This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch TIKA-4971
in repository https://gitbox.apache.org/repos/asf/tika.git
from 7365479a16 TIKA-4971: review fixes -- package replaces the metadata
emit, sidecars are list rows
add 5c60cf17b6 Support max_completion_tokens in OpenAI VLM parser (#3350)
add 4847f78c8f refuse wire-blocked component names given as bare strings
(#3351)
add fe5ba58bc1 TIKA-4966: apply font formatting styles in docx (#3316)
add d857a8e6d0 TIKA-4967: link REF/PAGEREF/NOTEREF and HYPERLINK \l fields
to bookmarks in docx (#3317)
add eb024f1e60 TIKA-4968: wrap OMML equations in span class=math in docx
(#3318)
add 9a6c38ffcc Bump com.azure:azure-sdk-bom from 1.3.8 to 1.3.9 (#3363)
add 9c650af6fc Bump com.github.luben:zstd-jni from 1.5.7-22 to 1.5.7-23
(#3362)
add 1ef2ab0399 Bump grpc.version from 1.84.2 to 1.85.0 (#3360)
add d7dcac67e5 Bump org.apache.kafka:kafka-clients from 4.3.1 to 4.4.0
(#3361)
add b4ddffb48e Bump org.codehaus.mojo:versions-maven-plugin from 2.22.0 to
2.23.0 (#3358)
add d7d818a749 Bump com.healthmarketscience.jackcess:jackcess from 5.0.3
to 5.0.4 (#3357)
add c13bb5ff87 Bump org.xerial.snappy:snappy-java from 1.1.10.11 to
1.1.10.12 (#3356)
add 799ff8d121 Bump commonmark.version from 0.30.0 to 0.30.1 (#3354)
add 7e2b51b196 Bump software.amazon.awssdk:bom from 2.55.13 to 2.56.0
(#3355)
add 1aacc4cebf Bump sis.version from 1.6 to 1.7 (#3359)
add 62fe6fcf74 TIKA-4969: opt-in typed metadata values in JSON output
(#3341)
add f28c1e7d25 TIKA-4977: detect *.rs as text/x-rust; RLS services XML by
root element (#3365)
add 1f6e2782ae TIKA-4970: write image and page embeddings once per
document (#3342)
add 043762c632 TIKA-4968: rename OMML span to class=omml; keep it across
hyperlinks (#3366)
add 297c097969 Merge branch 'main' into TIKA-4971
No new revisions were added by this update.
Summary of changes:
CHANGES.txt | 40 +++
docs/modules/ROOT/pages/configuration/index.adoc | 39 ++-
.../pages/configuration/parsers/vlm-parsers.adoc | 6 +-
.../pages/migration-to-4x/chunk-strategies.adoc | 4 +-
.../java/org/apache/tika/metadata/Property.java | 18 +-
.../apache/tika/metadata/TikaCoreProperties.java | 2 +-
.../org/apache/tika/mime/tika-mimetypes.xml | 9 +-
.../java/org/apache/tika/TikaDetectionTest.java | 3 +-
.../org/apache/tika/mime/MimeDetectionTest.java | 28 +++
.../org/apache/tika/metadata/metadata-keys.json | 2 +-
tika-parent/pom.xml | 20 +-
.../org/apache/tika/inference/ChunkTarget.java | 7 +-
.../java/org/apache/tika/inference/EmbedTask.java | 75 ++++--
.../org/apache/tika/inference/EmbedTaskTest.java | 66 +++++
.../apache/tika/parser/vlm/OpenAIVLMParser.java | 5 +-
.../org/apache/tika/parser/vlm/VLMOCRConfig.java | 16 ++
.../tika/parser/vlm/OpenAIVLMParserTest.java | 8 +
.../tika/parser/vlm/VLMOperatorOnlyConfigTest.java | 2 +-
.../resources/config-examples/openai-vlm-full.json | 1 +
.../tika/parser/microsoft/OfficeParserConfig.java | 18 ++
.../tika/parser/microsoft/WordExtractor.java | 25 +-
.../parser/microsoft/ooxml/FieldCodeParser.java | 34 +++
.../microsoft/ooxml/FormattingTagManager.java | 71 +++++-
.../microsoft/ooxml/OOXMLTikaBodyPartHandler.java | 38 ++-
.../ooxml/OOXMLWordAndPowerPointTextHandler.java | 138 ++++++++---
.../tika/parser/microsoft/ooxml/RunProperties.java | 45 ++++
.../microsoft/ooxml/XWPFBodyContentsHandler.java | 9 +
.../microsoft/ooxml/xwpf/XWPFStylesShim.java | 127 ++++++++--
.../tika/parser/microsoft/WordParserTest.java | 14 ++
.../parser/microsoft/ooxml/OOXMLDocxSAXTest.java | 74 ++++++
.../test-documents/testWORD_characterStyles.docx | Bin 0 -> 1944 bytes
.../resources/test-documents/testWORD_omml.docx | Bin 0 -> 1113 bytes
.../test-documents/testWORD_refFields.docx | Bin 0 -> 1261 bytes
.../test-documents/testWORD_unclosedFields.docx | Bin 0 -> 1072 bytes
.../core/serialization/EmitDataDeserializer.java | 18 ++
.../core/serialization/EmitDataSerializer.java | 17 ++
.../core/serialization/EmitDataValueTypesTest.java | 85 +++++++
.../org/apache/tika/pipes/emitter/es/ESClient.java | 15 +-
.../pipes/emitter/opensearch/OpenSearchClient.java | 16 +-
.../org/apache/tika/config/loader/TikaLoader.java | 25 +-
.../apache/tika/serialization/JsonMetadata.java | 38 ++-
.../tika/serialization/JsonMetadataList.java | 38 ++-
.../tika/serialization/MetadataValueTypes.java | 94 +++++++
.../serialization/serdes/MetadataDeserializer.java | 64 ++++-
.../serialization/serdes/MetadataSerializer.java | 102 +++++++-
.../serdes/ParseContextDeserializer.java | 16 +-
.../tika/serialization/MetadataValueTypesTest.java | 97 ++++++++
.../serialization/TypedMetadataValuesTest.java | 272 +++++++++++++++++++++
.../WireRestrictedParseContextTest.java | 12 +
.../tika/server/standard/TikaResourceTest.java | 6 +
50 files changed, 1702 insertions(+), 157 deletions(-)
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testWORD_characterStyles.docx
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testWORD_omml.docx
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testWORD_refFields.docx
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-microsoft-module/src/test/resources/test-documents/testWORD_unclosedFields.docx
create mode 100644
tika-pipes/tika-pipes-core/src/test/java/org/apache/tika/pipes/core/serialization/EmitDataValueTypesTest.java
create mode 100644
tika-serialization/src/main/java/org/apache/tika/serialization/MetadataValueTypes.java
create mode 100644
tika-serialization/src/test/java/org/apache/tika/serialization/MetadataValueTypesTest.java
create mode 100644
tika-serialization/src/test/java/org/apache/tika/serialization/TypedMetadataValuesTest.java