This is an automated email from the ASF dual-hosted git repository.
ndipiazza pushed a change to branch TIKA-4572
in repository https://gitbox.apache.org/repos/asf/tika.git
from 10eeb7814 TIKA-4572: refactor TikaGrpcServer to use JSON config and
improve error handling
add 25cb0e939 TIKA-4541-tis-everywhere (#2449)
add 8bfb43182 Merge branch 'main' of github.com:apache/tika into TIKA-4572
No new revisions were added by this update.
Summary of changes:
.../src/main/java/org/apache/tika/cli/TikaCLI.java | 20 +-
.../src/main/java/org/apache/tika/gui/TikaGUI.java | 48 +-
.../test/java/org/apache/tika/bundle/BundleIT.java | 45 +-
tika-core/src/main/java/org/apache/tika/Tika.java | 14 +-
.../org/apache/tika/detect/AutoDetectReader.java | 18 +-
.../org/apache/tika/detect/CompositeDetector.java | 6 +-
.../tika/detect/CompositeEncodingDetector.java | 8 +-
.../main/java/org/apache/tika/detect/Detector.java | 15 +-
.../java/org/apache/tika/detect/EmptyDetector.java | 4 +-
.../org/apache/tika/detect/EncodingDetector.java | 12 +-
.../apache/tika/detect/FileCommandDetector.java | 28 +-
.../java/org/apache/tika/detect/MagicDetector.java | 20 +-
.../java/org/apache/tika/detect/NameDetector.java | 6 +-
.../org/apache/tika/detect/OverrideDetector.java | 4 +-
.../tika/detect/OverrideEncodingDetector.java | 4 +-
.../java/org/apache/tika/detect/TextDetector.java | 16 +-
.../apache/tika/detect/TrainedModelDetector.java | 11 +-
.../java/org/apache/tika/detect/TypeDetector.java | 7 +-
.../apache/tika/detect/ZeroSizeFileDetector.java | 12 +-
.../org/apache/tika/digest/CompositeDigester.java | 19 +-
.../java/org/apache/tika/digest/DigestHelper.java | 18 +-
.../main/java/org/apache/tika/digest/Digester.java | 14 +-
.../apache/tika/digest/InputStreamDigester.java | 35 +-
.../tika/extractor/ParserContainerExtractor.java | 43 +-
.../apache/tika/extractor/RUnpackExtractor.java | 4 +-
.../apache/tika/fork}/AutoDetectParserFactory.java | 11 +-
.../main/java/org/apache/tika/fork/ForkParser.java | 14 +-
.../main/java/org/apache/tika/fork/ForkServer.java | 6 +-
.../tika/{parser => fork}/ParserFactory.java | 3 +-
.../org/apache/tika/fork/ParserFactoryFactory.java | 1 -
.../main/java/org/apache/tika/fork/ParserShim.java | 14 +-
.../java/org/apache/tika/fork/ParserWrapper.java | 28 +-
.../main/java/org/apache/tika/fork/RPWShim.java | 31 +-
.../main/java/org/apache/tika/mime/MagicMatch.java | 7 +-
.../main/java/org/apache/tika/mime/MimeTypes.java | 21 +-
.../mime/ProbabilisticMimeDetectionSelector.java | 12 +-
.../org/apache/tika/parser/AbstractParser.java | 10 +-
.../org/apache/tika/parser/AutoDetectParser.java | 88 ++-
.../org/apache/tika/parser/CompositeParser.java | 11 +-
.../java/org/apache/tika/parser/CryptoParser.java | 9 +-
.../org/apache/tika/parser/DelegatingParser.java | 6 +-
.../org/apache/tika/parser/DigestingParser.java | 6 +-
.../java/org/apache/tika/parser/EmptyParser.java | 4 +-
.../java/org/apache/tika/parser/ErrorParser.java | 4 +-
.../java/org/apache/tika/parser/NetworkParser.java | 18 +-
.../main/java/org/apache/tika/parser/Parser.java | 4 +-
.../org/apache/tika/parser/ParserDecorator.java | 6 +-
.../apache/tika/parser/ParserPostProcessor.java | 6 +-
