[
https://issues.apache.org/jira/browse/LUCENE-7711?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16080677#comment-16080677
]
Steve Rowe commented on LUCENE-7711:
------------------------------------
Another reproducing failure on branch_7_0, from my Jenkins:
{noformat}
Checking out Revision 6cdc0060e5c3b93f0764d7e8e441fa21931fe60d
(refs/remotes/origin/branch_7_0)
[...]
[junit4] Suite: org.apache.lucene.analysis.core.TestRandomChains
[junit4] 2> TEST FAIL: useCharFilter=true text='arr]]
[[ja:\u30de\u30b7\u30e5\u30fc\u30fb\u30d1\u30fc\u30eb '
[junit4] 2> Exception from random analyzer:
[junit4] 2> charfilters=
[junit4] 2> tokenizer=
[junit4] 2> org.apache.lucene.analysis.standard.StandardTokenizer()
[junit4] 2> filters=
[junit4] 2>
org.apache.lucene.analysis.miscellaneous.KeywordRepeatFilter(ValidatingTokenFilter@218bc4e4
term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,termFrequency=1,keyword=false)
[junit4] 2>
org.apache.lucene.analysis.core.DecimalDigitFilter(ValidatingTokenFilter@48b9b511
term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,termFrequency=1,keyword=false)
[junit4] 2>
org.apache.lucene.analysis.miscellaneous.HyphenatedWordsFilter(ValidatingTokenFilter@6800dfe4
term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,termFrequency=1,keyword=false)
[junit4] 2>
org.apache.lucene.analysis.cjk.CJKBigramFilter(ValidatingTokenFilter@507e81ab
term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,termFrequency=1,keyword=false)
[junit4] 2> offsetsAreCorrect=false
[junit4] 2> NOTE: download the large Jenkins line-docs file by running
'ant get-jenkins-line-docs' in the lucene directory.
[junit4] 2> NOTE: reproduce with: ant test -Dtestcase=TestRandomChains
-Dtests.method=testRandomChains -Dtests.seed=2577EBB6844BD489
-Dtests.multiplier=2 -Dtests.nightly=true -Dtests.slow=true
-Dtests.linedocsfile=/home/jenkins/lucene-data/enwiki.random.lines.txt
-Dtests.locale=en-ZA -Dtests.timezone=America/Argentina/Jujuy
-Dtests.asserts=true -Dtests.file.encoding=US-ASCII
[junit4] ERROR 18.9s J2 | TestRandomChains.testRandomChains <<<
[junit4] > Throwable #1: java.lang.IllegalArgumentException: startOffset
must be non-negative, and endOffset must be >= startOffset, and offsets must
not go backwards startOffset=11,endOffset=13,lastStartOffset=13 for field
'dummy'
[junit4] > at
__randomizedtesting.SeedInfo.seed([2577EBB6844BD489:1896C2D7C359C949]:0)
[junit4] > at
org.apache.lucene.index.DefaultIndexingChain$PerField.invert(DefaultIndexingChain.java:769)
[junit4] > at
org.apache.lucene.index.DefaultIndexingChain.processField(DefaultIndexingChain.java:431)
[junit4] > at
org.apache.lucene.index.DefaultIndexingChain.processDocument(DefaultIndexingChain.java:393)
[junit4] > at
org.apache.lucene.index.DocumentsWriterPerThread.updateDocument(DocumentsWriterPerThread.java:239)
[junit4] > at
org.apache.lucene.index.DocumentsWriter.updateDocument(DocumentsWriter.java:481)
[junit4] > at
org.apache.lucene.index.IndexWriter.updateDocument(IndexWriter.java:1717)
[junit4] > at
org.apache.lucene.index.IndexWriter.addDocument(IndexWriter.java:1462)
[junit4] > at
org.apache.lucene.index.RandomIndexWriter.addDocument(RandomIndexWriter.java:171)
[junit4] > at
org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData(BaseTokenStreamTestCase.java:650)
[junit4] > at
org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData(BaseTokenStreamTestCase.java:540)
[junit4] > at
org.apache.lucene.analysis.core.TestRandomChains.testRandomChains(TestRandomChains.java:856)
{noformat}
> TestRandomChains.testRandomChains() failure: got startOffset=10,endOffset=9
> ---------------------------------------------------------------------------
>
> Key: LUCENE-7711
> URL: https://issues.apache.org/jira/browse/LUCENE-7711
> Project: Lucene - Core
> Issue Type: Bug
> Reporter: Steve Rowe
>
