You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2020/07/17 17:17:18 UTC

[tika] branch main updated (23329a6 -> bf224dc)

This is an automated email from the ASF dual-hosted git repository.

tallison pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git.


    from 23329a6  TIKA-3129 -- add a status endpoint to report server status.  Users must turn it on via the commandline -status option.
     add 3bdcd97  TIKA-3137 -- first pass, need to add unit tests for tika-batch
     add 78e5b9a  TIKA-3140 -- initial commit
     add eb6e07e  TIKA-3137 add a list type for Param/configuration to avoid the comma-delimited lists which will get huge and ugly and were a bad idea.
     add 4971e2e  TIKA-3137 add a list type for Param/configuration to avoid the comma-delimited lists which will get huge and ugly and were a bad idea.
     new bf224dc  Merge remote-tracking branch 'origin/TIKA-3140' into main

The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails.  The revisions
listed as "add" were already present in the repository and have only
been added to this reference.


Summary of changes:
 .../src/main/java/org/apache/tika/cli/TikaCLI.java |   4 +-
 .../batch/fs/RecursiveParserWrapperFSConsumer.java |   9 +-
 .../tika/batch/fs/StreamOutRPWFSConsumer.java      |  20 ++-
 .../fs/builders/BasicTikaFSConsumersBuilder.java   |  11 +-
 .../RecursiveParserWrapperFSConsumerTest.java      |   5 +-
 .../main/java/org/apache/tika/config/Param.java    |  70 +++++++--
 .../java/org/apache/tika/config/TikaConfig.java    | 115 +++++++++++++-
 .../metadata/filter/ClearByMimeMetadataFilter.java |  72 +++++++++
 .../metadata/filter/CompositeMetadataFilter.java   |  23 +--
 .../filter/DefaultMetadataFilter.java}             |  38 +++--
 .../filter/ExcludeFieldMetadataFilter.java         |  41 +++--
 .../filter/IncludeFieldMetadataFilter.java}        |  54 +++----
 .../tika/metadata/filter/MetadataFilter.java       |  15 +-
 .../apache/tika/metadata/filter/NoOpFilter.java    |  21 ++-
 .../tika/sax/RecursiveParserWrapperHandler.java    |  31 +++-
 .../org.apache.tika.metadata.filter.MetadataFilter |   2 +-
 .../java/org/apache/tika/config/ParamTest.java     |   7 +
 .../org/apache/tika/config/TikaConfigTest.java     |   2 +
 .../tika/metadata/filter/MockUpperCaseFilter.java  |  27 ++--
 .../tika/metadata/filter/TestMetadataFilter.java   | 170 +++++++++++++++++++++
 .../tika/parser/ParameterizedParserTest.java       |   3 +-
 ...3-vowel-parser-ae.xml => TIKA-3137-exclude.xml} |  13 +-
 ...owel-parser-ae.xml => TIKA-3137-include-uc.xml} |  14 +-
 ...3-vowel-parser-ae.xml => TIKA-3137-include.xml} |  13 +-
 ...-vowel-parser-ae.xml => TIKA-3137-mimes-uc.xml} |  14 +-
 .../tika/eval/metadata/TikaEvalMetadataFilter.java | 104 +++++++++++++
 .../eval/metadata/TikaEvalMetadataFilterTest.java  |  51 +++++++
 .../tika/parser/RecursiveParserWrapperTest.java    |  43 ++++++
 .../org/apache/tika/parser/TIKA-3137-include.xml   |  22 ++-
 .../server/resource/RecursiveMetadataResource.java |   3 +-
 .../java/org/apache/tika/server/CXFTestBase.java   |   7 +-
 .../tika/server/RecursiveMetadataFilterTest.java   | 108 +++++++++++++
 .../org/apache/tika/server/TIKA-3137-include.xml   |  22 ++-
 33 files changed, 981 insertions(+), 173 deletions(-)
 create mode 100644 tika-core/src/main/java/org/apache/tika/metadata/filter/ClearByMimeMetadataFilter.java
 copy tika-server/src/main/java/org/apache/tika/server/MetadataList.java => tika-core/src/main/java/org/apache/tika/metadata/filter/CompositeMetadataFilter.java (65%)
 copy tika-core/src/main/java/org/apache/tika/{mime/OrClause.java => metadata/filter/DefaultMetadataFilter.java} (51%)
 copy tika-fuzzing/src/main/java/org/apache/tika/fuzzing/Transformer.java => tika-core/src/main/java/org/apache/tika/metadata/filter/ExcludeFieldMetadataFilter.java (53%)
 copy tika-core/src/main/java/org/apache/tika/{detect/NonDetectingEncodingDetector.java => metadata/filter/IncludeFieldMetadataFilter.java} (51%)
 copy tika-parsers/src/main/java/org/apache/tika/parser/utils/DataURISchemeParseException.java => tika-core/src/main/java/org/apache/tika/metadata/filter/MetadataFilter.java (74%)
 copy tika-server/src/main/java/org/apache/tika/server/MetadataList.java => tika-core/src/main/java/org/apache/tika/metadata/filter/NoOpFilter.java (69%)
 copy tika-parsers/src/main/resources/org/apache/tika/parser/ner/nltk/NLTKServer.properties => tika-core/src/main/resources/META-INF/services/org.apache.tika.metadata.filter.MetadataFilter (94%)
 copy tika-server/src/main/java/org/apache/tika/server/DefaultInputStreamFactory.java => tika-core/src/test/java/org/apache/tika/metadata/filter/MockUpperCaseFilter.java (61%)
 create mode 100644 tika-core/src/test/java/org/apache/tika/metadata/filter/TestMetadataFilter.java
 copy tika-core/src/test/resources/org/apache/tika/config/{TIKA-2653-vowel-parser-ae.xml => TIKA-3137-exclude.xml} (76%)
 copy tika-core/src/test/resources/org/apache/tika/config/{TIKA-2653-vowel-parser-ae.xml => TIKA-3137-include-uc.xml} (70%)
 copy tika-core/src/test/resources/org/apache/tika/config/{TIKA-2653-vowel-parser-ae.xml => TIKA-3137-include.xml} (76%)
 copy tika-core/src/test/resources/org/apache/tika/config/{TIKA-2653-vowel-parser-ae.xml => TIKA-3137-mimes-uc.xml} (70%)
 create mode 100644 tika-eval/src/main/java/org/apache/tika/eval/metadata/TikaEvalMetadataFilter.java
 create mode 100644 tika-eval/src/test/java/org/apache/tika/eval/metadata/TikaEvalMetadataFilterTest.java
 copy tika-core/src/test/resources/org/apache/tika/config/TIKA-2653-vowel-parser-ae.xml => tika-parsers/src/test/resources/org/apache/tika/parser/TIKA-3137-include.xml (58%)
 create mode 100644 tika-server/src/test/java/org/apache/tika/server/RecursiveMetadataFilterTest.java
 copy tika-core/src/test/resources/org/apache/tika/config/TIKA-2653-vowel-parser-ae.xml => tika-server/src/test/resources/org/apache/tika/server/TIKA-3137-include.xml (58%)


