Sharath Kumar created TIKA-2146:
-----------------------------------
Summary: Unable to extract contents from protected MS
word-doc-java.lang.ArrayIndexOutOfBoundsException
Key: TIKA-2146
URL: https://issues.apache.org/jira/browse/TIKA-2146
Project: Tika
Issue Type: Bug
Components: core
Affects Versions: 1.11
Environment: Windows 7
Reporter: Sharath Kumar
When I try to parse a MS word document which is protected, I am unable to
extract the content rather, i get the below exception
org.apache.tika.exception.TikaException: Unexpected RuntimeException from
org.apache.tika.parser.microsoft.OfficeParser@29402a40
at
org.apache.tika.parser.CompositeParser.parse(CompositeParser.java:282)
at
org.apache.tika.parser.AutoDetectParser.parse(AutoDetectParser.java:120)
at org.apache.tika.Tika.parseToString(Tika.java:537)
at
org.elasticsearch.mapper.attachments.TikaImpl$1.run(TikaImpl.java:102)
at org.elasticsearch.mapper.attachments.TikaImpl$1.run(TikaImpl.java:1)
at java.security.AccessController.doPrivileged(Native Method)
at org.elasticsearch.mapper.attachments.TikaImpl.parse(TikaImpl.java:99)
at
org.elasticsearch.mapper.attachments.AttachmentMapper.parse(AttachmentMapper.java:482)
at
org.elasticsearch.index.mapper.DocumentParser.parseObjectOrField(DocumentParser.java:309)
at
org.elasticsearch.index.mapper.DocumentParser.parseValue(DocumentParser.java:436)
at
org.elasticsearch.index.mapper.DocumentParser.parseObject(DocumentParser.java:262)
at
org.elasticsearch.index.mapper.DocumentParser.parseDocument(DocumentParser.java:122)
at
org.elasticsearch.index.mapper.DocumentMapper.parse(DocumentMapper.java:309)
at
org.elasticsearch.index.shard.IndexShard.prepareCreate(IndexShard.java:529)
at
org.elasticsearch.index.shard.IndexShard.prepareCreateOnPrimary(IndexShard.java:506)
at
org.elasticsearch.action.index.TransportIndexAction.prepareIndexOperationOnPrimary(TransportIndexAction.java:215)
at
org.elasticsearch.action.index.TransportIndexAction.executeIndexRequestOnPrimary(TransportIndexAction.java:224)
at
org.elasticsearch.action.bulk.TransportShardBulkAction.shardIndexOperation(TransportShardBulkAction.java:326)
at
org.elasticsearch.action.bulk.TransportShardBulkAction.shardUpdateOperation(TransportShardBulkAction.java:389)
at
org.elasticsearch.action.bulk.TransportShardBulkAction.shardOperationOnPrimary(TransportShardBulkAction.java:191)
at
org.elasticsearch.action.bulk.TransportShardBulkAction.shardOperationOnPrimary(TransportShardBulkAction.java:68)
at
org.elasticsearch.action.support.replication.TransportReplicationAction$PrimaryPhase.doRun(TransportReplicationAction.java:639)
at
org.elasticsearch.common.util.concurrent.AbstractRunnable.run(AbstractRunnable.java:37)
at
org.elasticsearch.action.support.replication.TransportReplicationAction$PrimaryOperationTransportHandler.messageReceived(TransportReplicationAction.java:279)
at
org.elasticsearch.action.support.replication.TransportReplicationAction$PrimaryOperationTransportHandler.messageReceived(TransportReplicationAction.java:271)
at
org.elasticsearch.transport.RequestHandlerRegistry.processMessageReceived(RequestHandlerRegistry.java:75)
at
org.elasticsearch.transport.TransportService$4.doRun(TransportService.java:376)
at
org.elasticsearch.common.util.concurrent.AbstractRunnable.run(AbstractRunnable.java:37)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.ArrayIndexOutOfBoundsException
at org.apache.poi.hwpf.model.SectionTable.<init>(SectionTable.java:84)
at org.apache.poi.hwpf.HWPFDocument.<init>(HWPFDocument.java:345)
at
org.apache.tika.parser.microsoft.WordExtractor.parse(WordExtractor.java:144)
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)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
