This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch TIKA-4875
in repository https://gitbox.apache.org/repos/asf/tika.git
from 898871888b Merge remote-tracking branch
'refs/remotes/origin/TIKA-4875' into TIKA-4875
add 4a563d6fdb Add a placeholder marker (#3122)
add 54a8ed6892 TIKA-4872 - improve ocr wiring (#3119)
add 1a55c51e79 Merge branch 'main' into TIKA-4875
No new revisions were added by this update.
Summary of changes:
CHANGES.txt | 38 +++
docs/modules/ROOT/pages/configuration/index.adoc | 31 ++
.../ROOT/pages/configuration/metadata-filters.adoc | 5 +
.../pages/configuration/parsers/tess4j-parser.adoc | 7 +
.../parsers/tesseract-ocr-parser.adoc | 18 +-
.../pages/configuration/parsers/vlm-parsers.adoc | 14 +-
.../java/org/apache/tika/io/PlaceholderSource.java | 122 +++++++
.../java/org/apache/tika/io/TikaInputSource.java | 8 +
.../java/org/apache/tika/io/TikaInputStream.java | 14 +-
.../parser/enricher/CompositeContentEnricher.java | 88 +++++
.../tika/parser/enricher/ContentEnrichers.java | 194 +++++++++++
.../tika/parser/enricher/EnrichingParser.java | 21 +-
.../parser/enricher/LegacyDispatchEnricher.java | 106 ++++++
.../org/apache/tika/renderer/RenderResult.java | 3 +-
.../org/apache/tika/io/PlaceholderStreamTest.java | 63 ++++
.../tika/parser/enricher/ContentEnrichersTest.java | 371 +++++++++++++++++++++
.../tika/inference/AbstractEmbeddingFilter.java | 68 +++-
.../apache/tika/inference/JinaEmbeddingFilter.java | 5 +
.../tika/inference/OpenAIEmbeddingFilter.java | 12 +
.../tika/inference/OpenAIEmbeddingFilterTest.java | 57 ++++
.../apache/tika/parser/vlm/OpenAIVLMParser.java | 3 +-
.../tika/parser/vlm/OpenAIVLMParserTest.java | 17 +
.../tika/parser/image/AbstractImageParser.java | 58 +---
.../apache/tika/parser/image/ImageParserTest.java | 80 ++++-
.../tika/parser/microsoft/MetafileRendering.java | 2 +-
.../apache/tika/parser/microsoft/OfficeParser.java | 11 +-
.../apache/tika/parser/ocr/TesseractOCRParser.java | 3 +-
.../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 69 ++--
.../java/org/apache/tika/parser/pdf/OCR2XHTML.java | 11 +-
.../java/org/apache/tika/parser/pdf/PDF2XHTML.java | 19 +-
.../tika/parser/pdf/PDFMarkedContent2XHTML.java | 11 +-
.../java/org/apache/tika/parser/pdf/PDFParser.java | 20 +-
.../tika/parser/pdf/image/ImageGraphicsEngine.java | 2 +-
.../org/apache/tika/parser/pdf/PDFParserTest.java | 94 ++++++
.../org/apache/tika/pipes/core/MockEnricher.java | 35 +-
.../apache/tika/pipes/core/PipesClientTest.java | 30 ++
...sic.json => tika-config-content-enrichers.json} | 1 +
.../tika/config/loader/ContentEnricherLoader.java | 69 ++++
.../apache/tika/config/loader/LoaderContext.java | 11 +
.../apache/tika/config/loader/ParserLoader.java | 64 +++-
.../apache/tika/config/loader/TikaJsonConfig.java | 1 +
.../org/apache/tika/config/loader/TikaLoader.java | 9 +
.../config/loader/ContentEnricherLoaderTest.java | 113 +++++++
...malTestParser.java => EnrichingTestParser.java} | 33 +-
.../{OptInTestParser.java => TestPngEnricher.java} | 18 +-
...estParser.java => TestUnavailableEnricher.java} | 17 +-
46 files changed, 1852 insertions(+), 194 deletions(-)
create mode 100644
tika-core/src/main/java/org/apache/tika/io/PlaceholderSource.java
create mode 100644
tika-core/src/main/java/org/apache/tika/parser/enricher/CompositeContentEnricher.java
create mode 100644
tika-core/src/main/java/org/apache/tika/parser/enricher/ContentEnrichers.java
copy
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/BytesRefCalculator.java
=>
tika-core/src/main/java/org/apache/tika/parser/enricher/EnrichingParser.java
(66%)
create mode 100644
tika-core/src/main/java/org/apache/tika/parser/enricher/LegacyDispatchEnricher.java
create mode 100644
tika-core/src/test/java/org/apache/tika/io/PlaceholderStreamTest.java
create mode 100644
tika-core/src/test/java/org/apache/tika/parser/enricher/ContentEnrichersTest.java
copy tika-core/src/main/java/org/apache/tika/parser/EmptyParser.java =>
tika-pipes/tika-pipes-integration-tests/src/test/java/org/apache/tika/pipes/core/MockEnricher.java
(69%)
copy
tika-pipes/tika-pipes-integration-tests/src/test/resources/configs/{tika-config-basic.json
=> tika-config-content-enrichers.json} (95%)
create mode 100644
tika-serialization/src/main/java/org/apache/tika/config/loader/ContentEnricherLoader.java
create mode 100644
tika-serialization/src/test/java/org/apache/tika/config/loader/ContentEnricherLoaderTest.java
copy
tika-serialization/src/test/java/org/apache/tika/config/loader/{MinimalTestParser.java
=> EnrichingTestParser.java} (66%)
copy
tika-serialization/src/test/java/org/apache/tika/config/loader/{OptInTestParser.java
=> TestPngEnricher.java} (71%)
copy
tika-serialization/src/test/java/org/apache/tika/config/loader/{OptInTestParser.java
=> TestUnavailableEnricher.java} (71%)