This is an automated email from the ASF dual-hosted git repository.

tallison pushed a change to branch TIKA-4672-es-emitter
in repository https://gitbox.apache.org/repos/asf/tika.git


    from c62f31e570 tweaks
     add d49b6d1d39 TIKA-4671-lang-aware-charset-detection (#2621)
     add d4d441e783 Bump org.springframework:spring-context from 7.0.4 to 7.0.5 
(#2643)
     add e627b4b3e6 Bump org.apache.maven.plugins:maven-surefire-plugin from 
3.5.4 to 3.5.5 (#2644)
     add bf4b55424f Bump com.nimbusds:nimbus-jose-jwt from 10.7 to 10.8 (#2640)
     add 7568faf8b8 Bump com.fasterxml.jackson:jackson-bom from 2.21.0 to 
2.21.1 (#2631)
     add 7a43f5ce20 Bump twelvemonkeys.version from 3.13.0 to 3.13.1 (#2630)
     add 7616e9ebd8 Bump software.amazon.awssdk:bom from 2.41.29 to 2.41.34 
(#2629)
     add 2e33ce5214 Bump org.jetbrains:annotations from 26.0.2-1 to 26.1.0 
(#2635)
     add 4db18e5341 Bump org.apache.kafka:kafka-clients from 4.1.1 to 4.2.0 
(#2636)
     add e1d3bfe5c2 Bump net.sourceforge.tess4j:tess4j from 5.16.0 to 5.18.0 
(#2628)
     add c6cd5a71bf Bump google-auth-library-oauth2-http.version from 1.42.1 to 
1.43.0 (#2627)
     add 372d74f646 Bump com.googlecode.plist:dd-plist from 1.28 to 1.29 (#2625)
     add 9fb60a94b8 Bump com.mchange:mchange-commons-java from 0.3.2 to 0.4.0 
(#2626)
     add 1c62c0ab3d Bump org.apache.maven.plugins:maven-failsafe-plugin from 
3.5.4 to 3.5.5 (#2641)
     add 3f26230c4a Bump org.jetbrains.kotlin:kotlin-stdlib-jdk8 from 1.9.10 to 
2.3.10 (#2632)
     add 1f0ca1b9c6 Bump org.jetbrains.kotlin:kotlin-stdlib from 1.9.10 to 
2.3.10 (#2633)
     add 24daa28bc0 Bump org.codehaus.mojo:flatten-maven-plugin from 1.6.0 to 
1.7.3 (#2642)
     add acc65b8683 Bump commonmark.version from 0.24.0 to 0.27.1 (#2638)
     add bab4893999 Bump org.jetbrains.kotlin:kotlin-stdlib-common from 1.9.10 
to 2.0.21 (#2637)
     add ac1836b5ef Bump org.jetbrains.kotlin:kotlin-stdlib-jdk7 from 1.9.10 to 
2.3.10 (#2639)
     add 2a5bb03109 upgrade okhttp (#2646)
     add 52fc58d6f8 TIKA-4327: update aws
     add e7238901df TIKA-4675 -- improve wide unicode detection (#2647)
     add b9b6efae2b TIKA-4327: update c3p0
     add 608019c068 TIKA-4327: update aws
     add 3b53d0d1dd TIKA-4674 - progress timeout (#2650)
     add fdeb82f179 simplify serialization, take 2 (#2651)
     add 8c0329132a TIKA-4676 -- refactor inference and fix endian bug in 
ESEmitter (#2653)
     add 8d8f3440f7 TIKA-4327: update aws, jwarc
     add e5151b1e5b TIKA-4327: update google-api
     add 2fd8c0eda2 TIKA-4327: update microsoft-graph.version, maven.bundle, 
aws, google cloud, junrar, mockito, error_prone_annotations
     add 9451da2d56 TIKA-4606: Upgrade Apache Ignite from 2.x to 3.x (fresh) 
(#2654)
     add 2a9957a12b Bump org.tukaani:xz from 1.11 to 1.12 (#2670)
     add 0385b58466 Bump io.swagger.core.v3:swagger-annotations from 2.2.38 to 
2.2.43 (#2669)
     add 1d46c8b97f Bump org.jetbrains.kotlin:kotlin-stdlib from 2.2.0 to 
2.3.10 (#2663)
     add aaef3ca7a3 Bump info.picocli:picocli from 4.7.5 to 4.7.7 (#2661)
     add b9903d0840 Bump org.jetbrains:annotations from 26.0.2-1 to 26.1.0 
(#2659)
     add 4ba11a4e19 Bump org.yaml:snakeyaml from 2.4 to 2.6 (#2671)
     add 4c9017fca3 Bump jakarta.inject:jakarta.inject-api from 2.0.1 to 
2.0.1.MR (#2667)
     add 93b5cfa96f TIKA-4488: update micronaut
     add d139bfe02e TIKA-4488: add micronaut version
     add a7116b05d9 TIKA-4488: add micronaut version
     add 27933e64b9 TIKA-4327: add comment
     add 9f94799669 TIKA-4327: update tyrus, kiota, solrj, spotless-maven-plugin
     add 30e46db4fa TIKA-4606: Add e2e tests for Ignite 3.x upgrade (#2655)
     add ca67465e90 TIKA-4327: update aws, swagger, jackrabbit; add comment on 
solrj 10 migration
     add a62fd73ec1 resolve merge conflicts

No new revisions were added by this update.

