This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch TIKA-4971
in repository https://gitbox.apache.org/repos/asf/tika.git
from 297c097969 Merge branch 'main' into TIKA-4971
add e88a4077eb TIKA-4973: slightly improve detection of rfc822 vs mhtml
(#3349)
add 67aea63ea2 TIKA-4972: try to do what we can with vlm ocr engines
(#3348)
add bea17ce11f TIKA-4978: per-request limits may tighten, not loosen, the
server's (#3367)
add 69ee8796d6 Merge branch 'main' into TIKA-4971
No new revisions were added by this update.
Summary of changes:
.skills/devs/development/SKILL.md | 21 ++
CHANGES.txt | 13 ++
.../modules/ROOT/examples/jina-ocr-basic.json | 6 +-
.../ROOT/pages/advanced/setting-limits.adoc | 19 ++
docs/modules/ROOT/pages/configuration/index.adoc | 57 ++++-
.../ROOT/pages/configuration/inference.adoc | 5 +-
docs/modules/ROOT/pages/configuration/pages.adoc | 6 +-
.../pages/configuration/parsers/vlm-parsers.adoc | 59 +++++-
.../ROOT/pages/developers/serialization.adoc | 15 +-
.../migration-to-4x/migrating-tika-server-4x.adoc | 6 +-
.../pages/migration-to-4x/migrating-to-4x.adoc | 2 +-
.../pages/migration-to-4x/serialization-4x.adoc | 10 +-
docs/modules/ROOT/pages/pipes/timeouts.adoc | 5 +-
docs/modules/ROOT/pages/security.adoc | 19 +-
docs/modules/ROOT/pages/using-tika/grpc/index.adoc | 3 +-
.../ROOT/pages/using-tika/server/index.adoc | 40 +++-
pom.xml | 4 +-
.../tika/annotation/TikaComponentProcessor.java | 1 +
tika-app/pom.xml | 6 +
...nkLiftTest.java => TikaCLIOcrWarningsTest.java} | 71 +++----
tika-bom/pom.xml | 5 +
.../org/apache/tika/config/EmbeddedLimits.java | 26 +++
.../java/org/apache/tika/config/OutputLimits.java | 24 +++
.../apache/tika/metadata/TikaCoreProperties.java | 8 +
.../StandardMetadataLimiterFactory.java | 27 +++
.../tika/parser/enricher/ContentEnrichers.java | 4 +-
.../{SizeGatedEnricher.java => GatedEnricher.java} | 56 ++---
.../apache/tika/parser/enricher/ImageCheck.java | 66 ++++++
.../apache/tika/parser/enricher/ImageProbe.java | 139 ++++++++++++
.../apache/tika/parser/enricher/OcrWarnings.java | 63 ++++++
...zeGatedEnricher.java => RecordedSizeCheck.java} | 47 ++---
.../tika/parser/enricher/SizeGatedEnricher.java | 15 +-
.../org/apache/tika/parser/pages/PagesConfig.java | 56 +++++
.../org/apache/tika/renderer/RenderSettings.java | 38 ++++
.../org/apache/tika/mime/tika-mimetypes.xml | 6 +-
.../apache/tika/config/LimitsTightenedToTest.java | 76 +++++++
.../tika/parser/enricher/ContentEnrichersTest.java | 5 +-
.../tika/parser/enricher/GatedEnricherTest.java | 164 +++++++++++++++
.../tika/parser/enricher/ImageProbeTest.java | 94 +++++++++
.../apache/tika/parser/pages/PagesConfigTest.java | 54 +++++
.../apache/tika/renderer/RenderSettingsTest.java | 23 ++
.../pom.xml | 131 +++++-------
.../tika/imageprocessing/BlankImageCheck.java | 138 ++++++++++++
.../apache/tika/imageprocessing/ByteSizeCheck.java | 81 +++++++
.../apache/tika/imageprocessing/ImageDecoding.java | 232 +++++++++++++++++++++
.../tika/imageprocessing/MinImageSizeCheck.java | 108 ++++++++++
.../tika/imageprocessing/BlankImageCheckTest.java | 198 ++++++++++++++++++
.../tika/imageprocessing/ByteSizeCheckTest.java | 82 ++++++++
.../imageprocessing/ImageChecksConfigTest.java | 161 ++++++++++++++
.../tika/imageprocessing/ImageDecodingTest.java | 88 ++++++++
.../apache/tika/imageprocessing/ImageFixtures.java | 77 +++++++
.../imageprocessing/MinImageSizeCheckTest.java | 121 +++++++++++
.../apache/tika/metadata/metadata-key-fields.json | 3 +
.../org/apache/tika/metadata/metadata-keys.json | 3 +
.../java/org/apache/tika/http/TikaHttpClient.java | 44 +++-
.../org/apache/tika/http/TikaHttpClientTest.java | 86 ++++++++
.../org/apache/tika/http/TikaTestHttpServer.java | 12 ++
.../tika/inference/OpenAIEmbeddingEngine.java | 2 +-
.../apache/tika/parser/vlm/AbstractVLMParser.java | 103 +++++++--
.../apache/tika/parser/vlm/ClaudeVLMParser.java | 9 +-
.../apache/tika/parser/vlm/GeminiVLMParser.java | 7 +
.../apache/tika/parser/vlm/OpenAIVLMParser.java | 7 +
.../org/apache/tika/parser/vlm/VLMOCRConfig.java | 22 +-
.../tika/parser/vlm/ClaudeVLMParserTest.java | 26 +++
.../tika/parser/vlm/GeminiVLMParserTest.java | 18 ++
