This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch TIKA-4813-timeout-improvements
in repository https://gitbox.apache.org/repos/asf/tika.git
from 2ef96c9c35 TIKA-4813 -- fix properties table
add 01767e6648 further tweaks after review
No new revisions were added by this update.
Summary of changes:
.../ROOT/pages/advanced/setting-limits.adoc | 66 ++++-----
.../migration-to-4x/migrating-tika-server-4x.adoc | 8 +-
docs/modules/ROOT/pages/pipes/timeouts.adoc | 77 ++++++++--
docs/modules/ROOT/pages/using-tika/cli/index.adoc | 10 +-
.../ROOT/pages/using-tika/server/index.adoc | 14 ++
.../src/main/java/org/apache/tika/cli/TikaCLI.java | 36 ++++-
.../test/java/org/apache/tika/cli/TikaCLITest.java | 31 ++++
.../tika/cli/XmlToJsonConfigConverterTest.java | 2 +-
.../xml-configs/tika-config-list-map-types.xml | 2 +-
.../apache/tika/detect/FileCommandDetector.java | 16 +-
.../ParsingEmbeddedDocumentExtractor.java | 18 ++-
.../org/apache/tika/parser/CompositeParser.java | 28 +++-
.../tika/parser/external/ExternalParser.java | 4 +-
.../tika/parser/external/ExternalParserConfig.java | 10 +-
.../java/org/apache/tika/utils/ProcessUtils.java | 16 +-
.../tika/detect/FileCommandDetectorTest.java | 26 ++++
...arsingEmbeddedDocumentExtractorTimeoutTest.java | 105 ++++++++++++++
.../apache/tika/parser/CompositeParserTest.java | 59 ++++++++
.../org/apache/tika/utils/ProcessUtilsTest.java | 24 +++
.../apache/tika/detect/magika/MagikaDetector.java | 14 +-
.../tika/detect/siegfried/SiegfriedDetector.java | 14 +-
.../java/org/apache/tika/http/TikaHttpClient.java | 161 +++++++++++++--------
.../org/apache/tika/http/TikaHttpClientTest.java | 78 +++++++++-
.../org/apache/tika/http/TikaTestHttpServer.java | 27 +++-
.../org/apache/tika/parser/gdal/GDALParser.java | 14 +-
.../tika/inference/AbstractEmbeddingFilter.java | 8 +-
.../tika/inference/ImageEmbeddingConfig.java | 10 +-
.../org/apache/tika/inference/InferenceConfig.java | 12 +-
.../tika/inference/OpenAIEmbeddingFilter.java | 2 +-
.../tika/inference/OpenAIImageEmbeddingParser.java | 14 +-
.../tika/inference/JinaEmbeddingFilterTest.java | 2 +-
.../tika/inference/OpenAIEmbeddingFilterTest.java | 2 +-
.../inference/OpenAIImageEmbeddingParserTest.java | 2 +-
.../tika/parser/ocr/tess4j/Tess4JConfig.java | 18 +--
.../tika/parser/ocr/tess4j/Tess4JParser.java | 97 ++++++++++++-
.../tika/parser/ocr/tess4j/Tess4JConfigTest.java | 2 +-
.../parser/ocr/tess4j/Tess4JOCRTimeoutTest.java | 123 ++++++++++++++++
.../tika/parser/ocr/tess4j/Tess4JParserTest.java | 6 +-
.../resources/config-examples/tess4j-full.json | 2 +-
.../apache/tika/parser/vlm/AbstractVLMParser.java | 12 +-
.../org/apache/tika/parser/vlm/VLMOCRConfig.java | 12 +-
.../tika/parser/vlm/ClaudeVLMParserTest.java | 2 +-
.../tika/parser/vlm/GeminiVLMParserTest.java | 2 +-
.../tika/parser/vlm/OpenAIVLMParserTest.java | 4 +-
.../resources/config-examples/claude-vlm-full.json | 2 +-
.../resources/config-examples/gemini-vlm-full.json | 2 +-
.../config-examples/openai-vlm-basic.json | 2 +-
.../resources/config-examples/openai-vlm-full.json | 2 +-
.../config-examples/migration-full-example.json | 2 +-
.../resources/config-examples/tesseract-basic.json | 2 +-
.../resources/config-examples/tesseract-full.json | 2 +-
.../apache/tika/parser/dwg/DWGParserConfig.java | 10 +-
.../org/apache/tika/parser/dwg/DWGReadParser.java | 4 +-
.../configs/tika-config-dwgRead-Timeout.json | 2 +-
.../tika/parser/microsoft/libpst/LibPstParser.java | 2 +-
.../microsoft/libpst/LibPstParserConfig.java | 10 +-
.../apache/tika/parser/ocr/TesseractOCRConfig.java | 16 +-
.../apache/tika/parser/ocr/TesseractOCRParser.java | 8 +-
.../tika/parser/ocr/TesseractOCRConfigTest.java | 6 +-
.../tika/parser/ocr/TesseractOCRParserTest.java | 2 +-
.../resources/configs/TIKA-3582-tesseract.json | 2 +-
.../configs/tika-config-tesseract-full.json | 2 +-
.../configs/tika-config-tesseract-partial.json | 2 +-
.../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 30 ++++
.../tika/renderer/pdf/poppler/PopplerRenderer.java | 12 +-
.../org/apache/tika/parser/pdf/PDFParserTest.java | 95 ++++++++++++
.../apache/tika/parser/strings/StringsConfig.java | 24 +--
.../apache/tika/parser/strings/StringsParser.java | 4 +-
.../tika/parser/strings/StringsConfigTest.java | 6 +-
.../configs/tika-config-strings-full.json | 2 +-
.../configs/tika-config-strings-partial.json | 2 +-
.../apache/tika/async/cli/AsyncProcessorTest.java | 76 +++++++++-
.../org/apache/tika/pipes/core/PipesClient.java | 51 +++++++
.../apache/tika/pipes/core/async/AsyncEmitter.java | 7 +
.../tika/pipes/core/async/AsyncProcessor.java | 10 +-
.../tika/pipes/core/server/ConnectionHandler.java | 21 ++-
.../apache/tika/pipes/core/server/EmitHandler.java | 28 +++-
.../apache/tika/pipes/core/server/PipesServer.java | 21 ++-
.../pipes/core/PartialTimeoutPassbackTest.java | 80 ++++++++++
.../apache/tika/pipes/core/PipesClientTest.java | 146 ++++++++++++++++++-
.../sample-configs/vision/vlm-openai.json | 2 +-
81 files changed, 1576 insertions(+), 313 deletions(-)
create mode 100644
tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/test/java/org/apache/tika/parser/ocr/tess4j/Tess4JOCRTimeoutTest.java
create mode 100644
tika-pipes/tika-pipes-integration-tests/src/test/java/org/apache/tika/pipes/core/PartialTimeoutPassbackTest.java