This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch metadata-key-format-kebab
in repository https://gitbox.apache.org/repos/asf/tika.git
from f3ca90885d Step 2 -- push kebab formatting in more parsers
add 4b72b0c49a kebab parser-module keys the interface pass missed
add bc3658a30d TIKA-4327: update aws, azure, grpc
add 379b32246f TIKA-4327: update microsoft-graph
add 711be693d4 TIKA-4327: update jar plugin, junrar, sqlite
add 6f966a22d1 TIKA-4327: update aws, ddplist, opennlp
add a94d44c38e Bump joda-time:joda-time from 2.14.2 to 2.14.3 (#2966)
add a2275e2ebf Bump com.github.luben:zstd-jni from 1.5.7-11 to 1.5.7-12
(#2967)
add 65a2f3ab6f TIKA-4796: compile MagicDetector regex once at construction
(#2968)
add c2ab806dcf TIKA-4797 - Metadata key registry (#2970)
add 80275fe8af TIKA-4794 - Metadata key passthrough (#2971)
add 63315d85ad Merge branch 'main' into metadata-key-format-kebab
add 680ec128dc TIKA-4794: convert remaining bare-String metadata keys to
Property; regenerate registries
No new revisions were added by this update.
Summary of changes:
.skills/dev.md | 11 +
.skills/metadata-schema.md | 77 +++
CHANGES.txt | 5 +
.../pages/migration-to-4x/metadata-changes-4x.adoc | 17 +
pom.xml | 1 +
.../test/java/org/apache/tika/cli/TikaCLITest.java | 6 +-
.../java/org/apache/tika/detect/MagicDetector.java | 35 +-
.../java/org/apache/tika/digest/DigestDef.java | 2 +-
.../main/java/org/apache/tika/metadata/DWG.java | 3 +
.../main/java/org/apache/tika/metadata/HTML.java | 3 +
.../java/org/apache/tika/metadata/HttpHeaders.java | 16 +-
.../main/java/org/apache/tika/metadata/MAPI.java | 1 +
.../java/org/apache/tika/metadata/Message.java | 46 +-
.../java/org/apache/tika/metadata/Metadata.java | 9 +
.../main/java/org/apache/tika/metadata/Office.java | 3 +
.../main/java/org/apache/tika/metadata/PDF.java | 3 +
.../apache/tika/metadata/PassthroughPrefix.java | 79 +++
.../java/org/apache/tika/metadata/RTFMetadata.java | 29 +-
.../apache/tika/metadata/TikaCoreProperties.java | 2 +-
.../writefilter/StandardMetadataLimiter.java | 8 +-
.../org/apache/tika/detect/MagicDetectorTest.java | 102 ++++
tika-metadata-schema/README.md | 72 +++
tika-metadata-schema/pom.xml | 95 +++
.../tika/metadata/schema/MetadataKeyValidator.java | 143 +++++
.../tika/metadata/schema/SchemaGenerator.java | 249 ++++++++
.../apache/tika/metadata/metadata-key-fields.json | 654 +++++++++++++++++++++
.../org/apache/tika/metadata/metadata-keys.json | 652 ++++++++++++++++++++
.../tika/metadata/metadata-open-namespaces.json | 23 +
.../tika/metadata/schema/MetadataCoverageTest.java | 150 +++++
.../metadata/schema/MetadataFieldTableTest.java | 46 ++
.../metadata/schema/MetadataKeyValidatorTest.java | 90 +++
.../metadata/schema/MetadataNoUnderscoreTest.java | 79 +++
.../tika/metadata/schema/MetadataSchemaTest.java | 59 ++
tika-parent/pom.xml | 22 +-
.../apache/tika/parser/envi/EnviHeaderParser.java | 11 +-
.../org/apache/tika/parser/grib/GribParser.java | 5 +-
.../apache/tika/parser/netcdf/NetCDFParser.java | 8 +-
.../org/apache/tika/inference/ChunkSerializer.java | 2 +-
.../tika/inference/ImageEmbeddingConfig.java | 2 +-
.../org/apache/tika/inference/InferenceConfig.java | 2 +-
.../tika/parser/ctakes/CTAKESContentHandler.java | 7 +-
.../tika/parser/journal/GrobidRESTParser.java | 6 +-
.../apache/tika/parser/ner/NamedEntityParser.java | 5 +-
.../apache/tika/parser/vlm/AbstractVLMParser.java | 4 +-
.../tika/parser/AutoDetectParserConfigTest.java | 8 +-
.../tika/parser/digest/DigestConfigTest.java | 28 +-
.../apache/tika/parser/mail/RFC822ParserTest.java | 3 +-