.../java/org/apache/tika/parser/ParsingReader.java | 13 +-
.../apache/tika/parser/RecursiveParserWrapper.java | 19 +-
.../org/apache/tika/parser/RegexCaptureParser.java | 6 +-
.../tika/parser/external/ExternalParser.java | 10 +-
.../tika/parser/external2/ExternalParser.java | 12 +-
.../parser/multiple/AbstractMultipleParser.java | 14 +-
.../apache/tika/renderer/CompositeRenderer.java | 6 +-
.../java/org/apache/tika/renderer/Renderer.java | 6 +-
.../java/org/apache/tika/utils/ParserUtils.java | 49 +-
.../org/apache/custom/detect/MyCustomDetector.java | 4 +-
.../org/apache/tika/MultiThreadedTikaTest.java | 13 +-
.../src/test/java/org/apache/tika/TikaTest.java | 84 ++-
.../tika/detect/FileCommandDetectorTest.java | 15 +-
.../org/apache/tika/detect/MagicDetectorTest.java | 32 +-
.../tika/detect/MimeDetectionWithNNTest.java | 26 +-
.../org/apache/tika/detect/TextDetectorTest.java | 15 +-
.../tika/detect/ZeroSizeFileDetectorTest.java | 7 +-
.../java/org/apache/tika/fork/ForkParserTest.java | 66 +-
.../apache/tika/fork/ForkParserTikaBinTest.java | 11 +-
.../java/org/apache/tika/fork/ForkTestParser.java | 22 +-
.../org/apache/tika/io/TikaInputStreamTest.java | 46 +-
.../org/apache/tika/mime/MimeDetectionTest.java | 78 +--
.../org/apache/tika/mime/MimeTypesReaderTest.java | 9 +-
.../tika/mime/ProbabilisticMimeDetectionTest.java | 69 +-
.../org/apache/tika/mime/RFC822DetectionTest.java | 10 +-
.../apache/tika/parser/CompositeParserTest.java | 12 +-
.../java/org/apache/tika/parser/DummyParser.java | 4 +-
.../apache/tika/parser/ParserDecoratorTest.java | 6 +-
.../apache/tika/parser/RegexCaptureParserTest.java | 5 +-
.../tika/parser/mock/AutoDetectParserFactory.java | 2 +-
.../org/apache/tika/parser/mock/MockParser.java | 7 +-
.../apache/tika/parser/mock/MockParserFactory.java | 2 +-
.../tika/parser/multiple/MultipleParserTest.java | 16 +-
.../tika/sax/BasicContentHandlerFactoryTest.java | 4 +-
.../apache/tika/sax/BodyContentHandlerTest.java | 6 +-
.../apache/tika/sax/CustomErrorHandlerTest.java | 5 +-
.../apache/tika/detect/magika/MagikaDetector.java | 27 +-
.../tika/detect/siegfried/SiegfriedDetector.java | 27 +-
.../apache/tika/example/AdvancedTypeDetector.java | 5 +-
.../apache/tika/example/ContentHandlerExample.java | 26 +-
.../org/apache/tika/example/DirListParser.java | 15 +-
.../apache/tika/example/DisplayMetInstance.java | 5 +-
.../example/EncryptedPrescriptionDetector.java | 5 +-
.../tika/example/EncryptedPrescriptionParser.java | 9 +-
.../apache/tika/example/ExtractEmbeddedFiles.java | 5 +-
.../tika/example/GrabPhoneNumbersExample.java | 6 +-
.../org/apache/tika/example/ImportContextImpl.java | 8 +-
.../tika/example/InterruptableParsingExample.java | 8 +-
.../java/org/apache/tika/example/Language.java | 5 +-
.../tika/example/LanguageDetectingParser.java | 6 +-
.../tika/example/MetadataAwareLuceneIndexer.java | 11 +-
.../java/org/apache/tika/example/MyFirstTika.java | 17 +-
.../org/apache/tika/example/ParsingExample.java | 24 +-
.../tika/example/PickBestTextEncodingParser.java | 10 +-
.../org/apache/tika/example/RollbackSoftware.java | 30 +-
.../org/apache/tika/example/SpringExample.java | 8 +-
.../tika/example/StandardsExtractionExample.java | 6 +-
