[ https://issues.apache.org/jira/browse/TIKA-1330?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14376175#comment-14376175 ]
Hudson commented on TIKA-1330: ------------------------------ SUCCESS: Integrated in tika-trunk-jdk1.7 #566 (See [https://builds.apache.org/job/tika-trunk-jdk1.7/566/]) initial commit of TIKA-1330 (tallison: http://svn.apache.org/viewvc/tika/trunk/?view=rev&rev=1668673) * /tika/trunk/CHANGES.txt * /tika/trunk/pom.xml * /tika/trunk/tika-app/pom.xml * /tika/trunk/tika-app/src/main/java/org/apache/tika/cli/BatchCommandLineBuilder.java * /tika/trunk/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java * /tika/trunk/tika-app/src/main/resources/log4j.properties * /tika/trunk/tika-app/src/test/java/org/apache/tika/cli/TikaCLIBatchCommandLineTest.java * /tika/trunk/tika-batch * /tika/trunk/tika-batch/pom.xml * /tika/trunk/tika-batch/src * /tika/trunk/tika-batch/src/main * /tika/trunk/tika-batch/src/main/examples * /tika/trunk/tika-batch/src/main/examples/batchExecutor.sh * /tika/trunk/tika-batch/src/main/examples/log4j.xml * /tika/trunk/tika-batch/src/main/examples/log4j_driver.xml * /tika/trunk/tika-batch/src/main/java * /tika/trunk/tika-batch/src/main/java/org * /tika/trunk/tika-batch/src/main/java/org/apache * /tika/trunk/tika-batch/src/main/java/org/apache/tika * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/AutoDetectParserFactory.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/BatchNoRestartError.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/BatchProcess.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/BatchProcessDriverCLI.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/ConsumersManager.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/FileConsumerFutureResult.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/FileResource.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/FileResourceConsumer.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/FileResourceCrawler.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/FileResourceCrawlerFutureResult.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/FileStarted.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/IFileProcessorFutureResult.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/Interrupter.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/InterrupterFutureResult.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/OutputStreamFactory.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/ParallelFileProcessingResult.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/ParserFactory.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/PoisonFileResource.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/StatusReporter.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/StatusReporterFutureResult.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/AbstractConsumersBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/BatchProcessBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/CommandLineParserBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/DefaultContentHandlerFactoryBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/IContentHandlerFactoryBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/ICrawlerBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/InterrupterBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/ObjectFromDOMAndQueueBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/ObjectFromDOMBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/ReporterBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/SimpleLogReporterBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/StatusReporterBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/AbstractFSConsumer.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/BasicTikaFSConsumer.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSBatchProcessCLI.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSConsumersManager.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSDirectoryCrawler.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSDocumentSelector.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSFileResource.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSListCrawler.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSOutputStreamFactory.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSProperties.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSUtil.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/RecursiveParserWrapperFSConsumer.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/builders * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/builders/BasicTikaFSConsumersBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/builders/FSCrawlerBuilder.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/strawman * /tika/trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/strawman/StrawManTikaAppDriver.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/util * /tika/trunk/tika-batch/src/main/java/org/apache/tika/util/ClassLoaderUtil.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/util/DurationFormatUtils.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/util/PropsUtil.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/util/TikaExceptionFilter.java * /tika/trunk/tika-batch/src/main/java/org/apache/tika/util/XMLDOMUtil.java * /tika/trunk/tika-batch/src/main/java/overview.html * /tika/trunk/tika-batch/src/main/resources * /tika/trunk/tika-batch/src/main/resources/org * /tika/trunk/tika-batch/src/main/resources/org/apache * /tika/trunk/tika-batch/src/main/resources/org/apache/tika * /tika/trunk/tika-batch/src/main/resources/org/apache/tika/batch * /tika/trunk/tika-batch/src/main/resources/org/apache/tika/batch/fs * /tika/trunk/tika-batch/src/main/resources/org/apache/tika/batch/fs/default-tika-batch-config.xml * /tika/trunk/tika-batch/src/test * /tika/trunk/tika-batch/src/test/java * /tika/trunk/tika-batch/src/test/java/org * /tika/trunk/tika-batch/src/test/java/org/apache * /tika/trunk/tika-batch/src/test/java/org/apache/tika * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/CommandLineParserBuilderTest.