mirror of https://github.com/apache/lucene.git
initial version
git-svn-id: https://svn.apache.org/repos/asf/incubator/solr/trunk@372455 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Yonik Seeley
parent
77e6e7313c
commit
148b4dbc92
|
|
@ -0,0 +1,24 @@
|
|||
|
||||
#change the query cache size to 3 and the autowarm size to 2 for this test
|
||||
<commit/>
|
||||
val_s:A
|
||||
val_s:B
|
||||
val_s:C
|
||||
val_s:D
|
||||
#B,C,D should be in cache
|
||||
val_s:A
|
||||
#miss, now C,D,A should be in cache
|
||||
<commit/>
|
||||
#should see old{lookups=5, hits=0, size=3}, new{size=2}
|
||||
#now D,A should be autowarmed in new
|
||||
|
||||
val_s:C
|
||||
#miss, now cache=D,A,C
|
||||
<commit/>
|
||||
#should see old{lookups,1 hits=0, size=3}, new{size=2}
|
||||
#now A,C should be autowarmed in new
|
||||
|
||||
val_s:A
|
||||
val_s:C
|
||||
<commit/>
|
||||
#should see old{lookups=2, hits=2, size=0}
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
|
||||
PATH=c:/cygwin/bin
|
||||
c:/cygwin/bin/bash.exe -c "echo handler called... cwd=`pwd` MYVAR=%MYVAR% > commit.outfile"
|
||||
exit 33
|
||||
|
|
@ -0,0 +1 @@
|
|||
userName:Alex;startDate top 2;
|
||||
|
|
@ -0,0 +1,540 @@
|
|||
#compact the index, keep things from getting out of hand
|
||||
<optimize/>
|
||||
|
||||
#test query
|
||||
qlkciyopsbgzyvkylsjhchghjrdf %//result[@numFound="0"]
|
||||
|
||||
#test escaping of ";"
|
||||
<delete><id>42</id></delete>
|
||||
<add><doc><field name="id">42</field><field name="val_s">aa;bb</field></doc></add>
|
||||
<commit/>
|
||||
id:42 AND val_s:aa\;bb %//*[@numFound="1"]
|
||||
id:42 AND val_s:"aa;bb" %//*[@numFound="1"]
|
||||
id:42 AND val_s:"aa" %//*[@numFound="0"]
|
||||
|
||||
|
||||
|
||||
#test allowDups default of false
|
||||
<delete><id>42</id></delete>
|
||||
<add><doc><field name="id">42</field><field name="val_s">AAA</field></doc></add>
|
||||
<add><doc><field name="id">42</field><field name="val_s">BBB</field></doc></add>
|
||||
<commit/>
|
||||
id:42 %//*[@numFound="1"] %//str[.="BBB"]
|
||||
<add><doc><field name="id">42</field><field name="val_s">CCC</field></doc></add>
|
||||
<add><doc><field name="id">42</field><field name="val_s">DDD</field></doc></add>
|
||||
<commit/>
|
||||
id:42 %//*[@numFound="1"] %//str[.="DDD"]
|
||||
<delete><id>42</id></delete>
|
||||
|
||||
#test deletes
|
||||
<delete><query>id:[100 TO 110]</query></delete>
|
||||
<add allowDups="false"><doc><field name="id">101</field></doc></add>
|
||||
<add allowDups="false"><doc><field name="id">101</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">105</field></doc></add>
|
||||
<add allowDups="false"><doc><field name="id">102</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">103</field></doc></add>
|
||||
<add allowDups="false"><doc><field name="id">101</field></doc></add>
|
||||
<commit/>
|
||||
id:[100 TO 110] %//*[@numFound="4"]
|
||||
<delete><id>102</id></delete>
|
||||
<commit/>
|
||||
id:[100 TO 110] %//*[@numFound="3"]
|
||||
<delete><query>id:105</query></delete>
|
||||
<commit/>
|
||||
id:[100 TO 110] %//*[@numFound="2"]
|
||||
<delete><query>id:[100 TO 110]</query></delete>
|
||||
<commit/>
|
||||
id:[100 TO 110] %//*[@numFound="0"]
|
||||
|
||||
#test range
|
||||
<delete><id>44</id></delete>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="val_s">apple</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="val_s">banana</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="val_s">pear</field></doc></add>
|
||||
<commit/>
|
||||
val_s:[a TO z] %//*[@numFound="3"] %*[count(//doc)=3] %//*[@start="0"]
|
||||
val_s:[a TO z] %%start=2&limit=5 %//*[@numFound="3"] %*[count(//doc)=1] %*//doc[1]/str[.="pear"] %//*[@start="2"]
|
||||
val_s:[a TO z] %%start=3&limit=5 %//*[@numFound="3"] %*[count(//doc)=0]
|
||||
val_s:[a TO z] %%start=4&limit=5 %//*[@numFound="3"] %*[count(//doc)=0]
|
||||
val_s:[a TO z] %%start=25&limit=5 %//*[@numFound="3"] %*[count(//doc)=0]
|
||||
val_s:[a TO z] %%start=0&limit=1 %//*[@numFound="3"] %*[count(//doc)=1] %*//doc[1]/str[.="apple"]
|
||||
val_s:[a TO z] %%start=0&limit=2 %//*[@numFound="3"] %*[count(//doc)=2] %*//doc[2]/str[.="banana"]
|
||||
val_s:[a TO z] %%start=1&limit=1 %//*[@numFound="3"] %*[count(//doc)=1] %*//doc[1]/str[.="banana"]
|
||||
val_s:[a TO z] %%start=3&limit=1 %//*[@numFound="3"] %*[count(//doc)=0]
|
||||
val_s:[a TO z] %%start=4&limit=1 %//*[@numFound="3"] %*[count(//doc)=0]
|
||||
val_s:[a TO z] %%start=1&limit=0 %//*[@numFound="3"] %*[count(//doc)=0]
|
||||
val_s:[a TO z] %%start=0&limit=0 %//*[@numFound="3"] %*[count(//doc)=0]
|
||||
val_s:[a TO z];val_s asc %%start=0&limit=0 %//*[@numFound="3"] %*[count(//doc)=0]
|
||||
val_s:[a TO z];val_s desc %%start=0&limit=0 %//*[@numFound="3"] %*[count(//doc)=0]
|
||||
val_s:[a TO b] %//*[@numFound="1"]
|
||||
val_s:[a TO cat] %//*[@numFound="2"]
|
||||
val_s:[a TO *] %//*[@numFound="3"]
|
||||
val_s:[* TO z] %//*[@numFound="3"]
|
||||
val_s:[* TO *] %//*[@numFound="3"]
|
||||
val_s:[apple TO pear] %//*[@numFound="3"]
|
||||
val_s:[bear TO boar] %//*[@numFound="0"]
|
||||
val_s:[a TO a] %//*[@numFound="0"]
|
||||
val_s:[apple TO apple] %//*[@numFound="1"]
|
||||
val_s:{apple TO pear} %//*[@numFound="1"]
|
||||
val_s:{a TO z} %//*[@numFound="3"]
|
||||
val_s:{* TO *} %//*[@numFound="3"]
|
||||
#test rangequery within a boolean query
|
||||
id:44 AND val_s:[a TO z] %//*[@numFound="3"]
|
||||
id:44 OR val_s:[a TO z] %//*[@numFound="3"]
|
||||
val_s:[a TO b] OR val_s:[b TO z] %//*[@numFound="3"]
|
||||
+val_s:[a TO b] -val_s:[b TO z] %//*[@numFound="1"]
|
||||
-val_s:[a TO b] +val_s:[b TO z] %//*[@numFound="2"]
|
||||
val_s:[a TO c] AND val_s:[apple TO z] %//*[@numFound="2"]
|
||||
val_s:[a TO c] AND val_s:[a TO apple] %//*[@numFound="1"]
|
||||
id:44 AND (val_s:[a TO c] AND val_s:[a TO apple]) %//*[@numFound="1"]
|
||||
(val_s:[apple TO apple] OR val_s:[a TO c]) AND (val_s:[b TO c] OR val_s:[b TO b]) %//*[@numFound="1"] %//str[.="banana"]
|
||||
(val_s:[apple TO apple] AND val_s:[a TO c]) OR (val_s:[p TO z] AND val_s:[a TO z]) %//*[@numFound="2"] %//str[.="apple"] %//str[.="pear"]
|
||||
|
||||
#check for docs that appear more than once in a range
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="val_s">apple</field><field name="val_s">banana</field></doc></add>
|
||||
<commit/>
|
||||
val_s:[* TO *] OR val_s:[* TO *] %//*[@numFound="4"]
|
||||
val_s:[* TO *] AND val_s:[* TO *] %//*[@numFound="4"]
|
||||
val_s:[* TO *] %//*[@numFound="4"]
|
||||
|
||||
|
||||
#<delete><id>44</id></delete>
|
||||
<add overwritePending="true" overwriteCommitted="true"><doc><field name="id">44</field><field name="text">red riding hood</field></doc></add>
|
||||
<commit/>
|
||||
id:44 AND red %//@numFound[.="1"] %*[count(//doc)=1]
|
||||
id:44 AND ride %//@numFound[.="1"]
|
||||
id:44 AND blue %//@numFound[.="0"]
|
||||
|
||||
#allow duplicates
|
||||
<delete><id>44</id></delete>
|
||||
<add allowDups="true" overwriteCommitted="false" overwritePending="false"><doc><field name="id">44</field><field name="text">red riding hood</field></doc></add>
|
||||
<add allowDups="true" overwriteCommitted="false" overwritePending="false"><doc><field name="id">44</field><field name="text">big bad wolf</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %//@numFound[.="2"]
|
||||
id:44 AND red %//@numFound[.="1"] %*[count(//doc)=1]
|
||||
id:44 AND wolf %//@numFound[.="1"] %*[count(//doc)=1]
|
||||
+id:44 red wolf %//@numFound[.="2"]
|
||||
|
||||
#test removal of multiples w/o adding anything else
|
||||
<delete><id>44</id></delete>
|
||||
<commit/>
|
||||
id:44 %//@numFound[.="0"]
|
||||
|
||||
#untokenized string type
|
||||
<delete><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="ssto">and a 10.4 ?</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %//str[.="and a 10.4 ?"]
|
||||
<delete><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="sind">abc123</field></doc></add>
|
||||
<commit/>
|
||||
#TODO: how to search for something with spaces....
|
||||
sind:abc123 %//@numFound[.="1"] %*[count(//@name[.="sind"])=0] %*[count(//@name[.="id"])=1]
|
||||
|
||||
<delete><id>44</id></delete>
|
||||
<delete><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="sindsto">abc123</field></doc></add>
|
||||
<commit/>
|
||||
#TODO: how to search for something with spaces....
|
||||
sindsto:abc123 %//str[.="abc123"]
|
||||
|
||||
#test output of multivalued fields
|
||||
<delete><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="title">yonik3</field><field name="title" boost="2">yonik4</field></doc></add>
|
||||
<commit></commit>
|
||||
id:44 %//arr[@name="title"][./str="yonik3" and ./str="yonik4"] %*[count(//@name[.="title"])=1]
|
||||
title:yonik3 %//@numFound[.>"0"]
|
||||
title:yonik4 %//@numFound[.>"0"]
|
||||
title:yonik5 %//@numFound[.="0"]
|
||||
<delete><query>title:yonik4</query></delete>
|
||||
<commit/>
|
||||
id:44 %//@numFound[.="0"]
|
||||
|
||||
|
||||
#not visible until commit
|
||||
<delete><id>44</id></delete>
|
||||
<commit/>
|
||||
<add><doc><field name="id">44</field></doc></add>
|
||||
id:44 %//@numFound[.="0"]
|
||||
<commit/>
|
||||
id:44 %//@numFound[.="1"]
|
||||
|
||||
#test configurable stop words
|
||||
<delete><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="teststop">world stopworda view</field></doc></add>
|
||||
<commit/>
|
||||
+id:44 +teststop:world %//@numFound[.="1"]
|
||||
teststop:stopworda %//@numFound[.="0"]
|
||||
|
||||
#test ignoreCase stop words
|
||||
<delete><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="stopfilt">world AnD view</field></doc></add>
|
||||
<commit/>
|
||||
+id:44 +stopfilt:world %//@numFound[.="1"]
|
||||
stopfilt:"and" %//@numFound[.="0"]
|
||||
stopfilt:"AND" %//@numFound[.="0"]
|
||||
stopfilt:"AnD" %//@numFound[.="0"]
|
||||
|
||||
#test dynamic field types
|
||||
<delete fromPending="true" fromCommitted="true"><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="gack_i">51778</field><field name="t_name">cats</field></doc></add>
|
||||
<commit/>
|
||||
#test if the dyn fields got added
|
||||
id:44 %*[count(//doc/*)>=3] %//int[@name="gack_i"][.="51778"] %//str[@name="t_name"][.="cats"]
|
||||
#now test if we can query by a dynamic field (requires analyzer support)
|
||||
t_name:cat %//str[@name="t_name" and .="cats"]
|
||||
#check that deleteByQuery works for dynamic fields
|
||||
<delete><query>t_name:cat</query></delete>
|
||||
<commit/>
|
||||
t_name:cat %//@numFound[.="0"]
|
||||
|
||||
#test that longest dynamic field match happens first
|
||||
<add><doc><field name="id">44</field><field name="xaa">mystr</field><field name="xaaa">12321</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %//str[@name="xaa"][.="mystr"] %//int[@name="xaaa"][.="12321"]
|
||||
|
||||
|
||||
#test integer ranges and sorting
|
||||
<delete><id>44</id></delete>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_i">1234567890</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_i">10</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_i">1</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_i">2</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_i">15</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_i">-1</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_i">-987654321</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_i">2147483647</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_i">-2147483648</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_i">0</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %*[count(//doc)=10]
|
||||
num_i:2147483647 %//@numFound[.="1"] %//int[.="2147483647"]
|
||||
num_i:"-2147483648" %//@numFound[.="1"] %//int[.="-2147483648"]
|
||||
id:44;num_i asc; %//doc[1]/int[.="-2147483648"] %//doc[last()]/int[.="2147483647"]
|
||||
id:44;num_i desc; %//doc[1]/int[.="2147483647"] %//doc[last()]/int[.="-2147483648"]
|
||||
num_i:[0 TO 9] %*[count(//doc)=3]
|
||||
num_i:[-2147483648 TO 2147483647] %*[count(//doc)=10]
|
||||
num_i:[-10 TO -1] %*[count(//doc)=1]
|
||||
|
||||
#test long ranges and sorting
|
||||
<delete><id>44</id></delete>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_l">1234567890</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_l">10</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_l">1</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_l">2</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_l">15</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_l">-1</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_l">-987654321</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_l">9223372036854775807</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_l">-9223372036854775808</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_l">0</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %*[count(//doc)=10]
|
||||
num_l:9223372036854775807 %//@numFound[.="1"] %//long[.="9223372036854775807"]
|
||||
num_l:"-9223372036854775808" %//@numFound[.="1"] %//long[.="-9223372036854775808"]
|
||||
id:44;num_l asc; %//doc[1]/long[.="-9223372036854775808"] %//doc[last()]/long[.="9223372036854775807"]
|
||||
id:44;num_l desc; %//doc[1]/long[.="9223372036854775807"] %//doc[last()]/long[.="-9223372036854775808"]
|
||||
num_l:[-1 TO 9] %*[count(//doc)=4]
|
||||
num_l:[-9223372036854775808 TO 9223372036854775807] %*[count(//doc)=10]
|
||||
num_l:[-10 TO -1] %*[count(//doc)=1]
|
||||
|
||||
#test binary float ranges and sorting
|
||||
<delete><id>44</id></delete>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_f">1.4142135</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_f">Infinity</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_f">-Infinity</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_f">NaN</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_f">2</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_f">-1</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_f">-987654321</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_f">-999999.99</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_f">-1e20</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_f">0</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %*[count(//doc)=10]
|
||||
num_f:Infinity %//@numFound[.="1"] %//float[.="Infinity"]
|
||||
num_f:"-Infinity" %//@numFound[.="1"] %//float[.="-Infinity"]
|
||||
num_f:"NaN" %//@numFound[.="1"] %//float[.="NaN"]
|
||||
num_f:"-1e20" %//@numFound[.="1"]
|
||||
id:44;num_f asc; %//doc[1]/float[.="-Infinity"] %//doc[last()]/float[.="NaN"]
|
||||
id:44;num_f desc; %//doc[1]/float[.="NaN"] %//doc[last()]/float[.="-Infinity"]
|
||||
num_f:[-1 TO 2] %*[count(//doc)=4]
|
||||
num_f:[-Infinity TO Infinity] %*[count(//doc)=9]
|
||||
|
||||
|
||||
|
||||
#test binary double ranges and sorting
|
||||
<delete><id>44</id></delete>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_d">1.4142135</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_d">Infinity</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_d">-Infinity</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_d">NaN</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_d">2</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_d">-1</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_d">1e-100</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_d">-999999.99</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_d">-1e100</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="num_d">0</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %*[count(//doc)=10]
|
||||
num_d:Infinity %//@numFound[.="1"] %//double[.="Infinity"]
|
||||
num_d:"-Infinity" %//@numFound[.="1"] %//double[.="-Infinity"]
|
||||
num_d:"NaN" %//@numFound[.="1"] %//double[.="NaN"]
|
||||
num_d:"-1e100" %//@numFound[.="1"]
|
||||
num_d:"1e-100" %//@numFound[.="1"]
|
||||
id:44;num_d asc; %//doc[1]/double[.="-Infinity"] %//doc[last()]/double[.="NaN"]
|
||||
id:44;num_d desc; %//doc[1]/double[.="NaN"] %//doc[last()]/double[.="-Infinity"]
|
||||
num_d:[-1 TO 2] %*[count(//doc)=5]
|
||||
num_d:[-Infinity TO Infinity] %*[count(//doc)=9]
|
||||
|
||||
|
||||
#test sorting on multiple fields
|
||||
<delete><id>44</id></delete>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="a_i">10</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="a_i">1</field><field name="b_i">100</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="a_i">-1</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="a_i">15</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="a_i">1</field><field name="b_i">50</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id">44</field><field name="a_i">0</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %*[count(//doc)=6]
|
||||
|
||||
id:44; a_i asc,b_i desc %*[count(//doc)=6] %//doc[3]/int[.="100"] %//doc[4]/int[.="50"]
|
||||
id:44;a_i asc , b_i asc; %*[count(//doc)=6] %//doc[3]/int[.="50"] %//doc[4]/int[.="100"]
|
||||
id:44;a_i asc; %*[count(//doc)=6] %//doc[1]/int[.="-1"] %//doc[last()]/int[.="15"]
|
||||
id:44;a_i asc , score top; %*[count(//doc)=6] %//doc[1]/int[.="-1"] %//doc[last()]/int[.="15"]
|
||||
id:44; score top , a_i top, b_i bottom ; %*[count(//doc)=6] %//doc[last()]/int[.="-1"] %//doc[1]/int[.="15"] %//doc[3]/int[.="50"] %//doc[4]/int[.="100"]
|
||||
|
||||
|
||||
#test sorting with some docs missing the sort field
|
||||
<delete><query>id_i:[1000 TO 1010]</query></delete>
|
||||
<add allowDups="true"><doc><field name="id_i">1000</field><field name="a_i">1</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id_i">1001</field><field name="a_i">10</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id_i">1002</field><field name="a_i">1</field><field name="b_i">100</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id_i">1003</field><field name="a_i">-1</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id_i">1004</field><field name="a_i">15</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id_i">1005</field><field name="a_i">1</field><field name="b_i">50</field></doc></add>
|
||||
<add allowDups="true"><doc><field name="id_i">1006</field><field name="a_i">0</field></doc></add>
|
||||
<commit/>
|
||||
id_i:[1000 TO 1010] %*[count(//doc)=7]
|
||||
id_i:[1000 TO 1010]; b_i asc %*[count(//doc)=7] %//doc[1]/int[.="50"] %//doc[2]/int[.="100"]
|
||||
id_i:[1000 TO 1010]; b_i desc %*[count(//doc)=7] %//doc[1]/int[.="100"] %//doc[2]/int[.="50"]
|
||||
id_i:[1000 TO 1010]; a_i asc,b_i desc %*[count(//doc)=7] %//doc[3]/int[.="100"] %//doc[4]/int[.="50"] %//doc[5]/int[.="1000"]
|
||||
id_i:[1000 TO 1010]; a_i asc,b_i asc %*[count(//doc)=7] %//doc[3]/int[.="50"] %//doc[4]/int[.="100"] %//doc[5]/int[.="1000"]
|
||||
|
||||
|
||||
#test prefix query
|
||||
<delete><query>val_s:[* TO *]</query></delete>
|
||||
<add><doc><field name="id">100</field><field name="val_s">apple</field></doc></add>
|
||||
<add><doc><field name="id">101</field><field name="val_s">banana</field></doc></add>
|
||||
<add><doc><field name="id">102</field><field name="val_s">apple</field></doc></add>
|
||||
<add><doc><field name="id">103</field><field name="val_s">pearing</field></doc></add>
|
||||
<add><doc><field name="id">104</field><field name="val_s">pear</field></doc></add>
|
||||
<add><doc><field name="id">105</field><field name="val_s">appalling</field></doc></add>
|
||||
<add><doc><field name="id">106</field><field name="val_s">pearson</field></doc></add>
|
||||
<add><doc><field name="id">107</field><field name="val_s">port</field></doc></add>
|
||||
<commit/>
|
||||
|
||||
val_s:a* %//*[@numFound="3"]
|
||||
val_s:p* %//*[@numFound="4"]
|
||||
#val_s:* %//*[@numFound="8"]
|
||||
|
||||
<delete><query>id:[100 TO 110]</query></delete>
|
||||
|
||||
#test copyField functionality
|
||||
<add><doc><field name="id">42</field><field name="title">How Now4 brown Cows</field></doc></add>
|
||||
<commit/>
|
||||
id:42 AND title:Now %*[count(//doc)=0]
|
||||
id:42 AND title_lettertok:Now %*[count(//doc)=1]
|
||||
id:42 AND title:cow %*[count(//doc)=0]
|
||||
id:42 AND title_stemmed:cow %*[count(//doc)=1]
|
||||
id:42 AND text:cow %*[count(//doc)=1]
|
||||
|
||||
#test slop
|
||||
<add><doc><field name="id">42</field><field name="text">foo bar</field></doc></add>
|
||||
<commit/>
|
||||
id:42 AND text:"foo bar" %*[count(//doc)=1]
|
||||
id:42 AND text:"foo" %*[count(//doc)=1]
|
||||
id:42 AND text:"bar" %*[count(//doc)=1]
|
||||
id:42 AND text:"bar foo" %*[count(//doc)=0]
|
||||
id:42 AND text:"bar foo"~2 %*[count(//doc)=1]
|
||||
|
||||
|
||||
#intra-word delimiter testing (WordDelimiterFilter)
|
||||
<add><doc><field name="id">42</field><field name="subword">foo bar</field></doc></add>
|
||||
<commit/>
|
||||
id:42 AND subword:"foo bar" %*[count(//doc)=1]
|
||||
id:42 AND subword:"foo" %*[count(//doc)=1]
|
||||
id:42 AND subword:"bar" %*[count(//doc)=1]
|
||||
id:42 AND subword:"bar foo" %*[count(//doc)=0]
|
||||
id:42 AND subword:"bar foo"~2 %*[count(//doc)=1]
|
||||
id:42 AND subword:"foo/bar" %*[count(//doc)=1]
|
||||
id:42 AND subword:"foobar" %*[count(//doc)=0]
|
||||
|
||||
<add><doc><field name="id">42</field><field name="subword">foo-bar</field></doc></add>
|
||||
<commit/>
|
||||
id:42 AND subword:"foo bar" %*[count(//doc)=1]
|
||||
id:42 AND subword:"foo" %*[count(//doc)=1]
|
||||
id:42 AND subword:"bar" %*[count(//doc)=1]
|
||||
id:42 AND subword:"bar foo" %*[count(//doc)=0]
|
||||
id:42 AND subword:"bar foo"~2 %*[count(//doc)=1]
|
||||
id:42 AND subword:"foo/bar" %*[count(//doc)=1]
|
||||
id:42 AND subword:foobar %*[count(//doc)=1]
|
||||
|
||||
<add><doc><field name="id">42</field><field name="subword">Canon PowerShot SD500 7MP</field></doc></add>
|
||||
<commit/>
|
||||
id:42 AND subword:"power-shot" %*[count(//doc)=1]
|
||||
id:42 AND subword:"power shot sd 500" %*[count(//doc)=1]
|
||||
id:42 AND subword:"powershot" %*[count(//doc)=1]
|
||||
id:42 AND subword:"SD-500" %*[count(//doc)=1]
|
||||
id:42 AND subword:"SD500" %*[count(//doc)=1]
|
||||
id:42 AND subword:"SD500-7MP" %*[count(//doc)=1]
|
||||
id:42 AND subword:"PowerShotSD500-7MP" %*[count(//doc)=1]
|
||||
|
||||
<add><doc><field name="id">42</field><field name="subword">Wi-Fi</field></doc></add>
|
||||
<commit/>
|
||||
id:42 AND subword:wifi %*[count(//doc)=1]
|
||||
id:42 AND subword:wi+=fi %*[count(//doc)=1]
|
||||
id:42 AND subword:wi+=fi %*[count(//doc)=1]
|
||||
id:42 AND subword:WiFi %*[count(//doc)=1]
|
||||
id:42 AND subword:"wi fi" %*[count(//doc)=1]
|
||||
|
||||
<add><doc><field name="id">42</field><field name="subword">'I.B.M' A's,B's,C's</field></doc></add>
|
||||
<commit/>
|
||||
id:42 AND subword:"'I.B.M.'" %*[count(//doc)=1]
|
||||
id:42 AND subword:I.B.M %*[count(//doc)=1]
|
||||
id:42 AND subword:IBM %*[count(//doc)=1]
|
||||
id:42 AND subword:I--B--M %*[count(//doc)=1]
|
||||
id:42 AND subword:"I B M" %*[count(//doc)=1]
|
||||
id:42 AND subword:IBM's %*[count(//doc)=1]
|
||||
id:42 AND subword:IBM'sx %*[count(//doc)=0]
|
||||
|
||||
#this one fails since IBM and ABC are separated by two tokens
|
||||
#id:42 AND subword:IBM's-ABC's %*[count(//doc)=1]
|
||||
id:42 AND subword:"IBM's-ABC's"~2 %*[count(//doc)=1]
|
||||
|
||||
id:42 AND subword:"A's B's-C's" %*[count(//doc)=1]
|
||||
|
||||
<add><doc><field name="id">42</field><field name="subword">Sony KDF-E50A10</field></doc></add>
|
||||
<commit/>
|
||||
|
||||
#check for exact match:
|
||||
# Sony KDF E/KDFE 50 A 10 (this is how it's indexed)
|
||||
# Sony KDF E 50 A 10 (and how it's queried)
|
||||
id:42 AND subword:"Sony KDF-E50A10" %*[count(//doc)=1]
|
||||
id:42 AND subword:10 %*[count(//doc)=1]
|
||||
id:42 AND subword:Sony %*[count(//doc)=1]
|
||||
|
||||
#this one fails without slop since Sony and KDFE have a token inbetween
|
||||
#id:42 AND subword:SonyKDFE50A10 %*[count(//doc)=1]
|
||||
id:42 AND subword:"SonyKDFE50A10"~10 %*[count(//doc)=1]
|
||||
|
||||
id:42 AND subword:"Sony KDF E-50-A-10" %*[count(//doc)=1]
|
||||
|
||||
<add><doc><field name="id">42</field><field name="subword">http://www.yahoo.com</field></doc></add>
|
||||
<commit/>
|
||||
id:42 AND subword:yahoo %*[count(//doc)=1]
|
||||
id:42 AND subword:www.yahoo.com %*[count(//doc)=1]
|
||||
id:42 AND subword:http://www.yahoo.com %*[count(//doc)=1]
|
||||
|
||||
<add><doc><field name="id">42</field><field name="subword">--Q 1-- W2 E-3 Ok xY 4R 5-T *6-Y- 7-8-- 10A-B</field></doc></add>
|
||||
<commit/>
|
||||
id:42 AND subword:Q %*[count(//doc)=1]
|
||||
id:42 AND subword:1 %*[count(//doc)=1]
|
||||
id:42 AND subword:"w 2" %*[count(//doc)=1]
|
||||
id:42 AND subword:"e 3" %*[count(//doc)=1]
|
||||
id:42 AND subword:"o k" %*[count(//doc)=0]
|
||||
id:42 AND subword:"ok" %*[count(//doc)=1]
|
||||
id:42 AND subword:"x y" %*[count(//doc)=1]
|
||||
id:42 AND subword:"xy" %*[count(//doc)=1]
|
||||
id:42 AND subword:"4 r" %*[count(//doc)=1]
|
||||
id:42 AND subword:"5 t" %*[count(//doc)=1]
|
||||
id:42 AND subword:"5 t" %*[count(//doc)=1]
|
||||
id:42 AND subword:"6 y" %*[count(//doc)=1]
|
||||
id:42 AND subword:"7 8" %*[count(//doc)=1]
|
||||
id:42 AND subword:"78" %*[count(//doc)=1]
|
||||
id:42 AND subword:"10 A+B" %*[count(//doc)=1]
|
||||
|
||||
<add><doc><field name="id">42</field><field name="subword">FooBarBaz</field></doc></add>
|
||||
<add><doc><field name="id">42</field><field name="subword">FooBar10</field></doc></add>
|
||||
<add><doc><field name="id">42</field><field name="subword">10FooBar</field></doc></add>
|
||||
<add><doc><field name="id">42</field><field name="subword">BAZ</field></doc></add>
|
||||
<add><doc><field name="id">42</field><field name="subword">10</field></doc></add>
|
||||
<add><doc><field name="id">42</field><field name="subword">Mark, I found what's the problem! It turns to be from the latest schema. I found tons of exceptions in the resin.stdout that prevented the builder from performing. It's all coming from the WordDelimiterFilter which was just added to the latest schema: [2005-08-29 15:11:38.375] java.lang.IndexOutOfBoundsException: Index: 3, Size: 3 673804 [2005-08-29 15:11:38.375] at java.util.ArrayList.RangeCheck(ArrayList.java:547) 673805 [2005-08-29 15:11:38.375] at java.util.ArrayList.get(ArrayList.java:322) 673806 [2005-08-29 15:11:38.375] at solar.analysis.WordDelimiterFilter.addCombos(WordDelimiterFilter.java:349) 673807 [2005-08-29 15:11:38.375] at solar.analysis.WordDelimiterFilter.next(WordDelimiterFilter.java:325) 673808 [2005-08-29 15:11:38.375] at org.apache.lucene.analysis.LowerCaseFilter.next(LowerCaseFilter.java:32) 673809 [2005-08-29 15:11:38.375] at org.apache.lucene.analysis.StopFilter.next(StopFilter.java:98) 673810 [2005-08-29 15:11:38.375] at solar.EnglishPorterFilter.next(TokenizerFactory.java:163) 673811 [2005-08-29 15:11:38.375] at org.apache.lucene.index.DocumentWriter.invertDocument(DocumentWriter.java:143) 673812 [2005-08-29 15:11:38.375] at org.apache.lucene.index.DocumentWriter.addDocument(DocumentWriter.java:81) 673813 [2005-08-29 15:11:38.375] at org.apache.lucene.index.IndexWriter.addDocument(IndexWriter.java:307) 673814 [2005-08-29 15:11:38.375] at org.apache.lucene.index.IndexWriter.addDocument(IndexWriter.java:294) 673815 [2005-08-29 15:11:38.375] at solar.DirectUpdateHandler2.doAdd(DirectUpdateHandler2.java:170) 673816 [2005-08-29 15:11:38.375] at solar.DirectUpdateHandler2.overwriteBoth(DirectUpdateHandler2.java:317) 673817 [2005-08-29 15:11:38.375] at solar.DirectUpdateHandler2.addDoc(DirectUpdateHandler2.java:191) 673818 [2005-08-29 15:11:38.375] at solar.SolarCore.update(SolarCore.java:795) 673819 [2005-08-29 15:11:38.375] at solarserver.SolarServlet.doPost(SolarServlet.java:71) 673820 [2005-08-29 15:11:38.375] at javax.servlet.http.HttpServlet.service(HttpServlet.java:154) 673821 [2005-08-29 15:11:38.375] at javax.servlet.http.HttpServlet.service(HttpServlet.java:92) 673822 [2005-08-29 15:11:38.375] at com.caucho.server.dispatch.ServletFilterChain.doFilter(ServletFilterChain.java:99) 673823 [2005-08-29 15:11:38.375] at com.caucho.server.cache.CacheFilterChain.doFilter(CacheFilterChain.java:188) 673824 [2005-08-29 15:11:38.375] at com.caucho.server.webapp.WebAppFilterChain.doFilter(WebAppFilterChain.java:163) 673825 [2005-08-29 15:11:38.375] at com.caucho.server.dispatch.ServletInvocation.service(ServletInvocation.java:208) 673826 [2005-08-29 15:11:38.375] at com.caucho.server.http.HttpRequest.handleRequest(HttpRequest.java:259) 673827 [2005-08-29 15:11:38.375] at com.caucho.server.port.TcpConnection.run(TcpConnection.java:363) 673828 [2005-08-29 15:11:38.375] at com.caucho.util.ThreadPool.runTasks(ThreadPool.java:490) 673829 [2005-08-29 15:11:38.375] at com.caucho.util.ThreadPool.run(ThreadPool.java:423) 673830 [2005-08-29 15:11:38.375] at java.lang.Thread.run(Thread.java:595) With the previous schema I'm able to perform a successful full build: http://c12-ssa-dev40-so-mas1.cnet.com:5078/select/?stylesheet=q=docTypeversion=2.0start=0rows=10indent=on Do you want to rollback to the previous schema version</field></doc></add>
|
||||
|
||||
|
||||
#
|
||||
<delete fromPending="true" fromCommitted="true"><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="fname_s">Yonik</field><field name="here_b">true</field><field name="iq_l">10000000000</field><field name="description_t">software engineer</field><field name="ego_d">1e100</field><field name="pi_f">3.1415962</field><field name="when_dt">2005-03-18T01:14:34Z</field><field name="arr_f">1.414213562</field><field name="arr_f">.999</field></doc></add>
|
||||
<commit/>
|
||||
id:44
|
||||
id:44 %%fl=fname_s,arr_f %//str[.="Yonik"] %//float[.="1.4142135"]
|
||||
id:44 %%fl= %//str[.="Yonik"] %//float[.="1.4142135"]
|
||||
|
||||
#test addition of score field
|
||||
id:44 %%fl=score %//str[.="Yonik"] %//float[.="1.4142135"] %//float[@name="score"] %*[count(//doc/*)=10]
|
||||
id:44 %%fl=*,score %//str[.="Yonik"] %//float[.="1.4142135"] %//float[@name="score"] %*[count(//doc/*)=10]
|
||||
id:44 %%fl=* %//str[.="Yonik"] %//float[.="1.4142135"] %*[count(//doc/*)>=9]
|
||||
|
||||
#test maxScore
|
||||
id:44 %%fl=score %//result[@maxScore>0]
|
||||
id:44;id desc; %%fl=score %//result[@maxScore>0]
|
||||
id:44; %%fl=score %//@maxScore = //doc/float[@name="score"]
|
||||
id:44;id desc; %%fl=score %//@maxScore = //doc/float[@name="score"]
|
||||
id:44;id desc; %%fl=score&limit=0 %//result[@maxScore>0]
|
||||
|
||||
|
||||
# test schema field attribute inheritance and overriding
|
||||
<delete><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="shouldbestored">hi</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %//*[@name="shouldbestored"]
|
||||
+id:44 +shouldbestored:hi %//*[@numFound="1"]
|
||||
|
||||
<delete><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="shouldbeunstored">hi</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %not(//*[@name="shouldbeunstored"])
|
||||
+id:44 +shouldbeunstored:hi %//*[@numFound="1"]
|
||||
|
||||
<delete><id>44</id></delete>
|
||||
<add><doc><field name="id">44</field><field name="shouldbeunindexed">hi</field></doc></add>
|
||||
<commit/>
|
||||
id:44 %//*[@name="shouldbeunindexed"]
|
||||
# this should result in an error... how to check for that?
|
||||
#+id:44 +shouldbeunindexed:hi %//*[@numFound="0"]
|
||||
|
||||
#test spaces between XML elements because that can introduce extra XML events that
|
||||
#can mess up parsing (and it has in the past)
|
||||
<delete> <id>44</id> </delete>
|
||||
<add> <doc> <field name="id">44</field> <field name="shouldbestored">hi</field> </doc> </add>
|
||||
<commit />
|
||||
|
||||
#test adding multiple docs per add command
|
||||
<delete><query>id:[0 TO 99]</query></delete>
|
||||
<add><doc><field name="id">1</field></doc><doc><field name="id">2</field></doc></add>
|
||||
<commit/>
|
||||
id:[0 TO 99] %//*[@numFound="2"]
|
||||
|
||||
#test synonym filter
|
||||
<delete><query>id:[10 TO 100]</query></delete>
|
||||
<add><doc><field name="id">10</field><field name="syn">a</field></doc></add>
|
||||
<add><doc><field name="id">11</field><field name="syn">b</field></doc></add>
|
||||
<add><doc><field name="id">12</field><field name="syn">c</field></doc></add>
|
||||
<add><doc><field name="id">13</field><field name="syn">foo</field></doc></add>
|
||||
<commit/>
|
||||
id:10 AND syn:a %//*[@numFound="1"]
|
||||
id:10 AND syn:aa %//*[@numFound="1"]
|
||||
id:11 AND syn:b %//*[@numFound="1"]
|
||||
id:11 AND syn:b1 %//*[@numFound="1"]
|
||||
id:11 AND syn:b2 %//*[@numFound="1"]
|
||||
id:12 AND syn:c %//*[@numFound="1"]
|
||||
id:12 AND syn:c1 %//*[@numFound="1"]
|
||||
id:12 AND syn:c2 %//*[@numFound="1"]
|
||||
id:13 AND syn:foo %//*[@numFound="1"]
|
||||
id:13 AND syn:bar %//*[@numFound="1"]
|
||||
id:13 AND syn:baz %//*[@numFound="1"]
|
||||
|
||||
#trigger output of custom value test
|
||||
values %%qt=test
|
||||
|
||||
|
|
@ -0,0 +1,5 @@
|
|||
#use a protected word file to avoid stemming two
|
||||
#unrelated words to the same base word.
|
||||
#to test, we will use words that would normally obviously be stemmed.
|
||||
cats
|
||||
ridding
|
||||
|
|
@ -0,0 +1 @@
|
|||
java -cp "../solar/classes;classes;../../lucene/lucene-1.4.3.jar" SolarPerf -schema test_schema.xml -index F:/root/index -verbose -test newtest.txt
|
||||
|
|
@ -0,0 +1,334 @@
|
|||
<?xml version="1.0" ?>
|
||||
<!-- The Solar schema file. This file should be named "schema.xml" and
|
||||
should be located where the classloader for the Solar webapp can find it.
|
||||
|
||||
$Id: schema.xml,v 1.1 2005/06/09 03:01:13 yonik Exp $
|
||||
$Source: /cvs/main/searching/solar-configs/test/WEB-INF/classes/schema.xml,v $
|
||||
$Name: $
|
||||
-->
|
||||
|
||||
<schema name="test" version="1.0">
|
||||
<types>
|
||||
|
||||
<!-- field type definitions... note that the "name" attribute is
|
||||
just a label to be used by field definitions. The "class"
|
||||
attribute and any other attributes determine the real type and
|
||||
behavior of the fieldtype.
|
||||
-->
|
||||
|
||||
<!-- numeric field types that store and index the text
|
||||
value verbatim (and hence don't sort correctly or support range queries.)
|
||||
These are provided more for backward compatability, allowing one
|
||||
to create a schema that matches an existing lucene index.
|
||||
-->
|
||||
<fieldtype name="integer" class="solar.IntField"/>
|
||||
<fieldtype name="long" class="solar.LongField"/>
|
||||
<fieldtype name="float" class="solar.FloatField"/>
|
||||
<fieldtype name="double" class="solar.DoubleField"/>
|
||||
|
||||
<!-- numeric field types that manipulate the value into
|
||||
a string value that isn't human readable in it's internal form,
|
||||
but sorts correctly and supports range queries.
|
||||
|
||||
If sortMissingLast="true" then a sort on this field will cause documents
|
||||
without the field to come after documents with the field,
|
||||
regardless of the requested sort order.
|
||||
If sortMissingFirst="true" then a sort on this field will cause documents
|
||||
without the field to come before documents with the field,
|
||||
regardless of the requested sort order.
|
||||
If sortMissingLast="false" and sortMissingFirst="false" (the default),
|
||||
then default lucene sorting will be used which places docs without the field
|
||||
first in an ascending sort and last in a descending sort.
|
||||
-->
|
||||
<fieldtype name="sint" class="solar.SortableIntField" sortMissingLast="true"/>
|
||||
<fieldtype name="slong" class="solar.SortableLongField" sortMissingLast="true"/>
|
||||
<fieldtype name="sfloat" class="solar.SortableFloatField" sortMissingLast="true"/>
|
||||
<fieldtype name="sdouble" class="solar.SortableDoubleField" sortMissingLast="true"/>
|
||||
|
||||
<!-- bcd versions of sortable numeric type may provide smaller
|
||||
storage space and support very large numbers.
|
||||
-->
|
||||
<fieldtype name="bcdint" class="solar.BCDIntField" sortMissingLast="true"/>
|
||||
<fieldtype name="bcdlong" class="solar.BCDLongField" sortMissingLast="true"/>
|
||||
<fieldtype name="bcdstr" class="solar.BCDStrField" sortMissingLast="true"/>
|
||||
|
||||
|
||||
<fieldtype name="boolean" class="solar.BoolField" sortMissingLast="true"/>
|
||||
<fieldtype name="string" class="solar.StrField" sortMissingLast="true"/>
|
||||
|
||||
<!-- format for date is 1995-12-31T23:59:59.999Z and only the fractional
|
||||
seconds part (.999) is optional.
|
||||
-->
|
||||
<fieldtype name="date" class="solar.DateField" sortMissingLast="true"/>
|
||||
|
||||
<!-- solar.TextField allows the specification of custom
|
||||
text analyzers specified as a tokenizer and a list
|
||||
of token filters.
