[
https://issues.apache.org/jira/browse/TIKA-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17241023#comment-17241023
]
Hudson commented on TIKA-3240:
------------------------------
SUCCESS: Integrated in Jenkins build Tika ยป tika-main-jdk8 #58 (See
[https://ci-builds.apache.org/job/Tika/job/tika-main-jdk8/58/])
TIKA-3240 -- break tika-eval into tika-eval-core and tika-eval-app for Tika
2.0.0 (tallison:
[https://github.com/apache/tika/commit/219338f0925ef55a4748906e14a757a05b94ce35])
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/CommonTokensHellinger.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/TokenCountPriorityQueue.java
* (add) tika-eval/tika-eval-core/pom.xml
* (delete) tika-eval/src/main/java/org/apache/tika/eval/io/XMLLogReader.java
* (delete) tika-eval/src/main/resources/common_tokens/afr
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/io/ExtractReaderException.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/hun
* (delete) tika-eval/src/main/resources/common_tokens/kat
* (delete) tika-eval/src/main/resources/common_tokens/slk
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/slv
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ces
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ben
* (delete)
tika-eval/src/test/resources/test-dirs/extractsA/file14_diffAttachOrder.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/vie
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/util/ContentTagParser.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/langid/LanguageIDWrapper.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/uzb
* (delete) tika-eval/src/main/resources/common_tokens/mlg
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/min
* (delete) tika-eval/src/main/java/org/apache/tika/eval/ExtractComparer.java
* (delete) tika-eval/src/test/resources/test-dirs/extractsA/file11_oom.txt.json
* (delete) tika-eval/src/main/resources/common_tokens/fao
* (delete)
tika-eval/src/test/resources/single-file-profiler-crawl-input-config.xml
* (delete)
tika-eval/src/test/java/org/apache/tika/tools/TopCommonTokenCounterTest.java
* (delete) tika-eval/src/main/resources/common_tokens/epo
* (delete) tika-eval/src/test/java/org/apache/tika/eval/langid/LangIdTest.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/sqi
* (delete)
tika-eval/src/test/resources/test-dirs/extractsB/file4_emptyB.pdf.json
* (delete) tika-eval/src/main/resources/common_tokens/hun
* (delete) tika-eval/src/main/java/org/apache/tika/eval/io/DBWriter.java
* (delete) tika-eval/src/main/resources/common_tokens/ben
* (delete) tika-eval/src/main/resources/common_tokens/gsw
* (add) tika-eval/tika-eval-core/src/main/resources/lucene-char-mapping.txt
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/cat
* (delete) tika-eval/src/main/resources/common_tokens/eus
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/bel
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/vol
* (delete) tika-eval/src/main/resources/common_tokens/pus
* (delete) tika-eval/src/test/resources/test-dirs/raw_input/file6_accessEx.pdf
* (delete) tika-eval/src/main/resources/common_tokens/pes
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/glg
* (delete) tika-eval/src/main/resources/tika-eval-comparison-config.xml
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/batch/FileProfilerBuilder.java
* (delete) tika-eval/src/main/java/org/apache/tika/eval/ExtractProfiler.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/nob
* (edit) tika-example/pom.xml
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/TokenLengths.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/TopNTokens.java
* (delete) tika-eval/src/test/resources/test-dirs/raw_input/file7_badJson.pdf
* (delete) tika-eval/src/main/resources/lucene-char-mapping.txt
* (delete)
tika-eval/src/main/resources/META-INF/services/org.apache.tika.metadata.filter.MetadataFilter
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenCounter.java
* (delete) tika-eval/src/test/resources/test-dirs/raw_input/file4_emptyB.pdf
* (delete) tika-eval/src/main/resources/common_tokens/msa
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/snd
* (delete) tika-eval/src/main/java/org/apache/tika/eval/db/JDBCUtil.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/slk
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/util/EvalExceptionUtils.java
* (delete) tika-eval/src/main/resources/common_tokens/kan
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/AnalyzerManager.java
* (delete) tika-eval/src/main/java/org/apache/tika/eval/tokens/LangModel.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ara
* (add)
tika-eval/tika-eval-core/src/main/resources/META-INF/services/org.apache.tika.metadata.filter.MetadataFilter
* (delete) tika-eval/src/test/resources/test-dirs/extractsB/file1.pdf.json
* (delete) tika-eval/src/main/java/org/apache/tika/eval/AbstractProfiler.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/CommonTokenResult.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ind
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/isl
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/kaz
* (delete) tika-eval/src/main/resources/tika-eval-profiler-config.xml
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/CommonTokensKLDNormed.java
