This is an automated email from the ASF dual-hosted git repository.
tallison pushed a change to branch TIKA-2552
in repository https://gitbox.apache.org/repos/asf/tika.git.
from da89caf TIKA-2552 -- add tests back after fixing POI-62591
add 2cdf627 TIKA-2695 -- upgrade Lucene to 7.4.0
add b717ca6 TIKA-2667 upgrade jmatio
add 719826a fix doubled junit dependency in tika-nlp
add f44e109 TIKA-2672 -- upgrade deeplearning4j to 1.0.0-beta2 via Thejan
Wijesinghe. Thank you, Thejan!!!
add b542f9b TIKA-2672 -- remove hard coded input dimensions
add ed0d3d1 TIKA-2707 -- upgrade to commons-compress 1.18
new 9523f50 Merge branch 'branch_1x' into TIKA-2552
new 657046d NPOIFS->POIFS and add jackcess shim
The 2 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
tika-dl/pom.xml | 223 ++++--
.../tika/dl/imagerec/DL4JInceptionV3Net.java | 121 ++-
.../org/apache/tika/dl/imagerec/DL4JVGG16Net.java | 52 +-
.../imagerec/imagenet_incpetionv3_class_index.json | 1 -
.../apache/tika/dl/imagerec/inceptionv3-model.json | 1 -
.../tika/dl/imagerec/DL4JInceptionV3NetTest.java | 5 +-
.../apache/tika/dl/imagerec/DL4JVGG16NetTest.java | 8 +-
.../tika/dl/imagerec/dl4j-inception3-config.xml | 3 +-
tika-eval/pom.xml | 5 +-
.../eval/tokens/AlphaIdeographFilterFactory.java | 2 +-
.../tika/eval/tokens/AnalyzerDeserializer.java | 179 +----
.../tokens/CJKBigramAwareLengthFilterFactory.java | 2 +-
tika-eval/src/main/resources/lucene-analyzers.json | 22 +-
tika-example/pom.xml | 2 +-
.../tika/example/LazyTextExtractorField.java | 210 ------
.../org/apache/tika/example/LuceneIndexer.java | 7 +-
.../apache/tika/example/LuceneIndexerExtended.java | 21 +-
.../tika/example/MetadataAwareLuceneIndexer.java | 7 +-
.../java/org/apache/tika/example/RecentFiles.java | 20 +-
tika-nlp/pom.xml | 16 +-
tika-parent/pom.xml | 2 +-
tika-parsers/pom.xml | 4 +-
.../tika/parser/microsoft/ExcelExtractor.java | 6 +-
.../tika/parser/microsoft/HSLFExtractor.java | 18 +-
.../parser/microsoft/JackcessCompoundOleUtil.java | 268 +++++++
.../tika/parser/microsoft/JackcessExtractor.java | 28 +-
.../tika/parser/microsoft/JackcessOleUtil.java | 813 +++++++++++++++++++++
.../apache/tika/parser/microsoft/OfficeParser.java | 21 +-
.../tika/parser/microsoft/OutlookExtractor.java | 4 +-
.../parser/microsoft/POIFSContainerDetector.java | 12 +-
.../tika/parser/microsoft/SummaryExtractor.java | 6 +-
.../tika/parser/microsoft/WordExtractor.java | 6 +-
.../microsoft/ooxml/AbstractOOXMLExtractor.java | 5 +-
.../apache/tika/parser/rtf/RTFObjDataParser.java | 4 +-
.../tika/detect/TestContainerAwareDetector.java | 6 +-
.../tika/parser/microsoft/JackcessParserTest.java | 1 +
36 files changed, 1488 insertions(+), 623 deletions(-)
delete mode 100644
tika-dl/src/main/resources/org/apache/tika/dl/imagerec/imagenet_incpetionv3_class_index.json
delete mode 100644
tika-dl/src/main/resources/org/apache/tika/dl/imagerec/inceptionv3-model.json
delete mode 100755
tika-example/src/main/java/org/apache/tika/example/LazyTextExtractorField.java
create mode 100644
tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessCompoundOleUtil.java
create mode 100644
tika-parsers/src/main/java/org/apache/tika/parser/microsoft/JackcessOleUtil.java