|
||||
-->
|
||||
<fieldtype name="text" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.StandardTokenizerFactory"/>
|
||||
<filter class="solar.StandardFilterFactory"/>
|
||||
<filter class="solar.LowerCaseFilterFactory"/>
|
||||
<filter class="solar.StopFilterFactory"/>
|
||||
<!-- lucene PorterStemFilterFactory deprecated
|
||||
<filter class="solar.PorterStemFilterFactory"/>
|
||||
-->
|
||||
<filter class="solar.EnglishPorterFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
|
||||
|
||||
<fieldtype name="nametext" class="solar.TextField">
|
||||
<analyzer class="org.apache.lucene.analysis.WhitespaceAnalyzer"/>
|
||||
</fieldtype>
|
||||
|
||||
<fieldtype name="teststop" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.LowerCaseTokenizerFactory"/>
|
||||
<filter class="solar.StandardFilterFactory"/>
|
||||
<filter class="solar.StopFilterFactory" words="stopwords.txt"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
|
||||
<!-- fieldtypes in this section isolate tokenizers and tokenfilters for testing -->
|
||||
<fieldtype name="lowertok" class="solar.TextField">
|
||||
<analyzer><tokenizer class="solar.LowerCaseTokenizerFactory"/></analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="standardtok" class="solar.TextField">
|
||||
<analyzer><tokenizer class="solar.StandardTokenizerFactory"/></analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="lettertok" class="solar.TextField">
|
||||
<analyzer><tokenizer class="solar.LetterTokenizerFactory"/></analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="whitetok" class="solar.TextField">
|
||||
<analyzer><tokenizer class="solar.WhitespaceTokenizerFactory"/></analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="HTMLstandardtok" class="solar.TextField">
|
||||
<analyzer><tokenizer class="solar.HTMLStripStandardTokenizerFactory"/></analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="HTMLwhitetok" class="solar.TextField">
|
||||
<analyzer><tokenizer class="solar.HTMLStripWhitespaceTokenizerFactory"/></analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="standardtokfilt" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.StandardTokenizerFactory"/>
|
||||
<filter class="solar.StandardFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="standardfilt" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.StandardFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="lowerfilt" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="porterfilt" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.PorterStemFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
<!-- fieldtype name="snowballfilt" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.SnowballPorterFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldtype -->
|
||||
<fieldtype name="engporterfilt" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.EnglishPorterFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="custengporterfilt" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.EnglishPorterFilterFactory" protected="protwords.txt"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="stopfilt" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.StopFilterFactory" ignoreCase="true"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="custstopfilt" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.StopFilterFactory" words="stopwords.txt"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
<fieldtype name="lengthfilt" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.LengthFilterFactory" min="2" max="5"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
|
||||
<fieldtype name="subword" class="solar.TextField">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
||||
<filter class="solar.LowerCaseFilterFactory"/>
|
||||
<filter class="solar.StopFilterFactory"/>
|
||||
<filter class="solar.EnglishPorterFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0"/>
|
||||
<filter class="solar.LowerCaseFilterFactory"/>
|
||||
<filter class="solar.StopFilterFactory"/>
|
||||
<filter class="solar.EnglishPorterFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
|
||||
<!-- more flexible in matching skus, but more chance of a false match -->
|
||||
<fieldtype name="skutype1" class="solar.TextField">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
||||
<filter class="solar.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
||||
<filter class="solar.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
|
||||
<!-- less flexible in matching skus, but less chance of a false match -->
|
||||
<fieldtype name="skutype2" class="solar.TextField">
|
||||
<analyzer type="index">
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
||||
<filter class="solar.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
<analyzer type="query">
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter class="solar.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
|
||||
<filter class="solar.LowerCaseFilterFactory"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
|
||||
<!-- less flexible in matching skus, but less chance of a false match -->
|
||||
<fieldtype name="syn" class="solar.TextField">
|
||||
<analyzer>
|
||||
<tokenizer class="solar.WhitespaceTokenizerFactory"/>
|
||||
<filter name="syn" class="solar.SynonymFilterFactory" synonyms="synonyms.txt"/>
|
||||
</analyzer>
|
||||
</fieldtype>
|
||||
|
||||
<fieldtype name="unstored" class="solar.StrField" indexed="true" stored="false"/>
|
||||
</types>
|
||||
|
||||
|
||||
<fields>
|
||||
<field name="id" type="integer" indexed="true" stored="true"/>
|
||||
<field name="name" type="nametext" indexed="true" stored="true"/>
|
||||
<field name="text" type="text" indexed="true" stored="false"/>
|
||||
<field name="subject" type="text" indexed="true" stored="true"/>
|
||||
<field name="title" type="nametext" indexed="true" stored="true"/>
|
||||
<field name="weight" type="float" indexed="true" stored="true"/>
|
||||
<field name="bday" type="date" indexed="true" stored="true"/>
|
||||
|
||||
<field name="title_stemmed" type="text" indexed="true" stored="false"/>
|
||||
<field name="title_lettertok" type="lettertok" indexed="true" stored="false"/>
|
||||
|
||||
<field name="syn" type="syn" indexed="true" stored="true"/>
|
||||
|
||||
<!-- to test property inheritance and overriding -->
|
||||
<field name="shouldbeunstored" type="unstored" />
|
||||
<field name="shouldbestored" type="unstored" stored="true"/>
|
||||
<field name="shouldbeunindexed" type="unstored" indexed="false" stored="true"/>
|
||||
|
||||
|
||||
<!-- test different combinations of indexed and stored -->
|
||||
<field name="bind" type="boolean" indexed="true" stored="false"/>
|
||||
<field name="bsto" type="boolean" indexed="false" stored="true"/>
|
||||
<field name="bindsto" type="boolean" indexed="true" stored="true"/>
|
||||
<field name="isto" type="integer" indexed="false" stored="true"/>
|
||||
<field name="iind" type="integer" indexed="true" stored="false"/>
|
||||
<field name="ssto" type="string" indexed="false" stored="true"/>
|
||||
<field name="sind" type="string" indexed="true" stored="false"/>
|
||||
<field name="sindsto" type="string" indexed="true" stored="true"/>
|
||||
|
||||
<!-- fields to test individual tokenizers and tokenfilters -->
|
||||
<field name="teststop" type="teststop" indexed="true" stored="true"/>
|
||||
<field name="lowertok" type="lowertok" indexed="true" stored="true"/>
|
||||
<field name="standardtok" type="standardtok" indexed="true" stored="true"/>
|
||||
<field name="HTMLstandardtok" type="HTMLstandardtok" indexed="true" stored="true"/>
|
||||
<field name="lettertok" type="lettertok" indexed="true" stored="true"/>
|
||||
<field name="whitetok" type="whitetok" indexed="true" stored="true"/>
|
||||
<field name="HTMLwhitetok" type="HTMLwhitetok" indexed="true" stored="true"/>
|
||||
<field name="standardtokfilt" type="standardtokfilt" indexed="true" stored="true"/>
|
||||
<field name="standardfilt" type="standardfilt" indexed="true" stored="true"/>
|
||||
<field name="lowerfilt" type="lowerfilt" indexed="true" stored="true"/>
|
||||
<field name="porterfilt" type="porterfilt" indexed="true" stored="true"/>
|
||||
<field name="engporterfilt" type="engporterfilt" indexed="true" stored="true"/>
|
||||
<field name="custengporterfilt" type="custengporterfilt" indexed="true" stored="true"/>
|
||||
<field name="stopfilt" type="stopfilt" indexed="true" stored="true"/>
|
||||
<field name="custstopfilt" type="custstopfilt" indexed="true" stored="true"/>
|
||||
<field name="lengthfilt" type="lengthfilt" indexed="true" stored="true"/>
|
||||
|
||||
|
||||
<field name="subword" type="subword" indexed="true" stored="true"/>
|
||||
<field name="sku1" type="skutype1" indexed="true" stored="true"/>
|
||||
<field name="sku2" type="skutype2" indexed="true" stored="true"/>
|
||||
|
||||
<!-- Dynamic field definitions. If a field name is not found, dynamicFields
|
||||
will be used if the name matches any of the patterns.
|
||||
RESTRICTION: the glob-like pattern in the name attribute must have
|
||||
a "*" only at the start or the end.
|
||||
EXAMPLE: name="*_i" will match any field ending in _i (like myid_i, z_i)
|
||||
Longer patterns will be matched first. if equal size patterns
|
||||
both match, the first appearing in the schema will be used.
|
||||
-->
|
||||
<dynamicField name="*_i" type="sint" indexed="true" stored="true"/>
|
||||
<dynamicField name="*_s" type="string" indexed="true" stored="true"/>
|
||||
<dynamicField name="*_l" type="slong" indexed="true" stored="true"/>
|
||||
<dynamicField name="*_t" type="text" indexed="true" stored="true"/>
|
||||
<dynamicField name="*_b" type="boolean" indexed="true" stored="true"/>
|
||||
<dynamicField name="*_f" type="sfloat" indexed="true" stored="true"/>
|
||||
<dynamicField name="*_d" type="sdouble" indexed="true" stored="true"/>
|
||||
<dynamicField name="*_dt" type="date" indexed="true" stored="true"/>
|
||||
<dynamicField name="*_bcd" type="bcdstr" indexed="true" stored="true"/>
|
||||
|
||||
<dynamicField name="*_sI" type="string" indexed="true" stored="false"/>
|
||||
<dynamicField name="*_sS" type="string" indexed="false" stored="true"/>
|
||||
<dynamicField name="t_*" type="text" indexed="true" stored="true"/>
|
||||
|
||||
|
||||
<!-- for testing to ensure that longer patterns are matched first -->
|
||||
<dynamicField name="*aa" type="string" indexed="true" stored="true"/>
|
||||
<dynamicField name="*aaa" type="integer" indexed="false" stored="true"/>
|
||||
|
||||
|
||||
</fields>
|
||||
|
||||
<defaultSearchField>text</defaultSearchField>
|
||||
<uniqueKey>id</uniqueKey>
|
||||
|
||||
<!-- copyField commands copy one field to another at the time a document
|
||||
is added to the index. It's used either to index the same field different
|
||||
ways, or to add multiple fields to the same field for easier/faster searching.
|
||||
-->
|
||||
<copyField source="title" dest="title_stemmed"/>
|
||||
<copyField source="title" dest="title_lettertok"/>
|
||||
|
||||
<copyField source="title" dest="text"/>
|
||||
<copyField source="subject" dest="text"/>
|
||||
|
||||
|
||||
<!-- Similarity is the scoring routine for each document vs a query.
|
||||
A custom similarity may be specified here, but the default is fine
|
||||
for most applications.
|
||||
-->
|
||||
<!-- <similarity class="org.apache.lucene.search.DefaultSimilarity"/> -->
|
||||
|
||||
</schema>
|
||||
|
|
@ -0,0 +1,191 @@
|
|||
<?xml version="1.0" ?>
|
||||
|
||||
<!-- $Id$
|
||||
$Source$
|
||||
$Name$
|
||||
-->
|
||||
|
||||
<config>
|
||||
|
||||
<!-- Used to specify an alternate directory to hold all index data.
|
||||
It defaults to "index" if not present, and should probably
|
||||
not be changed if replication is in use. -->
|
||||
<!--
|
||||
<indexDir>index</indexDir>
|
||||
-->
|
||||
|
||||
<indexDefaults>
|
||||
<!-- Values here affect all index writers and act as a default
|
||||
unless overridden. -->
|
||||
<useCompoundFile>false</useCompoundFile>
|
||||
<mergeFactor>10</mergeFactor>
|
||||
<maxBufferedDocs>1000</maxBufferedDocs>
|
||||
<maxMergeDocs>2147483647</maxMergeDocs>
|
||||
<maxFieldLength>10000</maxFieldLength>
|
||||
|
||||
<!-- these are global... can't currently override per index -->
|
||||
<writeLockTimeout>1000</writeLockTimeout>
|
||||
<commitLockTimeout>10000</commitLockTimeout>
|
||||
|
||||
</indexDefaults>
|
||||
|
||||
<mainIndex>
|
||||
<!-- lucene options specific to the main on-disk lucene index -->
|
||||
<useCompoundFile>false</useCompoundFile>
|
||||
<mergeFactor>10</mergeFactor>
|
||||
<maxBufferedDocs>1000</maxBufferedDocs>
|
||||
<maxMergeDocs>2147483647</maxMergeDocs>
|
||||
<maxFieldLength>10000</maxFieldLength>
|
||||
|
||||
<unlockOnStartup>true</unlockOnStartup>
|
||||
</mainIndex>
|
||||
|
||||
<updateHandler class="solar.DirectUpdateHandler2">
|
||||
|
||||
<!-- autocommit pending docs if certain criteria are met -->
|
||||
<autocommit> <!-- NOTE: autocommit not implemented yet -->
|
||||
<maxDocs>10000</maxDocs>
|
||||
<maxSec>3600</maxSec>
|
||||
</autocommit>
|
||||
|
||||
<!-- represents a lower bound on the frequency that commits may
|
||||
occur (in seconds). NOTE: not yet implemented
|
||||
-->
|
||||
<commitIntervalLowerBound>0</commitIntervalLowerBound>
|
||||
|
||||
<!-- The RunExecutableListener executes an external command.
|
||||
exe - the name of the executable to run
|
||||
dir - dir to use as the current working directory. default="."
|
||||
wait - the calling thread waits until the executable returns. default="true"
|
||||
args - the arguments to pass to the program. default=nothing
|
||||
env - environment variables to set. default=nothing
|
||||
-->
|
||||
<!-- A postCommit event is fired after every commit
|
||||
<listener event="postCommit" class="solar.RunExecutableListener">
|
||||
<str name="exe">/var/opt/resin3/__PORT__/scripts/solar/snapshooter</str>
|
||||
<str name="dir">/var/opt/resin3/__PORT__</str>
|
||||
<bool name="wait">true</bool>
|
||||
<arr name="args"> <str>arg1</str> <str>arg2</str> </arr>
|
||||
<arr name="env"> <str>MYVAR=val1</str> </arr>
|
||||
</listener>
|
||||
-->
|
||||
|
||||
|
||||
</updateHandler>
|
||||
|
||||
|
||||
<query>
|
||||
<!-- Maximum number of clauses in a boolean query... can affect
|
||||
range or wildcard queries that expand to big boolean
|
||||
queries. An exception is thrown if exceeded.
|
||||
-->
|
||||
<maxBooleanClauses>1024</maxBooleanClauses>
|
||||
|
||||
|
||||
<!-- Cache specification for Filters or DocSets - unordered set of *all* documents
|
||||
that match a particular query.
|
||||
-->
|
||||
<filterCache
|
||||
class="solar.search.LRUCache"
|
||||
size="512"
|
||||
initialSize="512"
|
||||
autowarmCount="256"/>
|
||||
|
||||
<queryResultCache
|
||||
class="solar.search.LRUCache"
|
||||
size="512"
|
||||
initialSize="512"
|
||||
autowarmCount="1024"/>
|
||||
|
||||
<documentCache
|
||||
class="solar.search.LRUCache"
|
||||
size="512"
|
||||
initialSize="512"
|
||||
autowarmCount="0"/>
|
||||
|
||||
<!--
|
||||
<cache name="myUserCache"
|
||||
class="solar.search.LRUCache"
|
||||
size="4096"
|
||||
initialSize="1024"
|
||||
autowarmCount="1024"
|
||||
regenerator="MyRegenerator"
|
||||
/>
|
||||
-->
|
||||
|
||||
|
||||
<useFilterForSortedQuery>true</useFilterForSortedQuery>
|
||||
|
||||
<queryResultWindowSize>10</queryResultWindowSize>
|
||||
|
||||
<HashDocSet maxSize="3000" loadFactor="0.75"/>
|
||||
|
||||
|
||||
<!-- boolToFilterOptimizer converts boolean clauses with zero boost
|
||||
into cached filters if the number of docs selected by the clause exceeds
|
||||
the threshold (represented as a fraction of the total index)
|
||||
-->
|
||||
<boolTofilterOptimizer enabled="true" cacheSize="32" threshold=".05"/>
|
||||
|
||||
|
||||
<!-- a newSearcher event is fired whenever a new searcher is being prepared
|
||||
and there is a current searcher handling requests (aka registered). -->
|
||||
<!-- QuerySenderListener takes an array of NamedList and executes a
|
||||
local query request for each NamedList in sequence. -->
|
||||
<!--
|
||||
<listener event="newSearcher" class="solar.QuerySenderListener">
|
||||
<arr name="queries">
|
||||
<lst> <str name="q">solar</str> <str name="start">0</str> <str name="rows">10</str> </lst>
|
||||
<lst> <str name="q">rocks</str> <str name="start">0</str> <str name="rows">10</str> </lst>
|
||||
</arr>
|
||||
</listener>
|
||||
-->
|
||||
|
||||
<!-- a firstSearcher event is fired whenever a new searcher is being
|
||||
prepared but there is no current registered searcher to handle
|
||||
requests or to gain prewarming data from. -->
|
||||
<!--
|
||||
<listener event="firstSearcher" class="solar.QuerySenderListener">
|
||||
<arr name="queries">
|
||||
<lst> <str name="q">fast_warm</str> <str name="start">0</str> <str name="rows">10</str> </lst>
|
||||
</arr>
|
||||
</listener>
|
||||
-->
|
||||
|
||||
|
||||
</query>
|
||||
|
||||
|
||||
<!-- An alternate set representation that uses an integer hash to store filters (sets of docids).
|
||||
If the set cardinality <= maxSize elements, then HashDocSet will be used instead of the bitset
|
||||
based HashBitset. -->
|
||||
|
||||
<!-- requestHandler plugins... incoming queries will be dispatched to the
|
||||
correct handler based on the qt (query type) param matching the
|
||||
name of registered handlers.
|
||||
The "standard" request handler is the default and will be used if qt
|
||||
is not specified in the request.
|
||||
-->
|
||||
<requestHandler name="standard" class="solar.StandardRequestHandler" />
|
||||
<requestHandler name="old" class="solar.tst.OldRequestHandler" >
|
||||
<int name="myparam">1000</int>
|
||||
<float name="ratio">1.4142135</float>
|
||||
<arr name="myarr"><int>1</int><int>2</int></arr>
|
||||
<str>foo</str>
|
||||
</requestHandler>
|
||||
<requestHandler name="oldagain" class="solar.tst.OldRequestHandler" >
|
||||
<lst name="lst1"> <str name="op">sqrt</str> <int name="val">2</int> </lst>
|
||||
<lst name="lst2"> <str name="op">log</str> <float name="val">10</float> </lst>
|
||||
</requestHandler>
|
||||
|
||||
<requestHandler name="test" class="solar.tst.TestRequestHandler" />
|
||||
|
||||
|
||||
<admin>
|
||||
<defaultQuery>solar</defaultQuery>
|
||||
<gettableFiles>solarconfig.xml conf/solar/WEB-INF/web.external.xml conf/resin.conf </gettableFiles>
|
||||
</admin>
|
||||
|
||||
|
||||
|
||||
</config>
|
||||
|
|
@ -0,0 +1,367 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
import org.apache.solr.core.SolrCore;
|
||||
import org.apache.solr.schema.IndexSchema;
|
||||
import org.apache.solr.request.*;
|
||||
|
||||
|
||||
import javax.xml.parsers.DocumentBuilder;
|
||||
import javax.xml.parsers.DocumentBuilderFactory;
|
||||
import javax.xml.parsers.ParserConfigurationException;
|
||||
import javax.xml.xpath.XPath;
|
||||
import javax.xml.xpath.XPathFactory;
|
||||
import javax.xml.xpath.XPathConstants;
|
||||
import java.io.*;
|
||||
import java.util.*;
|
||||
import java.util.logging.Logger;
|
||||
import java.util.logging.Level;
|
||||
import java.util.logging.Handler;
|
||||
import java.util.logging.ConsoleHandler;
|
||||
|
||||
import org.w3c.dom.Document;
|
||||
|
||||
|
||||
/**
|
||||
* User: Yonik Seeley
|
||||
* Date: Aug 16, 2004
|
||||
*/
|
||||
public class SolrTest extends Thread {
|
||||
static SolrCore core;
|
||||
|
||||
static String[] requestDict;
|
||||
static String[] updateDict;
|
||||
static String[] testDict;
|
||||
static List<Integer> testDictLineno;
|
||||
|
||||
static List<Integer> lineno;
|
||||
public static String[] readDict(String filename) throws IOException {
|
||||
BufferedReader br = new BufferedReader(new FileReader(filename));
|
||||
ArrayList lst = new ArrayList(1024);
|
||||
lineno = new ArrayList<Integer>(1024);
|
||||
String line;
|
||||
int lineNum=0;
|
||||
while ((line = br.readLine())!=null) {
|
||||
lineNum++;
|
||||
if (line.length() <= 1) continue;
|
||||
lst.add(line);
|
||||
lineno.add(lineNum);
|
||||
}
|
||||
br.close();
|
||||
return (String[]) lst.toArray(new String[lst.size()]);
|
||||
}
|
||||
|
||||
|
||||
public static boolean verbose=false;
|
||||
static boolean doValidate=true;
|
||||
|
||||
static int countdown;
|
||||
static synchronized boolean runAgain() {
|
||||
return countdown-- > 0;
|
||||
}
|
||||
|
||||
|
||||
// statistics per client
|
||||
int numReq=0;
|
||||
int numErr=0;
|
||||
int numBodyChars=0;
|
||||
|
||||
boolean isWriter=false;
|
||||
boolean sequenceTest=false;
|
||||
|
||||
public void run() {
|
||||
if (sequenceTest) {
|
||||
for (int i=0; i<testDict.length; i++) {
|
||||
String s = testDict[i];
|
||||
int lineno = testDictLineno.get(i);
|
||||
String req;
|
||||
String test=null;
|
||||
String params=null;
|
||||
char[] resp;
|
||||
if (s.length()<2 || s.startsWith("#")) continue; // comment
|
||||
System.out.println("LINE=" + lineno + " EXECUTING " + s);
|
||||
|
||||
int endQuery = s.length();
|
||||
int startParams = s.indexOf("%%");
|
||||
int endParams = s.length();
|
||||
int endTests = s.length();
|
||||
if (startParams > 0) {
|
||||
endQuery = startParams;
|
||||
endParams = s.length();
|
||||
}
|
||||
int startTests = s.indexOf('%', startParams+2);
|
||||
if (startTests > 0) {
|
||||
if (endQuery == s.length()) endQuery = startTests;
|
||||
endParams = startTests;
|
||||
}
|
||||
|
||||
req = s.substring(0,endQuery).trim();
|
||||
if (startParams > 0) params = s.substring(startParams+2,endParams).trim();
|
||||
if (startTests > 0) test = s.substring(startTests+1,endTests).trim();
|
||||
|
||||
System.out.println("###req=" + req);
|
||||
System.out.println("###params=" + params);
|
||||
System.out.println("###tests=" + test);
|
||||
|
||||
if (req.startsWith("<")) {
|
||||
resp = doUpdate(req);
|
||||
} else {
|
||||
resp = doReq(req,params);
|
||||
}
|
||||
if (doValidate) {
|
||||
validate(req,test,resp);
|
||||
} else {
|
||||
System.out.println("#### no validation performed");
|
||||
}
|
||||
}
|
||||
System.out.println(">>>>>>>>>>>>>>>>>>>>>>>> SUCCESS <<<<<<<<<<<<<<<<<<<<<<<<<<");
|
||||
}
|
||||
|
||||
else {
|
||||
while(runAgain()) {
|
||||
if (isWriter) doUpdate(updateDict[(int)(Math.random()*updateDict.length)]);
|
||||
else doReq(requestDict[(int)(Math.random()*requestDict.length)], null);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private DocumentBuilder builder;
|
||||
private XPath xpath = XPathFactory.newInstance().newXPath();
|
||||
{
|
||||
try {
|
||||
builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
|
||||
} catch (ParserConfigurationException e) {
|
||||
e.printStackTrace();
|
||||
}
|
||||
}
|
||||
|
||||
private void validate(String req, String test, char[] resp) {
|
||||
if (test==null || test.length()==0) return;
|
||||
Document document=null;
|
||||
try {
|
||||
// the resp[] contains a declaration that it is UTF-8, so we
|
||||
// need to change it to that for the XML parser.
|
||||
|
||||
document = builder.parse(new ByteArrayInputStream(new String(resp).getBytes("UTF-8")));
|
||||
// document = builder.parse(new String(resp));
|
||||
} catch (Exception e) {
|
||||
System.out.println("ERROR parsing '" + new String(resp) + "'");
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
|
||||
String[] tests = test.split("%");
|
||||
for (String xp : tests) {
|
||||
Boolean bool=false;
|
||||
xp=xp.trim();
|
||||
try {
|
||||
bool = (Boolean) xpath.evaluate(xp, document, XPathConstants.BOOLEAN);
|
||||
} catch (Exception e) {
|
||||
System.out.println("##################ERROR EVALUATING XPATH '" + xp + "'");
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
if (!bool) {
|
||||
System.out.println("##################ERROR");
|
||||
System.out.println("req="+req);
|
||||
System.out.println("xp="+xp);
|
||||
throw new RuntimeException("test failed.");
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
public char[] doUpdate(String req) {
|
||||
try {
|
||||
// String lucene=updateDict[(int)(Math.random()*updateDict.length)];
|
||||
String lucene=req;
|
||||
StringReader ureq = new StringReader(lucene);
|
||||
CharArrayWriter writer = new CharArrayWriter(32000);
|
||||
core.update(ureq, writer);
|
||||
if (verbose) System.out.println("UPDATE RESPONSE:'" + writer + "'");
|
||||
// if (verbose) System.out.println("BODY chars read:" + writer.size());
|
||||
this.numBodyChars+=writer.size();
|
||||
this.numReq++;
|
||||
return writer.toCharArray();
|
||||
} catch (Exception e) {
|
||||
this.numErr++;
|
||||
e.printStackTrace();
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
|
||||
static XMLResponseWriter xmlwriter = new XMLResponseWriter();
|
||||
static SolrRequestHandler handler =
|
||||
// new OldRequestHandler();
|
||||
new StandardRequestHandler();
|
||||
|
||||
public char[] doReq(String req, String params) {
|
||||
int start=0;
|
||||
int limit=10;
|
||||
String handler="standard";
|
||||
//handler="test";
|
||||
|
||||
|
||||
Map args = new HashMap();
|
||||
args.put("indent", "on");
|
||||
args.put("debugQuery", "on");
|
||||
args.put("fl", "score");
|
||||
args.put("version", "2.0");
|
||||
|
||||
if (params != null) {
|
||||
String[] plist = params.split("&");
|
||||
for (String decl : plist) {
|
||||
String[] nv = decl.split("=");
|
||||
if (nv.length==1) {
|
||||
nv = new String[] { nv[0], "" };
|
||||
}
|
||||
if (nv[0].equals("start")) {
|
||||
start=Integer.parseInt(nv[1]);
|
||||
}
|
||||
else if (nv[0].equals("limit")) {
|
||||
limit=Integer.parseInt(nv[1]);
|
||||
}
|
||||
else if (nv[0].equals("qt")) {
|
||||
handler = nv[1];
|
||||
} else {
|
||||
args.put(nv[0], nv[1]);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
try {
|
||||
// String lucene=requestDict[(int)(Math.random()*requestDict.length)];
|
||||
String lucene=req;
|
||||
CharArrayWriter writer = new CharArrayWriter(32000);
|
||||
|
||||
System.out.println("start="+start+" limit="+limit+" handler="+handler);
|
||||
LocalSolrQueryRequest qreq = new LocalSolrQueryRequest(core,lucene,handler,start,limit,args);
|
||||
SolrQueryResponse qrsp = new SolrQueryResponse();
|
||||
try {
|
||||
core.execute(qreq,qrsp);
|
||||
if (qrsp.getException() != null) throw qrsp.getException();
|
||||
// handler.handleRequest(qreq,qrsp);
|
||||
xmlwriter.write(writer,qreq,qrsp);
|
||||
} finally {
|
||||
qreq.close();
|
||||
}
|
||||
if (verbose) System.out.println("GOT:'" + writer + "'");
|
||||
if (verbose) System.out.println("BODY chars read:" + writer.size());
|
||||
this.numBodyChars+=writer.size();
|
||||
this.numReq++;
|
||||
return writer.toCharArray();
|
||||
} catch (Exception e) {
|
||||
this.numErr++;
|
||||
e.printStackTrace();
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
int readers=1;
|
||||
int requests=1;
|
||||
int writers=0;
|
||||
|
||||
Logger log = Logger.getLogger("solar");
|
||||
log.setUseParentHandlers(false);
|
||||
log.setLevel(Level.FINEST);
|
||||
Handler handler = new ConsoleHandler();
|
||||
handler.setLevel(Level.FINEST);
|
||||
log.addHandler(handler);
|
||||
|
||||
String filename="dict.txt";
|
||||
String updateFilename="update_dict.txt";
|
||||
String luceneDir=null;
|
||||
String schemaFile="schema.xml";
|
||||
String testFile=null;
|
||||
|
||||
boolean b_numUpdates=false; boolean b_writers=false;
|
||||
|
||||
int i=0; String arg;
|
||||
while (i < args.length && args[i].startsWith("-")) {
|
||||
arg = args[i++];
|
||||
if (arg.equals("-verbose")) {
|
||||
verbose=true;
|
||||
} else if (arg.equals("-dict")) {
|
||||
filename=args[i++];
|
||||
} else if (arg.equals("-index")) {
|
||||
luceneDir=args[i++];
|
||||
} else if (arg.equals("-readers")) {
|
||||
readers=Integer.parseInt(args[i++]);
|
||||
} else if (arg.equals("-numRequests")) {
|
||||
requests=Integer.parseInt(args[i++]);
|
||||
} else if (arg.equals("-writers")) {
|
||||
writers=Integer.parseInt(args[i++]);
|
||||
b_writers=true;
|
||||
} else if (arg.equals("-schema")) {
|
||||
schemaFile=args[i++];
|
||||
} else if (arg.equals("-test")) {
|
||||
testFile=args[i++];
|
||||
} else if (arg.equals("-noValidate")) {
|
||||
doValidate=false;
|
||||
} else {
|
||||
System.out.println("Unknown option: " + arg);
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
try {
|
||||
|
||||
IndexSchema schema = new IndexSchema(schemaFile);
|
||||
countdown = requests;
|
||||
core=new SolrCore(luceneDir,schema);
|
||||
|
||||
try {
|
||||
if (readers > 0) requestDict = readDict(filename);
|
||||
if (writers > 0) updateDict = readDict(updateFilename);
|
||||
if (testFile != null) {
|
||||
testDict = readDict(testFile);
|
||||
testDictLineno = lineno;
|
||||
}
|
||||
} catch (IOException e) {
|
||||
e.printStackTrace();
|
||||
System.out.println("Can't read "+filename);
|
||||
return;
|
||||
}
|
||||
|
||||
SolrTest[] clients = new SolrTest[readers+writers];
|
||||
for (i=0; i<readers; i++) {
|
||||
clients[i] = new SolrTest();
|
||||
if (testFile != null) clients[i].sequenceTest=true;
|
||||
clients[i].start();
|
||||
}
|
||||
for (i=readers; i<readers+writers; i++) {
|
||||
clients[i] = new SolrTest();
|
||||
clients[i].isWriter = true;
|
||||
clients[i].start();
|
||||
}
|
||||
|
||||
for (i=0; i<readers; i++) {
|
||||
clients[i].join();
|
||||
}
|
||||
for (i=readers; i<readers+writers; i++) {
|
||||
clients[i].join();
|
||||
}
|
||||
|
||||
} finally {
|
||||
if (core != null) core.close();
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,2 @@
|
|||
stopworda
|
||||
stopwordb
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
a => aa
|
||||
b => b1 b2
|
||||
c => c1,c2
|
||||
a\=>a => b\=>b
|
||||
a\,a => b\,b
|
||||
foo,bar,baz
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
<delete><query>id:[* TO *]</query></delete>
|
||||
<optimize/>
|
||||
|
||||
<delete><query>id[0 TO 9]</query></delete>
|
||||
<commit/>
|
||||
|
||||
<add><doc><field name="id">3</field></doc></add>
|
||||
<add><doc><field name="id">1</field></doc></add>
|
||||
<add><doc><field name="id">7</field></doc></add>
|
||||
<add><doc><field name="id">0</field></doc></add>
|
||||
<add><doc><field name="id">5</field></doc></add>
|
||||
<commit/>
|
||||
|
||||
_val_:"linear(id,2,3)"
|
||||
+id:[ 0 TO 5 ] +_val_:"linear(id,2,3)"^0.1
|
||||
+id:[ 0 TO 5 ] +_val_:"linear(rord(id),2,3)"^0.1
|
||||
+id:[ 0 TO 5 ] +_val_:"recip(rord(id),2,3,4)"^0.1
|
||||
+id:[ 0 TO 5 ] +_val_:"linear(linear(rord(id),6,5),2,3)"^0.1
|
||||
|
||||
#<delete><query>id:[0 TO 9]</query></delete>
|
||||
#<commit/>
|
||||
|
||||
<delete><query>weight:[* TO *]</query></delete>
|
||||
<commit/>
|
||||
|
||||
<add><doc><field name="id">10</field><field name="weight">3</field></doc></add>
|
||||
<add><doc><field name="id">11</field><field name="weight">1</field></doc></add>
|
||||
<add><doc><field name="id">12</field><field name="weight">7</field></doc></add>
|
||||
<add><doc><field name="id">13</field><field name="weight">0</field></doc></add>
|
||||
<add><doc><field name="id">14</field><field name="weight">5</field></doc></add>
|
||||
<commit/>
|
||||
|
||||
+id:[10 TO 14] +_val_:weight^2
|
||||
+id:[10 TO 14] +_val_:"ord(weight)"^2
|
||||
+id:[10 TO 14] +_val_:"rord(weight)"^2
|
||||
|
||||
#+id:[10 TO 14] +weight:_int_^2
|
||||
#+id:[10 TO 14] +weight:_ord_^2
|
||||
#+id:[10 TO 14] +weight:_rord_^2
|
||||
|
||||
<add><doc><field name="id">10</field><field name="q_i">2</field></doc></add>
|
||||
<add><doc><field name="id">11</field><field name="q_f">3.14159</field></doc></add>
|
||||
<add><doc><field name="id">12</field><field name="q_l">900</field></doc></add>
|
||||
<add><doc><field name="id">13</field><field name="q_d">.1</field></doc></add>
|
||||
<add><doc><field name="id">14</field><field name="q_dt">2005-01-01T01:01:01Z</field></doc></add>
|
||||
<commit/>
|
||||
_val_:q_i %%fl=score %//@maxScore = //doc/float[@name="score"] %//doc/float[@name="score"] = "2.0"
|
||||
_val_:q_f %%fl=score %//@maxScore = //doc/float[@name="score"] %//doc/float[@name="score"] = "3.14159"
|
||||
_val_:q_l %%fl=score %//@maxScore = //doc/float[@name="score"] %//doc/float[@name="score"] = "900.0"
|
||||
_val_:q_d %%fl=score %//@maxScore = //doc/float[@name="score"] %//doc/float[@name="score"] = "0.1"
|
||||
_val_:q_dt %%fl=score %//@maxScore = //doc/float[@name="score"] %//doc/float[@name="score"] = "1.0"
|
||||
|
|
@ -0,0 +1,68 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
|
||||
import java.util.Map;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: BaseTokenFilterFactory.java,v 1.5 2005/12/06 04:16:16 yonik Exp $
|
||||
*/
|
||||
public abstract class BaseTokenFilterFactory implements TokenFilterFactory {
|
||||
protected Map<String,String> args;
|
||||
public void init(Map<String,String> args) {
|
||||
this.args=args;
|
||||
}
|
||||
|
||||
public Map<String,String> getArgs() {
|
||||
return args;
|
||||
}
|
||||
|
||||
// TODO: move these somewhere that tokenizers and others
|
||||
// can also use them...
|
||||
protected int getInt(String name) {
|
||||
return getInt(name,-1,false);
|
||||
}
|
||||
|
||||
protected int getInt(String name, int defaultVal) {
|
||||
return getInt(name,defaultVal,true);
|
||||
}
|
||||
|
||||
protected int getInt(String name, int defaultVal, boolean useDefault) {
|
||||
String s = args.get(name);
|
||||
if (s==null) {
|
||||
if (useDefault) return defaultVal;
|
||||
throw new RuntimeException("Configuration Error: missing parameter '" + name + "'");
|
||||
}
|
||||
return Integer.parseInt(s);
|
||||
}
|
||||
|
||||
protected boolean getBoolean(String name, boolean defaultVal) {
|
||||
return getBoolean(name,defaultVal,true);
|
||||
}
|
||||
|
||||
protected boolean getBoolean(String name, boolean defaultVal, boolean useDefault) {
|
||||
String s = args.get(name);
|
||||
if (s==null) {
|
||||
if (useDefault) return defaultVal;
|
||||
throw new RuntimeException("Configuration Error: missing parameter '" + name + "'");
|
||||
}
|
||||
return Boolean.parseBoolean(s);
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import java.util.Map;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: BaseTokenizerFactory.java,v 1.3 2005/09/20 04:57:50 yonik Exp $
|
||||
*/
|
||||
public abstract class BaseTokenizerFactory implements TokenizerFactory {
|
||||
protected Map<String,String> args;
|
||||
public void init(Map<String,String> args) {
|
||||
this.args=args;
|
||||
}
|
||||
|
||||
public Map<String,String> getArgs() {
|
||||
return args;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,111 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.solr.core.Config;
|
||||
import org.apache.lucene.analysis.StopFilter;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.TokenFilter;
|
||||
import org.apache.lucene.analysis.Token;
|
||||
|
||||
import java.util.Map;
|
||||
import java.util.List;
|
||||
import java.util.Set;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class EnglishPorterFilterFactory extends BaseTokenFilterFactory {
|
||||
public void init(Map<String, String> args) {
|
||||
super.init(args);
|
||||
String wordFile = args.get("protected");
|
||||
if (wordFile != null) {
|
||||
try {
|
||||
List<String> wlist = Config.getLines(wordFile);
|
||||
protectedWords = StopFilter.makeStopSet((String[])wlist.toArray(new String[0]));
|
||||
} catch (IOException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private Set protectedWords = null;
|
||||
|
||||
public TokenStream create(TokenStream input) {
|
||||
return new EnglishPorterFilter(input,protectedWords);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/** English Porter2 filter that doesn't use reflection to
|
||||
/* adapt lucene to the snowball stemmer code.
|
||||
*/
|
||||
class EnglishPorterFilter extends TokenFilter {
|
||||
private final Set protWords;
|
||||
private net.sf.snowball.ext.EnglishStemmer stemmer;
|
||||
|
||||
public EnglishPorterFilter(TokenStream source, Set protWords) {
|
||||
super(source);
|
||||
this.protWords=protWords;
|
||||
stemmer = new net.sf.snowball.ext.EnglishStemmer();
|
||||
}
|
||||
|
||||
|
||||
/** the original code from lucene sandbox
|
||||
public final Token next() throws IOException {
|
||||
Token token = input.next();
|
||||
if (token == null)
|
||||
return null;
|
||||
stemmer.setCurrent(token.termText());
|
||||
try {
|
||||
stemMethod.invoke(stemmer, EMPTY_ARGS);
|
||||
} catch (Exception e) {
|
||||
throw new RuntimeException(e.toString());
|
||||
}
|
||||
return new Token(stemmer.getCurrent(),
|
||||
token.startOffset(), token.endOffset(), token.type());
|
||||
}
|
||||
**/
|
||||
|
||||
public Token next() throws IOException {
|
||||
Token tok = input.next();
|
||||
if (tok==null) return null;
|
||||
String tokstr = tok.termText();
|
||||
|
||||
// if protected, don't stem. use this to avoid stemming collisions.
|
||||
if (protWords != null && protWords.contains(tokstr)) {
|
||||
return tok;
|
||||
}
|
||||
|
||||
stemmer.setCurrent(tokstr);
|
||||
stemmer.stem();
|
||||
String newstr = stemmer.getCurrent();
|
||||
if (tokstr.equals(newstr)) {
|
||||
return tok;
|
||||
} else {
|
||||
// TODO: it would be nice if I could just set termText directly like
|
||||
// lucene packages can.
|
||||
Token newtok = new Token(newstr, tok.startOffset(), tok.endOffset(), tok.type());
|
||||
newtok.setPositionIncrement(tok.getPositionIncrement());
|
||||
return newtok;
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,32 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.standard.StandardTokenizer;
|
||||
|
||||
import java.io.Reader;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class HTMLStripStandardTokenizerFactory extends BaseTokenizerFactory {
|
||||
public TokenStream create(Reader input) {
|
||||
return new StandardTokenizer(new HTMLStripReader(input));
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.WhitespaceTokenizer;
|
||||
|
||||
import java.io.Reader;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class HTMLStripWhitespaceTokenizerFactory extends BaseTokenizerFactory {
|
||||
public TokenStream create(Reader input) {
|
||||
return new WhitespaceTokenizer(new HTMLStripReader(input));
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,47 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenFilter;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.Token;
|
||||
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: LengthFilter.java,v 1.2 2005/04/24 02:53:35 yonik Exp $
|
||||
*/
|
||||
public final class LengthFilter extends TokenFilter {
|
||||
final int min,max;
|
||||
|
||||
public LengthFilter(TokenStream in, int min, int max) {
|
||||
super(in);
|
||||
this.min=min;
|
||||
this.max=max;
|
||||
//System.out.println("min="+min+" max="+max);
|
||||
}
|
||||
|
||||
public final Token next() throws IOException {
|
||||
for (Token token=input.next(); token!=null; token=input.next()) {
|
||||
final int len = token.endOffset() - token.startOffset();
|
||||
if (len<min || len>max) continue;
|
||||
return token;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,38 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.LengthFilter;
|
||||
|
||||
import java.util.Map;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class LengthFilterFactory extends BaseTokenFilterFactory {
|
||||
int min,max;
|
||||
public void init(Map<String, String> args) {
|
||||
super.init(args);
|
||||
min=Integer.parseInt(args.get("min"));
|
||||
max=Integer.parseInt(args.get("max"));
|
||||
}
|
||||
public TokenStream create(TokenStream input) {
|
||||
return new LengthFilter(input,min,max);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.LetterTokenizer;
|
||||
|
||||
import java.io.Reader;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class LetterTokenizerFactory extends BaseTokenizerFactory {
|
||||
public TokenStream create(Reader input) {
|
||||
return new LetterTokenizer(input);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.LowerCaseFilter;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class LowerCaseFilterFactory extends BaseTokenFilterFactory {
|
||||
public TokenStream create(TokenStream input) {
|
||||
return new LowerCaseFilter(input);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.LowerCaseTokenizer;
|
||||
|
||||
import java.io.Reader;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class LowerCaseTokenizerFactory extends BaseTokenizerFactory {
|
||||
public TokenStream create(Reader input) {
|
||||
return new LowerCaseTokenizer(input);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.PorterStemFilter;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class PorterStemFilterFactory extends BaseTokenFilterFactory {
|
||||
public TokenStream create(TokenStream input) {
|
||||
return new PorterStemFilter(input);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.snowball.SnowballFilter;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class SnowballPorterFilterFactory extends BaseTokenFilterFactory {
|
||||
public TokenStream create(TokenStream input) {
|
||||
// Browsing the code, SnowballFilter uses reflection to adapt to Lucene...
|
||||
// don't use this if you are concerned about speed. Use EnglishPorterFilterFactory.
|
||||
|
||||
// TODO: make language configurable
|
||||
return new SnowballFilter(input,"English");
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.standard.StandardFilter;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class StandardFilterFactory extends BaseTokenFilterFactory {
|
||||
public TokenStream create(TokenStream input) {
|
||||
return new StandardFilter(input);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,33 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.standard.StandardTokenizer;
|
||||
|
||||
import java.io.Reader;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
|
||||
public class StandardTokenizerFactory extends BaseTokenizerFactory {
|
||||
public TokenStream create(Reader input) {
|
||||
return new StandardTokenizer(input);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,55 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.solr.core.Config;
|
||||
import org.apache.lucene.analysis.StopFilter;
|
||||
import org.apache.lucene.analysis.StopAnalyzer;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
|
||||
import java.util.Map;
|
||||
import java.util.List;
|
||||
import java.util.Set;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class StopFilterFactory extends BaseTokenFilterFactory {
|
||||
public void init(Map<String, String> args) {
|
||||
super.init(args);
|
||||
String stopWordFile = args.get("words");
|
||||
ignoreCase = getBoolean("ignoreCase",false);
|
||||
|
||||
if (stopWordFile != null) {
|
||||
try {
|
||||
List<String> wlist = Config.getLines(stopWordFile);
|
||||
stopWords = StopFilter.makeStopSet((String[])wlist.toArray(new String[0]), ignoreCase);
|
||||
} catch (IOException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private Set stopWords = StopFilter.makeStopSet(StopAnalyzer.ENGLISH_STOP_WORDS);
|
||||
private boolean ignoreCase;
|
||||
|
||||
public TokenStream create(TokenStream input) {
|
||||
return new StopFilter(input,stopWords,ignoreCase);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,125 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.SynonymFilter;
|
||||
import org.apache.lucene.analysis.SynonymMap;
|
||||
|
||||
import java.util.Map;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
import java.io.IOException;
|
||||
|
||||
import org.apache.solr.util.StrUtils;
|
||||
import org.apache.solr.analysis.BaseTokenFilterFactory;
|
||||
import org.apache.solr.core.Config;
|
||||
import org.apache.solr.core.SolrCore;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class SynonymFilterFactory extends BaseTokenFilterFactory {
|
||||
public void init(Map<String, String> args) {
|
||||
super.init(args);
|
||||
String synonyms = args.get("synonyms");
|
||||
|
||||
ignoreCase = getBoolean("ignoreCase",false);
|
||||
expand = getBoolean("expand",true);
|
||||
|
||||
if (synonyms != null) {
|
||||
List<String> wlist=null;
|
||||
try {
|
||||
wlist = Config.getLines(synonyms);
|
||||
} catch (IOException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
synMap = new SynonymMap();
|
||||
parseRules(wlist, synMap, "=>", ",", ignoreCase,expand);
|
||||
if (wlist.size()<=20) {
|
||||
SolrCore.log.fine("SynonymMap "+synonyms +":"+synMap);
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
private SynonymMap synMap;
|
||||
private boolean ignoreCase;
|
||||
private boolean expand;
|
||||
|
||||
private static void parseRules(List<String> rules, SynonymMap map, String mappingSep, String synSep, boolean ignoreCase, boolean expansion) {
|
||||
int count=0;
|
||||
for (String rule : rules) {
|
||||
// To use regexes, we need an expression that specifies an odd number of chars.
|
||||
// This can't really be done with string.split(), and since we need to
|
||||
// do unescaping at some point anyway, we wouldn't be saving any effort
|
||||
// by using regexes.
|
||||
|
||||
List<String> mapping = StrUtils.splitSmart(rule, mappingSep, false);
|
||||
|
||||
List<List<String>> source;
|
||||
List<List<String>> target;
|
||||
|
||||
if (mapping.size() > 2) {
|
||||
throw new RuntimeException("Invalid Synonym Rule:" + rule);
|
||||
} else if (mapping.size()==2) {
|
||||
source = getSynList(mapping.get(0), synSep);
|
||||
target = getSynList(mapping.get(1), synSep);
|
||||
} else {
|
||||
source = getSynList(mapping.get(0), synSep);
|
||||
if (expansion) {
|
||||
// expand to all arguments
|
||||
target = source;
|
||||
} else {
|
||||
// reduce to first argument
|
||||
target = new ArrayList<List<String>>(1);
|
||||
target.add(source.get(0));
|
||||
}
|
||||
}
|
||||
|
||||
boolean includeOrig=false;
|
||||
for (List<String> fromToks : source) {
|
||||
count++;
|
||||
for (List<String> toToks : target) {
|
||||
map.add(ignoreCase ? StrUtils.toLower(fromToks) : fromToks,
|
||||
SynonymMap.makeTokens(toToks),
|
||||
includeOrig,
|
||||
true);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// a , b c , d e f => [[a],[b,c],[d,e,f]]
|
||||
private static List<List<String>> getSynList(String str, String separator) {
|
||||
List<String> strList = StrUtils.splitSmart(str, separator, false);
|
||||
// now split on whitespace to get a list of token strings
|
||||
List<List<String>> synList = new ArrayList<List<String>>();
|
||||
for (String toks : strList) {
|
||||
List<String> tokList = StrUtils.splitWS(toks, true);
|
||||
synList.add(tokList);
|
||||
}
|
||||
return synList;
|
||||
}
|
||||
|
||||
|
||||
public TokenStream create(TokenStream input) {
|
||||
return new SynonymFilter(input,synMap,ignoreCase);
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
|
||||
import java.util.Map;
|
||||
|
||||
/**
|
||||
* Factory to create a token filter that transforms one TokenStream to another.
