This is an automated email from the ASF dual-hosted git repository.
ndipiazza pushed a commit to branch TIKA-4272-docker
in repository https://gitbox.apache.org/repos/asf/tika.git
commit 843a26b970ac86bfb92e5cf2787fa9bc0b17bbc6
Merge: 9fbaadfad 9543d034c
Author: Nicholas DiPiazza <ndipia...@apache.org>
AuthorDate: Sun Aug 18 10:08:59 2024 -0500
Merge branch 'main' of github.com:apache/tika into TIKA-4272-docker
.../src/main/java/org/apache/tika/gui/TikaGUI.java | 9 +-
.../test/java/org/apache/tika/bundle/BundleIT.java | 2 +-
.../main/java/org/apache/tika/config/Param.java | 7 +-
.../java/org/apache/tika/detect/MagicDetector.java | 3 +-
.../AbstractEmbeddedDocumentBytesHandler.java | 18 ++-
.../ParsingEmbeddedDocumentExtractor.java | 4 +-
.../java/org/apache/tika/io/TikaInputStream.java | 2 +-
.../java/org/apache/tika/metadata/Metadata.java | 19 ++-
.../main/java/org/apache/tika/mime/MagicMatch.java | 2 +-
.../main/java/org/apache/tika/mime/MimeTypes.java | 4 +-
.../tika/parser/external/ExternalParser.java | 4 +-
.../external/ExternalParsersConfigReader.java | 2 +-
.../java/org/apache/tika/pipes/PipesClient.java | 4 +-
.../org/apache/tika/pipes/PipesConfigBase.java | 3 +-
.../java/org/apache/tika/pipes/PipesServer.java | 8 +-
.../extractor/EmbeddedDocumentBytesConfig.java | 64 +++++-----
.../EmittingEmbeddedDocumentBytesHandler.java | 4 +-
.../pipesiterator/fs/FileSystemPipesIterator.java | 2 +-
.../org/apache/tika/parser/mock/MockParser.java | 2 +-
.../org/apache/tika/pipes/PipesServerTest.java | 6 +-
.../org/apache/tika/utils/ConcurrentUtilsTest.java | 20 +--
.../org/apache/tika/eval/app/reports/Report.java | 6 +-
.../eval/core/textstats/TextProfileSignature.java | 2 +-
.../java/org/apache/tika/example/MyFirstTika.java | 7 +-
.../java/org/apache/tika/example/RecentFiles.java | 2 +-
.../org/apache/tika/example/TIAParsingExample.java | 4 +-
.../apache/tika/example/TextStatsFromTikaEval.java | 1 -
.../org/apache/tika/fuzzing/cli/FuzzingCLI.java | 6 +-
tika-grpc/pom.xml | 6 +-
.../tika/langdetect/tika/LanguageIdentifier.java | 13 +-
.../langdetect/tika/LanguageProfilerBuilder.java | 11 +-
tika-parent/pom.xml | 31 ++---
.../geoinfo/GeographicInformationParser.java | 10 +-
.../apache/tika/parser/isatab/ISArchiveParser.java | 10 +-
.../tika/parser/sqlite3/SQLite3ParserTest.java | 3 +-
.../tika-parsers-ml/tika-age-recogniser/pom.xml | 138 ++++++++++++++++++++-
.../tika/dl/imagerec/DL4JInceptionV3Net.java | 17 +--
.../tika/parser/pot/PooledTimeSeriesParser.java | 5 +-
.../apache/tika/parser/ctakes/CTAKESConfig.java | 16 ++-
.../geo/topic/gazetteer/GeoGazetteerClient.java | 4 +-
.../apache/tika/parser/journal/TEIDOMParser.java | 22 +++-
.../tika/parser/ner/grobid/GrobidNERecogniser.java | 137 ++++++++++----------
.../tika/parser/iwork/AutoPageNumberUtils.java | 6 +-
.../parser/iwork/iwana/IWork13PackageParser.java | 2 +-
.../parser/iwork/iwana/IWork18PackageParser.java | 2 +-
.../tika/detect/apple/IWorkDetectorTest.java | 4 +-
.../java/org/apache/tika/parser/mp3/Mp3Parser.java | 2 +-
.../org/apache/tika/parser/video/FLVParser.java | 3 +-
.../tika/parser/dwg/DWGReadFormatRemover.java | 2 +-
