This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch TIKA-4769
in repository https://gitbox.apache.org/repos/asf/tika.git
from a8ad0ac685 improve metadata resiliency
add 5c650b18c4 Bump software.amazon.awssdk:bom from 2.46.17 to 2.46.21
(#2932)
add 767a8b2e33 Bump google-http-client.version from 2.1.0 to 2.1.1 (#2931)
add b0c946a61c Bump log4j2.version from 2.26.0 to 2.26.1 (#2930)
add 4cdd494f8a Bump com.diffplug.spotless:spotless-maven-plugin from 3.7.0
to 3.8.0 (#2929)
add 822c87c8bf Bump org.apache.groovy:groovy-all from 5.0.6 to 5.0.7
(#2928)
add efd000f9a6 Remove lombok e2e (#2925)
add 32ef64bc07 follow on updates to new MarkdownParser (#2926)
add 82534d9c98 this fixes split packages across the repo in 4.x (#2933)
add 77c4c23044 TIKA-4327: update aws, jackcess, netty
add daa1473b52 Merge branch 'main' into TIKA-4769
No new revisions were added by this update.
Summary of changes:
.github/scripts/check_split_packages.py | 69 +++++++++++++++++++
.../workflows/split-packages.yml | 20 +++++-
.../ROOT/pages/advanced/language-detection.adoc | 2 +-
.../ROOT/pages/developers/serialization.adoc | 2 +-
.../tika/{config => annotation}/TikaComponent.java | 2 +-
.../tika/annotation/TikaComponentProcessor.java | 3 +-
.../java/org/apache/tika/cli/TikaCLIAsyncTest.java | 2 +-
.../org/apache/tika/config/EmbeddedLimits.java | 2 +-
.../java/org/apache/tika/config/OutputLimits.java | 2 +-
.../java/org/apache/tika/config/TimeoutLimits.java | 2 +-
.../java/org/apache/tika/detect/BOMDetector.java | 2 +-
.../org/apache/tika/detect/DefaultDetector.java | 2 +-
.../java/org/apache/tika/detect/EmptyDetector.java | 2 +-
.../apache/tika/detect/FileCommandDetector.java | 2 +-
.../java/org/apache/tika/detect/MagicDetector.java | 2 +-
.../tika/detect/MetadataCharsetDetector.java | 2 +-
.../tika/detect/OverrideEncodingDetector.java | 2 +-
.../extractor/SkipEmbeddedDocumentSelector.java | 2 +-
.../tika/extractor/StandardExtractorFactory.java | 2 +-
.../java/org/apache/tika/io/SpoolingStrategy.java | 2 +-
.../tika/language/translate/DefaultTranslator.java | 2 +-
.../tika/language/translate/EmptyTranslator.java | 2 +-
.../filter/CaptureGroupMetadataFilter.java | 2 +-
.../ClearByAttachmentTypeMetadataFilter.java | 2 +-
.../filter/DateNormalizingMetadataFilter.java | 2 +-
.../filter/ExcludeFieldMetadataFilter.java | 2 +-
.../metadata/filter/FieldNameMappingFilter.java | 2 +-
.../metadata/filter/GeoPointMetadataFilter.java | 2 +-
.../filter/IncludeFieldMetadataFilter.java | 2 +-
.../apache/tika/metadata/filter/NoOpFilter.java | 2 +-
.../filter/RemoveByMimeMetadataFilter.java | 2 +-
.../StandardMetadataLimiterFactory.java | 2 +-
.../main/java/org/apache/tika/mime/MimeTypes.java | 2 +-
.../apache/tika/parser/AutoDetectParserConfig.java | 2 +-
.../java/org/apache/tika/parser/DefaultParser.java | 2 +-
.../java/org/apache/tika/parser/EmptyParser.java | 2 +-
.../java/org/apache/tika/parser/ErrorParser.java | 2 +-
.../org/apache/tika/parser/RegexCaptureParser.java | 2 +-
.../apache/tika/parser/SimplePasswordProvider.java | 2 +-
.../tika/parser/external/ExternalParser.java | 2 +-
.../tika/sax/BasicContentHandlerFactory.java | 2 +-