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: TokenFilterFactory.java,v 1.3 2005/09/20 04:58:28 yonik Exp $
|
||||
*/
|
||||
|
||||
public interface TokenFilterFactory {
|
||||
public void init(Map<String,String> args);
|
||||
public Map<String,String> getArgs();
|
||||
public TokenStream create(TokenStream input);
|
||||
}
|
||||
|
|
@ -0,0 +1,65 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.Analyzer;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.solr.analysis.TokenizerFactory;
|
||||
|
||||
import java.io.Reader;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: TokenizerChain.java,v 1.3 2005/08/26 05:21:08 yonik Exp $
|
||||
*/
|
||||
|
||||
//
|
||||
// An analyzer that uses a tokenizer and a list of token filters to
|
||||
// create a TokenStream.
|
||||
//
|
||||
public class TokenizerChain extends Analyzer {
|
||||
final private TokenizerFactory tokenizer;
|
||||
final private TokenFilterFactory[] filters;
|
||||
|
||||
public TokenizerChain(TokenizerFactory tokenizer, TokenFilterFactory[] filters) {
|
||||
this.tokenizer = tokenizer;
|
||||
this.filters = filters;
|
||||
}
|
||||
|
||||
public TokenizerFactory getTokenizerFactory() { return tokenizer; }
|
||||
public TokenFilterFactory[] getTokenFilterFactories() { return filters; }
|
||||
|
||||
public TokenStream tokenStream(String fieldName, Reader reader) {
|
||||
TokenStream ts = tokenizer.create(reader);
|
||||
for (int i=0; i<filters.length; i++) {
|
||||
ts = filters[i].create(ts);
|
||||
}
|
||||
return ts;
|
||||
}
|
||||
|
||||
public String toString() {
|
||||
StringBuilder sb = new StringBuilder("TokenizerChain(");
|
||||
sb.append(tokenizer);
|
||||
for (TokenFilterFactory filter: filters) {
|
||||
sb.append(", ");
|
||||
sb.append(filter);
|
||||
}
|
||||
sb.append(')');
|
||||
return sb.toString();
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,37 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import java.io.*;
|
||||
import java.util.Map;
|
||||
|
||||
import org.apache.lucene.analysis.*;
|
||||
|
||||
|
||||
/**
|
||||
* A <code>TokenizerFactory</code> creates a <code>Tokenizer</code> on demand
|
||||
* that breaks up a stream of characters into tokens.
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: TokenizerFactory.java,v 1.10 2005/12/13 05:16:03 yonik Exp $
|
||||
*/
|
||||
public interface TokenizerFactory {
|
||||
public void init(Map<String,String> args);
|
||||
public Map<String,String> getArgs();
|
||||
public TokenStream create(Reader input);
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.WhitespaceTokenizer;
|
||||
|
||||
import java.io.Reader;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class WhitespaceTokenizerFactory extends BaseTokenizerFactory {
|
||||
public TokenStream create(Reader input) {
|
||||
return new WhitespaceTokenizer(input);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,444 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenFilter;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.Token;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* Splits words into subwords and performs optional transformations on subword groups.
|
||||
* Words are split into subwords with the following rules:
|
||||
* - split on intra-word delimiters (by default, all non alpha-numeric characters).
|
||||
* - "Wi-Fi" -> "Wi", "Fi"
|
||||
* - split on case transitions
|
||||
* - "PowerShot" -> "Power", "Shot"
|
||||
* - split on letter-number transitions
|
||||
* - "SD500" -> "SD", "500"
|
||||
* - leading and trailing intra-word delimiters on each subword are ignored
|
||||
* - "//hello---there, 'dude'" -> "hello", "there", "dude"
|
||||
* - trailing "'s" are removed for each subword
|
||||
* - "O'Neil's" -> "O", "Neil"
|
||||
* - Note: this step isn't performed in a separate filter because of possible subword combinations.
|
||||
*
|
||||
* The <b>combinations</b> parameter affects how subwords are combined:
|
||||
* - combinations="0" causes no subword combinations.
|
||||
* - "PowerShot" -> 0:"Power", 1:"Shot" (0 and 1 are the token positions)
|
||||
* - combinations="1" means that in addition to the subwords, maximum runs of non-numeric subwords are catenated and produced at the same position of the last subword in the run.
|
||||
* - "PowerShot" -> 0:"Power", 1:"Shot" 1:"PowerShot"
|
||||
* - "A's+B's&C's" -> 0:"A", 1:"B", 2:"C", 2:"ABC"
|
||||
* - "Super-Duper-XL500-42-AutoCoder!" -> 0:"Super", 1:"Duper", 2:"XL", 2:"SuperDuperXL", 3:"500" 4:"42", 5:"Auto", 6:"Coder", 6:"AutoCoder"
|
||||
*
|
||||
* One use for WordDelimiterFilter is to help match words with different subword delimiters.
|
||||
* For example, if the source text contained "wi-fi" one may want "wifi" "WiFi" "wi-fi" "wi+fi"
|
||||
* queries to all match.
|
||||
* One way of doing so is to specify combinations="1" in the analyzer
|
||||
* used for indexing, and combinations="0" (the default) in the analyzer
|
||||
* used for querying. Given that the current StandardTokenizer
|
||||
* immediately removes many intra-word delimiters, it is recommended that
|
||||
* this filter be used after a tokenizer that does not do this
|
||||
* (such as WhitespaceTokenizer).
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: WordDelimiterFilter.java,v 1.6 2005/09/20 03:54:05 yonik Exp $
|
||||
*/
|
||||
final class WordDelimiterFilter extends TokenFilter {
|
||||
private final byte[] charTypeTable;
|
||||
|
||||
public static final int LOWER=0x01;
|
||||
public static final int UPPER=0x02;
|
||||
public static final int DIGIT=0x04;
|
||||
public static final int SUBWORD_DELIM=0x08;
|
||||
|
||||
// combinations: for testing, not for setting bits
|
||||
public static final int ALPHA=0x03;
|
||||
public static final int ALPHANUM=0x07;
|
||||
|
||||
// TODO: should there be a WORD_DELIM category for
|
||||
// chars that only separate words (no catenation of subwords
|
||||
// will be done if separated by these chars?)
|
||||
// "," would be an obvious candidate...
|
||||
|
||||
static byte[] defaultWordDelimTable;
|
||||
static {
|
||||
byte[] tab = new byte[256];
|
||||
for (int i=0; i<256; i++) {
|
||||
byte code = 0;
|
||||
if (Character.isLowerCase(i)) code |= LOWER;
|
||||
else if (Character.isUpperCase(i)) code |= UPPER;
|
||||
else if (Character.isDigit(i)) code |= DIGIT;
|
||||
if (code==0) code=SUBWORD_DELIM;
|
||||
tab[i]=code;
|
||||
}
|
||||
defaultWordDelimTable = tab;
|
||||
}
|
||||
|
||||
final int generateWordParts;
|
||||
final int generateNumberParts;
|
||||
final int catenateWords;
|
||||
final int catenateNumbers;
|
||||
final int catenateAll;
|
||||
|
||||
public WordDelimiterFilter(TokenStream in, byte[] charTypeTable, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll) {
|
||||
super(in);
|
||||
this.generateWordParts = generateWordParts;
|
||||
this.generateNumberParts = generateNumberParts;
|
||||
this.catenateWords = catenateWords;
|
||||
this.catenateNumbers = catenateNumbers;
|
||||
this.catenateAll = catenateAll;
|
||||
this.charTypeTable = charTypeTable;
|
||||
}
|
||||
|
||||
public WordDelimiterFilter(TokenStream in, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll) {
|
||||
this(in, defaultWordDelimTable, generateWordParts, generateNumberParts, catenateWords, catenateNumbers, catenateAll);
|
||||
}
|
||||
|
||||
int charType(int ch) {
|
||||
if (ch<charTypeTable.length) {
|
||||
return charTypeTable[ch];
|
||||
} else if (Character.isLowerCase(ch)) {
|
||||
return LOWER;
|
||||
} else if (Character.isLetter(ch)) {
|
||||
return UPPER;
|
||||
} else {
|
||||
return SUBWORD_DELIM;
|
||||
}
|
||||
}
|
||||
|
||||
private int charType(String s, int pos) {
|
||||
return charType(s.charAt(pos));
|
||||
}
|
||||
|
||||
// use the type of the first char as the type
|
||||
// of the token.
|
||||
private int tokType(Token t) {
|
||||
return charType(t.termText().charAt(0));
|
||||
}
|
||||
|
||||
// There isn't really an efficient queue class, so we will
|
||||
// just use an array for now.
|
||||
private ArrayList<Token> queue = new ArrayList<Token>(4);
|
||||
private int queuePos=0;
|
||||
|
||||
// temporary working queue
|
||||
private ArrayList<Token> tlist = new ArrayList<Token>(4);
|
||||
|
||||
|
||||
private Token newTok(Token orig, int start, int end) {
|
||||
return new Token(orig.termText().substring(start,end),
|
||||
orig.startOffset() + start,
|
||||
orig.startOffset() + end,
|
||||
orig.type());
|
||||
}
|
||||
|
||||
|
||||
public final Token next() throws IOException {
|
||||
|
||||
// check the queue first
|
||||
if (queuePos<queue.size()) {
|
||||
return queue.get(queuePos++);
|
||||
}
|
||||
|
||||
// reset the queue if it had been previously used
|
||||
if (queuePos!=0) {
|
||||
queuePos=0;
|
||||
queue.clear();
|
||||
}
|
||||
|
||||
|
||||
// optimize for the common case: assume there will be
|
||||
// no subwords (just a simple word)
|
||||
//
|
||||
// Would it actually be faster to check for the common form
|
||||
// of isLetter() isLower()*, and then backtrack if it doesn't match?
|
||||
|
||||
while(true) {
|
||||
Token t = input.next();
|
||||
if (t == null) return null;
|
||||
|
||||
String s = t.termText();
|
||||
int off=t.startOffset();
|
||||
int start=0;
|
||||
int end=s.length();
|
||||
if (end==0) continue;
|
||||
|
||||
// Avoid calling charType more than once for each char (basically
|
||||
// avoid any backtracking).
|
||||
// makes code slightly more difficult, but faster.
|
||||
int ch=s.charAt(start);
|
||||
int type=charType(ch);
|
||||
|
||||
int numWords=0;
|
||||
|
||||
while (start<end) {
|
||||
// first eat delimiters at the start of this subword
|
||||
while ((type & SUBWORD_DELIM)!=0 && ++start<end) {
|
||||
ch=s.charAt(start);
|
||||
type=charType(ch);
|
||||
}
|
||||
|
||||
int pos=start;
|
||||
|
||||
// save the type of the first char of the subword
|
||||
// as a way to tell what type of subword token this is (number, word, etc)
|
||||
int firstType=type;
|
||||
int lastType=type; // type of the previously read char
|
||||
|
||||
|
||||
while (pos<end) {
|
||||
|
||||
if (type!=lastType) {
|
||||
// check and remove "'s" from the end of a token.
|
||||
// the pattern to check for is
|
||||
// ALPHA "'" ("s"|"S") (SUBWORD_DELIM | END)
|
||||
if ((lastType & ALPHA)!=0) {
|
||||
if (ch=='\'' && pos+1<end
|
||||
&& (s.charAt(pos+1)=='s' || s.charAt(pos+1)=='S'))
|
||||
{
|
||||
int subWordEnd=pos;
|
||||
if (pos+2>=end) {
|
||||
// end of string detected after "'s"
|
||||
pos+=2;
|
||||
} else {
|
||||
// make sure that a delimiter follows "'s"
|
||||
int ch2 = s.charAt(pos+2);
|
||||
int type2 = charType(ch2);
|
||||
if ((type2 & SUBWORD_DELIM)!=0) {
|
||||
// if delimiter, move position pointer
|
||||
// to it (skipping over "'s"
|
||||
ch=ch2;
|
||||
type=type2;
|
||||
pos+=2;
|
||||
}
|
||||
}
|
||||
|
||||
queue.add(newTok(t,start,subWordEnd));
|
||||
if ((firstType & ALPHA)!=0) numWords++;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// For case changes, only split on a transition from
|
||||
// lower to upper case, not vice-versa.
|
||||
// That will correctly handle the
|
||||
// case of a word starting with a capital (won't split).
|
||||
// It will also handle pluralization of
|
||||
// an uppercase word such as FOOs (won't split).
|
||||
|
||||
if ((lastType & UPPER)!=0 && (type & LOWER)!=0) {
|
||||
// UPPER->LOWER: Don't split
|
||||
} else {
|
||||
// NOTE: this code currently assumes that only one flag
|
||||
// is set for each character now, so we don't have
|
||||
// to explicitly check for all the classes of transitions
|
||||
// listed below.
|
||||
|
||||
// LOWER->UPPER
|
||||
// ALPHA->NUMERIC
|
||||
// NUMERIC->ALPHA
|
||||
// *->DELIMITER
|
||||
queue.add(newTok(t,start,pos));
|
||||
if ((firstType & ALPHA)!=0) numWords++;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
if (++pos >= end) {
|
||||
if (start==0) {
|
||||
// the subword is the whole original token, so
|
||||
// return it unchanged.
|
||||
return t;
|
||||
}
|
||||
|
||||
Token newtok = newTok(t,start,pos);
|
||||
|
||||
// optimization... if this is the only token,
|
||||
// return it immediately.
|
||||
if (queue.size()==0) {
|
||||
return newtok;
|
||||
}
|
||||
|
||||
queue.add(newtok);
|
||||
if ((firstType & ALPHA)!=0) numWords++;
|
||||
break;
|
||||
}
|
||||
|
||||
lastType = type;
|
||||
ch = s.charAt(pos);
|
||||
type = charType(ch);
|
||||
}
|
||||
|
||||
// start of the next subword is the current position
|
||||
start=pos;
|
||||
}
|
||||
|
||||
// System.out.println("##########TOKEN=" + s + " ######### WORD DELIMITER QUEUE=" + str(queue));
|
||||
|
||||
final int numtok = queue.size();
|
||||
|
||||
// We reached the end of the current token.
|
||||
// If the queue is empty, we should continue by reading
|
||||
// the next token
|
||||
if (numtok==0) {
|
||||
continue;
|
||||
}
|
||||
|
||||
// if number of tokens is 1, always return the single tok
|
||||
if (numtok==1) {
|
||||
break;
|
||||
}
|
||||
|
||||
final int numNumbers = numtok - numWords;
|
||||
|
||||
// check conditions under which the current token
|
||||
// queue may be used as-is (no catenations needed)
|
||||
if (catenateAll==0 // no "everything" to catenate
|
||||
&& (catenateWords==0 || numWords<=1) // no words to catenate
|
||||
&& (catenateNumbers==0 || numNumbers<=1) // no numbers to catenate
|
||||
&& (generateWordParts!=0 || numWords==0) // word generation is on
|
||||
&& (generateNumberParts!=0 || numNumbers==0)) // number generation is on
|
||||
{
|
||||
break;
|
||||
}
|
||||
|
||||
|
||||
// swap queue and the temporary working list, then clear the
|
||||
// queue in preparation for adding all combinations back to it.
|
||||
ArrayList<Token> tmp=tlist;
|
||||
tlist=queue;
|
||||
queue=tmp;
|
||||
queue.clear();
|
||||
|
||||
if (numWords==0) {
|
||||
// all numbers
|
||||
addCombos(tlist,0,numtok,generateNumberParts!=0,catenateNumbers!=0 || catenateAll!=0, 1);
|
||||
break;
|
||||
} else if (numNumbers==0) {
|
||||
// all words
|
||||
addCombos(tlist,0,numtok,generateWordParts!=0,catenateWords!=0 || catenateAll!=0, 1);
|
||||
break;
|
||||
} else if (generateNumberParts==0 && generateWordParts==0 && catenateNumbers==0 && catenateWords==0) {
|
||||
// catenate all *only*
|
||||
// OPT:could be optimized to add to current queue...
|
||||
addCombos(tlist,0,numtok,false,catenateAll!=0, 1);
|
||||
break;
|
||||
}
|
||||
|
||||
//
|
||||
// Find all adjacent tokens of the same type.
|
||||
//
|
||||
Token tok = tlist.get(0);
|
||||
boolean isWord = (tokType(tok) & ALPHA) != 0;
|
||||
boolean wasWord=isWord;
|
||||
|
||||
for(int i=0; i<numtok;) {
|
||||
int j;
|
||||
for (j=i+1; j<numtok; j++) {
|
||||
wasWord=isWord;
|
||||
tok = tlist.get(j);
|
||||
isWord = (tokType(tok) & ALPHA) != 0;
|
||||
if (isWord != wasWord) break;
|
||||
}
|
||||
if (wasWord) {
|
||||
addCombos(tlist,i,j,generateWordParts!=0,catenateWords!=0,1);
|
||||
} else {
|
||||
addCombos(tlist,i,j,generateNumberParts!=0,catenateNumbers!=0,1);
|
||||
}
|
||||
i=j;
|
||||
}
|
||||
|
||||
// take care catenating all subwords
|
||||
if (catenateAll!=0) {
|
||||
addCombos(tlist,0,numtok,false,true,0);
|
||||
}
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
// System.out.println("##########AFTER COMBINATIONS:"+ str(queue));
|
||||
|
||||
queuePos=1;
|
||||
return queue.get(0);
|
||||
}
|
||||
|
||||
|
||||
// index "a","b","c" as pos0="a", pos1="b", pos2="c", pos2="abc"
|
||||
private void addCombos(List<Token> lst, int start, int end, boolean generateSubwords, boolean catenateSubwords, int posOffset) {
|
||||
if (end-start==1) {
|
||||
// always generate a word alone, even if generateSubwords=0 because
|
||||
// the catenation of all the subwords *is* the subword.
|
||||
queue.add(lst.get(start));
|
||||
return;
|
||||
}
|
||||
|
||||
StringBuilder sb = null;
|
||||
if (catenateSubwords) sb=new StringBuilder();
|
||||
Token firstTok=null;
|
||||
Token tok=null;
|
||||
for (int i=start; i<end; i++) {
|
||||
tok = lst.get(i);
|
||||
if (catenateSubwords) {
|
||||
if (i==start) firstTok=tok;
|
||||
sb.append(tok.termText());
|
||||
}
|
||||
if (generateSubwords) {
|
||||
queue.add(tok);
|
||||
}
|
||||
}
|
||||
|
||||
if (catenateSubwords) {
|
||||
Token concatTok = new Token(sb.toString(),
|
||||
firstTok.startOffset(),
|
||||
tok.endOffset(),
|
||||
firstTok.type());
|
||||
// if we indexed some other tokens, then overlap concatTok with the last.
|
||||
// Otherwise, use the value passed in as the position offset.
|
||||
concatTok.setPositionIncrement(generateSubwords==true ? 0 : posOffset);
|
||||
queue.add(concatTok);
|
||||
}
|
||||
}
|
||||
|
||||
private String str(List<Token> lst) {
|
||||
StringBuilder sb = new StringBuilder();
|
||||
sb.append('{');
|
||||
for (Token t : lst) {
|
||||
sb.append('(');
|
||||
sb.append('"');
|
||||
sb.append(t.termText());
|
||||
sb.append("\",increment=");
|
||||
sb.append(Integer.toString(t.getPositionIncrement()));
|
||||
sb.append(')');
|
||||
|
||||
sb.append(',');
|
||||
}
|
||||
sb.append('}');
|
||||
return sb.toString();
|
||||
}
|
||||
|
||||
|
||||
|
||||
// questions:
|
||||
// negative numbers? -42 indexed as just 42?
|
||||
// dollar sign? $42
|
||||
// percent sign? 33%
|
||||
// downsides: if source text is "powershot" then a query of "PowerShot" won't match!
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.analysis;
|
||||
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
|
||||
import java.util.Map;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class WordDelimiterFilterFactory extends BaseTokenFilterFactory {
|
||||
int generateWordParts=0;
|
||||
int generateNumberParts=0;
|
||||
int catenateWords=0;
|
||||
int catenateNumbers=0;
|
||||
int catenateAll=0;
|
||||
|
||||
public void init(Map<String, String> args) {
|
||||
super.init(args);
|
||||
generateWordParts = getInt("generateWordParts",1);
|
||||
generateNumberParts = getInt("generateNumberParts",1);
|
||||
catenateWords = getInt("catenateWords",0);
|
||||
catenateNumbers = getInt("catenateNumbers",0);
|
||||
catenateAll = getInt("catenateAll",0);
|
||||
}
|
||||
|
||||
public TokenStream create(TokenStream input) {
|
||||
return new WordDelimiterFilter(input,
|
||||
generateWordParts, generateNumberParts,
|
||||
catenateWords, catenateNumbers, catenateAll);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,43 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import org.apache.solr.search.SolrIndexSearcher;
|
||||
import org.apache.solr.util.NamedList;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
*/
|
||||
class AbstractSolrEventListener implements SolrEventListener {
|
||||
protected NamedList args;
|
||||
|
||||
public void init(NamedList args) {
|
||||
this.args = args;
|
||||
}
|
||||
|
||||
public void postCommit() {
|
||||
throw new UnsupportedOperationException();
|
||||
}
|
||||
|
||||
public void newSearcher(SolrIndexSearcher newSearcher, SolrIndexSearcher currentSearcher) {
|
||||
throw new UnsupportedOperationException();
|
||||
}
|
||||
|
||||
public String toString() {
|
||||
return getClass().getName() + args;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,260 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import org.w3c.dom.Document;
|
||||
import org.w3c.dom.Node;
|
||||
import org.xml.sax.SAXException;
|
||||
import org.apache.solr.core.SolrCore;
|
||||
import org.apache.solr.core.SolrException;
|
||||
|
||||
import javax.xml.parsers.*;
|
||||
import javax.xml.xpath.XPath;
|
||||
import javax.xml.xpath.XPathFactory;
|
||||
import javax.xml.xpath.XPathConstants;
|
||||
import javax.xml.xpath.XPathExpressionException;
|
||||
import javax.xml.namespace.QName;
|
||||
import java.io.*;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
import java.util.logging.Logger;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: Config.java,v 1.10 2005/12/20 16:05:46 yonik Exp $
|
||||
*/
|
||||
public class Config {
|
||||
public static final Logger log = Logger.getLogger(SolrCore.class.getName());
|
||||
|
||||
static final XPathFactory xpathFactory = XPathFactory.newInstance();
|
||||
|
||||
private Document doc;
|
||||
private String prefix;
|
||||
private String name;
|
||||
|
||||
public Config(String name, InputStream is, String prefix) throws ParserConfigurationException, IOException, SAXException {
|
||||
this.name = name;
|
||||
this.prefix = prefix;
|
||||
if (prefix!=null && !prefix.endsWith("/")) prefix += '/';
|
||||
|
||||
javax.xml.parsers.DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
|
||||
doc = builder.parse(is);
|
||||
}
|
||||
|
||||
public Document getDocument() {
|
||||
return doc;
|
||||
}
|
||||
|
||||
public XPath getXPath() {
|
||||
return xpathFactory.newXPath();
|
||||
}
|
||||
|
||||
private String normalize(String path) {
|
||||
return (prefix==null || path.startsWith("/")) ? path : prefix+path;
|
||||
}
|
||||
|
||||
|
||||
public Object evaluate(String path, QName type) {
|
||||
XPath xpath = xpathFactory.newXPath();
|
||||
try {
|
||||
String xstr=normalize(path);
|
||||
|
||||
// TODO: instead of prepending /prefix/, we could do the search rooted at /prefix...
|
||||
Object o = xpath.evaluate(xstr, doc, type);
|
||||
return o;
|
||||
|
||||
} catch (XPathExpressionException e) {
|
||||
throw new SolrException(500,"Error in xpath:" + path +" for " + name,e,false);
|
||||
}
|
||||
}
|
||||
|
||||
public Node getNode(String path, boolean errIfMissing) {
|
||||
XPath xpath = xpathFactory.newXPath();
|
||||
Node nd = null;
|
||||
String xstr = normalize(path);
|
||||
|
||||
try {
|
||||
nd = (Node)xpath.evaluate(xstr, doc, XPathConstants.NODE);
|
||||
|
||||
if (nd==null) {
|
||||
if (errIfMissing) {
|
||||
throw new RuntimeException(name + " missing "+path);
|
||||
} else {
|
||||
log.fine(name + " missing optional " + path);
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
log.finest(name + ":" + path + "=" + nd);
|
||||
return nd;
|
||||
|
||||
} catch (XPathExpressionException e) {
|
||||
SolrException.log(log,"Error in xpath",e);
|
||||
throw new SolrException(500,"Error in xpath:" + xstr + " for " + name,e,false);
|
||||
} catch (SolrException e) {
|
||||
throw(e);
|
||||
} catch (Throwable e) {
|
||||
SolrException.log(log,"Error in xpath",e);
|
||||
throw new SolrException(500,"Error in xpath:" + xstr+ " for " + name,e,false);
|
||||
}
|
||||
}
|
||||
|
||||
public String getVal(String path, boolean errIfMissing) {
|
||||
Node nd = getNode(path,errIfMissing);
|
||||
if (nd==null) return null;
|
||||
|
||||
// should do the right thing for both attributes and elements.
|
||||
// Oops, when running in Resin, I get an unsupported operation
|
||||
// exception... need to use Sun default (apache)
|
||||
String txt = nd.getTextContent();
|
||||
log.fine(name + ' '+path+'='+txt);
|
||||
return txt;
|
||||
|
||||
/******
|
||||
short typ = nd.getNodeType();
|
||||
if (typ==Node.ATTRIBUTE_NODE || typ==Node.TEXT_NODE) {
|
||||
return nd.getNodeValue();
|
||||
}
|
||||
return nd.getTextContent();
|
||||
******/
|
||||
}
|
||||
|
||||
|
||||
public String get(String path) {
|
||||
return getVal(path,true);
|
||||
}
|
||||
|
||||
public String get(String path, String def) {
|
||||
String val = getVal(path, false);
|
||||
return val!=null ? val : def;
|
||||
}
|
||||
|
||||
public int getInt(String path) {
|
||||
return Integer.parseInt(getVal(path, false));
|
||||
}
|
||||
|
||||
public int getInt(String path, int def) {
|
||||
String val = getVal(path, false);
|
||||
return val!=null ? Integer.parseInt(val) : def;
|
||||
}
|
||||
|
||||
public boolean getBool(String path) {
|
||||
return Boolean.parseBoolean(getVal(path, false));
|
||||
}
|
||||
|
||||
public boolean getBool(String path, boolean def) {
|
||||
String val = getVal(path, false);
|
||||
return val!=null ? Boolean.parseBoolean(val) : def;
|
||||
}
|
||||
|
||||
public float getFloat(String path) {
|
||||
return Float.parseFloat(getVal(path, false));
|
||||
}
|
||||
|
||||
public float getFloat(String path, float def) {
|
||||
String val = getVal(path, false);
|
||||
return val!=null ? Float.parseFloat(val) : def;
|
||||
}
|
||||
|
||||
|
||||
//
|
||||
// classloader related functions
|
||||
//
|
||||
|
||||
private static final String project = "solr";
|
||||
private static final String base = "org.apache" + "." + project;
|
||||
private static final String[] packages = {"","analysis.","schema.","search.","update.","core.","request.","util."};
|
||||
|
||||
public static Class findClass(String cname, String... subpackages) {
|
||||
ClassLoader loader = Thread.currentThread().getContextClassLoader();
|
||||
if (subpackages.length==0) subpackages = packages;
|
||||
|
||||
// first try cname == full name
|
||||
try {
|
||||
return Class.forName(cname, true, loader);
|
||||
} catch (ClassNotFoundException e) {
|
||||
String newName=cname;
|
||||
if (newName.startsWith("solar.")) {
|
||||
// handle legacy package names
|
||||
newName = cname.substring("solar.".length());
|
||||
} else if (cname.startsWith(project+".")) {
|
||||
newName = cname.substring(project.length()+1);
|
||||
}
|
||||
|
||||
for (String subpackage : subpackages) {
|
||||
try {
|
||||
String name = base + '.' + subpackage + newName;
|
||||
log.finest("Trying class name " + name);
|
||||
return Class.forName(name, true, loader);
|
||||
} catch (ClassNotFoundException e1) {
|
||||
// ignore... assume first exception is best.
|
||||
}
|
||||
}
|
||||
|
||||
throw new SolrException(500, "Error loading class '" + cname + "'", e, false);
|
||||
}
|
||||
}
|
||||
|
||||
public static Object newInstance(String cname, String... subpackages) {
|
||||
Class clazz = findClass(cname,subpackages);
|
||||
try {
|
||||
return clazz.newInstance();
|
||||
} catch (Exception e) {
|
||||
throw new SolrException(500,"Error instantiating class " + clazz, e, false);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public static InputStream openResource(String resource) {
|
||||
ClassLoader loader = Thread.currentThread().getContextClassLoader();
|
||||
InputStream is = loader.getResourceAsStream(resource);
|
||||
if (is==null) {
|
||||
throw new SolrException(500,"Can't open " + resource);
|
||||
}
|
||||
return is;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns a list of non-blank non-comment lines with whitespace trimmed from front and back.
|
||||
* @param resource
|
||||
* @return
|
||||
* @throws IOException
|
||||
*/
|
||||
public static List<String> getLines(String resource) throws IOException {
|
||||
BufferedReader input = null;
|
||||
try {
|
||||
// todo - allow configurable charset?
|
||||
input = new BufferedReader(new InputStreamReader(openResource(resource), "UTF-8"));
|
||||
} catch (UnsupportedEncodingException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
ArrayList<String> lines = new ArrayList<String>();
|
||||
for (String word=null; (word=input.readLine())!=null;) {
|
||||
// skip comments
|
||||
if (word.startsWith("#")) continue;
|
||||
word=word.trim();
|
||||
// skip blank lines
|
||||
if (word.length()==0) continue;
|
||||
lines.add(word);
|
||||
}
|
||||
return lines;
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import org.apache.solr.search.SolrIndexSearcher;
|
||||
import org.apache.solr.request.LocalSolrQueryRequest;
|
||||
import org.apache.solr.request.SolrQueryResponse;
|
||||
import org.apache.solr.util.NamedList;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
class QuerySenderListener extends AbstractSolrEventListener {
|
||||
|
||||
public void newSearcher(SolrIndexSearcher newSearcher, SolrIndexSearcher currentSearcher) {
|
||||
SolrCore core = SolrCore.getSolrCore();
|
||||
log.info("QuerySenderListener sending requests to " + newSearcher);
|
||||
for (NamedList nlst : (List<NamedList>)args.get("queries")) {
|
||||
try {
|
||||
LocalSolrQueryRequest req = new LocalSolrQueryRequest(core, nlst);
|
||||
|
||||
SolrQueryResponse rsp = new SolrQueryResponse();
|
||||
core.execute(req,rsp);
|
||||
} catch (Exception e) {
|
||||
// do nothing... we want to continue with the other requests.
|
||||
// the failure should have already been logged.
|
||||
}
|
||||
log.info("QuerySenderListener done.");
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,91 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import org.apache.solr.util.DOMUtil;
|
||||
import org.apache.solr.request.SolrRequestHandler;
|
||||
import org.apache.solr.request.StandardRequestHandler;
|
||||
import org.w3c.dom.NodeList;
|
||||
import org.w3c.dom.Node;
|
||||
|
||||
import javax.xml.xpath.XPathConstants;
|
||||
import java.util.logging.Logger;
|
||||
import java.util.HashMap;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
*/
|
||||
final class RequestHandlers {
|
||||
public static Logger log = Logger.getLogger(org.apache.solr.core.RequestHandlers.class.getName());
|
||||
|
||||
public static final String DEFAULT_HANDLER_NAME="standard";
|
||||
|
||||
final HashMap<String, SolrRequestHandler> map = new HashMap<String,SolrRequestHandler>();
|
||||
|
||||
public RequestHandlers(Config config) {
|
||||
NodeList nodes = (NodeList)config.evaluate("requestHandler", XPathConstants.NODESET);
|
||||
|
||||
if (nodes!=null) {
|
||||
for (int i=0; i<nodes.getLength(); i++) {
|
||||
Node node = nodes.item(i);
|
||||
|
||||
// We can tolerate an error in some request handlers, still load the
|
||||
// others, and have a working system.
|
||||
try {
|
||||
String name = DOMUtil.getAttr(node,"name","requestHandler config");
|
||||
String className = DOMUtil.getAttr(node,"class","requestHandler config");
|
||||
log.info("adding requestHandler " + name + "=" + className);
|
||||
|
||||
SolrRequestHandler handler = (SolrRequestHandler) Config.newInstance(className);
|
||||
handler.init(DOMUtil.childNodesToNamedList(node));
|
||||
|
||||
put(name, handler);
|
||||
|
||||
} catch (Exception e) {
|
||||
SolrException.logOnce(log,null,e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
//
|
||||
// Get the default handler and add it in the map under null and empty
|
||||
// to act as the default.
|
||||
//
|
||||
SolrRequestHandler handler = get(DEFAULT_HANDLER_NAME);
|
||||
if (handler == null) {
|
||||
handler = new StandardRequestHandler();
|
||||
put(DEFAULT_HANDLER_NAME, handler);
|
||||
}
|
||||
put(null, handler);
|
||||
put("", handler);
|
||||
|
||||
}
|
||||
|
||||
public SolrRequestHandler get(String handlerName) {
|
||||
return map.get(handlerName);
|
||||
}
|
||||
|
||||
public void put(String handlerName, SolrRequestHandler handler) {
|
||||
map.put(handlerName, handler);
|
||||
if (handlerName != null && handlerName != "") {
|
||||
if (handler instanceof SolrInfoMBean) {
|
||||
SolrInfoRegistry.getRegistry().put(handlerName, (SolrInfoMBean)handler);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,103 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import org.apache.solr.util.NamedList;
|
||||
import org.apache.solr.search.SolrIndexSearcher;
|
||||
|
||||
import java.io.File;
|
||||
import java.io.IOException;
|
||||
import java.util.List;
|
||||
import java.util.ArrayList;
|
||||
import java.util.logging.Level;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
*/
|
||||
class RunExecutableListener extends AbstractSolrEventListener {
|
||||
protected String[] cmd;
|
||||
protected File dir;
|
||||
protected String[] envp;
|
||||
protected boolean wait=true;
|
||||
|
||||
public void init(NamedList args) {
|
||||
super.init(args);
|
||||
|
||||
List cmdlist = new ArrayList();
|
||||
cmdlist.add(args.get("exe"));
|
||||
List lst = (List)args.get("args");
|
||||
if (lst != null) cmdlist.addAll(lst);
|
||||
cmd = (String[])cmdlist.toArray(new String[cmdlist.size()]);
|
||||
|
||||
lst = (List)args.get("env");
|
||||
if (lst != null) {
|
||||
envp = (String[])lst.toArray(new String[lst.size()]);
|
||||
}
|
||||
|
||||
String str = (String)args.get("dir");
|
||||
if (str==null || str.equals("") || str.equals(".") || str.equals("./")) {
|
||||
dir = null;
|
||||
} else {
|
||||
dir = new File(str);
|
||||
}
|
||||
|
||||
if ("false".equals(args.get("wait"))) wait=false;
|
||||
}
|
||||
|
||||
protected int exec(String callback) {
|
||||
int ret = 0;
|
||||
|
||||
try {
|
||||
boolean doLog = log.isLoggable(Level.FINE);
|
||||
if (doLog) {
|
||||
log.fine("About to exec " + cmd[0]);
|
||||
}
|
||||
Process proc = Runtime.getRuntime().exec(cmd, envp ,dir);
|
||||
|
||||
if (wait) {
|
||||
try {
|
||||
ret = proc.waitFor();
|
||||
} catch (InterruptedException e) {
|
||||
SolrException.log(log,e);
|
||||
}
|
||||
}
|
||||
|
||||
if (wait && doLog) {
|
||||
log.fine("Executable " + cmd[0] + " returned " + ret);
|
||||
}
|
||||
|
||||
} catch (IOException e) {
|
||||
// don't throw exception, just log it...
|
||||
SolrException.log(log,e);
|
||||
}
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
||||
public void postCommit() {
|
||||
// anything generic need to be passed to the external program?
|
||||
// the directory of the index? the command that caused it to be
|
||||
// invoked? the version of the index?
|
||||
exec("postCommit");
|
||||
}
|
||||
|
||||
public void newSearcher(SolrIndexSearcher newSearcher, SolrIndexSearcher currentSearcher) {
|
||||
exec("newSearcher");
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import java.io.InputStream;
|
||||
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: SolrConfig.java,v 1.3 2005/12/02 04:31:06 yonik Exp $
|
||||
*/
|
||||
public class SolrConfig {
|
||||
public static Config config;
|
||||
static {
|
||||
Exception e=null;
|
||||
String file="solrconfig.xml";
|
||||
InputStream is;
|
||||
try {
|
||||
is = Config.openResource(file);
|
||||
} catch (Exception ee) {
|
||||
e=ee;
|
||||
file = "solarconfig.xml"; // backward compat
|
||||
is = Config.openResource(file);
|
||||
}
|
||||
if (is!=null) {
|
||||
try {
|
||||
config=new Config(file, is, "/config/");
|
||||
is.close();
|
||||
} catch (Exception ee) {
|
||||
throw new RuntimeException(ee);
|
||||
}
|
||||
Config.log.info("Loaded Config solarconfig.xml");
|
||||
} else {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,970 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import org.apache.lucene.index.IndexReader;
|
||||
import org.apache.lucene.search.BooleanQuery;
|
||||
import org.apache.lucene.store.Directory;
|
||||
import org.apache.lucene.store.FSDirectory;
|
||||
import org.apache.solr.request.SolrRequestHandler;
|
||||
import org.apache.solr.request.SolrQueryRequest;
|
||||
import org.apache.solr.request.SolrQueryResponse;
|
||||
import org.apache.solr.schema.IndexSchema;
|
||||
import org.apache.solr.search.SolrIndexSearcher;
|
||||
import org.apache.solr.update.*;
|
||||
import org.apache.solr.util.DOMUtil;
|
||||
import org.apache.solr.util.RefCounted;
|
||||
import org.apache.solr.util.StrUtils;
|
||||
import org.apache.solr.util.XML;
|
||||
import org.w3c.dom.Node;
|
||||
import org.w3c.dom.NodeList;
|
||||
import org.xmlpull.v1.XmlPullParser;
|
||||
import org.xmlpull.v1.XmlPullParserException;
|
||||
import org.xmlpull.v1.XmlPullParserFactory;
|
||||
|
||||
import javax.xml.xpath.XPathConstants;
|
||||
import java.io.File;
|
||||
import java.io.IOException;
|
||||
import java.io.Reader;
|
||||
import java.io.Writer;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
import java.util.concurrent.Callable;
|
||||
import java.util.concurrent.ExecutorService;
|
||||
import java.util.concurrent.Executors;
|
||||
import java.util.concurrent.Future;
|
||||
import java.util.logging.Logger;
|
||||
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: SolrCore.java,v 1.47 2006/01/10 05:04:44 yonik Exp $
|
||||
*/
|
||||
|
||||
public final class SolrCore {
|
||||
public static final String cvsId="$Id: SolrCore.java,v 1.47 2006/01/10 05:04:44 yonik Exp $";
|
||||
public static final String cvsSource="$Source: /cvs/main/searching/solr/solarcore/src/solr/SolrCore.java,v $";
|
||||
public static final String cvsTag="$Name: $";
|
||||
public static final String version="1.0";
|
||||
|
||||
public static Logger log = Logger.getLogger(SolrCore.class.getName());
|
||||
|
||||
private final IndexSchema schema;
|
||||
private final String index_path;
|
||||
private final UpdateHandler updateHandler;
|
||||
|
||||
public static SolrIndexConfig mainIndexConfig = new SolrIndexConfig("mainIndex");
|
||||
|
||||
static {
|
||||
BooleanQuery.setMaxClauseCount(SolrConfig.config.getInt("query/maxBooleanClauses",BooleanQuery.getMaxClauseCount()));
|
||||
}
|
||||
|
||||
|
||||
public static List<SolrEventListener> parseListener(String path) {
|
||||
List<SolrEventListener> lst = new ArrayList<SolrEventListener>();
|
||||
log.info("Searching for listeners: " +path);
|
||||
NodeList nodes = (NodeList)SolrConfig.config.evaluate(path, XPathConstants.NODESET);
|
||||
if (nodes!=null) {
|
||||
for (int i=0; i<nodes.getLength(); i++) {
|
||||
Node node = nodes.item(i);
|
||||
String className = DOMUtil.getAttr(node,"class");
|
||||
SolrEventListener listener = (SolrEventListener)Config.newInstance(className);
|
||||
listener.init(DOMUtil.childNodesToNamedList(node));
|
||||
lst.add(listener);
|
||||
log.info("added SolrEventListener: " + listener);
|
||||
}
|
||||
}
|
||||
return lst;
|
||||
}
|
||||
|
||||
List<SolrEventListener> firstSearcherListeners;
|
||||
List<SolrEventListener> newSearcherListeners;
|
||||
private void parseListeners() {
|
||||
firstSearcherListeners = parseListener("//listener[@event=\"firstSearcher\"]");
|
||||
newSearcherListeners = parseListener("//listener[@event=\"newSearcher\"]");
|
||||
}
|
||||
|
||||
|
||||
public IndexSchema getSchema() { return schema; }
|
||||
public String getDir() { return index_path; }
|
||||
|
||||
|
||||
private final RequestHandlers reqHandlers = new RequestHandlers(SolrConfig.config);
|
||||
|
||||
public SolrRequestHandler getRequestHandler(String handlerName) {
|
||||
return reqHandlers.get(handlerName);
|
||||
}
|
||||
|
||||
|
||||
// TODO - what about a master that not might have a searcher normally open?
|
||||
@Deprecated
|
||||
public int maxDoc() {
|
||||
RefCounted<SolrIndexSearcher> holder=null;
|
||||
int num=0;
|
||||
try {
|
||||
holder = getSearcher();
|
||||
SolrIndexSearcher searcher = holder.get();
|
||||
num = searcher.maxDoc();
|
||||
} catch (IOException e) {
|
||||
log(e);
|
||||
} finally {
|
||||
if (holder != null) holder.decref();
|
||||
}
|
||||
return num;
|
||||
}
|
||||
|
||||
|
||||
// gets a non-caching searcher
|
||||
public SolrIndexSearcher newSearcher(String name) throws IOException {
|
||||
return new SolrIndexSearcher(schema, name,getDir(),false);
|
||||
}
|
||||
|
||||
|
||||
void initIndex() {
|
||||
try {
|
||||
File dirFile = new File(getDir());
|
||||
boolean indexExists = dirFile.canRead();
|
||||
|
||||
|
||||
boolean removeLocks = SolrConfig.config.getBool("mainIndex/unlockOnStartup", false);
|
||||
if (removeLocks) {
|
||||
// to remove locks, the directory must already exist... so we create it
|
||||
// if it didn't exist already...
|
||||
Directory dir = FSDirectory.getDirectory(dirFile, !indexExists);
|
||||
if (IndexReader.isLocked(dir)) {
|
||||
log.warning("WARNING: Solr index directory '" + getDir() + "' is locked. Unlocking...");
|
||||
IndexReader.unlock(dir);
|
||||
}
|
||||
}
|
||||
|
||||
// Create the index if it doesn't exist. Note that indexExists was tested *before*
|
||||
// lock removal, since that will result in the creation of the directory.
|
||||
if(!indexExists) {
|
||||
log.warning("Solr index directory '" + dirFile + "' doesn't exist."
|
||||
+ " Creating new index...");
|
||||
|
||||
SolrIndexWriter writer = new SolrIndexWriter("SolrCore.initIndex",getDir(), true, schema, mainIndexConfig);
|
||||
writer.close();
|
||||
|
||||
}
|
||||
|
||||
} catch (IOException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
private UpdateHandler createUpdateHandler(String className) {
|
||||
try {
|
||||
Class handlerClass = Config.findClass(className);
|
||||
java.lang.reflect.Constructor cons = handlerClass.getConstructor(new Class[]{SolrCore.class});
|
||||
return (UpdateHandler)cons.newInstance(new Object[]{this});
|
||||
} catch (SolrException e) {
|
||||
throw e;
|
||||
} catch (Exception e) {
|
||||
throw new SolrException(500,"Error Instantiating Update Handler "+className, e);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// Singleton for now...
|
||||
private static SolrCore core;
|
||||
|
||||
public static SolrCore getSolrCore() {
|
||||
synchronized (SolrCore.class) {
|
||||
if (core==null) core = new SolrCore(null,null);
|
||||
return core;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public SolrCore(String index_path, IndexSchema schema) {
|
||||
synchronized (SolrCore.class) {
|
||||
// this is for backward compatibility (and also the reason
|
||||
// the sync block is needed)
|
||||
core = this; // set singleton
|
||||
try {
|
||||
if (index_path==null) {
|
||||
index_path=SolrConfig.config.get("indexDir","index");
|
||||
}
|
||||
|
||||
log.info("Opening new SolrCore at " + index_path);
|
||||
|
||||
if (schema==null) {
|
||||
schema = new IndexSchema("schema.xml");
|
||||
}
|
||||
|
||||
this.schema = schema;
|
||||
this.index_path = index_path;
|
||||
|
||||
parseListeners();
|
||||
|
||||
initIndex();
|
||||
|
||||
try {
|
||||
// Open the searcher *before* the handler so we don't end up opening
|
||||
// one in the middle.