* (add) tika-eval/tika-eval-core/src/main/resources/log4j.properties
* (delete) tika-eval/src/test/resources/test-dirs/extractsA/file16_badTags.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/uig
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tools/TrainTestSplit.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/CommonTokensKLDivergence.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/TextSha256Signature.java
* (delete) tika-eval/src/test/resources/test-dirs/extractsB/file16_badTags.html
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/BasicTokenCountStatsCalculator.java
* (delete)
tika-eval/src/test/java/org/apache/tika/eval/tokens/LuceneTokenCounter.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/StringStatsCalculator.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/oci
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/LanguageAwareTokenCountStats.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/metadata/TikaEvalMetadataFilter.java
* (delete) tika-eval/src/main/resources/common_tokens/nob
* (delete) tika-eval/src/test/resources/test-dirs/extractsA/file12_es.txt.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ban
* (delete) tika-eval/src/main/java/org/apache/tika/eval/io/IDBWriter.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tools/BatchTopCommonTokenCounter.java
* (delete)
tika-eval/src/test/resources/test-dirs/extractsA/file7_badJson.pdf.json
* (delete) tika-eval/src/main/resources/common_tokens/fra
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/som
* (delete) tika-eval/src/main/resources/common_tokens/sqi
* (delete) tika-eval/src/main/resources/comparison-reports.xml
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/reports/XLSXHREFFormatter.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/ContrastStatistics.java
* (delete) tika-eval/src/test/resources/common_tokens/es
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/pes
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/urd
* (delete) tika-eval/src/main/resources/common_tokens/pol
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/CommonTokensCosine.java
* (add)
tika-eval/tika-eval-core/src/main/resources/META-INF/services/org.apache.lucene.analysis.util.TokenFilterFactory
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/StringStatsCalculator.java
* (delete) tika-eval/src/main/java/org/apache/tika/eval/io/ExtractReader.java
* (delete)
tika-eval/src/test/resources/test-dirs/extractsB/file5_emptyA.pdf.json
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tools/CommonTokenOverlapCounter.java
* (delete) tika-eval/src/main/resources/common_tokens/bel
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/swe
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/batch/EvalConsumerBuilder.java
* (delete) tika-eval/src/main/resources/common_tokens/tha
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/lit
* (delete) tika-eval/src/main/resources/common_tokens/est
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/pan
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/BytesRefCalculator.java
* (delete) tika-eval/src/main/resources/common_tokens/lav
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/plt
* (delete)
tika-eval/src/test/resources/test-dirs/extractsA/file13_attachANotB.doc.json
* (delete) tika-eval/src/test/resources/test-dirs/raw_input/file5_emptyA.pdf
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/bre
* (delete)
tika-eval/src/main/resources/META-INF/services/org.apache.lucene.analysis.util.TokenFilterFactory
* (add)
tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/tokens/LuceneTokenCounter.java
* (delete) tika-eval/src/main/resources/common_tokens/mal
* (delete) tika-eval/src/main/resources/common_tokens/ron
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/div
* (delete)
tika-eval/src/test/resources/test-dirs/extractsA/file3_attachBNotA.doc.json
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/URLEmailNormalizingFilterFactory.java
* (delete) tika-eval/src/main/resources/common_tokens/ces
* (delete) tika-eval/src/main/resources/common_tokens/nld
* (delete) tika-eval/src/main/resources/common_tokens/nds
* (delete)
tika-eval/src/test/resources/test-dirs/extractsA/file10_permahang.txt.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/nld
* (delete) tika-eval/src/main/resources/common_tokens/ast
* (delete) tika-eval/src/main/java/org/apache/tika/eval/tokens/TokenIntPair.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/mlt
* (delete) tika-eval/src/main/resources/common_tokens/spa
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/kat
* (add)
tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/util/LanguageIdTest.java
* (delete) tika-eval/src/test/resources/test-dirs/extractsB/file12_es.txt.json
* (delete) tika-eval/src/main/resources/common_tokens/jpn
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/util/EvalExceptionUtils.java
* (delete)
tika-eval/src/test/resources/test-dirs/extractsA/file4_emptyB.pdf.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ron
* (delete) tika-eval/src/main/java/org/apache/tika/eval/db/DBBuffer.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/langid/LanguageIDWrapper.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ita
* (delete) tika-eval/src/main/resources/common_tokens/mkd
