This is an automated email from the ASF dual-hosted git repository.
tallison pushed a change to branch TIKA-4628
in repository https://gitbox.apache.org/repos/asf/tika.git
from daa116419a Merge remote-tracking branch 'origin/main' into TIKA-4628
add 9465afc4a7 TIKA-4628 -- further cleanup
add 755f26d391 TIKA-4628 -- fixes
add 19eb31632f TIKA-4631 -- add a detect/no-parse option to pipes (#2549)
add 231ac690b6 TIKA-4625: Add AsciiDoc documentation module (#2536)
add 170c4b0086 Merge branch 'main' into TIKA-4628
No new revisions were added by this update.
Summary of changes:
.github/workflows/main-jdk17-build.yml | 4 +
.../main-jdk17-windows-build-multi-locale.yml | 4 +
.github/workflows/main-jdk17-windows-build.yml | 4 +
.github/workflows/main-jdk21-build.yml | 2 +
.github/workflows/main-jdk25-build.yml | 2 +
docs/pom.xml | 96 ++++++++
docs/src/assembly/docs.xml | 37 +++
docs/src/main/asciidoc/advanced/index.adoc | 31 +++
docs/src/main/asciidoc/advanced/robustness.adoc | 137 +++++++++++
.../{ => src/main/asciidoc/advanced}/spooling.adoc | 0
docs/src/main/asciidoc/configuration/index.adoc | 40 +++
.../asciidoc/configuration/parsers/pdf-parser.adoc | 43 ++++
.../parsers/tesseract-ocr-parser.adoc | 67 +++++
docs/src/main/asciidoc/faq.adoc | 28 +++
docs/src/main/asciidoc/index.adoc | 72 ++++++
docs/src/main/asciidoc/maintainers/index.adoc | 29 +++
.../maintainers/release-guides/docker.adoc | 133 ++++++++++
.../asciidoc/maintainers/release-guides/grpc.adoc | 32 +++
.../asciidoc/maintainers/release-guides/helm.adoc | 138 +++++++++++
.../asciidoc/maintainers/release-guides/index.adoc | 32 +++
.../asciidoc/maintainers/release-guides/tika.adoc | 271 +++++++++++++++++++++
.../asciidoc/migration-to-4x/design-notes-4x.adoc | 127 ++++++++++
docs/src/main/asciidoc/migration-to-4x/index.adoc | 32 +++
.../migration-to-4x/metadata-changes-4x.adoc | 121 +++++++++
.../asciidoc/migration-to-4x/migrating-to-4x.adoc | 157 ++++++++++++
.../asciidoc/migration-to-4x/serialization-4x.adoc | 101 ++++++++
docs/src/main/asciidoc/pipes/index.adoc | 37 +++
docs/src/main/asciidoc/roadmap.adoc | 96 ++++++++
docs/src/main/asciidoc/security.adoc | 34 +++
docs/src/main/asciidoc/using-tika/cli/index.adoc | 39 +++
docs/src/main/asciidoc/using-tika/grpc/index.adoc | 32 +++
docs/src/main/asciidoc/using-tika/index.adoc | 65 +++++
.../using-tika/java-api/getting-started.adoc | 130 ++++++++++
.../main/asciidoc/using-tika/java-api/index.adoc | 38 +++
.../src/main/asciidoc/using-tika/server/index.adoc | 42 ++++
pom.xml | 3 +
.../ParsingEmbeddedDocumentExtractor.java | 14 ++
.../java/org/apache/tika/parser/ParseRecord.java | 120 +++++++++
.../apache/tika/parser/RecursiveParserWrapper.java | 12 +
.../sax/AbstractRecursiveParserWrapperHandler.java | 2 +
.../org/apache/tika/config/ConfigExamplesTest.java | 97 ++++++++
.../config-examples/migration-full-example.json | 26 ++
.../config-examples/pdf-parser-basic.json} | 1 +
.../resources/config-examples/pdf-parser-full.json | 53 ++++
.../config-examples/tesseract-basic.json} | 4 +-
.../resources/config-examples/tesseract-full.json | 35 +++
.../java/org/apache/tika/pipes/api/ParseMode.java | 13 +-
tika-pipes/tika-pipes-core/pom.xml | 4 +
.../pipes/core/serialization/JsonPipesIpc.java | 26 +-
.../tika/pipes/core/server/ParseHandler.java | 45 +++-
.../tika/pipes/fork/PipesForkParserTest.java | 76 ++++++
.../apache/tika/pipes/fs/ConfigExamplesTest.java | 69 ++++++
.../config-examples/file-system-emitter.json | 13 +
.../config-examples/file-system-fetcher.json | 11 +
.../config-examples/file-system-pipeline.json | 27 ++
tika-serialization/pom.xml | 5 +
.../apache/tika/config/loader/FrameworkConfig.java | 11 +-
.../config/loader/TikaObjectMapperFactory.java | 22 +-
.../org/apache/tika/serialization/TikaModule.java | 8 +-
.../serdes/ParseContextDeserializer.java | 15 +-
.../serdes/ParseContextSerializer.java | 7 +-
.../tika/server/core/ConfigExamplesTest.java | 64 +++++
.../resources/config-examples/server-basic.json | 13 +