.../org/apache/tika/example/TIAParsingExample.java | 151 ++---
.../org/apache/custom/parser/MyCustomParser.java | 4 +-
tika-parent/intellij-code-style.xml | 78 +--
tika-parent/pom.xml | 149 ++---
.../apache/tika/parser/envi/EnviHeaderParser.java | 12 +-
.../org/apache/tika/parser/gdal/GDALParser.java | 9 +-
.../geoinfo/GeographicInformationParser.java | 10 +-
.../org/apache/tika/parser/grib/GribParser.java | 6 +-
.../java/org/apache/tika/parser/hdf/HDFParser.java | 6 +-
.../org/apache/tika/parser/isatab/ISATabUtils.java | 10 +-
.../apache/tika/parser/isatab/ISArchiveParser.java | 12 +-
.../apache/tika/parser/netcdf/NetCDFParser.java | 11 +-
.../tika/parser/envi/EnviHeaderParserTest.java | 18 +-
.../apache/tika/parser/gdal/TestGDALParser.java | 19 +-
.../apache/tika/parser/grib/GribParserTest.java | 9 +-
.../org/apache/tika/parser/hdf/HDFParserTest.java | 14 +-
.../tika/parser/isatab/ISArchiveParserTest.java | 10 +-
.../tika/parser/netcdf/NetCDFParserTest.java | 9 +-
.../src/test/resources/2.4.0-no-tesseract.txt | 38 +-
.../src/test/resources/2.4.0-tesseract.txt | 38 +-
.../src/test/resources/2.4.1-no-tesseract.txt | 38 +-
.../src/test/resources/2.4.1-tesseract.txt | 38 +-
.../apache/tika/parser/geopkg/GeoPkgParser.java | 6 +-
.../tika/parser/sqlite3/SQLite3DBParser.java | 20 +-
.../apache/tika/parser/sqlite3/SQLite3Parser.java | 6 +-
.../tika/parser/sqlite3/SQLite3ParserTest.java | 7 +-
.../apache/tika/mime/TestMimeTypesExtended.java | 11 +-
.../tika/parser/sqlite3/SQLite3ParserTest.java | 29 +-
.../apache/tika/parser/ctakes/CTAKESParser.java | 6 +-
.../apache/tika/parser/geo/topic/GeoParser.java | 6 +-
.../apache/tika/parser/journal/JournalParser.java | 8 +-
.../apache/tika/parser/ner/NamedEntityParser.java | 8 +-
.../parser/sentiment/SentimentAnalysisParser.java | 6 +-
.../tika/parser/geo/topic/GeoParserTest.java | 13 +-
.../tika/parser/journal/JournalParserTest.java | 8 +-
.../org/apache/tika/parser/journal/TEITest.java | 6 +-
.../tika/parser/ner/NamedEntityParserTest.java | 7 +-
.../tika/parser/ner/nltk/NLTKNERecogniserTest.java | 4 +-
.../parser/ner/regex/RegexNERecogniserTest.java | 4 +-
.../sentiment/SentimentAnalysisParserTest.java | 12 +-
.../parser/transcribe/aws/AmazonTranscribe.java | 7 +-
.../apache/tika/detect/apple/BPListDetector.java | 23 +-
.../tika/parser/apple/AppleSingleFileParser.java | 51 +-
.../org/apache/tika/parser/apple/PListParser.java | 13 +-
.../tika/parser/iwork/IWorkPackageParser.java | 9 +-
.../parser/iwork/iwana/IWork13PackageParser.java | 19 +-
.../parser/iwork/iwana/IWork18PackageParser.java | 20 +-
.../apache/tika/parser/iwork/IWorkParserTest.java | 20 +-
.../tika/parser/iwork/iwana/IWork13ParserTest.java | 18 +-
.../tika-parser-audiovideo-module/pom.xml | 11 -
.../org/apache/tika/detect/MatroskaDetector.java | 14 +-
.../org/apache/tika/detect/ogg/OggDetector.java | 235 +++++++
.../org/apache/tika/parser/audio/AudioParser.java | 13 +-
.../org/apache/tika/parser/audio/MidiParser.java | 12 +-
.../java/org/apache/tika/parser/mp3/Mp3Parser.java | 9 +-
.../java/org/apache/tika/parser/mp4/MP4Parser.java | 60 +-
.../org/apache/tika/parser/ogg/FlacParser.java | 104 +++