.../java/org/apache/tika/sax/SAXOutputConfig.java | 2 +-
.../apache/tika/detect/magika/MagikaDetector.java | 2 +-
.../tika/detect/siegfried/SiegfriedDetector.java | 2 +-
tika-e2e-tests/pom.xml | 17 -----
tika-e2e-tests/tika-grpc/pom.xml | 7 --
.../org/apache/tika/pipes/ExternalTestBase.java | 43 ++++++------
.../pipes/filesystem/FileSystemFetcherTest.java | 24 +++----
.../tika/pipes/filesystem/HandlerTypeTest.java | 41 ++++++------
.../tika/pipes/ignite/IgniteConfigStoreTest.java | 77 +++++++++++-----------
.../html/HtmlEncodingDetector.java | 4 +-
.../html/TikaHtmlCharsetAliases.java | 2 +-
.../StandardHtmlEncodingDetector.java | 4 +-
.../org.apache.tika.detect.EncodingDetector | 2 +-
.../html/StandardCharsets_unsupported_by_IANA.txt | 0
.../tika/parser/html/HtmlEncodingDetectorTest.java | 3 +-
.../tika-encoding-detector-icu4j/pom.xml | 2 +-
.../txt => detect/icu4j}/CharsetDetector.java | 2 +-
.../{parser/txt => detect/icu4j}/CharsetMatch.java | 2 +-
.../txt => detect/icu4j}/CharsetRecog_2022.java | 2 +-
.../txt => detect/icu4j}/CharsetRecog_UTF8.java | 2 +-
.../txt => detect/icu4j}/CharsetRecog_Unicode.java | 2 +-
.../txt => detect/icu4j}/CharsetRecog_mbcs.java | 2 +-
.../txt => detect/icu4j}/CharsetRecog_sbcs.java | 2 +-
.../txt => detect/icu4j}/CharsetRecognizer.java | 2 +-
.../icu4j}/Icu4jEncodingDetector.java | 4 +-
.../tika/parser/txt/CharsetDetectorTest.java | 3 +-
.../ml/chardetect/MojibusterEncodingDetector.java | 2 +-
.../Utf16SpecialistEncodingDetector.java | 2 +-
.../universal}/UniversalEncodingDetector.java | 4 +-
.../universal}/UniversalEncodingListener.java | 2 +-
.../eval/core/metadata/TikaEvalMetadataFilter.java | 2 +-
.../tika/eval/core/tokens/TikaEvalTokenizer.java | 4 +-
.../core/tokens/tools/CommonTokenGenerator.java | 4 +-
.../apache/tika/pipes/grpc/TikaGrpcServerTest.java | 2 +-
.../elasticsearch/tests/ElasticsearchTest.java | 2 +-
.../tika/pipes/kafka/tests/TikaPipesKafkaTest.java | 2 +-
.../pipes/opensearch/tests/OpenSearchTest.java | 2 +-
.../tika/pipes/s3/tests/S3PipeIntegrationTest.java | 2 +-
.../pipes/solr/tests/TikaPipesSolrTestBase.java | 2 +-
.../{ => core}/CharSoupFeatureExtractor.java | 4 +-
.../charsoup/{ => core}/CharSoupModel.java | 2 +-
.../charsoup/{ => core}/FeatureExtractor.java | 2 +-
.../{ => core}/SaltedNgramFeatureExtractor.java | 2 +-
.../{ => core}/ScriptAwareFeatureExtractor.java | 4 +-
.../charsoup/{ => core}/ScriptCategory.java | 2 +-
.../{ => core}/ShortTextFeatureExtractor.java | 4 +-
.../charsoup/{ => core}/WordTokenizer.java | 2 +-
.../charsoup/CharSoupLanguageDetector.java | 7 +-
.../charsoup/CharSoupMetadataFilter.java | 4 +-
.../charsoup/CharSoupModelRoutingTest.java | 1 -
.../langdetect/charsoup/LangIdRegressionTest.java | 1 -
.../langdetect/charsoup/SjisLangSignalTest.java | 1 -
.../{ => core}/CharSoupFeatureExtractorTest.java | 4 +-
.../charsoup/{ => core}/CharSoupModelTest.java | 4 +-
.../ScriptAwareFeatureExtractorTest.java | 4 +-
.../charsoup/{ => core}/WordTokenizerTest.java | 4 +-
.../langdetect/charsoup/tools/AblationRunner.java | 4 +-
.../charsoup/tools/BucketSaturationAnalyzer.java | 2 +-
.../charsoup/tools/CalibrateConfidence.java | 4 +-
