-----------------------------------------------------------
This is an automatically generated e-mail. To reply, visit:
https://reviews.apache.org/r/31758/
-----------------------------------------------------------

Review request for tika.


Repository: tika


Description
-------

TIKA-1330: tika batch code integrated into Tika-app.  This offers robust batch 
processing code filesystem input -> filesystem output on a single machine.  The 
goals are:

1) to make the code robust against permanent hangs and oom 
2) enable easy(ish) extensibility
3) include robust logging


Diffs
-----

  trunk/pom.xml 1664211 
  trunk/tika-app/pom.xml 1664211 
  trunk/tika-app/src/main/java/org/apache/tika/cli/BatchCommandLineBuilder.java 
PRE-CREATION 
  trunk/tika-app/src/main/java/org/apache/tika/cli/TikaCLI.java 1664211 
  
trunk/tika-app/src/test/java/org/apache/tika/cli/TikaCLIBatchCommandLineTest.java
 PRE-CREATION 
  trunk/tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java 1664211 
  trunk/tika-batch/pom.xml PRE-CREATION 
  trunk/tika-batch/src/main/examples/batchExecutor.sh PRE-CREATION 
  trunk/tika-batch/src/main/examples/log4j.xml PRE-CREATION 
  trunk/tika-batch/src/main/examples/log4j_driver.xml PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/AutoDetectParserFactory.java
 PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/BatchNoRestartError.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/BatchProcess.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/BatchProcessDriverCLI.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/CommandLineInterrupter.java
 PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/ConsumersManager.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/FileConsumerFutureResult.java
 PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/FileResource.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/FileResourceConsumer.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/FileResourceCrawler.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/FileResourceCrawlerFutureResult.java
 PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/FileStarted.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/IFileProcessorFutureResult.java
 PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/IInterrupter.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/IStatusReporter.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/InterrupterFutureResult.java
 PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/OutputStreamFactory.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/ParallelFileProcessingResult.java
 PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/ParserFactory.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/PoisonFileResource.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/SimpleLogStatusReporter.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/StatusReporterFutureResult.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/AbstractConsumersBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/BatchProcessBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/CommandLineInterrupterBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/CommandLineParserBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/ContentHandlerFactoryBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/DefaultContentHandlerFactoryBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/ICrawlerBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/IInterupterBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/ObjectFromDOMAndQueueBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/ObjectFromDOMBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/ReporterBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/SimpleLogReporterBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/builders/StatusReporterBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/BasicTikaFSConsumer.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSBatchProcessCLI.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSConsumersManager.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSDirectoryCrawler.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSDocumentSelector.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSFileResource.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSListCrawler.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSOutputStreamFactory.java
 PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSProperties.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/FSUtil.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/RecursiveParserWrapperFSConsumer.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/builders/BasicTikaFSConsumersBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/builders/FSCrawlerBuilder.java
 PRE-CREATION 
  
trunk/tika-batch/src/main/java/org/apache/tika/batch/fs/strawman/StrawManTikaAppDriver.java
 PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/util/BatchLocalization.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/util/ClassLoaderUtil.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/util/DurationFormatUtils.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/util/PropsUtil.java 
PRE-CREATION 
  trunk/tika-batch/src/main/java/org/apache/tika/util/XMLDOMUtil.java 
PRE-CREATION 
  
trunk/tika-batch/src/main/resources/org/apache/tika/batch/fs/default-tika-batch-config.xml
 PRE-CREATION 
  
trunk/tika-batch/src/test/java/org/apache/tika/batch/CommandLineParserBuilderTest.java
 PRE-CREATION 
  trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/BatchDriverTest.java 
PRE-CREATION 
  trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/BatchProcessTest.java 
PRE-CREATION 
  trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/FSBatchTestBase.java 
PRE-CREATION 
  
trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/HandlerBuilderTest.java 
PRE-CREATION 
  
trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/OutputStreamFactoryTest.java
 PRE-CREATION 
  
trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/StringStreamGobbler.java
 PRE-CREATION 
  
trunk/tika-batch/src/test/java/org/apache/tika/batch/fs/strawman/StrawmanTest.java
 PRE-CREATION 
  
trunk/tika-batch/src/test/java/org/apache/tika/parser/evil/EvilParserFactory.java
 PRE-CREATION 
  trunk/tika-batch/src/test/resources/evil/assertion_error.evil PRE-CREATION 
  trunk/tika-batch/src/test/resources/evil/hang_heavy_load.evil PRE-CREATION 
  trunk/tika-batch/src/test/resources/evil/no_problem.txt PRE-CREATION 
  trunk/tika-batch/src/test/resources/evil/oom_exception.evil PRE-CREATION 
  trunk/tika-batch/src/test/resources/evil/runtime_exception.evil PRE-CREATION 
  trunk/tika-batch/src/test/resources/evil/sleep.evil PRE-CREATION 
  trunk/tika-batch/src/test/resources/evil/sleep_2000.evil PRE-CREATION 
  trunk/tika-batch/src/test/resources/evil/tika-evil-config.xml PRE-CREATION 
  trunk/tika-batch/src/test/resources/evil/tika-evil-mimetypes.xml PRE-CREATION 
  trunk/tika-batch/src/test/resources/evil/tika_exception.evil PRE-CREATION 
  trunk/tika-batch/src/test/resources/log4j.properties PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/basic/test1.txt PRE-CREATION 
  
trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/hang_heavy_load1.evil
 PRE-CREATION 
  
trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/hang_heavy_load2.evil
 PRE-CREATION 
  
trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/hang_heavy_load3.evil
 PRE-CREATION 
  
trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/hang_heavy_load4.evil
 PRE-CREATION 
  
trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/hang_heavy_load5.evil
 PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/heavy_heavy_hangs/test1.txt 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/no_restart/test1.txt 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/no_restart/test2.evil 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/no_restart/test3.txt 
PRE-CREATION 
  
trunk/tika-batch/src/test/resources/test-input/one_heavy_hang/hang_heavy_load1.evil
 PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/one_heavy_hang/test1.txt 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/one_heavy_hang/test2.txt 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/one_heavy_hang/test3.txt 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/one_heavy_hang/test4.txt 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/oom/asleep_10000.evil 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/oom/hang_heavy_load.evil 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/oom/test1.txt PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/oom/test1b_oom_exception.evil 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/oom/test2.txt PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/oom/test3.txt PRE-CREATION 
  trunk/tika-batch/src/test/resources/test-input/oom/test4.txt PRE-CREATION 
  
trunk/tika-batch/src/test/resources/test-input/timeout_after_early_termination/asleep_60000.evil
 PRE-CREATION 
  
trunk/tika-batch/src/test/resources/test-input/wait_after_early_termination/asleep_10000.evil
 PRE-CREATION 
  trunk/tika-batch/src/test/resources/tika-batch-config-basic-test.xml 
PRE-CREATION 
  trunk/tika-batch/src/test/resources/tika-batch-config-evil-test.xml 
PRE-CREATION 
  trunk/tika-core/src/main/java/org/apache/tika/io/IOUtils.java 1664211 
  trunk/tika-parsers/src/test/java/org/apache/tika/TikaTest.java 1664211 
  trunk/tika-parsers/src/test/java/org/apache/tika/parser/evil/EvilParser.java 
1664211 

Diff: https://reviews.apache.org/r/31758/diff/


Testing
-------

Code has been in development as part of another fielded project for the last 
two years.  Numerous unit tests...could always use more


Thanks,

Tim Allison

Reply via email to