This is an automated email from the ASF dual-hosted git repository.
tallison pushed a change to branch TIKA-1997
in repository https://gitbox.apache.org/repos/asf/tika.git
from e98079ef9 TIKA-1997 -- initial poc, derived from rob975's work on:
https://github.com/apache/tika/pull/267
add 734c4f10f TIKA-4327: update mirosoft-graph
add b5c779333 TIKA-4327: update google cloud, junit
add 2797ded0c TIKA-4327: update log4j
add 1e35bd108 TIKA-4327: update jackrabbit
add 0190cf7e0 [TIKA-4457] Updating Automatic-Module tag for cad module.
(#2280)
add 8035d71e6 TIKA-4327: update maven-enforcer-plugin, aws, cxf, jwarc,
netty, reactor
add dd1cc5720 TIKA-4327: update commons-io, aws, jackson
add e4c77ec07 TIKA-4327: update microsoft-graph
add 0a5e3e560 Bump org.xerial.snappy:snappy-java from 1.1.10.7 to 1.1.10.8
(#2285)
add 950acba6c Bump org.apache.maven:maven-model from 3.9.10 to 3.9.11
(#2284)
add 15ce4c987 Bump org.xerial:sqlite-jdbc from 3.50.2.0 to 3.50.3.0 (#2283)
add 7d501f447 Bump com.nimbusds:nimbus-jose-jwt from 10.3.1 to 10.4 (#2282)
add 3c6cee9e2 TIKA-4327: update aws
add 49e96cfb5 TIKA-4327: update aws, commons-codec, opennlp
add 557eda5f4 TIKA-4327: update microsoft-graph
add 81094f7db TIKA-4327: update aws
add c906c0578 TIKA-4327: update aws
add ac72529b3 TIKA-4327: update error_prone_annotations
add d14c294b0 TIKA-4327: update mime4j, solrj
add 901150ca8 TIKA-4327: update aws
add cfd5a7993 Bump junit5.version from 5.13.3 to 5.13.4 (#2290)
add d64833892 Bump curator.version from 5.8.0 to 5.9.0 (#2286)
add 25a56dd64 Bump org.apache.commons:commons-text from 1.13.1 to 1.14.0
(#2287)
add 72ffb771c Bump com.azure:azure-identity from 1.16.2 to 1.16.3 (#2288)
add b568cd3f8 Bump org.opensearch:opensearch-testcontainers from 2.1.3 to
2.1.4 (#2289)
add 5c9677e3e TIKA-4327: replace deprecated
add 382e7d908 TIKA-4327: replace deprecated
add e5154cb2d TIKA-4459 -- force stream to zip file to handle encrypted
od* documents correctly (#2291)
add 2d1a42121 TIKA-4327: update aws
add 2a94b97a2 TIKA-4327: adjust exception, remove unneeded code
add 1537fc995 TIKA-4327: update commons compress, commons csv, google cloud
add 9625737df TIKA-4327: remove null check that isn't needed
add c3066e18a TIKA-4327: update microsoft graph, grpc
add cbe3c9b67 Add secure processing to transformer handlers throughout the
codebase to avoid static analysis reports. (#2292)
add 9f0a514d1 TIKA-4327: update lucene
add 82da57eae TIKA-4327: update commons-net, aws
add 6e8d2ce85 TIKA-4327: remove json-smart exclusion, no longer needed
add c71ed90e0 TIKA-4327: replace deprecated
add 1cf02a9f3 Bump commons-cli:commons-cli from 1.9.0 to 1.10.0 (#2293)
add 6e224a1fd Simplify path naming
add bfee6d556 Improve configuration of xmlinputfactory (#2294)
add c32695684 TIKA-4327: update microsoft-graph, aws, nimbus
add fd2016ffe further improvements
add 924dcb204 Bump com.azure:azure-identity from 1.16.3 to 1.17.0 (#2298)
add 4bcb771f4 Bump com.azure:azure-core from 1.55.5 to 1.56.0 (#2297)
add fb8dddabb Bump org.glassfish.jersey.core:jersey-common from 3.1.10 to
3.1.11 (#2301)
add b4d39304b Bump com.google.cloud:google-cloud-storage from 2.54.0 to
2.55.0 (#2300)
add 846cd83f0 Bump microsoft-kiota.version from 1.8.8 to 1.8.9 (#2299)
add 02be12c62 Bump com.azure:azure-core-http-netty from 1.15.13 to 1.16.0
(#2296)
add 54ea129b8 Bump org.jline:jline from 3.30.4 to 3.30.5 (#2302)
add 6208165f2 Bump software.amazon.awssdk:bom from 2.32.16 to 2.32.19
(#2295)
add b1572a4e4 Bump com.puppycrawl.tools:checkstyle from 10.26.1 to 11.0.0
(#2303)
add aa8c5bef4 TIKA-4327: update aws
add 7aa063685 TIKA-4327: update microsoft-graph
add 1675fe228 TIKA-4327: update microsoft-graph, aws, reactor-netty,
reactor-core
add ec33cac33 TIKA-4327: update aws, nimbus, netty, jackrabbit
add 9b45f1673 TIKA-4327: update aws, spring
add aeafe5397 TIKA-4327: replace deprecated
add a712cac4a TIKA-4327: update j2objc-annotations
add 2989c8c12 TIKA-4327: update aws, jetty
add 993d37be9 TIKA-4327: update cxf
add b01244135 TIKA-4327: replace deprecated
add 275f9d9bc TIKA-4327: replace deprecated
add f4d9242a6 TIKA-4327: update mockito, byte-buddy
add 88a94ef2d Bump org.jetbrains.kotlin:kotlin-stdlib from 2.2.0 to 2.2.10
(#2306)
add 7f4796e5e Bump org.apache.maven.plugins:maven-javadoc-plugin from
3.11.2 to 3.11.3 (#2307)
add b466c4920 TIKA-4465 -- extract javascript from name tree (#2305)
add a6effe236 TIKA-4327: update aws
add 93d35c321 TIKA-4327: update aws
add 7827e7cc7 improve documentation for DefaultZipContainerDetector
add dc69e39e3 TIKA-4466 -- allow multiple values for many DublinCore
values (#2308)
add b1acb75eb TIKA-4472 -- extract macros by default in tika-app when
parsing a single file (#2309)
add 7bbc41dad TIKA-4472 -- extract macros by default in tika-app when
parsing a single file and in the gui! (#2310)
add 6b0c6a97c TIKA-4473: remove test-jar goal that isn't needed
add 67672e14a TIKA-4473: remove test-jar goal that isn't needed
add 9aedc0c1f TIKA-4473: remove test-jar goal that isn't needed
add d1c5caca3 TIKA-4473: remove test-jar goal that isn't needed
add b9366b2aa TIKA-4327: update aws
add a201805b9 TIKA-4327: update grpc, microsoft-graph, kotlin
add 46e4b46f0 Bump org.jsoup:jsoup from 1.21.1 to 1.21.2 (#2312)
add 4bfd4604f Bump io.dropwizard.metrics:metrics-core from 4.2.33 to
4.2.34 (#2311)
add f2b24a5ad TIKA-4475: avoid NPE
add abc9c28e7 TIKA-4327:update aws, google cloud
add e30e3c2ac TIKA-4327: update jackson, zookeeper
add 0a189af4b Return correct result code from start script (#2314)
add 155245130 Fix shell variable name TIKA_TIKA_FORKED_OPTS =>
TIKA_FORKED_OPTS (#2313)
add 1ff7790e0 TIKA-4327: update aws
add 943cacc21 Auto-link commits to TIKA Jira issues (#2279)
add 8b3247145 TIKA-4327: update jetbrains annotations, kotlin
add 3f411db0b TIKA-4327: update jetbrains annotations, kotlin, kafka,
puppycrawl
add 8b643d3ee TIKA-4327: update jetbrains annotations, kotlin, kafka,
puppycrawl
add 42cd94417 TIKA-4327: update aws
add 5780f9fcc TIKA-4327: update aws
add 0cc6a2448 TIKA-4327: update aws, nimbus, netty
add b0ae13834 TIKA-4327: update aws
add 2b1f0b17f TIKA-4327: update versions plugin
add b17f09334 Bump io.dropwizard.metrics:metrics-core from 4.2.34 to
4.2.36 (#2317)
add b70bb3408 Bump hadoop.version from 3.4.1 to 3.4.2 (#2316)
add 60abc9556 TIKA-4471 -- add unit tests to confirm defense against xxe
in sax, dom and stax. (#2318)
add 3e10cbe81 TIKA-4453 -- slight mods (#2278)
add 2c7caa751 TIKA-4471 -- add unit tests to confirm defense against xxe
in sax, dom and stax -- add flexibility for DOM
add 9db2fb877 TIKA-4471 -- fix i18n for new unit tests (#2319)
add a7954354f bump netty
add 16de8cc0e TIKA-4482 -- don't fail if woodstox is on the classpath
(#2320)
add ff1b8e83c [TIKA-4476] Force audio/mp4 where mp4 container is
exclusively sound (#2315)
add c2b7df2f6 TIKA-4476 -- checkstyle
add 2b3dd510f TIKA-1180: Add MatroskaDetector for improved MKV/WEBM
detection (#2251)
add 758283898 TIKA-1180 -- fixes for pr #2251
add 0fc944218 update CHANGES.txt
add fea48c397 TIKA-4327: update reactor-netty
add 4d5ff157a TIKA-4482 -- add integration test in tika-server for xfa.
