You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@solr.apache.org by buchman <bu...@gmail.com> on 2021/03/20 22:42:54 UTC
facet alias with "duplicate" uniqueKey
Hi folks,
I've noticed the following warning in the aliases documentation:
"...Reindexing a document with a different route value for the same ID
produces two distinct documents with the same ID accessible via the
alias..."
When tested such case it seems that really only one doc is retrieved but
when turning on facets they aren't aligned with the result set.
My test:
1) create two collections test1 and test2 and alias named test for both
2) index docs with the same id to both of the collections
{"id":123}
3) querying the alias as followed with explained debug:
http://localhost:8983/solr/test/select?debug.explain.structured=true&debugQuery=on&facet.field=id&facet=on&q=*%3A*
{
"responseHeader":{
"zkConnected":true,
"status":0,
"QTime":25,
"params":{
"q":"*:*",
"facet.field":"id",
"debug.explain.structured":"true",
"facet":"on",
"debugQuery":"on",
"_":"1616269705741"}},
"response":{*"numFound":1*,"start":0,"maxScore":1.0,"numFoundExact":true,"docs":[
{
"id":"123",
"_version_":1694670492462481408}]
},
"facet_counts":{
"facet_queries":{},
"facet_fields":{
*"id":[
"123",2]},*
"facet_ranges":{},
"facet_intervals":{},
"facet_heatmaps":{}},
"debug":{
"track":{
"rid":"-31",
"EXECUTE_QUERY":{
"http://some_ip:8983/solr/test2_shard1_replica_n1/":{
"QTime":"3",
"ElapsedTime":"10",
"RequestPurpose":"GET_TOP_IDS,GET_FACETS,SET_TERM_STATS",
"NumFound":"1",
"Response":"{responseHeader={zkConnected=true,status=0,QTime=3,params={df=_text_,distrib=false,fl=[id,
score],shards.purpose=16404,fsv=true,shard.url=http://some_ip:8983/solr/test2_shard1_replica_n1/,rid=-31,wt=javabin,_=1616269705741,facet.field=id,f.id.facet.mincount=0,debug=[false,
timing,
track],start=0,f.id.facet.limit=160,collection=test1,test2,rows=10,debug.explain.structured=true,version=2,q=*:*,omitHeader=false,requestPurpose=GET_TOP_IDS,GET_FACETS,SET_TERM_STATS,NOW=1616270594521,isShard=true,facet=on,debugQuery=false}},response={numFound=1,numFoundExact=true,start=0,maxScore=1.0,docs=[SolrDocument{id=123,
score=1.0}]},sort_values={},facet_counts={facet_queries={},facet_fields={id={123=1}},facet_ranges={},facet_intervals={},facet_heatmaps={}},debug={facet-debug={elapse=0,sub-facet=[{processor=SimpleFacets,elapse=0,action=field
facet,maxThreads=0,sub-facet=[{elapse=0,requestedMethod=not
specified,appliedMethod=FC,inputDocSetSize=1,field=id,numBuckets=2}]}]},timing={time=2.0,prepare={time=0.0,query={time=0.0},facet={time=0.0},facet_module={time=0.0},mlt={time=0.0},highlight={time=0.0},stats={time=0.0},expand={time=0.0},terms={time=0.0},debug={time=0.0}},process={time=2.0,query={time=0.0},facet={time=1.0},facet_module={time=0.0},mlt={time=0.0},highlight={time=0.0},stats={time=0.0},expand={time=0.0},terms={time=0.0},debug={time=0.0}}}}}"},
"http://some_ip:8983/solr/test1_shard1_replica_n1/":{
"QTime":"2",
"ElapsedTime":"12",
"RequestPurpose":"GET_TOP_IDS,GET_FACETS,SET_TERM_STATS",
"NumFound":"1",
"Response":"{responseHeader={zkConnected=true,status=0,QTime=2,params={df=_text_,distrib=false,fl=[id,
score],shards.purpose=16404,fsv=true,shard.url=http://some_ip:8983/solr/test1_shard1_replica_n1/,rid=-31,wt=javabin,_=1616269705741,facet.field=id,f.id.facet.mincount=0,debug=[false,
timing,