Summary of changes:
 .github/workflows/main-jdk17-build.yml             |  19 +
 .../main-jdk17-windows-build-multi-locale.yml      |   2 +-
 .github/workflows/main-jdk17-windows-build.yml     |   2 +-
 .java-version                                      |  18 -
 docs/modules/ROOT/nav.adoc                         |   1 +
 docs/modules/ROOT/pages/pipes/index.adoc           |   1 +
 .../ROOT/pages/pipes/shared-server-mode.adoc       |  10 +-
 docs/modules/ROOT/pages/pipes/timeouts.adoc        | 170 ++++++
 pom.xml                                            |   6 +
 tika-app/pom.xml                                   |  12 +
 .../src/main/java/org/apache/tika/cli/TikaCLI.java |   4 +-
 .../test/resources/configs/config-template.json    |   6 +-
 .../apache/tika/config/TikaProgressTracker.java    |  82 +++
 .../org/apache/tika/config/TikaTaskTimeout.java    |  76 ---
 .../java/org/apache/tika/config/TimeoutLimits.java | 112 +++-
 .../tika/detect/CompositeEncodingDetector.java     | 155 ++++-
 .../tika/detect/DefaultEncodingDetector.java       |  27 +-
 .../tika/detect/EncodingDetectorContext.java       | 105 ++++
 .../apache/tika/detect/MetaEncodingDetector.java   |  39 ++
 .../apache/tika/detect/WideUnicodeDetector.java    | 490 +++++++++++++++
 .../tika/language/detect/LanguageResult.java       |  28 +
 .../apache/tika/metadata/TikaCoreProperties.java   |   8 +
 .../tika/parser/external2/ExternalParser.java      |   6 +-
 .../tika/config/TikaProgressTrackerTest.java       | 103 ++++
 .../tika/detect/WideUnicodeDetectorTest.java       | 452 ++++++++++++++
 tika-e2e-tests/README.md                           |  12 +-
 tika-e2e-tests/pom.xml                             |  66 +-
 tika-e2e-tests/tika-grpc/README.md                 | 100 +--
 tika-e2e-tests/tika-grpc/pom.xml                   |  52 +-
 .../tika/parser/ocr/TesseractOCRConfig.properties  |  25 -
 .../customocr/tika-config-inline.json              |  26 -
 .../customocr/tika-config-inline.xml               |  49 --
 .../customocr/tika-config-rendered.json            |  28 -
 .../customocr/tika-config-rendered.xml             |  55 --
 .../tika/parser/journal/GrobidExtractor.properties |  16 -
 .../sample-configs/grobid/tika-config.json         |  23 -
 .../sample-configs/grobid/tika-config.xml          |  41 --
 .../tika-grpc/sample-configs/ignite/README.md      | 117 ----
 .../sample-configs/ignite/tika-config-ignite.json  |   2 +-
 .../sample-configs/ner/run_tika_server.sh          |  62 --
 .../tika-grpc/sample-configs/ner/tika-config.json  |  26 -
 .../tika-grpc/sample-configs/ner/tika-config.xml   |  45 --
 .../tika-grpc/sample-configs/test-simple.json      |  20 -
 .../vision/inception-rest-caption.json             |  18 -
 .../vision/inception-rest-caption.xml              |  32 -
 .../vision/inception-rest-video.json               |  18 -
 .../sample-configs/vision/inception-rest-video.xml |  32 -
 .../sample-configs/vision/inception-rest.json      |  18 -
 .../sample-configs/vision/inception-rest.xml       |  32 -
 .../org/apache/tika/pipes/ExternalTestBase.java    | 285 +++++++--
 .../pipes/filesystem/FileSystemFetcherTest.java    |  79 ++-
 .../tika/pipes/ignite/IgniteConfigStoreTest.java   | 679 ++++++++++++++-------
 .../java/org/apache/tika/pipes/ignite/README.md    | 172 ------
 .../src/test/resources/docker-compose-ignite.yml   |  25 -
 .../src/test/resources/docker-compose.yml          |  16 -
 .../tika-grpc/src/test/resources/log4j2.xml        |  19 -
 .../src/test/resources/test-fixtures/sample.csv    |   4 +
 .../src/test/resources/test-fixtures/sample.html   |   8 +
