[
https://issues.apache.org/jira/browse/LUCENE-8371?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16525750#comment-16525750
]
Steve Rowe commented on LUCENE-8371:
------------------------------------
Another reproducing seed from
[https://builds.apache.org/job/Lucene-Solr-NightlyTests-7.x/249/]:
{noformat}
Checking out Revision dc2c9e98632ec7ceb7fb1bee336ec0ecac377270
(refs/remotes/origin/branch_7x)
[...]
[junit4] Suite: org.apache.lucene.analysis.core.TestRandomChains
[junit4] 2> TEST FAIL: useCharFilter=false text='c
\u052c\u8443\ueedd\ua291x\ue16d\ud87b\ude42\u7e7f jnssft
\u1df5\u1df3\u1dcc\u1dc8\u1ddf\u1ddf\u1dc2\u1de8\u1dde\u1de1 t mgzelt ?'
[junit4] 2> Exception from random analyzer:
[junit4] 2> charfilters=
[junit4] 2>
org.apache.lucene.analysis.charfilter.MappingCharFilter(org.apache.lucene.analysis.charfilter.NormalizeCharMap@1490adc8,
java.io.StringReader@6d79ac4d)
[junit4] 2>
org.apache.lucene.analysis.charfilter.HTMLStripCharFilter(org.apache.lucene.analysis.charfilter.MappingCharFilter@5f9d7e8f)
[junit4] 2> tokenizer=
[junit4] 2>
org.apache.lucene.analysis.standard.UAX29URLEmailTokenizer(org.apache.lucene.util.AttributeFactory$1@7cd0d664)
[junit4] 2> filters=
[junit4] 2>
Conditional:org.apache.lucene.analysis.no.NorwegianLightStemFilter(OneTimeWrapper@2904482
term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,termFrequency=1,flags=0,payload=null,keyword=false)
[junit4] 2>
Conditional:org.apache.lucene.analysis.shingle.FixedShingleFilter(OneTimeWrapper@6b50d367
term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,termFrequency=1,flags=0,payload=null,keyword=false,
3, <KATAKANA>, <HANGUL>)
[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=testRandomChainsWithLargeStrings -Dtests.seed=319F02FFE4F7A86B
-Dtests.multiplier=2 -Dtests.nightly=true -Dtests.slow=true
-Dtests.linedocsfile=/home/jenkins/jenkins-slave/workspace/Lucene-Solr-NightlyTests-7.x/test-data/enwiki.random.lines.txt
-Dtests.locale=he-IL -Dtests.timezone=Pacific/Gambier -Dtests.asserts=true
-Dtests.file.encoding=US-ASCII
[junit4] FAILURE 16.0s J0 |
TestRandomChains.testRandomChainsWithLargeStrings <<<
[junit4] > Throwable #1: java.lang.AssertionError: finalOffset
expected:<40> but was:<38>
[junit4] > at
__randomizedtesting.SeedInfo.seed([319F02FFE4F7A86B:5BC4BDEEBDB98898]:0)
[junit4] > at
org.apache.lucene.analysis.BaseTokenStreamTestCase.assertTokenStreamContents(BaseTokenStreamTestCase.java:305)
[junit4] > at
org.apache.lucene.analysis.BaseTokenStreamTestCase.assertTokenStreamContents(BaseTokenStreamTestCase.java:320)
[junit4] > at
org.apache.lucene.analysis.BaseTokenStreamTestCase.assertTokenStreamContents(BaseTokenStreamTestCase.java:324)
[junit4] > at
org.apache.lucene.analysis.BaseTokenStreamTestCase.checkAnalysisConsistency(BaseTokenStreamTestCase.java:860)
[junit4] > at
org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData(BaseTokenStreamTestCase.java:659)
[junit4] > at
org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData(BaseTokenStreamTestCase.java:561)
[junit4] > at
org.apache.lucene.analysis.core.TestRandomChains.testRandomChainsWithLargeStrings(TestRandomChains.java:893)
[junit4] > at java.lang.Thread.run(Thread.java:748)
[junit4] 2> NOTE: leaving temporary files on disk at:
/x1/jenkins/jenkins-slave/workspace/Lucene-Solr-NightlyTests-7.x/checkout/lucene/build/analysis/common/test/J0/temp/lucene.analysis.core.TestRandomChains_319F02FFE4F7A86B-001
[junit4] 2> NOTE: test params are: codec=SimpleText,
sim=RandomSimilarity(queryNorm=true): {dummy=DFR GB1}, locale=he-IL,
timezone=Pacific/Gambier
[junit4] 2> NOTE: Linux 3.13.0-88-generic amd64/Oracle Corporation
1.8.0_172 (64-bit)/cpus=4,threads=1,free=269319248,total=336592896
{noformat}
> TestRandomChains.testRandomChainsWithLargeStrings() failure
> -----------------------------------------------------------
>
> Key: LUCENE-8371
> URL: https://issues.apache.org/jira/browse/LUCENE-8371
> Project: Lucene - Core
> Issue Type: Bug
> Components: modules/analysis
> Reporter: Steve Rowe
> Assignee: Alan Woodward
> Priority: Major
>
> Reproducing seed for {{TestRandomChains.testRandomChainsWithLargeStrings()}}
> failure from [https://jenkins.thetaphi.de/job/Lucene-Solr-7.x-Linux/2196/]:
> {noformat}
> Checking out Revision 53ec8224705f4f0d35751b18b3f0168517c43121
> (refs/remotes/origin/branch_7x)
> [...]