.../charsoup/tools/CompareDetectors.java | 2 +-
.../langdetect/charsoup/tools/ConfusionDumper.java | 4 +-
.../langdetect/charsoup/tools/CrossDomainEval.java | 6 +-
.../charsoup/tools/DiagnoseUnknownScript.java | 4 +-
.../charsoup/tools/KoreanFalsePositives.java | 6 +-
.../langdetect/charsoup/tools/ModelQuantizer.java | 2 +-
.../langdetect/charsoup/tools/Phase2SmokeTest.java | 2 +-
.../langdetect/charsoup/tools/Phase2Trainer.java | 6 +-
.../langdetect/charsoup/tools/PrepareCorpus.java | 2 +-
.../langdetect/charsoup/tools/PrintDiscLabels.java | 2 +-
.../langdetect/charsoup/tools/QuickF1Eval.java | 4 +-
.../charsoup/tools/ResearchFeatureExtractor.java | 12 ++--
.../charsoup/tools/TrainLanguageModel.java | 6 +-
.../tika/langdetect/opennlp/OpenNLPDetector.java | 2 +-
.../metadatafilter/OpenNLPMetadataFilter.java | 2 +-
.../optimaize/OptimaizeLangDetector.java | 2 +-
.../metadatafilter/OptimaizeMetadataFilter.java | 2 +-
.../tools/BenchmarkCharsetDetectors.java | 4 +-
.../ml/chardetect/tools/EvalCharsetDetectors.java | 4 +-
.../ml/junkdetect/JunkFilterEncodingDetector.java | 2 +-
tika-parent/pom.xml | 11 ++--
.../tika/parser/ocrencode/EncodeOCRParser.java | 2 +-
.../apache/tika/parser/envi/EnviHeaderParser.java | 2 +-
.../org/apache/tika/parser/gdal/GDALParser.java | 2 +-
.../geoinfo/GeographicInformationParser.java | 2 +-
.../org/apache/tika/parser/grib/GribParser.java | 2 +-
.../java/org/apache/tika/parser/hdf/HDFParser.java | 2 +-
.../apache/tika/parser/isatab/ISArchiveParser.java | 2 +-
.../apache/tika/parser/netcdf/NetCDFParser.java | 2 +-
.../apache/tika/parser/geopkg/GeoPkgParser.java | 2 +-
.../apache/tika/parser/sqlite3/SQLite3Parser.java | 2 +-
.../apache/tika/inference/JinaEmbeddingFilter.java | 2 +-
.../tika/inference/OpenAIEmbeddingFilter.java | 2 +-
.../tika/inference/OpenAIImageEmbeddingParser.java | 2 +-
.../tika-parsers-ml/tika-parser-nlp-module/pom.xml | 2 +-
.../apache/tika/parser/geo/topic/GeoParser.java | 2 +-
.../tika/parser/journal/GrobidRESTParser.java | 2 +-
.../apache/tika/parser/journal/JournalParser.java | 2 +-
.../apache/tika/parser/ner/NamedEntityParser.java | 2 +-
.../tika/parser/ocr/tess4j/Tess4JParser.java | 2 +-
.../tika-parsers-ml/tika-transcribe-aws/pom.xml | 1 -
.../parser/transcribe/aws/AmazonTranscribe.java | 2 +-
.../apache/tika/parser/vlm/ClaudeVLMParser.java | 2 +-
.../apache/tika/parser/vlm/GeminiVLMParser.java | 2 +-
.../apache/tika/parser/vlm/OpenAIVLMParser.java | 2 +-
.../tika/config/TikaEncodingDetectorTest.java | 2 +-
.../apache/tika/detect/TestDetectorLoading.java | 8 +--
.../DoublingContentHandlerDecoratorFactory.java | 2 +-
.../UpcasingContentHandlerDecoratorFactory.java | 2 +-
.../apache/tika/detect/apple/BPListDetector.java | 2 +-
.../tika/parser/apple/AppleSingleFileParser.java | 2 +-
.../org/apache/tika/parser/apple/PListParser.java | 2 +-
.../tika/parser/iwork/IWorkPackageParser.java | 2 +-
.../parser/iwork/iwana/IWork13PackageParser.java | 2 +-
.../parser/iwork/iwana/IWork18PackageParser.java | 2 +-
.../tika/detect/{ => mkv}/MatroskaDetector.java | 6 +-
.../org/apache/tika/detect/ogg/OggDetector.java | 2 +-
.../org/apache/tika/parser/audio/AudioParser.java | 2 +-