|
||||
getSearcher(false,false,null);
|
||||
|
||||
updateHandler = createUpdateHandler(
|
||||
SolrConfig.config.get("updateHandler/@class", DirectUpdateHandler.class.getName())
|
||||
);
|
||||
|
||||
} catch (IOException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
} finally {
|
||||
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public void close() {
|
||||
log.info("CLOSING SolrCore!");
|
||||
try {
|
||||
closeSearcher();
|
||||
} catch (Exception e) {
|
||||
SolrException.log(log,e);
|
||||
}
|
||||
try {
|
||||
searcherExecutor.shutdown();
|
||||
} catch (Exception e) {
|
||||
SolrException.log(log,e);
|
||||
}
|
||||
try {
|
||||
updateHandler.close();
|
||||
} catch (Exception e) {
|
||||
SolrException.log(log,e);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
void finalizer() { close(); }
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
// Searcher Control
|
||||
////////////////////////////////////////////////////////////////////////////////
|
||||
|
||||
// The current searcher used to service queries.
|
||||
// Don't access this directly!!!! use getSearcher() to
|
||||
// get it (and it will increment the ref count at the same time)
|
||||
private RefCounted<SolrIndexSearcher> _searcher;
|
||||
|
||||
final ExecutorService searcherExecutor = Executors.newSingleThreadExecutor();
|
||||
private int onDeckSearchers; // number of searchers preparing
|
||||
private Object searcherLock = new Object(); // the sync object for the searcher
|
||||
|
||||
|
||||
public RefCounted<SolrIndexSearcher> getSearcher() {
|
||||
try {
|
||||
return getSearcher(false,true,null);
|
||||
} catch (IOException e) {
|
||||
SolrException.log(log,null,e);
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Get a {@link SolrIndexSearcher} or start the process of creating a new one.
|
||||
* <p>
|
||||
* The registered searcher is the default searcher used to service queries.
|
||||
* A searcher will normally be registered after all of the warming
|
||||
* and event handlers (newSearcher or firstSearcher events) have run.
|
||||
* In the case where there is no registered searcher, the newly created searcher will
|
||||
* be registered before running the event handlers (a slow searcher is better than no searcher).
|
||||
*
|
||||
* <p>
|
||||
* If <tt>forceNew==true</tt> then
|
||||
* A new searcher will be opened and registered irregardless if there is already
|
||||
* a registered searcher or other searchers in the process of being created.
|
||||
* <p>
|
||||
* If <tt>forceNew==false</tt> then:<ul>
|
||||
* <li>If a searcher is already registered, that searcher will be returned</li>
|
||||
* <li>If no searcher is currently registered, but at least one is in the process of being created, then
|
||||
* this call will block until the first searcher is registered</li>
|
||||
* <li>If no searcher is currently registered, and no searchers in the process of being registered, a new
|
||||
* searcher will be created.</li>
|
||||
* </ul>
|
||||
* <p>
|
||||
* If <tt>returnSearcher==true</tt> then a {@link RefCounted}<{@link SolrIndexSearcher}> will be returned with
|
||||
* the reference count incremented. It <b>must</b> be decremented when no longer needed.
|
||||
* <p>
|
||||
* If <tt>waitSearcher!=null</tt> and a new {@link SolrIndexSearcher} was created,
|
||||
* then it is filled in with a Future that will return after the searcher is registered. The Future may be set to
|
||||
* <tt>null</tt> in which case the SolrIndexSearcher created has already been registered at the time
|
||||
* this method returned.
|
||||
* <p>
|
||||
* @param forceNew if true, force the open of a new index searcher regardless if there is already one open.
|
||||
* @param returnSearcher if true, returns a {@link <SolrIndexSearcher>} holder with the refcount already incremented.
|
||||
* @param waitSearcher if non-null, will be filled in with a {@link Future} that will return after the new searcher is registered.
|
||||
* @return
|
||||
* @throws IOException
|
||||
*/
|
||||
public RefCounted<SolrIndexSearcher> getSearcher(boolean forceNew, boolean returnSearcher, final Future[] waitSearcher) throws IOException {
|
||||
// it may take some time to open an index.... we may need to make
|
||||
// sure that two threads aren't trying to open one at the same time
|
||||
// if it isn't necessary.
|
||||
|
||||
synchronized (searcherLock) {
|
||||
// see if we can return the current searcher
|
||||
if (_searcher!=null && !forceNew) {
|
||||
if (returnSearcher) {
|
||||
_searcher.incref();
|
||||
return _searcher;
|
||||
} else {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
// check to see if we can wait for someone elses searcher to be set
|
||||
if (onDeckSearchers>0 && !forceNew && _searcher==null) {
|
||||
try {
|
||||
searcherLock.wait();
|
||||
} catch (InterruptedException e) {
|
||||
log.info(SolrException.toStr(e));
|
||||
}
|
||||
}
|
||||
|
||||
// check again: see if we can return right now
|
||||
if (_searcher!=null && !forceNew) {
|
||||
if (returnSearcher) {
|
||||
_searcher.incref();
|
||||
return _searcher;
|
||||
} else {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
// At this point, we know we need to open a new searcher...
|
||||
// first: increment count to signal other threads that we are
|
||||
// opening a new searcher.
|
||||
onDeckSearchers++;
|
||||
}
|
||||
|
||||
// open the index synchronously
|
||||
// if this fails, we need to decrement onDeckSearchers again.
|
||||
SolrIndexSearcher tmp;
|
||||
try {
|
||||
if (onDeckSearchers < 1) {
|
||||
// should never happen... just a sanity check
|
||||
log.severe("ERROR!!! onDeckSearchers is " + onDeckSearchers);
|
||||
// reset to 1 (don't bother synchronizing)
|
||||
onDeckSearchers=1;
|
||||
} else if (onDeckSearchers > 1) {
|
||||
log.info("PERFORMANCE WARNING: Overlapping onDeckSearchers=" + onDeckSearchers);
|
||||
}
|
||||
tmp = new SolrIndexSearcher(schema, "main", index_path, true);
|
||||
} catch (Throwable th) {
|
||||
synchronized(searcherLock) {
|
||||
onDeckSearchers--;
|
||||
// notify another waiter to continue... it may succeed
|
||||
// and wake any others.
|
||||
searcherLock.notify();
|
||||
}
|
||||
// need to close the searcher here??? we shouldn't have to.
|
||||
throw new RuntimeException(th);
|
||||
}
|
||||
|
||||
final SolrIndexSearcher newSearcher=tmp;
|
||||
|
||||
RefCounted<SolrIndexSearcher> currSearcherHolder=null;
|
||||
final RefCounted<SolrIndexSearcher> newSearchHolder=newHolder(newSearcher);
|
||||
if (returnSearcher) newSearchHolder.incref();
|
||||
|
||||
// a signal to decrement onDeckSearchers if something goes wrong.
|
||||
final boolean[] decrementOnDeckCount=new boolean[1];
|
||||
decrementOnDeckCount[0]=true;
|
||||
|
||||
try {
|
||||
|
||||
synchronized (searcherLock) {
|
||||
if (_searcher == null) {
|
||||
// if there isn't a current searcher then register this one
|
||||
// before warming is complete instead of waiting.
|
||||
registerSearcher(newSearchHolder);
|
||||
decrementOnDeckCount[0]=false;
|
||||
} else {
|
||||
// get a reference to the current searcher for purposes of autowarming.
|
||||
currSearcherHolder=_searcher;
|
||||
currSearcherHolder.incref();
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
final SolrIndexSearcher currSearcher = currSearcherHolder==null ? null : currSearcherHolder.get();
|
||||
|
||||
//
|
||||
// Note! if we registered the new searcher (but didn't increment it's
|
||||
// reference count because returnSearcher==false, it's possible for
|
||||
// someone else to register another searcher, and thus cause newSearcher
|
||||
// to close while we are warming.
|
||||
//
|
||||
// Should we protect against that by incrementing the reference count?
|
||||
// Maybe we should just let it fail? After all, if returnSearcher==false
|
||||
// and newSearcher has been de-registered, what's the point of continuing?
|
||||
//
|
||||
|
||||
Future future=null;
|
||||
|
||||
// warm the new searcher based on the current searcher.
|
||||
// should this go before the other event handlers or after?
|
||||
if (currSearcher != null) {
|
||||
future = searcherExecutor.submit(
|
||||
new Callable() {
|
||||
public Object call() throws Exception {
|
||||
try {
|
||||
newSearcher.warm(currSearcher);
|
||||
} catch (Throwable e) {
|
||||
SolrException.logOnce(log,null,e);
|
||||
}
|
||||
return null;
|
||||
}
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
if (currSearcher==null && firstSearcherListeners.size() > 0) {
|
||||
future = searcherExecutor.submit(
|
||||
new Callable() {
|
||||
public Object call() throws Exception {
|
||||
try {
|
||||
for (SolrEventListener listener : firstSearcherListeners) {
|
||||
listener.newSearcher(newSearcher,null);
|
||||
}
|
||||
} catch (Throwable e) {
|
||||
SolrException.logOnce(log,null,e);
|
||||
}
|
||||
return null;
|
||||
}
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
if (currSearcher!=null && newSearcherListeners.size() > 0) {
|
||||
future = searcherExecutor.submit(
|
||||
new Callable() {
|
||||
public Object call() throws Exception {
|
||||
try {
|
||||
for (SolrEventListener listener : newSearcherListeners) {
|
||||
listener.newSearcher(newSearcher,null);
|
||||
}
|
||||
} catch (Throwable e) {
|
||||
SolrException.logOnce(log,null,e);
|
||||
}
|
||||
return null;
|
||||
}
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
// WARNING: this code assumes a single threaded executor (that all tasks
|
||||
// queued will finish first).
|
||||
final RefCounted<SolrIndexSearcher> currSearcherHolderF = currSearcherHolder;
|
||||
Future finalFuture=null;
|
||||
if (currSearcherHolder != null) {
|
||||
finalFuture = searcherExecutor.submit(
|
||||
new Callable() {
|
||||
public Object call() throws Exception {
|
||||
try {
|
||||
// signal that we no longer need to decrement
|
||||
// the count *before* registering the searcher since
|
||||
// registertSearcher will decrement even if it errors.
|
||||
decrementOnDeckCount[0]=false;
|
||||
registerSearcher(newSearchHolder);
|
||||
} catch (Throwable e) {
|
||||
SolrException.logOnce(log,null,e);
|
||||
} finally {
|
||||
// we are all done with the old searcher we used
|
||||
// for warming...
|
||||
currSearcherHolderF.decref();
|
||||
}
|
||||
return null;
|
||||
}
|
||||
}
|
||||
);
|
||||
}
|
||||
|
||||
if (waitSearcher != null) {
|
||||
waitSearcher[0] = finalFuture;
|
||||
}
|
||||
|
||||
// Return the searcher as the warming tasks run in parallel
|
||||
// callers may wait on the waitSearcher future returned.
|
||||
return returnSearcher ? newSearchHolder : null;
|
||||
|
||||
}
|
||||
catch (Exception e) {
|
||||
SolrException.logOnce(log,null,e);
|
||||
if (currSearcherHolder != null) currSearcherHolder.decref();
|
||||
|
||||
synchronized (searcherLock) {
|
||||
if (decrementOnDeckCount[0]) {
|
||||
onDeckSearchers--;
|
||||
}
|
||||
if (onDeckSearchers < 0) {
|
||||
// sanity check... should never happen
|
||||
log.severe("ERROR!!! onDeckSearchers after decrement=" + onDeckSearchers);
|
||||
onDeckSearchers=0; // try and recover
|
||||
}
|
||||
// if we failed, we need to wake up at least one waiter to continue the process
|
||||
searcherLock.notify();
|
||||
}
|
||||
|
||||
// since the indexreader was already opened, assume we can continue on
|
||||
// even though we got an exception.
|
||||
return returnSearcher ? newSearchHolder : null;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
private RefCounted<SolrIndexSearcher> newHolder(SolrIndexSearcher newSearcher) {
|
||||
RefCounted<SolrIndexSearcher> holder = new RefCounted<SolrIndexSearcher>(newSearcher)
|
||||
{
|
||||
public void close() {
|
||||
try {
|
||||
resource.close();
|
||||
} catch (IOException e) {
|
||||
log.severe("Error closing searcher:" + SolrException.toStr(e));
|
||||
}
|
||||
}
|
||||
};
|
||||
holder.incref(); // set ref count to 1 to account for this._searcher
|
||||
return holder;
|
||||
}
|
||||
|
||||
|
||||
// Take control of newSearcherHolder (which should have a reference count of at
|
||||
// least 1 already. If the caller wishes to use the newSearcherHolder directly
|
||||
// after registering it, then they should increment the reference count *before*
|
||||
// calling this method.
|
||||
//
|
||||
// onDeckSearchers will also be decremented (it should have been incremented
|
||||
// as a result of opening a new searcher).
|
||||
private void registerSearcher(RefCounted<SolrIndexSearcher> newSearcherHolder) throws IOException {
|
||||
synchronized (searcherLock) {
|
||||
try {
|
||||
if (_searcher != null) {
|
||||
_searcher.decref(); // dec refcount for this._searcher
|
||||
_searcher=null;
|
||||
}
|
||||
|
||||
_searcher = newSearcherHolder;
|
||||
SolrIndexSearcher newSearcher = newSearcherHolder.get();
|
||||
|
||||
SolrInfoRegistry.getRegistry().put("currentSearcher", newSearcher);
|
||||
newSearcher.register(); // register subitems (caches)
|
||||
log.info("Registered new searcher " + newSearcher);
|
||||
|
||||
} catch (Throwable e) {
|
||||
log(e);
|
||||
} finally {
|
||||
// wake up anyone waiting for a searcher
|
||||
// even in the face of errors.
|
||||
onDeckSearchers--;
|
||||
searcherLock.notifyAll();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
public void closeSearcher() {
|
||||
log.info("Closing main searcher on request.");
|
||||
synchronized (searcherLock) {
|
||||
if (_searcher != null) {
|
||||
_searcher.decref(); // dec refcount for this._searcher
|
||||
_searcher=null;
|
||||
SolrInfoRegistry.getRegistry().remove("currentSearcher");
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
public void execute(SolrQueryRequest req, SolrQueryResponse rsp) {
|
||||
SolrRequestHandler handler = getRequestHandler(req.getQueryType());
|
||||
if (handler==null) {
|
||||
log.warning("Unknown Request Handler '" + req.getQueryType() +"' :" + req);
|
||||
throw new SolrException(400,"Unknown Request Handler '" + req.getQueryType() + "'", true);
|
||||
}
|
||||
handler.handleRequest(req,rsp);
|
||||
log.info(req.getParamString()+ " 0 "+
|
||||
(int)(rsp.getEndTime() - req.getStartTime()));
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
XmlPullParserFactory factory;
|
||||
{
|
||||
try {
|
||||
factory = XmlPullParserFactory.newInstance();
|
||||
} catch (XmlPullParserException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
factory.setNamespaceAware(false);
|
||||
}
|
||||
|
||||
|
||||
private int findNextTag(XmlPullParser xpp, String tag) throws XmlPullParserException, IOException {
|
||||
int eventType;
|
||||
while((eventType=xpp.next()) != XmlPullParser.END_DOCUMENT) {
|
||||
if(eventType == XmlPullParser.START_TAG) {
|
||||
if (tag.equals(xpp.getName())) break;
|
||||
}
|
||||
}
|
||||
return eventType;
|
||||
}
|
||||
|
||||
|
||||
public void update(Reader reader, Writer writer) {
|
||||
|
||||
// TODO: add param to specify maximum time to commit?
|
||||
|
||||
// todo - might be nice to separate command parsing w/ a factory
|
||||
// then new commands could be added w/o risk to old ones
|
||||
|
||||
|
||||
XmlPullParser xpp = null;
|
||||
try {
|
||||
xpp = factory.newPullParser();
|
||||
} catch (XmlPullParserException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
|
||||
long startTime=System.currentTimeMillis();
|
||||
|
||||
try {
|
||||
xpp.setInput(reader);
|
||||
xpp.nextTag();
|
||||
|
||||
String currTag = xpp.getName();
|
||||
if ("add".equals(currTag)) {
|
||||
log.finest("SolrCore.update(add)");
|
||||
AddUpdateCommand cmd = new AddUpdateCommand();
|
||||
cmd.allowDups=false; // the default
|
||||
|
||||
int status=0;
|
||||
boolean pendingAttr=false, committedAttr=false;
|
||||
int attrcount = xpp.getAttributeCount();
|
||||
for (int i=0; i<attrcount; i++) {
|
||||
String attrName = xpp.getAttributeName(i);
|
||||
String attrVal = xpp.getAttributeValue(i);
|
||||
if ("allowDups".equals(attrName)) {
|
||||
cmd.allowDups = StrUtils.parseBoolean(attrVal);
|
||||
} else if ("overwritePending".equals(attrName)) {
|
||||
cmd.overwritePending = StrUtils.parseBoolean(attrVal);
|
||||
pendingAttr=true;
|
||||
} else if ("overwriteCommitted".equals(attrName)) {
|
||||
cmd.overwriteCommitted = StrUtils.parseBoolean(attrVal);
|
||||
committedAttr=true;
|
||||
} else {
|
||||
log.warning("Unknown attribute id in add:" + attrName);
|
||||
}
|
||||
}
|
||||
|
||||
//set defaults for committed and pending based on allowDups value
|
||||
if (!pendingAttr) cmd.overwritePending=!cmd.allowDups;
|
||||
if (!committedAttr) cmd.overwriteCommitted=!cmd.allowDups;
|
||||
|
||||
DocumentBuilder builder = new DocumentBuilder(schema);
|
||||
int eventType=0;
|
||||
while(true) {
|
||||
// this may be our second time through the loop in the case
|
||||
// that there are multiple docs in the add... so make sure that
|
||||
// objects can handle that.
|
||||
|
||||
cmd.id = null; // reset the id for this add
|
||||
|
||||
if (eventType !=0) {
|
||||
eventType=xpp.getEventType();
|
||||
if (eventType==XmlPullParser.END_DOCUMENT) break;
|
||||
}
|
||||
// eventType = xpp.next();
|
||||
eventType = xpp.nextTag();
|
||||
if (eventType == XmlPullParser.END_TAG || eventType == XmlPullParser.END_DOCUMENT) break; // should match </add>
|
||||
|
||||
try {
|
||||
readDoc(builder,xpp);
|
||||
builder.endDoc();
|
||||
cmd.doc = builder.getDoc();
|
||||
log.finest("adding doc...");
|
||||
updateHandler.addDoc(cmd);
|
||||
log.info("add "+status+" "+(System.currentTimeMillis()-startTime));
|
||||
writer.write("<result status=\"" + status + "\"></result>");
|
||||
} catch (SolrException e) {
|
||||
log(e);
|
||||
log.info("add "+e.code+" "+(System.currentTimeMillis()-startTime));
|
||||
writeResult(writer,e);
|
||||
// we may not have finised reading the XML for this cmd,
|
||||
// so eat any unused input up till "</add>"
|
||||
eventType = xpp.getEventType();
|
||||
while (true) {
|
||||
if ( eventType == XmlPullParser.END_DOCUMENT
|
||||
|| (eventType == XmlPullParser.END_TAG && "add".equals(xpp.getName())))
|
||||
{
|
||||
break;
|
||||
}
|
||||
eventType = xpp.next();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/***
|
||||
while (findNextTag(xpp,"doc") != XmlPullParser.END_DOCUMENT) {
|
||||
readDoc(builder,xpp);
|
||||
Document doc = builder.endDoc();
|
||||
indexWriter.addDocument(doc);
|
||||
docsAdded++;
|
||||
}
|
||||
***/
|
||||
|
||||
} // end add
|
||||
|
||||
else if ("commit".equals(currTag) || "optimize".equals(currTag)) {
|
||||
log.finest("parsing "+currTag);
|
||||
try {
|
||||
CommitUpdateCommand cmd = new CommitUpdateCommand("optimize".equals(currTag));
|
||||
|
||||
boolean sawWaitSearcher=false, sawWaitFlush=false;
|
||||
int attrcount = xpp.getAttributeCount();
|
||||
for (int i=0; i<attrcount; i++) {
|
||||
String attrName = xpp.getAttributeName(i);
|
||||
String attrVal = xpp.getAttributeValue(i);
|
||||
if ("waitFlush".equals(attrName)) {
|
||||
cmd.waitFlush = StrUtils.parseBoolean(attrVal);
|
||||
sawWaitFlush=true;
|
||||
} else if ("waitSearcher".equals(attrName)) {
|
||||
cmd.waitSearcher = StrUtils.parseBoolean(attrVal);
|
||||
sawWaitSearcher=true;
|
||||
} else {
|
||||
log.warning("unexpected attribute commit/@" + attrName);
|
||||
}
|
||||
}
|
||||
|
||||
// If waitFlush is specified and waitSearcher wasn't, then
|
||||
// clear waitSearcher.
|
||||
if (sawWaitFlush && !sawWaitSearcher) {
|
||||
cmd.waitSearcher=false;
|
||||
}
|
||||
|
||||
updateHandler.commit(cmd);
|
||||
if ("optimize".equals(currTag)) {
|
||||
log.info("optimize 0 "+(System.currentTimeMillis()-startTime));
|
||||
}
|
||||
else {
|
||||
log.info("commit 0 "+(System.currentTimeMillis()-startTime));
|
||||
}
|
||||
while (true) {
|
||||
int eventType = xpp.nextTag();
|
||||
if (eventType == XmlPullParser.END_TAG) break; // match </commit>
|
||||
}
|
||||
writer.write("<result status=\"0\"></result>");
|
||||
} catch (SolrException e) {
|
||||
log(e);
|
||||
if ("optimize".equals(currTag)) {
|
||||
log.info("optimize "+e.code+" "+
|
||||
(System.currentTimeMillis()-startTime));
|
||||
}
|
||||
else {
|
||||
log.info("commit "+e.code+" "+
|
||||
(System.currentTimeMillis()-startTime));
|
||||
}
|
||||
writeResult(writer,e);
|
||||
} catch (Exception e) {
|
||||
SolrException.log(log, "Exception during commit/optimize",e);
|
||||
writeResult(writer,e);
|
||||
}
|
||||
} // end commit
|
||||
|
||||
else if ("delete".equals(currTag)) {
|
||||
log.finest("parsing delete");
|
||||
try {
|
||||
DeleteUpdateCommand cmd = new DeleteUpdateCommand();
|
||||
cmd.fromPending=true;
|
||||
cmd.fromCommitted=true;
|
||||
int attrcount = xpp.getAttributeCount();
|
||||
for (int i=0; i<attrcount; i++) {
|
||||
String attrName = xpp.getAttributeName(i);
|
||||
String attrVal = xpp.getAttributeValue(i);
|
||||
if ("fromPending".equals(attrName)) {
|
||||
cmd.fromPending = StrUtils.parseBoolean(attrVal);
|
||||
} else if ("fromCommitted".equals(attrName)) {
|
||||
cmd.fromCommitted = StrUtils.parseBoolean(attrVal);
|
||||
} else {
|
||||
log.warning("unexpected attribute delete/@" + attrName);
|
||||
}
|
||||
}
|
||||
|
||||
int eventType = xpp.nextTag();
|
||||
currTag = xpp.getName();
|
||||
String val = xpp.nextText();
|
||||
|
||||
if ("id".equals(currTag)) {
|
||||
cmd.id = val;
|
||||
updateHandler.delete(cmd);
|
||||
log.info("delete(id " + val + ") 0 " +
|
||||
(System.currentTimeMillis()-startTime));
|
||||
} else if ("query".equals(currTag)) {
|
||||
cmd.query = val;
|
||||
updateHandler.deleteByQuery(cmd);
|
||||
log.info("deleteByQuery(query " + val + ") 0 " +
|
||||
(System.currentTimeMillis()-startTime));
|
||||
} else {
|
||||
log.warning("unexpected XML tag /delete/"+currTag);
|
||||
throw new SolrException(400,"unexpected XML tag /delete/"+currTag);
|
||||
}
|
||||
|
||||
writer.write("<result status=\"0\"></result>");
|
||||
|
||||
while (xpp.nextTag() != XmlPullParser.END_TAG);
|
||||
|
||||
} catch (SolrException e) {
|
||||
log(e);
|
||||
log.info("delete "+e.code+" "+(System.currentTimeMillis()-startTime));
|
||||
writeResult(writer,e);
|
||||
} catch (Exception e) {
|
||||
log(e);
|
||||
writeResult(writer,e);
|
||||
}
|
||||
} // end delete
|
||||
|
||||
|
||||
} catch (XmlPullParserException e) {
|
||||
log(e);
|
||||
writeResult(writer,e);
|
||||
} catch (IOException e) {
|
||||
log(e);
|
||||
writeResult(writer,e);
|
||||
} catch (SolrException e) {
|
||||
log(e);
|
||||
log.info("update "+e.code+" "+(System.currentTimeMillis()-startTime));
|
||||
writeResult(writer,e);
|
||||
} catch (Throwable e) {
|
||||
log(e);
|
||||
writeResult(writer,e);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
private void readDoc(DocumentBuilder builder, XmlPullParser xpp) throws IOException, XmlPullParserException {
|
||||
// xpp should be at <doc> at this point
|
||||
|
||||
builder.startDoc();
|
||||
|
||||
int attrcount = xpp.getAttributeCount();
|
||||
float docBoost = 1.0f;
|
||||
|
||||
for (int i=0; i<attrcount; i++) {
|
||||
String attrName = xpp.getAttributeName(i);
|
||||
String attrVal = xpp.getAttributeValue(i);
|
||||
if ("boost".equals(attrName)) {
|
||||
docBoost = Float.parseFloat(attrVal);
|
||||
} else {
|
||||
log.warning("Unknown attribute doc/@" + attrName);
|
||||
}
|
||||
}
|
||||
if (docBoost != 1.0f) builder.setBoost(docBoost);
|
||||
|
||||
// while (findNextTag(xpp,"field") != XmlPullParser.END_DOCUMENT) {
|
||||
|
||||
while(true) {
|
||||
int eventType = xpp.nextTag();
|
||||
if (eventType == XmlPullParser.END_TAG) break; // </doc>
|
||||
|
||||
String tname=xpp.getName();
|
||||
// System.out.println("FIELD READER AT TAG " + tname);
|
||||
|
||||
if (!"field".equals(tname)) {
|
||||
log.warning("unexpected XML tag doc/"+tname);
|
||||
throw new SolrException(400,"unexpected XML tag doc/"+tname);
|
||||
}
|
||||
|
||||
//
|
||||
// get field name and parse field attributes
|
||||
//
|
||||
attrcount = xpp.getAttributeCount();
|
||||
String name=null;
|
||||
float boost=1.0f;
|
||||
boolean isNull=false;
|
||||
|
||||
for (int i=0; i<attrcount; i++) {
|
||||
String attrName = xpp.getAttributeName(i);
|
||||
String attrVal = xpp.getAttributeValue(i);
|
||||
if ("name".equals(attrName)) {
|
||||
name=attrVal;
|
||||
} else if ("boost".equals(attrName)) {
|
||||
boost=Float.parseFloat(attrVal);
|
||||
} else if ("null".equals(attrName)) {
|
||||
isNull=StrUtils.parseBoolean(attrVal);
|
||||
} else {
|
||||
log.warning("Unknown attribute doc/field/@" + attrName);
|
||||
}
|
||||
}
|
||||
|
||||
// now get the field value
|
||||
String val = xpp.nextText(); // todo... text event for <field></field>???
|
||||
// need this line for isNull???
|
||||
// Don't add fields marked as null (for now at least)
|
||||
if (!isNull) {
|
||||
if (docBoost != 1.0f) {
|
||||
builder.addField(name,val,docBoost);
|
||||
} else {
|
||||
builder.addField(name,val);
|
||||
}
|
||||
}
|
||||
|
||||
// do I have to do a nextTag here to read the end_tag?
|
||||
|
||||
} // end field loop
|
||||
|
||||
}
|
||||
|
||||
|
||||
final public static void log(Throwable e) {
|
||||
SolrException.logOnce(log,null,e);
|
||||
}
|
||||
|
||||
|
||||
final static void writeResult(Writer out, SolrException e) {
|
||||
try {
|
||||
XML.writeXML(out,"result",e.getMessage(),"status",e.code());
|
||||
} catch (Exception ee) {
|
||||
log.severe("Error writing to putput stream: "+ee);
|
||||
}
|
||||
}
|
||||
|
||||
final static void writeResult(Writer out, Throwable e) {
|
||||
try {
|
||||
XML.writeXML(out,"result",SolrException.toStr(e),"status","1");
|
||||
} catch (Exception ee) {
|
||||
log.severe("Error writing to putput stream: "+ee);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,37 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import org.apache.solr.util.NamedList;
|
||||
import org.apache.solr.search.SolrIndexSearcher;
|
||||
|
||||
import java.util.logging.Logger;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: SolrEventListener.java,v 1.4 2005/05/25 04:26:47 yonik Exp $
|
||||
*/
|
||||
public interface SolrEventListener {
|
||||
static final Logger log = Logger.getLogger(SolrCore.class.getName());
|
||||
|
||||
public void init(NamedList args);
|
||||
|
||||
public void postCommit();
|
||||
|
||||
public void newSearcher(SolrIndexSearcher newSearcher, SolrIndexSearcher currentSearcher);
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,108 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import java.util.logging.Logger;
|
||||
import java.io.CharArrayWriter;
|
||||
import java.io.PrintWriter;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: SolrException.java,v 1.6 2005/06/14 20:42:26 yonik Exp $
|
||||
*/
|
||||
|
||||
|
||||
public class SolrException extends RuntimeException {
|
||||
public boolean logged=false;
|
||||
|
||||
public SolrException(int code, String msg) {
|
||||
super(msg);
|
||||
this.code=code;
|
||||
}
|
||||
public SolrException(int code, String msg, boolean alreadyLogged) {
|
||||
super(msg);
|
||||
this.code=code;
|
||||
this.logged=alreadyLogged;
|
||||
}
|
||||
|
||||
public SolrException(int code, String msg, Throwable th, boolean alreadyLogged) {
|
||||
super(msg,th);
|
||||
this.code=code;
|
||||
logged=alreadyLogged;
|
||||
}
|
||||
|
||||
public SolrException(int code, String msg, Throwable th) {
|
||||
this(code,msg,th,true);
|
||||
}
|
||||
|
||||
public SolrException(int code, Throwable th) {
|
||||
super(th);
|
||||
this.code=code;
|
||||
logged=true;
|
||||
}
|
||||
|
||||
int code=0;
|
||||
public int code() { return code; }
|
||||
|
||||
|
||||
|
||||
|
||||
public void log(Logger log) { log(log,this); }
|
||||
public static void log(Logger log, Throwable e) {
|
||||
log.severe(toStr(e));
|
||||
if (e instanceof SolrException) {
|
||||
((SolrException)e).logged = true;
|
||||
}
|
||||
}
|
||||
|
||||
public static void log(Logger log, String msg, Throwable e) {
|
||||
log.severe(msg + ':' + toStr(e));
|
||||
if (e instanceof SolrException) {
|
||||
((SolrException)e).logged = true;
|
||||
}
|
||||
}
|
||||
|
||||
public static void logOnce(Logger log, String msg, Throwable e) {
|
||||
if (e instanceof SolrException) {
|
||||
if(((SolrException)e).logged) return;
|
||||
}
|
||||
if (msg!=null) log(log,msg,e);
|
||||
else log(log,e);
|
||||
}
|
||||
|
||||
|
||||
// public String toString() { return toStr(this); } // oops, inf loop
|
||||
public String toString() { return super.toString(); }
|
||||
|
||||
public static String toStr(Throwable e) {
|
||||
CharArrayWriter cw = new CharArrayWriter();
|
||||
PrintWriter pw = new PrintWriter(cw);
|
||||
e.printStackTrace(pw);
|
||||
pw.flush();
|
||||
return cw.toString();
|
||||
|
||||
/** This doesn't work for some reason!!!!!
|
||||
StringWriter sw = new StringWriter();
|
||||
PrintWriter pw = new PrintWriter(sw);
|
||||
e.printStackTrace(pw);
|
||||
pw.flush();
|
||||
System.out.println("The STRING:" + sw.toString());
|
||||
return sw.toString();
|
||||
**/
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,104 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import java.net.URL;
|
||||
import org.apache.solr.util.*;
|
||||
|
||||
/**
|
||||
* @author ronp
|
||||
* @version $Id: SolrInfo.java,v 1.3 2005/05/02 19:04:59 ronp Exp $
|
||||
*/
|
||||
|
||||
// MBean pattern for holding various ui friendly strings and URLs
|
||||
// for use by objects which are 'plugable' to make administering
|
||||
// production use easier
|
||||
// name - simple common usage name, e.g. BasicQueryHandler
|
||||
// version - simple common usage version, e.g. 2.0
|
||||
// description - simple one or two line description
|
||||
// cvsId - yes, really the CVS Id (type 'man co')
|
||||
// cvsName - yes, really the CVS Name (type 'man co')
|
||||
// cvsSource - yes, really the CVS Source (type 'man co')
|
||||
// docs - URL list: TWIKI, Faq, Design doc, something! :)
|
||||
|
||||
abstract class SolrInfo implements SolrInfoMBean {
|
||||
public static String _cvsId="$Id: SolrInfo.java,v 1.3 2005/05/02 19:04:59 ronp Exp $";
|
||||
public static String _cvsSource="$Source: /cvs/main/searching/solr/solarcore/src/solr/SolrInfo.java,v $";
|
||||
public static String _cvsName="$Name: $";
|
||||
|
||||
|
||||
public String getName() { return this.name; }
|
||||
public String getVersion() { return this.version; }
|
||||
public String getDescription() { return this.description; }
|
||||
public Category getCategory() { return SolrInfoMBean.Category.QUERYHANDLER; }
|
||||
public String getCvsId() { return this.cvsId; }
|
||||
public String getCvsName() { return this.cvsName; }
|
||||
public String getCvsSource() { return this.cvsSource; }
|
||||
public URL[] getDocs() { return this.docs; }
|
||||
public NamedList getStatistics() { return null; }
|
||||
|
||||
|
||||
public void setName(String name ) { this.name = name; }
|
||||
public void setVersion(String vers) { this.version = vers; }
|
||||
public void setDescription(String desc) { this.description = desc; }
|
||||
public void setCvsId(String cvsId) { this.cvsId = cvsId; }
|
||||
public void setCvsName(String cvsName) { this.cvsName = cvsName; }
|
||||
public void setCvsSource(String cvsSource) { this.cvsSource = cvsSource; }
|
||||
public void setDocs(URL[] docs) { this.docs = docs; }
|
||||
|
||||
public void addDoc(URL doc)
|
||||
{
|
||||
if (doc == null) {
|
||||
// should throw runtime exception
|
||||
return;
|
||||
}
|
||||
if (docs != null) {
|
||||
URL[] newDocs = new URL[docs.length+1];
|
||||
int i;
|
||||
for (i = 0; i < docs.length; i++) {
|
||||
newDocs[i] = docs[i];
|
||||
}
|
||||
newDocs[i] = doc;
|
||||
docs = newDocs;
|
||||
} else {
|
||||
docs = new URL[1];
|
||||
docs[0] = doc;
|
||||
}
|
||||
}
|
||||
|
||||
public void addDoc(String doc)
|
||||
{
|
||||
if (doc == null) {
|
||||
// should throw runtime exception
|
||||
return;
|
||||
}
|
||||
try {
|
||||
URL docURL = new URL(doc);
|
||||
addDoc(docURL);
|
||||
} catch (Exception e) {
|
||||
// ignore for now
|
||||
}
|
||||
}
|
||||
|
||||
private String name;
|
||||
private String version;
|
||||
private String description;
|
||||
public String cvsId;
|
||||
public String cvsSource;
|
||||
public String cvsName;
|
||||
private URL[] docs;
|
||||
}
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import java.net.URL;
|
||||
import org.apache.solr.util.*;
|
||||
|
||||
/**
|
||||
* @author ronp
|
||||
* @version $Id: SolrInfoMBean.java,v 1.3 2005/05/04 19:15:23 ronp Exp $
|
||||
*/
|
||||
|
||||
// MBean interface for getting various ui friendly strings and URLs
|
||||
// for use by objects which are 'plugable' to make administering
|
||||
// production use easier
|
||||
// name - simple common usage name, e.g. BasicQueryHandler
|
||||
// version - simple common usage version, e.g. 2.0
|
||||
// description - simple one or two line description
|
||||
// cvsId - yes, really the CVS Id (type 'man co')
|
||||
// cvsName - yes, really the CVS Name (type 'man co')
|
||||
// cvsSource - yes, really the CVS Source (type 'man co')
|
||||
// docs - URL list: TWIKI, Faq, Design doc, something! :)
|
||||
|
||||
public interface SolrInfoMBean {
|
||||
|
||||
public enum Category { CORE, QUERYHANDLER, UPDATEHANDLER, CACHE, OTHER };
|
||||
|
||||
public String getName();
|
||||
public String getVersion();
|
||||
public String getDescription();
|
||||
public Category getCategory();
|
||||
public String getCvsId();
|
||||
public String getCvsName();
|
||||
public String getCvsSource();
|
||||
public URL[] getDocs();
|
||||
public NamedList getStatistics();
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.core;
|
||||
|
||||
import org.apache.solr.core.SolrInfoMBean;
|
||||
|
||||
import java.util.*;
|
||||
|
||||
/**
|
||||
* @author ronp
|
||||
* @version $Id: SolrInfoRegistry.java,v 1.5 2005/05/14 03:34:39 yonik Exp $
|
||||
*/
|
||||
|
||||
// A Registry to hold a collection of SolrInfo objects
|
||||
|
||||
public class SolrInfoRegistry {
|
||||
public static final String cvsId="$Id: SolrInfoRegistry.java,v 1.5 2005/05/14 03:34:39 yonik Exp $";
|
||||
public static final String cvsSource="$Source: /cvs/main/searching/solr/solarcore/src/solr/SolrInfoRegistry.java,v $";
|
||||
public static final String cvsName="$Name: $";
|
||||
|
||||
private static final Map<String,SolrInfoMBean> inst = Collections.synchronizedMap(new LinkedHashMap<String,SolrInfoMBean>());
|
||||
|
||||
public static Map<String, SolrInfoMBean> getRegistry()
|
||||
{
|
||||
return inst;
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,198 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.request;
|
||||
|
||||
import org.apache.solr.search.SolrIndexSearcher;
|
||||
import org.apache.solr.util.RefCounted;
|
||||
import org.apache.solr.util.StrUtils;
|
||||
import org.apache.solr.util.NamedList;
|
||||
import org.apache.solr.schema.IndexSchema;
|
||||
import org.apache.solr.core.SolrCore;
|
||||
|
||||
import java.util.Map;
|
||||
import java.util.HashMap;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: LocalSolrQueryRequest.java,v 1.6 2005/06/02 22:03:38 yonik Exp $
|
||||
*/
|
||||
public class LocalSolrQueryRequest extends SolrQueryRequestBase {
|
||||
private final NamedList args;
|
||||
private final String query;
|
||||
private final String qtype;
|
||||
private final int start;
|
||||
private final int limit;
|
||||
|
||||
public final static Map emptyArgs = new HashMap(0,1);
|
||||
|
||||
public LocalSolrQueryRequest(SolrCore core, String query, String qtype, int start, int limit, Map args) {
|
||||
super(core);
|
||||
this.query=query;
|
||||
this.qtype=qtype;
|
||||
this.start=start;
|
||||
this.limit=limit;
|
||||
|
||||
this.args = new NamedList();
|
||||
if (query!=null) this.args.add(SolrQueryRequestBase.QUERY_NAME, query);
|
||||
if (qtype!=null) this.args.add(SolrQueryRequestBase.QUERYTYPE_NAME, qtype);
|
||||
this.args.add(SolrQueryRequestBase.START_NAME, Integer.toString(start));
|
||||
this.args.add(SolrQueryRequestBase.ROWS_NAME, Integer.toString(limit));
|
||||
|
||||
if (args!=null) this.args.addAll(args);
|
||||
}
|
||||
|
||||
|
||||
public LocalSolrQueryRequest(SolrCore core, NamedList args) {
|
||||
super(core);
|
||||
this.args=args;
|
||||
this.query=getStrParam(QUERY_NAME,null);
|
||||
this.qtype=getStrParam(QUERYTYPE_NAME,null);;
|
||||
this.start=getIntParam(START_NAME,0);
|
||||
this.limit=getIntParam(ROWS_NAME,10);
|
||||
}
|
||||
|
||||
|
||||
public String getParam(String name) {
|
||||
return (String)args.get(name);
|
||||
}
|
||||
|
||||
public String getQueryString() {
|
||||
return query;
|
||||
}
|
||||
|
||||
// signifies the syntax and the handler that should be used
|
||||
// to execute this query.
|
||||
public String getQueryType() {
|
||||
return qtype;
|
||||
}
|
||||
|
||||
|
||||
// starting position in matches to return to client
|
||||
public int getStart() {
|
||||
return start;
|
||||
}
|
||||
|
||||
// number of matching documents to return
|
||||
public int getLimit() {
|
||||
return limit;
|
||||
}
|
||||
|
||||
final long startTime=System.currentTimeMillis();
|
||||
// Get the start time of this request in milliseconds
|
||||
public long getStartTime() {
|
||||
return startTime;
|
||||
}
|
||||
|
||||
// The index searcher associated with this request
|
||||
RefCounted<SolrIndexSearcher> searcherHolder;
|
||||
public SolrIndexSearcher getSearcher() {
|
||||
// should this reach out and get a searcher from the core singleton, or
|
||||
// should the core populate one in a factory method to create requests?
|
||||
// or there could be a setSearcher() method that Solr calls
|
||||
|
||||
if (searcherHolder==null) {
|
||||
searcherHolder = core.getSearcher();
|
||||
}
|
||||
|
||||
return searcherHolder.get();
|
||||
}
|
||||
|
||||
// The solr core (coordinator, etc) associated with this request
|
||||
public SolrCore getCore() {
|
||||
return core;
|
||||
}
|
||||
|
||||
// The index schema associated with this request
|
||||
public IndexSchema getSchema() {
|
||||
return core.getSchema();
|
||||
}
|
||||
|
||||
public String getParamString() {
|
||||
StringBuilder sb = new StringBuilder(128);
|
||||
try {
|
||||
|
||||
boolean first=true;
|
||||
if (query!=null) {
|
||||
if (!first) {
|
||||
sb.append('&');
|
||||
}
|
||||
first=false;
|
||||
sb.append("q=");
|
||||
StrUtils.partialURLEncodeVal(sb,query);
|
||||
}
|
||||
|
||||
// null, "", and "standard" are all the default query handler.
|
||||
if (qtype!=null && !(qtype.equals("") || qtype.equals("standard"))) {
|
||||
if (!first) {
|
||||
sb.append('&');
|
||||
}
|
||||
first=false;
|
||||
sb.append("qt=");
|
||||
sb.append(qtype);
|
||||
}
|
||||
|
||||
if (start!=0) {
|
||||
if (!first) {
|
||||
sb.append('&');
|
||||
}
|
||||
first=false;
|
||||
sb.append("start=");
|
||||
sb.append(start);
|
||||
}
|
||||
|
||||
if (!first) {
|
||||
sb.append('&');
|
||||
}
|
||||
first=false;
|
||||
sb.append("rows=");
|
||||
sb.append(limit);
|
||||
|
||||
if (args != null && args.size() > 0) {
|
||||
for (int i=0; i<args.size(); i++) {
|
||||
if (!first) {
|
||||
sb.append('&');
|
||||
}
|
||||
first=false;
|
||||
|
||||
sb.append(args.getName(i));
|
||||
sb.append('=');
|
||||
StrUtils.partialURLEncodeVal(sb,args.getVal(i).toString());
|
||||
}
|
||||
}
|
||||
|
||||
} catch (Exception e) {
|
||||
// should never happen... we only needed this because
|
||||
// partialURLEncodeVal can throw an IOException, but it
|
||||
// never will when adding to a StringBuilder.