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/fs * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/BatchDriverTest.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/BatchProcessTest.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/FSBatchTestBase.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/HandlerBuilderTest.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/OutputStreamFactoryTest.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/StringStreamGobbler.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/strawman * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/strawman/StrawmanTest.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/mock * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/mock/MockConsumersBuilder.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/batch/mock/MockConsumersManager.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/parser * /tika/trunk/tika-batch/src/test/java/org/apache/tika/parser/mock * /tika/trunk/tika-batch/src/test/java/org/apache/tika/parser/mock/MockParserFactory.java * /tika/trunk/tika-batch/src/test/java/org/apache/tika/util * /tika/trunk/tika-batch/src/test/java/org/apache/tika/util/TikaExceptionFilterTest.java * /tika/trunk/tika-batch/src/test/resources * /tika/trunk/tika-batch/src/test/resources/log4j.properties * /tika/trunk/tika-batch/src/test/resources/log4j_process.properties * /tika/trunk/tika-batch/src/test/resources/test-documents * /tika/trunk/tika-batch/src/test/resources/test-documents/null_pointer.xml * /tika/trunk/tika-batch/src/test/resources/test-input * /tika/trunk/tika-batch/src/test/resources/test-input/basic * /tika/trunk/tika-batch/src/test/resources/test-input/basic/test0.xml * /tika/trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs * /tika/trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/test0_heavy_hang.xml * /tika/trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/test1_heavy_hang.xml * /tika/trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/test2_heavy_hang.xml * /tika/trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/test3_heavy_hang.xml * /tika/trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/test4_heavy_hang.xml * /tika/trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/test5_heavy_hang.xml * /tika/trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/test6_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/max_restarts * /tika/trunk/tika-batch/src/test/resources/test-input/max_restarts/test0_oom.xml * /tika/trunk/tika-batch/src/test/resources/test-input/max_restarts/test1_oom.xml * /tika/trunk/tika-batch/src/test/resources/test-input/max_restarts/test2_oom.xml * /tika/trunk/tika-batch/src/test/resources/test-input/max_restarts/test3_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/no_restart * /tika/trunk/tika-batch/src/test/resources/test-input/no_restart/test1_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/no_restart/test2_norestart.xml * /tika/trunk/tika-batch/src/test/resources/test-input/no_restart/test3_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/noisy_parsers * /tika/trunk/tika-batch/src/test/resources/test-input/noisy_parsers/test0.xml * /tika/trunk/tika-batch/src/test/resources/test-input/one_heavy_hang * /tika/trunk/tika-batch/src/test/resources/test-input/one_heavy_hang/test0_heavy_hang.xml * /tika/trunk/tika-batch/src/test/resources/test-input/one_heavy_hang/test1_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/one_heavy_hang/test2_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/one_heavy_hang/test3_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/one_heavy_hang/test4_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/oom * /tika/trunk/tika-batch/src/test/resources/test-input/oom/test0_sleep.xml * /tika/trunk/tika-batch/src/test/resources/test-input/oom/test1_heavy_hang.xml * /tika/trunk/tika-batch/src/test/resources/test-input/oom/test2_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/oom/test3_oom.xml * /tika/trunk/tika-batch/src/test/resources/test-input/oom/test4_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/oom/test5_ok.xml * /tika/trunk/tika-batch/src/test/resources/test-input/timeout_after_early_termination * /tika/trunk/tika-batch/src/test/resources/test-input/timeout_after_early_termination/test0_sleep.xml * /tika/trunk/tika-batch/src/test/resources/test-input/wait_after_early_termination * /tika/trunk/tika-batch/src/test/resources/test-input/wait_after_early_termination/test0_sleep.xml * /tika/trunk/tika-batch/src/test/resources/tika-batch-config-MockConsumersBuilder.xml * /tika/trunk/tika-batch/src/test/resources/tika-batch-config-broken.xml * /tika/trunk/tika-batch/src/test/resources/tika-batch-config-test.xml > Add robust tika-batch code > -------------------------- > > Key: TIKA-1330 > URL: https://issues.apache.org/jira/browse/TIKA-1330 > Project: Tika > Issue Type: Sub-task > Components: cli, general, server > Reporter: Tim Allison > Assignee: Tim Allison > Attachments: TIKA-1330v1-patch.zip > > > In my current design plan, I see creating a separate component "tika-batch" > that includes a small bit of configurable code to run Tika against a large > batch of documents. This code should be robust against OOM and hangs, and it > should have fairly robust logging. -- This message was sent by Atlassian JIRA (v6.3.4#6332)