.../org/apache/tika/parser/audio/MidiParser.java | 2 +-
.../java/org/apache/tika/parser/mp3/Mp3Parser.java | 2 +-
.../java/org/apache/tika/parser/mp4/MP4Parser.java | 2 +-
.../org/apache/tika/parser/ogg/FlacParser.java | 2 +-
.../java/org/apache/tika/parser/ogg/OggParser.java | 2 +-
.../org/apache/tika/parser/ogg/OpusParser.java | 2 +-
.../org/apache/tika/parser/ogg/SpeexParser.java | 2 +-
.../org/apache/tika/parser/ogg/TheoraParser.java | 2 +-
.../org/apache/tika/parser/ogg/VorbisParser.java | 2 +-
.../org/apache/tika/parser/video/FLVParser.java | 2 +-
.../apache/tika/detect/MatroskaDetectorTest.java | 3 +-
.../org/apache/tika/parser/dgn/DGN8Parser.java | 2 +-
.../java/org/apache/tika/parser/dwg/DWGParser.java | 2 +-
.../org/apache/tika/parser/dwg/DWGReadParser.java | 2 +-
.../java/org/apache/tika/parser/prt/PRTParser.java | 2 +-
.../org/apache/tika/parser/asm/ClassParser.java | 2 +-
.../apache/tika/parser/code/SourceCodeParser.java | 2 +-
.../tika/parser/executable/ExecutableParser.java | 2 +-
.../executable/UniversalExecutableParser.java | 2 +-
.../java/org/apache/tika/parser/mat/MatParser.java | 2 +-
.../org/apache/tika/parser/sas/SAS7BDATParser.java | 2 +-
.../org/apache/tika/parser/crypto/Pkcs7Parser.java | 2 +-
.../org/apache/tika/parser/crypto/TSDParser.java | 2 +-
.../digestutils/BouncyCastleDigesterFactory.java | 2 +-
.../parser/digestutils/CommonsDigesterFactory.java | 2 +-
.../tika/parser/font/AdobeFontMetricParser.java | 2 +-
.../apache/tika/parser/font/TrueTypeParser.java | 2 +-
.../org/apache/tika/parser/html/JSoupParser.java | 2 +-
.../org/apache/tika/parser/image/BPGParser.java | 2 +-
.../org/apache/tika/parser/image/HeifParser.java | 2 +-
.../org/apache/tika/parser/image/ICNSParser.java | 2 +-
.../org/apache/tika/parser/image/ImageParser.java | 2 +-
.../org/apache/tika/parser/image/JXLParser.java | 2 +-
.../org/apache/tika/parser/image/JpegParser.java | 2 +-
.../org/apache/tika/parser/image/PSDParser.java | 2 +-
.../org/apache/tika/parser/image/TiffParser.java | 2 +-
.../org/apache/tika/parser/image/WebPParser.java | 2 +-
.../org/apache/tika/parser/mail/RFC822Parser.java | 2 +-
.../org/apache/tika/parser/mbox/MboxParser.java | 2 +-
.../detect/microsoft/POIFSContainerDetector.java | 2 +-
.../apache/tika/parser/microsoft/EMFParser.java | 2 +-
.../tika/parser/microsoft/JackcessParser.java | 2 +-
.../tika/parser/microsoft/MSOwnerFileParser.java | 2 +-
.../apache/tika/parser/microsoft/OfficeParser.java | 2 +-
.../tika/parser/microsoft/OldExcelParser.java | 2 +-
.../apache/tika/parser/microsoft/TNEFParser.java | 2 +-
.../apache/tika/parser/microsoft/WMFParser.java | 2 +-
.../microsoft/activemime/ActiveMimeParser.java | 2 +-
.../tika/parser/microsoft/chm/ChmParser.java | 2 +-
.../tika/parser/microsoft/libpst/LibPstParser.java | 2 +-
.../parser/microsoft/onenote/OneNoteParser.java | 2 +-
.../tika/parser/microsoft/ooxml/OOXMLParser.java | 2 +-
.../ooxml/xwpf/ml2006/Word2006MLParser.java | 2 +-
.../parser/microsoft/pst/OutlookPSTParser.java | 2 +-
.../parser/microsoft/pst/PSTMailItemParser.java | 2 +-
.../tika/parser/microsoft/rtf/RTFParser.java | 2 +-
.../parser/microsoft/xml/SpreadsheetMLParser.java | 2 +-
