[
https://issues.apache.org/jira/browse/TIKA-4884?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18114037#comment-18114037
]
Hudson commented on TIKA-4884:
------------------------------
SUCCESS: Integrated in Jenkins build Tika ยป tika-main-jdk17 #1626 (See
[https://ci-builds.apache.org/job/Tika/job/tika-main-jdk17/1626/])
TIKA-4884: rm ocr pseudo types (#3147) (github:
[https://github.com/apache/tika/commit/39d5ca53f4f64f55f373c02ac29350b9d2bc6a09])
* (edit)
tika-core/src/main/java/org/apache/tika/parser/enricher/CompositeContentEnricher.java
* (edit) docs/modules/ROOT/nav.adoc
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/main/java/org/apache/tika/parser/vlm/AbstractVLMParser.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/OpenAIVLMParserTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/resources/config-examples/claude-vlm-basic.json
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/main/java/org/apache/tika/parser/vlm/VLMOCRConfig.java
* (add)
tika-pipes/tika-pipes-integration-tests/src/test/resources/configs/tika-config-text-recognizers.json
* (add) docs/modules/ROOT/pages/developers/custom-ocr-engine.adoc
* (edit)
tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/test/resources/config-examples/tess4j-basic.json
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/resources/config-examples/gemini-vlm-full.json
* (edit)
tika-serialization/src/main/java/org/apache/tika/config/loader/ContentEnricherLoader.java
* (edit) tika-core/src/main/java/org/apache/tika/parser/AutoDetectParser.java
* (edit)
tika-core/src/main/java/org/apache/tika/parser/enricher/ContentEnrichers.java
* (delete)
tika-pipes/tika-pipes-integration-tests/src/test/resources/configs/tika-config-content-enrichers.json
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/java/org/apache/tika/parser/html/HtmlParserTest.java
* (edit)
tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/CXFTestBase.java
* (edit) tika-core/src/test/java/org/apache/tika/parser/mock/MockEnricher.java
* (edit)
tika-serialization/src/test/java/org/apache/tika/config/loader/TikaLoaderRoundTripTest.java
* (edit)
tika-serialization/src/test/java/org/apache/tika/config/loader/ContentEnricherLoaderTest.java
* (edit) tika-core/src/main/java/org/apache/tika/parser/ParseRecord.java
* (edit)
tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/test/java/org/apache/tika/parser/ocr/tess4j/Tess4JParserTest.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
* (edit)
tika-serialization/src/main/java/org/apache/tika/config/loader/AbstractSpiComponentLoader.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/resources/config-examples/pdf-parser-full.json
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/resources/config-examples/tesseract-full.json
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/VLMRuntimeConfigMergeTest.java
* (edit)
tika-serialization/src/main/java/org/apache/tika/config/loader/ComponentInstantiator.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/test/java/org/apache/tika/parser/image/ImageParserTest.java
* (edit)
tika-serialization/src/main/java/org/apache/tika/config/loader/TikaJsonConfig.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/main/java/org/apache/tika/parser/vlm/ClaudeVLMParser.java
* (add)
tika-serialization/src/test/java/org/apache/tika/config/loader/TestSpiEnricher.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/resources/config-examples/gemini-vlm-basic.json
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/TesseractOCRParser.java
* (edit)
tika-server/docker-build/sample-configs/customocr/tika-config-rendered.json
* (edit) docs/modules/ROOT/pages/configuration/parsers/tesseract-ocr-parser.adoc
* (edit) tika-core/src/main/java/org/apache/tika/parser/CompositeParser.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/java/org/apache/tika/parser/ocr/TesseractOCRParserTest.java
* (edit)
tika-core/src/main/java/org/apache/tika/extractor/EmbeddedDocumentUtil.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/main/java/org/apache/tika/parser/vlm/GeminiVLMParser.java
* (edit)
tika-server/docker-build/sample-configs/customocr/tika-config-inline.json
* (delete)
tika-server/tika-server-standard/src/test/java/org/apache/tika/server/standard/ContentEnricherWireTest.java
* (edit)
tika-parsers/tika-parsers-extended/tika-parser-ocr-encode-module/src/main/java/org/apache/tika/parser/ocrencode/EncodeOCRParser.java
* (edit) docs/modules/ROOT/pages/configuration/parsers/vlm-parsers.adoc
* (edit)
tika-serialization/src/main/java/org/apache/tika/config/loader/ParserLoader.java
* (add)
tika-server/tika-server-standard/src/test/resources/configs/tika-config-text-recognizers.json
* (edit)
tika-parsers/tika-parsers-extended/tika-parser-scientific-package/src/test/resources/2.4.1-tesseract.txt