.../parser/microsoft/ooxml/OOXMLParserTest.java | 2 +-
.../tika/parser/iwork/IWorkPackageParser.java | 2 +-
.../tika/parser/iwork/NumbersContentHandler.java | 6 +-
.../parser/iwork/iwana/IWork13PackageParser.java | 5 +-
.../parser/iwork/iwana/IWork18PackageParser.java | 2 +-
.../apache/tika/parser/iwork/IWorkParserTest.java | 6 +-
.../org/apache/tika/parser/ogg/OggAudioParser.java | 6 +-
.../org/apache/tika/parser/video/FLVParser.java | 5 +-
.../java/org/apache/tika/parser/dwg/DWGParser.java | 9 +-
.../org/apache/tika/parser/dwg/DWGReadParser.java | 4 +-
.../org/apache/tika/parser/crypto/TSDParser.java | 2 +-
.../org/apache/tika/parser/html/HtmlHandler.java | 2 +-
.../tika/parser/image/ImageMetadataExtractor.java | 11 +-
.../tika/parser/mail/MailContentHandler.java | 6 +-
.../org/apache/tika/parser/mbox/MboxParser.java | 10 +-
.../apache/tika/parser/mbox/MboxParserTest.java | 2 +-
.../apache/tika/parser/microsoft/EMFParser.java | 4 +-
.../tika/parser/microsoft/JackcessExtractor.java | 6 +-
.../tika/parser/microsoft/JackcessParser.java | 15 +-
.../tika/parser/microsoft/SummaryExtractor.java | 3 +-
.../microsoft/msg/ExtendedMetadataExtractor.java | 2 +-
.../parser/microsoft/rtf/RTFObjDataParser.java | 8 +-
.../rtf/jflex/RTFObjDataStreamParser.java | 8 +-
.../tika/parser/microsoft/OutlookParserTest.java | 5 +-
.../tika/parser/odf/OpenDocumentMetaParser.java | 2 +-
.../apache/tika/parser/ocr/TesseractOCRParser.java | 8 +-
.../java/org/apache/tika/parser/pdf/PDFParser.java | 2 +-
.../apache/tika/parser/csv/TextAndCSVParser.java | 4 +-
.../org/apache/tika/parser/warc/WARCParser.java | 10 +-
.../org/apache/tika/parser/xml/XMLProfiler.java | 6 +-
.../org/apache/tika/parser/xmp/XmpExtractor.java | 4 +-
.../pipes/core/DigestingOpenContainersTest.java | 2 +-
.../tika/pipes/emitter/azblob/AZBlobEmitter.java | 2 +-
.../tika-pipes-microsoft-graph/pom.xml | 2 +-
.../tika/server/core/resource/TikaResource.java | 4 +-
.../tika/xmp/convert/MSOfficeBinaryConverter.java | 2 +-
.../tika/xmp/convert/MSOfficeXMLConverter.java | 2 +-
.../tika/xmp/convert/OpenDocumentConverter.java | 2 +-
.../org/apache/tika/xmp/convert/RTFConverter.java | 2 +-
86 files changed, 2894 insertions(+), 174 deletions(-)
create mode 100644 .skills/metadata-schema.md
create mode 100644
tika-core/src/main/java/org/apache/tika/metadata/PassthroughPrefix.java
create mode 100644 tika-metadata-schema/README.md
create mode 100644 tika-metadata-schema/pom.xml
create mode 100644
tika-metadata-schema/src/main/java/org/apache/tika/metadata/schema/MetadataKeyValidator.java
create mode 100644
tika-metadata-schema/src/main/java/org/apache/tika/metadata/schema/SchemaGenerator.java
create mode 100644
tika-metadata-schema/src/main/resources/org/apache/tika/metadata/metadata-key-fields.json
create mode 100644
tika-metadata-schema/src/main/resources/org/apache/tika/metadata/metadata-keys.json
create mode 100644
tika-metadata-schema/src/main/resources/org/apache/tika/metadata/metadata-open-namespaces.json
create mode 100644
tika-metadata-schema/src/test/java/org/apache/tika/metadata/schema/MetadataCoverageTest.java
create mode 100644
tika-metadata-schema/src/test/java/org/apache/tika/metadata/schema/MetadataFieldTableTest.java
create mode 100644
tika-metadata-schema/src/test/java/org/apache/tika/metadata/schema/MetadataKeyValidatorTest.java
create mode 100644
tika-metadata-schema/src/test/java/org/apache/tika/metadata/schema/MetadataNoUnderscoreTest.java
create mode 100644
tika-metadata-schema/src/test/java/org/apache/tika/metadata/schema/MetadataSchemaTest.java