This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch TIKA-4848
in repository https://gitbox.apache.org/repos/asf/tika.git
from 8531dd6ca6 TIKA-4848: add exception-reporting parse-context config,
step 1
add ab22ec9c9a TIKA-4844: scope shared-server restart reports to the
process they de… (#3077)
add 3afde32dac TIKA-4837 - flag extra contents in ooxml files (#3063)
add 2d1e43ab32 TIKA-4843: fix per-request parse-context config for parsers
with lock… (#3076)
add c1dc3f29c4 TIKA-4835 spill sites (#3079)
add d016f8aaed TIKA-4839 - add micrometer to tika-server (#3064)
add 9cad39e1d5 TIKA-4838: Expose the MP4 audio and video track codecs as
FourCCs (audio:fourcc, video:fourcc) (#3062)
add 1ac322b1ea TIKA-4842 - update docs and skills (#3078)
add e2940fd226 TIKA-4845 - improve BAT estimation (#3080)
add ccec84eb03 TIKA-4831: Add content-based detection and a parser for
GeoGebra files (ggb, ggs, ggt) (#3044)
add ff2d687d69 TIKA-4839 - simplify signature (#3081)
add bb052f5e84 TIKA-4836: update aws, xmlbeans, pf4j
add de70a7d0eb Merge remote-tracking branch 'origin/main' into TIKA-4848
No new revisions were added by this update.
Summary of changes:
.github/pull_request_template.md | 3 +-
.skills/{dev => devs/development}/SKILL.md | 30 +-
.skills/devs/feature-workflow/SKILL.md | 79 ++++
.skills/{ => devs}/metadata-schema/SKILL.md | 3 +
.skills/{ => devs}/oss-fuzz/SKILL.md | 12 +-
.skills/devs/pr-review/SKILL.md | 297 ++++++++++++++
.skills/{ => devs}/tika-eval-compare/SKILL.md | 3 +
.../tika-eval-encoding-regression/SKILL.md | 3 +
.skills/{ => devs}/tika-eval-h2-query/SKILL.md | 3 +
.../{ => devs}/update-site-for-release/SKILL.md | 3 +
.../update-site-for-release/scripts/README.md | 0
.../scripts/extract-tika-contribs.py | 0
.../scripts/extract-tika-issues.py | 0
.../scripts/scaffold-stable-version.sh | 0
.skills/pr-review/SKILL.md | 211 ----------
.skills/{ => users}/file-forensics/SKILL.md | 97 ++++-
.skills/{ => users}/file-forensics/demo/README.md | 9 +-
.../{ => users}/file-forensics/demo/budget.xlsx | Bin
.../{ => users}/file-forensics/demo/contract.pdf | Bin
.../users/file-forensics/demo/invoice.pdf | 0
.skills/{ => users}/file-forensics/demo/memo.docx | Bin
.../users/file-forensics/demo/newsletter.html | 0
.../file-forensics/demo/quarterly-report.docm | Bin
.../file-forensics/file-forensics-config.json | 0
.../{ => users}/file-to-markdown-docker/SKILL.md | 3 +
.skills/{ => users}/file-to-markdown/SKILL.md | 3 +
AGENTS.md | 39 +-
CHANGES.txt | 122 ++++++
CONTRIBUTING.md | 13 +-
README.md | 4 +-
assembly.xml | 5 +
docs/modules/ROOT/nav.adoc | 1 +
docs/modules/ROOT/pages/advanced/spooling.adoc | 30 +-
.../ROOT/pages/developers/metadata-keys.adoc | 2 +-
docs/modules/ROOT/pages/pipes/performance.adoc | 58 ++-
.../ROOT/pages/pipes/shared-server-mode.adoc | 18 +-
docs/modules/ROOT/pages/pipes/troubleshooting.adoc | 14 +-
docs/modules/ROOT/pages/security.adoc | 5 +
.../ROOT/pages/using-tika/server/index.adoc | 16 +-
.../ROOT/pages/using-tika/server/monitoring.adoc | 207 ++++++++++
pom.xml | 7 +
.../main/java/org/apache/tika/metadata/Audio.java | 12 +
.../main/java/org/apache/tika/metadata/Office.java | 32 ++
.../main/java/org/apache/tika/metadata/Video.java | 12 +
.../org/apache/tika/mime/tika-mimetypes.xml | 14 +
.../java/org/apache/tika/TikaDetectionTest.java | 2 +
tika-metadata-schema/README.md | 2 +-
tika-metadata-schema/pom.xml | 2 +-
tika-metadata-schema/regen.sh | 6 +-