* (delete) tika-eval/src/main/java/org/apache/tika/eval/tokens/TokenCounts.java
* (delete) tika-eval/src/main/resources/common_tokens/div
* (delete) tika-eval/src/test/java/org/apache/tika/eval/ProfilerBatchTest.java
* (delete)
tika-eval/src/test/resources/test-dirs/extractsB/file13_attachANotB.doc.txt
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/swa
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ekk
* (delete)
tika-eval/src/test/resources/test-dirs/extractsA/file5_emptyA.pdf.json
* (delete) tika-eval/src/main/resources/common_tokens/hin
* (delete) tika-eval/src/main/java/org/apache/tika/eval/db/Cols.java
* (delete) tika-eval/src/main/resources/common_tokens/cym
* (delete) tika-eval/src/main/java/org/apache/tika/eval/db/MimeBuffer.java
* (delete) tika-eval/src/main/resources/common_tokens/sun
* (delete) tika-eval/src/main/resources/common_tokens/zul
* (delete) tika-eval/src/main/resources/common_tokens/cat
* (edit) tika-eval/pom.xml
* (delete) tika-eval/src/test/java/org/apache/tika/eval/SimpleComparerTest.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/AnalyzerDeserializer.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/xho
* (add) tika-eval/tika-eval-app/pom.xml
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/CommonTokenCountManager.java
* (delete) tika-eval/src/test/resources/test-dirs/raw_input/file1.pdf
* (delete) tika-eval/src/main/resources/common_tokens/nno
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/TextProfileSignature.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/fao
* (delete)
tika-eval/src/test/resources/test-dirs/raw_input/file2_attachANotB.doc
* (delete) tika-eval/src/main/java/org/apache/tika/eval/XMLErrorLogUpdater.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/pol
* (delete) tika-eval/src/main/resources/common_tokens/ell
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/TopNTokens.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ckb
* (delete) tika-eval/src/main/resources/db.properties
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/BasicTokenCountStatsCalculator.java
* (delete) tika-eval/src/main/resources/common_tokens/hrv
* (delete) tika-eval/src/main/resources/common_tokens/aze
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/batch/EvalConsumersBuilder.java
* (delete) tika-eval/src/main/resources/common_tokens/kor
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/hye
* (delete) tika-eval/src/main/resources/common_tokens/nan
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/TokenCountStatsCalculator.java
* (delete) tika-eval/src/main/resources/common_tokens/heb
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tools/LeipzigSampler.java
* (delete) tika-eval/src/main/resources/common_tokens/oci
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/che
* (delete) tika-eval/src/main/resources/common_tokens/tgl
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/asm
* (delete) tika-eval/src/test/resources/test-dirs/extractsA/file1.pdf.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/hat
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/tuk
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/san
* (delete)
tika-eval/src/test/resources/test-dirs/batch-logs/batch-process-fatal.xml
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/pus
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/amh
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/fra
* (delete) tika-eval/src/main/resources/common_tokens/lvs
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/reports/XLSXNumFormatter.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/lim
* (delete) tika-eval/src/main/resources/common_tokens/pnb
* (delete) tika-eval/src/main/resources/common_tokens/glg
* (delete) tika-eval/src/main/resources/common_tokens/vol
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenIntPair.java
* (add)
tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/metadata/TikaEvalMetadataFilterTest.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/CJKBigramAwareLengthFilterFactory.java
* (delete) tika-eval/src/main/resources/common_tokens/kur
* (delete) tika-eval/src/main/resources/common_tokens/yid
* (delete)
tika-eval/src/test/resources/test-dirs/extractsA/file17_tagsOutOfOrder.json
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/AnalyzerDeserializer.java
* (delete) tika-eval/src/main/resources/common_tokens/mri
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/kor
* (delete)
tika-eval/src/test/java/org/apache/tika/eval/io/ExtractReaderTest.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/tha
* (delete)
tika-eval/src/test/resources/test-dirs/extractsB/file7_badJson.pdf.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/lvs
* (delete) tika-eval/src/main/resources/common_tokens/tel
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/TextSha256Signature.java
* (delete) tika-eval/src/main/resources/common_tokens/bre
* (delete) tika-eval/src/main/resources/common_tokens/mhr
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/zul
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/CommonTokensHellinger.java
* (delete)
tika-eval/src/test/resources/test-dirs/extractsB/file6_accessEx.pdf.json
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/AnalyzerManager.java
* (delete)
tika-eval/src/test/resources/test-dirs/extractsB/file3_attachBNotA.doc.json