 .../src/test/resources/test-fixtures/sample.txt    |   3 +
 .../src/test/resources/test-fixtures/sample.xml    |   5 +
 ...g-ignite.json => tika-config-ignite-local.json} |   4 +-
 .../src/test/resources/tika-config-ignite.json     |   2 +-
 .../tika-grpc/src/test/resources/tika-config.json  |  49 +-
 .../tika/example/PipesForkParserExample.java       |  10 +-
 tika-grpc/dev-tika-config.json                     |   3 +-
 tika-grpc/pom.xml                                  |  22 +-
 tika-grpc/run-dev.sh                               |  15 +-
 .../org/apache/tika/pipes/grpc/TikaGrpcServer.java |   7 +-
 .../apache/tika/pipes/grpc/TikaGrpcServerImpl.java |  39 +-
 tika-grpc/src/main/proto/tika.proto                |   2 +
 .../src/test/resources/tika-config-ignite.json     |   2 +-
 .../src/test/resources/tika-pipes-test-config.json |   6 +-
 .../elasticsearch/tests/ElasticsearchTest.java     |  27 +
 .../resources/elasticsearch/plugins-template.json  |  12 +-
 .../src/test/resources/kafka/plugins-template.json |   1 -
 .../resources/opensearch/plugins-template.json     |   3 +-
 .../opensearch/tika-config-opensearch.json         |   3 +-
 .../src/test/resources/s3/plugins-template.json    |   1 -
 .../src/test/resources/solr/plugins-template.json  |   3 +-
 .../src/test/resources/tika-config-solr-urls.json  |   1 -
 .../tika/langdetect/charsoup/CharSoupModel.java    |  18 +-
 .../charsoup/CharSoupEncodingDetector.java         | 186 ++++++
 .../charsoup/CharSoupLanguageDetector.java         | 155 ++++-
 .../charsoup/CharSoupEncodingDetectorTest.java     | 206 +++++++
 .../langdetect/charsoup/TextQualityDiagTest.java   | 141 +++++
 tika-langdetect/tika-langdetect-optimaize/pom.xml  |   2 +-
 tika-parent/pom.xml                                | 141 ++++-
 tika-parsers/pom.xml                               |   2 +
 .../pom.xml                                        |  46 +-
 .../java/org/apache/tika/http/TikaHttpClient.java  | 150 +++++
 .../org/apache/tika/http/TikaTestHttpServer.java   | 268 ++++++++
 .../org/apache/tika/parser/gdal/GDALParser.java    |   6 +-
 tika-parsers/tika-parsers-ml/pom.xml               |   2 +-
 .../tika-parsers-ml/tika-inference/pom.xml         |  48 +-
 .../tika/inference/OpenAIEmbeddingFilter.java      |  85 +--
 .../tika/inference/OpenAIImageEmbeddingParser.java | 103 +---
 .../apache/tika/inference/VectorSerializer.java    |   8 +-
 .../tika/inference/OpenAIEmbeddingFilterTest.java  |  53 +-
 .../inference/OpenAIImageEmbeddingParserTest.java  | 111 ++--
 .../apache/tika/parser/ner/NamedEntityParser.java  |   2 +
 .../src/test/resources/configs/tika-config.json    |   2 +-
 .../tika-parser-tess4j-module/pom.xml              |   2 +-
 .../tika/parser/ocr/tess4j/Tess4JParser.java       |   6 +-
 .../pom.xml                                        |  53 +-
 .../apache/tika/parser/vlm/AbstractVLMParser.java  | 107 ++--
 .../apache/tika/parser/vlm/ClaudeVLMParser.java    |  21 +-
 .../apache/tika/parser/vlm/GeminiVLMParser.java    |  14 +-
 .../tika/parser/vlm/MarkdownToXHTMLEmitter.java    |   0
 .../apache/tika/parser/vlm/OpenAIVLMParser.java    |  19 +-
 .../org/apache/tika/parser/vlm/VLMOCRConfig.java   |   0
 .../tika/parser/vlm/ClaudeVLMParserTest.java       |  62 +-
 .../tika/parser/vlm/GeminiVLMParserTest.java       |  64 +-
 .../parser/vlm/MarkdownToXHTMLEmitterTest.java     |   0
 .../tika/parser/vlm/OpenAIVLMParserTest.java       |  64 +-
 .../apache/tika/parser/ocr/TesseractOCRParser.java |   6 +-
 .../tika/parser/ocr/TesseractOCRParserTest.java    |   4 +-
 .../apache/tika/parser/strings/StringsParser.java  |  11 +-
 .../tika-parsers-standard-package/pom.xml          |   6 +
