Skip to content

call keywords expansion results from ram vs disk chunks #3113

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 8 additions & 9 deletions src/queryfilter.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -85,15 +85,14 @@ void ISphQueryFilter::GetKeywords ( CSphVector<CSphKeywordInfo> & dKeywords, Exp
}
}

if ( !bExpanded || !tWordlist.m_dExpanded.GetLength() )
{
CSphKeywordInfo& tInfo = dKeywords.Add();
tInfo.m_sTokenized = (const char*)sWord;
tInfo.m_sNormalized = (const char*)sWord;
tInfo.m_iDocs = iDocs;
tInfo.m_iHits = iHits;
tInfo.m_iQpos = iQpos;
}
// lets keep original term to get the same result from empty disk chunks of the RT index or chunks wo matches
CSphKeywordInfo& tInfo = dKeywords.Add();
tInfo.m_sTokenized = (const char*)sWord;
tInfo.m_sNormalized = (const char*)sWord;
tInfo.m_iDocs = iDocs;
tInfo.m_iHits = iHits;
tInfo.m_iQpos = iQpos;

} else
{
AddKeywordStats ( sWord, sTokenized, iQpos, dKeywords );
Expand Down
30 changes: 30 additions & 0 deletions test/clt-tests/bugs/489-different-result-with-ramchunk.rec
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
––– block: ../base/start-searchd –––
––– input –––
mysql -P9306 -h0 -e "drop table if exists t; create table t(name text) min_infix_len='2' diskchunk_flush_write_timeout = '9999';"
––– output –––
––– input –––
mysql -P9306 -h0 -e "insert into t values(1, 'LIMITED LIABILIYT COMPANY TVK'); insert into t values(2, 'LIPITED LIABILITY COMPANY ABCDEF'); insert into t values(3, 'LIXITED LIABILITY COMPANY XXXXXX');"
––– output –––
––– input –––
mysql -P9306 -h0 -e "call keywords('LI\\?ITED LIQBILITY CO\\?PQNY TVK', 't')\G" | grep normalized | sort
––– output –––
normalized: co?pqny
normalized: li?ited
normalized: limited
normalized: lipited
normalized: liqbility
normalized: lixited
normalized: tvk
––– input –––
mysql -P9306 -h0 -e "flush ramchunk t"
––– output –––
––– input –––
mysql -P9306 -h0 -e "call keywords('LI\\?ITED LIQBILITY CO\\?PQNY TVK', 't')\G" | grep normalized | sort
––– output –––
normalized: co?pqny
normalized: li?ited
normalized: limited
normalized: lipited
normalized: liqbility
normalized: lixited
normalized: tvk
2 changes: 1 addition & 1 deletion test/test_254/model.bin

Large diffs are not rendered by default.