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/TokenStatistics.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/URLEmailNormalizingFilterFactory.java
* (delete) tika-eval/src/main/resources/common_tokens/isl
* (delete) tika-eval/src/main/resources/common_tokens/tgk
* (delete) tika-eval/src/test/resources/test-dirs/extractsB/file15_tags.html
* (delete) tika-eval/src/main/java/org/apache/tika/eval/db/ColInfo.java
* (delete) tika-eval/src/main/java/org/apache/tika/eval/EvalFilePaths.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/afr
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/TokenCountStatsCalculator.java
* (delete) tika-eval/src/main/resources/common_tokens/snd
* (delete) tika-eval/src/main/resources/common_tokens/cmn
* (delete) tika-eval/src/main/resources/common_tokens/bak
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/CommonTokenResult.java
* (delete) tika-eval/src/main/resources/common_tokens/ltz
* (delete) tika-eval/src/main/resources/common_tokens/ceb
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ell
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/TextProfileSignature.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/LanguageAwareTokenCountStats.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/deu
* (delete) tika-eval/src/main/resources/log4j.properties
* (add)
tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/textstats/TextStatsTest.java
* (delete) tika-eval/src/main/java/org/apache/tika/eval/util/ContentTags.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/CommonTokenCountManager.java
* (delete) tika-eval/src/test/resources/test-dirs/extractsA/file8_IOEx.pdf.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/sun
* (add)
tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/util/MimeUtilTest.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ceb
* (delete) tika-eval/src/main/resources/common_tokens/lug
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/LangModel.java
* (delete) tika-eval/src/main/resources/common_tokens/por
* (delete) tika-eval/src/main/resources/comparison-reports-pg.xml
* (delete)
tika-eval/src/test/java/org/apache/tika/eval/db/AbstractBufferTest.java
* (delete) tika-eval/src/main/resources/common_tokens/urd
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/CompositeTextStatsCalculator.java
* (delete) tika-eval/src/test/resources/common_tokens/zh-tw
* (delete) tika-eval/src/test/java/org/apache/tika/eval/ComparerBatchTest.java
* (add)
tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/langid/LangIdTest.java
* (delete) tika-eval/src/main/resources/profile-reports.xml
* (delete) tika-eval/src/main/resources/common_tokens/slv
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/tgl
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/nno
* (edit)
tika-example/src/main/java/org/apache/tika/example/TextStatsFromTikaEval.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/guj
* (delete) tika-eval/src/test/java/org/apache/tika/MockDBWriter.java
* (delete) tika-eval/src/main/resources/common_tokens/mlt
* (delete) tika-eval/src/main/resources/common_tokens/xho
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ast
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/mkd
* (delete) tika-eval/src/main/resources/common_tokens/fin
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/CommonTokensKLDNormed.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/fin
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/azj
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/CommonTokensBhattacharyya.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/tam
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/tgk
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/TextStatsCalculator.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenContraster.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/jpn
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/pnb
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/TokenEntropy.java
* (delete) tika-eval/src/main/resources/common_tokens/gle
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/kur
* (delete) tika-eval/src/main/resources/common_tokens/jav
* (delete) tika-eval/src/test/resources/test-dirs/raw_input/file9_noextract.txt
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/batch/ExtractProfilerBuilder.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/yid
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/est
* (delete)
tika-eval/src/test/java/org/apache/tika/eval/reports/ResultsReporterTest.java
* (delete) tika-eval/src/main/resources/common_tokens/guj
* (delete) tika-eval/src/test/resources/test-dirs/extractsB/file8_IOEx.pdf.json
* (delete) tika-eval/src/main/resources/common_tokens/rus
* (delete) tika-eval/src/test/java/org/apache/tika/eval/AnalyzerManagerTest.java
* (delete) tika-eval/src/test/resources/test-dirs/raw_input/file11_oom.txt
* (delete) tika-eval/src/main/resources/common_tokens/war
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/util/ContentTagParser.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/hrv
* (delete) tika-eval/src/main/resources/common_tokens/asm
* (delete) tika-eval/src/main/java/org/apache/tika/eval/db/H2Util.java
* (delete)
tika-eval/src/test/resources/test-dirs/extractsA/file6_accessEx.pdf.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/epo
