This is an automated email from the ASF dual-hosted git repository.
tallison pushed a change to branch TIKA-4641-step2
in repository https://gitbox.apache.org/repos/asf/tika.git
from c9963eaae5 refactor serialization, further. add docs
add 86857ce8af TIKA-4644 - improve config endpoints (#2566)
add acca2fec6c TIKA-4637 (#2565) add UNPACK option for tika-pipes and
integrate it in tika-app and tika-server
add 778acde282 TIKA-4643 -- add frictionless
add 867daffe99 Merge remote-tracking branch 'origin/main' into
TIKA-4641-step2
No new revisions were added by this update.
Summary of changes:
docs/modules/ROOT/nav.adoc | 1 +
.../ROOT/pages/advanced/setting-limits.adoc | 59 ++
docs/modules/ROOT/pages/pipes/index.adoc | 2 +
docs/modules/ROOT/pages/pipes/unpack-config.adoc | 202 ++++++
.../main/java/org/apache/tika/cli/AsyncHelper.java | 24 +
.../src/main/java/org/apache/tika/cli/TikaCLI.java | 120 +---
.../test/java/org/apache/tika/cli/TikaCLITest.java | 141 ++--
.../tika/cli/XmlToJsonConfigConverterTest.java | 11 -
.../org/apache/tika/config/EmbeddedLimits.java | 2 +-
.../tika/extractor/BasicEmbeddedBytesSelector.java | 77 ---
.../EmbeddedDocumentByteStoreExtractorFactory.java | 7 +-
.../ParsingEmbeddedDocumentExtractor.java | 14 +-
...ocumentBytesHandler.java => UnpackHandler.java} | 2 +-
...eddedBytesSelector.java => UnpackSelector.java} | 6 +-
.../org/apache/tika/parser/mock/MockParser.java | 4 +
.../apache/tika/async/cli/SimpleAsyncConfig.java | 52 +-
.../org/apache/tika/async/cli/TikaAsyncCLI.java | 69 +-
.../apache/tika/async/cli/AsyncProcessorTest.java | 14 +-
.../tika/async/cli/TikaConfigAsyncWriterTest.java | 2 +-
.../java/org/apache/tika/pipes/api/ParseMode.java | 22 +-
...ytesHandler.java => AbstractUnpackHandler.java} | 4 +-
...ytesHandler.java => EmittingUnpackHandler.java} | 9 +-
.../core/extractor/FrictionlessUnpackHandler.java | 337 ++++++++++
.../core/extractor/StandardUnpackSelector.java | 143 +++++
.../core/extractor/TempFileUnpackHandler.java | 159 +++++
.../tika/pipes/core/extractor/UnpackConfig.java | 232 ++++---
...{RUnpackExtractor.java => UnpackExtractor.java} | 58 +-
...torFactory.java => UnpackExtractorFactory.java} | 12 +-
.../core/extractor/frictionless/DataPackage.java | 226 +++++++
.../frictionless/FrictionlessResource.java | 83 +++
.../apache/tika/pipes/core/server/EmitHandler.java | 24 +-
.../core/server/MetadataListAndEmbeddedBytes.java | 40 +-
.../tika/pipes/core/server/ParseHandler.java | 12 +-
.../apache/tika/pipes/core/server/PipesServer.java | 34 +-
.../apache/tika/pipes/core/server/PipesWorker.java | 538 +++++++++++++++-
...orTest.java => StandardUnpackSelectorTest.java} | 34 +-
.../core/serialization/JsonFetchEmitTupleTest.java | 43 ++
.../pipes/core/DigestingOpenContainersTest.java | 4 +-
.../apache/tika/pipes/core/EmbeddedLimitsTest.java | 304 +++++++++
.../tika/pipes/core/FrictionlessUnpackTest.java | 713 +++++++++++++++++++++
.../tika/pipes/core/MetadataWriteLimiterTest.java | 7 -
.../org/apache/tika/pipes/core/UnpackModeTest.java | 635 ++++++++++++++++++
.../pipesiterator/json/TestJsonPipesIterator.java | 4 +-
...h-embedded-bytes.json => test-with-unpack.json} | 400 ++++++------
.../org/apache/tika/serialization/TikaModule.java | 2 +
.../serdes/ParseContextDeserializer.java | 2 +-
.../serdes/ParseContextSerializer.java | 2 +-
.../serialization/RoundTripSerializationTest.java | 6 +-
.../TestParseContextSerialization.java | 4 +-
.../org/apache/tika/server/client/TestBasic.java | 3 -
...lter.java => ConfigEndpointSecurityFilter.java} | 37 +-
.../apache/tika/server/core/TikaServerConfig.java | 11 +-
.../apache/tika/server/core/TikaServerProcess.java | 61 +-
.../tika/server/core/resource/AsyncResource.java | 3 +-