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
|
||||
return sb.toString();
|
||||
}
|
||||
|
||||
|
||||
public void close() {
|
||||
if (searcherHolder!=null) {
|
||||
searcherHolder.decref();
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,29 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.request;
|
||||
|
||||
import java.io.Writer;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: QueryResponseWriter.java,v 1.2 2005/04/24 02:53:35 yonik Exp $
|
||||
*/
|
||||
public interface QueryResponseWriter {
|
||||
public void write(Writer writer, SolrQueryRequest request, SolrQueryResponse response) throws IOException;
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,65 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.request;
|
||||
|
||||
import org.apache.solr.search.SolrIndexSearcher;
|
||||
import org.apache.solr.schema.IndexSchema;
|
||||
import org.apache.solr.core.SolrCore;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: SolrQueryRequest.java,v 1.3 2005/05/10 19:40:12 yonik Exp $
|
||||
*/
|
||||
public interface SolrQueryRequest {
|
||||
public String getParam(String name);
|
||||
|
||||
public String getQueryString();
|
||||
|
||||
// signifies the syntax and the handler that should be used
|
||||
// to execute this query.
|
||||
public String getQueryType();
|
||||
|
||||
// starting position in matches to return to client
|
||||
public int getStart();
|
||||
|
||||
// number of matching documents to return
|
||||
public int getLimit();
|
||||
|
||||
// Get the start time of this request in milliseconds
|
||||
public long getStartTime();
|
||||
|
||||
// The index searcher associated with this request
|
||||
public SolrIndexSearcher getSearcher();
|
||||
|
||||
// The solr core (coordinator, etc) associated with this request
|
||||
public SolrCore getCore();
|
||||
|
||||
// The index schema associated with this request
|
||||
public IndexSchema getSchema();
|
||||
|
||||
/**
|
||||
* Returns a string representing all the important parameters.
|
||||
* Suitable for logging.
|
||||
*/
|
||||
public String getParamString();
|
||||
|
||||
/******
|
||||
// Get the current elapsed time in milliseconds
|
||||
public long getElapsedTime();
|
||||
******/
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,130 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.request;
|
||||
|
||||
import org.apache.solr.search.SolrIndexSearcher;
|
||||
import org.apache.solr.util.RefCounted;
|
||||
import org.apache.solr.schema.IndexSchema;
|
||||
import org.apache.solr.core.SolrCore;
|
||||
import org.apache.solr.core.SolrException;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: SolrQueryRequestBase.java,v 1.6 2005/06/12 02:36:09 yonik Exp $
|
||||
*/
|
||||
public abstract class SolrQueryRequestBase implements SolrQueryRequest {
|
||||
// some standard query argument names
|
||||
public static final String QUERY_NAME="q";
|
||||
public static final String START_NAME="start";
|
||||
public static final String ROWS_NAME="rows";
|
||||
public static final String XSL_NAME="xsl";
|
||||
public static final String QUERYTYPE_NAME="qt";
|
||||
|
||||
|
||||
protected final SolrCore core;
|
||||
|
||||
public SolrQueryRequestBase(SolrCore core) {
|
||||
this.core=core;
|
||||
}
|
||||
|
||||
public int getIntParam(String name) {
|
||||
String s = getParam(name);
|
||||
if (s==null) {
|
||||
throw new SolrException(500,"Missing required parameter '"+name+"' from " + this);
|
||||
}
|
||||
return Integer.parseInt(s);
|
||||
}
|
||||
|
||||
public int getIntParam(String name, int defval) {
|
||||
String s = getParam(name);
|
||||
return s==null ? defval : Integer.parseInt(s);
|
||||
}
|
||||
|
||||
public String getStrParam(String name) {
|
||||
String s = getParam(name);
|
||||
if (s==null) {
|
||||
throw new SolrException(500,"Missing required parameter '"+name+"' from " + this);
|
||||
}
|
||||
return s;
|
||||
}
|
||||
|
||||
public String getStrParam(String name, String defval) {
|
||||
String s = getParam(name);
|
||||
return s==null ? defval : s;
|
||||
}
|
||||
|
||||
public String getQueryString() {
|
||||
return getParam(QUERY_NAME);
|
||||
}
|
||||
|
||||
public String getQueryType() {
|
||||
return getParam(QUERYTYPE_NAME);
|
||||
}
|
||||
|
||||
// starting position in matches to return to client
|
||||
public int getStart() {
|
||||
return getIntParam(START_NAME, 0);
|
||||
}
|
||||
|
||||
// number of matching documents to return
|
||||
public int getLimit() {
|
||||
return getIntParam(ROWS_NAME, 10);
|
||||
}
|
||||
|
||||
|
||||
protected final long startTime=System.currentTimeMillis();
|
||||
// Get the start time of this request in milliseconds
|
||||
public long getStartTime() {
|
||||
return startTime;
|
||||
}
|
||||
|
||||
// The index searcher associated with this request
|
||||
protected RefCounted<SolrIndexSearcher> searcherHolder;
|
||||
public SolrIndexSearcher getSearcher() {
|
||||
// should this reach out and get a searcher from the core singleton, or
|
||||
// should the core populate one in a factory method to create requests?
|
||||
// or there could be a setSearcher() method that Solr calls
|
||||
|
||||
if (searcherHolder==null) {
|
||||
searcherHolder = core.getSearcher();
|
||||
}
|
||||
|
||||
return searcherHolder.get();
|
||||
}
|
||||
|
||||
// The solr core (coordinator, etc) associated with this request
|
||||
public SolrCore getCore() {
|
||||
return core;
|
||||
}
|
||||
|
||||
// The index schema associated with this request
|
||||
public IndexSchema getSchema() {
|
||||
return core.getSchema();
|
||||
}
|
||||
|
||||
|
||||
public void close() {
|
||||
if (searcherHolder!=null) {
|
||||
searcherHolder.decref();
|
||||
}
|
||||
}
|
||||
|
||||
public String toString() {
|
||||
return this.getClass().getSimpleName() + '{' + getParamString() + '}';
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,125 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.request;
|
||||
|
||||
import org.apache.solr.util.NamedList;
|
||||
|
||||
import java.util.*;
|
||||
|
||||
/**
|
||||
* <code>SolrQueryResponse</code> is used by a query handler to return
|
||||
* the response to a query.
|
||||
* @author yonik
|
||||
* @version $Id: SolrQueryResponse.java,v 1.5 2005/08/10 04:27:04 yonik Exp $
|
||||
* @since solr 0.9
|
||||
*/
|
||||
|
||||
public class SolrQueryResponse {
|
||||
|
||||
protected NamedList values = new NamedList();
|
||||
// current holder for user defined values
|
||||
|
||||
protected Set<String> defaultReturnFields;
|
||||
|
||||
// error if this is set...
|
||||
protected Exception err;
|
||||
|
||||
/***
|
||||
// another way of returning an error
|
||||
int errCode;
|
||||
String errMsg;
|
||||
***/
|
||||
|
||||
public NamedList getValues() { return values; }
|
||||
|
||||
/**
|
||||
* Sets a list of all the named values to return.
|
||||
*/
|
||||
public void setAllValues(NamedList nameValuePairs) {
|
||||
values=nameValuePairs;
|
||||
}
|
||||
|
||||
/**
|
||||
* Sets the document field names of fields to return by default.
|
||||
*/
|
||||
public void setReturnFields(Set<String> fields) {
|
||||
defaultReturnFields=fields;
|
||||
}
|
||||
// TODO: should this be represented as a String[] such
|
||||
// that order can be maintained if needed?
|
||||
|
||||
/**
|
||||
* The document field names to return by default.
|
||||
*/
|
||||
public Set<String> getReturnFields() {
|
||||
return defaultReturnFields;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Appends a named value to the list of named values to be returned.
|
||||
* @param name the name of the value - may be null if unnamed
|
||||
* @param val the value to add - also may be null since null is a legal value
|
||||
*/
|
||||
public void add(String name, Object val) {
|
||||
values.add(name,val);
|
||||
}
|
||||
|
||||
/**
|
||||
* Causes an error to be returned instead of the results.
|
||||
*/
|
||||
public void setException(Exception e) {
|
||||
err=e;
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns an Exception if there was a fatal error in processing the request.
|
||||
* Returns null if the request succeeded.
|
||||
*/
|
||||
public Exception getException() {
|
||||
return err;
|
||||
}
|
||||
|
||||
// Get and Set the endtime in milliseconds... used
|
||||
// to calculate query time.
|
||||
protected long endtime;
|
||||
|
||||
/** Time in milliseconds when the response officially finished.
|
||||
*/
|
||||
public long getEndTime() {
|
||||
if (endtime==0) {
|
||||
setEndTime();
|
||||
}
|
||||
return endtime;
|
||||
}
|
||||
|
||||
/**
|
||||
* Stop the timer for how long this query took.
|
||||
*/
|
||||
public long setEndTime() {
|
||||
return setEndTime(System.currentTimeMillis());
|
||||
}
|
||||
|
||||
public long setEndTime(long endtime) {
|
||||
if (endtime!=0) {
|
||||
this.endtime=endtime;
|
||||
}
|
||||
return this.endtime;
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,63 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.request;
|
||||
|
||||
import org.apache.solr.util.NamedList;
|
||||
import org.apache.solr.core.SolrInfoMBean;
|
||||
|
||||
/**
|
||||
* Implementations of <code>SolrRequestHandler</code> are called to handle query requests.
|
||||
*
|
||||
* Different <code>SolrRequestHandler</code>s are registered with the <code>SolrCore</code>.
|
||||
* One way to register a SolrRequestHandler with the core is thorugh the <code>solarconfig.xml</code> file.
|
||||
* <p>
|
||||
* Example <code>solarconfig.xml</code> entry to register a <code>SolrRequestHandler</code> implementation to
|
||||
* handle all queries with a query type of "test":
|
||||
* <p>
|
||||
* <code>
|
||||
* <requestHandler name="test" class="solr.tst.TestRequestHandler" />
|
||||
* </code>
|
||||
* <p>
|
||||
* A single instance of any registered SolrRequestHandler is created
|
||||
* via the default constructor and is reused for all relevant queries.
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: SolrRequestHandler.java,v 1.7 2005/12/02 04:31:06 yonik Exp $
|
||||
*/
|
||||
public interface SolrRequestHandler extends SolrInfoMBean {
|
||||
|
||||
/** <code>init</code> will be called just once, immediately after creation.
|
||||
* <p>The args are user-level initialization parameters that
|
||||
* may be specified when declaring a request handler in
|
||||
* solarconfig.xml
|
||||
*/
|
||||
public void init(NamedList args);
|
||||
|
||||
|
||||
/**
|
||||
* Handles a query request. This method must be thread safe.
|
||||
* <p>
|
||||
* Information about the request may be obtained from <code>req</code> and
|
||||
* response information may be set using <code>rsp</code>.
|
||||
* <p>
|
||||
* There are no mandatory actions that handleRequest must perform.
|
||||
* An empty handleRequest implementation would fulfill
|
||||
* all interface obligations.
|
||||
*/
|
||||
public void handleRequest(SolrQueryRequest req, SolrQueryResponse rsp);
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,225 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.request;
|
||||
|
||||
import org.apache.lucene.search.*;
|
||||
import org.apache.lucene.document.Document;
|
||||
|
||||
import java.util.List;
|
||||
import java.util.Set;
|
||||
import java.util.HashSet;
|
||||
import java.util.logging.Level;
|
||||
import java.util.regex.Pattern;
|
||||
import java.io.IOException;
|
||||
import java.net.URL;
|
||||
|
||||
import org.apache.solr.util.StrUtils;
|
||||
import org.apache.solr.util.NamedList;
|
||||
import org.apache.solr.search.*;
|
||||
import org.apache.solr.schema.IndexSchema;
|
||||
import org.apache.solr.core.SolrCore;
|
||||
import org.apache.solr.core.SolrInfoMBean;
|
||||
import org.apache.solr.core.SolrException;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: StandardRequestHandler.java,v 1.17 2005/12/02 04:31:06 yonik Exp $
|
||||
*/
|
||||
public class StandardRequestHandler implements SolrRequestHandler, SolrInfoMBean {
|
||||
|
||||
// statistics
|
||||
// TODO: should we bother synchronizing these, or is an off-by-one error
|
||||
// acceptable every million requests or so?
|
||||
long numRequests;
|
||||
long numErrors;
|
||||
|
||||
|
||||
public void init(NamedList args) {
|
||||
SolrCore.log.log(Level.INFO, "Unused request handler arguments:" + args);
|
||||
}
|
||||
|
||||
|
||||
private final Pattern splitList=Pattern.compile(",| ");
|
||||
|
||||
public void handleRequest(SolrQueryRequest req, SolrQueryResponse rsp) {
|
||||
numRequests++;
|
||||
|
||||
|
||||
// TODO: test if lucene will accept an escaped ';', otherwise
|
||||
// we need to un-escape them before we pass to QueryParser
|
||||
try {
|
||||
String sreq = req.getQueryString();
|
||||
String debug = req.getParam("debugQuery");
|
||||
|
||||
// find fieldnames to return (fieldlist)
|
||||
String fl = req.getParam("fl");
|
||||
int flags=0;
|
||||
if (fl != null) {
|
||||
// TODO - this could become more efficient if widely used.
|
||||
// TODO - should field order be maintained?
|
||||
String[] flst = splitList.split(fl,0);
|
||||
if (flst.length > 0 && !(flst.length==1 && flst[0].length()==0)) {
|
||||
Set<String> set = new HashSet<String>();
|
||||
for (String fname : flst) {
|
||||
if ("score".equals(fname)) flags |= SolrIndexSearcher.GET_SCORES;
|
||||
set.add(fname);
|
||||
}
|
||||
rsp.setReturnFields(set);
|
||||
}
|
||||
}
|
||||
|
||||
if (sreq==null) throw new SolrException(400,"Missing queryString");
|
||||
List<String> commands = StrUtils.splitSmart(sreq,';');
|
||||
|
||||
String qs = commands.size() >= 1 ? commands.get(0) : "";
|
||||
Query query = QueryParsing.parseQuery(qs, req.getSchema());
|
||||
|
||||
// If the first non-query, non-filter command is a simple sort on an indexed field, then
|
||||
// we can use the Lucene sort ability.
|
||||
Sort sort = null;
|
||||
if (commands.size() >= 2) {
|
||||
QueryParsing.SortSpec sortSpec = QueryParsing.parseSort(commands.get(1), req.getSchema());
|
||||
if (sortSpec != null) {
|
||||
sort = sortSpec.getSort();
|
||||
// ignore the count for now... it's currently only controlled by start & limit on req
|
||||
// count = sortSpec.getCount();
|
||||
}
|
||||
}
|
||||
|
||||
DocList results = req.getSearcher().getDocList(query, null, sort, req.getStart(), req.getLimit(), flags);
|
||||
rsp.add(null,results);
|
||||
|
||||
if (debug!=null) {
|
||||
NamedList dbg = new NamedList();
|
||||
try {
|
||||
dbg.add("querystring",qs);
|
||||
dbg.add("parsedquery",QueryParsing.toString(query,req.getSchema()));
|
||||
dbg.add("explain", getExplainList(query, results, req.getSearcher(), req.getSchema()));
|
||||
String otherQueryS = req.getParam("explainOther");
|
||||
if (otherQueryS != null && otherQueryS.length() > 0) {
|
||||
DocList otherResults = doQuery(otherQueryS,req.getSearcher(), req.getSchema(),0,10);
|
||||
dbg.add("otherQuery",otherQueryS);
|
||||
dbg.add("explainOther", getExplainList(query, otherResults, req.getSearcher(), req.getSchema()));
|
||||
}
|
||||
} catch (Exception e) {
|
||||
SolrException.logOnce(SolrCore.log,"Exception during debug:",e);
|
||||
dbg.add("exception_during_debug", SolrException.toStr(e));
|
||||
}
|
||||
rsp.add("debug",dbg);
|
||||
}
|
||||
|
||||
} catch (SolrException e) {
|
||||
rsp.setException(e);
|
||||
numErrors++;
|
||||
return;
|
||||
} catch (Exception e) {
|
||||
SolrException.log(SolrCore.log,e);
|
||||
rsp.setException(e);
|
||||
numErrors++;
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
private NamedList getExplainList(Query query, DocList results, SolrIndexSearcher searcher, IndexSchema schema) throws IOException {
|
||||
NamedList explainList = new NamedList();
|
||||
DocIterator iterator = results.iterator();
|
||||
for (int i=0; i<results.size(); i++) {
|
||||
int id = iterator.nextDoc();
|
||||
|
||||
Explanation explain = searcher.explain(query, id);
|
||||
//explainList.add(Integer.toString(id), explain.toString().split("\n"));
|
||||
|
||||
Document doc = searcher.doc(id);
|
||||
String strid = schema.printableUniqueKey(doc);
|
||||
String docname = "";
|
||||
if (strid != null) docname="id="+strid+",";
|
||||
docname = docname + "internal_docid="+id;
|
||||
|
||||
explainList.add(docname, "\n" +explain.toString());
|
||||
}
|
||||
return explainList;
|
||||
}
|
||||
|
||||
|
||||
private DocList doQuery(String sreq, SolrIndexSearcher searcher, IndexSchema schema, int start, int limit) throws IOException {
|
||||
List<String> commands = StrUtils.splitSmart(sreq,';');
|
||||
|
||||
String qs = commands.size() >= 1 ? commands.get(0) : "";
|
||||
Query query = QueryParsing.parseQuery(qs, schema);
|
||||
|
||||
// If the first non-query, non-filter command is a simple sort on an indexed field, then
|
||||
// we can use the Lucene sort ability.
|
||||
Sort sort = null;
|
||||
if (commands.size() >= 2) {
|
||||
QueryParsing.SortSpec sortSpec = QueryParsing.parseSort(commands.get(1), schema);
|
||||
if (sortSpec != null) {
|
||||
sort = sortSpec.getSort();
|
||||
if (sortSpec.getCount() >= 0) {
|
||||
limit = sortSpec.getCount();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
DocList results = searcher.getDocList(query,(DocSet)null, sort, start, limit);
|
||||
return results;
|
||||
}
|
||||
|
||||
|
||||
|
||||
//////////////////////// SolrInfoMBeans methods //////////////////////
|
||||
|
||||
|
||||
public String getName() {
|
||||
return StandardRequestHandler.class.getName();
|
||||
}
|
||||
|
||||
public String getVersion() {
|
||||
return SolrCore.version;
|
||||
}
|
||||
|
||||
public String getDescription() {
|
||||
return "The standard Solr request handler";
|
||||
}
|
||||
|
||||
public Category getCategory() {
|
||||
return Category.QUERYHANDLER;
|
||||
}
|
||||
|
||||
public String getCvsId() {
|
||||
return "$Id: StandardRequestHandler.java,v 1.17 2005/12/02 04:31:06 yonik Exp $";
|
||||
}
|
||||
|
||||
public String getCvsName() {
|
||||
return "$Name: $";
|
||||
}
|
||||
|
||||
public String getCvsSource() {
|
||||
return "$Source: /cvs/main/searching/solr/solarcore/src/solr/StandardRequestHandler.java,v $";
|
||||
}
|
||||
|
||||
public URL[] getDocs() {
|
||||
return null;
|
||||
}
|
||||
|
||||
public NamedList getStatistics() {
|
||||
NamedList lst = new NamedList();
|
||||
lst.add("requests", numRequests);
|
||||
lst.add("errors", numErrors);
|
||||
return lst;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,33 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.request;
|
||||
|
||||
import java.io.Writer;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: XMLResponseWriter.java,v 1.6 2005/04/24 02:53:35 yonik Exp $
|
||||
*/
|
||||
|
||||
public class XMLResponseWriter implements QueryResponseWriter {
|
||||
public void write(Writer writer, SolrQueryRequest req, SolrQueryResponse rsp) throws IOException {
|
||||
XMLWriter.writeResponse(writer,req,rsp);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,620 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.request;
|
||||
|
||||
import org.apache.solr.util.NamedList;
|
||||
import org.apache.solr.util.XML;
|
||||
import org.apache.solr.search.SolrIndexSearcher;
|
||||
import org.apache.solr.search.DocList;
|
||||
import org.apache.solr.search.DocIterator;
|
||||
import org.apache.solr.search.DocSet;
|
||||
import org.apache.solr.schema.IndexSchema;
|
||||
import org.apache.solr.schema.SchemaField;
|
||||
|
||||
import java.io.Writer;
|
||||
import java.io.IOException;
|
||||
import java.util.*;
|
||||
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.document.Document;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: XMLWriter.java,v 1.16 2005/12/02 04:31:06 yonik Exp $
|
||||
*/
|
||||
final public class XMLWriter {
|
||||
//
|
||||
// static thread safe part
|
||||
//
|
||||
private static final char[] XML_START1="<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n".toCharArray();
|
||||
|
||||
private static final char[] XML_STYLESHEET="<?xml-stylesheet type=\"text/xsl\" href=\"/admin/".toCharArray();
|
||||
private static final char[] XML_STYLESHEET_END=".xsl\"?>\n".toCharArray();
|
||||
|
||||
private static final char[] XML_START2_SCHEMA=(
|
||||
"<response xmlns:xsi=\"http://www.w3.org/2001/XMLSchema-instance\"\n"
|
||||
+" xsi:noNamespaceSchemaLocation=\"http://pi.cnet.com/cnet-search/response.xsd\">\n"
|
||||
).toCharArray();
|
||||
private static final char[] XML_START2_NOSCHEMA=(
|
||||
"<response>\n"
|
||||
).toCharArray();
|
||||
|
||||
|
||||
public static void writeResponse(Writer writer, SolrQueryRequest req, SolrQueryResponse rsp) throws IOException {
|
||||
|
||||
// get total time up until now
|
||||
int qtime=(int)(rsp.getEndTime() - req.getStartTime());
|
||||
|
||||
String ver = req.getParam("version");
|
||||
|
||||
writer.write(XML_START1);
|
||||
|
||||
String stylesheet = req.getParam("stylesheet");
|
||||
if (stylesheet != null && stylesheet.length() > 0) {
|
||||
writer.write(XML_STYLESHEET);
|
||||
writer.write(stylesheet);
|
||||
writer.write(XML_STYLESHEET_END);
|
||||
}
|
||||
|
||||
String noSchema = req.getParam("noSchema");
|
||||
// todo - change when schema becomes available?
|
||||
if (false && noSchema == null)
|
||||
writer.write(XML_START2_SCHEMA);
|
||||
else
|
||||
writer.write(XML_START2_NOSCHEMA);
|
||||
|
||||
writer.write("<responseHeader><status>");
|
||||
writer.write('0'); // it's 0 (success) if we got this far...
|
||||
writer.write("</status><QTime>");
|
||||
writer.write(Integer.toString((int)qtime));
|
||||
writer.write("</QTime></responseHeader>\n");
|
||||
|
||||
//
|
||||
// create an instance for each request to handle
|
||||
// non-thread safe stuff (indentation levels, etc)
|
||||
// and to encapsulate writer, schema, and searcher so
|
||||
// they don't have to be passed around in every function.
|
||||
//
|
||||
XMLWriter xw = new XMLWriter(writer, req.getSchema(), req.getSearcher(), ver);
|
||||
xw.defaultFieldList = rsp.getReturnFields();
|
||||
|
||||
String indent = req.getParam("indent");
|
||||
if (indent != null) {
|
||||
if ("".equals(indent) || "off".equals(indent)) {
|
||||
xw.setIndent(false);
|
||||
} else {
|
||||
xw.setIndent(true);
|
||||
}
|
||||
}
|
||||
|
||||
NamedList lst = rsp.getValues();
|
||||
int sz = lst.size();
|
||||
for (int i=0; i<sz; i++) {
|
||||
xw.writeVal(lst.getName(i),lst.getVal(i));
|
||||
}
|
||||
|
||||
writer.write("\n</response>\n");
|
||||
}
|
||||
|
||||
|
||||
////////////////////////////////////////////////////////////
|
||||
// request instance specific (non-static, not shared between threads)
|
||||
////////////////////////////////////////////////////////////
|
||||
|
||||
private final Writer writer;
|
||||
private final IndexSchema schema; // needed to write fields of docs
|
||||
private final SolrIndexSearcher searcher; // needed to retrieve docs
|
||||
|
||||
private int level;
|
||||
private boolean defaultIndent=false;
|
||||
private boolean doIndent=false;
|
||||
|
||||
// fieldList... the set of fields to return for each document
|
||||
private Set<String> defaultFieldList;
|
||||
|
||||
|
||||
// if a list smaller than this threshold is encountered, elements
|
||||
// will be written on the same line.
|
||||
// maybe constructed types should always indent first?
|
||||
private final int indentThreshold=0;
|
||||
|
||||
private final int version;
|
||||
|
||||
|
||||
// temporary working objects...
|
||||
// be careful not to use these recursively...
|
||||
private final ArrayList tlst = new ArrayList();
|
||||
private final Calendar cal = Calendar.getInstance(TimeZone.getTimeZone("GMT"));
|
||||
private final StringBuilder sb = new StringBuilder();
|
||||
|
||||
XMLWriter(Writer writer, IndexSchema schema, SolrIndexSearcher searcher, String version) {
|
||||
this.writer = writer;
|
||||
this.schema = schema;
|
||||
this.searcher = searcher;
|
||||
float ver = version==null? 2.1f : Float.parseFloat(version);
|
||||
this.version = (int)(ver*1000);
|
||||
}
|
||||
|
||||
//
|
||||
// Functions to manipulate the current logical nesting level.
|
||||
// Any indentation will be partially based on level.
|
||||
//
|
||||
public void setLevel(int level) { this.level = level; }
|
||||
public int level() { return level; }
|
||||
public int incLevel() { return ++level; }
|
||||
public int decLevel() { return --level; }
|
||||
public void setIndent(boolean doIndent) {
|
||||
this.doIndent = doIndent;
|
||||
defaultIndent = doIndent;
|
||||
}
|
||||
|
||||
public void writeAttr(String name, String val) throws IOException {
|
||||
if (val != null) {
|
||||
writer.write(' ');
|
||||
writer.write(name);
|
||||
writer.write("=\"");
|
||||
writer.write(val);
|
||||
writer.write('"');
|
||||
}
|
||||
}
|
||||
|
||||
public void startTag(String tag, String name, boolean closeTag) throws IOException {
|
||||
if (doIndent) indent();
|
||||
|
||||
writer.write('<');
|
||||
writer.write(tag);
|
||||
if (name!=null) {
|
||||
writer.write(" name=\"");
|
||||
writer.write(name);
|
||||
if (closeTag) {
|
||||
writer.write("\"/>");
|
||||
} else {
|
||||
writer.write("\">");
|
||||
}
|
||||
} else {
|
||||
if (closeTag) {
|
||||
writer.write("/>");
|
||||
} else {
|
||||
writer.write('>');
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private static final String[] indentArr = new String[] {
|
||||
"\n",
|
||||
"\n ",
|
||||
"\n ",
|
||||
"\n\t",
|
||||
"\n\t ",
|
||||
"\n\t ", // could skip this one (the only 3 char seq)
|
||||
"\n\t\t" };
|
||||
|
||||
public void indent() throws IOException {
|
||||
indent(level);
|
||||
}
|
||||
|
||||
public void indent(int lev) throws IOException {
|
||||
int arrsz = indentArr.length-1;
|
||||
// another option would be lev % arrsz (wrap around)
|
||||
String istr = indentArr[ lev > arrsz ? arrsz : lev ];
|
||||
writer.write(istr);
|
||||
}
|
||||
|
||||
private static final Comparator fieldnameComparator = new Comparator() {
|
||||
public int compare(Object o, Object o1) {
|
||||
Field f1 = (Field)o; Field f2 = (Field)o1;
|
||||
int cmp = f1.name().compareTo(f2.name());
|
||||
return cmp;
|
||||
// note - the sort is stable, so this should not have affected the ordering
|
||||
// of fields with the same name w.r.t eachother.
|
||||
}
|
||||
};
|
||||
|
||||
public final void writeDoc(String name, Document doc, Set<String> returnFields, float score, boolean includeScore) throws IOException {
|
||||
startTag("doc", name, false);
|
||||
incLevel();
|
||||
|
||||
if (includeScore) {
|
||||
writeFloat("score", score);
|
||||
}
|
||||
|
||||
|
||||
// Lucene Documents have multivalued types as multiple fields
|
||||
// with the same name.
|
||||
// The XML needs to represent these as
|
||||
// an array. The fastest way to detect multiple fields
|
||||
// with the same name is to sort them first.
|
||||
|
||||
Enumeration ee = doc.fields();
|
||||
|
||||
// using global tlst here, so we shouldn't call any other
|
||||
// function that uses it until we are done.
|
||||
tlst.clear();
|
||||
while (ee.hasMoreElements()) {
|
||||
Field ff = (Field) ee.nextElement();
|
||||
// skip this field if it is not a field to be returned.
|
||||
if (returnFields!=null && !returnFields.contains(ff.name())) {
|
||||
continue;
|
||||
}
|
||||
tlst.add(ff);
|
||||
}
|
||||
Collections.sort(tlst, fieldnameComparator);
|
||||
|
||||
int sz = tlst.size();
|
||||
int fidx1 = 0, fidx2 = 0;
|
||||
while (fidx1 < sz) {
|
||||
Field f1 = (Field)tlst.get(fidx1);
|
||||
String fname = f1.name();
|
||||
|
||||
// find the end of fields with this name
|
||||
fidx2 = fidx1+1;
|
||||
while (fidx2 < sz && fname.equals(((Field)tlst.get(fidx2)).name()) ) {
|
||||
fidx2++;
|
||||
}
|
||||
|
||||
/***
|
||||
// more efficient to use getFieldType instead of
|
||||
// getField since that way dynamic fields won't have
|
||||
// to create a SchemaField on the fly.
|
||||
FieldType ft = schema.getFieldType(fname);
|
||||
***/
|
||||
|
||||
SchemaField sf = schema.getField(fname);
|
||||
|
||||
if (fidx1+1 == fidx2) {
|
||||
// single field value
|
||||
if (version>=2100 && sf.multiValued()) {
|
||||
startTag("arr",fname,false);
|
||||
doIndent=false;
|
||||
sf.write(this, null, f1);
|
||||
writer.write("</arr>");
|
||||
doIndent=defaultIndent;
|
||||
} else {
|
||||
sf.write(this, f1.name(), f1);
|
||||
}
|
||||
} else {
|
||||
// multiple fields with same name detected
|
||||
|
||||
startTag("arr",fname,false);
|
||||
incLevel();
|
||||
doIndent=false;
|
||||
int cnt=0;
|
||||
for (int i=fidx1; i<fidx2; i++) {
|
||||
if (defaultIndent && ++cnt==4) { // only indent every 4th item
|
||||
indent();
|
||||
cnt=0;
|
||||
}
|
||||
sf.write(this, null, (Field)tlst.get(i));
|
||||
}
|
||||
decLevel();
|
||||
// if (doIndent) indent();
|
||||
writer.write("</arr>");
|
||||
// doIndent=true;
|
||||
doIndent=defaultIndent;
|
||||
}
|
||||
fidx1 = fidx2;
|
||||
}
|
||||
|
||||
decLevel();
|
||||
if (doIndent) indent();
|
||||
writer.write("</doc>");
|
||||
}
|
||||
|
||||
public final void writeDocList(String name, DocList ids, Set<String> fields) throws IOException {
|
||||
boolean includeScore=false;
|
||||
if (fields!=null) {
|
||||
includeScore = fields.contains("score");
|
||||
if (fields.size()==0 || (fields.size()==1 && includeScore) || fields.contains("*")) {
|
||||
fields=null; // null means return all stored fields
|
||||
}
|
||||
}
|
||||
|
||||
int sz=ids.size();
|
||||
|
||||
if (doIndent) indent();
|
||||
writer.write("<result");
|
||||
writeAttr("name",name);
|
||||
writeAttr("numFound",Integer.toString(ids.matches()));
|
||||
writeAttr("start",Integer.toString(ids.offset()));
|
||||
if (includeScore) {
|
||||
writeAttr("maxScore",Float.toString(ids.maxScore()));
|
||||
}
|
||||
if (sz==0) {
|
||||
writer.write("/>");
|
||||
return;
|
||||
} else {
|
||||
writer.write('>');
|
||||
}
|
||||
|
||||
incLevel();
|
||||
DocIterator iterator = ids.iterator();
|
||||
for (int i=0; i<sz; i++) {
|
||||
int id = iterator.nextDoc();
|
||||
Document doc = searcher.doc(id);
|
||||
writeDoc(null, doc, fields, (includeScore ? iterator.score() : 0.0f), includeScore);
|
||||
}
|
||||
decLevel();
|
||||
|
||||
if (doIndent) indent();
|
||||
writer.write("</result>");
|
||||
}
|
||||
|
||||
|
||||
public void writeVal(String name, Object val) throws IOException {
|
||||
|
||||
// if there get to be enough types, perhaps hashing on the type
|
||||
// to get a handler might be faster (but types must be exact to do that...)
|
||||
|
||||
// go in order of most common to least common
|
||||
if (val==null) {
|
||||
writeNull(name);
|
||||
} else if (val instanceof String) {
|
||||
writeStr(name, (String)val);
|
||||
} else if (val instanceof Integer) {
|
||||
// it would be slower to pass the int ((Integer)val).intValue()
|
||||
writeInt(name, val.toString());
|
||||
} else if (val instanceof Boolean) {
|
||||
// could be optimized... only two vals
|
||||
writeBool(name, val.toString());
|
||||
} else if (val instanceof Long) {
|
||||
writeLong(name, val.toString());
|
||||
} else if (val instanceof Date) {
|
||||
writeDate(name,(Date)val);
|
||||
} else if (val instanceof Float) {
|
||||
// we pass the float instead of using toString() because
|
||||
// it may need special formatting. same for double.
|
||||
writeFloat(name, ((Float)val).floatValue());
|
||||
} else if (val instanceof Double) {
|
||||
writeDouble(name, ((Double)val).doubleValue());
|
||||
} else if (val instanceof Document) {
|
||||
writeDoc(name, (Document)val, null, 0.0f, false);
|
||||
} else if (val instanceof DocList) {
|
||||
// requires access to IndexReader
|
||||
writeDocList(name, (DocList)val, defaultFieldList);
|
||||
} else if (val instanceof DocSet) {
|
||||
// how do we know what fields to read?
|
||||
// todo: have a DocList/DocSet wrapper that
|
||||
// restricts the fields to write...?
|
||||
} else if (val instanceof Map) {
|
||||
writeMap(name, (Map)val);
|
||||
} else if (val instanceof NamedList) {
|
||||
writeNamedList(name, (NamedList)val);
|
||||
} else if (val instanceof Collection) {
|
||||
writeArray(name,(Collection)val);
|
||||
} else if (val instanceof Object[]) {
|
||||
writeArray(name,(Object[])val);
|
||||
} else {
|
||||
// default...
|
||||
writeStr(name, val.getClass().getName() + ':' + val.toString());
|
||||
}
|
||||
}
|
||||
|
||||
//
|
||||
// Generic compound types
|
||||
//
|
||||
|
||||
public void writeNamedList(String name, NamedList val) throws IOException {
|
||||
int sz = val.size();
|
||||
startTag("lst", name, sz<=0);
|
||||
|
||||
if (sz<indentThreshold) {
|
||||
doIndent=false;
|
||||
}
|
||||
|
||||
incLevel();
|
||||
for (int i=0; i<sz; i++) {
|
||||
writeVal(val.getName(i),val.getVal(i));
|
||||
}
|
||||
decLevel();
|
||||
|
||||
if (sz > 0) {
|
||||
if (doIndent) indent();
|
||||
writer.write("</lst>");
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
//A map is currently represented as a named list
|
||||
public void writeMap(String name, Map val) throws IOException {
|
||||
Map map = val;
|
||||
int sz = map.size();
|
||||
startTag("lst", name, sz<=0);
|
||||
incLevel();
|
||||
for (Map.Entry entry : (Set<Map.Entry>)map.entrySet()) {
|
||||
// possible class-cast exception here...
|
||||
String k = (String)entry.getKey();
|
||||
Object v = entry.getValue();
|
||||
// if (sz<indentThreshold) indent();
|
||||
writeVal(k,v);
|
||||
}
|
||||
decLevel();
|
||||
if (sz > 0) {
|
||||
if (doIndent) indent();
|
||||
writer.write("</lst>");
|
||||
}
|
||||
}
|
||||
|
||||
public void writeArray(String name, Object[] val) throws IOException {
|
||||
writeArray(name, Arrays.asList(val));
|
||||
}
|
||||
|
||||
public void writeArray(String name, Collection val) throws IOException {
|
||||
int sz = val.size();
|
||||
startTag("arr", name, sz<=0);
|
||||
incLevel();
|
||||
for (Object o : val) {
|
||||
// if (sz<indentThreshold) indent();
|
||||
writeVal(null, o);
|
||||
}
|
||||
decLevel();
|
||||
if (sz > 0) {
|
||||
if (doIndent) indent();
|
||||
writer.write("</arr>");
|
||||
}
|
||||
}
|
||||
|
||||
//
|
||||
// Primitive types
|
||||
//
|
||||
|
||||
public void writeNull(String name) throws IOException {
|
||||
writePrim("null",name,"",false);
|
||||
}
|
||||
|
||||
public void writeStr(String name, String val) throws IOException {
|
||||
writePrim("str",name,val,true);
|
||||
}
|
||||
|
||||
public void writeInt(String name, String val) throws IOException {
|
||||
writePrim("int",name,val,false);
|
||||
}
|
||||
|
||||
public void writeInt(String name, int val) throws IOException {
|
||||
writeInt(name,Integer.toString(val));
|
||||
}
|
||||
|
||||
public void writeLong(String name, String val) throws IOException {
|
||||
writePrim("long",name,val,false);
|
||||
}
|
||||
|
||||
public void writeLong(String name, long val) throws IOException {
|
||||
writeLong(name,Long.toString(val));
|
||||
}
|
||||
|
||||
public void writeBool(String name, String val) throws IOException {
|
||||
writePrim("bool",name,val,false);
|
||||
}
|
||||
|
||||
public void writeBool(String name, boolean val) throws IOException {
|
||||
writeBool(name,Boolean.toString(val));
|
||||
}
|
||||
|
||||
public void writeFloat(String name, String val) throws IOException {
|
||||
writePrim("float",name,val,false);
|
||||
}
|
||||
|
||||
public void writeFloat(String name, float val) throws IOException {
|
||||
writeFloat(name,Float.toString(val));
|
||||
}
|
||||
|
||||
public void writeDouble(String name, String val) throws IOException {
|
||||
writePrim("double",name,val,false);
|
||||
}
|
||||
|
||||
public void writeDouble(String name, double val) throws IOException {
|
||||
writeDouble(name,Double.toString(val));
|
||||
}
|
||||
|
||||
public void writeDate(String name, Date val) throws IOException {
|
||||
// using a stringBuilder for numbers can be nice since
|
||||
// a temporary string isn't used (it's added directly to the
|
||||
// builder's buffer.
|
||||
|
||||
cal.setTime(val);
|
||||
|
||||
sb.setLength(0);
|
||||
int i = cal.get(Calendar.YEAR);
|
||||
sb.append(i);
|
||||
sb.append('-');
|
||||
i = cal.get(Calendar.MONTH) + 1; // 0 based, so add 1
|
||||
if (i<10) sb.append('0');
|
||||
sb.append(i);
|
||||
sb.append('-');
|
||||
i=cal.get(Calendar.DAY_OF_MONTH);
|
||||
if (i<10) sb.append('0');
|
||||
sb.append(i);
|
||||
sb.append('T');
|
||||
i=cal.get(Calendar.HOUR_OF_DAY); // 24 hour time format
|
||||
if (i<10) sb.append('0');
|
||||
sb.append(i);
|
||||
sb.append(':');
|
||||
i=cal.get(Calendar.MINUTE);
|
||||
if (i<10) sb.append('0');
|
||||
sb.append(i);
|
||||
sb.append(':');
|
||||
i=cal.get(Calendar.SECOND);
|
||||
if (i<10) sb.append('0');
|
||||
sb.append(i);
|
||||
i=cal.get(Calendar.MILLISECOND);
|
||||
if (i != 0) {
|
||||
sb.append('.');
|
||||
if (i<100) sb.append('0');
|
||||
if (i<10) sb.append('0');
|
||||
sb.append(i);
|
||||
|
||||
// handle canonical format specifying fractional
|
||||
// seconds shall not end in '0'. Given the slowness of
|
||||
// integer div/mod, simply checking the last character
|
||||
// is probably the fastest way to check.
|
||||
int lastIdx = sb.length()-1;
|
||||
if (sb.charAt(lastIdx)=='0') {
|
||||
lastIdx--;
|
||||
if (sb.charAt(lastIdx)=='0') {
|
||||
lastIdx--;
|
||||
}
|
||||
sb.setLength(lastIdx+1);
|
||||
}
|
||||
|
||||
}
|
||||
sb.append('Z');
|
||||
writeDate(name, sb.toString());
|
||||
}
|
||||
|
||||
public void writeDate(String name, String val) throws IOException {
|
||||
writePrim("date",name,val,false);
|
||||
}
|
||||
|
||||
|
||||
//
|
||||
// OPT - specific writeInt, writeFloat, methods might be faster since
|
||||
// there would be less write calls (write("<int name=\"" + name + ... + </int>)
|
||||
//
|
||||
public void writePrim(String tag, String name, String val, boolean escape) throws IOException {
|
||||
// OPT - we could use a temp char[] (or a StringBuilder) and if the
|
||||
// size was small enough to fit (if escape==false we can calc exact size)
|
||||
// then we could put things directly in the temp buf.
|
||||
// need to see what percent of CPU this takes up first though...
|
||||
// Could test a reusable StringBuilder...
|
||||
|
||||
// is this needed here???
|
||||
// Only if a fieldtype calls writeStr or something
|
||||
// with a null val instead of calling writeNull
|
||||
/***
|
||||
if (val==null) {
|
||||
if (name==null) writer.write("<null/>");
|
||||
else writer.write("<null name=\"" + name + "/>");
|
||||
}
|
||||
***/
|
||||
|
||||
int contentLen=val.length();
|
||||
|
||||
startTag(tag, name, contentLen==0);
|
||||
if (contentLen==0) return;
|
||||
|
||||
if (escape) {
|
||||
XML.escapeCharData(val,writer);
|
||||
} else {
|
||||
writer.write(val,0,contentLen);
|
||||
}
|
||||
|
||||
writer.write("</");
|
||||
writer.write(tag);
|
||||
writer.write('>');
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,60 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.solr.util.BCDUtils;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class BCDIntField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return getStringSort(field,reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
throw new UnsupportedOperationException("ValueSource not implemented");
|
||||
}
|
||||
|
||||
public String toInternal(String val) {
|
||||
return BCDUtils.base10toBase10kSortableInt(val);
|
||||
}
|
||||
|
||||
public String toExternal(Field f) {
|
||||
return indexedToReadable(f.stringValue());
|
||||
}
|
||||
|
||||
public String indexedToReadable(String indexedForm) {
|
||||
return BCDUtils.base10kSortableIntToBase10(indexedForm);
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeInt(name,toExternal(f));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
import org.apache.lucene.document.Field;
|
||||
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class BCDLongField extends BCDIntField {
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeLong(name,toExternal(f));
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
import org.apache.lucene.document.Field;
|
||||
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class BCDStrField extends BCDIntField {
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeStr(name,toExternal(f));
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,97 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.OrdFieldSource;
|
||||
import org.apache.lucene.analysis.Token;
|
||||
import org.apache.lucene.analysis.Analyzer;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.Tokenizer;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.Reader;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class BoolField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return getStringSort(field,reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
return new OrdFieldSource(field.name);
|
||||
}
|
||||
|
||||
// avoid instantiating every time...
|
||||
protected final static Token TRUE_TOKEN = new Token("T",0,1);
|
||||
protected final static Token FALSE_TOKEN = new Token("F",0,1);
|
||||
|
||||
////////////////////////////////////////////////////////////////////////
|
||||
// TODO: look into creating my own queryParser that can more efficiently
|
||||
// handle single valued non-text fields (int,bool,etc) if needed.
|
||||
|
||||
|
||||
protected final static Analyzer boolAnalyzer = new Analyzer() {
|
||||
public TokenStream tokenStream(String fieldName, Reader reader) {
|
||||
return new Tokenizer(reader) {
|
||||
boolean done=false;
|
||||
public Token next() throws IOException {
|
||||
if (done) return null;
|
||||
done=true;
|
||||
int ch = input.read();
|
||||
if (ch==-1) return null;
|
||||
return (ch=='t' || ch=='T' || ch=='1') ? TRUE_TOKEN : FALSE_TOKEN;
|
||||
}
|
||||
};
|
||||
}
|
||||
};
|
||||
|
||||
public Analyzer getAnalyzer() {
|
||||
return boolAnalyzer;
|
||||
}
|
||||
|
||||
public Analyzer getQueryAnalyzer() {
|
||||
return boolAnalyzer;
|
||||
}
|
||||
|
||||
public String toInternal(String val) {
|
||||
char ch = (val!=null && val.length()>0) ? val.charAt(0) : 0;
|
||||
return (ch=='1' || ch=='t' || ch=='T') ? "T" : "F";
|
||||
}
|
||||
|
||||
public String toExternal(Field f) {
|
||||
return indexedToReadable(f.stringValue());
|
||||
}
|
||||
|
||||
public String indexedToReadable(String indexedForm) {
|
||||
char ch = indexedForm.charAt(0);
|
||||
return ch=='T' ? "true" : "false";
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeBool(name, f.stringValue().charAt(0) =='T');
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,94 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.solr.core.SolrException;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.OrdFieldSource;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
|
||||
/***
|
||||
Date Format for the XML, incoming and outgoing:
|
||||
|
||||
A date field shall be of the form 1995-12-31T23:59:59Z
|
||||
The trailing "Z" designates UTC time and is mandatory.
|
||||
Optional fractional seconds are allowed: 1995-12-31T23:59:59.999Z
|
||||
All other parts are mandatory.
|
||||
|
||||
This format was derived to be standards compliant (ISO 8601) and is a more
|
||||
restricted form of the canonical representation of dateTime from XML schema part 2.
|
||||
http://www.w3.org/TR/xmlschema-2/#dateTime
|
||||
|
||||
"In 1970 the Coordinated Universal Time system was devised by an international
|
||||
advisory group of technical experts within the International Telecommunication
|
||||
Union (ITU). The ITU felt it was best to designate a single abbreviation for
|
||||
use in all languages in order to minimize confusion. Since unanimous agreement
|
||||
could not be achieved on using either the English word order, CUT, or the
|
||||
French word order, TUC, the acronym UTC was chosen as a compromise."
|
||||
***/
|
||||
|
||||
// The XML (external) date format will sort correctly, except if
|
||||
// fractions of seconds are present (because '.' is lower than 'Z').
|
||||
// The easiest fix is to simply remove the 'Z' for the internal
|
||||
// format.
|
||||
|
||||
// TODO: make a FlexibleDateField that can accept dates in multiple
|
||||
// formats, better for human entered dates.
|
||||
|
||||
// TODO: make a DayField that only stores the day?
