This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch TIKA-4839-metrics
in repository https://gitbox.apache.org/repos/asf/tika.git
from ac64357519 Merge remote-tracking branch 'origin/main' into
TIKA-4839-metrics
add f1645e6e55 TIKA-4840: host-provided Jackson for pipes plugins; one
strict Plugin… (#3066)
add 8396a84f14 TIKA-4836: update aws, jsoup
add cf893e8e3c [TIKA-4830]: Handle additional exceptions in
JackcessParser, as suggested by Tim Scheckenbach (#3072)
add b08d4c2057 [TIKA-4841] Add unit tests for Metadata reserved-key
blocking, write limiter, and composite properties (#2948)
add 7ca4d6eea9 TIKA-4842 - update docs and javadocs post 4.0.0 release
(#3074)
add 4f910a58c5 TIKA-4842 (#3075)
add 5cc0e80f48 Merge remote-tracking branch 'origin/main' into
TIKA-4839-metrics
add 478f089e5d TIKA-4839: fix restart attribution for exit codes, mark
priority, and the no-arg mark
add 1468136e9e TIKA-4835 -- tika-core primitives for spill-less parsing
(#3073)
add ab22ec9c9a TIKA-4844: scope shared-server restart reports to the
process they de… (#3077)
add 3afde32dac TIKA-4837 - flag extra contents in ooxml files (#3063)
add 2d1e43ab32 TIKA-4843: fix per-request parse-context config for parsers
with lock… (#3076)
add c3ef7bbf21 Merge remote-tracking branch 'origin/main' into
TIKA-4839-metrics
No new revisions were added by this update.
Summary of changes:
.skills/pr-review/SKILL.md | 89 +-----
CHANGES.txt | 98 +++++-
docs/modules/ROOT/pages/configuration/index.adoc | 5 +-
.../ROOT/pages/configuration/metadata-filters.adoc | 6 +-
.../pages/configuration/parsers/tess4j-parser.adoc | 5 +-
.../ROOT/pages/developers/serialization.adoc | 6 +-
.../pages/maintainers/release-guides/tika.adoc | 18 +-
docs/modules/ROOT/pages/migration-to-4x/index.adoc | 4 +-
.../pages/migration-to-4x/metadata-changes-4x.adoc | 12 +-
.../pages/migration-to-4x/migrating-to-4x.adoc | 9 +-
docs/modules/ROOT/pages/pipes/configuration.adoc | 27 +-
.../ROOT/pages/pipes/plugins/elasticsearch.adoc | 4 +-
docs/modules/ROOT/pages/pipes/plugins/jdbc.adoc | 2 +-
docs/modules/ROOT/pages/pipes/plugins/kafka.adoc | 4 +-
.../ROOT/pages/pipes/plugins/opensearch.adoc | 4 +-
docs/modules/ROOT/pages/pipes/plugins/solr.adoc | 6 +-
.../ROOT/pages/pipes/plugins/writing-a-plugin.adoc | 34 +-
docs/modules/ROOT/pages/pipes/unpack-config.adoc | 2 +-
docs/modules/ROOT/pages/using-tika/docker.adoc | 4 +-
.../ROOT/pages/using-tika/server/monitoring.adoc | 4 +-
.../src/main/java/org/apache/tika/gui/TikaGUI.java | 4 +-
.../apache/tika/digest/BufferingDigestSink.java | 108 +++++++
.../org/apache/tika/digest/CompositeDigester.java | 54 ++++
.../java/org/apache/tika/digest/DigestHelper.java | 41 ++-
.../java/org/apache/tika/digest/DigestSink.java | 82 +++++
.../main/java/org/apache/tika/digest/Digester.java | 19 ++
.../apache/tika/digest/InputStreamDigester.java | 30 ++
.../java/org/apache/tika/io/ByteArraySource.java | 12 +-
.../org/apache/tika/io/CachingInputStream.java | 14 +-
.../java/org/apache/tika/io/CachingSource.java | 35 +-
.../main/java/org/apache/tika/io/FileSource.java | 5 +
.../apache/tika/io/MemorySeekableByteChannel.java | 7 +