add 753870d2e Bump org.jetbrains.kotlin:kotlin-stdlib from 2.2.20-RC2 to
2.2.20 (#2321)
add 78aaf08c3 Bump com.azure:azure-core-http-netty from 1.16.0 to 1.16.1
(#2322)
add 56e7b48b8 Bump jakarta.activation:jakarta.activation-api from 2.1.3 to
2.1.4 (#2323)
add 1fe0d9e9b Bump org.apache.maven.plugins:maven-shade-plugin from 3.6.0
to 3.6.1 (#2324)
add 16efb5928 Bump com.google.cloud:google-cloud-storage from 2.56.0 to
2.57.0 (#2325)
add 0f09971c9 Bump io.projectreactor:reactor-core from 3.8.0-M6 to
3.8.0-M7 (#2327)
add 945e3facf Bump org.apache.maven.plugins:maven-surefire-plugin from
3.5.3 to 3.5.4 (#2328)
add 005758ce4 Bump software.amazon.awssdk:bom from 2.33.4 to 2.33.9 (#2329)
add d6359e1d4 Bump com.microsoft.graph:microsoft-graph from 6.51.0 to
6.52.0 (#2334)
add 8e466cf4b Bump org.jline:jline from 3.30.5 to 3.30.6 (#2333)
add 78e25f04d Bump com.google.code.gson:gson from 2.13.1 to 2.13.2 (#2331)
add a2634f45b Bump com.azure:azure-core from 1.56.0 to 1.56.1 (#2330)
add 5fcb7f76a Bump org.apache.maven.plugins:maven-failsafe-plugin from
3.5.3 to 3.5.4 (#2332)
add c0077dcfb Bump microsoft-kiota.version from 1.8.9 to 1.8.10 (#2326)
add 89e8b5832 TIKA-4327: update activati0on, xml bind
add f11a42c76 TIKA-4485: fix relative files + test
add 4f0de0e4b TIKA-4327: update aws
add f6964a7c3 TIKA-4327: update microsoft-graph, guava, bc
add 2dc50bfbe TIKA-4327: update azure-identity
add 3c84f9d91 TIKA-4327: update spring
add 6bd736e34 TIKA-4327: update aws
add 69b25471b TIKA-4327: update aws, mockito, error_prone_annotations
add 2bd4d12f3 Bump org.apache.maven.plugins:maven-compiler-plugin (#2337)
add 8ab134783 Bump org.apache.maven.plugins:maven-javadoc-plugin from
3.11.3 to 3.12.0 (#2336)
add 893612c8b Bump io.dropwizard.metrics:metrics-core from 4.2.36 to
4.2.37 (#2335)
add 4ee4dafcd TIKA-4327: update versions plugin
add 0e1495c13 TIKA-4327:update aws, jna, log4j
add e11996618 TIKA-4327:update jackrabbit
add 5780f9ff0 TIKA-4327: update aws, google cloud, jaxb; introduce
angus-activation because of convergence problem
add e4ed706f9 TIKA-4392: core osgi requirements now list xerces as
optional (#2338)
add cfe32a292 TIKA-4327: update aws, commons lang3, h2
add c52830cb2 TIKA-4327: update aws, scm
add eac373286 TIKA-4327: update aws
add 5fde7d5b4 Bump com.puppycrawl.tools:checkstyle from 11.0.1 to 11.1.0
(#2340)
add 5431d91f1 TIKA-4327: update aws
add 5aeca6202 TIKA-4496 - bump workflow from jdk23 to jdk25 (#2341)
add 4b96303cd Merge branch 'main' of
https://gitbox.apache.org/repos/asf/tika
add 39159c46e TIKA-4334 - move tika-pipes out of core (#2339)
add 0018039c6 TIKA-4327: update aws, jna
add 807279b6d TIKA-4334b (#2342)
add 507c9933c TIKA-4497 -- allow per file timeouts in tika-pipes (#2343)
add 223dba0a4 TIKA-4327: update aws
add 669a594cd TIKA-4327: update scala
add 245c62dd9 TIKA-4327: update exec-maven-plugin, uimaj
add 8ba4e8ad5 TIKA-4332 -- remove dotnet module
add 3c0dab1f0 add errorprone back in (#2224)
add 8a0bbe87c TIKA-4490 (#2349) -- fixes for problems found via ossfuzz
integration
add 5b2b17de9 TIKA-4490 (#2350)
add a95b53458 TIKA-4327: update aws
add db58497d7 TIKA-4327: update zstd, enforcer plugin
add d7eb05ccf TIKA-4495 -- skip ossindex
add 485b8ee02 TIKA-4448 -- bump junit to 6.0.0 (#2352)
add dbc6cb41f TIKA-4502 -- remove snaps deployment (#2344)
add 20e782969 TIKA-4343 -- remove agepredictor (#2346)
add 5f2e30215 TIKA-4499 - remove tika-dl module (#2347)
add 2d8851888 TIKA-4500 -- remove advanced media module (#2348)
add baee4e384 TIKA-4503 -- refactor serialization (#2351)
add a3ffce540 TIKA-4503 -- checkstyle
add 2b38ed18f TIKA-4327: update aws
add a1f3a9413 TIKA-4504: add pdf file
add 9cdb66fd2 TIKA-4498 -- add a PassbackFilter to enable passing back
some of the … (#2353)
add b314111e2 TIKA-4504: add apache header
add 136e7a8be TIKA-4504: add exclusions
add 6048f0eba TIKA-4504: add / remove exclusions
add 0560f0954 TIKA-4504: add exclusions
add c9e41e30c TIKA-4504: restore version
add f36b283da TIKA-4504: add exclusions
add d544f0e6a TIKA-4504: add exclusions
add a36cc7f89 TIKA-4504: add exclusions
add 3d39b9ba8 Bump org.ow2.asm:asm from 9.8 to 9.9 (#2356)
add 9b5014028 Bump org.codehaus.mojo:exec-maven-plugin from 3.6.0 to 3.6.1
(#2355)
add 212463255 Bump de.thetaphi:forbiddenapis from 3.9 to 3.10 (#2354)
add 294f19e3f TIKA-4505: fix javadoc
add 24318bda3 TIKA-4504: add exclusions
add 6a713db68 TIKA-4504: add exclusions
add 2e341fe0f TIKA-4504: add exclusions
add ad25279f0 TIKA-4504: remove double line
add 79d017047 TIKA-4508 -- allow tika async to inherit from existing
tika-config.xml
add e5036c357 TIKA-4507 -- improve tika-eval-app's commandline in 4.x
(#2357)
add cd7e8f5fc TIKA-4508 -- fix unit test (#2359)
add 475f791a2 TIKA-4504: add exclusions
add 7b5d76989 TIKA-4506 -- remove tika-fuzzing module (#2358)
add 79ffae122 TIKA-4504: add exclusions
add bd4931430 TIKA-4504: add header
add 91761a078 TIKA-4327: update sis, microsoft-graph, google cloud, azure
add 255700e47 TIKA-4327: update kotlin, grpc
add b385819af TIKA-4510: Fix nondeterministic failures in
LanguageResourceTest (#2360)
add 616c35fdb TIKA-4511 -- detected compressed bmp (#2361)
add 7b4709f24 TIKA-4327: update aws, puppycrawl
add 2aadf30e3 TIKA-4327: update puppycrawl
add b08023e41 TIKA-4327: update jacoco
add fde81e87e TIKA-4327: update opennlp
add cb1b9fef1 TIKA-4515 -- add fully recursive extraction (#2363)
add 2af3ae0f3 TIKA-4514 (#2364)
add a0b088749 TIKA-4517 -- improve async cli (#2365)
add a9854028b TIKA-4327: update aws, netty
add f370d845f TIKA-4327: revert netty update
add b8b869e89 TIKA-4327: update azure-identity, reactor
add 8b0dd1fa1 TIKA-4517 -- fix windows
add 17826b53e TIKA-4518 (#2366)
add e4da37eba TIKA-4518 -- escape quotes in filenames for better cross
platform robustness
add 0983c54e3 TIKA-4327: update aws, netty
add cc45d250b TIKA-4327: update junrar
add 307248b48 TIKA-4327: update junrar
add 64c7d9020 TIKA-4327: update aws
add 0bc03abab TIKA-4524: migrate to aws v2
add 7a614f669 TIKA-4524: try using requestChecksumCalculation instead of
checksum
add f0f109cb2 TIKA-4327: update websockets
add b4314bdf6 TIKA-4327: update aws
add 6e3bdd9ba TIKA-4524: remove commented code
add 5af2992bd TIKA-4327: update rat; prepare for testcontainers 2
add 8d4b6e824 TIKA-4504: add exclusions
add d217fa897 TIKA-4504: add exclusions
add 7c5260f3f TIKA-4488: avoid shaded testcontainers classes that are gone
in v2
add a76b0f591 TIKA-4504: add exclusions
add bf023d288 TIKA-4327: update testcontainers to v2
add a78ad6048 TIKA-4327: update spring
add 879d1a34d TIKA-4488: avoid shaded testcontainers classes
add 6800faa44 TIKA-4525: migrate to aws v2
add d21a66fb7 TIKA-4525: migrate to aws v2
add db392986f TIKA-4525: migrate to aws v2
add efb956ad8 Bump pdfbox.version from 3.0.5 to 3.0.6 (#2372)
add 764d1af5e Bump org.codehaus.mojo:exec-maven-plugin from 3.6.1 to 3.6.2
(#2371)
add 1dfd9cbb2 Bump com.puppycrawl.tools:checkstyle from 12.0.1 to 12.1.0
(#2369)
add 5d6ede477 TIKA-4525: minor cosmetic fixes
add 7f10ce33c TIKA-4525: migrate to aws v2
add 3c0c67cdd TIKA-4525: migrate to aws v2
add af0990ae3 TIKA-4525: restore exception handling (should have read the
comment!)