2 changes: 1 addition & 1 deletion test/test_324/model.bin
Original file line number Diff line number Diff line change
@@ -1 +1 @@
a:1:{i:0;a:12:{i:0;a:3:{s:8:"sphinxql";s:71:"CALL KEYWORDS ( '*qu* test', 'dist1', 1 AS stats, 0 AS fold_wildcards )";s:10:"total_rows";i:4;s:4:"rows";a:4:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:5:"quest";s:4:"docs";s:1:"4";s:4:"hits";s:1:"4";}i:1;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:9:"sidequest";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}i:2;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:7:"questik";s:4:"docs";s:1:"1";s:4:"hits";s:1:"1";}i:3;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:4:"test";s:10:"normalized";s:4:"test";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}}}i:1;a:3:{s:8:"sphinxql";s:71:"CALL KEYWORDS ( '*qu* test', 'dist2', 1 AS stats, 0 AS fold_wildcards )";s:10:"total_rows";i:4;s:4:"rows";a:4:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:5:"quest";s:4:"docs";s:1:"4";s:4:"hits";s:1:"4";}i:1;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:9:"sidequest";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}i:2;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:7:"questik";s:4:"docs";s:1:"1";s:4:"hits";s:1:"1";}i:3;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:4:"test";s:10:"normalized";s:4:"test";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}}}i:2;a:3:{s:8:"sphinxql";s:71:"CALL KEYWORDS ( '*qu* test', 'dist3', 1 AS stats, 0 AS fold_wildcards )";s:10:"total_rows";i:4;s:4:"rows";a:4:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:5:"quest";s:4:"docs";s:1:"4";s:4:"hits";s:1:"4";}i:1;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:9:"sidequest";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}i:2;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:7:"questik";s:4:"docs";s:1:"1";s:4:"hits";s:1:"1";}i:3;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:4:"test";s:10:"normalized";s:4:"test";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}}}i:3;a:3:{s:8:"sphinxql";s:70:"CALL KEYWORDS ( '*qu* te*', 'dist1', 1 AS stats, 1 AS fold_wildcards )";s:10:"total_rows";i:2;s:4:"rows";a:2:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:4:"*qu*";s:4:"docs";s:1:"8";s:4:"hits";s:1:"8";}i:1;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:3:"te*";s:10:"normalized";s:3:"te*";s:4:"docs";s:1:"7";s:4:"hits";s:1:"7";}}}i:4;a:3:{s:8:"sphinxql";s:70:"CALL KEYWORDS ( '*qu* te*', 'dist2', 1 AS stats, 1 AS fold_wildcards )";s:10:"total_rows";i:2;s:4:"rows";a:2:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:4:"*qu*";s:4:"docs";s:1:"8";s:4:"hits";s:1:"8";}i:1;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:3:"te*";s:10:"normalized";s:3:"te*";s:4:"docs";s:1:"7";s:4:"hits";s:1:"7";}}}i:5;a:3:{s:8:"sphinxql";s:70:"CALL KEYWORDS ( '*qu* te*', 'dist3', 1 AS stats, 1 AS fold_wildcards )";s:10:"total_rows";i:2;s:4:"rows";a:2:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:4:"*qu*";s:4:"docs";s:1:"8";s:4:"hits";s:1:"8";}i:1;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:3:"te*";s:10:"normalized";s:3:"te*";s:4:"docs";s:1:"7";s:4:"hits";s:1:"7";}}}i:6;a:2:{s:8:"sphinxql";s:58:"insert into rt_a1 values ( 1,'abc', 11 ), ( 2,'abc', 11 )";s:14:"total_affected";i:2;}i:7;a:2:{s:8:"sphinxql";s:75:"insert into rt_a2 values ( 1,'abc', 11 ), ( 2,'abc', 11 ), ( 3,'abc', 11 )";s:14:"total_affected";i:3;}i:8;a:2:{s:8:"sphinxql";s:20:"flush ramchunk rt_a1";s:14:"total_affected";i:0;}i:9;a:2:{s:8:"sphinxql";s:20:"flush ramchunk rt_a2";s:14:"total_affected";i:0;}i:10;a:3:{s:8:"sphinxql";s:48:"call keywords ( 'abc abc', 'rt_a1', 1 as stats )";s:10:"total_rows";i:2;s:4:"rows";a:2:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:3:"abc";s:10:"normalized";s:3:"abc";s:4:"docs";s:1:"2";s:4:"hits";s:1:"2";}i:1;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:3:"abc";s:10:"normalized";s:3:"abc";s:4:"docs";s:1:"2";s:4:"hits";s:1:"2";}}}i:11;a:3:{s:8:"sphinxql";s:48:"call keywords ( 'abc abc', 'dist4', 1 as stats )";s:10:"total_rows";i:2;s:4:"rows";a:2:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:3:"abc";s:10:"normalized";s:3:"abc";s:4:"docs";s:1:"5";s:4:"hits";s:1:"5";}i:1;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:3:"abc";s:10:"normalized";s:3:"abc";s:4:"docs";s:1:"5";s:4:"hits";s:1:"5";}}}}}