.../java/org/apache/tika/io/ReopenableSource.java | 5 +
.../main/java/org/apache/tika/io/StreamCache.java | 5 +
.../org/apache/tika/io/TemporaryResources.java | 47 ++-
.../java/org/apache/tika/io/TikaInputSource.java | 9 +
.../java/org/apache/tika/io/TikaInputStream.java | 42 ++-
.../main/java/org/apache/tika/metadata/Office.java | 32 ++
.../org/apache/tika/digest/DigestHelperTest.java | 128 ++++++++
.../org/apache/tika/digest/DigestSinkTest.java | 356 +++++++++++++++++++++
.../apache/tika/digest/FailingTestTranslator.java | 63 ++++
.../apache/tika/io/InMemoryContentViewTest.java | 266 +++++++++++++++
.../org/apache/tika/io/StreamCacheBudgetTest.java | 59 ++++
.../org/apache/tika/io/TemporaryResourcesTest.java | 32 ++
.../org/apache/tika/metadata/TestMetadata.java | 119 +++++++
...apache.tika.extractor.EmbeddedStreamTranslator} | 2 +-
.../apache/tika/metadata/metadata-key-fields.json | 2 +
.../org/apache/tika/metadata/metadata-keys.json | 2 +
tika-ml/tika-ml-junkdetect-tools/pom.xml | 5 +-
.../ml/junkdetect/JunkFilterEncodingDetector.java | 11 +-
tika-parent/pom.xml | 4 +-
.../ImageEmbeddingRuntimeConfigMergeTest.java | 78 +++++
.../tika/parser/ocr/tess4j/Tess4JConfig.java | 7 +-
.../ocr/tess4j/Tess4JRuntimeConfigMergeTest.java | 76 +++++
.../tika/parser/vlm/VLMRuntimeConfigMergeTest.java | 107 +++++++
.../tika/parser/microsoft/JackcessParser.java | 14 +-
.../microsoft/ooxml/OOXMLExtractorFactory.java | 68 ++++
.../tika/parser/microsoft/ooxml/OOXMLParser.java | 98 +++---
.../microsoft/ooxml/MacroPartResolutionTest.java | 145 +++++++++
.../microsoft/ooxml/ZipStructureCoverageTest.java | 181 +++++++++++
.../apache/tika/parser/ocr/ImagePreprocessor.java | 2 +-
.../apache/tika/parser/ocr/TesseractOCRConfig.java | 4 -
.../tika/pipes/core/PerClientServerManager.java | 5 +
.../org/apache/tika/pipes/core/PipesClient.java | 32 +-
.../org/apache/tika/pipes/core/PipesParser.java | 9 +
.../org/apache/tika/pipes/core/RestartCounter.java | 33 +-
.../org/apache/tika/pipes/core/RestartReason.java | 7 +-
.../org/apache/tika/pipes/core/ServerManager.java | 43 ++-
.../tika/pipes/core/SharedServerManager.java | 81 ++++-
.../apache/tika/pipes/core/server/PipesServer.java | 40 ++-
.../apache/tika/pipes/core/RestartCounterTest.java | 23 +-
.../pipes/core/ServerManagerMarkContractTest.java | 150 +++++++++
.../pipes/core/SharedServerManagerClosedTest.java | 34 +-
.../core/server/CacheMemoryBudgetSeedingTest.java | 24 +-
.../apache/tika/pipes/core/FontCacheWarmer.java | 55 ++++
.../tika/pipes/core/SharedServerModeTest.java | 126 ++++++++
.../pipes/core/async/AsyncChaosMonkeyTest.java | 2 +
.../org.junit.jupiter.api.extension.Extension | 2 +-
.../resources/configs/tika-config-passback.json | 2 +-
.../resources/configs/tika-config-truncate.json | 61 ----
.../resources/configs/tika-config-uppercasing.json | 2 +-
.../configs/tika-config-write-limiter.json | 2 +-
.../src/test/resources/junit-platform.properties | 4 +-
tika-pipes/tika-pipes-plugins/pom.xml | 23 +-
.../tika-pipes-atlassian-jwt/pom.xml | 8 -
.../atlassianjwt/AtlassianJwtFetcherFactory.java | 4 +-