add 7223eebaf TIKA-4525: migrate to aws v2
add 2ddcb0e5b TIKA-4525: remove aws v1
add 30fd3cd93 TIKA-4525: restore aws v1
add f24204d28 TIKA-4526: Fix nondeterministic failures in
TranslateResourceTest by splitting @PUT/@POST handlers (#2368)
add 9d30530d3 TIKA-4525: restore aws v1
add 8ba427a4c clarify warning in PipesClient
add 6caad04dc Merge branch 'main' into TIKA-1997
No new revisions were added by this update.
Summary of changes:
.asf.yaml | 2 +
.../{main-jdk23-build.yml => main-jdk25-build.yml} | 4 +-
.gitignore | 12 +-
CHANGES.txt | 40 +-
assembly.xml | 1 -
pom.xml | 4 +-
tika-app/pom.xml | 92 --
.../main/java/org/apache/tika/cli/AsyncHelper.java | 38 +-
.../src/main/java/org/apache/tika/cli/TikaCLI.java | 208 ++-
.../src/main/java/org/apache/tika/gui/TikaGUI.java | 15 +-
.../resources/tika-config-default-single-file.xml | 49 +
.../java/org/apache/tika/cli/AsyncHelperTest.java | 13 +-
.../java/org/apache/tika/cli/TikaCLIAsyncTest.java | 7 +-
.../test/java/org/apache/tika/cli/TikaCLITest.java | 131 +-
.../test/resources/test-data}/testPDFPackage.pdf | Bin
.../test/resources/test-data}/testPPT_macros.ppt | Bin
.../src/test/resources/test-data}/testPST.pst | Bin
tika-bom/pom.xml | 12 +-
tika-bundles/pom.xml | 14 +
tika-core/pom.xml | 8 +-
.../java/org/apache/tika/config/TikaConfig.java | 2 +-
.../org/apache/tika/config/TikaTaskTimeout.java | 7 +-
.../extractor/DefaultEmbeddedStreamTranslator.java | 21 +-
.../tika/extractor/EmbeddedStreamTranslator.java | 8 +-
.../apache/tika/extractor/RUnpackExtractor.java | 42 +-
.../java/org/apache/tika/io/FilenameUtils.java | 233 ++-
.../java/org/apache/tika/metadata/DublinCore.java | 20 +-
.../main/java/org/apache/tika/metadata/PDF.java | 6 +
.../main/java/org/apache/tika/mime/MimeTypes.java | 33 +-
.../sax/AbstractRecursiveParserWrapperHandler.java | 11 +-
.../java/org/apache/tika/utils/ProcessUtils.java | 4 +-
.../java/org/apache/tika/utils/XMLReaderUtils.java | 69 +-
.../org/apache/tika/mime/tika-mimetypes.xml | 44 +-
.../org/apache/tika/config/TikaConfigTest.java | 21 +
.../java/org/apache/tika/io/FilenameUtilsTest.java | 130 ++
.../org/apache/tika/utils/XMLReaderUtilsTest.java | 237 +++-
tika-deployment/tika-snap-app/snapcraft.yaml | 45 -
tika-deployment/tika-snap-server/snapcraft.yaml | 39 -
tika-detectors/tika-detector-magika/pom.xml | 9 +
tika-detectors/tika-detector-siegfried/pom.xml | 9 +
tika-dotnet/pom.xml | 185 ---
tika-dotnet/src/main/java/Tika/Tika.java | 77 -
tika-eval/pom.xml | 9 +
tika-eval/tika-eval-app/pom.xml | 9 +-
.../java/org/apache/tika/eval/app/EvalConfig.java | 8 +
.../org/apache/tika/eval/app/ExtractComparer.java | 17 +-
.../tika/eval/app/ExtractComparerRunner.java | 40 +-
.../apache/tika/eval/app/ExtractProfileRunner.java | 38 +-
.../org/apache/tika/eval/app/ExtractProfiler.java | 2 +-
.../org/apache/tika/eval/app/ProfilerBase.java | 2 +-
.../org/apache/tika/eval/app/StatusReporter.java | 2 +-
.../tika/eval/app/reports/ResultsReporter.java | 11 +-
tika-eval/tika-eval-core/pom.xml | 5 -
tika-example/pom.xml | 5 -
tika-fuzzing/pom.xml | 136 --
.../apache/tika/fuzzing/AutoDetectTransformer.java | 96 --
.../java/org/apache/tika/fuzzing/Transformer.java | 40 -
.../java/org/apache/tika/fuzzing/cli/FuzzOne.java | 244 ----
.../org/apache/tika/fuzzing/cli/FuzzingCLI.java | 282 ----
.../apache/tika/fuzzing/cli/FuzzingCLIConfig.java | 108 --
.../tika/fuzzing/exceptions/CantFuzzException.java | 25 -
.../apache/tika/fuzzing/general/ByteDeleter.java | 51 -
.../apache/tika/fuzzing/general/ByteFlipper.java | 67 -
.../apache/tika/fuzzing/general/ByteInjector.java | 76 -
.../tika/fuzzing/general/GeneralTransformer.java | 95 --
.../apache/tika/fuzzing/general/SpanSwapper.java | 82 --
.../org/apache/tika/fuzzing/general/Truncator.java | 61 -
.../org/apache/tika/fuzzing/pdf/EvilCOSWriter.java | 1486 --------------------
.../apache/tika/fuzzing/pdf/PDFTransformer.java | 62 -
.../tika/fuzzing/pdf/PDFTransformerConfig.java | 192 ---
.../services/org.apache.tika.fuzzing.Transformer | 17 -
tika-fuzzing/src/main/resources/log4j2.xml | 38 -
tika-fuzzing/src/test/java/TestFuzzingCLI.java | 64 -
tika-fuzzing/src/test/java/TestTransformer.java | 50 -
.../test/resources/configs/tika-fuzzing-config.xml | 57 -
tika-fuzzing/src/test/resources/log4j2.xml | 42 -
.../test/resources/test-documents/heavy_hang.xml | 25 -
.../test/resources/test-documents/null_pointer.xml | 25 -
tika-grpc/pom.xml | 10 +-
.../tika/pipes/grpc/ExpiringFetcherStore.java | 4 +-
.../apache/tika/pipes/grpc/TikaGrpcServerImpl.java | 31 +-
.../tika/pipes/grpc/ExpiringFetcherStoreTest.java | 4 +-
.../apache/tika/pipes/grpc/TikaGrpcServerTest.java | 2 +-
tika-integration-tests/pom.xml | 13 +-
.../tika/pipes/kafka/tests/TikaPipesKafkaTest.java | 6 +-
.../pom.xml | 2 +-
.../pipes/opensearch/tests/OpenSearchTest.java | 10 +-
.../tika-pipes-s3-integration-tests/pom.xml | 10 +
.../tika/pipes/s3/tests/PipeIntegrationTests.java | 14 +-
.../tika/pipes/s3/tests/S3PipeIntegrationTest.java | 80 +-
.../src/test/resources/docker-compose.yml | 14 +
.../tika/pipes/solr/tests/TikaPipesSolr9Test.java | 2 +-
.../pipes/solr/tests/TikaPipesSolrTestBase.java | 8 +-
.../pom.xml | 10 +-
.../tika/woodstox/WoodstoxXMLReaderUtilsTest.java | 265 ++++
tika-langdetect/tika-langdetect-optimaize/pom.xml | 2 +-
tika-parent/pom.xml | 192 +--
tika-parsers/pom.xml | 22 +
tika-parsers/tika-parsers-extended/pom.xml | 24 +-
.../tika-parser-scientific-module/pom.xml | 1 +
.../geoinfo/GeographicInformationParser.java | 5 +-
.../tika-parser-scientific-package/pom.xml | 7 -
tika-parsers/tika-parsers-ml/pom.xml | 39 +-
.../tika-parsers-ml/tika-age-recogniser/pom.xml | 374 -----
.../tika/parser/recognition/AgeRecogniser.java | 142 --
.../parser/recognition/AgeRecogniserConfig.java | 66 -
.../tika/parser/recognition/AgeRecogniserTest.java | 85 --
.../tika/parser/recognition/tika-config-age.xml | 31 -
tika-parsers/tika-parsers-ml/tika-dl/pom.xml | 195 ---
.../tika/dl/imagerec/DL4JInceptionV3Net.java | 340 -----
.../org/apache/tika/dl/imagerec/DL4JVGG16Net.java | 158 ---
.../tika/dl/imagerec/DL4JInceptionV3NetTest.java | 63 -
.../apache/tika/dl/imagerec/DL4JVGG16NetTest.java | 64 -
.../resources/org/apache/tika/dl/imagerec/cat.jpg | Bin 7686 -> 0 bytes
.../tika/dl/imagerec/dl4j-inception3-config.xml | 35 -
.../apache/tika/dl/imagerec/dl4j-vgg16-config.xml | 32 -
.../resources/org/apache/tika/dl/imagerec/lion.jpg | Bin 44441 -> 0 bytes
.../tika-parser-advancedmedia-module/pom.xml | 85 --
.../tika/parser/captioning/CaptionObject.java | 39 -
.../captioning/tf/TensorflowRESTCaptioner.java | 170 ---
.../tika/parser/pot/PooledTimeSeriesParser.java | 237 ----
.../tika/parser/recognition/ObjectRecogniser.java | 81 --
.../recognition/ObjectRecognitionParser.java | 170 ---
.../tika/parser/recognition/RecognisedObject.java | 88 --
.../recognition/tf/TensorflowImageRecParser.java | 174 ---
.../recognition/tf/TensorflowRESTRecogniser.java | 178 ---
.../tf/TensorflowRESTVideoRecogniser.java | 94 --
.../tika/parser/captioning/tf/caption_generator.py | 179 ---
.../apache/tika/parser/captioning/tf/im2txtapi.py | 266 ----
.../tika/parser/captioning/tf/model_info.xml | 22 -
.../tika/parser/captioning/tf/model_wrapper.py | 340 -----
.../apache/tika/parser/captioning/tf/vocabulary.py | 67 -