.../server/core/resource/PipesParsingHelper.java | 218 ++++++-
.../core/resource/RecursiveMetadataResource.java | 8 +-
.../tika/server/core/resource/TikaResource.java | 26 +-
.../server/core/resource/UnpackerResource.java | 476 ++++++--------
.../org/apache/tika/server/core/CXFTestBase.java | 44 +-
.../core/ConfigEndpointSecurityEnabledTest.java | 111 ++++
.../server/core/ConfigEndpointSecurityTest.java | 143 +++++
.../server/core/RecursiveMetadataResourceTest.java | 3 -
.../apache/tika/server/core/StackTraceTest.java | 42 +-
.../apache/tika/server/core/TikaResourceTest.java | 2 -
.../configs/cxf-unpack-test-template.json | 38 ++
.../tika/server/standard/MetadataResourceTest.java | 1 -
.../standard/OptimaizeMetadataFilterTest.java | 2 -
.../apache/tika/server/standard/TikaPipesTest.java | 5 +-
.../tika/server/standard/TikaResourceTest.java | 26 +-
.../tika/server/standard/UnpackerResourceTest.java | 413 +++++++++---
.../standard/UnpackerResourceWithConfigTest.java | 114 +++-
71 files changed, 5530 insertions(+), 1159 deletions(-)
create mode 100644 docs/modules/ROOT/pages/pipes/unpack-config.adoc
delete mode 100644
tika-core/src/main/java/org/apache/tika/extractor/BasicEmbeddedBytesSelector.java
rename
tika-core/src/main/java/org/apache/tika/extractor/{EmbeddedDocumentBytesHandler.java
=> UnpackHandler.java} (94%)
rename
tika-core/src/main/java/org/apache/tika/extractor/{EmbeddedBytesSelector.java
=> UnpackSelector.java} (87%)
rename
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/extractor/{AbstractEmbeddedDocumentBytesHandler.java
=> AbstractUnpackHandler.java} (95%)
rename
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/extractor/{EmittingEmbeddedDocumentBytesHandler.java
=> EmittingUnpackHandler.java} (90%)
create mode 100644
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/extractor/FrictionlessUnpackHandler.java
create mode 100644
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/extractor/StandardUnpackSelector.java
create mode 100644
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/extractor/TempFileUnpackHandler.java
rename
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/extractor/{RUnpackExtractor.java
=> UnpackExtractor.java} (77%)
rename
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/extractor/{RUnpackExtractorFactory.java
=> UnpackExtractorFactory.java} (72%)
create mode 100644
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/extractor/frictionless/DataPackage.java
create mode 100644
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/extractor/frictionless/FrictionlessResource.java
rename
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core/extractor/{UnpackConfigSelectorTest.java
=> StandardUnpackSelectorTest.java} (67%)
create mode 100644
tika-pipes/tika-pipes-integration-tests/src/test/java/org/apache/tika/pipes/core/EmbeddedLimitsTest.java
create mode 100644
tika-pipes/tika-pipes-integration-tests/src/test/java/org/apache/tika/pipes/core/FrictionlessUnpackTest.java
create mode 100644
tika-pipes/tika-pipes-integration-tests/src/test/java/org/apache/tika/pipes/core/UnpackModeTest.java
rename
tika-pipes/tika-pipes-plugins/tika-pipes-json/src/test/resources/test-documents/{test-with-embedded-bytes.json
=> test-with-unpack.json} (76%)
copy
tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/{TikaLoggingFilter.java
=> ConfigEndpointSecurityFilter.java} (51%)
create mode 100644
tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/ConfigEndpointSecurityEnabledTest.java
create mode 100644
tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/ConfigEndpointSecurityTest.java
create mode 100644
tika-server/tika-server-core/src/test/resources/configs/cxf-unpack-test-template.json