.../org/apache/tika/parser/ogg/OggAudioParser.java | 158 +++++
.../java/org/apache/tika/parser/ogg/OggParser.java | 156 +++++
.../org/apache/tika/parser/ogg/OpusParser.java | 95 +++
.../org/apache/tika/parser/ogg/SpeexParser.java | 95 +++
.../org/apache/tika/parser/ogg/TheoraParser.java | 95 +++
.../org/apache/tika/parser/ogg/VorbisParser.java | 93 +++
.../org/apache/tika/parser/video/FLVParser.java | 8 +-
.../apache/tika/detect/MatroskaDetectorTest.java | 22 +-
.../org/apache/tika/parser/mp3/Mp3ParserTest.java | 5 +-
.../org/apache/tika/parser/mp3/MpegStreamTest.java | 15 +-
.../org/apache/tika/parser/dgn/DGN8Parser.java | 49 +-
.../java/org/apache/tika/parser/dwg/DWGParser.java | 79 +--
.../org/apache/tika/parser/dwg/DWGReadParser.java | 6 +-
.../java/org/apache/tika/parser/prt/PRTParser.java | 43 +-
.../org/apache/tika/parser/dwg/DWGParserTest.java | 66 +-
.../org/apache/tika/parser/prt/PRTParserTest.java | 11 +-
.../org/apache/tika/parser/asm/ClassParser.java | 6 +-
.../apache/tika/parser/code/SourceCodeParser.java | 10 +-
.../tika/parser/executable/ExecutableParser.java | 59 +-
.../executable/UniversalExecutableParser.java | 30 +-
.../java/org/apache/tika/parser/mat/MatParser.java | 138 ++--
.../org/apache/tika/parser/sas/SAS7BDATParser.java | 6 +-
.../tika/parser/code/SourceCodeParserTest.java | 3 +-
.../org/apache/tika/parser/mat/MatParserTest.java | 7 +-
.../apache/tika/parser/sas/SAS7BDATParserTest.java | 10 +-
.../org/apache/tika/parser/crypto/Pkcs7Parser.java | 15 +-
.../org/apache/tika/parser/crypto/TSDParser.java | 12 +-
.../apache/tika/parser/crypto/Pkcs7ParserTest.java | 7 +-
.../apache/tika/parser/crypto/TSDParserTest.java | 14 +-
.../tika/parser/font/AdobeFontMetricParser.java | 6 +-
.../apache/tika/parser/font/TrueTypeParser.java | 13 +-
.../apache/tika/parser/font/FontParsersTest.java | 8 +-
.../tika/parser/html/HtmlEncodingDetector.java | 14 +-
.../org/apache/tika/parser/html/JSoupParser.java | 17 +-
.../StandardHtmlEncodingDetector.java | 9 +-
.../tika/parser/html/HtmlEncodingDetectorTest.java | 5 +-
.../apache/tika/parser/html/HtmlParserTest.java | 315 ++++++----
.../html/StandardHtmlEncodingDetectorTest.java | 14 +-
.../tika/parser/image/AbstractImageParser.java | 7 +-
.../org/apache/tika/parser/image/ICNSParser.java | 10 +-
.../org/apache/tika/parser/image/JXLParser.java | 6 +-
.../org/apache/tika/parser/image/PSDParser.java | 43 +-
.../org/apache/tika/parser/image/WebPParser.java | 12 +-
.../apache/tika/parser/image/HeifParserTest.java | 33 +-
.../apache/tika/parser/image/ICNSParserTest.java | 14 +-
.../apache/tika/parser/image/ImageParserTest.java | 31 +-
.../apache/tika/parser/image/JpegParserTest.java | 50 +-
.../apache/tika/parser/image/PSDParserTest.java | 11 +-
.../apache/tika/parser/jdbc/AbstractDBParser.java | 12 +-
.../apache/tika/parser/jdbc/JDBCTableReader.java | 10 +-
.../org/apache/tika/parser/mail/RFC822Parser.java | 10 +-
.../org/apache/tika/parser/mbox/MboxParser.java | 5 +-
.../apache/tika/parser/mail/RFC822ParserTest.java | 52 +-
.../apache/tika/parser/mbox/MboxParserTest.java | 22 +-
.../detect/microsoft/POIFSContainerDetector.java | 50 +-
.../parser/microsoft/AbstractPOIFSExtractor.java | 6 +-