.../tika/parser/recognition/tf/inception_v4.py | 362 -----
.../tika/parser/recognition/tf/inceptionapi.py | 483 -------
.../tika/parser/recognition/tf/video_util.py | 113 --
.../recognition/tika-config-tflow-im2txt-rest.xml | 33 -
.../parser/recognition/tika-config-tflow-rest.xml | 33 -
.../recognition/tika-config-tflow-video-rest.xml | 33 -
.../tika/parser/recognition/tika-config-tflow.xml | 29 -
.../recognition/ObjectRecognitionParserTest.java | 206 ---
.../tf/TensorflowImageRecParserTest.java | 60 -
.../tf/TensorflowVideoRecParserTest.java | 57 -
.../tika-parser-advancedmedia-package/pom.xml | 115 --
.../tika-parsers-ml/tika-parser-nlp-module/pom.xml | 4 +-
.../sentiment/SentimentAnalysisParserTest.java | 2 +-
.../tika/parser/ner/opennlp/ModelGetter.groovy | 7 +-
.../tika-parser-nlp-package/pom.xml | 7 -
.../tika-parsers-ml/tika-transcribe-aws/pom.xml | 7 -
tika-parsers/tika-parsers-standard/pom.xml | 30 +-
.../tika-parsers-standard-modules/pom.xml | 31 +-
.../org/apache/tika/detect/MatroskaDetector.java | 95 ++
.../java/org/apache/tika/parser/mp4/MP4Parser.java | 39 +-
.../services/org.apache.tika.detect.Detector | 3 +-
.../apache/tika/detect/MatroskaDetectorTest.java | 73 +
.../org/apache/tika/parser/mp4/MP4ParserTest.java | 41 +
.../test/resources/test-documents/sample-mkv.noext | Bin 0 -> 5759 bytes
.../resources/test-documents/sample-webm.noext | Bin 0 -> 16234 bytes
.../src/test/resources/test-documents/testMKV.mkv | Bin
.../{testMP3lyrics.mp3 => testMP4AudioOnly.mp4} | Bin 34688 -> 35236 bytes
.../tika-parser-cad-module/pom.xml | 4 +-
.../org/apache/tika/parser/dwg/DWGReadParser.java | 3 +-
.../tika-parser-code-module/pom.xml | 10 +
.../tika-parser-font-module/pom.xml | 9 +
.../tika-parser-html-module/pom.xml | 10 +
.../apache/tika/parser/html/HtmlParserTest.java | 3 +-
.../tika-parser-mail-module/pom.xml | 10 +
.../org/apache/tika/parser/mail/RFC822Parser.java | 13 +
.../tika-parser-microsoft-module/pom.xml | 9 +
.../detect/microsoft/ooxml/OPCPackageDetector.java | 4 +
.../microsoft/MSEmbeddedStreamTranslator.java | 39 +-
.../microsoft/PSTEmailStreamTranslator.java | 55 +
.../tika/parser/microsoft/ExcelExtractor.java | 3 +
....apache.tika.extractor.EmbeddedStreamTranslator | 3 +-
.../tika/parser/microsoft/OutlookParserTest.java | 7 +-
.../parser/microsoft/ooxml/OOXMLParserTest.java | 3 +-
.../tika-parser-miscoffice-module/pom.xml | 10 +
.../org/apache/tika/parser/mif/MIFExtractor.java | 5 +-
.../apache/tika/parser/odf/OpenDocumentParser.java | 65 +-
.../apache/tika/parser/epub/EpubParserTest.java | 42 +
.../org/apache/tika/parser/odf/ODFParserTest.java | 7 +
.../testEPUB_multi-metadata-vals.epub | Bin 0 -> 571926 bytes
.../tika-parser-news-module/pom.xml | 9 +
.../tika-parser-pdf-module/pom.xml | 10 +
.../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 352 +++--
.../tika/parser/pdf/PDMetadataExtractor.java | 16 +-
.../org/apache/tika/parser/pdf/PDFParserTest.java | 12 +-
.../tika-parser-pkg-module/pom.xml | 10 +
.../apache/tika/parser/pkg/CompressorParser.java | 2 +-
.../apache/tika/parser/txt/CharsetDetector.java | 30 +-
.../tika-parser-webarchive-module/pom.xml | 9 +
.../tika-parser-xml-module/pom.xml | 10 +
.../org/apache/tika/parser/xml/DcXMLParser.java | 1 +
.../tika-parser-xmp-commons/pom.xml | 9 +
.../detect/zip/DefaultZipContainerDetector.java | 23 +-
.../tika-parsers-standard-package/pom.xml | 3 +-
.../apache/tika/detect/TestDetectorLoading.java | 3 +-
.../org/apache/tika/ossfuzz/OssFuzzReplicator.java | 17 +-
.../java/org/apache/tika/ossfuzz/ParserFuzzer.java | 76 +
.../org/apache/tika/parser/pdf/PDFParserTest.java | 92 +-
.../org/apache/tika/sax/BoilerpipeHandlerTest.java | 3 +-
.../test/resources/configs/tika-4424-config.xml | 16 +
tika-pipes/pom.xml | 12 +
tika-pipes/tika-async-cli/pom.xml | 21 +-
.../apache/tika/async/cli/SimpleAsyncConfig.java | 24 +-
.../org/apache/tika/async/cli/TikaAsyncCLI.java | 189 ++-
.../tika/async/cli/TikaConfigAsyncWriter.java | 132 +-
.../apache/tika/async/cli/AsyncCliParserTest.java | 5 +-
.../apache/tika/async/cli/AsyncProcessorTest.java | 18 +-
.../tika/async/cli/TikaConfigAsyncWriterTest.java | 105 ++
.../test/resources/configs/TIKA-4508-emitters.xml | 58 +
.../test/resources/configs/TIKA-4508-parsers.xml | 49 +
tika-pipes/tika-emitters/pom.xml | 15 +-
.../tika-emitters/tika-emitter-az-blob/pom.xml | 16 +-
.../tika/pipes/emitter/azblob/AZBlobEmitter.java | 6 +-
.../pipes/emitter/azblob/TestAZBlobEmitter.java | 4 +-
tika-pipes/tika-emitters/tika-emitter-fs/pom.xml | 116 --
tika-pipes/tika-emitters/tika-emitter-gcs/pom.xml | 16 +-
.../apache/tika/pipes/emitter/gcs/GCSEmitter.java | 6 +-
.../tika/pipes/emitter/gcs/TestGCSEmitter.java | 4 +-
tika-pipes/tika-emitters/tika-emitter-jdbc/pom.xml | 2 +-
.../tika/pipes/emitter/jdbc/JDBCEmitter.java | 8 +-
.../tika/pipes/emitter/jdbc/JDBCEmitterTest.java | 4 +-
.../tika-emitters/tika-emitter-kafka/pom.xml | 16 +-
.../tika/pipes/emitter/kafka/KafkaEmitter.java | 4 +-
.../tika-emitters/tika-emitter-opensearch/pom.xml | 14 +-
.../pipes/emitter/opensearch/OpenSearchClient.java | 2 +-
.../emitter/opensearch/OpenSearchEmitter.java | 6 +-
tika-pipes/tika-emitters/tika-emitter-s3/pom.xml | 20 +-
.../apache/tika/pipes/emitter/s3/S3Emitter.java | 117 +-
tika-pipes/tika-emitters/tika-emitter-solr/pom.xml | 9 +-
.../tika/pipes/emitter/solr/SolrEmitter.java | 6 +-
.../tika-fetchers/tika-fetcher-az-blob/pom.xml | 15 +-
.../tika/pipes/fetcher/azblob/AZBlobFetcher.java | 2 +-
.../fetcher/azblob/config/AZBlobFetcherConfig.java | 2 +-
.../pipes/fetcher/azblob/TestAZBlobFetcher.java | 4 +-
tika-pipes/tika-fetchers/tika-fetcher-gcs/pom.xml | 9 +-
.../apache/tika/pipes/fetcher/gcs/GCSFetcher.java | 2 +-
.../pipes/fetcher/gcs/config/GCSFetcherConfig.java | 2 +-
.../tika/pipes/fetcher/s3/TestGCSFetcher.java | 4 +-
tika-pipes/tika-fetchers/tika-fetcher-http/pom.xml | 9 +-
.../tika/pipes/fetcher/http/HttpFetcher.java | 6 +-
.../fetcher/http/config/HttpFetcherConfig.java | 2 +-
.../tika/pipes/fetcher/http/HttpFetcherTest.java | 4 +-
.../tika-fetcher-microsoft-graph/pom.xml | 15 +-
.../microsoftgraph/MicrosoftGraphFetcher.java | 2 +-
.../config/MicrosoftGraphFetcherConfig.java | 2 +-
tika-pipes/tika-fetchers/tika-fetcher-s3/pom.xml | 21 +-
.../apache/tika/pipes/fetcher/s3/S3Fetcher.java | 130 +-
.../pipes/fetcher/s3/config/S3FetcherConfig.java | 2 +-
.../tika/pipes/fetcher/s3/TestS3Fetcher.java | 4 +-
tika-pipes/tika-httpclient-commons/pom.xml | 2 +-
.../tika-pipes-core}/pom.xml | 56 +-
.../tika/pipes/core}/CompositePipesReporter.java | 4 +-
.../pipes/core}/FailedToStartClientException.java | 2 +-
.../apache/tika/pipes/core}/FetchEmitTuple.java | 8 +-
.../org/apache/tika/pipes/core}/HandlerConfig.java | 2 +-
.../tika/pipes/core}/LoggingPipesReporter.java | 2 +-
.../org/apache/tika/pipes/core/PassbackFilter.java | 11 +-
.../org/apache/tika/pipes/core}/PipesClient.java | 45 +-
.../org/apache/tika/pipes/core}/PipesConfig.java | 2 +-
.../apache/tika/pipes/core}/PipesConfigBase.java | 2 +-
.../apache/tika/pipes/core}/PipesException.java | 2 +-
.../org/apache/tika/pipes/core}/PipesParser.java | 2 +-
.../org/apache/tika/pipes/core}/PipesReporter.java | 4 +-
.../apache/tika/pipes/core}/PipesReporterBase.java | 2 +-
.../org/apache/tika/pipes/core}/PipesResult.java | 7 +-
