This is an automated email from the ASF dual-hosted git repository. tallison pushed a commit to branch TIKA-4519 in repository https://gitbox.apache.org/repos/asf/tika.git
commit 883d9366cba34c561605259360bfee060cbc345e Merge: 18f0d77a3 a32098b94 Author: tallison <[email protected]> AuthorDate: Mon Nov 3 09:47:27 2025 -0500 Merge branch 'main' into TIKA-4519 .../apache/tika/extractor/RUnpackExtractor.java | 32 ++++++------- .../java/org/apache/tika/io/FilenameUtils.java | 3 +- .../java/org/apache/tika/io/TikaInputStream.java | 43 ++++++++++++++++- .../org/apache/tika/parser/DigestingParser.java | 23 ++++++++- .../org/apache/tika/sax/SecureContentHandler.java | 10 ++-- .../src/test/java/org/apache/tika/TikaTest.java | 9 ++++ .../tika/eval/app/ExtractComparerRunner.java | 4 +- .../apache/tika/eval/app/ExtractProfileRunner.java | 4 +- .../org/apache/tika/eval/app/db/MimeBuffer.java | 16 +++---- .../org/apache/tika/eval/app/io/ExtractReader.java | 8 ++-- tika-parent/pom.xml | 10 ++-- .../org/apache/tika/parser/isatab/ISATabUtils.java | 25 +++++----- .../parser/microsoft/AbstractPOIFSExtractor.java | 36 ++++++++------ .../microsoft/ooxml/AbstractOOXMLExtractor.java | 52 ++++++++++----------- .../parser/microsoft/pst/OutlookPSTParser.java | 31 ++++++++++-- .../parser/microsoft/pst/PSTMailItemParser.java | 5 +- .../parser/microsoft/chm/TestChmExtraction.java | 4 +- .../apache/tika/parser/AutoDetectParserTest.java | 37 +++++++++++++++ .../src/test/resources/configs/tika-4533.xml | 47 +++++++++++++++++++ .../resources/test-documents/testLargeOLEDoc.doc | Bin 0 -> 2077696 bytes .../tika/pipes/fetcher/azblob/AZBlobFetcher.java | 2 +- .../tika-fetcher-microsoft-graph/pom.xml | 2 +- .../server/core/resource/UnpackerResource.java | 18 ++++--- tika-translate/pom.xml | 2 +- .../language/translate/impl/RTGTranslatorTest.java | 4 +- 25 files changed, 305 insertions(+), 122 deletions(-)