.../tika/parser/vlm/OpenAIVLMParserTest.java | 213 ++++++++++++++++++-
.../tika/parser/vlm/VLMConfigExamplesTest.java | 30 ++-
.../tika/parser/vlm/VLMOperatorOnlyConfigTest.java | 3 +-
.../tika/parser/vlm/VLMPdfPageEndToEndTest.java | 109 ++++++++++
.../{openai-vlm-basic.json => jina-ocr-basic.json} | 6 +-
.../java/org/apache/tika/mime/TestMimeTypes.java | 39 ++++
.../apache/tika/parser/image/RawTiffParser.java | 2 +
.../parser/microsoft/AbstractMetafileParser.java | 3 +-
.../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 12 ++
.../java/org/apache/tika/parser/pdf/PDFParser.java | 2 +-
.../apache/tika/parser/pdf/PDFParserConfig.java | 1 +
.../org/apache/tika/parser/pdf/PDFParserTest.java | 68 ++++++
.../tika/pipes/core/config/ConfigMerger.java | 19 ++
.../tika/pipes/core/config/ConfigOverrides.java | 38 ++++
.../tika/pipes/core/server/ConnectionHandler.java | 6 -
.../apache/tika/pipes/core/server/PipesServer.java | 34 ++-
.../tika/pipes/core/server/ServerProtocolIO.java | 107 ++++++++++
.../pipes/core/server/SharedServerResources.java | 6 +-
.../tika/pipes/core/config/ConfigMergerTest.java | 25 +++
.../tika/pipes/core/server/PresetMergeTest.java | 39 ++++
.../pipes/core/server/ServerProtocolIOTest.java | 148 ++++++++++++-
.../apache/tika/pipes/fork/PipesForkParser.java | 6 +
.../tika/config/loader/ContentEnricherLoader.java | 95 +++++++--
.../config/loader/TikaObjectMapperFactory.java | 1 +
.../config/loader/ContentEnricherLoaderTest.java | 49 ++++-
.../tika/server/core/PipesRequestLimitsTest.java | 156 ++++++++++++++
tika-server/tika-server-standard/pom.xml | 6 +
92 files changed, 4044 insertions(+), 302 deletions(-)
copy
tika-parsers/tika-parsers-ml/tika-vlm/src/test/resources/config-examples/openai-vlm-basic.json
=> docs/modules/ROOT/examples/jina-ocr-basic.json (55%)
copy tika-app/src/test/java/org/apache/tika/cli/{TikaCLIChunkLiftTest.java =>
TikaCLIOcrWarningsTest.java} (70%)
copy
tika-core/src/main/java/org/apache/tika/parser/enricher/{SizeGatedEnricher.java
=> GatedEnricher.java} (54%)
create mode 100644
tika-core/src/main/java/org/apache/tika/parser/enricher/ImageCheck.java
create mode 100644
tika-core/src/main/java/org/apache/tika/parser/enricher/ImageProbe.java
create mode 100644
tika-core/src/main/java/org/apache/tika/parser/enricher/OcrWarnings.java
copy
tika-core/src/main/java/org/apache/tika/parser/enricher/{SizeGatedEnricher.java
=> RecordedSizeCheck.java} (58%)
create mode 100644
tika-core/src/test/java/org/apache/tika/config/LimitsTightenedToTest.java
create mode 100644
tika-core/src/test/java/org/apache/tika/parser/enricher/GatedEnricherTest.java
create mode 100644
tika-core/src/test/java/org/apache/tika/parser/enricher/ImageProbeTest.java
copy {tika-serialization => tika-image-processing}/pom.xml (64%)
create mode 100644
tika-image-processing/src/main/java/org/apache/tika/imageprocessing/BlankImageCheck.java
create mode 100644
tika-image-processing/src/main/java/org/apache/tika/imageprocessing/ByteSizeCheck.java
create mode 100644
tika-image-processing/src/main/java/org/apache/tika/imageprocessing/ImageDecoding.java
create mode 100644
tika-image-processing/src/main/java/org/apache/tika/imageprocessing/MinImageSizeCheck.java
create mode 100644
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/BlankImageCheckTest.java
create mode 100644
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/ByteSizeCheckTest.java
create mode 100644
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/ImageChecksConfigTest.java
create mode 100644
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/ImageDecodingTest.java
create mode 100644
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/ImageFixtures.java
create mode 100644
tika-image-processing/src/test/java/org/apache/tika/imageprocessing/MinImageSizeCheckTest.java
create mode 100644
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/VLMPdfPageEndToEndTest.java
copy
tika-parsers/tika-parsers-ml/tika-vlm/src/test/resources/config-examples/{openai-vlm-basic.json
=> jina-ocr-basic.json} (55%)
create mode 100644
tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/PipesRequestLimitsTest.java