.../org/apache/tika/pipes/core}/PipesServer.java | 102 +-
.../apache/tika/pipes/core}/async/AsyncConfig.java | 6 +-
.../tika/pipes/core}/async/AsyncEmitter.java | 10 +-
.../tika/pipes/core}/async/AsyncProcessor.java | 22 +-
.../apache/tika/pipes/core}/async/AsyncStatus.java | 6 +-
.../core}/async/OfferLargerThanQueueSize.java | 2 +-
.../tika/pipes/core}/emitter/AbstractEmitter.java | 2 +-
.../apache/tika/pipes/core}/emitter/EmitData.java | 2 +-
.../apache/tika/pipes/core}/emitter/EmitKey.java | 2 +-
.../apache/tika/pipes/core}/emitter/Emitter.java | 2 +-
.../tika/pipes/core}/emitter/EmitterManager.java | 2 +-
.../tika/pipes/core}/emitter/EmptyEmitter.java | 2 +-
.../tika/pipes/core}/emitter/StreamEmitter.java | 2 +-
.../pipes/core}/emitter/TikaEmitterException.java | 2 +-
.../AbstractEmbeddedDocumentBytesHandler.java | 41 +-
.../BasicEmbeddedDocumentBytesHandler.java | 4 +-
.../extractor/EmbeddedDocumentBytesConfig.java | 59 +-
.../EmittingEmbeddedDocumentBytesHandler.java | 15 +-
.../tika/pipes/core}/fetcher/AbstractFetcher.java | 2 +-
.../tika/pipes/core}/fetcher/EmptyFetcher.java | 2 +-
.../apache/tika/pipes/core}/fetcher/FetchKey.java | 2 +-
.../apache/tika/pipes/core}/fetcher/Fetcher.java | 2 +-
.../tika/pipes/core}/fetcher/FetcherManager.java | 2 +-
.../core}/fetcher/FetcherStringException.java | 2 +-
.../tika/pipes/core}/fetcher/RangeFetcher.java | 2 +-
.../pipes/core}/fetcher/config/AbstractConfig.java | 2 +-
.../fetcher/config/FetcherConfigContainer.java | 2 +-
.../core}/pipesiterator/CallablePipesIterator.java | 4 +-
.../pipes/core}/pipesiterator/PipesIterator.java | 6 +-
.../core}/pipesiterator/TotalCountResult.java | 2 +-
.../pipes/core}/pipesiterator/TotalCounter.java | 2 +-
.../serialization/FetchEmitTupleDeserializer.java | 126 +-
.../serialization/FetchEmitTupleSerializer.java | 65 +
.../pipes/core/serialization/JsonEmitData.java | 46 +
.../core/serialization/JsonFetchEmitTuple.java | 59 +
.../serialization}/JsonFetchEmitTupleList.java | 56 +-
.../tika/pipes/emitter/fs/FileSystemEmitter.java | 15 +-
.../tika/pipes/fetcher/fs/FileSystemFetcher.java | 2 +-
.../fetcher/fs/config/FileSystemFetcherConfig.java | 2 +-
.../apache/tika/pipes/fetcher/url/UrlFetcher.java | 2 +-
.../filelist/FileListPipesIterator.java | 10 +-
.../pipesiterator/fs/FileSystemPipesIterator.java | 16 +-
.../resources/pipes-fork-server-default-log4j2.xml | 0
.../apache/tika/pipes/core/PassbackFilterTest.java | 127 ++
.../apache/tika/pipes/core}/PipesClientTest.java | 38 +-
.../apache/tika/pipes/core}/PipesServerTest.java | 14 +-
.../tika/pipes/core}/TikaPipesConfigTest.java | 19 +-
.../pipes/core}/async/AsyncChaosMonkeyTest.java | 20 +-
.../pipes/core}/async/MockDigesterFactory.java | 2 +-
.../apache/tika/pipes/core}/async/MockEmitter.java | 10 +-
.../apache/tika/pipes/core}/async/MockFetcher.java | 4 +-
.../tika/pipes/core}/async/MockReporter.java | 8 +-
.../tika/pipes/core}/async/MockReporterTest.java | 6 +-
.../tika/pipes/core}/emitter/MockEmitter.java | 2 +-
.../tika/pipes/core}/fetcher/MockFetcher.java | 2 +-
.../filelist/FileListPipesIteratorTest.java | 5 +-
.../serialization}/JsonFetchEmitTupleListTest.java | 8 +-
.../serialization}/JsonFetchEmitTupleTest.java | 10 +-
.../pipes/fetcher/fs/FileSystemFetcherTest.java | 1 +
.../fs}/FileSystemPipesIteratorTest.java | 6 +-
.../test/resources/configs/TIKA-4207-emitter.xml | 0
.../test/resources/configs/tika-config-broken.xml | 0
.../org/apache/tika/config/TIKA-3865-params.xml | 6 +-
.../org/apache/tika/config/emitters-config.xml | 4 +-
.../tika/config/emitters-duplicate-config.xml | 4 +-
.../tika/config/emitters-mock-throw-on-check.xml | 2 +-
.../org/apache/tika/config/fetchers-config.xml | 0
.../tika/config/fetchers-duplicate-config.xml | 0
.../tika/config/fetchers-mock-throw-on-check.xml | 2 +-
.../tika/config/fetchers-nobasepath-config.xml | 0
.../apache/tika/config/fetchers-noname-config.xml | 0
.../apache/tika/config/pipes-iterator-config.xml | 0
.../tika/config/pipes-iterator-multiple-config.xml | 0
.../org/apache/tika/pipes/core}/TIKA-3941.xml | 2 +-
.../tika/pipes/core}/TIKA-4207-limit-bytes.xml | 2 +-
.../org/apache/tika/pipes/core}/TIKA-4207.xml | 2 +-
.../apache/tika/pipes/core}/async/TIKA-3507.xml | 2 +-
.../apache/tika/pipes/core}/async/TIKA-3865.xml | 6 +-
.../apache/tika/pipes/core/tika-emit-config.xml | 10 +-
.../apache/tika/pipes/core}/tika-sample-config.xml | 2 +-
.../resources/test-documents/basic_embedded.xml | 0
.../test/resources/test-documents/file-list.txt | 0
.../resources/test-documents/mock/embedded.xml | 0
.../resources/test-documents/mock/timeout-10s.xml | 8 +-
.../test/resources/test-documents/mock_times.xml | 0
.../test-documents/testOverlappingText.pdf | Bin
tika-pipes/tika-pipes-iterators/pom.xml | 14 +
.../tika-pipes-iterator-az-blob/pom.xml | 9 +-
.../pipesiterator/azblob/AZBlobPipesIterator.java | 10 +-
.../azblob/TestAZBlobPipesIterator.java | 4 +-
.../tika-pipes-iterator-csv/pom.xml | 9 +-
.../pipes/pipesiterator/csv/CSVPipesIterator.java | 10 +-
.../src/test/java/TestCSVPipesIterator.java | 4 +-
.../tika-pipes-iterator-gcs/pom.xml | 9 +-
.../pipes/pipesiterator/gcs/GCSPipesIterator.java | 10 +-
.../pipesiterator/gcs/TestGCSPipesIterator.java | 4 +-
.../tika-pipes-iterator-jdbc/pom.xml | 9 +-
.../pipesiterator/jdbc/JDBCPipesIterator.java | 10 +-
.../pipesiterator/jdbc/TestJDBCPipesIterator.java | 4 +-
.../tika-pipes-iterator-json/pom.xml | 15 +-
.../pipesiterator/json/JsonPipesIterator.java | 6 +-
.../pipesiterator/json/TestJsonPipesIterator.java | 2 +-
.../tika-pipes-iterator-kafka/pom.xml | 9 +-
.../pipesiterator/kafka/KafkaPipesIterator.java | 10 +-
.../kafka/TestKafkaPipesIterator.java | 4 +-
.../tika-pipes-iterator-s3/pom.xml | 17 +-
.../pipes/pipesiterator/s3/S3PipesIterator.java | 111 +-
.../pipesiterator/s3/TestS3PipesIterator.java | 4 +-
.../tika-pipes-iterator-solr/pom.xml | 9 +-
.../pipesiterator/solr/SolrPipesIterator.java | 10 +-
.../tika-pipes-reporter-fs-status/pom.xml | 33 +-
.../reporters/fs/FileSystemStatusReporter.java | 10 +-
.../reporters/fs/TestFileSystemStatusReporter.java | 10 +-
.../tika-pipes-reporter-jdbc/pom.xml | 10 +-
.../pipes/reporters/jdbc/JDBCPipesReporter.java | 6 +-
.../reporters/jdbc/TestJDBCPipesReporter.java | 21 +-
.../tika-pipes-reporter-opensearch/pom.xml | 9 +-
.../opensearch/OpenSearchPipesReporter.java | 6 +-
tika-serialization/pom.xml | 7 -
.../apache/tika/serialization/JsonMetadata.java | 140 +-
.../tika/serialization/JsonMetadataList.java | 102 +-
.../serialization/JsonStreamingSerializer.java | 64 -
.../tika/serialization/MetadataDeserializer.java | 71 +
.../tika/serialization/MetadataSerializer.java | 76 +
.../tika/serialization/ParseContextSerializer.java | 1 -
.../tika/serialization/pipes/JsonEmitData.java | 59 -
.../tika/serialization/JsonMetadataListTest.java | 77 +-
.../tika/serialization/JsonMetadataTest.java | 14 +-
.../TestParseContextSerialization.java | 2 -
tika-server/tika-server-client/pom.xml | 20 +-
.../org/apache/tika/server/client/TikaClient.java | 4 +-
.../apache/tika/server/client/TikaClientCLI.java | 6 +-
tika-server/tika-server-core/pom.xml | 15 +-
.../tika/server/core/FetcherStreamFactory.java | 6 +-
.../org/apache/tika/server/core/TikaServerCli.java | 9 +-
.../apache/tika/server/core/TikaServerProcess.java | 4 +-