 .../tika/config/TikaEncodingDetectorTest.java      |  49 +-
 .../org/apache/tika/parser/pdf/PDFParserTest.java  |  32 +-
 ...A-4671-exclude-charsoup-encoding-detector.json} |   6 +-
 .../testArabicMisleadingCharset.html               |  11 +
 .../org/apache/tika/async/cli/PluginsWriter.java   |  15 +-
 .../test/resources/configs/config-template.json    |   6 +-
 tika-pipes/tika-pipes-api/pom.xml                  |  19 +
 .../java/org/apache/tika/pipes/api/ParseMode.java  |   3 +
 tika-pipes/tika-pipes-config-store-ignite/pom.xml  | 113 +++-
 .../tika/pipes/ignite/ExtensionConfigDTO.java      |  29 +-
 .../tika/pipes/ignite/IgniteConfigStore.java       | 182 +++---
 .../ignite/config/IgniteConfigStoreConfig.java     |  59 +-
 .../pipes/ignite/server/IgniteStoreServer.java     | 201 +++---
 .../tika/pipes/ignite/IgniteConfigStoreTest.java   | 119 ++--
 .../org/apache/tika/pipes/core/PipesClient.java    |  41 +-
 .../org/apache/tika/pipes/core/PipesConfig.java    |  15 -
 .../tika/pipes/core/config/ConfigMerger.java       |  22 +-
 .../tika/pipes/core/config/ConfigOverrides.java    |  39 +-
 .../tika/pipes/core/protocol/PipesMessage.java     |  16 +-
 .../tika/pipes/core/server/ConnectionHandler.java  |  62 +-
 .../apache/tika/pipes/core/server/PipesServer.java |  43 +-
 .../tika/pipes/core/config/ConfigMergerTest.java   |  11 +-
 .../tika/pipes/core/protocol/PipesMessageTest.java |   2 +-
 .../apache/tika/pipes/fork/PipesForkParser.java    |   6 +-
 .../tika/pipes/fork/PipesForkParserConfig.java     |  22 +-
 .../tika/pipes/fork/PipesForkParserTest.java       |  52 +-
 .../apache/tika/pipes/core/CrashingDetector.java   |   2 +
 .../apache/tika/pipes/core/PipesClientTest.java    |  30 +-
 .../resources/configs/tika-config-bad-class.json   |   6 +-
 .../configs/tika-config-bad-java-path.json         |   6 +-
 .../configs/tika-config-bad-jvm-args.json          |   6 +-
 .../test/resources/configs/tika-config-basic.json  |   8 +-
 .../configs/tika-config-crashing-detector.json     |   8 +-
 .../resources/configs/tika-config-emit-all.json    |   6 +-
 .../resources/configs/tika-config-passback.json    |   8 +-
 .../configs/tika-config-shared-server.json         |   8 +-
 .../configs/tika-config-timeout-lt-heartbeat.json  |   6 +-
 .../resources/configs/tika-config-truncate.json    |   4 +-
 .../resources/configs/tika-config-uppercasing.json |   8 +-
 .../configs/tika-config-write-limiter.json         |   4 +-
 .../apache/tika/pipes/emitter/es/ESEmitter.java    |   8 +-
 .../tika/pipes/emitter/es/HttpClientConfig.java    |   8 +-
 .../tika/pipes/reporter/es/ESPipesReporter.java    |   8 +-
 .../tika-pipes-google-drive/pom.xml                |   6 +-
 .../tika-pipes-microsoft-graph/pom.xml             |   4 +-
 .../tika/config/loader/ComponentInstantiator.java  | 157 ++++-
 .../config/loader/TikaObjectMapperFactory.java     |  29 +
 .../tika/serialization/ComponentNameResolver.java  | 104 +++-
 .../tika/serialization/ParseContextUtils.java      |  36 +-
 .../org/apache/tika/serialization/TikaModule.java  | 238 +-------
 .../serdes/ParseContextDeserializer.java           |  47 +-
 .../serdes/ParseContextSerializer.java             |  42 +-
 .../java/org/apache/tika/config/AllLimitsTest.java |  11 +-
 .../org/apache/tika/config/TimeoutLimitsTest.java  |  55 +-
 .../tika/config/loader/ConfigLoaderTest.java       |  24 +-
 .../serialization/RoundTripSerializationTest.java  |  38 +-
 .../TestParseContextSerialization.java             |  49 +-
 .../test/resources/configs/all-limits-test.json    |   3 +-
 .../test/resources/configs/test-config-loader.json |   2 +-
