This is an automated email from the ASF dual-hosted git repository.
tballison pushed a change to branch TIKA-4745-more-junk-charset
in repository https://gitbox.apache.org/repos/asf/tika.git
from b199a699db TIKA-4745 -- respond to copilot
add c324793f49 TIKA-4745 -- clean up module boundaries and respond to
copilot
No new revisions were added by this update.
Summary of changes:
.../NaiveBayesBigramEncodingDetector.java | 13 +++--
tika-ml/pom.xml | 1 +
.../pom.xml | 56 +++++--------------
.../ml/junkdetect/tools/BoundaryBigramAudit.java | 0
.../ml/junkdetect/tools/BuildJunkTrainingData.java | 0
.../tika/ml/junkdetect/tools/DebugScriptRuns.java | 0
.../tools/JunkDetectorTrainingConfig.java | 0
.../ml/junkdetect/tools/LineScriptFractions.java | 0
.../tika/ml/junkdetect/tools/ScriptCensus.java | 0
.../tika/ml/junkdetect/tools/TrainJunkModel.java | 11 ++--
.../ml/junkdetect/JunkDetectorRoundTripTest.java | 0
.../tools/BuildJunkAugmentationData.java | 0
.../tools/BuildJunkAugmentationDataTest.java | 0
.../tools/JunkDetectorTrainingConfigTest.java | 0
tika-ml/tika-ml-junkdetect/pom.xml | 65 +---------------------
.../apache/tika/ml/junkdetect/BigramTables.java | 13 ++---
16 files changed, 35 insertions(+), 124 deletions(-)
copy tika-ml/{tika-ml-junkdetect => tika-ml-junkdetect-tools}/pom.xml (72%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/main/java/org/apache/tika/ml/junkdetect/tools/BoundaryBigramAudit.java
(100%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/main/java/org/apache/tika/ml/junkdetect/tools/BuildJunkTrainingData.java
(100%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/main/java/org/apache/tika/ml/junkdetect/tools/DebugScriptRuns.java
(100%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/main/java/org/apache/tika/ml/junkdetect/tools/JunkDetectorTrainingConfig.java
(100%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/main/java/org/apache/tika/ml/junkdetect/tools/LineScriptFractions.java
(100%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/main/java/org/apache/tika/ml/junkdetect/tools/ScriptCensus.java
(100%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/main/java/org/apache/tika/ml/junkdetect/tools/TrainJunkModel.java
(99%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/test/java/org/apache/tika/ml/junkdetect/JunkDetectorRoundTripTest.java
(100%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/test/java/org/apache/tika/ml/junkdetect/tools/BuildJunkAugmentationData.java
(100%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/test/java/org/apache/tika/ml/junkdetect/tools/BuildJunkAugmentationDataTest.java
(100%)
rename tika-ml/{tika-ml-junkdetect =>
tika-ml-junkdetect-tools}/src/test/java/org/apache/tika/ml/junkdetect/tools/JunkDetectorTrainingConfigTest.java
(100%)