.../server/core/config/DocumentSelectorConfig.java | 4 +-
.../tika/server/core/resource/AsyncRequest.java | 2 +-
.../tika/server/core/resource/AsyncResource.java | 16 +-
.../server/core/resource/LanguageResource.java | 37 +-
.../tika/server/core/resource/PipesResource.java | 12 +-
.../core/resource/RecursiveMetadataResource.java | 2 +-
.../tika/server/core/resource/TikaResource.java | 10 +-
.../server/core/resource/TranslateResource.java | 50 +-
.../server/core/resource/UnpackerResource.java | 27 +-
.../org/apache/tika/server/core/TikaPipesTest.java | 21 +-
.../tika/server/core/TikaResourceFetcherTest.java | 2 +-
.../core/TikaServerAsyncIntegrationTest.java | 10 +-
.../tika/server/core/TikaServerConfigTest.java | 4 +-
.../core/TikaServerPipesIntegrationTest.java | 23 +-
tika-server/tika-server-eval/pom.xml | 9 +-
tika-server/tika-server-standard/bin/tika | 6 +-
tika-server/tika-server-standard/pom.xml | 14 +-
.../server/standard/config/PDFServerConfig.java | 4 +-
.../standard/config/TesseractServerConfig.java | 4 +-
.../apache/tika/server/standard/FetcherTest.java | 2 +-
.../standard/RecursiveMetadataResourceTest.java | 18 +
.../apache/tika/server/standard/TikaPipesTest.java | 35 +-
.../test-documents/testPDF_XFA_govdocs1_258578.pdf | Bin
tika-translate/pom.xml | 9 +-
tika-xmp/pom.xml | 7 -
.../apache/tika/xmp/convert/AbstractConverter.java | 2 +-
.../java/org/apache/tika/xmp/TikaToXMPTest.java | 4 +-
429 files changed, 5016 insertions(+), 11748 deletions(-)
rename .github/workflows/{main-jdk23-build.yml => main-jdk25-build.yml} (96%)
copy
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/parser/microsoft/onenote/fsshttpb/util/ByteUtil.java
=> tika-app/src/main/java/org/apache/tika/cli/AsyncHelper.java (55%)
create mode 100644
tika-app/src/main/resources/tika-config-default-single-file.xml
copy
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/parser/apple/IWorkTest.java
=> tika-app/src/test/java/org/apache/tika/cli/AsyncHelperTest.java (69%)
copy
{tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module/src/test/resources/test-documents
=> tika-app/src/test/resources/test-data}/testPDFPackage.pdf (100%)
copy
{tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents
=> tika-app/src/test/resources/test-data}/testPPT_macros.ppt (100%)
copy
{tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents
=> tika-app/src/test/resources/test-data}/testPST.pst (100%)
delete mode 100644 tika-deployment/tika-snap-app/snapcraft.yaml
delete mode 100644 tika-deployment/tika-snap-server/snapcraft.yaml
delete mode 100644 tika-dotnet/pom.xml
delete mode 100644 tika-dotnet/src/main/java/Tika/Tika.java
delete mode 100644 tika-fuzzing/pom.xml
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/AutoDetectTransformer.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/Transformer.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/cli/FuzzOne.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/cli/FuzzingCLI.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/cli/FuzzingCLIConfig.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/exceptions/CantFuzzException.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/general/ByteDeleter.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/general/ByteFlipper.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/general/ByteInjector.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/general/GeneralTransformer.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/general/SpanSwapper.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/general/Truncator.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/EvilCOSWriter.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/PDFTransformer.java
delete mode 100644
tika-fuzzing/src/main/java/org/apache/tika/fuzzing/pdf/PDFTransformerConfig.java
delete mode 100644
tika-fuzzing/src/main/resources/META-INF/services/org.apache.tika.fuzzing.Transformer
delete mode 100644 tika-fuzzing/src/main/resources/log4j2.xml
delete mode 100644 tika-fuzzing/src/test/java/TestFuzzingCLI.java
delete mode 100644 tika-fuzzing/src/test/java/TestTransformer.java
delete mode 100644
tika-fuzzing/src/test/resources/configs/tika-fuzzing-config.xml
delete mode 100644 tika-fuzzing/src/test/resources/log4j2.xml
delete mode 100644
tika-fuzzing/src/test/resources/test-documents/heavy_hang.xml
delete mode 100644
tika-fuzzing/src/test/resources/test-documents/null_pointer.xml
copy tika-integration-tests/{tika-resource-loading-tests =>
tika-woodstox-tests}/pom.xml (84%)
create mode 100644
tika-integration-tests/tika-woodstox-tests/src/test/java/org/apache/tika/woodstox/WoodstoxXMLReaderUtilsTest.java
delete mode 100644 tika-parsers/tika-parsers-ml/tika-age-recogniser/pom.xml
delete mode 100644
tika-parsers/tika-parsers-ml/tika-age-recogniser/src/main/java/org/apache/tika/parser/recognition/AgeRecogniser.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-age-recogniser/src/main/java/org/apache/tika/parser/recognition/AgeRecogniserConfig.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-age-recogniser/src/test/java/org/apache/tika/parser/recognition/AgeRecogniserTest.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-age-recogniser/src/test/resources/org/apache/tika/parser/recognition/tika-config-age.xml
delete mode 100644 tika-parsers/tika-parsers-ml/tika-dl/pom.xml
delete mode 100644
tika-parsers/tika-parsers-ml/tika-dl/src/main/java/org/apache/tika/dl/imagerec/DL4JInceptionV3Net.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-dl/src/main/java/org/apache/tika/dl/imagerec/DL4JVGG16Net.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-dl/src/test/java/org/apache/tika/dl/imagerec/DL4JInceptionV3NetTest.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-dl/src/test/java/org/apache/tika/dl/imagerec/DL4JVGG16NetTest.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-dl/src/test/resources/org/apache/tika/dl/imagerec/cat.jpg
delete mode 100644
tika-parsers/tika-parsers-ml/tika-dl/src/test/resources/org/apache/tika/dl/imagerec/dl4j-inception3-config.xml
delete mode 100644
tika-parsers/tika-parsers-ml/tika-dl/src/test/resources/org/apache/tika/dl/imagerec/dl4j-vgg16-config.xml
delete mode 100644
tika-parsers/tika-parsers-ml/tika-dl/src/test/resources/org/apache/tika/dl/imagerec/lion.jpg
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/pom.xml
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/captioning/CaptionObject.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/captioning/tf/TensorflowRESTCaptioner.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/pot/PooledTimeSeriesParser.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/ObjectRecogniser.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/ObjectRecognitionParser.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/RecognisedObject.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/tf/TensorflowImageRecParser.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/tf/TensorflowRESTRecogniser.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/java/org/apache/tika/parser/recognition/tf/TensorflowRESTVideoRecogniser.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/captioning/tf/caption_generator.py
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/captioning/tf/im2txtapi.py
