[
https://issues.apache.org/jira/browse/TIKA-4745?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18086634#comment-18086634
]
Hudson commented on TIKA-4745:
------------------------------
SUCCESS: Integrated in Jenkins build Tika ยป tika-main-jdk17 #1413 (See
[https://ci-builds.apache.org/job/Tika/job/tika-main-jdk17/1413/])
TIKA-4745 -- efficiency improvements (#2878) (github:
[https://github.com/apache/tika/commit/8d9900e21127de0a20334ebc59ca0529395575bf])
* (edit) tika-ml/pom.xml
* (add)
tika-encoding-detectors/tika-encoding-detector-html/src/main/resources/org/apache/tika/parser/html/StandardCharsets_unsupported_by_IANA.txt
* (edit)
tika-encoding-detectors/tika-encoding-detector-mojibuster/src/main/resources/org/apache/tika/ml/chardetect/nb-bigram.bin
* (add)
tika-ml/tika-ml-junkdetect-tools/src/test/java/org/apache/tika/ml/junkdetect/tools/JunkDetectorTrainingConfigTest.java
* (edit)
tika-core/src/main/java/org/apache/tika/detect/EncodingDetectorContext.java
* (edit)
tika-ml/tika-ml-junkdetect/src/main/resources/org/apache/tika/ml/junkdetect/junkdetect.bin
* (add)
tika-encoding-detectors/tika-encoding-detector-html/src/test/java/org/apache/tika/parser/html/HtmlEncodingDetectorTest.java
* (delete)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/tools/BuildJunkTrainingData.java
* (add)
tika-ml/tika-ml-junkdetect-tools/src/main/java/org/apache/tika/ml/junkdetect/tools/ScriptCensus.java
* (edit)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/BigramTables.java
* (edit)
tika-encoding-detectors/tika-encoding-detector-mojibuster/src/main/java/org/apache/tika/ml/chardetect/MojibusterEncodingDetector.java
* (edit)
tika-ml/tika-ml-chardetect/src/main/java/org/apache/tika/ml/chardetect/tools/TrainNaiveBayesBigram.java
* (add)
tika-ml/tika-ml-junkdetect-tools/src/test/java/org/apache/tika/ml/junkdetect/tools/BuildJunkAugmentationDataTest.java
* (delete)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/tools/DebugScriptRuns.java
* (add)
tika-ml/tika-ml-junkdetect-tools/src/main/java/org/apache/tika/ml/junkdetect/tools/DebugScriptRuns.java
* (add)
tika-ml/tika-ml-junkdetect-tools/src/main/java/org/apache/tika/ml/junkdetect/tools/BoundaryBigramAudit.java
* (delete)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/main/resources/org/apache/tika/parser/html/StandardCharsets_unsupported_by_IANA.txt
* (delete)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/HtmlEncodingDetectorTest.java
* (add)
tika-ml/tika-ml-junkdetect-tools/src/test/java/org/apache/tika/ml/junkdetect/JunkDetectorRoundTripTest.java
* (edit)
tika-encoding-detectors/tika-encoding-detector-html/src/main/java/org/apache/tika/parser/html/HtmlEncodingDetector.java
* (edit) tika-ml/tika-ml-junkdetect/pom.xml
* (delete)
tika-ml/tika-ml-junkdetect/src/test/java/org/apache/tika/ml/junkdetect/tools/BuildJunkAugmentationDataTest.java
* (add) tika-ml/tika-ml-junkdetect-tools/pom.xml
* (delete)
tika-ml/tika-ml-junkdetect/src/test/java/org/apache/tika/ml/junkdetect/tools/BuildJunkAugmentationData.java
* (edit)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/pom.xml
* (edit)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/TextQualityFeatures.java
* (add)
tika-ml/tika-ml-junkdetect-tools/src/main/java/org/apache/tika/ml/junkdetect/tools/TrainJunkModel.java
* (edit)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/JunkFilterEncodingDetector.java
* (delete)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/tools/LineScriptFractions.java
* (delete)
tika-ml/tika-ml-junkdetect/src/test/java/org/apache/tika/ml/junkdetect/JunkDetectorRoundTripTest.java
* (edit)
tika-encoding-detectors/tika-encoding-detector-mojibuster/src/main/java/org/apache/tika/ml/chardetect/AdaptiveProbe.java
* (delete)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/tools/JunkDetectorTrainingConfig.java
* (edit)
tika-langdetect/tika-langdetect-charsoup-core/src/main/java/org/apache/tika/langdetect/charsoup/CharSoupFeatureExtractor.java
* (add)
tika-ml/tika-ml-junkdetect-tools/src/main/java/org/apache/tika/ml/junkdetect/tools/BuildJunkTrainingData.java
* (add)
tika-ml/tika-ml-junkdetect-tools/src/main/java/org/apache/tika/ml/junkdetect/tools/LineScriptFractions.java
* (edit)
tika-encoding-detectors/tika-encoding-detector-mojibuster/src/main/java/org/apache/tika/ml/chardetect/NaiveBayesBigramEncodingDetector.java
* (delete)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/tools/ScriptCensus.java
* (delete)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/tools/TrainJunkModel.java
* (edit)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/JunkDetector.java
* (add) tika-core/src/main/java/org/apache/tika/detect/EncodingProbeCache.java
* (delete)
tika-ml/tika-ml-junkdetect/src/test/java/org/apache/tika/ml/junkdetect/tools/JunkDetectorTrainingConfigTest.java
* (delete)
tika-parsers/tika-parsers-standard/tika-parsers-standard-modules/tika-parser-html-module/src/test/java/org/apache/tika/parser/html/StandardHtmlEncodingDetectorTest.java
* (add)
tika-ml/tika-ml-junkdetect-tools/src/main/java/org/apache/tika/ml/junkdetect/tools/JunkDetectorTrainingConfig.java
* (add)
tika-encoding-detectors/tika-encoding-detector-html/src/test/java/org/apache/tika/parser/html/StandardHtmlEncodingDetectorTest.java
* (add)
tika-ml/tika-ml-junkdetect-tools/src/test/java/org/apache/tika/ml/junkdetect/tools/BuildJunkAugmentationData.java
* (delete)
tika-ml/tika-ml-junkdetect/src/main/java/org/apache/tika/ml/junkdetect/tools/BoundaryBigramAudit.java
> Small improvements to lang detection, charset detection and junk detection
> --------------------------------------------------------------------------
>
> Key: TIKA-4745
> URL: https://issues.apache.org/jira/browse/TIKA-4745
> Project: Tika
> Issue Type: Task
> Reporter: Tim Allison
> Priority: Minor
> Fix For: 4.0.0
>
>
> I ran a regression test in prep for the 4.0.0-beta-1 release. There are a
> number of smallish things that we can clean up in the components listed in
> the title.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)