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class DateField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
}
|
||||
|
||||
public String toInternal(String val) {
|
||||
int len=val.length();
|
||||
if (val.charAt(len-1)=='Z') {
|
||||
return val.substring(0,len-1);
|
||||
}
|
||||
throw new SolrException(1,"Invalid Date String:'" +val+'\'');
|
||||
}
|
||||
|
||||
public String indexedToReadable(String indexedForm) {
|
||||
return indexedForm + 'Z';
|
||||
}
|
||||
|
||||
public String toExternal(Field f) {
|
||||
return indexedToReadable(f.stringValue());
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return getStringSort(field,reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
return new OrdFieldSource(field.name);
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeDate(name, toExternal(f));
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,50 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.FloatFieldSource;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class DoubleField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
restrictProps(SORT_MISSING_FIRST | SORT_MISSING_LAST);
|
||||
}
|
||||
|
||||
/////////////////////////////////////////////////////////////
|
||||
// TODO: ACK.. there is currently no SortField.DOUBLE!
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return new SortField(field.name,SortField.FLOAT, reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
// fieldCache doesn't support double
|
||||
return new FloatFieldSource(field.name);
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeDouble(name, f.stringValue());
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,144 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import java.util.Map;
|
||||
import java.util.HashMap;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
abstract class FieldProperties {
|
||||
|
||||
// use a bitfield instead of many different boolean variables since
|
||||
// many of the variables are independent or semi-independent.
|
||||
|
||||
// bit values for boolean field properties.
|
||||
final static int INDEXED = 0x00000001;
|
||||
final static int TOKENIZED = 0x00000002;
|
||||
final static int STORED = 0x00000004;
|
||||
final static int BINARY = 0x00000008;
|
||||
final static int COMPRESSED = 0x00000010;
|
||||
final static int OMIT_NORMS = 0x00000020;
|
||||
final static int STORE_TERMVECTORS = 0x00000040;
|
||||
final static int STORE_TERMPOSITIONS = 0x00000080;
|
||||
final static int STORE_TERMOFFSETS = 0x00000100;
|
||||
|
||||
final static int MULTIVALUED = 0x00000200;
|
||||
final static int SORT_MISSING_FIRST = 0x00000400;
|
||||
final static int SORT_MISSING_LAST = 0x00000800;
|
||||
|
||||
static final String[] propertyNames = {
|
||||
"indexed", "tokenized", "stored",
|
||||
"binary", "compressed", "omitNorms",
|
||||
"termVectors", "termPositions", "termOffsets",
|
||||
"multiValued",
|
||||
"sortMissingFirst","sortMissingLast"
|
||||
};
|
||||
|
||||
static final Map<String,Integer> propertyMap = new HashMap<String,Integer>();
|
||||
static {
|
||||
for (String prop : propertyNames) {
|
||||
propertyMap.put(prop, propertyNameToInt(prop));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
/** Returns the symbolic name for the property. */
|
||||
static String getPropertyName(int property) {
|
||||
return propertyNames[ Integer.numberOfTrailingZeros(property) ];
|
||||
}
|
||||
|
||||
static int propertyNameToInt(String name) {
|
||||
for (int i=0; i<propertyNames.length; i++) {
|
||||
if (propertyNames[i].equals(name)) {
|
||||
return 1 << i;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
||||
static String propertiesToString(int properties) {
|
||||
StringBuilder sb = new StringBuilder();
|
||||
boolean first=true;
|
||||
while (properties != 0) {
|
||||
if (!first) sb.append(',');
|
||||
first=false;
|
||||
int bitpos = Integer.numberOfTrailingZeros(properties);
|
||||
sb.append(getPropertyName(1 << bitpos));
|
||||
properties &= ~(1<<bitpos); // clear that bit position
|
||||
}
|
||||
return sb.toString();
|
||||
}
|
||||
|
||||
static boolean on(int bitfield, int props) {
|
||||
return (bitfield & props) != 0;
|
||||
}
|
||||
|
||||
static boolean off(int bitfield, int props) {
|
||||
return (bitfield & props) == 0;
|
||||
}
|
||||
|
||||
/***
|
||||
static int normalize(int properties) {
|
||||
int p = properties;
|
||||
if (on(p,TOKENIZED) && off(p,INDEXED)) {
|
||||
throw new RuntimeException("field must be indexed to be tokenized.");
|
||||
}
|
||||
|
||||
if (on(p,STORE_TERMPOSITIONS)) p|=STORE_TERMVECTORS;
|
||||
if (on(p,STORE_TERMOFFSETS)) p|=STORE_TERMVECTORS;
|
||||
if (on(p,STORE_TERMOFFSETS) && off(p,INDEXED)) {
|
||||
throw new RuntimeException("field must be indexed to store term vectors.");
|
||||
}
|
||||
|
||||
if (on(p,OMIT_NORMS) && off(p,INDEXED)) {
|
||||
throw new RuntimeException("field must be indexed for norms to be omitted.");
|
||||
}
|
||||
|
||||
if (on(p,SORT_MISSING_FIRST) && on(p,SORT_MISSING_LAST)) {
|
||||
throw new RuntimeException("conflicting options sortMissingFirst,sortMissingLast.");
|
||||
}
|
||||
|
||||
if ((on(p,SORT_MISSING_FIRST) || on(p,SORT_MISSING_LAST)) && off(p,INDEXED)) {
|
||||
throw new RuntimeException("field must be indexed to be sorted.");
|
||||
}
|
||||
|
||||
if ((on(p,BINARY) || on(p,COMPRESSED)) && off(p,STORED)) {
|
||||
throw new RuntimeException("field must be stored for compressed or binary options.");
|
||||
}
|
||||
|
||||
return p;
|
||||
}
|
||||
***/
|
||||
|
||||
|
||||
static int parseProperties(Map<String,String> properties, boolean which) {
|
||||
int props = 0;
|
||||
for (String prop : properties.keySet()) {
|
||||
if (propertyMap.get(prop)==null) continue;
|
||||
String val = properties.get(prop);
|
||||
if (Boolean.parseBoolean(val) == which) {
|
||||
props |= propertyNameToInt(prop);
|
||||
}
|
||||
}
|
||||
return props;
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,271 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.analysis.Analyzer;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.analysis.Tokenizer;
|
||||
import org.apache.lucene.analysis.Token;
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.OrdFieldSource;
|
||||
import org.apache.solr.search.Sorting;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.logging.Logger;
|
||||
import java.util.Map;
|
||||
import java.util.HashMap;
|
||||
import java.io.Reader;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* Base class for all field types used by an index schema.
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: FieldType.java,v 1.14 2006/01/06 04:23:15 yonik Exp $
|
||||
*/
|
||||
public abstract class FieldType extends FieldProperties {
|
||||
public static final Logger log = Logger.getLogger(FieldType.class.getName());
|
||||
|
||||
protected String typeName; // the name of the type, not the name of the field
|
||||
protected Map<String,String> args; // additional arguments
|
||||
protected int trueProperties; // properties explicitly set to true
|
||||
protected int falseProperties; // properties explicitly set to false
|
||||
int properties;
|
||||
|
||||
// these are common enough, they were moved to the base class to handle.
|
||||
// not all subclasses will be able to support these options.
|
||||
protected int positionIncrementGap;
|
||||
|
||||
protected boolean isTokenized() {
|
||||
return (properties & TOKENIZED) != 0;
|
||||
}
|
||||
|
||||
/** subclasses should initialize themselves with the args provided
|
||||
* and remove valid arguments. leftover arguments will cause an exception.
|
||||
* Common boolean properties have already been handled.
|
||||
*
|
||||
*/
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
}
|
||||
|
||||
// Handle additional arguments...
|
||||
void setArgs(IndexSchema schema, Map<String,String> args) {
|
||||
// default to STORED and INDEXED, and MULTIVALUED depending on schema version
|
||||
properties = (STORED | INDEXED);
|
||||
if (schema.getVersion()< 1.1f) properties |= MULTIVALUED;
|
||||
|
||||
this.args=args;
|
||||
Map<String,String> initArgs = new HashMap<String,String>(args);
|
||||
|
||||
String str;
|
||||
|
||||
str = initArgs.get("positionIncrementGap");
|
||||
if (str!=null) positionIncrementGap = Integer.parseInt(str);
|
||||
initArgs.remove("positionIncrementGap");
|
||||
|
||||
trueProperties = FieldProperties.parseProperties(initArgs,true);
|
||||
falseProperties = FieldProperties.parseProperties(initArgs,false);
|
||||
|
||||
properties &= ~falseProperties;
|
||||
properties |= trueProperties;
|
||||
|
||||
for (String prop : FieldProperties.propertyNames) initArgs.remove(prop);
|
||||
|
||||
init(schema, initArgs);
|
||||
|
||||
if (initArgs.size() > 0) {
|
||||
throw new RuntimeException("schema fieldtype " + typeName
|
||||
+ "("+ this.getClass().getName() + ")"
|
||||
+ " invalid arguments:" + initArgs);
|
||||
}
|
||||
}
|
||||
|
||||
protected void restrictProps(int props) {
|
||||
if ((properties & props) != 0) {
|
||||
throw new RuntimeException("schema fieldtype " + typeName
|
||||
+ "("+ this.getClass().getName() + ")"
|
||||
+ " invalid properties:" + propertiesToString(properties & props));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public String getTypeName() {
|
||||
return typeName;
|
||||
}
|
||||
|
||||
void setTypeName(String typeName) {
|
||||
this.typeName = typeName;
|
||||
}
|
||||
|
||||
public String toString() {
|
||||
return typeName + "{class=" + this.getClass().getName()
|
||||
// + propertiesToString(properties)
|
||||
+ (analyzer != null ? ",analyzer=" + analyzer.getClass().getName() : "")
|
||||
+ ",args=" + args
|
||||
+"}";
|
||||
}
|
||||
|
||||
|
||||
// used for adding a document when a field needs to be created from a type and a string
|
||||
// by default, the indexed value is the same as the stored value (taken from toInternal())
|
||||
// Having a different representation for external, internal, and indexed would present quite
|
||||
// a few problems given the current Lucene architecture. An analyzer for adding docs would
|
||||
// need to translate internal->indexed while an analyzer for querying would need to
|
||||
// translate external->indexed.
|
||||
//
|
||||
// The only other alternative to having internal==indexed would be to have
|
||||
// internal==external.
|
||||
// In this case, toInternal should convert to the indexed representation,
|
||||
// toExternal() should do nothing, and createField() should *not* call toInternal,
|
||||
// but use the external value and set tokenized=true to get Lucene to convert
|
||||
// to the internal(indexed) form.
|
||||
public Field createField(SchemaField field, String externalVal, float boost) {
|
||||
String val = toInternal(externalVal);
|
||||
if (val==null) return null;
|
||||
Field f = new Field(field.getName(), val, field.stored(), field.indexed(), isTokenized());
|
||||
f.setOmitNorms(field.omitNorms());
|
||||
f.setBoost(boost);
|
||||
return f;
|
||||
}
|
||||
|
||||
|
||||
// Convert an external value (from XML update command or from query string)
|
||||
// into the internal format.
|
||||
// - used in delete when a Term needs to be created.
|
||||
// - used by the default getTokenizer() and createField()
|
||||
public String toInternal(String val) {
|
||||
return val;
|
||||
}
|
||||
|
||||
// Convert the stored-field format to an external (string, human readable) value
|
||||
// currently used in writing XML of the search result (but perhaps
|
||||
// a more efficient toXML(Field f, Writer w) should be used
|
||||
// in the future.
|
||||
public String toExternal(Field f) {
|
||||
return f.stringValue();
|
||||
}
|
||||
|
||||
|
||||
public String indexedToReadable(String indexedForm) {
|
||||
return indexedForm;
|
||||
}
|
||||
|
||||
|
||||
/*********
|
||||
// default analyzer for non-text fields.
|
||||
// Only reads 80 bytes, but that should be plenty for a single value.
|
||||
public Analyzer getAnalyzer() {
|
||||
if (analyzer != null) return analyzer;
|
||||
|
||||
// the default analyzer...
|
||||
return new Analyzer() {
|
||||
public TokenStream tokenStream(String fieldName, Reader reader) {
|
||||
return new Tokenizer(reader) {
|
||||
final char[] cbuf = new char[80];
|
||||
public Token next() throws IOException {
|
||||
int n = input.read(cbuf,0,80);
|
||||
if (n<=0) return null;
|
||||
String s = toInternal(new String(cbuf,0,n));
|
||||
return new Token(s,0,n);
|
||||
};
|
||||
};
|
||||
}
|
||||
};
|
||||
}
|
||||
**********/
|
||||
|
||||
|
||||
//
|
||||
// Default analyzer for types that only produce 1 verbatim token...
|
||||
// A maximum size of chars to be read must be specified
|
||||
//
|
||||
protected final class DefaultAnalyzer extends Analyzer {
|
||||
final int maxChars;
|
||||
|
||||
DefaultAnalyzer(int maxChars) {
|
||||
this.maxChars=maxChars;
|
||||
}
|
||||
|
||||
public TokenStream tokenStream(String fieldName, Reader reader) {
|
||||
return new Tokenizer(reader) {
|
||||
char[] cbuf = new char[maxChars];
|
||||
public Token next() throws IOException {
|
||||
int n = input.read(cbuf,0,maxChars);
|
||||
if (n<=0) return null;
|
||||
String s = toInternal(new String(cbuf,0,n)); // virtual func on parent
|
||||
return new Token(s,0,n);
|
||||
};
|
||||
};
|
||||
}
|
||||
|
||||
public int getPositionIncrementGap(String fieldName) {
|
||||
return positionIncrementGap;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
//analyzer set by schema for text types.
|
||||
//subclasses can set analyzer themselves or override getAnalyzer()
|
||||
protected Analyzer analyzer=new DefaultAnalyzer(256);
|
||||
protected Analyzer queryAnalyzer=analyzer;
|
||||
|
||||
// get analyzer should be fast to call... since the addition of dynamic fields,
|
||||
// this can be called all the time instead of just once at startup.
|
||||
// The analyzer will only be used in the following scenarios:
|
||||
// - during a document add for any field that has "tokenized" set (typically
|
||||
// only Text fields)
|
||||
// - during query parsing
|
||||
|
||||
public Analyzer getAnalyzer() {
|
||||
return analyzer;
|
||||
}
|
||||
|
||||
public Analyzer getQueryAnalyzer() {
|
||||
return queryAnalyzer;
|
||||
}
|
||||
|
||||
// This is called by the schema parser if a custom analyzer is defined
|
||||
public void setAnalyzer(Analyzer analyzer) {
|
||||
this.analyzer = analyzer;
|
||||
log.finest("FieldType: " + typeName + ".setAnalyzer(" + analyzer.getClass().getName() + ")" );
|
||||
}
|
||||
|
||||
// This is called by the schema parser if a custom analyzer is defined
|
||||
public void setQueryAnalyzer(Analyzer analyzer) {
|
||||
this.queryAnalyzer = analyzer;
|
||||
log.finest("FieldType: " + typeName + ".setQueryAnalyzer(" + analyzer.getClass().getName() + ")" );
|
||||
}
|
||||
|
||||
|
||||
public abstract void write(XMLWriter xmlWriter, String name, Field f) throws IOException;
|
||||
|
||||
|
||||
public abstract SortField getSortField(SchemaField field, boolean top);
|
||||
|
||||
protected SortField getStringSort(SchemaField field, boolean reverse) {
|
||||
return Sorting.getStringSortField(field.name, reverse, field.sortMissingLast(),field.sortMissingFirst());
|
||||
}
|
||||
|
||||
/** called to get the default value source (normally, from the
|
||||
* Lucene FieldCache.)
|
||||
*/
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
return new OrdFieldSource(field.name);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,48 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.FloatFieldSource;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class FloatField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
restrictProps(SORT_MISSING_FIRST | SORT_MISSING_LAST);
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return new SortField(field.name,SortField.FLOAT, reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
return new FloatFieldSource(field.name);
|
||||
}
|
||||
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeFloat(name, f.stringValue());
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,542 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.analysis.Analyzer;
|
||||
import org.apache.lucene.analysis.TokenStream;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.search.DefaultSimilarity;
|
||||
import org.apache.lucene.search.Similarity;
|
||||
import org.apache.solr.core.SolrException;
|
||||
import org.apache.solr.core.Config;
|
||||
import org.apache.solr.analysis.TokenFilterFactory;
|
||||
import org.apache.solr.analysis.TokenizerChain;
|
||||
import org.apache.solr.analysis.TokenizerFactory;
|
||||
import org.apache.solr.util.DOMUtil;
|
||||
import org.w3c.dom.Document;
|
||||
import org.w3c.dom.NamedNodeMap;
|
||||
import org.w3c.dom.Node;
|
||||
import org.w3c.dom.NodeList;
|
||||
|
||||
import javax.xml.xpath.XPath;
|
||||
import javax.xml.xpath.XPathConstants;
|
||||
import javax.xml.xpath.XPathExpressionException;
|
||||
import javax.xml.xpath.XPathFactory;
|
||||
import java.io.InputStream;
|
||||
import java.io.Reader;
|
||||
import java.util.*;
|
||||
import java.util.logging.Logger;
|
||||
|
||||
/**
|
||||
* <code>IndexSchema</code> contains information about the valid fields in an index
|
||||
* and the types of those fields.
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: IndexSchema.java,v 1.21 2005/12/20 16:05:46 yonik Exp $
|
||||
*/
|
||||
|
||||
public final class IndexSchema {
|
||||
final static Logger log = Logger.getLogger(IndexSchema.class.getName());
|
||||
|
||||
private final String schemaFile;
|
||||
private String name;
|
||||
private float version;
|
||||
|
||||
public IndexSchema(String schemaFile) {
|
||||
this.schemaFile=schemaFile;
|
||||
readConfig();
|
||||
}
|
||||
|
||||
public InputStream getInputStream() {
|
||||
return Config.openResource(schemaFile);
|
||||
}
|
||||
|
||||
|
||||
float getVersion() {
|
||||
return version;
|
||||
}
|
||||
|
||||
public String getName() { return name; }
|
||||
|
||||
private final HashMap<String, SchemaField> fields = new HashMap<String,SchemaField>();
|
||||
private final HashMap<String, FieldType> fieldTypes = new HashMap<String,FieldType>();
|
||||
|
||||
public Map<String,SchemaField> getFields() { return fields; }
|
||||
public Map<String,FieldType> getFieldTypes() { return fieldTypes; }
|
||||
|
||||
|
||||
private Similarity similarity;
|
||||
public Similarity getSimilarity() { return similarity; }
|
||||
|
||||
private Analyzer analyzer;
|
||||
public Analyzer getAnalyzer() { return analyzer; }
|
||||
|
||||
private Analyzer queryAnalyzer;
|
||||
public Analyzer getQueryAnalyzer() { return queryAnalyzer; }
|
||||
|
||||
private String defaultSearchFieldName=null;
|
||||
public String getDefaultSearchFieldName() {
|
||||
return defaultSearchFieldName;
|
||||
}
|
||||
|
||||
private SchemaField uniqueKeyField;
|
||||
public SchemaField getUniqueKeyField() { return uniqueKeyField; }
|
||||
|
||||
private String uniqueKeyFieldName;
|
||||
private FieldType uniqueKeyFieldType;
|
||||
|
||||
public Field getUniqueKeyField(org.apache.lucene.document.Document doc) {
|
||||
return doc.getField(uniqueKeyFieldName); // this should return null if name is null
|
||||
}
|
||||
|
||||
public String printableUniqueKey(org.apache.lucene.document.Document doc) {
|
||||
Field f = doc.getField(uniqueKeyFieldName);
|
||||
return f==null ? null : uniqueKeyFieldType.toExternal(f);
|
||||
}
|
||||
|
||||
private SchemaField getIndexedField(String fname) {
|
||||
SchemaField f = getFields().get(fname);
|
||||
if (f==null) {
|
||||
throw new RuntimeException("unknown field '" + fname + "'");
|
||||
}
|
||||
if (!f.indexed()) {
|
||||
throw new RuntimeException("'"+fname+"' is not an indexed field:" + f);
|
||||
}
|
||||
return f;
|
||||
}
|
||||
|
||||
|
||||
|
||||
private class SolrAnalyzer extends Analyzer {
|
||||
protected final HashMap<String,Analyzer> analyzers;
|
||||
|
||||
SolrAnalyzer() {
|
||||
analyzers = analyzerCache();
|
||||
}
|
||||
|
||||
protected HashMap<String,Analyzer> analyzerCache() {
|
||||
HashMap<String,Analyzer> cache = new HashMap<String,Analyzer>();
|
||||
for (SchemaField f : getFields().values()) {
|
||||
Analyzer analyzer = f.getType().getAnalyzer();
|
||||
cache.put(f.getName(), analyzer);
|
||||
}
|
||||
return cache;
|
||||
}
|
||||
|
||||
protected Analyzer getAnalyzer(String fieldName)
|
||||
{
|
||||
Analyzer analyzer = analyzers.get(fieldName);
|
||||
return analyzer!=null ? analyzer : getDynamicFieldType(fieldName).getAnalyzer();
|
||||
}
|
||||
|
||||
public TokenStream tokenStream(String fieldName, Reader reader)
|
||||
{
|
||||
return getAnalyzer(fieldName).tokenStream(fieldName,reader);
|
||||
}
|
||||
|
||||
public int getPositionIncrementGap(String fieldName) {
|
||||
return getAnalyzer(fieldName).getPositionIncrementGap(fieldName);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
private class SolrQueryAnalyzer extends SolrAnalyzer {
|
||||
protected HashMap<String,Analyzer> analyzerCache() {
|
||||
HashMap<String,Analyzer> cache = new HashMap<String,Analyzer>();
|
||||
for (SchemaField f : getFields().values()) {
|
||||
Analyzer analyzer = f.getType().getQueryAnalyzer();
|
||||
cache.put(f.getName(), analyzer);
|
||||
}
|
||||
return cache;
|
||||
}
|
||||
|
||||
protected Analyzer getAnalyzer(String fieldName)
|
||||
{
|
||||
Analyzer analyzer = analyzers.get(fieldName);
|
||||
return analyzer!=null ? analyzer : getDynamicFieldType(fieldName).getQueryAnalyzer();
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
private void readConfig() {
|
||||
log.info("Reading Solr Schema");
|
||||
|
||||
try {
|
||||
/***
|
||||
DocumentBuilder builder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
|
||||
Document document = builder.parse(getInputStream());
|
||||
***/
|
||||
|
||||
Config config = new Config("schema", getInputStream(), "/schema/");
|
||||
Document document = config.getDocument();
|
||||
XPath xpath = config.getXPath();
|
||||
|
||||
Node nd = (Node) xpath.evaluate("/schema/@name", document, XPathConstants.NODE);
|
||||
if (nd==null) {
|
||||
log.warning("schema has no name!");
|
||||
} else {
|
||||
name = nd.getNodeValue();
|
||||
log.info("Schema name=" + name);
|
||||
}
|
||||
|
||||
version = config.getFloat("/schema/@version", 1.0f);
|
||||
|
||||
String expression = "/schema/types/fieldtype";
|
||||
NodeList nodes = (NodeList) xpath.evaluate(expression, document, XPathConstants.NODESET);
|
||||
|
||||
|
||||
for (int i=0; i<nodes.getLength(); i++) {
|
||||
Node node = nodes.item(i);
|
||||
NamedNodeMap attrs = node.getAttributes();
|
||||
|
||||
String name = DOMUtil.getAttr(attrs,"name","fieldtype error");
|
||||
log.finest("reading fieldtype "+name);
|
||||
String clsName = DOMUtil.getAttr(attrs,"class", "fieldtype error");
|
||||
FieldType ft = (FieldType)Config.newInstance(clsName);
|
||||
ft.setTypeName(name);
|
||||
|
||||
expression = "./analyzer[@type='query']";
|
||||
Node anode = (Node)xpath.evaluate(expression, node, XPathConstants.NODE);
|
||||
Analyzer queryAnalyzer = readAnalyzer(anode);
|
||||
|
||||
// An analyzer without a type specified, or with type="index"
|
||||
expression = "./analyzer[not(@type)] | ./analyzer[@type='index']";
|
||||
anode = (Node)xpath.evaluate(expression, node, XPathConstants.NODE);
|
||||
Analyzer analyzer = readAnalyzer(anode);
|
||||
|
||||
if (queryAnalyzer==null) queryAnalyzer=analyzer;
|
||||
if (analyzer==null) analyzer=queryAnalyzer;
|
||||
if (analyzer!=null) {
|
||||
ft.setAnalyzer(analyzer);
|
||||
ft.setQueryAnalyzer(queryAnalyzer);
|
||||
}
|
||||
|
||||
|
||||
ft.setArgs(this, DOMUtil.toMapExcept(attrs,"name","class"));
|
||||
fieldTypes.put(ft.typeName,ft);
|
||||
log.finest("fieldtype defined: " + ft);
|
||||
}
|
||||
|
||||
|
||||
ArrayList<DynamicField> dFields = new ArrayList<DynamicField>();
|
||||
expression = "/schema/fields/field | /schema/fields/dynamicField";
|
||||
nodes = (NodeList) xpath.evaluate(expression, document, XPathConstants.NODESET);
|
||||
|
||||
for (int i=0; i<nodes.getLength(); i++) {
|
||||
Node node = nodes.item(i);
|
||||
|
||||
NamedNodeMap attrs = node.getAttributes();
|
||||
|
||||
String name = DOMUtil.getAttr(attrs,"name","field definition");
|
||||
log.finest("reading field def "+name);
|
||||
String type = DOMUtil.getAttr(attrs,"type","field " + name);
|
||||
String val;
|
||||
|
||||
FieldType ft = fieldTypes.get(type);
|
||||
if (ft==null) {
|
||||
throw new SolrException(400,"Unknown fieldtype '" + type + "'",false);
|
||||
}
|
||||
|
||||
Map<String,String> args = DOMUtil.toMapExcept(attrs, "name", "type");
|
||||
|
||||
SchemaField f = SchemaField.create(name,ft,args);
|
||||
|
||||
if (node.getNodeName().equals("field")) {
|
||||
fields.put(f.getName(),f);
|
||||
log.fine("field defined: " + f);
|
||||
} else if (node.getNodeName().equals("dynamicField")) {
|
||||
dFields.add(new DynamicField(f));
|
||||
log.fine("dynamic field defined: " + f);
|
||||
} else {
|
||||
// we should never get here
|
||||
throw new RuntimeException("Unknown field type");
|
||||
}
|
||||
}
|
||||
|
||||
// OK, now sort the dynamic fields largest to smallest size so we don't get
|
||||
// any false matches. We want to act like a compiler tool and try and match
|
||||
// the largest string possible.
|
||||
Collections.sort(dFields, new Comparator<DynamicField>() {
|
||||
public int compare(DynamicField a, DynamicField b) {
|
||||
// swap natural ordering to get biggest first.
|
||||
// The sort is stable, so elements of the same size should
|
||||
// be
|
||||
if (a.regex.length() < b.regex.length()) return 1;
|
||||
else if (a.regex.length() > b.regex.length()) return -1;
|
||||
return 0;
|
||||
}
|
||||
}
|
||||
);
|
||||
|
||||
log.finest("Dynamic Field Ordering:" + dFields);
|
||||
|
||||
// stuff it in a normal array for faster access
|
||||
dynamicFields = (DynamicField[])dFields.toArray(new DynamicField[dFields.size()]);
|
||||
|
||||
|
||||
Node node = (Node) xpath.evaluate("/schema/similarity/@class", document, XPathConstants.NODE);
|
||||
if (node==null) {
|
||||
similarity = new DefaultSimilarity();
|
||||
log.fine("using default similarity");
|
||||
} else {
|
||||
similarity = (Similarity)Config.newInstance(node.getNodeValue().trim());
|
||||
log.fine("using similarity " + similarity.getClass().getName());
|
||||
}
|
||||
|
||||
node = (Node) xpath.evaluate("/schema/defaultSearchField/text()", document, XPathConstants.NODE);
|
||||
if (node==null) {
|
||||
log.warning("no default search field specified in schema.");
|
||||
} else {
|
||||
String defName=node.getNodeValue().trim();
|
||||
defaultSearchFieldName = getIndexedField(defName)!=null ? defName : null;
|
||||
log.info("default search field is "+defName);
|
||||
}
|
||||
|
||||
node = (Node) xpath.evaluate("/schema/uniqueKey/text()", document, XPathConstants.NODE);
|
||||
if (node==null) {
|
||||
log.warning("no uniqueKey specified in schema.");
|
||||
} else {
|
||||
uniqueKeyField=getIndexedField(node.getNodeValue().trim());
|
||||
uniqueKeyFieldName=uniqueKeyField.getName();
|
||||
uniqueKeyFieldType=uniqueKeyField.getType();
|
||||
log.info("unique key field: "+uniqueKeyFieldName);
|
||||
}
|
||||
|
||||
/////////////// parse out copyField commands ///////////////
|
||||
// Map<String,ArrayList<SchemaField>> cfields = new HashMap<String,ArrayList<SchemaField>>();
|
||||
// expression = "/schema/copyField";
|
||||
expression = "//copyField";
|
||||
nodes = (NodeList) xpath.evaluate(expression, document, XPathConstants.NODESET);
|
||||
|
||||
for (int i=0; i<nodes.getLength(); i++) {
|
||||
node = nodes.item(i);
|
||||
NamedNodeMap attrs = node.getAttributes();
|
||||
|
||||
String source = DOMUtil.getAttr(attrs,"source","copyField definition");
|
||||
String dest = DOMUtil.getAttr(attrs,"dest","copyField definition");
|
||||
log.fine("copyField source='"+source+"' dest='"+dest+"'");
|
||||
SchemaField f = getField(source);
|
||||
SchemaField d = getField(dest);
|
||||
SchemaField[] destArr = copyFields.get(source);
|
||||
if (destArr==null) {
|
||||
destArr=new SchemaField[]{d};
|
||||
} else {
|
||||
destArr = (SchemaField[])append(destArr,d);
|
||||
}
|
||||
copyFields.put(source,destArr);
|
||||
}
|
||||
|
||||
|
||||
} catch (SolrException e) {
|
||||
throw e;
|
||||
} catch(Exception e) {
|
||||
// unexpected exception...
|
||||
throw new SolrException(1,"Schema Parsing Failed",e,false);
|
||||
}
|
||||
|
||||
analyzer = new SolrAnalyzer();
|
||||
queryAnalyzer = new SolrQueryAnalyzer();
|
||||
}
|
||||
|
||||
private static Object[] append(Object[] orig, Object item) {
|
||||
Object[] newArr = (Object[])java.lang.reflect.Array.newInstance(orig.getClass().getComponentType(), orig.length+1);
|
||||
System.arraycopy(orig, 0, newArr, 0, orig.length);
|
||||
newArr[orig.length] = item;
|
||||
return newArr;
|
||||
}
|
||||
|
||||
//
|
||||
// <analyzer><tokenizer class="...."/><tokenizer class="...." arg="....">
|
||||
//
|
||||
//
|
||||
private Analyzer readAnalyzer(Node node) throws XPathExpressionException {
|
||||
// parent node used to be passed in as "fieldtype"
|
||||
// if (!fieldtype.hasChildNodes()) return null;
|
||||
// Node node = DOMUtil.getChild(fieldtype,"analyzer");
|
||||
|
||||
if (node == null) return null;
|
||||
NamedNodeMap attrs = node.getAttributes();
|
||||
String analyzerName = DOMUtil.getAttr(attrs,"class");
|
||||
if (analyzerName != null) {
|
||||
return (Analyzer)Config.newInstance(analyzerName);
|
||||
}
|
||||
|
||||
XPath xpath = XPathFactory.newInstance().newXPath();
|
||||
Node tokNode = (Node)xpath.evaluate("./tokenizer", node, XPathConstants.NODE);
|
||||
NodeList nList = (NodeList)xpath.evaluate("./filter", node, XPathConstants.NODESET);
|
||||
|
||||
if (tokNode==null){
|
||||
throw new SolrException(1,"analyzer without class or tokenizer & filter list");
|
||||
}
|
||||
TokenizerFactory tfac = readTokenizerFactory(tokNode);
|
||||
|
||||
/******
|
||||
// oops, getChildNodes() includes text (newlines, etc) in addition
|
||||
// to the actual child elements
|
||||
NodeList nList = node.getChildNodes();
|
||||
TokenizerFactory tfac = readTokenizerFactory(nList.item(0));
|
||||
if (tfac==null) {
|
||||
throw new SolrException(1,"TokenizerFactory must be specified first in analyzer");
|
||||
}
|
||||
******/
|
||||
|
||||
ArrayList<TokenFilterFactory> filters = new ArrayList<TokenFilterFactory>();
|
||||
for (int i=0; i<nList.getLength(); i++) {
|
||||
TokenFilterFactory filt = readTokenFilterFactory(nList.item(i));
|
||||
if (filt != null) filters.add(filt);
|
||||
}
|
||||
|
||||
return new TokenizerChain(tfac, filters.toArray(new TokenFilterFactory[filters.size()]));
|
||||
};
|
||||
|
||||
// <tokenizer class="solr.StandardFilterFactory"/>
|
||||
private TokenizerFactory readTokenizerFactory(Node node) {
|
||||
// if (node.getNodeName() != "tokenizer") return null;
|
||||
NamedNodeMap attrs = node.getAttributes();
|
||||
String className = DOMUtil.getAttr(attrs,"class","tokenizer");
|
||||
TokenizerFactory tfac = (TokenizerFactory)Config.newInstance(className);
|
||||
tfac.init(DOMUtil.toMapExcept(attrs,"class"));
|
||||
return tfac;
|
||||
}
|
||||
|
||||
// <tokenizer class="solr.StandardFilterFactory"/>
|
||||
private TokenFilterFactory readTokenFilterFactory(Node node) {
|
||||
// if (node.getNodeName() != "filter") return null;
|
||||
NamedNodeMap attrs = node.getAttributes();
|
||||
String className = DOMUtil.getAttr(attrs,"class","token filter");
|
||||
TokenFilterFactory tfac = (TokenFilterFactory)Config.newInstance(className);
|
||||
tfac.init(DOMUtil.toMapExcept(attrs,"class"));
|
||||
return tfac;
|
||||
}
|
||||
|
||||
|
||||
//
|
||||
// Instead of storing a type, this could be implemented as a hierarchy
|
||||
// with a virtual matches().
|
||||
// Given how often a search will be done, however, speed is the overriding
|
||||
// concern and I'm not sure which is faster.
|
||||
//
|
||||
final static class DynamicField {
|
||||
final static int STARTS_WITH=1;
|
||||
final static int ENDS_WITH=2;
|
||||
|
||||
final String regex;
|
||||
final int type;
|
||||
final SchemaField prototype;
|
||||
|
||||
final String str;
|
||||
|
||||
DynamicField(SchemaField prototype) {
|
||||
this.regex=prototype.name;
|
||||
if (regex.startsWith("*")) {
|
||||
type=ENDS_WITH;
|
||||
str=regex.substring(1);
|
||||
}
|
||||
else if (regex.endsWith("*")) {
|
||||
type=STARTS_WITH;
|
||||
str=regex.substring(0,regex.length()-1);
|
||||
}
|
||||
else {
|
||||
throw new RuntimeException("dynamic field name must start or end with *");
|
||||
}
|
||||
this.prototype=prototype;
|
||||
}
|
||||
|
||||
boolean matches(String name) {
|
||||
if (type==STARTS_WITH && name.startsWith(str)) return true;
|
||||
else if (type==ENDS_WITH && name.endsWith(str)) return true;
|
||||
else return false;
|
||||
}
|
||||
|
||||
SchemaField makeSchemaField(String name) {
|
||||
// could have a cache instead of returning a new one each time, but it might
|
||||
// not be worth it.
|
||||
// Actually, a higher level cache could be worth it to avoid too many
|
||||
// .startsWith() and .endsWith() comparisons. it depends on how many
|
||||
// dynamic fields there are.
|
||||
return new SchemaField(prototype, name);
|
||||
}
|
||||
|
||||
public String toString() {
|
||||
return prototype.toString();
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
private DynamicField[] dynamicFields;
|
||||
|
||||
|
||||
// get a field, and if not statically defined, check dynamic fields.
|
||||
public SchemaField getField(String fieldName) {
|
||||
SchemaField f = fields.get(fieldName);
|
||||
if (f != null) return f;
|
||||
|
||||
for (DynamicField df : dynamicFields) {
|
||||
if (df.matches(fieldName)) return df.makeSchemaField(fieldName);
|
||||
}
|
||||
|
||||
// Hmmm, default field could also be implemented with a dynamic field of "*".
|
||||
// It would have to be special-cased and only used if nothing else matched.
|
||||
/*** REMOVED -YCS
|
||||
if (defaultFieldType != null) return new SchemaField(fieldName,defaultFieldType);
|
||||
***/
|
||||
throw new SolrException(1,"undefined field "+fieldName);
|
||||
}
|
||||
|
||||
// This method exists because it can be more efficient for dynamic fields
|
||||
// if a full SchemaField isn't needed.
|
||||
public FieldType getFieldType(String fieldName) {
|
||||
SchemaField f = fields.get(fieldName);
|
||||
if (f != null) return f.getType();
|
||||
|
||||
return getDynamicFieldType(fieldName);
|
||||
}
|
||||
|
||||
/**
|
||||
* return null instead of throwing an exception if
|
||||
* the field is undefined.
|
||||
*/
|
||||
public FieldType getFieldTypeNoEx(String fieldName) {
|
||||
SchemaField f = fields.get(fieldName);
|
||||
if (f != null) return f.getType();
|
||||
return dynFieldType(fieldName);
|
||||
}
|
||||
|
||||
|
||||
public FieldType getDynamicFieldType(String fieldName) {
|
||||
for (DynamicField df : dynamicFields) {
|
||||
if (df.matches(fieldName)) return df.prototype.getType();
|
||||
}
|
||||
throw new SolrException(400,"undefined field "+fieldName);
|
||||
}
|
||||
|
||||
private FieldType dynFieldType(String fieldName) {
|
||||
for (DynamicField df : dynamicFields) {
|
||||
if (df.matches(fieldName)) return df.prototype.getType();
|
||||
}
|
||||
return null;
|
||||
};
|
||||
|
||||
|
||||
private final Map<String, SchemaField[]> copyFields = new HashMap<String,SchemaField[]>();
|
||||
public SchemaField[] getCopyFields(String sourceField) {
|
||||
return copyFields.get(sourceField);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,47 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.IntFieldSource;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class IntField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
restrictProps(SORT_MISSING_FIRST | SORT_MISSING_LAST);
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return new SortField(field.name,SortField.INT, reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
return new IntFieldSource(field.name);
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeInt(name, f.stringValue());
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,52 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.IntFieldSource;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class LongField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
restrictProps(SORT_MISSING_FIRST | SORT_MISSING_LAST);
|
||||
}
|
||||
|
||||
/////////////////////////////////////////////////////////////
|
||||
// TODO: ACK.. there is no SortField.LONG!