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/resources/config-examples/tesseract-basic.json
* (edit)
tika-serialization/src/main/java/org/apache/tika/config/loader/LoaderContext.java
* (edit)
tika-serialization/src/main/java/org/apache/tika/config/loader/TikaLoader.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
* (edit)
tika-pipes/tika-pipes-integration-tests/src/test/java/org/apache/tika/pipes/core/PipesClientTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-inference/src/main/java/org/apache/tika/inference/OpenAIImageEmbeddingParser.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/java/org/apache/tika/parser/microsoft/rtf/RTFParserTest.java
* (edit)
tika-core/src/test/java/org/apache/tika/extractor/EmbeddedDocumentUtilExtensionTest.java
* (edit) CHANGES.txt
* (edit) docs/modules/ROOT/pages/developers/serialization.adoc
* (edit) docs/modules/ROOT/pages/configuration/parsers/pdf-parser.adoc
* (edit)
tika-core/src/test/java/org/apache/tika/parser/enricher/ContentEnrichersTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/resources/config-examples/openai-vlm-full.json
* (add)
tika-server/tika-server-standard/src/test/java/org/apache/tika/server/standard/TextRecognizerWireTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/test/resources/config-examples/tess4j-full.json
* (edit) docs/modules/ROOT/pages/configuration/index.adoc
* (edit) docs/modules/ROOT/pages/using-tika/docker.adoc
* (edit)
tika-serialization/src/test/java/org/apache/tika/config/loader/TestPngEnricher.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/AbstractPDF2XHTML.java
* (add)
tika-serialization/src/test/java/org/apache/tika/config/loader/TestPngRecognizer.java
* (edit)
tika-parsers/tika-parsers-extended/tika-parser-ocr-encode-module/src/test/java/org/apache/tika/parser/ocrencode/EncodeOCRParserTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/VLMConfigExamplesTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/resources/config-examples/openai-vlm-basic.json
* (edit) tika-app/src/test/java/org/apache/tika/cli/TikaCLITest.java
* (edit)
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/server/ParseHandler.java
* (edit) tika-core/src/test/java/org/apache/tika/parser/CompositeParserTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/test/java/org/apache/tika/parser/ocr/tess4j/Tess4JConfigExamplesTest.java
* (delete)
tika-core/src/main/java/org/apache/tika/parser/enricher/LegacyDispatchEnricher.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/AbstractImageParser.java
* (edit)
tika-parsers/tika-parsers-ml/tika-inference/src/test/java/org/apache/tika/inference/OpenAIImageEmbeddingParserTest.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/main/java/org/apache/tika/parser/vlm/OpenAIVLMParser.java
* (edit)
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/extractor/StandardUnpackSelector.java
* (edit)
tika-core/src/main/java/org/apache/tika/parser/enricher/TextRecognizer.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserTest.java
* (edit) docs/modules/ROOT/pages/advanced/local-vlm-server.adoc
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/java/org/apache/tika/parser/AutoDetectParserTest.java
* (edit) docs/modules/ROOT/pages/developers/index.adoc
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/ImageParser.java
* (edit) docs/modules/ROOT/pages/migration-to-4x/migrating-to-4x.adoc
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/java/org/apache/tika/config/ConfigExamplesTest.java
* (add)
tika-core/src/main/java/org/apache/tika/parser/enricher/ContentEnricher.java
* (delete)
tika-server/tika-server-standard/src/test/resources/configs/tika-config-content-enrichers.json
* (edit) tika-core/src/main/java/org/apache/tika/parser/DefaultParser.java
* (edit)
tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/main/java/org/apache/tika/parser/ocr/tess4j/Tess4JParser.java
* (edit)
tika-parsers/tika-parsers-ml/tika-vlm/src/test/resources/config-examples/claude-vlm-full.json
* (edit) docs/modules/ROOT/pages/configuration/parsers/tess4j-parser.adoc
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/java/org/apache/tika/parser/odf/ODFParserTest.java
* (edit) docs/modules/ROOT/pages/pipes/timeouts.adoc
> Clean up enrichers
> ------------------
>
> Key: TIKA-4884
> URL: https://issues.apache.org/jira/browse/TIKA-4884
> Project: Tika
> Issue Type: Task
> Reporter: Tim Allison
> Priority: Minor
>
> We added content enrichers to enable multiple parsers in a controlled way. We
> should clean up the initial implementation before the 4.1.0 release,
> including louder warnings on edge cases etc.
> There's also area for cleanup in handling the legacy "image/ocr-png"
> workarounds.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)