[
https://issues.apache.org/jira/browse/TIKA-2094?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15534813#comment-15534813
]
wangruochan commented on TIKA-2094:
-----------------------------------
It's OK to use the file under the Apache License.
However, I try to using the solution above like this,there are some other
classes not found
{code:xml}
<dependencies>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parsers</artifactId>
<version>1.13</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>3.15-beta1</version>
<exclusions>
<exclusion>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml-schemas</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>ooxml-schemas</artifactId>
<version>1.3</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>ooxml-security</artifactId>
<version>1.1</version>
</dependency>
</dependencies>
{code}
Exception in thread "main" java.lang.NoClassDefFoundError:
com/microsoft/schemas/office/visio/x2012/main/VisioDocumentDocument1$Factory
at
org.apache.poi.xdgf.usermodel.XmlVisioDocument.<init>(XmlVisioDocument.java:69)
at
org.apache.poi.xdgf.extractor.XDGFVisioExtractor.<init>(XDGFVisioExtractor.java:41)
at
org.apache.poi.extractor.ExtractorFactory.createExtractor(ExtractorFactory.java:212)
at
org.apache.tika.parser.microsoft.ooxml.OOXMLExtractorFactory.parse(OOXMLExtractorFactory.java:86)
at
org.apache.tika.parser.microsoft.ooxml.OOXMLParser.parse(OOXMLParser.java:87)
at
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280)
at
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280)
at
org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at
org.apache.tika.parser.DelegatingParser.parse(DelegatingParser.java:72)
at
org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor.parseEmbedded(ParsingEmbeddedDocumentExtractor.java:102)
at
org.apache.tika.parser.microsoft.AbstractPOIFSExtractor.handleEmbeddedResource(AbstractPOIFSExtractor.java:140)
at
org.apache.tika.parser.microsoft.AbstractPOIFSExtractor.handleEmbeddedOfficeDoc(AbstractPOIFSExtractor.java:164)
at
org.apache.tika.parser.microsoft.WordExtractor.parse(WordExtractor.java:208)
at
org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:146)
at
org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:117)
at
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280)
at
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280)
at
org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at test.apache.tika.Test.main(Test.java:29)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at com.intellij.rt.execution.application.AppMain.main(AppMain.java:147)
Caused by: java.lang.ClassNotFoundException:
com.microsoft.schemas.office.visio.x2012.main.VisioDocumentDocument1$Factory
at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
... 24 more
{code}
> Error parsing .doc file with visio embed
> ----------------------------------------
>
> Key: TIKA-2094
> URL: https://issues.apache.org/jira/browse/TIKA-2094
> Project: Tika
> Issue Type: Bug
> Affects Versions: 1.13
> Environment: JDK7
> Reporter: wangruochan
> Attachments: testtika.doc, testtika.doc
>
>
> when I try to parse a .doc file with a visio embeb,an exception occurred,
> Print the stacktrace below:
> Exception in thread "main" java.lang.NoClassDefFoundError:
> com/microsoft/schemas/office/visio/x2012/main/ConnectsType
> at
> com.microsoft.schemas.office.visio.x2012.main.impl.PageContentsTypeImpl.getConnects(Unknown
> Source)
> at
> org.apache.poi.xdgf.usermodel.XDGFBaseContents.onDocumentRead(XDGFBaseContents.java:89)
> at
> org.apache.poi.xdgf.usermodel.XDGFPageContents.onDocumentRead(XDGFPageContents.java:73)
> at
> org.apache.poi.xdgf.usermodel.XDGFPages.onDocumentRead(XDGFPages.java:94)
> at
> org.apache.poi.xdgf.usermodel.XmlVisioDocument.onDocumentRead(XmlVisioDocument.java:108)
> at org.apache.poi.POIXMLDocument.load(POIXMLDocument.java:160)
> at
> org.apache.poi.xdgf.usermodel.XmlVisioDocument.<init>(XmlVisioDocument.java:79)
> at
> org.apache.poi.xdgf.extractor.XDGFVisioExtractor.<init>(XDGFVisioExtractor.java:41)
> at
> org.apache.poi.extractor.ExtractorFactory.createExtractor(ExtractorFactory.java:212)
> at
> org.apache.tika.parser.microsoft.ooxml.OOXMLExtractorFactory.parse(OOXMLExtractorFactory.java:86)
> at
> org.apache.tika.parser.microsoft.ooxml.OOXMLParser.parse(OOXMLParser.java:87)
> at
> org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280)
> at
> org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280)
> at
> org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
> at
> org.apache.tika.parser.DelegatingParser.parse(DelegatingParser.java:72)
> at
> org.apache.tika.extractor.ParsingEmbeddedDocumentExtractor.parseEmbedded(ParsingEmbeddedDocumentExtractor.java:102)
> at
> org.apache.tika.parser.microsoft.AbstractPOIFSExtractor.handleEmbeddedResource(AbstractPOIFSExtractor.java:140)
> at
> org.apache.tika.parser.microsoft.AbstractPOIFSExtractor.handleEmbeddedOfficeDoc(AbstractPOIFSExtractor.java:164)
> at
> org.apache.tika.parser.microsoft.WordExtractor.parse(WordExtractor.java:208)
> at
> org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:146)
> at
> org.apache.tika.parser.microsoft.OfficeParser.parse(OfficeParser.java:117)
> at
> org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280)
> at
> org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:280)
> at
> org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
> at test.apache.tika.Test.main(Test.java:29)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at com.intellij.rt.execution.application.AppMain.main(AppMain.java:147)
> Caused by: java.lang.ClassNotFoundException:
> com.microsoft.schemas.office.visio.x2012.main.ConnectsType
> at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
> at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
> at java.security.AccessController.doPrivileged(Native Method)
> at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
> at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
> at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
> ... 30 more
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)