.../apache/tika/metadata/metadata-key-fields.json | 10 +
.../org/apache/tika/metadata/metadata-keys.json | 10 +
tika-parent/pom.xml | 22 +-
.../ImageEmbeddingRuntimeConfigMergeTest.java | 78 ++++
.../ocr/tess4j/Tess4JRuntimeConfigMergeTest.java | 76 ++++
.../tika/parser/vlm/VLMRuntimeConfigMergeTest.java | 107 +++++
.../tika/detect/TestContainerAwareDetector.java | 6 +
.../tika/parser/microsoft/rtf/RTFParserTest.java | 4 +-
.../test-documents/testGeoGebra_classic.ggb | Bin 0 -> 4761 bytes
.../test-documents/testGeoGebra_notes.ggs | Bin 0 -> 45929 bytes
.../apache/tika/parser/mp4/Mp4SampleEntries.java | 174 +++++++++
.../tika/parser/mp4/TikaMp4SoundHandler.java | 76 ++--
.../tika/parser/mp4/TikaMp4VideoHandler.java | 56 ++-
.../org/apache/tika/parser/mp4/MP4ParserTest.java | 47 ++-
.../tika/parser/mp4/Mp4SampleEntriesTest.java | 172 ++++++++
.../resources/test-documents/testMP4VideoAudio.mp4 | Bin 0 -> 11065 bytes
.../resources/test-documents/testMP4_drm_frma.m4a | Bin 0 -> 664 bytes
.../{testMP4Video.mp4 => testMP4_encv.mp4} | Bin 1810 -> 1890 bytes
.../test-documents/testMP4_twoSampleEntries.m4a | Bin 0 -> 550 bytes
.../tika/parser/image/AbstractImageParser.java | 6 +-
.../apache/tika/parser/image/ByteBufferReader.java | 74 ++++
.../tika/parser/image/ImageMetadataExtractor.java | 80 +++-
.../org/apache/tika/parser/image/ImageXmp.java | 55 ++-
.../org/apache/tika/parser/image/JpegParser.java | 8 +-
.../org/apache/tika/parser/image/TiffParser.java | 6 +-
.../org/apache/tika/parser/image/WebPParser.java | 7 +-
.../parser/image/ImageParsersNoTempFileTest.java | 143 +++++++
.../detect/microsoft/POIFSContainerDetector.java | 169 +++++++-
.../microsoft/ooxml/OOXMLExtractorFactory.java | 68 ++++
.../tika/parser/microsoft/ooxml/OOXMLParser.java | 98 +++--
.../POIFSContainerDetectorNoTempFileTest.java | 116 ++++++
.../detect/microsoft/POIFSDeclaredSizeTest.java | 265 +++++++++++++
.../microsoft/ooxml/MacroPartResolutionTest.java | 145 +++++++
.../microsoft/ooxml/ZipStructureCoverageTest.java | 181 +++++++++
.../tika-parser-miscoffice-module/pom.xml | 5 +
.../tika/parser/geogebra/GeoGebraParser.java | 433 +++++++++++++++++++++
.../tika/parser/geogebra/GeoGebraXMLHandler.java | 178 +++++++++
.../apache/tika/parser/odf/OpenDocumentParser.java | 6 +-
.../tika/parser/geogebra/GeoGebraParserTest.java | 409 +++++++++++++++++++
.../odf/OpenDocumentParserNoTempFileTest.java | 104 +++++
.../test/resources/test-documents/testGeoGebra.ggb | Bin 0 -> 2010 bytes
.../test-documents/testGeoGebraSlides.ggs | Bin 0 -> 2466 bytes
.../resources/test-documents/testGeoGebraTool.ggt | Bin 0 -> 517 bytes
.../test-documents/testGeoGebra_classic.ggb | Bin 0 -> 4761 bytes
.../test-documents/testGeoGebra_notes.ggs | Bin 0 -> 45929 bytes
.../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 2 +-
.../java/org/apache/tika/parser/pdf/PDFParser.java | 43 +-
.../apache/tika/parser/pdf/PDFRandomAccess.java | 79 ++++
.../tika/renderer/pdf/pdfbox/PDFBoxRenderer.java | 19 +-
.../tika/parser/pdf/PDFParserNoTempFileTest.java | 71 ++++
.../org/apache/tika/parser/pdf/PDFParserTest.java | 10 +
.../tika/parser/pdf/PDFPerPageRenderTest.java | 95 +++++
.../java/org/apache/tika/parser/pkg/ZipParser.java | 2 +
.../apache/tika/detect/zip/GeoGebraDetector.java | 126 ++++++
...org.apache.tika.detect.zip.ZipContainerDetector | 4 +-
.../tika/detect/zip/GeoGebraDetectionTest.java | 69 ++++
