This is an automated email from the ASF dual-hosted git repository. tallison pushed a commit to branch TIKA-4567 in repository https://gitbox.apache.org/repos/asf/tika.git
commit c47412266d41fcbcb2c335081ad2e01aeb7e3d8d Merge: acad345d62 5387cef917 Author: tallison <[email protected]> AuthorDate: Thu Dec 11 10:06:36 2025 -0500 Merge remote-tracking branch 'origin/main' into TIKA-4567 .../tika/language/translate/DefaultTranslator.java | 6 + .../java/org/apache/tika/parser/EmptyParser.java | 2 + .../java/org/apache/tika/parser/ErrorParser.java | 2 + .../tika/config/TikaConfigSerializerTest.java | 15 +- .../apache/tika/config/TikaDetectorConfigTest.java | 38 +--- .../tika/config/TikaEncodingDetectorTest.java | 3 +- .../apache/tika/config/TikaParserConfigTest.java | 164 +++++++------- .../tika/config/TikaTranslatorConfigTest.java | 54 ++--- .../org/apache/tika/detect/TestZipDetector.java | 7 +- .../java/org/apache/tika/parser/TestXXEInXML.java | 244 --------------------- .../parser/fork/ForkParserIntegrationTest.java | 8 +- .../tika/parser/ocr/TesseractOCRParserTest.java | 9 +- .../pkg/CompositeZipContainerDetectorTest.java | 14 +- .../org/apache/tika/parser/pkg/GzipParserTest.java | 9 +- .../apache/tika/parser/pkg/UnrarParserTest.java | 10 +- .../configs/TIKA-1708-detector-composite.json | 13 ++ .../configs/TIKA-1708-detector-default.json | 11 +- .../test/resources/configs/tika-4424-config.xml | 26 --- .../src/test/resources/configs/tika-4441-120.xml | 36 --- .../test/resources/configs/tika-4441-12000000.xml | 36 --- .../src/test/resources/configs/tika-4441-neg1.xml | 36 --- .../src/test/resources/configs/tika-4533.xml | 47 ---- .../configs/tika-config-digests-pdf-only.xml | 33 --- .../configs/tika-config-digests-skip-container.xml | 33 --- .../test/resources/configs/tika-config-digests.xml | 32 --- ...ka-config-doubling-custom-handler-decorator.xml | 27 --- .../tika-config-geo-point-metadata-filter.xml | 24 -- .../resources/configs/tika-config-lib-pst.json | 11 +- .../test/resources/configs/tika-config-lib-pst.xml | 26 --- .../resources/configs/tika-config-multiple-gz.json | 14 ++ .../resources/configs/tika-config-multiple-gz.xml | 29 --- .../test/resources/configs/tika-unrar-config.json | 12 + .../org/apache/tika/config/TIKA-1558-exclude.json | 23 +- .../org/apache/tika/config/TIKA-1558-exclude.xml | 29 --- .../apache/tika/config/TIKA-1558-excludesub.json | 7 +- .../apache/tika/config/TIKA-1558-excludesub.xml | 24 -- .../tika/config/TIKA-1702-detector-exclude.xml | 31 --- .../tika/config/TIKA-1702-translator-default.json | 10 +- .../tika/config/TIKA-1702-translator-default.xml | 24 -- .../config/TIKA-1702-translator-empty-default.json | 11 +- .../config/TIKA-1702-translator-empty-default.xml | 22 -- .../tika/config/TIKA-1702-translator-empty.json | 8 +- .../tika/config/TIKA-1702-translator-empty.xml | 20 -- .../tika/config/TIKA-1708-detector-composite.json | 13 +- .../tika/config/TIKA-1708-detector-composite.xml | 25 --- ...-2273-encoding-detector-outside-static-init.xml | 34 --- ...TIKA-2273-exclude-encoding-detector-default.xml | 29 --- .../TIKA-2273-no-icu4j-encoding-detector.xml | 27 --- .../TIKA-2273-non-detecting-params-bad-charset.xml | 29 --- .../tika/config/TIKA-2273-non-detecting-params.xml | 29 --- .../TIKA-2273-parameterize-encoding-detector.xml | 30 --- .../TIKA-2485-encoding-detector-mark-limits.xml | 38 ---- .../org/apache/tika/parser/TIKA-3137-include.xml | 34 --- .../apache/tika/parser/ocr/tesseract-config.json | 14 +- .../apache/tika/parser/ocr/tesseract-config.xml | 32 --- .../apache/tika/config/loader/DetectorLoader.java | 7 + .../apache/tika/config/loader/ParserLoader.java | 24 +- 57 files changed, 260 insertions(+), 1345 deletions(-)
