXML_TYPES.contains(type)) {
+ // Not a supported type, delegate to Empty Parser
+ EmptyParser.INSTANCE.parse(stream, baseHandler, metadata,
context);
+ return;
+ }
+ metadata.set(Metadata.CONTENT_TYPE, type.toString());
+ // Have the appropriate OOXML text extractor picked
+ POIXMLTextExtractor poiExtractor =
ExtractorFactory.createExtractor(pkg);
+
POIXMLDocument document = poiExtractor.getDocument();
if (poiExtractor instanceof XSSFEventBasedExcelExtractor) {
extractor = new XSSFExcelExtractorDecorator(
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java?rev=1231117&r1=1231116&r2=1231117&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParser.java
Fri Jan 13 15:01:54 2012
@@ -27,7 +27,6 @@ import org.apache.tika.exception.TikaExc
import org.apache.tika.metadata.Metadata;
import org.apache.tika.mime.MediaType;
import org.apache.tika.parser.AbstractParser;
-import org.apache.tika.parser.EmptyParser;
import org.apache.tika.parser.ParseContext;
import org.xml.sax.ContentHandler;
import org.xml.sax.SAXException;
@@ -40,7 +39,7 @@ public class OOXMLParser extends Abstrac
/** Serial version UID */
private static final long serialVersionUID = 6535995710857776481L;
- private static final Set<MediaType> SUPPORTED_TYPES =
+ protected static final Set<MediaType> SUPPORTED_TYPES =
Collections.unmodifiableSet(new HashSet<MediaType>(Arrays.asList(
MediaType.application("x-tika-ooxml"),
MediaType.application("vnd.openxmlformats-officedocument.presentationml.presentation"),
@@ -65,7 +64,7 @@ public class OOXMLParser extends Abstrac
* This list is used to decline certain formats that are not yet supported
* by Tika and/or POI.
*/
- private static final Set<MediaType> UNSUPPORTED_OOXML_TYPES =
+ protected static final Set<MediaType> UNSUPPORTED_OOXML_TYPES =
Collections.unmodifiableSet(new HashSet<MediaType>(Arrays.asList(
MediaType.application("vnd.ms-excel.sheet.binary.macroenabled.12"),
MediaType.application("vnd.ms-xpsdocument")
@@ -79,14 +78,6 @@ public class OOXMLParser extends Abstrac
InputStream stream, ContentHandler handler,
Metadata metadata, ParseContext context)
throws IOException, SAXException, TikaException {
- // Is this an OOXML derived type that we can't help with?
- String type = metadata.get(Metadata.CONTENT_TYPE);
- if (type != null &&
UNSUPPORTED_OOXML_TYPES.contains(MediaType.parse(type))) {
- // Not a supported type, delegate to Empty Parser
- EmptyParser.INSTANCE.parse(stream, handler, metadata, context);
- return;
- }
-
// Have the OOXML file processed
OOXMLExtractorFactory.parse(stream, handler, metadata, context);
}
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java?rev=1231117&r1=1231116&r2=1231117&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/POIXMLTextExtractorDecorator.java
Fri Jan 13 15:01:54 2012
@@ -28,7 +28,7 @@ import org.xml.sax.SAXException;
public class POIXMLTextExtractorDecorator extends AbstractOOXMLExtractor {
public POIXMLTextExtractorDecorator(ParseContext context,
POIXMLTextExtractor extractor) {
- super(context, extractor, null);
+ super(context, extractor);
}
@Override
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java?rev=1231117&r1=1231116&r2=1231117&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSLFPowerPointExtractorDecorator.java
Fri Jan 13 15:01:54 2012
@@ -45,12 +45,8 @@ import org.openxmlformats.schemas.presen
import org.xml.sax.SAXException;
public class XSLFPowerPointExtractorDecorator extends AbstractOOXMLExtractor {
- // TODO Have this detected rather than hard coded
- //private static final String TYPE =
"application/vnd.openxmlformats-officedocument.presentationml.presentation";
- private static final String TYPE = null;
-
public XSLFPowerPointExtractorDecorator(ParseContext context,
XSLFPowerPointExtractor extractor) {
- super(context, extractor, TYPE);
+ super(context, extractor);
}
/**