.../test/resources/test-documents/testGeoGebra.ggb | Bin 0 -> 2010 bytes
.../test-documents/testGeoGebraSlides.ggs | Bin 0 -> 2466 bytes
.../resources/test-documents/testGeoGebraTool.ggt | Bin 0 -> 517 bytes
.../tika/pipes/core/PerClientServerManager.java | 83 +++-
.../org/apache/tika/pipes/core/PipesClient.java | 38 +-
.../org/apache/tika/pipes/core/PipesParser.java | 23 ++
.../org/apache/tika/pipes/core/RestartCounter.java | 105 +++++
.../core/{EmitStrategy.java => RestartReason.java} | 25 +-
.../org/apache/tika/pipes/core/ServerManager.java | 37 +-
.../tika/pipes/core/SharedServerManager.java | 98 ++++-
.../tika/pipes/core/async/AsyncProcessor.java | 11 +
.../apache/tika/pipes/core/server/PipesServer.java | 6 +-
.../pipes/core/PipesClientClosedManagerTest.java | 64 +++
.../tika/pipes/core/PipesClientInterruptTest.java | 6 +
.../pipes/core/PipesClientPayloadLimitTest.java | 4 +
.../apache/tika/pipes/core/RestartCounterTest.java | 125 ++++++
.../tika/pipes/core/SentinelServerManager.java | 23 +-
.../pipes/core/SharedServerManagerClosedTest.java | 34 +-
.../apache/tika/pipes/core/PipesClientTest.java | 20 +
.../tika/pipes/core/SharedServerModeTest.java | 124 ++++++
.../apache/tika/config/loader/JsonMergeUtils.java | 39 +-
.../tika/config/loader/JsonMergeUtilsTest.java | 155 ++++++++
tika-server/tika-server-core/pom.xml | 12 +
.../org/apache/tika/server/core/ServerStatus.java | 5 +
.../org/apache/tika/server/core/TikaServerCli.java | 3 +
.../apache/tika/server/core/TikaServerConfig.java | 29 ++
.../apache/tika/server/core/TikaServerProcess.java | 69 +++-
.../tika/server/core/metrics/MetricsServer.java | 113 ++++++
.../server/core/metrics/TikaMetricsFilter.java | 95 +++++
.../server/core/metrics/TikaServerMetrics.java | 204 ++++++++++
.../tika/server/core/resource/AsyncResource.java | 4 +
.../tika/server/core/TikaServerConfigTest.java | 56 +++
.../core/TikaServerMetricsIntegrationTest.java | 247 ++++++++++++
.../server/core/metrics/MetricsServerTest.java | 96 +++++
.../server/core/metrics/RejectedReasonTest.java | 65 ++++
.../server/core/metrics/TikaMetricsFilterTest.java | 269 +++++++++++++
....json => tika-config-server-async-metrics.json} | 4 +-
.../tika-config-server-metrics-restarts.json | 18 +
...json => tika-config-server-metrics-shared.json} | 11 +-
...son => tika-config-server-metrics-timeout.json} | 9 +-
...-flags.json => tika-config-server-metrics.json} | 9 +-
.../src/main/appended-resources/META-INF/LICENSE | 84 ++++
147 files changed, 7144 insertions(+), 574 deletions(-)
rename .skills/{dev => devs/development}/SKILL.md (87%)
create mode 100644 .skills/devs/feature-workflow/SKILL.md
rename .skills/{ => devs}/metadata-schema/SKILL.md (97%)
rename .skills/{ => devs}/oss-fuzz/SKILL.md (96%)
create mode 100644 .skills/devs/pr-review/SKILL.md
rename .skills/{ => devs}/tika-eval-compare/SKILL.md (98%)
rename .skills/{ => devs}/tika-eval-encoding-regression/SKILL.md (98%)
rename .skills/{ => devs}/tika-eval-h2-query/SKILL.md (98%)
rename .skills/{ => devs}/update-site-for-release/SKILL.md (99%)
rename .skills/{ => devs}/update-site-for-release/scripts/README.md (100%)
rename .skills/{ =>
devs}/update-site-for-release/scripts/extract-tika-contribs.py (100%)
rename .skills/{ =>
devs}/update-site-for-release/scripts/extract-tika-issues.py (100%)
rename .skills/{ =>
devs}/update-site-for-release/scripts/scaffold-stable-version.sh (100%)
delete mode 100644 .skills/pr-review/SKILL.md