.../apache/tika/parser/microsoft/EMFParser.java | 5 +-
.../tika/parser/microsoft/ExcelExtractor.java | 4 +-
.../tika/parser/microsoft/HSLFExtractor.java | 16 +-
.../tika/parser/microsoft/JackcessParser.java | 4 +-
.../tika/parser/microsoft/MSOwnerFileParser.java | 12 +-
.../apache/tika/parser/microsoft/OfficeParser.java | 49 +-
.../tika/parser/microsoft/OldExcelParser.java | 6 +-
.../tika/parser/microsoft/OutlookExtractor.java | 6 +-
.../apache/tika/parser/microsoft/TNEFParser.java | 5 +-
.../apache/tika/parser/microsoft/WMFParser.java | 10 +-
.../tika/parser/microsoft/WordExtractor.java | 4 +-
.../microsoft/activemime/ActiveMimeParser.java | 29 +-
.../tika/parser/microsoft/chm/ChmParser.java | 5 +-
.../tika/parser/microsoft/libpst/LibPstParser.java | 17 +-
.../parser/microsoft/onenote/OneNoteParser.java | 18 +-
.../microsoft/onenote/OneNoteTreeWalker.java | 8 +-
.../microsoft/ooxml/AbstractOOXMLExtractor.java | 16 +-
.../microsoft/ooxml/OOXMLExtractorFactory.java | 14 +-
.../tika/parser/microsoft/ooxml/OOXMLParser.java | 6 +-
.../ooxml/SXSLFPowerPointExtractorDecorator.java | 5 +-
.../ooxml/SXWPFWordExtractorDecorator.java | 3 +-
.../ooxml/XWPFWordExtractorDecorator.java | 6 +-
.../microsoft/ooxml/xps/XPSExtractorDecorator.java | 7 +-
.../ooxml/xwpf/XWPFEventBasedWordExtractor.java | 3 +-
.../ooxml/xwpf/ml2006/BinaryDataHandler.java | 4 +-
.../ooxml/xwpf/ml2006/Word2006MLParser.java | 10 +-
.../parser/microsoft/pst/OutlookPSTParser.java | 8 +-
.../parser/microsoft/pst/PSTMailItemParser.java | 4 +-
.../parser/microsoft/rtf/RTFEmbObjHandler.java | 8 +-
.../tika/parser/microsoft/rtf/RTFParser.java | 7 +-
.../microsoft/xml/AbstractXML2003Parser.java | 9 +-
.../tika/parser/microsoft/xml/WordMLParser.java | 4 +-
.../microsoft/POIFSContainerDetectorTest.java | 35 +-
.../AbstractPOIContainerExtractionTest.java | 8 +-
.../tika/parser/microsoft/ExcelParserTest.java | 58 +-
.../tika/parser/microsoft/JackcessParserTest.java | 32 +-
.../tika/parser/microsoft/OfficeParserTest.java | 4 +-
.../tika/parser/microsoft/OldExcelParserTest.java | 12 +-
.../tika/parser/microsoft/OutlookParserTest.java | 26 +-
.../parser/microsoft/PowerPointParserTest.java | 22 +-
.../tika/parser/microsoft/ProjectParserTest.java | 18 +-
.../tika/parser/microsoft/PublisherParserTest.java | 9 +-
.../parser/microsoft/SolidworksParserTest.java | 27 +-
.../tika/parser/microsoft/TNEFParserTest.java | 8 +-
.../tika/parser/microsoft/VisioParserTest.java | 9 +-
.../tika/parser/microsoft/WordParserTest.java | 26 +-
.../parser/microsoft/WriteProtectedParserTest.java | 11 +-
.../parser/microsoft/chm/TestChmExtraction.java | 37 +-
.../parser/microsoft/chm/TestChmExtractor.java | 4 +-
.../parser/microsoft/ooxml/OOXMLParserTest.java | 29 +-
.../parser/microsoft/ooxml/SXSLFExtractorTest.java | 22 +-
.../parser/microsoft/ooxml/xps/XPSParserTest.java | 6 +-
.../apache/tika/detect/ole/MiscOLEDetector.java | 35 +-
.../java/org/apache/tika/parser/dbf/DBFParser.java | 11 +-
.../java/org/apache/tika/parser/dif/DIFParser.java | 9 +-
.../apache/tika/parser/epub/EpubContentParser.java | 14 +-
.../org/apache/tika/parser/epub/EpubParser.java | 160 +++--
.../org/apache/tika/parser/hwp/HwpV5Parser.java | 6 +-