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java?rev=1231117&r1=1231116&r2=1231117&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XSSFExcelExtractorDecorator.java
Fri Jan 13 15:01:54 2012
@@ -66,12 +66,9 @@ public class XSSFExcelExtractorDecorator
private final List<PackagePart> sheetParts = new ArrayList<PackagePart>();
private final List<Boolean> sheetProtected = new ArrayList<Boolean>();
- // TODO Have this detected rather than hard coded
- private static final String TYPE =
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet";
-
public XSSFExcelExtractorDecorator(
ParseContext context, XSSFEventBasedExcelExtractor extractor,
Locale locale) {
- super(context, extractor, TYPE);
+ super(context, extractor);
this.extractor = extractor;
extractor.setFormulasNotResults(false);
@@ -350,7 +347,7 @@ public class XSSFExcelExtractorDecorator
@Override
public MetadataExtractor getMetadataExtractor() {
- return new MetadataExtractor(extractor, TYPE) {
+ return new MetadataExtractor(extractor) {
@Override
public void extract(Metadata metadata) throws TikaException {
super.extract(metadata);
Modified:
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java?rev=1231117&r1=1231116&r2=1231117&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
(original)
+++
tika/trunk/tika-parsers/src/main/java/org/apache/tika/parser/microsoft/ooxml/XWPFWordExtractorDecorator.java
Fri Jan 13 15:01:54 2012
@@ -24,7 +24,22 @@ import org.apache.poi.openxml4j.opc.Pack
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.model.XWPFCommentsDecorator;
import org.apache.poi.xwpf.model.XWPFHeaderFooterPolicy;
-import org.apache.poi.xwpf.usermodel.*;
+import org.apache.poi.xwpf.usermodel.BodyType;
+import org.apache.poi.xwpf.usermodel.IBody;
+import org.apache.poi.xwpf.usermodel.IBodyElement;
+import org.apache.poi.xwpf.usermodel.XWPFDocument;
+import org.apache.poi.xwpf.usermodel.XWPFHeaderFooter;
+import org.apache.poi.xwpf.usermodel.XWPFHyperlink;
+import org.apache.poi.xwpf.usermodel.XWPFHyperlinkRun;
+import org.apache.poi.xwpf.usermodel.XWPFParagraph;
+import org.apache.poi.xwpf.usermodel.XWPFPicture;
+import org.apache.poi.xwpf.usermodel.XWPFPictureData;
+import org.apache.poi.xwpf.usermodel.XWPFRun;
+import org.apache.poi.xwpf.usermodel.XWPFStyle;
+import org.apache.poi.xwpf.usermodel.XWPFStyles;
+import org.apache.poi.xwpf.usermodel.XWPFTable;
+import org.apache.poi.xwpf.usermodel.XWPFTableCell;
+import org.apache.poi.xwpf.usermodel.XWPFTableRow;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.parser.microsoft.WordExtractor;
import org.apache.tika.parser.microsoft.WordExtractor.TagAndStyle;
@@ -40,8 +55,7 @@ public class XWPFWordExtractorDecorator
private XWPFStyles styles;
public XWPFWordExtractorDecorator(ParseContext context, XWPFWordExtractor
extractor) {
- // TODO Have the type detected rather than hard coded
- super(context, extractor,
"application/vnd.openxmlformats-officedocument.wordprocessingml.document");
+ super(context, extractor);
document = (XWPFDocument) extractor.getDocument();
styles = document.getStyles();
Modified:
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java?rev=1231117&r1=1231116&r2=1231117&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
(original)
+++
tika/trunk/tika-parsers/src/test/java/org/apache/tika/parser/microsoft/ooxml/OOXMLParserTest.java
Fri Jan 13 15:01:54 2012
@@ -749,10 +749,9 @@ public class OOXMLParserTest extends Tik
input.close();
}
- // When detection / type is fixed, re-enable this
-// assertEquals(
-//
"application/vnd.openxmlformats-officedocument.presentationml.presentation",
-// metadata.get(Metadata.CONTENT_TYPE));
+ assertEquals(
+
"application/vnd.openxmlformats-officedocument.presentationml.presentation",
+ metadata.get(Metadata.CONTENT_TYPE));
assertEquals("JOUVIN ETIENNE", metadata.get(Metadata.AUTHOR));
assertEquals("EJ04325S",
metadata.get(Metadata.LAST_AUTHOR));
assertEquals("2011-08-22T13:30:53Z", metadata.get(Metadata.DATE));