> [junit4] Suite: org.apache.lucene.analysis.core.TestRandomChains
> [junit4] 2> TEST FAIL: useCharFilter=true text='\ua97b
> \uebcf\ueb06\uf85b\uf649\uf0b7 esgm s \uabfd
> \ue11c\udbb4\udc48\ue90d\u0142\u0014\u0018 cr \u30ed\u30a8\u30ec\u30e1 <? gr
> \ud835\udf53\ud835\udc58\ud835\ude2b
> \ueff5\uda61\ude33\ud94d\udcbb\udb3b\uddc8\u0738 \ua711\ua719 xqu ygvfwc
> ~?\u0781%'
> [junit4] 2> Exception from random analyzer:
> [junit4] 2> charfilters=
> [junit4] 2>
> org.apache.lucene.analysis.fa.PersianCharFilter(java.io.StringReader@12c9ec6)
> [junit4] 2> tokenizer=
> [junit4] 2> org.apache.lucene.analysis.core.LowerCaseTokenizer()
> [junit4] 2> filters=
> [junit4] 2>
> org.apache.lucene.analysis.hunspell.HunspellStemFilter(ValidatingTokenFilter@17533c4
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,termFrequency=1,keyword=false,
> org.apache.lucene.analysis.hunspell.Dictionary@1e0b337, true, false)
> [junit4] 2>
> Conditional:org.apache.lucene.analysis.no.NorwegianLightStemFilter(OneTimeWrapper@3e3989
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,termFrequency=1,keyword=false)
> [junit4] 2>
> Conditional:org.apache.lucene.analysis.en.EnglishPossessiveFilter(OneTimeWrapper@96b77b
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,termFrequency=1,keyword=false)
> [junit4] 2>
> Conditional:org.apache.lucene.analysis.shingle.FixedShingleFilter(OneTimeWrapper@d4fade
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,termFrequency=1,keyword=false,
> 3)
> [junit4] 2> NOTE: reproduce with: ant test -Dtestcase=TestRandomChains
> -Dtests.method=testRandomChainsWithLargeStrings -Dtests.seed=8C3CDE29C6D4A774
> -Dtests.multiplier=3 -Dtests.slow=true -Dtests.locale=ms
> -Dtests.timezone=Europe/Saratov -Dtests.asserts=true
> -Dtests.file.encoding=UTF-8
> [junit4] FAILURE 0.42s J2 |
> TestRandomChains.testRandomChainsWithLargeStrings <<<
> [junit4] > Throwable #1: java.lang.AssertionError: finalOffset
> expected:<74> but was:<73>
> [junit4] > at
> __randomizedtesting.SeedInfo.seed([8C3CDE29C6D4A774:E66761389F9A8787]:0)
> [junit4] > at
> org.apache.lucene.analysis.BaseTokenStreamTestCase.assertTokenStreamContents(BaseTokenStreamTestCase.java:305)
> [junit4] > at
> org.apache.lucene.analysis.BaseTokenStreamTestCase.assertTokenStreamContents(BaseTokenStreamTestCase.java:320)
> [junit4] > at
> org.apache.lucene.analysis.BaseTokenStreamTestCase.assertTokenStreamContents(BaseTokenStreamTestCase.java:324)
> [junit4] > at
> org.apache.lucene.analysis.BaseTokenStreamTestCase.checkAnalysisConsistency(BaseTokenStreamTestCase.java:860)
> [junit4] > at
> org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData(BaseTokenStreamTestCase.java:659)
> [junit4] > at
> org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData(BaseTokenStreamTestCase.java:561)
> [junit4] > at
> org.apache.lucene.analysis.core.TestRandomChains.testRandomChainsWithLargeStrings(TestRandomChains.java:893)
> [junit4] > at java.lang.Thread.run(Thread.java:748)
> [junit4] 2> NOTE: test params are: codec=Asserting(Lucene70):
> {dummy=PostingsFormat(name=Memory)}, docValues:{}, maxPointsInLeafNode=1890,
> maxMBSortInHeap=7.329943162959591, sim=RandomSimilarity(queryNorm=false): {},
> locale=ms, timezone=Europe/Saratov
> [junit4] 2> NOTE: Linux 4.13.0-41-generic i386/Oracle Corporation
> 1.8.0_172 (32-bit)/cpus=8,threads=1,free=313060856,total=533725184
> {noformat}
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