.../tika/parser/microsoft/xml/WordMLParser.java | 2 +-
.../apache/tika/detect/ole/MiscOLEDetector.java | 2 +-
.../java/org/apache/tika/parser/dbf/DBFParser.java | 2 +-
.../java/org/apache/tika/parser/dif/DIFParser.java | 2 +-
.../org/apache/tika/parser/epub/EpubParser.java | 2 +-
.../org/apache/tika/parser/hwp/HwpV5Parser.java | 2 +-
.../apache/tika/parser/indesign/IDMLParser.java | 2 +-
.../java/org/apache/tika/parser/mif/MIFParser.java | 2 +-
.../tika/parser/odf/FlatOpenDocumentParser.java | 2 +-
.../apache/tika/parser/odf/OpenDocumentParser.java | 2 +-
.../tika/parser/wordperfect/QuattroProParser.java | 2 +-
.../tika/parser/wordperfect/WordPerfectParser.java | 2 +-
.../org/apache/tika/parser/feed/FeedParser.java | 2 +-
.../apache/tika/parser/iptc/IptcAnpaParser.java | 2 +-
.../tika/parser/ocr/{tess4j => }/ImageDeskew.java | 2 +-
.../apache/tika/parser/ocr/ImagePreprocessor.java | 1 -
.../tika/parser/ocr/{tess4j => }/ImageUtil.java | 2 +-
.../apache/tika/parser/ocr/TesseractOCRParser.java | 2 +-
.../java/org/apache/tika/parser/pdf/PDFParser.java | 2 +-
.../tika/renderer/pdf/pdfbox/PDFBoxRenderer.java | 2 +-
.../tika/renderer/pdf/poppler/PopplerRenderer.java | 2 +-
.../detect/gzip/GZipSpecializationDetector.java | 2 +-
.../apache/tika/parser/pkg/CompressorParser.java | 2 +-
.../org/apache/tika/parser/pkg/PackageParser.java | 2 +-
.../java/org/apache/tika/parser/pkg/RarParser.java | 2 +-
.../org/apache/tika/parser/pkg/SevenZParser.java | 2 +-
.../org/apache/tika/parser/pkg/UnrarParser.java | 2 +-
.../java/org/apache/tika/parser/pkg/ZipParser.java | 2 +-
.../apache/tika/parser/csv/TextAndCSVParser.java | 2 +-
.../tika/parser/markdown/MarkdownParser.java | 14 +++-
.../tika/parser/strings/Latin1StringsParser.java | 2 +-
.../apache/tika/parser/strings/StringsParser.java | 2 +-
.../java/org/apache/tika/parser/txt/TXTParser.java | 2 +-
.../tika/parser/markdown/MarkdownParserTest.java | 8 +++
.../org/apache/tika/parser/http/HttpParser.java | 2 +-
.../org/apache/tika/parser/wacz/WACZParser.java | 2 +-
.../org/apache/tika/parser/warc/WARCParser.java | 2 +-
.../java/org/apache/tika/parser/tmx/TMXParser.java | 2 +-
.../apache/tika/parser/xliff/XLIFF12Parser.java | 2 +-
.../org/apache/tika/parser/xliff/XLZParser.java | 2 +-
.../org/apache/tika/parser/xml/DcXMLParser.java | 2 +-
.../apache/tika/parser/xml/FictionBookParser.java | 2 +-
.../java/org/apache/tika/parser/xml/XMLParser.java | 2 +-
.../org/apache/tika/parser/xml/XMLProfiler.java | 2 +-
.../detect/zip/DefaultZipContainerDetector.java | 2 +-
.../apache/tika/async/cli/AsyncProcessorTest.java | 2 +-
.../java/org/apache/tika/pipes/api/ParseMode.java | 2 +-
.../core/extractor/StandardUnpackSelector.java | 2 +-
.../tika/pipes/core/extractor/UnpackConfig.java | 2 +-
.../core/extractor/UnpackExtractorFactory.java | 2 +-
.../filter/AttachmentCountingListFilter.java | 2 +-
.../tika/metadata/filter/MockUpperCaseFilter.java | 2 +-
.../apache/tika/pipes/core/CrashingDetector.java | 2 +-
.../apache/tika/pipes/core/MockPassbackFilter.java | 2 +-
.../apache/tika/pipes/core/PluginsTestHelper.java | 2 +-
.../pipes/core/emitter/EmitterManagerTest.java | 2 +-
.../pipes/core/fetcher/FetcherManagerTest.java | 2 +-