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/captioning/tf/model_info.xml
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/captioning/tf/model_wrapper.py
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/captioning/tf/vocabulary.py
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/recognition/tf/inception_v4.py
delete mode 100755
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/recognition/tf/inceptionapi.py
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/recognition/tf/video_util.py
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/recognition/tika-config-tflow-im2txt-rest.xml
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/recognition/tika-config-tflow-rest.xml
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/recognition/tika-config-tflow-video-rest.xml
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/main/resources/org/apache/tika/parser/recognition/tika-config-tflow.xml
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/test/java/org/apache/tika/parser/recognition/ObjectRecognitionParserTest.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/test/java/org/apache/tika/parser/recognition/tf/TensorflowImageRecParserTest.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-module/src/test/java/org/apache/tika/parser/recognition/tf/TensorflowVideoRecParserTest.java
delete mode 100644
tika-parsers/tika-parsers-ml/tika-parser-advancedmedia-package/pom.xml
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/detect/MatroskaDetector.java
copy
tika-core/src/test/resources/META-INF/services/org.apache.tika.parser.Parser =>
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/resources/META-INF/services/org.apache.tika.detect.Detector
(95%)
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/java/org/apache/tika/detect/MatroskaDetectorTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/resources/test-documents/sample-mkv.noext
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/resources/test-documents/sample-webm.noext
rename tika-parsers/tika-parsers-standard/{tika-parsers-standard-package =>
tika-parsers-standard-modules/tika-parser-audiovideo-module}/src/test/resources/test-documents/testMKV.mkv
(100%)
copy
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/test/resources/test-documents/{testMP3lyrics.mp3
=> testMP4AudioOnly.mp4} (96%)
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/main/java/org/apache/tika/extractor/microsoft/PSTEmailStreamTranslator.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-miscoffice-module/src/test/resources/test-documents/testEPUB_multi-metadata-vals.epub
copy
tika-example/src/test/java/org/apache/tika/example/AdvancedTypeDetectorTest.java
=>
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/ossfuzz/OssFuzzReplicator.java
(68%)
mode change 100755 => 100644
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/ossfuzz/ParserFuzzer.java
create mode 100644
tika-pipes/tika-async-cli/src/test/java/org/apache/tika/async/cli/TikaConfigAsyncWriterTest.java
create mode 100644
tika-pipes/tika-async-cli/src/test/resources/configs/TIKA-4508-emitters.xml
create mode 100644
tika-pipes/tika-async-cli/src/test/resources/configs/TIKA-4508-parsers.xml
delete mode 100644 tika-pipes/tika-emitters/tika-emitter-fs/pom.xml
copy
{tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module
=> tika-pipes/tika-pipes-core}/pom.xml (68%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/CompositePipesReporter.java
(97%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/FailedToStartClientException.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/FetchEmitTuple.java
(95%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/HandlerConfig.java
(99%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/LoggingPipesReporter.java
(97%)
copy tika-core/src/main/java/org/apache/tika/fork/ForkProxy.java =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/PassbackFilter.java
(74%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/PipesClient.java
(92%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/PipesConfig.java
(98%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/PipesConfigBase.java
(99%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/PipesException.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/PipesParser.java
(98%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/PipesReporter.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/PipesReporterBase.java
(99%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/PipesResult.java
(93%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/PipesServer.java
(91%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/async/AsyncConfig.java
(95%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/async/AsyncEmitter.java
(94%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/async/AsyncProcessor.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/async/AsyncStatus.java
(94%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/async/OfferLargerThanQueueSize.java
(97%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/emitter/AbstractEmitter.java
(97%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/emitter/EmitData.java
(98%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/emitter/EmitKey.java
(98%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/emitter/Emitter.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/emitter/EmitterManager.java
(98%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/emitter/EmptyEmitter.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/emitter/StreamEmitter.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/emitter/TikaEmitterException.java
(96%)
rename {tika-core/src/main/java/org/apache/tika =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/extractor/AbstractEmbeddedDocumentBytesHandler.java
(68%)
rename {tika-core/src/main/java/org/apache/tika =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/extractor/BasicEmbeddedDocumentBytesHandler.java
(94%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/extractor/EmbeddedDocumentBytesConfig.java
(70%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/extractor/EmittingEmbeddedDocumentBytesHandler.java
(87%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/fetcher/AbstractFetcher.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/fetcher/EmptyFetcher.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/fetcher/FetchKey.java
(98%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/fetcher/Fetcher.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/fetcher/FetcherManager.java
(98%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/fetcher/FetcherStringException.java
(95%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/fetcher/RangeFetcher.java
(97%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/fetcher/config/AbstractConfig.java
(94%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/fetcher/config/FetcherConfigContainer.java
(96%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/pipesiterator/CallablePipesIterator.java
(98%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/pipesiterator/PipesIterator.java
(98%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/pipesiterator/TotalCountResult.java
(97%)
