This is an automated email from the ASF dual-hosted git repository. tallison pushed a commit to branch TIKA-4207 in repository https://gitbox.apache.org/repos/asf/tika.git
commit dae75c632055d980fdad047fe07dd745359fca3f Merge: 7ca6d1759 08727d522 Author: tallison <talli...@apache.org> AuthorDate: Thu Mar 21 12:21:52 2024 -0400 Merge remote-tracking branch 'origin/main' into TIKA-4207 .../src/main/java/org/apache/tika/cli/TikaCLI.java | 2 +- tika-core/src/main/java/org/apache/tika/Tika.java | 4 ++ .../main/java/org/apache/tika/metadata/PDF.java | 4 ++ .../org/apache/tika/mime/tika-mimetypes.xml | 53 +++++++++++++++---- tika-eval/tika-eval-app/pom.xml | 2 - .../org/apache/tika/eval/app/AbstractProfiler.java | 17 +++++- .../org/apache/tika/eval/app/ExtractProfiler.java | 4 ++ .../java/org/apache/tika/eval/app/db/Cols.java | 3 ++ tika-parent/pom.xml | 60 ++++++++++++---------- .../ooxml/XSLFPowerPointExtractorDecorator.java | 3 +- .../apache/tika/parser/ocr/TesseractOCRParser.java | 20 ++++++-- .../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 6 +++ .../org/apache/tika/parser/pdf/OCRPageCounter.java | 4 ++ .../org/apache/tika/parser/pdf/PDFParserTest.java | 8 +++ .../org/apache/tika/parser/pkg/PackageParser.java | 50 +----------------- .../parser/microsoft/ooxml/TruncatedOOXMLTest.java | 4 +- .../tika/parser/ocr/TesseractOCRParserTest.java | 9 ++++ .../apache/tika/parser/pkg/Seven7ParserTest.java | 3 +- .../pipes/reporters/jdbc/JDBCPipesReporter.java | 52 ++++++++++--------- .../apache/tika/server/core/TikaServerProcess.java | 2 +- .../tika/server/core/resource/TikaResource.java | 2 +- .../apache/tika/server/core/TikaVersionTest.java | 2 +- .../apache/tika/server/core/TikaWelcomeTest.java | 4 +- 23 files changed, 193 insertions(+), 125 deletions(-)