 .../resources/configs/test-partial-config.json     |   2 +-
 .../resources/configs/timeout-limits-test.json     |   3 +-
 .../apache/tika/server/core/TikaServerProcess.java |   4 +-
 .../org/apache/tika/server/core/CXFTestBase.java   |   8 +-
 .../core/TikaServerPipesIntegrationTest.java       |   2 +-
 .../resources/configs/cxf-test-base-template.json  |   8 +-
 .../configs/cxf-unpack-test-template.json          |   4 +-
 .../configs/tika-config-server-basic.json          |   6 +-
 .../configs/tika-config-server-emitter.json        |   6 +-
 .../tika-config-server-fetcher-template.json       |   6 +-
 .../tika-config-server-fetchers-emitters.json      |   6 +-
 .../configs/tika-config-server-pipes-basic.json    |   6 +-
 .../tika-config-server-tls-one-way-template.json   |   6 +-
 .../tika-config-server-tls-two-way-template.json   |   6 +-
 .../resources/configs/tika-config-server-tls.json  |   6 +-
 .../test/resources/configs/tika-config-server.json |   6 +-
 .../configs/tika-config-timeout-100ms.json         |   4 +-
 .../configs/tika-config-with-timeout.json          |   4 +-
 tika-server/tika-server-standard/pom.xml           |  12 +
 .../resources/configs/cxf-test-base-template.json  |   8 +-
 .../configs/tika-config-for-server-tests.json      |   6 +-
 .../test/resources/configs/tika-config-json.json   |   6 +-
 .../tika-config-langdetect-opennlp-filter.json     |   6 +-
 .../tika-config-langdetect-optimaize-filter.json   |   6 +-
 tika-translate/pom.xml                             |   2 +-
 202 files changed, 5676 insertions(+), 3147 deletions(-)
 delete mode 100644 .java-version
 create mode 100644 docs/modules/ROOT/pages/pipes/timeouts.adoc
 create mode 100644 
tika-core/src/main/java/org/apache/tika/config/TikaProgressTracker.java
 delete mode 100644 
tika-core/src/main/java/org/apache/tika/config/TikaTaskTimeout.java
 create mode 100644 
tika-core/src/main/java/org/apache/tika/detect/EncodingDetectorContext.java
 create mode 100644 
tika-core/src/main/java/org/apache/tika/detect/MetaEncodingDetector.java
 create mode 100644 
tika-core/src/main/java/org/apache/tika/detect/WideUnicodeDetector.java
 create mode 100644 
tika-core/src/test/java/org/apache/tika/config/TikaProgressTrackerTest.java
 create mode 100644 
tika-core/src/test/java/org/apache/tika/detect/WideUnicodeDetectorTest.java
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/customocr/org/apache/tika/parser/ocr/TesseractOCRConfig.properties
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/customocr/tika-config-inline.json
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/customocr/tika-config-inline.xml
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/customocr/tika-config-rendered.json
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/customocr/tika-config-rendered.xml
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/grobid/org/apache/tika/parser/journal/GrobidExtractor.properties
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/grobid/tika-config.json
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/grobid/tika-config.xml
 delete mode 100644 tika-e2e-tests/tika-grpc/sample-configs/ignite/README.md
 delete mode 100755 
tika-e2e-tests/tika-grpc/sample-configs/ner/run_tika_server.sh
 delete mode 100644 tika-e2e-tests/tika-grpc/sample-configs/ner/tika-config.json
 delete mode 100644 tika-e2e-tests/tika-grpc/sample-configs/ner/tika-config.xml
 delete mode 100644 tika-e2e-tests/tika-grpc/sample-configs/test-simple.json
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/vision/inception-rest-caption.json
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/vision/inception-rest-caption.xml