.../tika-pipes-google-drive/pom.xml | 2 +-
.../org/apache/tika/config/loader/TikaLoader.java | 2 +-
.../{ => serialization}/config/GlobalSettings.java | 2 +-
.../config/JsonConfigHelper.java | 2 +-
.../apache/tika/config/JsonConfigHelperTest.java | 3 +-
.../tika/config/loader/ConfigurableTestParser.java | 2 +-
.../tika/config/loader/FallbackTestParser.java | 2 +-
.../tika/config/loader/MinimalTestParser.java | 2 +-
.../apache/tika/config/loader/OptInTestParser.java | 2 +-
.../apache/tika/digest/MockDigesterFactory.java | 2 +-
.../filter/AttachmentCountingListFilter.java | 2 +-
.../tika/metadata/filter/JsonConfigOnlyFilter.java | 2 +-
.../tika/metadata/filter/MockUpperCaseFilter.java | 2 +-
.../tika/sax/UppercasingContentHandlerFactory.java | 2 +-
.../org/apache/tika/server/core/CXFTestBase.java | 2 +-
.../apache/tika/server/core/StackTraceTest.java | 2 +-
.../tika/server/standard/UnpackerResourceTest.java | 2 +-
.../standard/UnpackerResourceWithConfigTest.java | 2 +-
tika-translate/pom.xml | 6 --
.../language/translate/impl/CachedTranslator.java | 2 +-
.../language/translate/impl/GoogleTranslator.java | 2 +-
.../translate/impl/JoshuaNetworkTranslator.java | 2 +-
.../language/translate/impl/Lingo24Translator.java | 2 +-
.../language/translate/impl/MarianTranslator.java | 2 +-
.../translate/impl/MicrosoftTranslator.java | 2 +-
.../language/translate/impl/MosesTranslator.java | 2 +-
.../language/translate/impl/RTGTranslator.java | 2 +-
.../language/translate/impl/YandexTranslator.java | 2 +-
300 files changed, 532 insertions(+), 462 deletions(-)
create mode 100644 .github/scripts/check_split_packages.py
copy tika-example/src/test/resources/junit-platform.properties =>
.github/workflows/split-packages.yml (68%)
rename tika-annotation-processor/src/main/java/org/apache/tika/{config =>
annotation}/TikaComponent.java (99%)
rename
tika-encoding-detectors/tika-encoding-detector-html/src/main/java/org/apache/tika/{parser
=> detect}/html/HtmlEncodingDetector.java (99%)
rename
tika-encoding-detectors/tika-encoding-detector-html/src/main/java/org/apache/tika/{parser
=> detect}/html/TikaHtmlCharsetAliases.java (99%)
rename
tika-encoding-detectors/tika-encoding-detector-html/src/main/resources/org/apache/tika/{parser
=> detect}/html/StandardCharsets_unsupported_by_IANA.txt (100%)
rename
tika-encoding-detectors/tika-encoding-detector-icu4j/src/main/java/org/apache/tika/{parser/txt
=> detect/icu4j}/CharsetDetector.java (99%)
rename
tika-encoding-detectors/tika-encoding-detector-icu4j/src/main/java/org/apache/tika/{parser/txt
=> detect/icu4j}/CharsetMatch.java (99%)
rename
tika-encoding-detectors/tika-encoding-detector-icu4j/src/main/java/org/apache/tika/{parser/txt
=> detect/icu4j}/CharsetRecog_2022.java (99%)
rename
tika-encoding-detectors/tika-encoding-detector-icu4j/src/main/java/org/apache/tika/{parser/txt
=> detect/icu4j}/CharsetRecog_UTF8.java (98%)
rename
tika-encoding-detectors/tika-encoding-detector-icu4j/src/main/java/org/apache/tika/{parser/txt
=> detect/icu4j}/CharsetRecog_Unicode.java (99%)
rename
tika-encoding-detectors/tika-encoding-detector-icu4j/src/main/java/org/apache/tika/{parser/txt
