You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2023/08/16 18:18:27 UTC
[tika] branch TIKA-3109 updated (83793014f -> 26ac30b54)
This is an automated email from the ASF dual-hosted git repository.
tallison pushed a change to branch TIKA-3109
in repository https://gitbox.apache.org/repos/asf/tika.git
from 83793014f TIKA-3109 -- parse iframe's srcdoc as an embedded document -- add check for iframe and remove debug
add 0ed9f8a0b TIKA-4048 -- revert change in default decompressConcatenated and add a gzip subtype detector for warc+gz (#1290)
add 26ac30b54 Merge branch 'main' into TIKA-3109
No new revisions were added by this update.
Summary of changes:
CHANGES.txt | 3 +-
.../org/apache/tika/mime/tika-mimetypes.xml | 6 ++
.../src/test/java/org/apache/tika/TikaTest.java | 63 +++++++++++++++
.../detect/gzip/GZipSpecializationDetector.java | 90 +++++++++++++++++++++
.../apache/tika/parser/pkg/CompressorParser.java | 2 +-
.../services/org.apache.tika.detect.Detector | 2 +-
.../tika-parser-webarchive-module/pom.xml | 8 +-
.../org/apache/tika/parser/warc/WARCParser.java | 5 +-
.../apache/tika/parser/warc/WARCParserTest.java | 23 +++++-
.../test-documents/testWARC_multiple.warc | Bin 0 -> 6773 bytes
.../test-documents/testWARC_multiple.warc.gz | Bin 0 -> 5907 bytes
.../apache/tika/detect/TestDetectorLoading.java | 8 +-
.../org/apache/tika/parser/pkg/GzipParserTest.java | 12 ++-
.../resources/configs/tika-config-multiple-gz.xml} | 4 +-
14 files changed, 211 insertions(+), 15 deletions(-)
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-pkg-module/src/main/java/org/apache/tika/detect/gzip/GZipSpecializationDetector.java
copy tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/{tika-parser-apple-module => tika-parser-pkg-module}/src/main/resources/META-INF/services/org.apache.tika.detect.Detector (93%)
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/test/resources/test-documents/testWARC_multiple.warc
create mode 100644 tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-webarchive-module/src/test/resources/test-documents/testWARC_multiple.warc.gz
copy tika-parsers/tika-parsers-standard/{tika-parsers-standard-modules/tika-parser-pkg-module/src/test/resources/org/apache/tika/parser/pkg/tika-gzip-config.xml => tika-parsers-standard-package/src/test/resources/configs/tika-config-multiple-gz.xml} (93%)