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 9214bd55db TIKA-4769 - improve metadata robustness
     add aca20dc144 TIKA-4770: Add a Markdown parser with structured, lossless 
XHTML output (#2922)
     add 17812252de Update serialization docs (#2924)
     add a8ad0ac685 improve metadata resiliency

No new revisions were added by this update.

Summary of changes:
 .../ROOT/pages/developers/serialization.adoc       |  56 +++
 .../pages/migration-to-4x/design-notes-4x.adoc     |  18 +-
 .../pages/migration-to-4x/serialization-4x.adoc    |  24 +-
 tika-bom/pom.xml                                   |   5 +
 .../apache/tika/digest/InputStreamDigester.java    |  12 +-
 .../java/org/apache/tika/metadata/Metadata.java    |  34 +-
 .../metadata/filter/CompositeMetadataFilter.java   |   2 +-
 .../tika/metadata/filter/MetadataFilter.java       |  26 +-
 .../tika/metadata/filter/MetadataFilterBase.java   |   3 +-
 .../apache/tika/metadata/filter/NoOpFilter.java    |   2 +-
 .../filter/RemoveByMimeMetadataFilter.java         |   2 +-
 .../org/apache/tika/parser/CompositeParser.java    |   2 +-
 .../metadata/MetadataInternalKeyGuardTest.java     |  42 +-
 .../geoinfo/GeographicInformationParser.java       |   7 +-
 .../org/apache/tika/parser/grib/GribParser.java    |  27 +-
 .../java/org/apache/tika/parser/hdf/HDFParser.java |   2 +-
 .../apache/tika/parser/netcdf/NetCDFParser.java    |  29 +-
 .../org/apache/tika/parser/hdf/HDFParserTest.java  |   2 +-
 .../tika/parser/netcdf/NetCDFParserTest.java       |   2 +-
 .../tika/inference/AbstractEmbeddingFilter.java    |   2 +-
 .../tika/inference/JinaEmbeddingFilterTest.java    |   6 +-
 .../tika/inference/OpenAIEmbeddingFilterTest.java  |  12 +-
 .../apache/tika/parser/geo/topic/GeoParser.java    |   5 +
 .../tika/parser/journal/GrobidRESTParser.java      |   4 +
 .../tika/config/TikaEncodingDetectorTest.java      |   6 +-
 .../tika-parsers-standard-modules/pom.xml          |   1 +
 .../tika/parser/iwork/NumbersContentHandler.java   |  32 +-
 .../tika/parser/iwork/PagesContentHandler.java     |   2 +-
 .../org/apache/tika/parser/audio/AudioParser.java  |   1 -
 .../java/org/apache/tika/parser/mp3/Mp3Parser.java |   1 -
 .../org/apache/tika/parser/ogg/OggAudioParser.java |   4 +-
 .../org/apache/tika/parser/video/FLVParser.java    |   6 +-
 .../apache/tika/parser/audio/AudioParserTest.java  |   7 +-
 .../org/apache/tika/parser/mp3/Mp3ParserTest.java  |  18 +-
 .../apache/tika/parser/video/FLVParserTest.java    |  10 +-
 .../org/apache/tika/parser/dwg/DWGReadParser.java  |   4 +-
 .../java/org/apache/tika/parser/mat/MatParser.java |   3 +-
 .../org/apache/tika/parser/mat/MatParserTest.java  |   3 +-
 .../pom.xml                                        |  20 +-
 .../apache/tika/parser/datauri}/DataURIScheme.java |   2 +-
 .../datauri}/DataURISchemeParseException.java      |   2 +-
 .../tika/parser/datauri}/DataURISchemeUtil.java    |   5 +-
 .../parser/datauri}/DataURISchemeParserTest.java   |   2 +-
 .../apache/tika/parser/font/TrueTypeParser.java    |   2 +-
 .../apache/tika/parser/font/FontParsersTest.java   |   2 +-
 .../tika-parser-html-module/pom.xml                |   5 +-
 .../org/apache/tika/parser/html/HtmlHandler.java   |   3 +
 .../rtf/jflex/RTFEmbeddedHandlerTest.java          |   2 +-
 .../apache/tika/parser/indesign/IDMLParser.java    |   3 +-
 .../apache/tika/parser/mif/MIFContentHandler.java  |   3 +-
 .../tika/parser/indesign/IDMLParserTest.java       |   5 +-
 .../org/apache/tika/parser/mif/MIFParserTest.java  |   5 +-
 .../tika/parser/pdf/PDMetadataExtractor.java       |  25 +-
 .../tika-parser-text-module/pom.xml                |  17 +-
 .../tika/parser/markdown/MarkdownParser.java       | 503 +++++++++++++++++++++
 .../tika/parser/markdown/MarkdownParserTest.java   | 137 ++++++
 .../test/resources/test-documents/testMARKDOWN.md  |  25 +
 .../test-documents/testMARKDOWN_dataURI.md         |   7 +
 .../serialization/FetchEmitTupleDeserializer.java  |   4 +-
 .../apache/tika/pipes/core/server/EmitHandler.java |  17 +-
 .../filter/AttachmentCountingListFilter.java       |   2 +-
 .../tika/serialization/ComponentNameResolver.java  |  11 +-
 .../filter/AttachmentCountingListFilter.java       |   2 +-
 .../CustomClassSerializationTest.java              |   2 +-
 .../tika/serialization/JsonMetadataTest.java       |   2 +-
 65 files changed, 1062 insertions(+), 177 deletions(-)
 copy 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/{tika-parser-digest-commons
 => tika-parser-datauri-commons}/pom.xml (79%)
 rename 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/{tika-parser-html-module/src/main/java/org/apache/tika/parser/html
 => 
tika-parser-datauri-commons/src/main/java/org/apache/tika/parser/datauri}/DataURIScheme.java
 (98%)
 rename 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/{tika-parser-html-module/src/main/java/org/apache/tika/parser/html
 => 
tika-parser-datauri-commons/src/main/java/org/apache/tika/parser/datauri}/DataURISchemeParseException.java
 (96%)
 rename 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/{tika-parser-html-module/src/main/java/org/apache/tika/parser/html
 => 
tika-parser-datauri-commons/src/main/java/org/apache/tika/parser/datauri}/DataURISchemeUtil.java
 (97%)
 rename 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/{tika-parser-html-module/src/test/java/org/apache/tika/parser/html
 => 
tika-parser-datauri-commons/src/test/java/org/apache/tika/parser/datauri}/DataURISchemeParserTest.java
 (98%)
 create mode 100644 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/main/java/org/apache/tika/parser/markdown/MarkdownParser.java
 create mode 100644 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/test/java/org/apache/tika/parser/markdown/MarkdownParserTest.java
 create mode 100644 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/test/resources/test-documents/testMARKDOWN.md
 create mode 100644 
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-text-module/src/test/resources/test-documents/testMARKDOWN_dataURI.md

Reply via email to