.../apache/tika/parser/indesign/IDMLParser.java | 19 +-
.../java/org/apache/tika/parser/mif/MIFParser.java | 10 +-
.../tika/parser/odf/FlatOpenDocumentParser.java | 9 +-
.../tika/parser/odf/OpenDocumentContentParser.java | 19 +-
.../tika/parser/odf/OpenDocumentMetaParser.java | 6 +-
.../apache/tika/parser/odf/OpenDocumentParser.java | 116 ++--
.../tika/parser/wordperfect/QuattroProParser.java | 6 +-
.../tika/parser/wordperfect/WordPerfectParser.java | 6 +-
.../org/apache/tika/parser/dbf/DBFParserTest.java | 5 +-
.../org/apache/tika/parser/dif/DIFParserTest.java | 7 +-
.../apache/tika/parser/epub/EpubParserTest.java | 20 +-
.../org/apache/tika/parser/odf/ODFParserTest.java | 60 +-
.../parser/odf/OpenDocumentContentParserTest.java | 11 +-
.../tika/parser/wordperfect/WPInputStreamTest.java | 5 +-
.../org/apache/tika/parser/feed/FeedParser.java | 10 +-
.../apache/tika/parser/iptc/IptcAnpaParser.java | 9 +-
.../apache/tika/parser/feed/FeedParserTest.java | 15 +-
.../apache/tika/parser/ocr/TesseractOCRParser.java | 14 +-
.../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 8 +-
.../java/org/apache/tika/parser/pdf/PDFParser.java | 45 +-
.../tika/renderer/pdf/mutool/MuPDFRenderer.java | 5 +-
.../tika/renderer/pdf/pdfbox/PDFBoxRenderer.java | 6 +-
.../apache/tika/parser/pdf/CustomTikaXMPTest.java | 6 +-
.../org/apache/tika/parser/pdf/PDFParserTest.java | 60 +-
.../detect/gzip/GZipSpecializationDetector.java | 15 +-
.../apache/tika/parser/pkg/CompressorParser.java | 23 +-
.../org/apache/tika/parser/pkg/PackageParser.java | 41 +-
.../java/org/apache/tika/parser/pkg/RarParser.java | 4 +-
.../org/apache/tika/parser/pkg/UnrarParser.java | 5 +-
.../apache/tika/parser/pkg/AbstractPkgTest.java | 6 +-
.../org/apache/tika/parser/pkg/ArParserTest.java | 11 +-
.../apache/tika/parser/pkg/Bzip2ParserTest.java | 7 +-
.../apache/tika/parser/pkg/CompressParserTest.java | 7 +-
.../org/apache/tika/parser/pkg/GzipParserTest.java | 7 +-
.../org/apache/tika/parser/pkg/RarParserTest.java | 11 +-
.../apache/tika/parser/pkg/Seven7ParserTest.java | 7 +-
.../org/apache/tika/parser/pkg/TarParserTest.java | 7 +-
.../apache/tika/parser/pkg/UnrarParserTest.java | 7 +-
.../org/apache/tika/parser/pkg/ZipParserTest.java | 14 +-
.../org/apache/tika/parser/pkg/ZlibParserTest.java | 7 +-
.../apache/tika/parser/csv/TextAndCSVParser.java | 27 +-
.../tika/parser/strings/Latin1StringsParser.java | 17 +-
.../apache/tika/parser/strings/StringsParser.java | 13 +-
.../org/apache/tika/parser/txt/BOMDetector.java | 10 +-
.../tika/parser/txt/Icu4jEncodingDetector.java | 8 +-
.../java/org/apache/tika/parser/txt/TXTParser.java | 10 +-
.../tika/parser/txt/UniversalEncodingDetector.java | 14 +-
.../tika/parser/csv/TextAndCSVParserTest.java | 24 +-
.../parser/strings/Latin1StringsParserTest.java | 7 +-
.../tika/parser/strings/StringsParserTest.java | 9 +-
.../apache/tika/parser/txt/BOMDetectorTest.java | 15 +-
.../tika/parser/txt/CharsetDetectorTest.java | 19 +-
.../org/apache/tika/parser/txt/TXTParserTest.java | 77 ++-
.../org/apache/tika/parser/http/HttpParser.java | 13 +-
.../org/apache/tika/parser/wacz/WACZParser.java | 35 +-
.../org/apache/tika/parser/warc/WARCParser.java | 9 +-