rename {tika-core/src/main/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core}/pipesiterator/TotalCounter.java
(97%)
rename
tika-serialization/src/main/java/org/apache/tika/serialization/pipes/JsonFetchEmitTuple.java
=>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/serialization/FetchEmitTupleDeserializer.java
(50%)
create mode 100644
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/serialization/FetchEmitTupleSerializer.java
create mode 100644
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/serialization/JsonEmitData.java
create mode 100644
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/serialization/JsonFetchEmitTuple.java
rename {tika-serialization/src/main/java/org/apache/tika/serialization/pipes
=>
tika-pipes/tika-pipes-core/src/main/java/org/apache/tika/pipes/core/serialization}/JsonFetchEmitTupleList.java
(50%)
rename tika-pipes/{tika-emitters/tika-emitter-fs =>
tika-pipes-core}/src/main/java/org/apache/tika/pipes/emitter/fs/FileSystemEmitter.java
(90%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/main/java/org/apache/tika/pipes/fetcher/fs/FileSystemFetcher.java
(99%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/main/java/org/apache/tika/pipes/fetcher/fs/config/FileSystemFetcherConfig.java
(95%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/main/java/org/apache/tika/pipes/fetcher/url/UrlFetcher.java
(97%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/main/java/org/apache/tika/pipes/pipesiterator/filelist/FileListPipesIterator.java
(93%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/main/java/org/apache/tika/pipes/pipesiterator/fs/FileSystemPipesIterator.java
(94%)
copy {tika-core =>
tika-pipes/tika-pipes-core}/src/main/resources/pipes-fork-server-default-log4j2.xml
(100%)
create mode 100644
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core/PassbackFilterTest.java
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/PipesClientTest.java
(70%)
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/PipesServerTest.java
(95%)
rename {tika-core/src/test/java/org/apache/tika/config =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/TikaPipesConfigTest.java
(90%)
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/async/AsyncChaosMonkeyTest.java
(93%)
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/async/MockDigesterFactory.java
(97%)
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/async/MockEmitter.java
(87%)
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/async/MockFetcher.java
(94%)
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/async/MockReporter.java
(89%)
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/async/MockReporterTest.java
(93%)
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/emitter/MockEmitter.java
(97%)
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/fetcher/MockFetcher.java
(98%)
rename {tika-core/src/test/java/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core}/pipesiterator/filelist/FileListPipesIteratorTest.java
(94%)
rename {tika-serialization/src/test/java/org/apache/tika/serialization/pipes
=>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core/serialization}/JsonFetchEmitTupleListTest.java
(90%)
rename {tika-serialization/src/test/java/org/apache/tika/serialization/pipes
=>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core/serialization}/JsonFetchEmitTupleTest.java
(94%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/java/org/apache/tika/pipes/fetcher/fs/FileSystemFetcherTest.java
(97%)
rename {tika-core/src/test/java/org/apache/tika/pipes/pipesiterator =>
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/pipesiterator/fs}/FileSystemPipesIteratorTest.java
(94%)
copy tika-pipes/{tika-async-cli =>
tika-pipes-core}/src/test/resources/configs/TIKA-4207-emitter.xml (100%)
copy tika-pipes/{tika-async-cli =>
tika-pipes-core}/src/test/resources/configs/tika-config-broken.xml (100%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/TIKA-3865-params.xml
(84%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/emitters-config.xml
(87%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/emitters-duplicate-config.xml
(88%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/emitters-mock-throw-on-check.xml
(93%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/fetchers-config.xml
(100%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/fetchers-duplicate-config.xml
(100%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/fetchers-mock-throw-on-check.xml
(93%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/fetchers-nobasepath-config.xml
(100%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/fetchers-noname-config.xml
(100%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/pipes-iterator-config.xml
(100%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/org/apache/tika/config/pipes-iterator-multiple-config.xml
(100%)
rename {tika-core/src/test/resources/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/resources/org/apache/tika/pipes/core}/TIKA-3941.xml
(92%)
rename {tika-core/src/test/resources/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/resources/org/apache/tika/pipes/core}/TIKA-4207-limit-bytes.xml
(93%)
rename {tika-core/src/test/resources/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/resources/org/apache/tika/pipes/core}/TIKA-4207.xml
(92%)
rename {tika-core/src/test/resources/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/resources/org/apache/tika/pipes/core}/async/TIKA-3507.xml
(92%)
rename {tika-core/src/test/resources/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/resources/org/apache/tika/pipes/core}/async/TIKA-3865.xml
(83%)
copy tika-core/src/test/resources/org/apache/tika/pipes/tika-sample-config.xml
=>
tika-pipes/tika-pipes-core/src/test/resources/org/apache/tika/pipes/core/tika-emit-config.xml
(80%)
rename {tika-core/src/test/resources/org/apache/tika/pipes =>
tika-pipes/tika-pipes-core/src/test/resources/org/apache/tika/pipes/core}/tika-sample-config.xml
(93%)
copy {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/test-documents/basic_embedded.xml
(100%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/test-documents/file-list.txt
(100%)
rename {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/test-documents/mock/embedded.xml
(100%)
rename tika-fuzzing/src/test/resources/test-documents/system_exit.xml =>
tika-pipes/tika-pipes-core/src/test/resources/test-documents/mock/timeout-10s.xml
(82%)
copy {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/test-documents/mock_times.xml
(100%)
copy {tika-core =>
tika-pipes/tika-pipes-core}/src/test/resources/test-documents/testOverlappingText.pdf
(100%)
delete mode 100644
tika-serialization/src/main/java/org/apache/tika/serialization/JsonStreamingSerializer.java
create mode 100644
tika-serialization/src/main/java/org/apache/tika/serialization/MetadataDeserializer.java
create mode 100644
tika-serialization/src/main/java/org/apache/tika/serialization/MetadataSerializer.java
delete mode 100644
tika-serialization/src/main/java/org/apache/tika/serialization/pipes/JsonEmitData.java
copy
{tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pdf-module
=>
tika-server/tika-server-standard}/src/test/resources/test-documents/testPDF_XFA_govdocs1_258578.pdf
(100%)