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/eus
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/war
* (delete) tika-eval/src/main/resources/common_tokens/deu
* (delete) tika-eval/src/main/resources/common_tokens/uzb
* (delete) tika-eval/src/main/resources/common_tokens/tuk
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ori
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/CommonTokens.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/batch/DBConsumersManager.java
* (delete) tika-eval/src/main/resources/common_tokens/nep
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/TokenCountPriorityQueue.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/TokenEntropy.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/CommonTokensKLDivergence.java
* (delete) tika-eval/src/main/resources/common_tokens/pan
* (delete) tika-eval/src/main/resources/common_tokens/srp
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/TokenContraster.java
* (delete) tika-eval/src/main/resources/common_tokens/lim
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/mon
* (delete) tika-eval/src/test/java/org/apache/tika/eval/util/LanguageIdTest.java
* (delete)
tika-eval/src/test/java/org/apache/tika/eval/textstats/TextStatsTest.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/ContentLengthCalculator.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/reports/ResultsReporter.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/msa
* (delete) tika-eval/src/main/java/org/apache/tika/eval/db/AbstractDBBuffer.java
* (delete) tika-eval/src/test/resources/test-dirs/raw_input/file8_IOEx.pdf
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/batch/ExtractComparerBuilder.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/nep
* (delete) tika-eval/src/main/resources/common_tokens/ckb
* (delete) tika-eval/src/main/java/org/apache/tika/eval/TikaEvalCLI.java
* (delete) tika-eval/src/main/resources/common_tokens/amh
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/srp
* (delete) tika-eval/src/test/resources/test-dirs/extractsA/file15_tags.json
* (delete) tika-eval/src/main/resources/common_tokens/ind
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/tat
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/TokenCountPriorityQueue.java
* (delete) tika-eval/src/main/resources/common_tokens/kin
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/lug
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/por
* (delete)
tika-eval/src/test/resources/test-dirs/extractsB/file2_attachANotB.doc.json
* (delete) tika-eval/src/main/resources/tika-eval-file-profiler-config.xml
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/CJKBigramAwareLengthFilterFactory.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/bul
* (add) tika-eval/tika-eval-core/src/main/resources/lucene-analyzers.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/bak
* (delete) tika-eval/src/main/resources/common_tokens/plt
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/cym
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/fas
* (delete) tika-eval/src/main/resources/common_tokens/uig
* (delete) tika-eval/src/main/resources/common_tokens/mon
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/kir
* (delete) tika-eval/src/main/resources/common_tokens/lat
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/nds
* (delete) tika-eval/src/main/resources/common_tokens/ara
* (delete) tika-eval/src/main/resources/common_tokens/lit
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tokens/AlphaIdeographFilterFactory.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/CommonTokensBhattacharyya.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ltz
* (delete) tika-eval/src/main/resources/common_tokens/hat
* (delete) tika-eval/src/main/resources/common_tokens/ukr
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/ContrastStatistics.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/fry
* (delete) tika-eval/src/main/resources/common_tokens/vie
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/CommonTokensCosine.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/ContentLengthCalculator.java
* (delete) tika-eval/src/main/resources/common_tokens/bos
* (delete) tika-eval/src/main/java/org/apache/tika/eval/tools/LeipzigHelper.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/kin
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/CommonTokens.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/hin
* (delete)
tika-eval/src/test/resources/test-dirs/raw_input/file3_attachBNotA.doc
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenStatistics.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/reports/XSLXCellFormatter.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/gsw
* (delete) tika-eval/src/main/resources/common_tokens/tat
* (delete) tika-eval/src/main/resources/common_tokens/dan
* (delete)
tika-eval/src/test/java/org/apache/tika/eval/io/FatalExceptionReaderTest.java
* (delete) tika-eval/src/main/java/org/apache/tika/eval/FileProfiler.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/rus
* (delete) tika-eval/src/main/resources/common_tokens/mar
* (delete) tika-eval/src/main/resources/common_tokens/ori
