[ https://issues.apache.org/jira/browse/TIKA-1565?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Tyler Palsulich updated TIKA-1565: ---------------------------------- Description: I am getting an exception parsing the following mht File {code} org.apache.tika.exception.TikaException: image/gif parse error at org.apache.tika.parser.image.ImageParser.parse(ImageParser.java:115) at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:239) at org.apache.tika.parser.mail.MailContentHandler.body(MailContentHandler.java:102) at org.apache.james.mime4j.parser.MimeStreamParser.parse(MimeStreamParser.java:133) at org.apache.tika.parser.mail.RFC822Parser.parse(RFC822Parser.java:76) at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:239) at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:239) at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:105) at org.apache.tika.example.MyTest.test1(MyTest.java:31) 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.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:45) at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:15) at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:42) at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:20) at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:28) at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:263) at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:68) at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:47) at org.junit.runners.ParentRunner$3.run(ParentRunner.java:231) at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:60) at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:229) at org.junit.runners.ParentRunner.access$000(ParentRunner.java:50) at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:222) at org.junit.runners.ParentRunner.run(ParentRunner.java:300) at org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:50) at org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:459) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:675) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:382) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:192) Caused by: javax.imageio.IIOException: Unexpected block type 1! at com.sun.imageio.plugins.gif.GIFImageReader.readMetadata(Unknown Source) at com.sun.imageio.plugins.gif.GIFImageReader.getWidth(Unknown Source) at org.apache.tika.parser.image.ImageParser.parse(ImageParser.java:92) ... 32 more {code} my test code: {code} AutoDetectParser parser = new AutoDetectParser(); BodyContentHandler handler = new BodyContentHandler(); Metadata metadata = new Metadata(); ParseContext context = new ParseContext(); parser.parse(new FileInputStream(new File(file)), handler, metadata,context); System.out.println(handler.toString()); {code} was: I am getting an exception parsing the following mht File org.apache.tika.exception.TikaException: image/gif parse error at org.apache.tika.parser.image.ImageParser.parse(ImageParser.java:115) at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:239) at org.apache.tika.parser.mail.MailContentHandler.body(MailContentHandler.java:102) at org.apache.james.mime4j.parser.MimeStreamParser.parse(MimeStreamParser.java:133) at org.apache.tika.parser.mail.RFC822Parser.parse(RFC822Parser.java:76) at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:239) at org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:239) at org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:105) at org.apache.tika.example.MyTest.test1(MyTest.java:31) 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.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:45) at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:15) at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:42) at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:20) at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:28) at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:263) at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:68) at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:47) at org.junit.runners.ParentRunner$3.run(ParentRunner.java:231) at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:60) at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:229) at org.junit.runners.ParentRunner.access$000(ParentRunner.java:50) at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:222) at org.junit.runners.ParentRunner.run(ParentRunner.java:300) at org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:50) at org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:459) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:675) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:382) at org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:192) Caused by: javax.imageio.IIOException: Unexpected block type 1! at com.sun.imageio.plugins.gif.GIFImageReader.readMetadata(Unknown Source) at com.sun.imageio.plugins.gif.GIFImageReader.getWidth(Unknown Source) at org.apache.tika.parser.image.ImageParser.parse(ImageParser.java:92) ... 32 more my test code: AutoDetectParser parser = new AutoDetectParser(); BodyContentHandler handler = new BodyContentHandler(); Metadata metadata = new Metadata(); ParseContext context = new ParseContext(); parser.parse(new FileInputStream(new File(file)), handler, metadata,context); System.out.println(handler.toString()); > image/gif parse error > --------------------- > > Key: TIKA-1565 > URL: https://issues.apache.org/jira/browse/TIKA-1565 > Project: Tika > Issue Type: Bug > Components: parser > Affects Versions: 1.7 > Environment: win7 x64 jdk1.7 > Reporter: lixin > Fix For: 1.7 > > Attachments: JNK16-1309-173.mht > > > I am getting an exception parsing the following mht File > {code} > org.apache.tika.exception.TikaException: image/gif parse error > at org.apache.tika.parser.image.ImageParser.parse(ImageParser.java:115) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:239) > at > org.apache.tika.parser.mail.MailContentHandler.body(MailContentHandler.java:102) > at > org.apache.james.mime4j.parser.MimeStreamParser.parse(MimeStreamParser.java:133) > at org.apache.tika.parser.mail.RFC822Parser.parse(RFC822Parser.java:76) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:239) > at > org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:239) > at > org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:105) > at org.apache.tika.example.MyTest.test1(MyTest.java:31) > 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.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:45) > at > org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:15) > at > org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:42) > at > org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:20) > at > org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:28) > at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:263) > at > org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:68) > at > org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:47) > at org.junit.runners.ParentRunner$3.run(ParentRunner.java:231) > at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:60) > at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:229) > at org.junit.runners.ParentRunner.access$000(ParentRunner.java:50) > at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:222) > at org.junit.runners.ParentRunner.run(ParentRunner.java:300) > at > org.eclipse.jdt.internal.junit4.runner.JUnit4TestReference.run(JUnit4TestReference.java:50) > at > org.eclipse.jdt.internal.junit.runner.TestExecution.run(TestExecution.java:38) > at > org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:459) > at > org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.runTests(RemoteTestRunner.java:675) > at > org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.run(RemoteTestRunner.java:382) > at > org.eclipse.jdt.internal.junit.runner.RemoteTestRunner.main(RemoteTestRunner.java:192) > Caused by: javax.imageio.IIOException: Unexpected block type 1! > at com.sun.imageio.plugins.gif.GIFImageReader.readMetadata(Unknown > Source) > at com.sun.imageio.plugins.gif.GIFImageReader.getWidth(Unknown Source) > at org.apache.tika.parser.image.ImageParser.parse(ImageParser.java:92) > ... 32 more > {code} > my test code: > {code} > AutoDetectParser parser = new AutoDetectParser(); > BodyContentHandler handler = new BodyContentHandler(); > Metadata metadata = new Metadata(); > ParseContext context = new ParseContext(); > parser.parse(new FileInputStream(new File(file)), handler, > metadata,context); > System.out.println(handler.toString()); > {code} -- This message was sent by Atlassian JIRA (v6.3.4#6332)