.../config/AtlassianJwtFetcherConfig.java | 13 +-
.../tika-pipes-plugins/tika-pipes-az-blob/pom.xml | 4 -
.../tika/pipes/emitter/azblob/AZBlobEmitter.java | 4 +-
.../pipes/emitter/azblob/AZBlobEmitterConfig.java | 12 +-
.../pipes/emitter/azblob/AZBlobEmitterFactory.java | 4 +-
.../pipes/fetcher/azblob/AZBlobFetcherFactory.java | 4 +-
.../fetcher/azblob/config/AZBlobFetcherConfig.java | 13 +-
.../iterator/azblob/AZBlobPipesIteratorConfig.java | 14 +-
.../pipes/iterator/csv/CSVPipesIteratorConfig.java | 14 +-
.../tika/pipes/emitter/es/ESEmitterConfig.java | 13 +-
.../tika/pipes/emitter/es/ESEmitterFactory.java | 4 +-
.../tika/pipes/reporter/es/ESReporterConfig.java | 14 +-
.../tika-pipes-file-system/pom.xml | 5 -
.../pipes/emitter/fs/FileSystemEmitterConfig.java | 14 +-
.../pipes/emitter/fs/FileSystemEmitterFactory.java | 4 +-
.../emitter/fs/FileSystemEmitterRuntimeConfig.java | 14 +-
.../pipes/fetcher/fs/FileSystemFetcherConfig.java | 14 +-
.../pipes/fetcher/fs/FileSystemFetcherFactory.java | 4 +-
.../iterator/fs/FileSystemPipesIteratorConfig.java | 15 +-
.../reporter/fs/FileSystemReporterConfig.java | 14 +-
.../pipes/fetcher/fs/FileSystemFetcherTest.java | 13 +
.../apache/tika/pipes/emitter/gcs/GCSEmitter.java | 4 +-
.../tika/pipes/emitter/gcs/GCSEmitterConfig.java | 12 +-
.../tika/pipes/emitter/gcs/GCSEmitterFactory.java | 4 +-
.../tika/pipes/fetcher/gcs/GCSFetcherFactory.java | 4 +-
.../pipes/fetcher/gcs/config/GCSFetcherConfig.java | 13 +-
.../pipes/iterator/gcs/GCSPipesIteratorConfig.java | 13 +-
.../tika-pipes-google-drive/pom.xml | 8 -
.../googledrive/GoogleDriveFetcherFactory.java | 4 +-
.../config/GoogleDriveFetcherConfig.java | 13 +-
.../tika-pipes-plugins/tika-pipes-http/pom.xml | 8 -
.../pipes/fetcher/http/HttpFetcherFactory.java | 4 +-
.../fetcher/http/config/HttpFetcherConfig.java | 13 +-
.../tika/pipes/emitter/jdbc/JDBCEmitter.java | 4 +-
.../tika/pipes/emitter/jdbc/JDBCEmitterConfig.java | 13 +-
.../pipes/emitter/jdbc/JDBCEmitterFactory.java | 4 +-
.../iterator/jdbc/JDBCPipesIteratorConfig.java | 14 +-
.../reporter/jdbc/JDBCPipesReporterConfig.java | 13 +-
.../json/JsonPipesIteratorConfig.java | 14 +-
.../tika-pipes-plugins/tika-pipes-kafka/pom.xml | 5 -
.../tika/pipes/emitter/kafka/KafkaEmitter.java | 4 +-
.../pipes/emitter/kafka/KafkaEmitterConfig.java | 13 +-
.../pipes/emitter/kafka/KafkaEmitterFactory.java | 4 +-
.../iterator/kafka/KafkaPipesIteratorConfig.java | 14 +-
.../MicrosoftGraphFetcherFactory.java | 4 +-
.../config/MicrosoftGraphFetcherConfig.java | 15 +-
.../pipes/emitter/opensearch/HttpClientConfig.java | 10 -
.../opensearch/OpenSearchEmitterConfig.java | 14 +-
.../opensearch/OpenSearchEmitterFactory.java | 4 +-
.../reporter/opensearch/HttpClientConfig.java | 10 -
.../opensearch/OpenSearchReporterConfig.java | 14 +-
.../tika-pipes-plugins/tika-pipes-s3/pom.xml | 5 -
.../apache/tika/pipes/emitter/s3/S3Emitter.java | 4 +-
.../tika/pipes/emitter/s3/S3EmitterConfig.java | 13 +-
.../tika/pipes/emitter/s3/S3EmitterFactory.java | 4 +-
.../tika/pipes/fetcher/s3/S3FetcherFactory.java | 4 +-
.../pipes/fetcher/s3/config/S3FetcherConfig.java | 13 +-