[tika] 01/01: Merge remote-tracking branch 'origin/TIKA-3140' into main

Posted by ta...@apache.org.
This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tika.git

commit bf224dc2f09c029df3f93ae0b136eb294e2c233f
Merge: 23329a6 4971e2e
Author: tallison <ta...@apache.org>
AuthorDate: Fri Jul 17 13:02:26 2020 -0400

    Merge remote-tracking branch 'origin/TIKA-3140' into main

 .../src/main/java/org/apache/tika/cli/TikaCLI.java |   4 +-
 .../batch/fs/RecursiveParserWrapperFSConsumer.java |   9 +-
 .../tika/batch/fs/StreamOutRPWFSConsumer.java      |  20 ++-
 .../fs/builders/BasicTikaFSConsumersBuilder.java   |  11 +-
 .../RecursiveParserWrapperFSConsumerTest.java      |   5 +-
 .../main/java/org/apache/tika/config/Param.java    |  70 +++++++--
 .../java/org/apache/tika/config/TikaConfig.java    | 115 +++++++++++++-
 .../metadata/filter/ClearByMimeMetadataFilter.java |  72 +++++++++
 .../metadata/filter/CompositeMetadataFilter.java   |  38 +++++
 .../metadata/filter/DefaultMetadataFilter.java     |  46 ++++++
 .../filter/ExcludeFieldMetadataFilter.java         |  52 +++++++
 .../filter/IncludeFieldMetadataFilter.java         |  56 +++++++
 .../tika/metadata/filter/MetadataFilter.java       |  33 ++++
 .../apache/tika/metadata/filter/NoOpFilter.java    |  34 +++++
 .../tika/sax/RecursiveParserWrapperHandler.java    |  31 +++-
 .../org.apache.tika.metadata.filter.MetadataFilter |  16 ++
 .../java/org/apache/tika/config/ParamTest.java     |   7 +
 .../org/apache/tika/config/TikaConfigTest.java     |   2 +
 .../tika/metadata/filter/MockUpperCaseFilter.java  |  39 +++++
 .../tika/metadata/filter/TestMetadataFilter.java   | 170 +++++++++++++++++++++
 .../tika/parser/ParameterizedParserTest.java       |   3 +-
 .../org/apache/tika/config/TIKA-3137-exclude.xml   |  29 ++++
 .../apache/tika/config/TIKA-3137-include-uc.xml    |  30 ++++
 .../org/apache/tika/config/TIKA-3137-include.xml   |  29 ++++
 .../org/apache/tika/config/TIKA-3137-mimes-uc.xml  |  30 ++++
 .../tika/eval/metadata/TikaEvalMetadataFilter.java | 104 +++++++++++++
 .../eval/metadata/TikaEvalMetadataFilterTest.java  |  51 +++++++
 .../tika/parser/RecursiveParserWrapperTest.java    |  43 ++++++
 .../org/apache/tika/parser/TIKA-3137-include.xml   |  38 +++++
 .../server/resource/RecursiveMetadataResource.java |   3 +-
 .../java/org/apache/tika/server/CXFTestBase.java   |   7 +-
 .../tika/server/RecursiveMetadataFilterTest.java   | 108 +++++++++++++
 .../org/apache/tika/server/TIKA-3137-include.xml   |  38 +++++
 33 files changed, 1308 insertions(+), 35 deletions(-)