.../apache/tika/parser/code/SourceCodeParser.java | 14 +--
.../org/apache/tika/parser/html/HtmlHandler.java | 8 +-
.../org/apache/tika/parser/html/JSoupParser.java | 2 +-
.../StandardHtmlEncodingDetector.java | 2 +-
.../tika/parser/image/ImageMetadataExtractor.java | 2 +-
.../org/apache/tika/parser/image/PSDParser.java | 4 +-
.../apache/tika/parser/jdbc/JDBCTableReader.java | 2 +-
.../tika/parser/mail/MailContentHandler.java | 2 +-
.../org/apache/tika/parser/mbox/MboxParser.java | 4 +-
.../detect/microsoft/ooxml/OPCPackageDetector.java | 5 +-
.../microsoft/MSEmbeddedStreamTranslator.java | 2 +-
.../tika/parser/microsoft/JackcessExtractor.java | 2 +-
.../apache/tika/parser/microsoft/OfficeParser.java | 4 +-
.../tika/parser/microsoft/OutlookExtractor.java | 6 +-
.../tika/parser/microsoft/chm/ChmItsfHeader.java | 5 +-
.../tika/parser/microsoft/chm/ChmItspHeader.java | 6 +-
.../tika/parser/microsoft/chm/ChmParser.java | 2 +-
.../tika/parser/microsoft/libpst/EmailVisitor.java | 3 +-
.../apache/tika/parser/microsoft/onenote/GUID.java | 2 +-
.../microsoft/onenote/OneNoteTreeWalker.java | 8 +-
.../parser/microsoft/onenote/PropertyValue.java | 2 +-
.../streamobj/RevisionManifestDataElementData.java | 3 +-
.../streamobj/StorageManifestDataElementData.java | 3 +-
.../streamobj/StreamObjectHeaderEnd16bit.java | 2 +-
.../onenote/fsshttpb/streamobj/basic/CellID.java | 5 +-
.../fsshttpb/streamobj/basic/CellIDArray.java | 3 +-
.../fsshttpb/streamobj/basic/ExGUIDArray.java | 3 +-
.../space/ObjectSpaceObjectStreamOfContextIDs.java | 3 +-
.../space/ObjectSpaceObjectStreamOfOIDs.java | 3 +-
.../space/ObjectSpaceObjectStreamOfOSIDs.java | 3 +-
.../ooxml/xwpf/ml2006/BinaryDataHandler.java | 4 +-
.../parser/microsoft/pst/PSTMailItemParser.java | 2 +-
.../parser/microsoft/rtf/RTFObjDataParser.java | 17 +--
.../parser/microsoft/ooxml/OOXMLParserTest.java | 15 +--
.../parser/microsoft/ooxml/TruncatedOOXMLTest.java | 6 +-
.../tika/parser/microsoft/rtf/RTFParserTest.java | 6 +-
.../java/org/apache/tika/parser/dbf/DBFCell.java | 3 +-
.../apache/tika/parser/dbf/DBFColumnHeader.java | 3 +-
.../org/apache/tika/parser/epub/EpubParser.java | 10 +-
.../org/apache/tika/parser/epub/OPFParser.java | 2 +-
.../apache/tika/parser/ocr/ImagePreprocessor.java | 2 +-
.../apache/tika/parser/ocr/TesseractOCRParser.java | 2 +-
.../apache/tika/parser/pdf/AbstractPDF2XHTML.java | 6 +-
.../java/org/apache/tika/parser/pdf/PDF2XHTML.java | 7 +-
.../java/org/apache/tika/parser/pdf/PDFParser.java | 4 +-
.../apache/tika/parser/pdf/PDFParserConfig.java | 2 +-
.../renderer/pdf/pdfbox/NoTextPDFRenderer.java | 2 +-
.../renderer/pdf/pdfbox/TextOnlyPDFRenderer.java | 2 +-
.../pdf/pdfbox/VectorGraphicsOnlyPDFRenderer.java | 2 +-
.../detect/gzip/GZipSpecializationDetector.java | 10 +-
.../apache/tika/parser/pkg/CompressorParser.java | 4 +-
.../org/apache/tika/parser/pkg/PackageParser.java | 15 ++-
.../org/apache/tika/parser/pkg/ZipParserTest.java | 3 +-
.../org/apache/tika/parser/txt/CharsetMatch.java | 34 +++--
.../tika/parser/txt/Icu4jEncodingDetector.java | 3 +-
.../apache/tika/parser/txt/BOMDetectorTest.java | 6 +-