rename .skills/{ => users}/file-forensics/SKILL.md (81%)
rename .skills/{ => users}/file-forensics/demo/README.md (71%)
rename .skills/{ => users}/file-forensics/demo/budget.xlsx (100%)
rename .skills/{ => users}/file-forensics/demo/contract.pdf (100%)
copy
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/resources/test-documents/testPDF_jsActionOnPage.pdf
=> .skills/users/file-forensics/demo/invoice.pdf (100%)
rename .skills/{ => users}/file-forensics/demo/memo.docx (100%)
copy
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/test/resources/test-documents/testHTML_script_in_body.html
=> .skills/users/file-forensics/demo/newsletter.html (100%)
rename .skills/{ => users}/file-forensics/demo/quarterly-report.docm (100%)
rename .skills/{ => users}/file-forensics/file-forensics-config.json (100%)
rename .skills/{ => users}/file-to-markdown-docker/SKILL.md (98%)
rename .skills/{ => users}/file-to-markdown/SKILL.md (99%)
create mode 100644 docs/modules/ROOT/pages/using-tika/server/monitoring.adoc
create mode 100644
tika-parsers/tika-parsers-ml/tika-inference/src/test/java/org/apache/tika/inference/ImageEmbeddingRuntimeConfigMergeTest.java
create mode 100644
tika-parsers/tika-parsers-ml/tika-parser-tess4j-module/src/test/java/org/apache/tika/parser/ocr/tess4j/Tess4JRuntimeConfigMergeTest.java
create mode 100644
tika-parsers/tika-parsers-ml/tika-vlm/src/test/java/org/apache/tika/parser/vlm/VLMRuntimeConfigMergeTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/resources/test-documents/testGeoGebra_classic.ggb
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-integration-tests/src/test/resources/test-documents/testGeoGebra_notes.ggs
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/mp4/Mp4SampleEntries.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/java/org/apache/tika/parser/mp4/Mp4SampleEntriesTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/resources/test-documents/testMP4VideoAudio.mp4
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/resources/test-documents/testMP4_drm_frma.m4a
copy
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/resources/test-documents/{testMP4Video.mp4
=> testMP4_encv.mp4} (64%)
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/resources/test-documents/testMP4_twoSampleEntries.m4a
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/main/java/org/apache/tika/parser/image/ByteBufferReader.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-image-module/src/test/java/org/apache/tika/parser/image/ImageParsersNoTempFileTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/detect/microsoft/POIFSContainerDetectorNoTempFileTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/detect/microsoft/POIFSDeclaredSizeTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/MacroPartResolutionTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/java/org/apache/tika/parser/microsoft/ooxml/ZipStructureCoverageTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/geogebra/GeoGebraParser.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/main/java/org/apache/tika/parser/geogebra/GeoGebraXMLHandler.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/java/org/apache/tika/parser/geogebra/GeoGebraParserTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/java/org/apache/tika/parser/odf/OpenDocumentParserNoTempFileTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/resources/test-documents/testGeoGebra.ggb
