Stefan Burger
Tue, 09 Feb 2010 18:31:53 -0800
Hi,
I'm new at TIKA and also on this mailing list.
I use the TIKA 0.6 bundle under eclipse to extract metadata from files and it
works with all kind of files except PDFs.
I get the error message below.
The code was tested with several PDF's. Also, I tested the PDF's with an older
program, which is working under TIKA 0.5. And there the PDFs can be read.
Can anybody help me?
All regards
Stefan
org.osgi.framework.BundleException: Exception in
edu.emich.compsci.virtus.metadata.Activator.start() of bundle
edu.emich.compsci.virtus.Metadata.
at
org.eclipse.osgi.framework.internal.core.BundleContextImpl.startActivator(BundleContextImpl.java:806)
at
org.eclipse.osgi.framework.internal.core.BundleContextImpl.start(BundleContextImpl.java:755)
at
org.eclipse.osgi.framework.internal.core.BundleHost.startWorker(BundleHost.java:352)
at
org.eclipse.osgi.framework.internal.core.AbstractBundle.start(AbstractBundle.java:280)
at
org.eclipse.osgi.framework.internal.core.AbstractBundle.start(AbstractBundle.java:272)
at
org.eclipse.osgi.framework.internal.core.FrameworkCommandProvider._start(FrameworkCommandProvider.java:253)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at
org.eclipse.osgi.framework.internal.core.FrameworkCommandInterpreter.execute(FrameworkCommandInterpreter.java:155)
at
org.eclipse.osgi.framework.internal.core.FrameworkConsole.docommand(FrameworkConsole.java:303)
at
org.eclipse.osgi.framework.internal.core.FrameworkConsole.console(FrameworkConsole.java:288)
at
org.eclipse.osgi.framework.internal.core.FrameworkConsole.run(FrameworkConsole.java:224)
at java.lang.Thread.run(Unknown Source)
Caused by: java.lang.NoClassDefFoundError: Could not initialize class
org.apache.pdfbox.pdfparser.PDFParser
at org.apache.pdfbox.pdmodel.PDDocument.load(PDDocument.java:840)
at org.apache.pdfbox.pdmodel.PDDocument.load(PDDocument.java:808)
at org.apache.tika.parser.pdf.PDFParser.parse(PDFParser.java:53)
at
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:120)
at
org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:101)
at
edu.emich.compsci.virtus.metadata.extractor.MetaDataExtractor.getMetaData(MetaDataExtractor.java:62)
at edu.emich.compsci.virtus.metadata.Activator.start(Activator.java:21)
at
org.eclipse.osgi.framework.internal.core.BundleContextImpl$1.run(BundleContextImpl.java:783)
at java.security.AccessController.doPrivileged(Native Method)
at
org.eclipse.osgi.framework.internal.core.BundleContextImpl.startActivator(BundleContextImpl.java:774)
... 14 more
Nested Exception:
java.lang.NoClassDefFoundError: Could not initialize class
org.apache.pdfbox.pdfparser.PDFParser
at org.apache.pdfbox.pdmodel.PDDocument.load(PDDocument.java:840)
at org.apache.pdfbox.pdmodel.PDDocument.load(PDDocument.java:808)
at org.apache.tika.parser.pdf.PDFParser.parse(PDFParser.java:53)
at
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:120)
at
org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:101)
at
edu.emich.compsci.virtus.metadata.extractor.MetaDataExtractor.getMetaData(MetaDataExtractor.java:62)
at edu.emich.compsci.virtus.metadata.Activator.start(Activator.java:21)
at
org.eclipse.osgi.framework.internal.core.BundleContextImpl$1.run(BundleContextImpl.java:783)
at java.security.AccessController.doPrivileged(Native Method)
at
org.eclipse.osgi.framework.internal.core.BundleContextImpl.startActivator(BundleContextImpl.java:774)
at
org.eclipse.osgi.framework.internal.core.BundleContextImpl.start(BundleContextImpl.java:755)
at
org.eclipse.osgi.framework.internal.core.BundleHost.startWorker(BundleHost.java:352)
at
org.eclipse.osgi.framework.internal.core.AbstractBundle.start(AbstractBundle.java:280)
at
org.eclipse.osgi.framework.internal.core.AbstractBundle.start(AbstractBundle.java:272)
at
org.eclipse.osgi.framework.internal.core.FrameworkCommandProvider._start(FrameworkCommandProvider.java:253)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at
org.eclipse.osgi.framework.internal.core.FrameworkCommandInterpreter.execute(FrameworkCommandInterpreter.java:155)
at
org.eclipse.osgi.framework.internal.core.FrameworkConsole.docommand(FrameworkConsole.java:303)
at
org.eclipse.osgi.framework.internal.core.FrameworkConsole.console(FrameworkConsole.java:288)
at
org.eclipse.osgi.framework.internal.core.FrameworkConsole.run(FrameworkConsole.java:224)
at java.lang.Thread.run(Unknown Source)
Nested Exception:
java.lang.NoClassDefFoundError: Could not initialize class
org.apache.pdfbox.pdfparser.PDFParser
at org.apache.pdfbox.pdmodel.PDDocument.load(PDDocument.java:840)
at org.apache.pdfbox.pdmodel.PDDocument.load(PDDocument.java:808)
at org.apache.tika.parser.pdf.PDFParser.parse(PDFParser.java:53)
at
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:120)
at
org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:101)
at
edu.emich.compsci.virtus.metadata.extractor.MetaDataExtractor.getMetaData(MetaDataExtractor.java:62)
at edu.emich.compsci.virtus.metadata.Activator.start(Activator.java:21)
at
org.eclipse.osgi.framework.internal.core.BundleContextImpl$1.run(BundleContextImpl.java:783)
at java.security.AccessController.doPrivileged(Native Method)
at
org.eclipse.osgi.framework.internal.core.BundleContextImpl.startActivator(BundleContextImpl.java:774)
at
org.eclipse.osgi.framework.internal.core.BundleContextImpl.start(BundleContextImpl.java:755)
at
org.eclipse.osgi.framework.internal.core.BundleHost.startWorker(BundleHost.java:352)
at
org.eclipse.osgi.framework.internal.core.AbstractBundle.start(AbstractBundle.java:280)
at
org.eclipse.osgi.framework.internal.core.AbstractBundle.start(AbstractBundle.java:272)
at
org.eclipse.osgi.framework.internal.core.FrameworkCommandProvider._start(FrameworkCommandProvider.java:253)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at
org.eclipse.osgi.framework.internal.core.FrameworkCommandInterpreter.execute(FrameworkCommandInterpreter.java:155)
at
org.eclipse.osgi.framework.internal.core.FrameworkConsole.docommand(FrameworkConsole.java:303)
at
org.eclipse.osgi.framework.internal.core.FrameworkConsole.console(FrameworkConsole.java:288)
at
org.eclipse.osgi.framework.internal.core.FrameworkConsole.run(FrameworkConsole.java:224)
at java.lang.Thread.run(Unknown Source)
osgi>