[
https://issues.apache.org/jira/browse/LUCENE-7805?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15984922#comment-15984922
]
Steve Rowe commented on LUCENE-7805:
------------------------------------
Another reproducing failure, this one on branch_6x, from my Jenkins, no
FlattenGraphFilter here though:
{noformat}
Checking out Revision b90bfaba1f065598033b60f0ba5ffaa40053eb42
(refs/remotes/origin/branch_6x)
[...]
[junit4] Suite: org.apache.lucene.analysis.core.TestRandomChains
[junit4] 2> TEST FAIL: useCharFilter=false
text='\u26a7\u26e4\u26e7\u2672\u2694\u2604\u26a5\u26d1
\u0566\u054e\u057d\u0553\u057f\u0549 os\uecda\ud92c\udcd2 fhyysvvo vzebx
\u30b2\u30d7\u30d8\u30dd\u30e3\u30f5\u30ea\u30dd\u30f7\u30ae\u30e6\u30c9
\uaa3e\uaa1a\uaa5b\uaa43\uaa49\uaa53\uaa19\uaa4f\uaa5c gvrfm fe '
[junit4] 2> Exception from random analyzer:
[junit4] 2> charfilters=
[junit4] 2>
org.apache.lucene.analysis.charfilter.HTMLStripCharFilter(java.io.StringReader@24cfdcc4)
[junit4] 2>
org.apache.lucene.analysis.fa.PersianCharFilter(org.apache.lucene.analysis.charfilter.HTMLStripCharFilter@12dc3e69)
[junit4] 2> tokenizer=
[junit4] 2>
org.apache.lucene.analysis.standard.UAX29URLEmailTokenizer(org.apache.lucene.util.AttributeFactory$1@cf373344)
[junit4] 2> filters=
[junit4] 2>
org.apache.lucene.analysis.gl.GalicianMinimalStemFilter(ValidatingTokenFilter@aec428a
term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,flags=0,payload=null,keyword=false)
[junit4] 2>
org.apache.lucene.analysis.miscellaneous.KeywordRepeatFilter(ValidatingTokenFilter@79bef7cf
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@55fed8e4
term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,flags=0,payload=null,keyword=false,
20)
[junit4] 2>
org.apache.lucene.analysis.shingle.ShingleFilter(ValidatingTokenFilter@226ff415
term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,flags=0,payload=null,keyword=false,
32)
[junit4] 2> offsetsAreCorrect=false
[junit4] 2> NOTE: reproduce with: ant test -Dtestcase=TestRandomChains
-Dtests.method=testRandomChainsWithLargeStrings -Dtests.seed=19C23372FBAA95FB
-Dtests.slow=true -Dtests.locale=bg -Dtests.timezone=Pacific/Ponape
-Dtests.asserts=true -Dtests.file.encoding=UTF-8
[junit4] ERROR 0.47s J7 |
TestRandomChains.testRandomChainsWithLargeStrings <<<
[junit4] > Throwable #1: java.lang.IllegalArgumentException: startOffset
must be non-negative, and endOffset must be >= startOffset; got
startOffset=41,endOffset=40
[junit4] > at
__randomizedtesting.SeedInfo.seed([19C23372FBAA95FB:73998C63A2E4B508]: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.BaseTokenStreamTestCase.checkAnalysisConsistency(BaseTokenStreamTestCase.java:730)
[junit4] > at
org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData(BaseTokenStreamTestCase.java:641)
[junit4] > at
org.apache.lucene.analysis.BaseTokenStreamTestCase.checkRandomData(BaseTokenStreamTestCase.java:539)
[junit4] > at
org.apache.lucene.analysis.core.TestRandomChains.testRandomChainsWithLargeStrings(TestRandomChains.java:880)
[junit4] > at java.lang.Thread.run(Thread.java:745)
[junit4] 2> NOTE: test params are: codec=Asserting(Lucene62):
{dummy=PostingsFormat(name=Memory doPackFST= true)}, docValues:{},
maxPointsInLeafNode=920, maxMBSortInHeap=6.66438430375091,
sim=RandomSimilarity(queryNorm=false,coord=crazy): {}, locale=bg,
timezone=Pacific/Ponape
[junit4] 2> NOTE: Linux 4.1.0-custom2-amd64 amd64/Oracle Corporation
1.8.0_77 (64-bit)/cpus=16,threads=1,free=383185632,total=512229376
{noformat}
> TestRandomChains.testRandomChainsWithLargeStrings() failure
> -----------------------------------------------------------
>
> Key: LUCENE-7805
> URL: https://issues.apache.org/jira/browse/LUCENE-7805
> Project: Lucene - Core
> Issue Type: Bug
> Reporter: Steve Rowe
>
> My Jenkins found a reproducing master seed, looks like FlattenGraphFilter is
> where the problem happens:
> {noformat}
> Checking out Revision 680f4d7fd378868254786107de92a894758f667c
> (refs/remotes/origin/master)
> [...]