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/resources/test-documents/testGeoGebraSlides.ggs
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/resources/test-documents/testGeoGebraTool.ggt
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/resources/test-documents/testGeoGebra_classic.ggb
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/resources/test-documents/testGeoGebra_notes.ggs
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/main/java/org/apache/tika/parser/pdf/PDFRandomAccess.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFParserNoTempFileTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/java/org/apache/tika/parser/pdf/PDFPerPageRenderTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-zip-commons/src/main/java/org/apache/tika/detect/zip/GeoGebraDetector.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-zip-commons/src/test/java/org/apache/tika/detect/zip/GeoGebraDetectionTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-zip-commons/src/test/resources/test-documents/testGeoGebra.ggb
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-zip-commons/src/test/resources/test-documents/testGeoGebraSlides.ggs
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-zip-commons/src/test/resources/test-documents/testGeoGebraTool.ggt
create mode 100644
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/RestartCounter.java
copy
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/{EmitStrategy.java
=> RestartReason.java} (61%)
create mode 100644
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core/PipesClientClosedManagerTest.java
create mode 100644
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core/RestartCounterTest.java
copy tika-core/src/test/java/org/apache/tika/config/TimeoutLimitsTest.java =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core/SharedServerManagerClosedTest.java
(50%)
create mode 100644
tika-serialization/src/test/java/org/apache/tika/config/loader/JsonMergeUtilsTest.java
create mode 100644
tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/metrics/MetricsServer.java
create mode 100644
tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/metrics/TikaMetricsFilter.java
create mode 100644
tika-server/tika-server-core/src/main/java/org/apache/tika/server/core/metrics/TikaServerMetrics.java
create mode 100644
tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/TikaServerMetricsIntegrationTest.java
create mode 100644
tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/metrics/MetricsServerTest.java
create mode 100644
tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/metrics/RejectedReasonTest.java
create mode 100644
tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/metrics/TikaMetricsFilterTest.java
copy
tika-server/tika-server-core/src/test/resources/configs/{tika-config-server-basic.json
=> tika-config-server-async-metrics.json} (92%)
create mode 100644
tika-server/tika-server-core/src/test/resources/configs/tika-config-server-metrics-restarts.json
copy
tika-server/tika-server-core/src/test/resources/configs/{tika-config-server-basic.json
=> tika-config-server-metrics-shared.json} (54%)
copy
tika-server/tika-server-core/src/test/resources/configs/{tika-config-server-basic.json
=> tika-config-server-metrics-timeout.json} (63%)
copy
tika-server/tika-server-core/src/test/resources/configs/{tika-config-server-status-no-flags.json
=> tika-config-server-metrics.json} (56%)