.../java/org/apache/tika/parser/tmx/TMXParser.java | 12 +-
.../apache/tika/parser/xliff/XLIFF12Parser.java | 13 +-
.../org/apache/tika/parser/xliff/XLZParser.java | 31 +-
.../java/org/apache/tika/parser/xml/XMLParser.java | 9 +-
.../org/apache/tika/parser/xml/XMLProfiler.java | 13 +-
.../org/apache/tika/parser/tmx/TMXParserTest.java | 7 +-
.../tika/parser/xliff/XLIFF12ParserTest.java | 7 +-
.../apache/tika/parser/xliff/XLZParserTest.java | 12 +-
.../apache/tika/parser/xml/DcXMLParserTest.java | 11 +-
.../EmptyAndDuplicateElementsXMLParserTest.java | 11 +-
.../tika/parser/xml/FictionBookParserTest.java | 13 +-
.../parser/xml/TextAndAttributeXMLParserTest.java | 6 +-
.../tika/parser/xmp/JempboxExtractorTest.java | 30 +-
.../detect/zip/DefaultZipContainerDetector.java | 24 +-
.../DeprecatedStreamingZipContainerDetector.java | 15 +-
.../detect/zip/StreamingZipContainerDetector.java | 18 +-
.../apache/tika/detect/zip/ZipDetectionTest.java | 23 +-
.../apache/tika/config/TikaDetectorConfigTest.java | 6 +-
.../tika/detect/TestContainerAwareDetector.java | 44 +-
.../apache/tika/detect/TestDetectorLoading.java | 15 +-
.../org/apache/tika/detect/TestZipDetector.java | 10 +-
.../java/org/apache/tika/mime/OneOffMimeTest.java | 8 +-
.../java/org/apache/tika/mime/TestMimeTypes.java | 32 +-
.../java/org/apache/tika/ossfuzz/ParserFuzzer.java | 5 +-
.../apache/tika/parser/AutoDetectParserTest.java | 40 +-
.../tika/parser/AutoDetectReaderParserTest.java | 4 +-
.../tika/parser/RecursiveParserWrapperTest.java | 65 +-
.../java/org/apache/tika/parser/TestParsers.java | 10 +-
.../apache/tika/parser/TestXMLEntityExpansion.java | 8 +-
.../java/org/apache/tika/parser/XMLTestBase.java | 8 +-
.../parser/fork/ForkParserIntegrationTest.java | 33 +-
.../apache/tika/parser/image/JpegParserTest.java | 3 +-
.../apache/tika/parser/mail/MboxParserTest.java | 6 +-
.../apache/tika/parser/mail/RFC822ParserTest.java | 13 +-
.../parser/microsoft/ooxml/TruncatedOOXMLTest.java | 9 +-
.../apache/tika/parser/mock/MockParserTest.java | 3 +-
.../org/apache/tika/parser/pkg/ArParserTest.java | 11 +-
.../apache/tika/parser/pkg/Bzip2ParserTest.java | 7 +-
.../pkg/CompositeZipContainerDetectorTest.java | 41 +-
.../apache/tika/parser/pkg/CompressParserTest.java | 7 +-
.../org/apache/tika/parser/pkg/GzipParserTest.java | 11 +-
.../org/apache/tika/parser/pkg/RarParserTest.java | 7 +-
.../apache/tika/parser/pkg/Seven7ParserTest.java | 22 +-
.../org/apache/tika/parser/pkg/TarParserTest.java | 7 +-
.../org/apache/tika/parser/pkg/ZipParserTest.java | 9 +-
.../org/apache/tika/parser/pkg/ZlibParserTest.java | 7 +-
.../tika/parser/xml/FictionBookParserTest.java | 6 +-
.../org/apache/tika/sax/BoilerpipeHandlerTest.java | 2 +-
.../sax/PhoneExtractingContentHandlerTest.java | 3 +-
.../sax/StandardsExtractingContentHandlerTest.java | 9 +-
.../apache/tika/utils/ServiceLoaderUtilsTest.java | 2 +-
.../org/apache/tika/pipes/api/fetcher/Fetcher.java | 6 +-
.../tika/pipes/api/fetcher/RangeFetcher.java | 6 +-
.../tika/pipes/core/fetcher/EmptyFetcher.java | 4 +-
.../tika/pipes/core/server/FetchHandler.java | 11 +-
.../tika/pipes/core/server/ParseHandler.java | 21 +-