track],start=0,f.id.facet.limit=160,collection=test1,test2,rows=10,debug.explain.structured=true,version=2,q=*:*,omitHeader=false,requestPurpose=GET_TOP_IDS,GET_FACETS,SET_TERM_STATS,NOW=1616270594521,isShard=true,facet=on,debugQuery=false}},response={numFound=1,numFoundExact=true,start=0,maxScore=1.0,docs=[SolrDocument{id=123,
score=1.0}]},sort_values={},facet_counts={facet_queries={},facet_fields={id={123=1}},facet_ranges={},facet_intervals={},facet_heatmaps={}},debug={facet-debug={elapse=0,sub-facet=[{processor=SimpleFacets,elapse=0,action=field
facet,maxThreads=0,sub-facet=[{elapse=0,requestedMethod=not
specified,appliedMethod=FC,inputDocSetSize=1,field=id,numBuckets=2}]}]},timing={time=2.0,prepare={time=0.0,query={time=0.0},facet={time=0.0},facet_module={time=0.0},mlt={time=0.0},highlight={time=0.0},stats={time=0.0},expand={time=0.0},terms={time=0.0},debug={time=0.0}},process={time=2.0,query={time=0.0},facet={time=1.0},facet_module={time=0.0},mlt={time=0.0},highlight={time=0.0},stats={time=0.0},expand={time=0.0},terms={time=0.0},debug={time=0.0}}}}}"}},
"GET_FIELDS":{
"http://some_ip:8983/solr/test2_shard1_replica_n1/":{
"QTime":"5",
"ElapsedTime":"8",
"RequestPurpose":"GET_FIELDS,GET_DEBUG,SET_TERM_STATS",
"NumFound":"1",
"Response":"{responseHeader={zkConnected=true,status=0,QTime=5,params={facet.field=id,df=_text_,distrib=false,debug=[timing,
track],shards.purpose=16704,collection=test1,test2,shard.url=http://some_ip:8983/solr/test2_shard1_replica_n1/,rows=10,rid=-31,debug.explain.structured=true,version=2,q=*:*,omitHeader=false,requestPurpose=GET_FIELDS,GET_DEBUG,SET_TERM_STATS,NOW=1616270594521,ids=123,isShard=true,facet=false,wt=javabin,debugQuery=true,_=1616269705741}},response={numFound=1,numFoundExact=true,start=0,docs=[SolrDocument{id=123,
_version_=1694670492462481408}]},debug={rawquerystring=*:*,querystring=*:*,parsedquery=MatchAllDocsQuery(*:*),parsedquery_toString=*:*,explain={123={match=true,value=1.0,description=*:*}},QParser=LuceneQParser,timing={time=4.0,prepare={time=0.0,query={time=0.0},facet={time=0.0},facet_module={time=0.0},mlt={time=0.0},highlight={time=0.0},stats={time=0.0},expand={time=0.0},terms={time=0.0},debug={time=0.0}},process={time=4.0,query={time=0.0},facet={time=0.0},facet_module={time=0.0},mlt={time=0.0},highlight={time=0.0},stats={time=0.0},expand={time=0.0},terms={time=0.0},debug={time=4.0}}}}}"}}},
"facet-debug":{
"elapse":0,
"sub-facet":[{
"processor":"SimpleFacets",
"elapse":0,
"action":"field facet",
"maxThreads":0,
"sub-facet":[{
"elapse":0,
"requestedMethod":"not specified",
"appliedMethod":"FC",
"inputDocSetSize":1,
"field":"id",
"numBuckets":2}]}]},
"timing":{
"time":8.0,
"prepare":{
"time":0.0,
"query":{
"time":0.0},
"facet":{
"time":0.0},
"facet_module":{
"time":0.0},
"mlt":{
"time":0.0},
"highlight":{
"time":0.0},
"stats":{
"time":0.0},
"expand":{
"time":0.0},
"terms":{
"time":0.0},
"debug":{
"time":0.0}},
"process":{
"time":8.0,
"query":{
"time":0.0},
"facet":{
"time":2.0},
"facet_module":{
"time":0.0},
"mlt":{
"time":0.0},
"highlight":{
"time":0.0},
"stats":{
"time":0.0},
"expand":{
"time":0.0},
"terms":{
"time":0.0},
"debug":{
"time":4.0}}},
"rawquerystring":"*:*",
"querystring":"*:*",
"parsedquery":"MatchAllDocsQuery(*:*)",
"parsedquery_toString":"*:*",
"QParser":"LuceneQParser",
"explain":{
"123":{
"match":true,
"value":1.0,
"description":"*:*"}}}}
Expected behavior or bug?
If expected - how should I avoid dups and implement upserts without the
overhead of preliminary queries?
Thanks.
--
Sent from: https://lucene.472066.n3.nabble.com/Solr-User-f472068.html