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
// todo - log warning
|
||||
return new SortField(field.name,SortField.INT, reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
// todo - log warning
|
||||
return new IntFieldSource(field.name);
|
||||
}
|
||||
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeLong(name, f.stringValue());
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,159 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: SchemaField.java,v 1.8 2005/11/28 06:03:19 yonik Exp $
|
||||
*/
|
||||
|
||||
|
||||
|
||||
public final class SchemaField extends FieldProperties {
|
||||
final String name;
|
||||
final FieldType type;
|
||||
final int properties;
|
||||
|
||||
|
||||
/** Create a new SchemaField with the given name and type,
|
||||
* using all the default properties from the type.
|
||||
*/
|
||||
public SchemaField(String name, FieldType type) {
|
||||
this(name, type, type.properties);
|
||||
}
|
||||
|
||||
/** Create a new SchemaField from an existing one by using all
|
||||
* of the properties of the prototype except the field name.
|
||||
*/
|
||||
public SchemaField(SchemaField prototype, String name) {
|
||||
this(name, prototype.type, prototype.properties);
|
||||
}
|
||||
|
||||
/** Create a new SchemaField with the given name and type,
|
||||
* and with the specified properties. Properties are *not*
|
||||
* inherited from the type in this case, so users of this
|
||||
* constructor should derive the properties from type.getProperties()
|
||||
* using all the default properties from the type.
|
||||
*/
|
||||
public SchemaField(String name, FieldType type, int properties) {
|
||||
this.name = name;
|
||||
this.type = type;
|
||||
this.properties = properties;
|
||||
}
|
||||
|
||||
public String getName() { return name; }
|
||||
public FieldType getType() { return type; }
|
||||
int getProperties() { return properties; }
|
||||
|
||||
public boolean indexed() { return (properties & INDEXED)!=0; }
|
||||
public boolean stored() { return (properties & STORED)!=0; }
|
||||
public boolean storeTermVector() { return (properties & STORE_TERMVECTORS)!=0; }
|
||||
public boolean storeTermPositions() { return (properties & STORE_TERMPOSITIONS)!=0; }
|
||||
public boolean storeTermOffsets() { return (properties & STORE_TERMOFFSETS)!=0; }
|
||||
public boolean omitNorms() { return (properties & OMIT_NORMS)!=0; }
|
||||
public boolean multiValued() { return (properties & MULTIVALUED)!=0; }
|
||||
public boolean sortMissingFirst() { return (properties & SORT_MISSING_FIRST)!=0; }
|
||||
public boolean sortMissingLast() { return (properties & SORT_MISSING_LAST)!=0; }
|
||||
|
||||
// things that should be determined by field type, not set as options
|
||||
boolean isTokenized() { return (properties & TOKENIZED)!=0; }
|
||||
boolean isBinary() { return (properties & BINARY)!=0; }
|
||||
boolean isCompressed() { return (properties & COMPRESSED)!=0; }
|
||||
|
||||
public Field createField(String val, float boost) {
|
||||
return type.createField(this,val,boost);
|
||||
}
|
||||
|
||||
public String toString() {
|
||||
return name + "{type="+type.getTypeName()
|
||||
+ ",properties=" + propertiesToString(properties)
|
||||
+ "}";
|
||||
}
|
||||
|
||||
public void write(XMLWriter writer, String name, Field val) throws IOException {
|
||||
// name is passed in because it may be null if name should not be used.
|
||||
type.write(writer,name,val);
|
||||
}
|
||||
|
||||
public SortField getSortField(boolean top) {
|
||||
return type.getSortField(this, top);
|
||||
}
|
||||
|
||||
|
||||
static SchemaField create(String name, FieldType ft, Map props) {
|
||||
int trueProps = parseProperties(props,true);
|
||||
int falseProps = parseProperties(props,false);
|
||||
|
||||
int p = ft.properties;
|
||||
|
||||
//
|
||||
// If any properties were explicitly turned off, then turn off other properties
|
||||
// that depend on that.
|
||||
//
|
||||
if (on(falseProps,STORED)) {
|
||||
int pp = STORED | BINARY | COMPRESSED;
|
||||
if (on(pp,trueProps)) {
|
||||
throw new RuntimeException("SchemaField: " + name + " conflicting stored field options:" + props);
|
||||
}
|
||||
p &= ~pp;
|
||||
}
|
||||
|
||||
if (on(falseProps,INDEXED)) {
|
||||
int pp = (INDEXED | OMIT_NORMS
|
||||
| STORE_TERMVECTORS | STORE_TERMPOSITIONS | STORE_TERMOFFSETS
|
||||
| SORT_MISSING_FIRST | SORT_MISSING_LAST);
|
||||
if (on(pp,trueProps)) {
|
||||
throw new RuntimeException("SchemaField: " + name + " conflicting indexed field options:" + props);
|
||||
}
|
||||
p &= ~pp;
|
||||
|
||||
}
|
||||
|
||||
if (on(falseProps,STORE_TERMVECTORS)) {
|
||||
int pp = (STORE_TERMVECTORS | STORE_TERMPOSITIONS | STORE_TERMOFFSETS);
|
||||
if (on(pp,trueProps)) {
|
||||
throw new RuntimeException("SchemaField: " + name + " conflicting termvector field options:" + props);
|
||||
}
|
||||
p &= ~pp;
|
||||
}
|
||||
|
||||
// override sort flags
|
||||
if (on(trueProps,SORT_MISSING_FIRST)) {
|
||||
p &= ~SORT_MISSING_LAST;
|
||||
}
|
||||
|
||||
if (on(trueProps,SORT_MISSING_LAST)) {
|
||||
p &= ~SORT_MISSING_FIRST;
|
||||
}
|
||||
|
||||
p &= ~falseProps;
|
||||
p |= trueProps;
|
||||
|
||||
return new SchemaField(name, ft, p);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,132 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.FieldCache;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.FieldCacheSource;
|
||||
import org.apache.lucene.search.function.DocValues;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.index.IndexReader;
|
||||
import org.apache.solr.util.NumberUtils;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class SortableDoubleField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return getStringSort(field,reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
return new SortableDoubleFieldSource(field.name);
|
||||
}
|
||||
|
||||
public String toInternal(String val) {
|
||||
return NumberUtils.double2sortableStr(val);
|
||||
}
|
||||
|
||||
public String toExternal(Field f) {
|
||||
return indexedToReadable(f.stringValue());
|
||||
}
|
||||
|
||||
public String indexedToReadable(String indexedForm) {
|
||||
return NumberUtils.SortableStr2doubleStr(indexedForm);
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
String sval = f.stringValue();
|
||||
xmlWriter.writeDouble(name, NumberUtils.SortableStr2double(sval));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
class SortableDoubleFieldSource extends FieldCacheSource {
|
||||
protected double defVal;
|
||||
|
||||
public SortableDoubleFieldSource(String field) {
|
||||
this(field, 0.0);
|
||||
}
|
||||
|
||||
public SortableDoubleFieldSource(String field, double defVal) {
|
||||
super(field);
|
||||
this.defVal = defVal;
|
||||
}
|
||||
|
||||
public String description() {
|
||||
return "sdouble(" + field + ')';
|
||||
}
|
||||
|
||||
public DocValues getValues(IndexReader reader) throws IOException {
|
||||
final FieldCache.StringIndex index = cache.getStringIndex(reader, field);
|
||||
final int[] order = index.order;
|
||||
final String[] lookup = index.lookup;
|
||||
final double def = defVal;
|
||||
|
||||
return new DocValues() {
|
||||
public float floatVal(int doc) {
|
||||
return (float)doubleVal(doc);
|
||||
}
|
||||
|
||||
public int intVal(int doc) {
|
||||
return (int)doubleVal(doc);
|
||||
}
|
||||
|
||||
public long longVal(int doc) {
|
||||
return (long)doubleVal(doc);
|
||||
}
|
||||
|
||||
public double doubleVal(int doc) {
|
||||
int ord=order[doc];
|
||||
return ord==0 ? def : NumberUtils.SortableStr2double(lookup[ord]);
|
||||
}
|
||||
|
||||
public String strVal(int doc) {
|
||||
return Double.toString(doubleVal(doc));
|
||||
}
|
||||
|
||||
public String toString(int doc) {
|
||||
return description() + '=' + doubleVal(doc);
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
public boolean equals(Object o) {
|
||||
return o instanceof SortableDoubleFieldSource
|
||||
&& super.equals(o)
|
||||
&& defVal == ((SortableDoubleFieldSource)o).defVal;
|
||||
}
|
||||
|
||||
private static int hcode = SortableDoubleFieldSource.class.hashCode();
|
||||
public int hashCode() {
|
||||
long bits = Double.doubleToLongBits(defVal);
|
||||
int ibits = (int)(bits ^ (bits>>>32)); // mix upper bits into lower.
|
||||
return hcode + super.hashCode() + ibits;
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,129 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.FieldCache;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.FieldCacheSource;
|
||||
import org.apache.lucene.search.function.DocValues;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.index.IndexReader;
|
||||
import org.apache.solr.util.NumberUtils;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class SortableFloatField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return getStringSort(field,reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
return new SortableFloatFieldSource(field.name);
|
||||
}
|
||||
|
||||
public String toInternal(String val) {
|
||||
return NumberUtils.float2sortableStr(val);
|
||||
}
|
||||
|
||||
public String toExternal(Field f) {
|
||||
return indexedToReadable(f.stringValue());
|
||||
}
|
||||
|
||||
public String indexedToReadable(String indexedForm) {
|
||||
return NumberUtils.SortableStr2floatStr(indexedForm);
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
String sval = f.stringValue();
|
||||
xmlWriter.writeFloat(name, NumberUtils.SortableStr2float(sval));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
class SortableFloatFieldSource extends FieldCacheSource {
|
||||
protected float defVal;
|
||||
|
||||
public SortableFloatFieldSource(String field) {
|
||||
this(field, 0.0f);
|
||||
}
|
||||
|
||||
public SortableFloatFieldSource(String field, float defVal) {
|
||||
super(field);
|
||||
this.defVal = defVal;
|
||||
}
|
||||
|
||||
public String description() {
|
||||
return "sfloat(" + field + ')';
|
||||
}
|
||||
|
||||
public DocValues getValues(IndexReader reader) throws IOException {
|
||||
final FieldCache.StringIndex index = cache.getStringIndex(reader, field);
|
||||
final int[] order = index.order;
|
||||
final String[] lookup = index.lookup;
|
||||
final float def = defVal;
|
||||
|
||||
return new DocValues() {
|
||||
public float floatVal(int doc) {
|
||||
int ord=order[doc];
|
||||
return ord==0 ? def : NumberUtils.SortableStr2float(lookup[ord]);
|
||||
}
|
||||
|
||||
public int intVal(int doc) {
|
||||
return (int)floatVal(doc);
|
||||
}
|
||||
|
||||
public long longVal(int doc) {
|
||||
return (long)floatVal(doc);
|
||||
}
|
||||
|
||||
public double doubleVal(int doc) {
|
||||
return (double)floatVal(doc);
|
||||
}
|
||||
|
||||
public String strVal(int doc) {
|
||||
return Float.toString(floatVal(doc));
|
||||
}
|
||||
|
||||
public String toString(int doc) {
|
||||
return description() + '=' + floatVal(doc);
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
public boolean equals(Object o) {
|
||||
return o instanceof SortableFloatFieldSource
|
||||
&& super.equals(o)
|
||||
&& defVal == ((SortableFloatFieldSource)o).defVal;
|
||||
}
|
||||
|
||||
private static int hcode = SortableFloatFieldSource.class.hashCode();
|
||||
public int hashCode() {
|
||||
return hcode + super.hashCode() + Float.floatToIntBits(defVal);
|
||||
};
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,132 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.FieldCache;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.FieldCacheSource;
|
||||
import org.apache.lucene.search.function.DocValues;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.index.IndexReader;
|
||||
import org.apache.solr.util.NumberUtils;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class SortableIntField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return getStringSort(field,reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
return new SortableIntFieldSource(field.name);
|
||||
}
|
||||
|
||||
public String toInternal(String val) {
|
||||
// special case single digits? years?, etc
|
||||
// stringCache? general stringCache on a
|
||||
// global field level?
|
||||
return NumberUtils.int2sortableStr(val);
|
||||
}
|
||||
|
||||
public String toExternal(Field f) {
|
||||
return indexedToReadable(f.stringValue());
|
||||
}
|
||||
|
||||
public String indexedToReadable(String indexedForm) {
|
||||
return NumberUtils.SortableStr2int(indexedForm);
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
String sval = f.stringValue();
|
||||
// since writeInt an int instead of a String since that may be more efficient
|
||||
// in the future (saves the construction of one String)
|
||||
xmlWriter.writeInt(name, NumberUtils.SortableStr2int(sval,0,sval.length()));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
class SortableIntFieldSource extends FieldCacheSource {
|
||||
protected int defVal;
|
||||
|
||||
public SortableIntFieldSource(String field) {
|
||||
this(field, 0);
|
||||
}
|
||||
|
||||
public SortableIntFieldSource(String field, int defVal) {
|
||||
super(field);
|
||||
this.defVal = defVal;
|
||||
}
|
||||
|
||||
public String description() {
|
||||
return "sint(" + field + ')';
|
||||
}
|
||||
|
||||
public DocValues getValues(IndexReader reader) throws IOException {
|
||||
final FieldCache.StringIndex index = cache.getStringIndex(reader, field);
|
||||
final int[] order = index.order;
|
||||
final String[] lookup = index.lookup;
|
||||
final int def = defVal;
|
||||
|
||||
return new DocValues() {
|
||||
public float floatVal(int doc) {
|
||||
return (float)intVal(doc);
|
||||
}
|
||||
|
||||
public int intVal(int doc) {
|
||||
int ord=order[doc];
|
||||
return ord==0 ? def : NumberUtils.SortableStr2int(lookup[ord],0,3);
|
||||
}
|
||||
|
||||
public long longVal(int doc) {
|
||||
return (long)intVal(doc);
|
||||
}
|
||||
|
||||
public double doubleVal(int doc) {
|
||||
return (double)intVal(doc);
|
||||
}
|
||||
|
||||
public String strVal(int doc) {
|
||||
return Integer.toString(intVal(doc));
|
||||
}
|
||||
|
||||
public String toString(int doc) {
|
||||
return description() + '=' + intVal(doc);
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
public boolean equals(Object o) {
|
||||
return o instanceof SortableIntFieldSource
|
||||
&& super.equals(o)
|
||||
&& defVal == ((SortableIntFieldSource)o).defVal;
|
||||
}
|
||||
|
||||
private static int hcode = SortableIntFieldSource.class.hashCode();
|
||||
public int hashCode() {
|
||||
return hcode + super.hashCode() + defVal;
|
||||
};
|
||||
}
|
||||
|
|
@ -0,0 +1,129 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.search.FieldCache;
|
||||
import org.apache.lucene.search.function.ValueSource;
|
||||
import org.apache.lucene.search.function.FieldCacheSource;
|
||||
import org.apache.lucene.search.function.DocValues;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.index.IndexReader;
|
||||
import org.apache.solr.util.NumberUtils;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class SortableLongField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return getStringSort(field,reverse);
|
||||
}
|
||||
|
||||
public ValueSource getValueSource(SchemaField field) {
|
||||
return new SortableLongFieldSource(field.name);
|
||||
}
|
||||
|
||||
public String toInternal(String val) {
|
||||
return NumberUtils.long2sortableStr(val);
|
||||
}
|
||||
|
||||
public String indexedToReadable(String indexedForm) {
|
||||
return NumberUtils.SortableStr2long(indexedForm);
|
||||
}
|
||||
|
||||
public String toExternal(Field f) {
|
||||
return indexedToReadable(f.stringValue());
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
String sval = f.stringValue();
|
||||
xmlWriter.writeLong(name, NumberUtils.SortableStr2long(sval,0,sval.length()));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
class SortableLongFieldSource extends FieldCacheSource {
|
||||
protected long defVal;
|
||||
|
||||
public SortableLongFieldSource(String field) {
|
||||
this(field, 0);
|
||||
}
|
||||
|
||||
public SortableLongFieldSource(String field, long defVal) {
|
||||
super(field);
|
||||
this.defVal = defVal;
|
||||
}
|
||||
|
||||
public String description() {
|
||||
return "slong(" + field + ')';
|
||||
}
|
||||
|
||||
public DocValues getValues(IndexReader reader) throws IOException {
|
||||
final FieldCache.StringIndex index = cache.getStringIndex(reader, field);
|
||||
final int[] order = index.order;
|
||||
final String[] lookup = index.lookup;
|
||||
final long def = defVal;
|
||||
|
||||
return new DocValues() {
|
||||
public float floatVal(int doc) {
|
||||
return (float)longVal(doc);
|
||||
}
|
||||
|
||||
public int intVal(int doc) {
|
||||
return (int)longVal(doc);
|
||||
}
|
||||
|
||||
public long longVal(int doc) {
|
||||
int ord=order[doc];
|
||||
return ord==0 ? def : NumberUtils.SortableStr2long(lookup[ord],0,5);
|
||||
}
|
||||
|
||||
public double doubleVal(int doc) {
|
||||
return (double)longVal(doc);
|
||||
}
|
||||
|
||||
public String strVal(int doc) {
|
||||
return Long.toString(longVal(doc));
|
||||
}
|
||||
|
||||
public String toString(int doc) {
|
||||
return description() + '=' + longVal(doc);
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
public boolean equals(Object o) {
|
||||
return o instanceof SortableLongFieldSource
|
||||
&& super.equals(o)
|
||||
&& defVal == ((SortableLongFieldSource)o).defVal;
|
||||
}
|
||||
|
||||
private static int hcode = SortableLongFieldSource.class.hashCode();
|
||||
public int hashCode() {
|
||||
return hcode + super.hashCode() + (int)defVal;
|
||||
};
|
||||
}
|
||||
|
|
@ -0,0 +1,41 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
//TODO: allow specification of max string size?
|
||||
public class StrField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field,boolean reverse) {
|
||||
return getStringSort(field,reverse);
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeStr(name, f.stringValue());
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,43 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.schema;
|
||||
|
||||
import org.apache.lucene.search.SortField;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.solr.request.XMLWriter;
|
||||
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
|
||||
/** <code>TextField</code> is the basic type for configurable text analysis.
|
||||
* Analyzers for field types using this implementation should be defined in the schema.
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class TextField extends FieldType {
|
||||
protected void init(IndexSchema schema, Map<String,String> args) {
|
||||
properties |= TOKENIZED;
|
||||
}
|
||||
|
||||
public SortField getSortField(SchemaField field, boolean reverse) {
|
||||
return new SortField(field.name,SortField.STRING, reverse);
|
||||
}
|
||||
|
||||
public void write(XMLWriter xmlWriter, String name, Field f) throws IOException {
|
||||
xmlWriter.writeStr(name, f.stringValue());
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,112 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import java.util.BitSet;
|
||||
|
||||
/**
|
||||
* <code>BitDocSet</code> represents an unordered set of Lucene Document Ids
|
||||
* using a BitSet. A set bit represents inclusion in the set for that document.
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: BitDocSet.java,v 1.4 2005/10/27 04:14:49 yonik Exp $
|
||||
* @since solr 0.9
|
||||
*/
|
||||
public class BitDocSet extends DocSetBase {
|
||||
final BitSet bits;
|
||||
int size; // number of docs in the set (cached for perf)
|
||||
|
||||
public BitDocSet() {
|
||||
bits = new BitSet();
|
||||
}
|
||||
|
||||
public BitDocSet(BitSet bits) {
|
||||
this.bits = bits;
|
||||
size=-1;
|
||||
}
|
||||
|
||||
public BitDocSet(BitSet bits, int size) {
|
||||
this.bits = bits;
|
||||
this.size = size;
|
||||
}
|
||||
|
||||
public DocIterator iterator() {
|
||||
return new DocIterator() {
|
||||
int pos=bits.nextSetBit(0);
|
||||
public boolean hasNext() {
|
||||
return pos>=0;
|
||||
}
|
||||
|
||||
public Integer next() {
|
||||
return nextDoc();
|
||||
}
|
||||
|
||||
public void remove() {
|
||||
bits.clear(pos);
|
||||
}
|
||||
|
||||
public int nextDoc() {
|
||||
int old=pos;
|
||||
pos=bits.nextSetBit(old+1);
|
||||
return old;
|
||||
}
|
||||
|
||||
public float score() {
|
||||
return 0.0f;
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
*
|
||||
* @return the <b>internal</b> BitSet that should <b>not</b> be modified.
|
||||
*/
|
||||
public BitSet getBits() {
|
||||
return bits;
|
||||
}
|
||||
|
||||
public void add(int doc) {
|
||||
bits.set(doc);
|
||||
size=-1; // invalidate size
|
||||
}
|
||||
|
||||
public void addUnique(int doc) {
|
||||
size++;
|
||||
bits.set(doc);
|
||||
}
|
||||
|
||||
public int size() {
|
||||
if (size!=-1) return size;
|
||||
return size=bits.cardinality();
|
||||
}
|
||||
|
||||
/**
|
||||
* The number of set bits - size - is cached. If the bitset is changed externally,
|
||||
* this method should be used to invalidate the previously cached size.
|
||||
*/
|
||||
public void invalidateSize() {
|
||||
size=-1;
|
||||
}
|
||||
|
||||
public boolean exists(int doc) {
|
||||
return bits.get(doc);
|
||||
}
|
||||
|
||||
public long memSize() {
|
||||
return (bits.size() >> 3) + 16;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,110 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.w3c.dom.Node;
|
||||
import org.w3c.dom.NodeList;
|
||||
|
||||
import java.util.Map;
|
||||
|
||||
import org.apache.solr.util.DOMUtil;
|
||||
import org.apache.solr.core.SolrException;
|
||||
import org.apache.solr.core.SolrConfig;
|
||||
import org.apache.solr.core.Config;
|
||||
|
||||
import javax.xml.xpath.XPathConstants;
|
||||
|
||||
/**
|
||||
* Contains the knowledge of how cache config is
|
||||
* stored in the solarconfig.xml file, and implements a
|
||||
* factory to create caches.
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: CacheConfig.java,v 1.2 2005/09/07 20:37:57 yonik Exp $
|
||||
*/
|
||||
class CacheConfig {
|
||||
private String nodeName;
|
||||
private Map args;
|
||||
|
||||
private String cacheImpl;
|
||||
private Class clazz;
|
||||
|
||||
private Object[] persistence = new Object[1];
|
||||
|
||||
private String regenImpl;
|
||||
private CacheRegenerator regenerator;
|
||||
|
||||
public CacheRegenerator getRegenerator() {
|
||||
return regenerator;
|
||||
}
|
||||
|
||||
public void setRegenerator(CacheRegenerator regenerator) {
|
||||
this.regenerator = regenerator;
|
||||
}
|
||||
|
||||
public static CacheConfig[] getMultipleConfigs(String configPath) {
|
||||
NodeList nodes = (NodeList)SolrConfig.config.evaluate(configPath, XPathConstants.NODESET);
|
||||
if (nodes==null || nodes.getLength()==0) return null;
|
||||
CacheConfig[] configs = new CacheConfig[nodes.getLength()];
|
||||
for (int i=0; i<nodes.getLength(); i++) {
|
||||
configs[i] = getConfig(nodes.item(i));
|
||||
}
|
||||
return configs;
|
||||
}
|
||||
|
||||
|
||||
public static CacheConfig getConfig(String xpath) {
|
||||
Node node = (Node)SolrConfig.config.getNode(xpath, false);
|
||||
return getConfig(node);
|
||||
}
|
||||
|
||||
|
||||
public static CacheConfig getConfig(Node node) {
|
||||
if (node==null) return null;
|
||||
CacheConfig config = new CacheConfig();
|
||||
config.nodeName = node.getNodeName();
|
||||
config.args = DOMUtil.toMap(node.getAttributes());
|
||||
String nameAttr = (String)config.args.get("name"); // OPTIONAL
|
||||
if (nameAttr==null) {
|
||||
config.args.put("name",config.nodeName);
|
||||
}
|
||||
|
||||
config.cacheImpl = (String)config.args.get("class");
|
||||
config.regenImpl = (String)config.args.get("regenerator");
|
||||
config.clazz = Config.findClass(config.cacheImpl);
|
||||
if (config.regenImpl != null) {
|
||||
config.regenerator = (CacheRegenerator) Config.newInstance(config.regenImpl);
|
||||
}
|
||||
|
||||
|
||||
return config;
|
||||
}
|
||||
|
||||
public SolrCache newInstance() {
|
||||
try {
|
||||
SolrCache cache = (SolrCache)clazz.newInstance();
|
||||
persistence[0] = cache.init(args, persistence[0], regenerator);
|
||||
return cache;
|
||||
} catch (Exception e) {
|
||||
SolrException.log(SolrCache.log,"Error instantiating cache",e);
|
||||
// we can carry on without a cache... but should we?
|
||||
// in some cases (like an OOM) we probably should try to continue.
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,43 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* Implementations of <code>CacheRegenerator</code> are used in autowarming to populate a new cache
|
||||
* based on an old cache. <code>regenerateItem</code> is called for each item that should be inserted into the new cache.
|
||||
* <p>
|
||||
* Implementations should have a noarg constructor and be thread safe (a single instance will be
|
||||
* used for all cache autowarmings).
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: CacheRegenerator.java,v 1.2 2005/09/07 20:37:57 yonik Exp $
|
||||
*/
|
||||
public interface CacheRegenerator {
|
||||
/**
|
||||
* Regenerate an old cache item and insert it into <code>newCache</code>
|
||||
*
|
||||
* @param newSearcher the new searcher who's caches are being autowarmed
|
||||
* @param newCache where regenerated cache items should be stored. the target of the autowarming
|
||||
* @param oldCache the old cache being used as a source for autowarming
|
||||
* @param oldKey the key of the old cache item to regenerate in the new cache
|
||||
* @param oldVal the old value of the cache item
|
||||
* @return true to continue with autowarming, false to stop
|
||||
*/
|
||||
public boolean regenerateItem(SolrIndexSearcher newSearcher, SolrCache newCache, SolrCache oldCache, Object oldKey, Object oldVal) throws IOException;
|
||||
}
|
||||
|
|
@ -0,0 +1,37 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import java.util.Iterator;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public interface DocIterator extends Iterator<Integer> {
|
||||
public boolean hasNext();
|
||||
|
||||
/**
|
||||
* returns the next document id if hasNext()==true
|
||||
*/
|
||||
public int nextDoc();
|
||||
|
||||
/**
|
||||
* returns the score for the document just returned by nextDoc()
|
||||
*/
|
||||
public float score();
|
||||
}
|
||||
|
|
@ -0,0 +1,128 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
|
||||
/**
|
||||
* <code>DocList</code> represents the result of a query: an ordered list of document ids with optional score.
|
||||
* This list contains a subset of the complete list of documents actually matched: <code>size()</code>
|
||||
* document ids starting at <code>offset()</code>.
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: DocList.java,v 1.6 2005/11/11 21:57:56 yonik Exp $
|
||||
* @since solr 0.9
|
||||
*/
|
||||
public interface DocList extends DocSet {
|
||||
|
||||
/**
|
||||
* Returns the zero based offset of this list within the total ordered list of matches to the query.
|
||||
*/
|
||||
public int offset();
|
||||
|
||||
/**
|
||||
* Returns the number of ids in this list.
|
||||
*/
|
||||
public int size();
|
||||
|
||||
/**
|
||||
* Returns the total number of matches for the search
|
||||
* (as opposed to just the number collected according
|
||||
* to <code>offset()</code> and <code>size()</code>).
|
||||
* Hence it's always true that matches() >= size()
|
||||
* @return number of matches for the search(query&filter)
|
||||
*/
|
||||
public int matches();
|
||||
|
||||
|
||||
/***
|
||||
public int getDoc(int pos);
|
||||
***/
|
||||
|
||||
// hmmm, what if a different slice could be generated from an existing DocSet
|
||||
// (and was before)...
|
||||
|
||||
// how to distinguish cached values from logical values?
|
||||
// docSet could represent docs 10-20, but actually contain 0-100
|
||||
// should the big slice be cached independently, and a new class called
|
||||
// DocListSubset be created to refer to a range within the DocList?
|
||||
|
||||
/**
|
||||
* Get a subset of an existing DocList.
|
||||
* Returns null if not possible.
|
||||
*/
|
||||
public DocList subset(int offset, int len);
|
||||
|
||||
/** True if scores were retained */
|
||||
public boolean hasScores();
|
||||
|
||||
/** The maximum score for the search... only valid if
|
||||
* scores were retained (if hasScores()==true)
|
||||
*/
|
||||
public float maxScore();
|
||||
}
|
||||
|
||||
|
||||
/**** Maybe do this at a higher level (more efficient)
|
||||
|
||||
class SmartDocSet implements DocSet {
|
||||
static int INITIAL_SIZE=10;
|
||||
static int TRANSITION_SIZE=10;
|
||||
|
||||
protected BitSet bits;
|
||||
int size;
|
||||
|
||||
protected int[] arr; // keep small set as an array, or as a hash?
|
||||
protected int arrsize;
|
||||
|
||||
public SmartDocSet() {
|
||||
if (INITIAL_SIZE>0) {
|
||||
arr=new int[INITIAL_SIZE];
|
||||
} else {
|
||||
bits=new BitSet();
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public void addUnique(int doc) {
|
||||
size++;
|
||||
if (bits != null) {
|
||||
bits.set(doc);
|
||||
}
|
||||
else {
|
||||
if (arrsize<10) {
|
||||
arr[arrsize++]=doc;
|
||||
} else {
|
||||
// TODO: transition to bit set
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
public int size() {
|
||||
return size;
|
||||
}
|
||||
public boolean exists(int docid) {
|
||||
return false;
|
||||
}
|
||||
public DocSet intersection(DocSet other) {
|
||||
return null;
|
||||
|
||||
}
|
||||
public DocSet union(DocSet other) {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
***/
|
||||
|
|
@ -0,0 +1,37 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
|
||||
/**
|
||||
* A struct who's only purpose is to hold both a DocList and a DocSet so that both
|
||||
* may be returned from a single method.
|
||||
* <p>
|
||||
* The DocList and DocSet returned should <b>not</b> be modified as they may
|
||||
* have been retrieved or inserted into a cache and should be considered shared.
|
||||
* <p>
|
||||
* Oh, if only java had "out" parameters or multiple return args...
|
||||
* <p>
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: DocListAndSet.java,v 1.3 2005/04/08 05:38:05 yonik Exp $
|
||||
* @since solr 0.9
|
||||
*/
|
||||
public final class DocListAndSet {
|
||||
public DocList docList;
|
||||
public DocSet docSet;
|
||||
}
|
||||
|
|
@ -0,0 +1,182 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.apache.solr.core.SolrException;
|
||||
|
||||
import java.util.BitSet;
|
||||
|
||||
/**
|
||||
* <code>DocSet</code> represents an unordered set of Lucene Document Ids.
|
||||
* <p>
|
||||
* WARNING: Any DocSet returned from SolrIndexSearcher should <b>not</b> be modified as it may have been retrieved from
|
||||
* a cache and could be shared.
|
||||
* @author yonik
|
||||
* @version $Id: DocSet.java,v 1.6 2005/05/13 21:20:15 yonik Exp $
|
||||
* @since solr 0.9
|
||||
*/
|
||||
public interface DocSet /* extends Collection<Integer> */ {
|
||||
public void add(int doc);
|
||||
public void addUnique(int doc);
|
||||
|
||||
/**
|
||||
* @return The number of document ids in the set.
|
||||
*/
|
||||
public int size();
|
||||
|
||||
/**
|
||||
*
|
||||
* @param docid
|
||||
* @return
|
||||
* true if the docid is in the set
|
||||
*/
|
||||
public boolean exists(int docid);
|
||||
|
||||
/**
|
||||
*
|
||||
* @return an interator that may be used to iterate over all of the documents in the set.
|
||||
*/
|
||||
public DocIterator iterator();
|
||||
|
||||
/**
|
||||
* Returns a BitSet view of the DocSet. Any changes to this BitSet <b>may</b>
|
||||
* be reflected in the DocSet, hence if the DocSet is shared or was returned from
|
||||
* a SolrIndexSearcher method, it's not safe to modify the BitSet.
|
||||
*
|
||||
* @return
|
||||
* A BitSet with the bit number of every docid set in the set.
|
||||
*/
|
||||
@Deprecated
|
||||
public BitSet getBits();
|
||||
|
||||
/**
|
||||
* Returns the approximate amount of memory taken by this DocSet.
|
||||
* This is only an approximation and doesn't take into account java object overhead.
|
||||
*
|
||||
* @return
|
||||
* the approximate memory consumption in bytes
|
||||
*/
|
||||
public long memSize();
|
||||
|
||||
/**
|
||||
* Returns the intersection of this set with another set. Neither set is modified - a new DocSet is
|
||||
* created and returned.
|
||||
* @param other
|
||||
* @return a DocSet representing the intersection
|
||||
*/
|
||||
public DocSet intersection(DocSet other);
|
||||
|
||||
/**
|
||||
* Returns the number of documents of the intersection of this set with another set.
|
||||
* May be more efficient than actually creating the intersection and then getting it's size.
|
||||
*/
|
||||
public int intersectionSize(DocSet other);
|
||||
|
||||
/**
|
||||
* Returns the union of this set with another set. Neither set is modified - a new DocSet is
|
||||
* created and returned.
|
||||
* @param other
|
||||
* @return a DocSet representing the union
|
||||
*/
|
||||
public DocSet union(DocSet other);
|
||||
|
||||
/**
|
||||
* Returns the number of documents of the union of this set with another set.
|
||||
* May be more efficient than actually creating the union and then getting it's size.
|
||||
*/
|
||||
public int unionSize(DocSet other);
|
||||
|
||||
}
|
||||
|
||||
|
||||
abstract class DocSetBase implements DocSet {
|
||||
|
||||
// Not implemented efficiently... for testing purposes only
|
||||
public boolean equals(Object obj) {
|
||||
if (!(obj instanceof DocSet)) return false;
|
||||
DocSet other = (DocSet)obj;
|
||||
if (this.size() != other.size()) return false;
|
||||
|
||||
if (this instanceof DocList && other instanceof DocList) {
|
||||
// compare ordering
|
||||
DocIterator i1=this.iterator();
|
||||
DocIterator i2=this.iterator();
|
||||
while(i1.hasNext() && i2.hasNext()) {
|
||||
if (i1.nextDoc() != i2.nextDoc()) return false;
|
||||
}
|
||||
return true;
|
||||
// don't compare matches
|
||||
}
|
||||
|
||||
// if (this.size() != other.size()) return false;
|
||||
return this.getBits().equals(other.getBits());
|
||||
}
|
||||
|
||||
public void add(int doc) {
|
||||
throw new SolrException(500,"Unsupported Operation");
|
||||
}
|
||||
|
||||
public void addUnique(int doc) {
|
||||
throw new SolrException(500,"Unsupported Operation");
|
||||
}
|
||||
|
||||
// Only the inefficient base implementation. DocSets based on
|
||||
// BitSets will return the actual BitSet without making a copy.
|
||||
public BitSet getBits() {
|
||||
BitSet bits = new BitSet();
|
||||
for (DocIterator iter = iterator(); iter.hasNext();) {
|
||||
bits.set(iter.nextDoc());
|
||||
}
|
||||
return bits;
|
||||
};
|
||||
|
||||
public DocSet intersection(DocSet other) {
|
||||
// intersection is overloaded in HashDocSet to be more
|
||||
// efficient, so if "other" is a HashDocSet, dispatch off
|
||||
// of it instead.
|
||||
if (other instanceof HashDocSet) {
|
||||
return other.intersection(this);
|
||||
}
|
||||
|
||||
// Default... handle with bitsets.
|
||||
BitSet newbits = (BitSet)(this.getBits().clone());
|
||||
newbits.and(other.getBits());
|
||||
return new BitDocSet(newbits);
|
||||
}
|
||||
|
||||
public DocSet union(DocSet other) {
|
||||
BitSet newbits = (BitSet)(this.getBits().clone());
|
||||
newbits.or(other.getBits());
|
||||
return new BitDocSet(newbits);
|
||||
}
|
||||
|
||||
// TODO: more efficient implementations
|
||||
public int intersectionSize(DocSet other) {
|
||||
return intersection(other).size();
|
||||
}
|
||||
|
||||
// TODO: more efficient implementations
|
||||
public int unionSize(DocSet other) {
|
||||
return union(other).size();
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,119 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
/**
|
||||
* <code>DocSlice</code> implements DocList as an array of docids and optional scores.
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: DocSlice.java,v 1.9 2005/11/11 21:57:56 yonik Exp $
|
||||
* @since solr 0.9
|
||||
*/
|
||||
public class DocSlice extends DocSetBase implements DocList {
|
||||
final int offset; // starting position of the docs (zero based)
|
||||
final int len; // number of positions used in arrays
|
||||
final int[] docs; // a slice of documents (docs 0-100 of the query)
|
||||
|
||||
final float[] scores; // optional score list
|
||||
final int matches;
|
||||
final float maxScore;
|
||||
|
||||
/**
|
||||
*
|
||||
* @param offset starting offset for this range of docs
|
||||
* @param len length of results
|
||||
* @param docs array of docids starting at position 0
|
||||
* @param scores
|
||||
* @param matches total number of matches for the query
|
||||
*/
|
||||
public DocSlice(int offset, int len, int[] docs, float[] scores, int matches, float maxScore) {
|
||||
this.offset=offset;
|
||||
this.len=len;
|
||||
this.docs=docs;
|
||||
this.scores=scores;
|
||||
this.matches=matches;
|
||||
this.maxScore=maxScore;
|
||||
}
|
||||
|
||||
public DocList subset(int offset, int len) {
|
||||
if (this.offset == offset && this.len==len) return this;
|
||||
|
||||
// if we didn't store enough (and there was more to store)
|
||||
// then we can't take a subset.
|
||||
int requestedEnd = offset + len;
|
||||
if (requestedEnd > docs.length && this.matches > docs.length) return null;
|
||||
int realEndDoc = Math.min(requestedEnd, docs.length);
|
||||
int realLen = Math.max(realEndDoc-offset,0);
|
||||
if (this.offset == offset && this.len == realLen) return this;
|
||||
return new DocSlice(offset, realLen, docs, scores, matches, maxScore);
|
||||
}
|
||||
|
||||
public boolean hasScores() {
|
||||
return scores!=null;
|
||||
}
|
||||
|
||||
public float maxScore() {
|
||||
return maxScore;
|
||||
}
|
||||
|
||||
|
||||
public int offset() { return offset; }
|
||||
public int size() { return len; }
|
||||
public int matches() { return matches; }
|
||||
|
||||
|
||||
public long memSize() {
|
||||
return (docs.length<<2)
|
||||
+ (scores==null ? 0 : (scores.length<<2))
|
||||
+ 24;
|
||||
}
|
||||
|
||||
|
||||
public boolean exists(int doc) {
|
||||
for (int i: docs) {
|
||||
if (i==doc) return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
// Hmmm, maybe I could have reused the scorer interface here...
|
||||
// except that it carries Similarity baggage...
|
||||
public DocIterator iterator() {
|
||||
return new DocIterator() {
|
||||
int pos=offset;
|
||||
final int end=offset+len;
|
||||
public boolean hasNext() {
|
||||
return pos < end;
|
||||
}
|
||||
|
||||
public Integer next() {
|
||||
return nextDoc();
|
||||
}
|
||||
|
||||
public void remove() {
|
||||
}
|
||||
|
||||
public int nextDoc() {
|
||||
return docs[pos++];
|
||||
}
|
||||
|
||||
public float score() {
|
||||
return scores[pos-1];
|
||||
}
|
||||
};
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,280 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.apache.solr.core.SolrConfig;
|
||||
|
||||
|
||||
/**
|
||||
* <code>HashDocSet</code> represents an unordered set of Lucene Document Ids
|
||||
* using a primitive int hash table. It can be a better choice if there are few docs
|
||||
* in the set because it takes up less memory and is faster to iterate and take
|
||||
* set intersections.
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: HashDocSet.java,v 1.7 2005/11/22 17:16:19 yonik Exp $
|
||||
* @since solr 0.9
|
||||
*/
|
||||
public final class HashDocSet extends DocSetBase {
|
||||
// keep track of the inverse of the Loadfactor since
|
||||
// multiplication is so much faster than division.
|
||||
final static float inverseLoadfactor = 1.0f / SolrConfig.config.getFloat("//HashDocSet/@loadFactor",0.75f);
|
||||
public final static int MAX_SIZE = SolrConfig.config.getInt("//HashDocSet/@maxSize",-1);
|
||||
|
||||
|
||||
// lucene docs are numbered from 0, so a neg number must be used for missing.
|
||||
// an alternative to having to init the array to EMPTY at the start is
|
||||
//
|
||||
private final static int EMPTY=-1;
|
||||
private final int tablesize;
|
||||
private final int[] table;
|
||||
private final int size;
|
||||
|
||||
private final int mask;
|
||||
|
||||
public HashDocSet(int[] docs, int offset, int len) {
|
||||
int tsize = Math.max(nextHighestPowerOfTwo(len), 1);
|
||||
if (tsize < len * inverseLoadfactor) {
|
||||
tsize <<= 1;
|
||||
}
|
||||
tablesize = tsize;
|
||||
mask=tablesize-1;
|
||||
|
||||
table = new int[tablesize];
|
||||
for (int i=0; i<tablesize; i++) table[i]=EMPTY;
|
||||
|
||||
for (int i=offset; i<len; i++) {
|
||||
put(docs[i]);
|
||||
}
|
||||
|
||||
size = len;
|
||||
}
|
||||
|
||||
static int nextHighestPowerOfTwo(int v) {
|
||||
v--;
|
||||
v |= v >> 1;
|
||||
v |= v >> 2;
|
||||
v |= v >> 4;
|
||||
v |= v >> 8;
|
||||
v |= v >> 16;
|
||||
v++;
|
||||
return v;
|
||||
}
|
||||
|
||||
|
||||
void put(int doc) {
|
||||
table[getSlot(doc)]=doc;
|
||||
}
|
||||
|
||||
private int getSlot(int val) {
|
||||
int s,v;
|
||||
s=val & mask;
|
||||
v=table[s];
|
||||
// check for EMPTY first since that value is more likely
|
||||
if (v==EMPTY || v==val) return s;
|
||||
s=rehash(val);
|
||||
return s;
|
||||
}
|
||||
|
||||
|
||||
// As the size of this int hashtable is expected to be small
|
||||
// (thousands at most), I did not try to keep the rehash function
|
||||
// reversible (important to avoid collisions in large hash tables).
|
||||
private int rehash(int val) {
|
||||
int h,s,v;
|
||||
final int comp=~val;
|
||||
|
||||
// don't left shift too far... the only bits
|
||||
// that count in the answer are the ones on the right.
|
||||
// We want to put more of the bits on the left
|
||||
// into the answer.
|
||||
// Keep small tables in mind. We may be only using
|
||||
// the first 5 or 6 bits.
|
||||
|
||||
// on the first rehash, use complement instead of val to shift
|
||||
// so we don't end up with 0 again if val==0.
|
||||
h = val ^ (comp>>8);
|
||||
s = h & mask;
|
||||
v = table[s];
|
||||
if (v==EMPTY || v==val) return s;
|
||||
|
||||
h ^= (v << 17) | (comp >>> 16); // this is reversible
|
||||
s = h & mask;
|
||||
v = table[s];
|
||||
if (v==EMPTY || v==val) return s;
|
||||
|
||||
h ^= (h << 8) | (comp >>> 25); // this is reversible
|
||||
s = h & mask;
|
||||
v = table[s];
|
||||
if (v==EMPTY || v==val) return s;
|
||||
|
||||
/**********************
|
||||
// Knuth, Thomas Wang, http://www.concentric.net/~Ttwang/tech/inthash.htm
|
||||
// This magic number has no common factors with 2^32, and magic/(2^32) approximates
|
||||
// the golden ratio.
|
||||
private static final int magic = (int)2654435761L;
|
||||
|
||||
h = magic*val;
|
||||
s = h & mask;
|
||||
v=table[s];
|
||||
if (v==EMPTY || v==val) return s;
|
||||
|
||||
// the mult with magic should have thoroughly mixed the bits.
|
||||
// add entropy to the right half from the left half.
|
||||
h ^= h>>>16;
|
||||
s = h & mask;
|
||||
v=table[s];
|
||||
if (v==EMPTY || v==val) return s;
|
||||
*************************/
|
||||
|
||||
// linear scan now... ug.
|
||||
final int start=s;
|
||||
while (++s<tablesize) {
|
||||
v=table[s];
|
||||
if (v==EMPTY || v==val) return s;
|
||||
}
|
||||
s=start;
|
||||
while (--s>=0) {
|
||||
v=table[s];
|
||||
if (v==EMPTY || v==val) return s;
|
||||
}
|
||||
return s;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
*
|
||||
* @return The number of document ids in the set.
|
||||
*/
|
||||
public int size() {
|
||||
return size;
|
||||
}
|
||||
|
||||
public boolean exists(int docid) {
|
||||
int v = table[docid & mask];
|
||||
if (v==EMPTY) return false;
|
||||
else if (v==docid) return true;
|
||||
else {
|
||||
v = table[rehash(docid)];
|
||||
if (v==docid) return true;
|
||||
else return false;
|
||||
}
|
||||
}
|
||||
|
||||
public DocIterator iterator() {
|
||||
return new DocIterator() {
|
||||
int pos=0;
|
||||
int doc;
|
||||
{ goNext(); }
|
||||
|
||||
public boolean hasNext() {
|
||||
return pos < tablesize;
|
||||
}
|
||||
|
||||
public Integer next() {
|
||||
return nextDoc();
|
||||
}
|
||||
|
||||
public void remove() {
|
||||
}
|
||||
|
||||
void goNext() {
|
||||
while (pos<tablesize && table[pos]==EMPTY) pos++;
|
||||
}
|
||||
|
||||
// modify to return -1 at end of iteration?
|
||||
public int nextDoc() {
|
||||
int doc = table[pos];
|
||||
pos++;
|
||||
goNext();
|
||||
return doc;
|
||||
}
|
||||
|
||||
public float score() {
|
||||
return 0.0f;
|
||||
}
|
||||
};
|
||||
}
|
||||
|
||||
|
||||
public long memSize() {
|
||||
return (tablesize<<2) + 20;
|
||||
}
|
||||
|
||||
|
||||
public DocSet intersection(DocSet other) {
|
||||
if (other instanceof HashDocSet) {
|
||||
// set "a" to the smallest doc set for the most efficient
|
||||
// intersection.
|
||||
final HashDocSet a = size()<=other.size() ? this : (HashDocSet)other;
|
||||
final HashDocSet b = size()<=other.size() ? (HashDocSet)other : this;
|
||||
|
||||
int[] result = new int[a.size()];
|
||||
int resultCount=0;
|
||||
for (int i=0; i<a.table.length; i++) {
|
||||
int id=a.table[i];
|
||||
if (id >= 0 && b.exists(id)) {
|
||||
result[resultCount++]=id;
|
||||
}
|
||||
}
|
||||
return new HashDocSet(result,0,resultCount);
|
||||
|
||||
} else {
|
||||
|
||||
int[] result = new int[size()];
|
||||
int resultCount=0;
|
||||
for (int i=0; i<table.length; i++) {
|
||||
int id=table[i];
|
||||
if (id >= 0 && other.exists(id)) {
|
||||
result[resultCount++]=id;
|
||||
}
|
||||
}
|
||||
return new HashDocSet(result,0,resultCount);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
public int intersectionSize(DocSet other) {
|
||||
if (other instanceof HashDocSet) {
|
||||
// set "a" to the smallest doc set for the most efficient
|
||||
// intersection.
|
||||
final HashDocSet a = size()<=other.size() ? this : (HashDocSet)other;
|
||||
final HashDocSet b = size()<=other.size() ? (HashDocSet)other : this;
|
||||
|
||||
int resultCount=0;
|
||||
for (int i=0; i<a.table.length; i++) {
|
||||
int id=a.table[i];
|
||||
if (id >= 0 && b.exists(id)) {
|
||||
resultCount++;
|
||||
}
|
||||
}
|
||||
return resultCount;
|
||||
} else {
|
||||
int resultCount=0;
|
||||
for (int i=0; i<table.length; i++) {
|
||||
int id=table[i];
|
||||
if (id >= 0 && other.exists(id)) {
|
||||
resultCount++;
|
||||
}
|
||||
}
|
||||
return resultCount;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,274 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.apache.solr.core.SolrCore;
|
||||
import org.apache.solr.core.SolrException;
|
||||
import org.apache.solr.util.NamedList;
|
||||
|
||||
import java.util.*;
|
||||
import java.util.concurrent.atomic.AtomicLong;
|
||||
import java.io.IOException;
|
||||
import java.net.URL;
|
||||
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: LRUCache.java,v 1.12 2005/11/30 06:12:55 yonik Exp $
|
||||
*/
|
||||
public class LRUCache implements SolrCache {
|
||||
|
||||
/* An instance of this class will be shared across multiple instances
|
||||
* of an LRUCache at the same time. Make sure everything is thread safe.
|
||||
*/
|
||||
private static class CumulativeStats {
|
||||
AtomicLong lookups = new AtomicLong();
|
||||
AtomicLong hits = new AtomicLong();
|
||||
AtomicLong inserts = new AtomicLong();
|
||||
AtomicLong evictions = new AtomicLong();
|
||||
}
|
||||
|
||||
private CumulativeStats stats;
|
||||
|
||||
// per instance stats. The synchronization used for the map will also be
|
||||
// used for updating these statistics (and hence they are not AtomicLongs
|
||||
private long lookups;
|
||||
private long hits;
|
||||
private long inserts;
|
||||
private long evictions;
|
||||
|
||||
private Map map;
|
||||
private String name;
|
||||
private int autowarmCount;
|
||||
private State state;
|
||||
private CacheRegenerator regenerator;
|
||||
|
||||
public Object init(Map args, Object persistence, CacheRegenerator regenerator) {
|
||||
state=State.CREATED;
|
||||
this.regenerator = regenerator;
|
||||
name = (String)args.get("name");
|
||||
String str = (String)args.get("size");
|
||||
final int limit = str==null ? 1024 : Integer.parseInt(str);
|
||||
str = (String)args.get("initialSize");
|
||||
final int initialSize = Math.min(str==null ? 1024 : Integer.parseInt(str), limit);
|
||||
str = (String)args.get("autowarmCount");
|
||||
autowarmCount = str==null ? 0 : Integer.parseInt(str);
|
||||
|
||||
map = new LinkedHashMap(initialSize, 0.75f, true) {
|
||||
protected boolean removeEldestEntry(Map.Entry eldest) {
|
||||
if (size() > limit) {
|
||||
// increment evictions regardless of state.
|
||||
// this doesn't need to be synchronized because it will
|
||||
// only be called in the context of a higher level synchronized block.
|
||||
evictions++;
|
||||
stats.evictions.incrementAndGet();
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
};
|
||||
|
||||
if (persistence==null) {
|
||||
// must be the first time a cache of this type is being created
|
||||
persistence = new CumulativeStats();
|
||||
}
|
||||
|
||||
stats = (CumulativeStats)persistence;
|
||||
|
||||
return persistence;
|
||||
}
|
||||
|
||||
public String name() {
|
||||
return name;
|
||||
}
|
||||
|
||||
public int size() {
|
||||
synchronized(map) {
|
||||
return map.size();
|
||||
}
|
||||
}
|
||||
|
||||
public synchronized Object put(Object key, Object value) {
|
||||
if (state == State.LIVE) {
|
||||
stats.inserts.incrementAndGet();
|
||||
}
|
||||
|
||||
synchronized (map) {
|
||||
// increment local inserts regardless of state???
|
||||
// it does make it more consistent with the current size...
|
||||
inserts++;
|
||||
return map.put(key,value);
|
||||
}
|
||||
}
|
||||
|
||||
public Object get(Object key) {
|
||||
synchronized (map) {
|
||||
Object val = map.get(key);
|
||||
if (state == State.LIVE) {
|
||||
// only increment lookups and hits if we are live.