tika-pipes/tika-pipes-integration-tests/pom.xml | 2 +-
.../apache/tika/pipes/core/CrashingDetector.java | 4 +-
.../tika/pipes/fetcher/azblob/AZBlobFetcher.java | 3 +-
.../tika/pipes/fetcher/fs/FileSystemFetcher.java | 3 +-
.../apache/tika/pipes/fetcher/gcs/GCSFetcher.java | 3 +-
.../tika/pipes/fetcher/http/HttpFetcher.java | 8 +-
.../microsoftgraph/MicrosoftGraphFetcher.java | 5 +-
.../apache/tika/pipes/emitter/s3/S3Emitter.java | 8 +-
.../apache/tika/pipes/fetcher/s3/S3Fetcher.java | 11 +-
.../tika/config/loader/ComponentRegistry.java | 3 -
.../src/test/java/org/apache/tika/TikaTest.java | 694 ---------------------
.../tika/config/loader/ConfigurableTestParser.java | 4 +-
.../tika/config/loader/FallbackTestParser.java | 4 +-
.../tika/config/loader/MinimalTestParser.java | 4 +-
.../apache/tika/config/loader/OptInTestParser.java | 4 +-
.../apache/tika/config/loader/TikaLoaderTest.java | 35 +-
.../writefilter/StandardWriteFilterTest.java | 8 +-
.../tika/parser/external2/ExternalParserTest.java | 6 +-
.../server/core/DefaultInputStreamFactory.java | 7 +-
.../tika/server/core/FetcherStreamFactory.java | 5 +-
.../tika/server/core/InputStreamFactory.java | 5 +-
.../server/core/resource/MetadataResource.java | 27 +-
.../core/resource/RecursiveMetadataResource.java | 28 +-
.../tika/server/core/resource/TikaResource.java | 100 ++-
.../server/core/resource/UnpackerResource.java | 21 +-
.../standard/resource/XMPMetadataResource.java | 17 +-
.../tika/server/standard/TikaDetectorsTest.java | 2 +-
.../tika/server/standard/TikaMimeTypesTest.java | 2 +-
.../tika/server/standard/TikaParsersTest.java | 2 +-
.../tika/server/standard/UnpackerResourceTest.java | 13 +-
.../standard/UnpackerResourceWithConfigTest.java | 25 +-
419 files changed, 4558 insertions(+), 4511 deletions(-)
copy tika-core/src/{test/java/org/apache/tika/parser/mock =>
main/java/org/apache/tika/fork}/AutoDetectParserFactory.java (81%)
rename tika-core/src/main/java/org/apache/tika/{parser =>
fork}/ParserFactory.java (94%)
copy
tika-pipes/tika-pipes-api/src/main/java/org/apache/tika/pipes/api/emitter/StreamEmitter.java
=> tika-core/src/main/java/org/apache/tika/fork/ParserShim.java (68%)
copy
tika-integration-tests/tika-resource-loading-tests/src/test/java/org/apache/custom/parser/MyCustomParser.java
=> tika-core/src/main/java/org/apache/tika/fork/ParserWrapper.java (58%)
copy
tika-example/src/main/java/org/apache/tika/example/DisplayMetInstance.java =>
tika-core/src/main/java/org/apache/tika/fork/RPWShim.java (58%)
mode change 100755 => 100644
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/detect/ogg/OggDetector.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/ogg/FlacParser.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/ogg/OggAudioParser.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/ogg/OggParser.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/ogg/OpusParser.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/ogg/SpeexParser.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/ogg/TheoraParser.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/parser/ogg/VorbisParser.java
delete mode 100644
tika-serialization/src/test/java/org/apache/tika/TikaTest.java