* (delete) tika-eval/src/test/resources/test-dirs/extractsB/file11_oom.txt.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/lav
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/mal
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/tur
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/gle
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/aze
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/heb
* (delete) tika-eval/src/main/resources/lucene-analyzers.json
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/nan
* (delete)
tika-eval/src/test/resources/test-dirs/extractsB/file14_diffAttachOrder.json
* (delete) tika-eval/src/main/java/org/apache/tika/eval/tokens/TokenCounter.java
* (delete) tika-eval/src/main/resources/common_tokens/som
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/TextStatsCalculator.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/cmn
* (delete) tika-eval/src/test/resources/common_tokens/zh-cn
* (delete) tika-eval/src/main/resources/common_tokens/sin
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/lat
* (delete) tika-eval/src/main/resources/common_tokens/ita
* (delete)
tika-eval/src/test/resources/single-file-profiler-crawl-extract-config.xml
* (delete) tika-eval/src/main/resources/common_tokens/hye
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/ukr
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/dan
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/util/ContentTags.java
* (delete) tika-eval/src/main/resources/common_tokens/min
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/eng
* (delete) tika-eval/src/main/resources/common_tokens/tam
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/jav
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/bos
* (delete) tika-eval/src/main/resources/common_tokens/tur
* (add)
tika-eval/tika-eval-core/src/test/java/org/apache/tika/eval/core/tokens/TokenCounterTest.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/UnicodeBlockCounter.java
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/CompositeTextStatsCalculator.java
* (delete) tika-eval/src/main/resources/common_tokens/ban
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tools/SlowCompositeReaderWrapper.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenCounts.java
* (delete) tika-eval/src/test/java/org/apache/tika/eval/util/MimeUtilTest.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/mhr
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/mlg
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/sin
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/textstats/UnicodeBlockCounter.java
* (delete) tika-eval/src/main/resources/common_tokens/bul
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/tools/TopCommonTokenCounter.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/spa
* (delete) tika-eval/src/main/java/org/apache/tika/eval/reports/Report.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/mri
* (delete) tika-eval/src/main/resources/common_tokens/kaz
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/tel
* (delete) tika-eval/src/main/java/org/apache/tika/eval/io/XMLLogMsgHandler.java
* (delete) tika-eval/src/main/java/org/apache/tika/eval/db/TableInfo.java
* (delete) tika-eval/src/main/resources/common_tokens/swa
* (delete) tika-eval/src/main/resources/common_tokens/fas
* (delete) tika-eval/src/main/resources/common_tokens/fry
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/BytesRefCalculator.java
* (delete) tika-eval/src/main/resources/common_tokens/swe
* (delete)
tika-eval/src/test/resources/test-dirs/extractsA/file2_attachANotB.doc.json
* (delete)
tika-eval/src/test/java/org/apache/tika/eval/tokens/TokenCounterTest.java
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/TokenCountPriorityQueue.java
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/mar
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/metadata/TikaEvalMetadataFilter.java
* (delete) tika-eval/src/main/resources/common_tokens/kir
* (delete) tika-eval/src/main/resources/common_tokens/san
* (delete) tika-eval/src/main/resources/common_tokens/che
* (delete) tika-eval/src/test/java/org/apache/tika/eval/TikaEvalCLITest.java
* (delete)
tika-eval/src/test/java/org/apache/tika/eval/metadata/TikaEvalMetadataFilterTest.java
* (delete) tika-eval/src/test/resources/common_tokens/en
* (delete) tika-eval/src/main/resources/common_tokens/ekk
* (delete)
tika-eval/src/main/java/org/apache/tika/eval/textstats/TokenLengths.java
* (delete) tika-eval/src/main/resources/common_tokens/eng
* (delete) tika-eval/src/main/resources/common_tokens/azj
* (add) tika-eval/tika-eval-core/src/main/resources/common_tokens/kan
* (add)
tika-eval/tika-eval-core/src/main/java/org/apache/tika/eval/core/tokens/AlphaIdeographFilterFactory.java
> Modularize tika-eval into core and app for 2.0.0
> ------------------------------------------------
>
> Key: TIKA-3240
> URL: https://issues.apache.org/jira/browse/TIKA-3240
> Project: Tika
> Issue Type: Task
> Components: tika-eval
> Reporter: Tim Allison
> Assignee: Tim Allison
> Priority: Minor
> Fix For: 2.0.0
>
>
> In keeping with modularity we're adding in Tika 2.0.0, let's break tika-eval
> into core and app. This will allow users who don't want the db and poi
> dependencies to skip them in tika-eval-core.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)