a:1:{i:0;a:12:{i:0;a:3:{s:8:"sphinxql";s:71:"CALL KEYWORDS ( '*qu* test', 'dist1', 1 AS stats, 0 AS fold_wildcards )";s:10:"total_rows";i:5;s:4:"rows";a:5:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:5:"quest";s:4:"docs";s:1:"4";s:4:"hits";s:1:"4";}i:1;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:9:"sidequest";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}i:2;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:7:"questik";s:4:"docs";s:1:"1";s:4:"hits";s:1:"1";}i:3;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:4:"*qu*";s:4:"docs";s:1:"0";s:4:"hits";s:1:"0";}i:4;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:4:"test";s:10:"normalized";s:4:"test";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}}}i:1;a:3:{s:8:"sphinxql";s:71:"CALL KEYWORDS ( '*qu* test', 'dist2', 1 AS stats, 0 AS fold_wildcards )";s:10:"total_rows";i:5;s:4:"rows";a:5:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:5:"quest";s:4:"docs";s:1:"4";s:4:"hits";s:1:"4";}i:1;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:9:"sidequest";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}i:2;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:7:"questik";s:4:"docs";s:1:"1";s:4:"hits";s:1:"1";}i:3;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:4:"*qu*";s:4:"docs";s:1:"0";s:4:"hits";s:1:"0";}i:4;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:4:"test";s:10:"normalized";s:4:"test";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}}}i:2;a:3:{s:8:"sphinxql";s:71:"CALL KEYWORDS ( '*qu* test', 'dist3', 1 AS stats, 0 AS fold_wildcards )";s:10:"total_rows";i:5;s:4:"rows";a:5:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:5:"quest";s:4:"docs";s:1:"4";s:4:"hits";s:1:"4";}i:1;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:9:"sidequest";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}i:2;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:7:"questik";s:4:"docs";s:1:"1";s:4:"hits";s:1:"1";}i:3;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:4:"*qu*";s:4:"docs";s:1:"0";s:4:"hits";s:1:"0";}i:4;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:4:"test";s:10:"normalized";s:4:"test";s:4:"docs";s:1:"3";s:4:"hits";s:1:"3";}}}i:3;a:3:{s:8:"sphinxql";s:70:"CALL KEYWORDS ( '*qu* te*', 'dist1', 1 AS stats, 1 AS fold_wildcards )";s:10:"total_rows";i:2;s:4:"rows";a:2:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:4:"*qu*";s:4:"docs";s:1:"8";s:4:"hits";s:1:"8";}i:1;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:3:"te*";s:10:"normalized";s:3:"te*";s:4:"docs";s:1:"7";s:4:"hits";s:1:"7";}}}i:4;a:3:{s:8:"sphinxql";s:70:"CALL KEYWORDS ( '*qu* te*', 'dist2', 1 AS stats, 1 AS fold_wildcards )";s:10:"total_rows";i:2;s:4:"rows";a:2:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:4:"*qu*";s:4:"docs";s:1:"8";s:4:"hits";s:1:"8";}i:1;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:3:"te*";s:10:"normalized";s:3:"te*";s:4:"docs";s:1:"7";s:4:"hits";s:1:"7";}}}i:5;a:3:{s:8:"sphinxql";s:70:"CALL KEYWORDS ( '*qu* te*', 'dist3', 1 AS stats, 1 AS fold_wildcards )";s:10:"total_rows";i:2;s:4:"rows";a:2:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:4:"*qu*";s:10:"normalized";s:4:"*qu*";s:4:"docs";s:1:"8";s:4:"hits";s:1:"8";}i:1;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:3:"te*";s:10:"normalized";s:3:"te*";s:4:"docs";s:1:"7";s:4:"hits";s:1:"7";}}}i:6;a:2:{s:8:"sphinxql";s:58:"insert into rt_a1 values ( 1,'abc', 11 ), ( 2,'abc', 11 )";s:14:"total_affected";i:2;}i:7;a:2:{s:8:"sphinxql";s:75:"insert into rt_a2 values ( 1,'abc', 11 ), ( 2,'abc', 11 ), ( 3,'abc', 11 )";s:14:"total_affected";i:3;}i:8;a:2:{s:8:"sphinxql";s:20:"flush ramchunk rt_a1";s:14:"total_affected";i:0;}i:9;a:2:{s:8:"sphinxql";s:20:"flush ramchunk rt_a2";s:14:"total_affected";i:0;}i:10;a:3:{s:8:"sphinxql";s:48:"call keywords ( 'abc abc', 'rt_a1', 1 as stats )";s:10:"total_rows";i:2;s:4:"rows";a:2:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:3:"abc";s:10:"normalized";s:3:"abc";s:4:"docs";s:1:"2";s:4:"hits";s:1:"2";}i:1;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:3:"abc";s:10:"normalized";s:3:"abc";s:4:"docs";s:1:"2";s:4:"hits";s:1:"2";}}}i:11;a:3:{s:8:"sphinxql";s:48:"call keywords ( 'abc abc', 'dist4', 1 as stats )";s:10:"total_rows";i:2;s:4:"rows";a:2:{i:0;a:5:{s:4:"qpos";s:1:"1";s:9:"tokenized";s:3:"abc";s:10:"normalized";s:3:"abc";s:4:"docs";s:1:"5";s:4:"hits";s:1:"5";}i:1;a:5:{s:4:"qpos";s:1:"2";s:9:"tokenized";s:3:"abc";s:10:"normalized";s:3:"abc";s:4:"docs";s:1:"5";s:4:"hits";s:1:"5";}}}}}
Loading