=> detect/icu4j}/CharsetRecog_mbcs.java (99%)
rename
tika-encoding-detectors/tika-encoding-detector-icu4j/src/main/java/org/apache/tika/{parser/txt
=> detect/icu4j}/CharsetRecog_sbcs.java (99%)
rename
tika-encoding-detectors/tika-encoding-detector-icu4j/src/main/java/org/apache/tika/{parser/txt
=> detect/icu4j}/CharsetRecognizer.java (98%)
rename
tika-encoding-detectors/tika-encoding-detector-icu4j/src/main/java/org/apache/tika/{parser/txt
=> detect/icu4j}/Icu4jEncodingDetector.java (98%)
rename
tika-encoding-detectors/tika-encoding-detector-universal/src/main/java/org/apache/tika/{parser/txt
=> detect/universal}/UniversalEncodingDetector.java (97%)
rename
tika-encoding-detectors/tika-encoding-detector-universal/src/main/java/org/apache/tika/{parser/txt
=> detect/universal}/UniversalEncodingListener.java (98%)
rename
tika-langdetect/tika-langdetect-charsoup-core/src/main/java/org/apache/tika/langdetect/charsoup/{
=> core}/CharSoupFeatureExtractor.java (99%)
rename
tika-langdetect/tika-langdetect-charsoup-core/src/main/java/org/apache/tika/langdetect/charsoup/{
=> core}/CharSoupModel.java (99%)
rename
tika-langdetect/tika-langdetect-charsoup-core/src/main/java/org/apache/tika/langdetect/charsoup/{
=> core}/FeatureExtractor.java (98%)
rename
tika-langdetect/tika-langdetect-charsoup-core/src/main/java/org/apache/tika/langdetect/charsoup/{
=> core}/SaltedNgramFeatureExtractor.java (99%)
rename
tika-langdetect/tika-langdetect-charsoup-core/src/main/java/org/apache/tika/langdetect/charsoup/{
=> core}/ScriptAwareFeatureExtractor.java (99%)
rename
tika-langdetect/tika-langdetect-charsoup-core/src/main/java/org/apache/tika/langdetect/charsoup/{
=> core}/ScriptCategory.java (99%)
rename
tika-langdetect/tika-langdetect-charsoup-core/src/main/java/org/apache/tika/langdetect/charsoup/{
=> core}/ShortTextFeatureExtractor.java (99%)
rename
tika-langdetect/tika-langdetect-charsoup-core/src/main/java/org/apache/tika/langdetect/charsoup/{
=> core}/WordTokenizer.java (99%)
rename
tika-langdetect/tika-langdetect-charsoup/src/test/java/org/apache/tika/langdetect/charsoup/{
=> core}/CharSoupFeatureExtractorTest.java (99%)
rename
tika-langdetect/tika-langdetect-charsoup/src/test/java/org/apache/tika/langdetect/charsoup/{
=> core}/CharSoupModelTest.java (99%)
rename
tika-langdetect/tika-langdetect-charsoup/src/test/java/org/apache/tika/langdetect/charsoup/{
=> core}/ScriptAwareFeatureExtractorTest.java (99%)
rename
tika-langdetect/tika-langdetect-charsoup/src/test/java/org/apache/tika/langdetect/charsoup/{
=> core}/WordTokenizerTest.java (99%)
rename
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-audiovideo-module/src/main/java/org/apache/tika/detect/{
=> mkv}/MatroskaDetector.java (96%)
rename
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/{tess4j
=> }/ImageDeskew.java (99%)
rename
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-ocr-module/src/main/java/org/apache/tika/parser/ocr/{tess4j
=> }/ImageUtil.java (98%)
rename tika-serialization/src/main/java/org/apache/tika/{ =>
serialization}/config/GlobalSettings.java (98%)
rename tika-serialization/src/main/java/org/apache/tika/{ =>
serialization}/config/JsonConfigHelper.java (99%)