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/vision/inception-rest-video.json
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/vision/inception-rest-video.xml
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/vision/inception-rest.json
 delete mode 100644 
tika-e2e-tests/tika-grpc/sample-configs/vision/inception-rest.xml
 delete mode 100644 
tika-e2e-tests/tika-grpc/src/test/java/org/apache/tika/pipes/ignite/README.md
 delete mode 100644 
tika-e2e-tests/tika-grpc/src/test/resources/docker-compose-ignite.yml
 delete mode 100644 
tika-e2e-tests/tika-grpc/src/test/resources/docker-compose.yml
 delete mode 100644 tika-e2e-tests/tika-grpc/src/test/resources/log4j2.xml
 create mode 100644 
tika-e2e-tests/tika-grpc/src/test/resources/test-fixtures/sample.csv
 create mode 100644 
tika-e2e-tests/tika-grpc/src/test/resources/test-fixtures/sample.html
 create mode 100644 
tika-e2e-tests/tika-grpc/src/test/resources/test-fixtures/sample.txt
 create mode 100644 
tika-e2e-tests/tika-grpc/src/test/resources/test-fixtures/sample.xml
 copy tika-e2e-tests/tika-grpc/src/test/resources/{tika-config-ignite.json => 
tika-config-ignite-local.json} (90%)
 create mode 100644 
tika-langdetect/tika-langdetect-charsoup/src/main/java/org/apache/tika/langdetect/charsoup/CharSoupEncodingDetector.java
 create mode 100644 
tika-langdetect/tika-langdetect-charsoup/src/test/java/org/apache/tika/langdetect/charsoup/CharSoupEncodingDetectorTest.java
 create mode 100644 
tika-langdetect/tika-langdetect-charsoup/src/test/java/org/apache/tika/langdetect/charsoup/TextQualityDiagTest.java
 copy tika-parsers/{tika-parsers-ml/tika-parser-tess4j-module => 
tika-http-jdk}/pom.xml (71%)
 create mode 100644 
tika-parsers/tika-http-jdk/src/main/java/org/apache/tika/http/TikaHttpClient.java
 create mode 100644 
tika-parsers/tika-http-jdk/src/test/java/org/apache/tika/http/TikaTestHttpServer.java
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/pom.xml (67%)
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/src/main/java/org/apache/tika/parser/vlm/AbstractVLMParser.java (80%)
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/src/main/java/org/apache/tika/parser/vlm/ClaudeVLMParser.java (92%)
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/src/main/java/org/apache/tika/parser/vlm/GeminiVLMParser.java (94%)
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/src/main/java/org/apache/tika/parser/vlm/MarkdownToXHTMLEmitter.java 
(100%)
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/src/main/java/org/apache/tika/parser/vlm/OpenAIVLMParser.java (94%)
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/src/main/java/org/apache/tika/parser/vlm/VLMOCRConfig.java (100%)
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/src/test/java/org/apache/tika/parser/vlm/ClaudeVLMParserTest.java 
(82%)
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/src/test/java/org/apache/tika/parser/vlm/GeminiVLMParserTest.java 
(81%)
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/src/test/java/org/apache/tika/parser/vlm/MarkdownToXHTMLEmitterTest.java
 (100%)
 rename tika-parsers/tika-parsers-ml/{tika-parser-vlm-ocr-module => 
tika-vlm}/src/test/java/org/apache/tika/parser/vlm/OpenAIVLMParserTest.java 
(84%)
 copy 
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/resources/configs/{TIKA-2273-exclude-encoding-detector-default.json
 => TIKA-4671-exclude-charsoup-encoding-detector.json} (53%)
 create mode 100644 
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/resources/test-documents/testArabicMisleadingCharset.html

Reply via email to