> Found while beasting TestRandomChains for LUCENE-7708 (note though that the
> failure below reproduces on a clean master checkout):
> {noformat}
> [junit4] Suite: org.apache.lucene.analysis.core.TestRandomChains
> [junit4] 2> TEST FAIL: useCharFilter=false text='\ufac4\u0552H
> \ua954\ua944 \ud0d2\uaddd\ub6cb\uc388\uc344\uca88\ud224\uc462\uaf42 g '
> [junit4] 2> Exception from random analyzer:
> [junit4] 2> charfilters=
> [junit4] 2>
> org.apache.lucene.analysis.charfilter.HTMLStripCharFilter(java.io.StringReader@72c69dd0,
> [<HOST>, <HANGUL>, <IDEOGRAPHIC>, <SOUTHEAST_ASIAN>])
> [junit4] 2> tokenizer=
> [junit4] 2>
> org.apache.lucene.analysis.standard.StandardTokenizer(org.apache.lucene.util.AttributeFactory$1@2ff87e59)
> [junit4] 2> filters=
> [junit4] 2>
> org.apache.lucene.analysis.miscellaneous.KeywordRepeatFilter(ValidatingTokenFilter@2c2ac1cc
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,flags=0,payload=null,keyword=false)
> [junit4] 2>
> org.apache.lucene.analysis.cjk.CJKBigramFilter(ValidatingTokenFilter@51f2f8f0
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,flags=0,payload=null,keyword=false)
> [junit4] 2>
> org.apache.lucene.analysis.shingle.ShingleFilter(ValidatingTokenFilter@2ea3d3ba
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,flags=0,payload=null,keyword=false,
> 49)
> [junit4] 2>
> org.apache.lucene.analysis.in.IndicNormalizationFilter(ValidatingTokenFilter@25d58ed7
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,flags=0,payload=null,keyword=false)
> [junit4] 2> offsetsAreCorrect=false
> [junit4] 2> NOTE: reproduce with: ant test -Dtestcase=TestRandomChains
> -Dtests.method=testRandomChains -Dtests.seed=E532502212098AC7
> -Dtests.slow=true -Dtests.locale=ko-KR -Dtests.timezone=Atlantic/Jan_Mayen
> -Dtests.asserts=true -Dtests.file.encoding=UTF-8
> [junit4] ERROR 0.23s | TestRandomChains.testRandomChains <<<
> [junit4] > Throwable #1: java.lang.IllegalArgumentException:
> startOffset must be non-negative, and endOffset must be >= startOffset; got
> startOffset=10,endOffset=9
> [junit4] > at
> __randomizedtesting.SeedInfo.seed([E532502212098AC7:D8D37943551B9707]:0)
> [junit4] > at
> org.apache.lucene.analysis.tokenattributes.PackedTokenAttributeImpl.setOffset(PackedTokenAttributeImpl.java:110)
> [junit4] > at
> org.apache.lucene.analysis.shingle.ShingleFilter.incrementToken(ShingleFilter.java:345)
> [junit4] > at
> org.apache.lucene.analysis.ValidatingTokenFilter.incrementToken(ValidatingTokenFilter.java:67)
> [junit4] > at
> org.apache.lucene.analysis.in.IndicNormalizationFilter.incrementToken(IndicNormalizationFilter.java:40)
> [junit4] > at
> org.apache.lucene.analysis.ValidatingTokenFilter.incrementToken(ValidatingTokenFilter.java:67)
> [junit4] > at
> org.apache.lucene.analysis.BaseTokenStreamTestCase.checkAnalysisConsistency(BaseTokenStreamTestCase.java:731)
> [junit4] > at
> org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData(BaseTokenStreamTestCase.java:642)
> [junit4] > at
> org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData(BaseTokenStreamTestCase.java:540)
> [junit4] > at
> org.apache.lucene.analysis.core.TestRandomChains.testRandomChains(TestRandomChains.java:853)
> [junit4] > at java.lang.Thread.run(Thread.java:745)
> [junit4] 2> NOTE: test params are: codec=Asserting(Lucene70):
> {dummy=PostingsFormat(name=LuceneVarGapFixedInterval)}, docValues:{},
> maxPointsInLeafNode=542, maxMBSortInHeap=7.773738401752009,
> sim=RandomSimilarity(queryNorm=false): {}, locale=ko-KR,
> timezone=Atlantic/Jan_Mayen
> [junit4] 2> NOTE: Mac OS X 10.12.3 x86_64/Oracle Corporation 1.8.0_112
> (64-bit)/cpus=8,threads=1,free=225448184,total=257425408
> [junit4] 2> NOTE: All tests run in this JVM: [TestRandomChains]
> [junit4] Completed [1/1 (1!)] in 1.92s, 1 test, 1 error <<< FAILURES!
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