.../pipes/iterator/s3/S3PipesIteratorConfig.java | 13 +-
.../tika-pipes-plugins/tika-pipes-solr/pom.xml | 4 -
.../tika/pipes/emitter/solr/SolrEmitter.java | 4 +-
.../tika/pipes/emitter/solr/SolrEmitterConfig.java | 12 +-
.../pipes/emitter/solr/SolrEmitterFactory.java | 4 +-
.../iterator/solr/SolrPipesIteratorConfig.java | 14 +-
.../java/org/apache/tika/plugins/PluginJson.java | 60 ++++
.../org/apache/tika/plugins/PluginJsonTest.java | 80 +++++
.../apache/tika/config/loader/JsonMergeUtils.java | 39 ++-
.../tika/config/loader/JsonMergeUtilsTest.java | 155 +++++++++
.../server/core/TikaServerIntegrationTest.java | 4 +-
154 files changed, 3552 insertions(+), 858 deletions(-)
create mode 100644
tika-core/src/main/java/org/apache/tika/digest/BufferingDigestSink.java
create mode 100644
tika-core/src/main/java/org/apache/tika/digest/DigestSink.java
create mode 100644
tika-core/src/test/java/org/apache/tika/digest/DigestHelperTest.java
create mode 100644
tika-core/src/test/java/org/apache/tika/digest/DigestSinkTest.java
create mode 100644
tika-core/src/test/java/org/apache/tika/digest/FailingTestTranslator.java
create mode 100644
tika-core/src/test/java/org/apache/tika/io/InMemoryContentViewTest.java
copy
tika-core/src/test/resources/META-INF/services/{org.apache.tika.parser.Parser
=> org.apache.tika.extractor.EmbeddedStreamTranslator} (94%)
create mode 100644
tika-parsers/tika-parsers-ml/tika-inference/src/test/java/org/apache/tika/inference/ImageEmbeddingRuntimeConfigMergeTest.java
create mode 100644
tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/test/java/org/apache/tika/parser/ocr/tess4j/Tess4JRuntimeConfigMergeTest.java
create mode 100644
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/VLMRuntimeConfigMergeTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/MacroPartResolutionTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/ZipStructureCoverageTest.java
create mode 100644
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core/ServerManagerMarkContractTest.java
copy tika-core/src/test/java/org/apache/tika/config/TimeoutLimitsTest.java =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core/SharedServerManagerClosedTest.java
(50%)
create mode 100644
tika-pipes/tika-pipes-integration-tests/src/test/java/org/apache/tika/pipes/core/FontCacheWarmer.java
copy
tika-core/src/test/resources/META-INF/services/org.apache.tika.parser.Parser =>
tika-pipes/tika-pipes-integration-tests/src/test/resources/META-INF/services/org.junit.jupiter.api.extension.Extension
(94%)
delete mode 100644
tika-pipes/tika-pipes-integration-tests/src/test/resources/configs/tika-config-truncate.json
copy
tika-server/tika-server-core/src/main/resources/tikaserver-version.properties
=>
tika-pipes/tika-pipes-integration-tests/src/test/resources/junit-platform.properties
(87%)
create mode 100644
tika-plugins-core/src/main/java/org/apache/tika/plugins/PluginJson.java
create mode 100644
tika-plugins-core/src/test/java/org/apache/tika/plugins/PluginJsonTest.java
create mode 100644
tika-serialization/src/test/java/org/apache/tika/config/loader/JsonMergeUtilsTest.java