> [junit4] Suite: org.apache.lucene.analysis.core.TestRandomChains
> [junit4] 2> TEST FAIL: useCharFilter=false text='\u0003J\u522f nwqbl
> uwtps ob zdyokom ){0'
> [junit4] 2> Exception from random analyzer:
> [junit4] 2> charfilters=
> [junit4] 2>
> org.apache.lucene.analysis.charfilter.HTMLStripCharFilter(java.io.StringReader@3ab617ae,
> [])
> [junit4] 2>
> org.apache.lucene.analysis.charfilter.HTMLStripCharFilter(org.apache.lucene.analysis.charfilter.HTMLStripCharFilter@23e3c717)
> [junit4] 2> tokenizer=
> [junit4] 2> org.apache.lucene.analysis.ngram.NGramTokenizer(9, 43)
> [junit4] 2> filters=
> [junit4] 2>
> org.apache.lucene.analysis.miscellaneous.CodepointCountFilter(ValidatingTokenFilter@6b4708ea
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,
> 33, 44)
> [junit4] 2>
> org.apache.lucene.analysis.shingle.ShingleFilter(ValidatingTokenFilter@5533fb25
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,
> <EMAIL>)
> [junit4] 2>
> org.apache.lucene.analysis.core.FlattenGraphFilter(ValidatingTokenFilter@4ef4c44
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word)
> [junit4] 2>
> org.apache.lucene.analysis.miscellaneous.KeepWordFilter(ValidatingTokenFilter@15baa1c7
>
> term=,bytes=[],startOffset=0,endOffset=0,positionIncrement=1,positionLength=1,type=word,
> [akbnucwt, vrkwm, jtomhk, jxgmfalr])
> [junit4] 2> offsetsAreCorrect=true
> [junit4] 2> NOTE: reproduce with: ant test -Dtestcase=TestRandomChains
> -Dtests.method=testRandomChainsWithLargeStrings -Dtests.seed=E9460213902F2F82
> -Dtests.slow=true -Dtests.locale=fi-FI -Dtests.timezone=Europe/Malta
> -Dtests.asserts=true -Dtests.file.encoding=US-ASCII
> [junit4] FAILURE 0.19s J7 |
> TestRandomChains.testRandomChainsWithLargeStrings <<<
> [junit4] > Throwable #1: java.lang.AssertionError: outputEndNode=3 vs
> inputTo=2
> [junit4] > at
> __randomizedtesting.SeedInfo.seed([E9460213902F2F82:831DBD02C9610F71]:0)
> [junit4] > at
> org.apache.lucene.analysis.core.FlattenGraphFilter.incrementToken(FlattenGraphFilter.java:335)
> [junit4] > at
> org.apache.lucene.analysis.ValidatingTokenFilter.incrementToken(ValidatingTokenFilter.java:67)
> [junit4] > at
> org.apache.lucene.analysis.FilteringTokenFilter.incrementToken(FilteringTokenFilter.java:51)
> [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.testRandomChainsWithLargeStrings(TestRandomChains.java:880)
> [junit4] > at java.lang.Thread.run(Thread.java:745)
> [junit4] 2> NOTE: test params are: codec=Asserting(Lucene70):
> {dummy=PostingsFormat(name=LuceneVarGapFixedInterval)}, docValues:{},
> maxPointsInLeafNode=807, maxMBSortInHeap=5.007333045299232,
> sim=RandomSimilarity(queryNorm=true): {}, locale=fi-FI, timezone=Europe/Malta
> [junit4] 2> NOTE: Linux 4.1.0-custom2-amd64 amd64/Oracle Corporation
> 1.8.0_77 (64-bit)/cpus=16,threads=1,free=492062472,total=525336576
> {noformat}
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