.../org/apache/tika/parser/wacz/WACZParser.java | 6 +-
.../apache/tika/parser/xml/FictionBookParser.java | 2 +-
.../apache/tika/parser/xmp/JempboxExtractor.java | 7 +-
.../detect/zip/DefaultZipContainerDetector.java | 19 +--
.../tika/detect/zip/StreamingDetectContext.java | 2 +-
.../org/apache/tika/zip/utils/ZipSalvager.java | 6 +-
.../apache/tika/config/TikaDetectorConfigTest.java | 2 +-
.../java/org/apache/tika/mime/OneOffMimeTest.java | 2 +-
.../tika/parser/ocr/TesseractOCRParserTest.java | 2 +-
.../pkg/CompositeZipContainerDetectorTest.java | 6 +-
.../apache/tika/parser/pkg/PackageParserTest.java | 7 ++
.../testZipEntryNameCharsetShiftSJIS.zip | Bin 0 -> 330 bytes
.../tika/pipes/emitter/azblob/AZBlobEmitter.java | 17 +--
.../tika/pipes/emitter/jdbc/JDBCEmitter.java | 4 -
.../pipes/emitter/opensearch/OpenSearchClient.java | 2 +-
.../tika/pipes/fetcher/azblob/AZBlobFetcher.java | 6 +-
.../tika/pipes/fetcher/http/HttpFetcher.java | 70 +++++++++--
.../pipes/fetcher/http/config/HttpHeaders.java | 4 +
.../tika/pipes/fetcher/http/HttpFetcherTest.java | 9 ++
.../src/test/resources/tika-config-http.xml | 5 +-
.../tika-fetcher-microsoft-graph/pom.xml | 13 +-
.../pipes/pipesiterator/csv/CSVPipesIterator.java | 2 +-
.../pipes/reporters/jdbc/JDBCPipesReporter.java | 4 +-
.../reporters/opensearch/OpenSearchClient.java | 2 +-
.../apache/tika/serialization/JsonMetadata.java | 9 +-
.../tika/serialization/JsonMetadataList.java | 4 +-
.../serialization/ParseContextDeserializer.java | 78 ++++++++++++
.../tika/serialization/ParseContextSerializer.java | 5 +-
.../tika/serialization/TikaJsonDeserializer.java | 35 ++++--
.../tika/serialization/TikaJsonSerializer.java | 30 ++---
.../serialization/pipes/JsonFetchEmitTuple.java | 37 +-----
.../TestParseContextSerialization.java | 67 ++++++++++
.../pipes/JsonFetchEmitTupleTest.java | 1 -
.../apache/tika/server/client/TikaClientCLI.java | 2 +-
tika-server/tika-server-core/pom.xml | 2 +-
.../tika/server/core/FetcherStreamFactory.java | 2 +-
.../apache/tika/server/core/TikaServerConfig.java | 2 +-
.../tika/server/core/resource/TikaMimeTypes.java | 2 +-
.../tika/server/core/resource/TikaWelcome.java | 2 +-
.../server/core/resource/UnpackerResource.java | 4 +-
.../org/apache/tika/server/core/CXFTestBase.java | 71 ++++++-----
.../apache/tika/server/standard/TikaPipesTest.java | 54 ++++++--
147 files changed, 985 insertions(+), 569 deletions(-)
diff --cc tika-pipes/tika-fetchers/tika-fetcher-microsoft-graph/pom.xml
index 66951cf2c,8ea120051..9d5d28bf0
--- a/tika-pipes/tika-fetchers/tika-fetcher-microsoft-graph/pom.xml
+++ b/tika-pipes/tika-fetchers/tika-fetcher-microsoft-graph/pom.xml
@@@ -56,6 -58,16 +58,11 @@@
</exclusion>
</exclusions>
</dependency>
+ <dependency>
+ <groupId>com.azure</groupId>
+ <artifactId>azure-json</artifactId>
+ <version>${azure.json.version}</version>
+ </dependency>
- <dependency>
- <groupId>${project.groupId}</groupId>
- <artifactId>tika-core</artifactId>
- <version>${project.version}</version>
- </dependency>
<dependency>
<groupId>com.microsoft.graph</groupId>
<artifactId>microsoft-graph</artifactId>