.../config-examples/server-with-parsers.json | 24 ++
64 files changed, 3041 insertions(+), 32 deletions(-)
create mode 100644 docs/pom.xml
create mode 100644 docs/src/assembly/docs.xml
create mode 100644 docs/src/main/asciidoc/advanced/index.adoc
create mode 100644 docs/src/main/asciidoc/advanced/robustness.adoc
rename docs/{ => src/main/asciidoc/advanced}/spooling.adoc (100%)
create mode 100644 docs/src/main/asciidoc/configuration/index.adoc
create mode 100644 docs/src/main/asciidoc/configuration/parsers/pdf-parser.adoc
create mode 100644
docs/src/main/asciidoc/configuration/parsers/tesseract-ocr-parser.adoc
create mode 100644 docs/src/main/asciidoc/faq.adoc
create mode 100644 docs/src/main/asciidoc/index.adoc
create mode 100644 docs/src/main/asciidoc/maintainers/index.adoc
create mode 100644
docs/src/main/asciidoc/maintainers/release-guides/docker.adoc
create mode 100644 docs/src/main/asciidoc/maintainers/release-guides/grpc.adoc
create mode 100644 docs/src/main/asciidoc/maintainers/release-guides/helm.adoc
create mode 100644 docs/src/main/asciidoc/maintainers/release-guides/index.adoc
create mode 100644 docs/src/main/asciidoc/maintainers/release-guides/tika.adoc
create mode 100644 docs/src/main/asciidoc/migration-to-4x/design-notes-4x.adoc
create mode 100644 docs/src/main/asciidoc/migration-to-4x/index.adoc
create mode 100644
docs/src/main/asciidoc/migration-to-4x/metadata-changes-4x.adoc
create mode 100644 docs/src/main/asciidoc/migration-to-4x/migrating-to-4x.adoc
create mode 100644 docs/src/main/asciidoc/migration-to-4x/serialization-4x.adoc
create mode 100644 docs/src/main/asciidoc/pipes/index.adoc
create mode 100644 docs/src/main/asciidoc/roadmap.adoc
create mode 100644 docs/src/main/asciidoc/security.adoc
create mode 100644 docs/src/main/asciidoc/using-tika/cli/index.adoc
create mode 100644 docs/src/main/asciidoc/using-tika/grpc/index.adoc
create mode 100644 docs/src/main/asciidoc/using-tika/index.adoc
create mode 100644
docs/src/main/asciidoc/using-tika/java-api/getting-started.adoc
create mode 100644 docs/src/main/asciidoc/using-tika/java-api/index.adoc
create mode 100644 docs/src/main/asciidoc/using-tika/server/index.adoc
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/java/org/apache/tika/config/ConfigExamplesTest.java
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/resources/config-examples/migration-full-example.json
copy
tika-parsers/tika-parsers-standard/{tika-parsers-standard-modules/tika-parser-pdf-module/src/test/resources/org/apache/tika/parser/pdf/tika-config.json
=>
tika-parsers-standard-package/src/test/resources/config-examples/pdf-parser-basic.json}
(72%)
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/resources/config-examples/pdf-parser-full.json
copy
tika-parsers/tika-parsers-standard/{tika-parsers-standard-modules/tika-parser-ocr-module/src/test/resources/configs/TIKA-3582-tesseract.json
=>
tika-parsers-standard-package/src/test/resources/config-examples/tesseract-basic.json}
(56%)
create mode 100644
tika-parsers/tika-parsers-standard/tika-parsers-standard-package/src/test/resources/config-examples/tesseract-full.json
create mode 100644
tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/test/java/org/apache/tika/pipes/fs/ConfigExamplesTest.java
create mode 100644
tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/test/resources/config-examples/file-system-emitter.json
create mode 100644
tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/test/resources/config-examples/file-system-fetcher.json
create mode 100644
tika-pipes/tika-pipes-plugins/tika-pipes-file-system/src/test/resources/config-examples/file-system-pipeline.json
create mode 100644
tika-server/tika-server-core/src/test/java/org/apache/tika/server/core/ConfigExamplesTest.java
create mode 100644
tika-server/tika-server-core/src/test/resources/config-examples/server-basic.json
create mode 100644
tika-server/tika-server-core/src/test/resources/config-examples/server-with-parsers.json