|
||||
lookups++;
|
||||
stats.lookups.incrementAndGet();
|
||||
if (val!=null) {
|
||||
hits++;
|
||||
stats.hits.incrementAndGet();
|
||||
}
|
||||
}
|
||||
return val;
|
||||
}
|
||||
}
|
||||
|
||||
public void clear() {
|
||||
synchronized(map) {
|
||||
map.clear();
|
||||
}
|
||||
}
|
||||
|
||||
public void setState(State state) {
|
||||
this.state = state;
|
||||
}
|
||||
|
||||
public State getState() {
|
||||
return state;
|
||||
}
|
||||
|
||||
public void warm(SolrIndexSearcher searcher, SolrCache old) throws IOException {
|
||||
if (regenerator==null) return;
|
||||
|
||||
LRUCache other = (LRUCache)old;
|
||||
|
||||
// warm entries
|
||||
if (autowarmCount != 0) {
|
||||
Object[] keys,vals = null;
|
||||
|
||||
// Don't do the autowarming in the synchronized block, just pull out the keys and values.
|
||||
synchronized (other.map) {
|
||||
int sz = other.map.size();
|
||||
if (autowarmCount!=-1) sz = Math.min(sz,autowarmCount);
|
||||
keys = new Object[sz];
|
||||
vals = new Object[sz];
|
||||
|
||||
Iterator iter = other.map.entrySet().iterator();
|
||||
|
||||
// iteration goes from oldest (least recently used) to most recently used,
|
||||
// so we need to skip over the oldest entries.
|
||||
int skip = other.map.size() - sz;
|
||||
for (int i=0; i<skip; i++) iter.next();
|
||||
|
||||
|
||||
for (int i=0; i<sz; i++) {
|
||||
Map.Entry entry = (Map.Entry)iter.next();
|
||||
keys[i]=entry.getKey();
|
||||
vals[i]=entry.getValue();
|
||||
}
|
||||
}
|
||||
|
||||
// autowarm from the oldest to the newest entries so that the ordering will be
|
||||
// correct in the new cache.
|
||||
for (int i=0; i<keys.length; i++) {
|
||||
try {
|
||||
boolean continueRegen = regenerator.regenerateItem(searcher, this, old, keys[i], vals[i]);
|
||||
if (!continueRegen) break;
|
||||
}
|
||||
catch (Throwable e) {
|
||||
SolrException.log(log,"Error during auto-warming of key:" + keys[i], e);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
public void close() {
|
||||
}
|
||||
|
||||
|
||||
//////////////////////// SolrInfoMBeans methods //////////////////////
|
||||
|
||||
|
||||
public String getName() {
|
||||
return LRUCache.class.getName();
|
||||
}
|
||||
|
||||
public String getVersion() {
|
||||
return SolrCore.version;
|
||||
}
|
||||
|
||||
public String getDescription() {
|
||||
return "LRU Cache";
|
||||
}
|
||||
|
||||
public Category getCategory() {
|
||||
return Category.CACHE;
|
||||
}
|
||||
|
||||
public String getCvsId() {
|
||||
return "$Id: LRUCache.java,v 1.12 2005/11/30 06:12:55 yonik Exp $";
|
||||
}
|
||||
|
||||
public String getCvsName() {
|
||||
return "$Name: $";
|
||||
}
|
||||
|
||||
public String getCvsSource() {
|
||||
return "$Source: /cvs/main/searching/solr/solarcore/src/solr/search/LRUCache.java,v $";
|
||||
}
|
||||
|
||||
public URL[] getDocs() {
|
||||
return null;
|
||||
}
|
||||
|
||||
|
||||
// returns a ratio, not a percent.
|
||||
private static String calcHitRatio(long lookups, long hits) {
|
||||
if (lookups==0) return "0.00";
|
||||
if (lookups==hits) return "1.00";
|
||||
int hundredths = (int)(hits*100/lookups); // rounded down
|
||||
if (hundredths < 10) return "0.0" + hundredths;
|
||||
return "0." + hundredths;
|
||||
|
||||
/*** code to produce a percent, if we want it...
|
||||
int ones = (int)(hits*100 / lookups);
|
||||
int tenths = (int)(hits*1000 / lookups) - ones*10;
|
||||
return Integer.toString(ones) + '.' + tenths;
|
||||
***/
|
||||
}
|
||||
|
||||
public NamedList getStatistics() {
|
||||
NamedList lst = new NamedList();
|
||||
synchronized (map) {
|
||||
lst.add("lookups", lookups);
|
||||
lst.add("hits", hits);
|
||||
lst.add("hitratio", calcHitRatio(lookups,hits));
|
||||
lst.add("inserts", inserts);
|
||||
lst.add("evictions", evictions);
|
||||
lst.add("size", map.size());
|
||||
}
|
||||
|
||||
long clookups = stats.lookups.get();
|
||||
long chits = stats.hits.get();
|
||||
lst.add("cumulative_lookups", clookups);
|
||||
lst.add("cumulative_hits", chits);
|
||||
lst.add("cumulative_hitratio", calcHitRatio(clookups,chits));
|
||||
lst.add("cumulative_inserts", stats.inserts.get());
|
||||
lst.add("cumulative_evictions", stats.evictions.get());
|
||||
|
||||
return lst;
|
||||
}
|
||||
|
||||
public String toString() {
|
||||
return name + getStatistics().toString();
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,116 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
/* Copyright (c) 2003 The Nutch Organization. All rights reserved. */
|
||||
/* Use subject to the conditions in http://www.nutch.org/LICENSE.txt. */
|
||||
|
||||
|
||||
import org.apache.lucene.search.*;
|
||||
|
||||
import java.util.LinkedHashMap;
|
||||
import java.util.Map;
|
||||
import java.io.IOException;
|
||||
|
||||
/** Utility which converts certain query clauses into {@link QueryFilter}s and
|
||||
* caches these. Only required {@link TermQuery}s whose boost is zero and
|
||||
* whose term occurs in at least a certain fraction of documents are converted
|
||||
* to cached filters. This accellerates query constraints like language,
|
||||
* document format, etc., which do not affect ranking but might otherwise slow
|
||||
* search considerably. */
|
||||
// Taken from Nutch and modified - YCS
|
||||
class LuceneQueryOptimizer {
|
||||
private LinkedHashMap cache; // an LRU cache of QueryFilter
|
||||
|
||||
private float threshold;
|
||||
|
||||
/** Construct an optimizer that caches and uses filters for required {@link
|
||||
* TermQuery}s whose boost is zero.
|
||||
* @param cacheSize the number of QueryFilters to cache
|
||||
* @param threshold the fraction of documents which must contain term
|
||||
*/
|
||||
public LuceneQueryOptimizer(final int cacheSize, float threshold) {
|
||||
this.cache = new LinkedHashMap(cacheSize, 0.75f, true) {
|
||||
protected boolean removeEldestEntry(Map.Entry eldest) {
|
||||
return size() > cacheSize; // limit size of cache
|
||||
}
|
||||
};
|
||||
this.threshold = threshold;
|
||||
}
|
||||
|
||||
public TopDocs optimize(BooleanQuery original,
|
||||
Searcher searcher,
|
||||
int numHits,
|
||||
Query[] queryOut,
|
||||
Filter[] filterOut
|
||||
)
|
||||
throws IOException {
|
||||
|
||||
BooleanQuery query = new BooleanQuery();
|
||||
BooleanQuery filterQuery = null;
|
||||
|
||||
BooleanClause[] clauses = original.getClauses();
|
||||
for (int i = 0; i < clauses.length; i++) {
|
||||
BooleanClause c = clauses[i];
|
||||
|
||||
/***
|
||||
System.out.println("required="+c.required);
|
||||
System.out.println("boost="+c.query.getBoost());
|
||||
System.out.println("isTermQuery="+(c.query instanceof TermQuery));
|
||||
if (c.query instanceof TermQuery) {
|
||||
System.out.println("term="+((TermQuery)c.query).getTerm());
|
||||
System.out.println("docFreq="+searcher.docFreq(((TermQuery)c.query).getTerm()));
|
||||
}
|
||||
***/
|
||||
if (c.required // required
|
||||
&& c.query.getBoost() == 0.0f // boost is zero
|
||||
&& c.query instanceof TermQuery // TermQuery
|
||||
&& (searcher.docFreq(((TermQuery)c.query).getTerm())
|
||||
/ (float)searcher.maxDoc()) >= threshold) { // check threshold
|
||||
if (filterQuery == null)
|
||||
filterQuery = new BooleanQuery();
|
||||
filterQuery.add(c.query, true, false); // filter it
|
||||
//System.out.println("WooHoo... qualified to be hoisted to a filter!");
|
||||
} else {
|
||||
query.add(c); // query it
|
||||
}
|
||||
}
|
||||
|
||||
Filter filter = null;
|
||||
if (filterQuery != null) {
|
||||
synchronized (cache) { // check cache
|
||||
filter = (Filter)cache.get(filterQuery);
|
||||
}
|
||||
if (filter == null) { // miss
|
||||
filter = new QueryFilter(filterQuery); // construct new entry
|
||||
synchronized (cache) {
|
||||
cache.put(filterQuery, filter); // cache it
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// YCS: added code to pass out optimized query and filter
|
||||
// so they can be used with Hits
|
||||
if (queryOut != null && filterOut != null) {
|
||||
queryOut[0] = query; filterOut[0] = filter;
|
||||
return null;
|
||||
} else {
|
||||
return searcher.search(query, filter, numHits);
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,115 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.apache.lucene.search.*;
|
||||
import org.apache.lucene.index.IndexReader;
|
||||
|
||||
import java.io.IOException;
|
||||
|
||||
|
||||
/**
|
||||
* A {@link SortComparatorSource} for strings that orders null values after non-null values.
|
||||
* Based on FieldSortedHitQueue.comparatorString
|
||||
* <p>
|
||||
*
|
||||
* @author Chris Hostetter
|
||||
* @author yonik
|
||||
* @version $Id: MissingStringLastComparatorSource.java,v 1.1 2005/06/02 04:43:06 yonik Exp $
|
||||
*
|
||||
*/
|
||||
|
||||
// move to apache package and make public if it is accepted as a patch
|
||||
class MissingStringLastComparatorSource implements SortComparatorSource {
|
||||
|
||||
public static final String bigString="\uffff\uffff\uffff\uffff\uffff\uffff\uffff\uffffNULL_VAL";
|
||||
|
||||
private final String missingValueProxy;
|
||||
|
||||
public MissingStringLastComparatorSource() {
|
||||
this(bigString);
|
||||
}
|
||||
|
||||
/**
|
||||
* Returns the value used to sort the given document. The
|
||||
* object returned must implement the java.io.Serializable
|
||||
* interface. This is used by multisearchers to determine how to collate results from their searchers.
|
||||
* @see FieldDoc
|
||||
* @param i Document
|
||||
* @return Serializable object
|
||||
*/
|
||||
|
||||
/** Creates a {@link SortComparatorSource} that uses <tt>missingValueProxy</tt> as the value to return from ScoreDocComparator.sortValue()
|
||||
* which is only used my multisearchers to determine how to collate results from their searchers.
|
||||
*
|
||||
* @param missingValueProxy The value returned when sortValue() is called for a document missing the sort field.
|
||||
* This value is *not* normally used for sorting, but used to create
|
||||
*/
|
||||
public MissingStringLastComparatorSource(String missingValueProxy) {
|
||||
this.missingValueProxy=missingValueProxy;
|
||||
}
|
||||
|
||||
public ScoreDocComparator newComparator(final IndexReader reader,
|
||||
final String fieldname)
|
||||
throws IOException {
|
||||
|
||||
final String field = fieldname.intern();
|
||||
final FieldCache.StringIndex index =
|
||||
FieldCache.DEFAULT.getStringIndex (reader, field);
|
||||
|
||||
// :HACK:
|
||||
// final String lastString =
|
||||
// (index.lookup[index.lookup.length-1]+"X").intern();
|
||||
//
|
||||
// Note: basing lastStringValue on the StringIndex won't work
|
||||
// with a multisearcher.
|
||||
|
||||
|
||||
return new ScoreDocComparator () {
|
||||
|
||||
public final int compare (final ScoreDoc i, final ScoreDoc j) {
|
||||
final int fi = index.order[i.doc];
|
||||
final int fj = index.order[j.doc];
|
||||
|
||||
// 0 is the magic position of null
|
||||
|
||||
/**** alternate logic
|
||||
if (fi < fj && fi != 0) return -1;
|
||||
if (fj < fi && fj != 0) return 1;
|
||||
if (fi==fj) return 0;
|
||||
return fi==0 ? 1 : -1;
|
||||
****/
|
||||
|
||||
if (fi==fj) return 0;
|
||||
if (fi==0) return 1;
|
||||
if (fj==0) return -1;
|
||||
return fi < fj ? -1 : 1;
|
||||
|
||||
}
|
||||
|
||||
public Comparable sortValue (final ScoreDoc i) {
|
||||
int f = index.order[i.doc];
|
||||
return (0 == f) ? missingValueProxy : index.lookup[f];
|
||||
}
|
||||
|
||||
public int sortType() {
|
||||
return SortField.CUSTOM;
|
||||
}
|
||||
};
|
||||
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,479 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.apache.lucene.search.*;
|
||||
import org.apache.lucene.search.function.*;
|
||||
import org.apache.lucene.queryParser.ParseException;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.index.Term;
|
||||
import org.apache.solr.core.SolrCore;
|
||||
import org.apache.solr.core.SolrException;
|
||||
import org.apache.solr.schema.IndexSchema;
|
||||
import org.apache.solr.schema.SchemaField;
|
||||
import org.apache.solr.schema.FieldType;
|
||||
|
||||
import java.util.ArrayList;
|
||||
import java.util.regex.Pattern;
|
||||
import java.util.logging.Level;
|
||||
import java.io.IOException;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: QueryParsing.java,v 1.10 2005/12/20 21:34:44 yonik Exp $
|
||||
*/
|
||||
public class QueryParsing {
|
||||
|
||||
public static Query parseQuery(String qs, IndexSchema schema) {
|
||||
try {
|
||||
Query query = new SolrQueryParser(schema).parse(qs);
|
||||
|
||||
if (SolrCore.log.isLoggable(Level.FINEST)) {
|
||||
SolrCore.log.finest("After QueryParser:" + query);
|
||||
}
|
||||
|
||||
return query;
|
||||
|
||||
} catch (ParseException e) {
|
||||
SolrCore.log(e);
|
||||
throw new SolrException(400,"Error parsing Lucene query",e);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
/***
|
||||
* SortSpec encapsulates a Lucene Sort and a count of the number of documents
|
||||
* to return.
|
||||
*/
|
||||
public static class SortSpec {
|
||||
private final Sort sort;
|
||||
private final int num;
|
||||
|
||||
SortSpec(Sort sort, int num) {
|
||||
this.sort=sort;
|
||||
this.num=num;
|
||||
}
|
||||
|
||||
/**
|
||||
* Gets the Lucene Sort object, or null for the default sort
|
||||
* by score descending.
|
||||
*/
|
||||
public Sort getSort() { return sort; }
|
||||
|
||||
/**
|
||||
* Gets the number of documens to return after sorting.
|
||||
* -1 means there is no cutoff (only do the sort)
|
||||
* @return
|
||||
*/
|
||||
public int getCount() { return num; }
|
||||
}
|
||||
|
||||
|
||||
private static Pattern sortSeparator = Pattern.compile("[\\s,]+");
|
||||
|
||||
/**
|
||||
* Returns null if the sortSpec string doesn't look like a sort specification,
|
||||
* or if the sort specification couldn't be converted into a Lucene Sort
|
||||
* (because of a field not being indexed or undefined, etc).
|
||||
*
|
||||
* The form of the sort specification string currently parsed is:
|
||||
* SortSpec ::= SingleSort [, SingleSort]* <number>?
|
||||
* SingleSort ::= <fieldname> SortDirection
|
||||
* SortDirection ::= top | desc | bottom | asc
|
||||
*
|
||||
* Examples:
|
||||
* top 10 #take the top 10 by score
|
||||
* desc 10 #take the top 10 by score
|
||||
* score desc 10 #take the top 10 by score
|
||||
* weight bottom 10 #sort by weight ascending and take the first 10
|
||||
* weight desc #sort by weight descending
|
||||
* height desc,weight desc #sort by height descending, and use weight descending to break any ties
|
||||
* height desc,weight asc top 20 #sort by height descending, using weight ascending as a tiebreaker
|
||||
*
|
||||
*/
|
||||
public static SortSpec parseSort(String sortSpec, IndexSchema schema) {
|
||||
if (sortSpec==null || sortSpec.length()==0) return null;
|
||||
|
||||
// I wonder how fast the regex is??? as least we cache the pattern.
|
||||
String[] parts = sortSeparator.split(sortSpec.trim(),0);
|
||||
if (parts.length == 0) return null;
|
||||
|
||||
ArrayList<SortField> lst = new ArrayList<SortField>();
|
||||
int num=-1;
|
||||
|
||||
int pos=0;
|
||||
String fn;
|
||||
boolean top=true;
|
||||
boolean normalSortOnScore=false;
|
||||
|
||||
while (pos < parts.length) {
|
||||
String str=parts[pos];
|
||||
if ("top".equals(str) || "bottom".equals(str) || "asc".equals(str) || "desc".equals(str)) {
|
||||
// if the field name seems to be missing, default to "score".
|
||||
// note that this will mess up a field name that has the same name
|
||||
// as a sort direction specifier.
|
||||
fn="score";
|
||||
} else {
|
||||
fn=str;
|
||||
pos++;
|
||||
}
|
||||
|
||||
// get the direction of the sort
|
||||
str=parts[pos];
|
||||
if ("top".equals(str) || "desc".equals(str)) {
|
||||
top=true;
|
||||
} else if ("bottom".equals(str) || "asc".equals(str)) {
|
||||
top=false;
|
||||
} else {
|
||||
return null; // must not be a sort command
|
||||
}
|
||||
|
||||
// get the field to sort on
|
||||
// hmmm - should there be a fake/pseudo-field named "score" in the schema?
|
||||
if ("score".equals(fn)) {
|
||||
if (top) {
|
||||
normalSortOnScore=true;
|
||||
lst.add(SortField.FIELD_SCORE);
|
||||
} else {
|
||||
lst.add(new SortField(null, SortField.SCORE, true));
|
||||
}
|
||||
} else {
|
||||
// getField could throw an exception if the name isn't found
|
||||
try {
|
||||
SchemaField f = schema.getField(fn);
|
||||
if (f == null || !f.indexed()) return null;
|
||||
lst.add(f.getType().getSortField(f,top));
|
||||
} catch (Exception e) {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
pos++;
|
||||
|
||||
// If there is a leftover part, assume it is a count
|
||||
if (pos+1 == parts.length) {
|
||||
try {
|
||||
num = Integer.parseInt(parts[pos]);
|
||||
} catch (Exception e) {
|
||||
return null;
|
||||
}
|
||||
pos++;
|
||||
}
|
||||
}
|
||||
|
||||
Sort sort;
|
||||
if (normalSortOnScore && lst.size() == 1) {
|
||||
// Normalize the default sort on score descending to sort=null
|
||||
sort=null;
|
||||
} else {
|
||||
sort = new Sort((SortField[]) lst.toArray(new SortField[lst.size()]));
|
||||
}
|
||||
return new SortSpec(sort,num);
|
||||
}
|
||||
|
||||
|
||||
///////////////////////////
|
||||
///////////////////////////
|
||||
///////////////////////////
|
||||
|
||||
static FieldType writeFieldName(String name, IndexSchema schema, Appendable out, int flags) throws IOException {
|
||||
FieldType ft = null;
|
||||
ft = schema.getFieldTypeNoEx(name);
|
||||
out.append(name);
|
||||
if (ft==null) {
|
||||
out.append("(UNKNOWN FIELD "+name+')');
|
||||
}
|
||||
out.append(':');
|
||||
return ft;
|
||||
}
|
||||
|
||||
static void writeFieldVal(String val, FieldType ft, Appendable out, int flags) throws IOException {
|
||||
if (ft!=null) {
|
||||
out.append(ft.toExternal(new Field("",val,true,true,false)));
|
||||
} else {
|
||||
out.append(val);
|
||||
}
|
||||
}
|
||||
|
||||
public static void toString(Query query, IndexSchema schema, Appendable out, int flags) throws IOException {
|
||||
boolean writeBoost=true;
|
||||
|
||||
if (query instanceof TermQuery) {
|
||||
TermQuery q = (TermQuery)query;
|
||||
Term t = q.getTerm();
|
||||
FieldType ft = writeFieldName(t.field(), schema, out, flags);
|
||||
writeFieldVal(t.text(), ft, out, flags);
|
||||
} else if (query instanceof RangeQuery) {
|
||||
RangeQuery q = (RangeQuery)query;
|
||||
String fname = q.getField();
|
||||
FieldType ft = writeFieldName(fname, schema, out, flags);
|
||||
out.append( q.isInclusive() ? '[' : '{' );
|
||||
Term lt = q.getLowerTerm();
|
||||
Term ut = q.getUpperTerm();
|
||||
if (lt==null) {
|
||||
out.append('*');
|
||||
} else {
|
||||
writeFieldVal(lt.text(), ft, out, flags);
|
||||
}
|
||||
|
||||
out.append(" TO ");
|
||||
|
||||
if (ut==null) {
|
||||
out.append('*');
|
||||
} else {
|
||||
writeFieldVal(ut.text(), ft, out, flags);
|
||||
}
|
||||
|
||||
out.append( q.isInclusive() ? ']' : '}' );
|
||||
|
||||
} else if (query instanceof ConstantScoreRangeQuery) {
|
||||
ConstantScoreRangeQuery q = (ConstantScoreRangeQuery)query;
|
||||
String fname = q.getField();
|
||||
FieldType ft = writeFieldName(fname, schema, out, flags);
|
||||
out.append( q.includesLower() ? '[' : '{' );
|
||||
String lt = q.getLowerVal();
|
||||
String ut = q.getUpperVal();
|
||||
if (lt==null) {
|
||||
out.append('*');
|
||||
} else {
|
||||
writeFieldVal(lt, ft, out, flags);
|
||||
}
|
||||
|
||||
out.append(" TO ");
|
||||
|
||||
if (ut==null) {
|
||||
out.append('*');
|
||||
} else {
|
||||
writeFieldVal(ut, ft, out, flags);
|
||||
}
|
||||
|
||||
out.append( q.includesUpper() ? ']' : '}' );
|
||||
} else if (query instanceof BooleanQuery) {
|
||||
BooleanQuery q = (BooleanQuery)query;
|
||||
boolean needParens=false;
|
||||
|
||||
if (q.getBoost() != 1.0 || q.getMinimumNumberShouldMatch() != 0) {
|
||||
needParens=true;
|
||||
}
|
||||
if (needParens) {
|
||||
out.append('(');
|
||||
}
|
||||
BooleanClause[] clauses = q.getClauses();
|
||||
boolean first=true;
|
||||
for (BooleanClause c : clauses) {
|
||||
if (!first) {
|
||||
out.append(' ');
|
||||
} else {
|
||||
first=false;
|
||||
}
|
||||
|
||||
if (c.prohibited) {
|
||||
out.append('-');
|
||||
} else if (c.required) {
|
||||
out.append('+');
|
||||
}
|
||||
Query subQuery = c.query;
|
||||
boolean wrapQuery=false;
|
||||
|
||||
// TODO: may need to put parens around other types
|
||||
// of queries too, depending on future syntax.
|
||||
if (subQuery instanceof BooleanQuery) {
|
||||
wrapQuery=true;
|
||||
}
|
||||
|
||||
if (wrapQuery) {
|
||||
out.append('(');
|
||||
}
|
||||
|
||||
toString(subQuery, schema, out, flags);
|
||||
|
||||
if (wrapQuery) {
|
||||
out.append(')');
|
||||
}
|
||||
}
|
||||
|
||||
if (needParens) {
|
||||
out.append(')');
|
||||
}
|
||||
if (q.getMinimumNumberShouldMatch()>0) {
|
||||
out.append('~');
|
||||
out.append(Integer.toString(q.getMinimumNumberShouldMatch()));
|
||||
}
|
||||
|
||||
} else if (query instanceof PrefixQuery) {
|
||||
PrefixQuery q = (PrefixQuery)query;
|
||||
Term prefix = q.getPrefix();
|
||||
FieldType ft = writeFieldName(prefix.field(), schema, out, flags);
|
||||
out.append(prefix.text());
|
||||
out.append('*');
|
||||
} else if (query instanceof ConstantScorePrefixQuery) {
|
||||
ConstantScorePrefixQuery q = (ConstantScorePrefixQuery)query;
|
||||
Term prefix = q.getPrefix();
|
||||
FieldType ft = writeFieldName(prefix.field(), schema, out, flags);
|
||||
out.append(prefix.text());
|
||||
out.append('*');
|
||||
} else if (query instanceof WildcardQuery) {
|
||||
out.append(query.toString());
|
||||
writeBoost=false;
|
||||
} else if (query instanceof FuzzyQuery) {
|
||||
out.append(query.toString());
|
||||
writeBoost=false;
|
||||
} else if (query instanceof ConstantScoreQuery) {
|
||||
out.append(query.toString());
|
||||
writeBoost=false;
|
||||
} else {
|
||||
out.append(query.getClass().getSimpleName()
|
||||
+ '(' + query.toString() + ')' );
|
||||
writeBoost=false;
|
||||
}
|
||||
|
||||
if (writeBoost && query.getBoost() != 1.0f) {
|
||||
out.append("^");
|
||||
out.append(Float.toString(query.getBoost()));
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
public static String toString(Query query, IndexSchema schema) {
|
||||
try {
|
||||
StringBuilder sb = new StringBuilder();
|
||||
toString(query, schema, sb, 0);
|
||||
return sb.toString();
|
||||
} catch (Exception e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
// simple class to help with parsing a string
|
||||
private static class StrParser {
|
||||
String val;
|
||||
int pos;
|
||||
int end;
|
||||
|
||||
StrParser(String val) {this.val = val; end=val.length(); }
|
||||
|
||||
void eatws() {
|
||||
while (pos<end && Character.isWhitespace(val.charAt(pos))) pos++;
|
||||
}
|
||||
|
||||
boolean opt(String s) {
|
||||
eatws();
|
||||
int slen=s.length();
|
||||
if (val.regionMatches(pos, s, 0, slen)) {
|
||||
pos+=slen;
|
||||
return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
void expect(String s) throws ParseException {
|
||||
eatws();
|
||||
int slen=s.length();
|
||||
if (val.regionMatches(pos, s, 0, slen)) {
|
||||
pos+=slen;
|
||||
} else {
|
||||
throw new ParseException("Expected '"+s+"' at position " + pos + " in '"+val+"'");
|
||||
}
|
||||
}
|
||||
|
||||
float getFloat() throws ParseException {
|
||||
eatws();
|
||||
char[] arr = new char[end-pos];
|
||||
int i;
|
||||
for (i=0; i<arr.length; i++) {
|
||||
char ch = val.charAt(pos);
|
||||
if ( (ch>='0' && ch<='9')
|
||||
|| ch=='+' || ch=='-'
|
||||
|| ch=='.' || ch=='e' || ch=='E'
|
||||
) {
|
||||
pos++;
|
||||
arr[i]=ch;
|
||||
} else {
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
return Float.parseFloat(new String(arr,0,i));
|
||||
}
|
||||
|
||||
String getId() throws ParseException {
|
||||
eatws();
|
||||
int id_start=pos;
|
||||
while (pos<end && Character.isJavaIdentifierPart(val.charAt(pos))) pos++;
|
||||
return val.substring(id_start, pos);
|
||||
}
|
||||
|
||||
char peek() {
|
||||
eatws();
|
||||
return pos<end ? val.charAt(pos) : 0;
|
||||
}
|
||||
|
||||
public String toString() {
|
||||
return "'" + val + "'" + ", pos=" + pos;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
private static ValueSource parseValSource(StrParser sp, IndexSchema schema) throws ParseException {
|
||||
String id = sp.getId();
|
||||
if (sp.opt("(")) {
|
||||
// a function: could contain a fieldname or another function.
|
||||
ValueSource vs=null;
|
||||
if (id.equals("ord")) {
|
||||
String field = sp.getId();
|
||||
vs = new OrdFieldSource(field);
|
||||
} else if (id.equals("rord")) {
|
||||
String field = sp.getId();
|
||||
vs = new ReverseOrdFieldSource(field);
|
||||
} else if (id.equals("linear")) {
|
||||
ValueSource source = parseValSource(sp, schema);
|
||||
sp.expect(",");
|
||||
float slope = sp.getFloat();
|
||||
sp.expect(",");
|
||||
float intercept = sp.getFloat();
|
||||
vs = new LinearFloatFunction(source,slope,intercept);
|
||||
} else if (id.equals("recip")) {
|
||||
ValueSource source = parseValSource(sp,schema);
|
||||
sp.expect(",");
|
||||
float m = sp.getFloat();
|
||||
sp.expect(",");
|
||||
float a = sp.getFloat();
|
||||
sp.expect(",");
|
||||
float b = sp.getFloat();
|
||||
vs = new ReciprocalFloatFunction(source,m,a,b);
|
||||
} else {
|
||||
throw new ParseException("Unknown function " + id + " in FunctionQuery(" + sp + ")");
|
||||
}
|
||||
sp.expect(")");
|
||||
return vs;
|
||||
}
|
||||
|
||||
SchemaField f = schema.getField(id);
|
||||
return f.getType().getValueSource(f);
|
||||
}
|
||||
|
||||
/** Parse a function, returning a FunctionQuery
|
||||
*/
|
||||
public static FunctionQuery parseFunction(String func, IndexSchema schema) throws ParseException {
|
||||
return new FunctionQuery(parseValSource(new StrParser(func), schema));
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,107 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.apache.lucene.search.Query;
|
||||
import org.apache.lucene.search.Sort;
|
||||
import org.apache.lucene.search.SortField;
|
||||
|
||||
import java.util.List;
|
||||
|
||||
/** A hash key encapsulating a query, a list of filters, and a sort
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public final class QueryResultKey {
|
||||
final Query query;
|
||||
final Sort sort; // change to normal Sort after Lucene 1.4.3
|
||||
final SortField[] sfields;
|
||||
final List<Query> filters;
|
||||
final int nc_flags; // non-comparable flags... ignored by hashCode and equals
|
||||
|
||||
private final int hc; // cached hashCode
|
||||
|
||||
private static SortField[] defaultSort = new SortField[0];
|
||||
|
||||
|
||||
public QueryResultKey(Query query, List<Query> filters, Sort sort, int nc_flags) {
|
||||
this.query = query;
|
||||
this.sort = sort;
|
||||
this.filters = filters;
|
||||
this.nc_flags = nc_flags;
|
||||
|
||||
int h = query.hashCode();
|
||||
|
||||
if (filters != null) h ^= filters.hashCode();
|
||||
|
||||
sfields = (this.sort !=null) ? this.sort.getSort() : defaultSort;
|
||||
for (SortField sf : sfields) {
|
||||
// mix the bits so that sortFields are position dependent
|
||||
// so that a,b won't hash to the same value as b,a
|
||||
h ^= (h << 8) | (h >>> 25); // reversible hash
|
||||
|
||||
if (sf.getField() != null) h += sf.getField().hashCode();
|
||||
h += sf.getType();
|
||||
if (sf.getReverse()) h=~h;
|
||||
if (sf.getLocale()!=null) h+=sf.getLocale().hashCode();
|
||||
if (sf.getFactory()!=null) h+=sf.getFactory().hashCode();
|
||||
}
|
||||
|
||||
hc = h;
|
||||
}
|
||||
|
||||
public int hashCode() {
|
||||
return hc;
|
||||
}
|
||||
|
||||
public boolean equals(Object o) {
|
||||
if (o==this) return true;
|
||||
if (!(o instanceof QueryResultKey)) return false;
|
||||
QueryResultKey other = (QueryResultKey)o;
|
||||
|
||||
// fast check of the whole hash code... most hash tables will only use
|
||||
// some of the bits, so if this is a hash collision, it's still likely
|
||||
// that the full cached hash code will be different.
|
||||
if (this.hc != other.hc) return false;
|
||||
|
||||
// check for the thing most likely to be different (and the fastest things)
|
||||
// first.
|
||||
if (this.sfields.length != other.sfields.length) return false;
|
||||
if (!this.query.equals(other.query)) return false;
|
||||
if (!isEqual(this.filters, other.filters)) return false;
|
||||
|
||||
for (int i=0; i<sfields.length; i++) {
|
||||
SortField sf1 = this.sfields[i];
|
||||
SortField sf2 = other.sfields[i];
|
||||
if (sf1.getType() != sf2.getType()) return false;
|
||||
if (sf1.getReverse() != sf2.getReverse()) return false;
|
||||
if (!isEqual(sf1.getField(),sf2.getField())) return false;
|
||||
if (!isEqual(sf1.getLocale(), sf2.getLocale())) return false;
|
||||
if (!isEqual(sf1.getFactory(), sf2.getFactory())) return false;
|
||||
// NOTE: the factory must be identical!!! use singletons!
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
private static boolean isEqual(Object o1, Object o2) {
|
||||
if (o1==o2) return true; // takes care of identity and null cases
|
||||
if (o1==null || o2==null) return false;
|
||||
return o1.equals(o2);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,102 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.apache.solr.core.SolrInfoMBean;
|
||||
|
||||
import java.util.Map;
|
||||
import java.util.logging.Logger;
|
||||
import java.io.IOException;
|
||||
|
||||
|
||||
/**
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: SolrCache.java,v 1.6 2005/06/21 05:26:43 yonik Exp $
|
||||
*/
|
||||
public interface SolrCache extends SolrInfoMBean {
|
||||
public final static Logger log = Logger.getLogger(SolrCache.class.getName());
|
||||
|
||||
|
||||
/**
|
||||
* The initialization routine. Instance specific arguments are passed in
|
||||
* the <code>args</code> map.
|
||||
* <p>
|
||||
* The persistence object will exist across different lifetimes of similar caches.
|
||||
* For example, all filter caches will share the same persistence object, sometimes
|
||||
* at the same time (it must be threadsafe). If null is passed, then the cache
|
||||
* implementation should create and return a new persistence object. If not null,
|
||||
* the passed in object should be returned again.
|
||||
* <p>
|
||||
* Since it will exist across the lifetime of many caches, care should be taken to
|
||||
* not reference any particular cache instance and prevent it from being
|
||||
* garbage collected (no using inner classes unless they are static).
|
||||
* <p>
|
||||
* Since the persistence object is designed to be used as a way for statistics
|
||||
* to accumulate across all instances of the same type of cache, however the
|
||||
* object may be of any type desired by the cache implementation.
|
||||
* <p>
|
||||
* The {@link CacheRegenerator} is what the cache uses during auto-warming to
|
||||
* renenerate an item in the new cache from an entry in the old cache.
|
||||
*
|
||||
*/
|
||||
public Object init(Map args, Object persistence, CacheRegenerator regenerator);
|
||||
// I don't think we need a factory for faster creation given that these
|
||||
// will be associated with slow-to-create SolrIndexSearchers.
|
||||
// change to NamedList when other plugins do?
|
||||
|
||||
// symbolic name for this cache
|
||||
public String name();
|
||||
|
||||
|
||||
// Should SolrCache just extend the java.util.Map interface?
|
||||
// Following the conventions of the java.util.Map interface in any case.
|
||||
|
||||
public int size();
|
||||
|
||||
public Object put(Object key, Object value);
|
||||
|
||||
public Object get(Object key);
|
||||
|
||||
public void clear();
|
||||
|
||||
|
||||
/**
|
||||
* Set different cache states.
|
||||
* The state a cache is in can have an effect on how statistics are kept.
|
||||
* The cache user (SolrIndexSearcher) will take care of switching
|
||||
* cache states.
|
||||
*/
|
||||
public enum State { CREATED, STATICWARMING, AUTOWARMING, LIVE }
|
||||
public void setState(State state);
|
||||
public State getState();
|
||||
|
||||
|
||||
/**
|
||||
* Warm this cache associated with <code>searcher</code> using the <code>old</code>
|
||||
* cache object. <code>this</code> and <code>old</code> will have the same concrete type.
|
||||
*/
|
||||
void warm(SolrIndexSearcher searcher, SolrCache old) throws IOException;
|
||||
// Q: an alternative to passing the searcher here would be to pass it in
|
||||
// init and have the cache implementation save it.
|
||||
|
||||
|
||||
/** Frees any non-memory resources */
|
||||
public void close();
|
||||
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,81 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.apache.lucene.queryParser.QueryParser;
|
||||
import org.apache.lucene.queryParser.ParseException;
|
||||
import org.apache.lucene.search.*;
|
||||
import org.apache.lucene.index.Term;
|
||||
import org.apache.solr.schema.IndexSchema;
|
||||
import org.apache.solr.schema.FieldType;
|
||||
|
||||
// TODO: implement the analysis of simple fields with
|
||||
// FieldType.toInternal() instead of going through the
|
||||
// analyzer. Should lead to faster query parsing.
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
*/
|
||||
public class SolrQueryParser extends QueryParser {
|
||||
protected final IndexSchema schema;
|
||||
|
||||
public SolrQueryParser(IndexSchema schema) {
|
||||
super(schema.getDefaultSearchFieldName(), schema.getQueryAnalyzer());
|
||||
this.schema = schema;
|
||||
setLowercaseExpandedTerms(false);
|
||||
}
|
||||
|
||||
protected Query getFieldQuery(String field, String queryText) throws ParseException {
|
||||
// intercept magic field name of "_" to use as a hook for our
|
||||
// own functions.
|
||||
if (field.equals("_val_")) {
|
||||
return QueryParsing.parseFunction(queryText, schema);
|
||||
}
|
||||
|
||||
// default to a normal field query
|
||||
return super.getFieldQuery(field, queryText);
|
||||
}
|
||||
|
||||
protected Query getRangeQuery(String field, String part1, String part2, boolean inclusive) throws ParseException {
|
||||
FieldType ft = schema.getFieldType(field);
|
||||
return new ConstantScoreRangeQuery(
|
||||
field,
|
||||
"*".equals(part1) ? null : ft.toInternal(part1),
|
||||
"*".equals(part2) ? null : ft.toInternal(part2),
|
||||
inclusive, inclusive);
|
||||
}
|
||||
|
||||
protected Query getPrefixQuery(String field, String termStr) throws ParseException {
|
||||
if (getLowercaseExpandedTerms()) {
|
||||
termStr = termStr.toLowerCase();
|
||||
}
|
||||
|
||||
// TODO: toInternal() won't necessarily work on partial
|
||||
// values, so it looks like i need a getPrefix() function
|
||||
// on fieldtype? Or at the minimum, a method on fieldType
|
||||
// that can tell me if I should lowercase or not...
|
||||
// Schema could tell if lowercase filter is in the chain,
|
||||
// but a more sure way would be to run something through
|
||||
// the first time and check if it got lowercased.
|
||||
|
||||
// TODO: throw exception of field type doesn't support prefixes?
|
||||
// (sortable numeric types don't do prefixes, but can do range queries)
|
||||
Term t = new Term(field, termStr);
|
||||
return new ConstantScorePrefixQuery(t);
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,37 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.apache.lucene.search.DefaultSimilarity;
|
||||
|
||||
import java.util.HashMap;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
*/
|
||||
// don't make it public for now... easier to change later.
|
||||
|
||||
// This class is currently unused.
|
||||
class SolrSimilarity extends DefaultSimilarity {
|
||||
private final HashMap<String,Float> lengthNormConfig = new HashMap<String,Float>();
|
||||
|
||||
public float lengthNorm(String fieldName, int numTerms) {
|
||||
// Float f = lengthNormConfig.
|
||||
// if (lengthNormDisabled.)
|
||||
return super.lengthNorm(fieldName, numTerms);
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,57 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search;
|
||||
|
||||
import org.apache.lucene.search.*;
|
||||
|
||||
/**
|
||||
* Extra lucene sorting utilities & convenience methods
|
||||
*
|
||||
* @author yonik
|
||||
* @version $Id: Sorting.java,v 1.1 2005/06/02 04:43:06 yonik Exp $
|
||||
*
|
||||
*/
|
||||
|
||||
public class Sorting {
|
||||
|
||||
|
||||
/** Returns a {@link SortField} for a string field.
|
||||
* If nullLast and nullFirst are both false, then default lucene string sorting is used where
|
||||
* null strings sort first in an ascending sort, and last in a descending sort.
|
||||
*
|
||||
* @param fieldName the name of the field to sort on
|
||||
* @param reverse true for a reverse (desc) sort
|
||||
* @param nullLast true if null should come last, regardless of sort order
|
||||
* @param nullFirst true if null should come first, regardless of sort order
|
||||
* @return SortField
|
||||
*/
|
||||
public static SortField getStringSortField(String fieldName, boolean reverse, boolean nullLast, boolean nullFirst) {
|
||||
if (nullLast) {
|
||||
if (!reverse) return new SortField(fieldName, nullStringLastComparatorSource);
|
||||
else return new SortField(fieldName, SortField.STRING, true);
|
||||
} else if (nullFirst) {
|
||||
if (reverse) return new SortField(fieldName, nullStringLastComparatorSource);
|
||||
else return new SortField(fieldName, SortField.STRING, false);
|
||||
} else {
|
||||
return new SortField(fieldName, SortField.STRING, reverse);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
static final SortComparatorSource nullStringLastComparatorSource = new MissingStringLastComparatorSource();
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,180 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.search.test;
|
||||
|
||||
import org.apache.solr.search.BitDocSet;
|
||||
import org.apache.solr.search.HashDocSet;
|
||||
import org.apache.solr.search.DocSet;
|
||||
|
||||
import java.util.Random;
|
||||
import java.util.BitSet;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
*/
|
||||
public class TestDocSet {
|
||||
|
||||
// use test instead of assert since asserts may be turned off
|
||||
public static void test(boolean condition) {
|
||||
if (!condition) {
|
||||
throw new RuntimeException("test requestHandler: assertion failed!");
|
||||
}
|
||||
}
|
||||
|
||||
static Random rand = new Random();
|
||||
|
||||
|
||||
static BitSet bs;
|
||||
static BitDocSet bds;
|
||||
static HashDocSet hds;
|
||||
static int[] ids; // not unique
|
||||
|
||||
static void generate(int maxSize, int bitsToSet) {
|
||||
bs = new BitSet(maxSize);
|
||||
ids = new int[bitsToSet];
|
||||
int count=0;
|
||||
if (maxSize>0) {
|
||||
for (int i=0; i<bitsToSet; i++) {
|
||||
int id=rand.nextInt(maxSize);
|
||||
if (!bs.get(id)) {
|
||||
bs.set(id);
|
||||
ids[count++]=id;
|
||||
}
|
||||
}
|
||||
}
|
||||
bds = new BitDocSet(bs,bitsToSet);
|
||||
hds = new HashDocSet(ids,0,count);
|
||||
}
|
||||
|
||||
|
||||
|
||||
public static void main(String[] args) {
|
||||
String bsSize=args[0];
|
||||
boolean randSize=false;
|
||||
|
||||
if (bsSize.endsWith("-")) {
|
||||
bsSize=bsSize.substring(0,bsSize.length()-1);
|
||||
randSize=true;
|
||||
}
|
||||
|
||||
int bitSetSize = Integer.parseInt(bsSize);
|
||||
int numSets = Integer.parseInt(args[1]);
|
||||
int numBitsSet = Integer.parseInt(args[2]);
|
||||
String test = args[3].intern();
|
||||
int iter = Integer.parseInt(args[4]);
|
||||
|
||||
int ret=0;
|
||||
|
||||
BitSet[] sets = new BitSet[numSets];
|
||||
DocSet[] bset = new DocSet[numSets];
|
||||
DocSet[] hset = new DocSet[numSets];
|
||||
BitSet scratch=new BitSet();
|
||||
|
||||
for (int i=0; i<numSets; i++) {
|
||||
generate(randSize ? rand.nextInt(bitSetSize) : bitSetSize, numBitsSet);
|
||||
sets[i] = bs;
|
||||
bset[i] = bds;
|
||||
hset[i] = hds;
|
||||
}
|
||||
|
||||
long start = System.currentTimeMillis();
|
||||
|
||||
if ("test".equals(test)) {
|
||||
for (int it=0; it<iter; it++) {
|
||||
generate(randSize ? rand.nextInt(bitSetSize) : bitSetSize, numBitsSet);
|
||||
BitSet bs1=bs;
|
||||
BitDocSet bds1=bds;
|
||||
HashDocSet hds1=hds;
|
||||
generate(randSize ? rand.nextInt(bitSetSize) : bitSetSize, numBitsSet);
|
||||
|
||||
BitSet res = ((BitSet)bs1.clone());
|
||||
res.and(bs);
|
||||
int icount = res.cardinality();
|
||||
|
||||
test(bds1.intersection(bds).size() == icount);
|
||||
test(bds1.intersectionSize(bds) == icount);
|
||||
if (bds1.intersection(hds).size() != icount) {
|
||||
DocSet ds = bds1.intersection(hds);
|
||||
System.out.println("STOP");
|
||||
}
|
||||
|
||||
test(bds1.intersection(hds).size() == icount);
|
||||
test(bds1.intersectionSize(hds) == icount);
|
||||
test(hds1.intersection(bds).size() == icount);
|
||||
test(hds1.intersectionSize(bds) == icount);
|
||||
test(hds1.intersection(hds).size() == icount);
|
||||
test(hds1.intersectionSize(hds) == icount);
|
||||
|
||||
ret += icount;
|
||||
}
|
||||
}
|
||||
|
||||
String type=null;
|
||||
String oper=null;
|
||||
|
||||
if (test.endsWith("B")) { type="B"; }
|
||||
if (test.endsWith("H")) { type="H"; }
|
||||
if (test.endsWith("M")) { type="M"; }
|
||||
if (test.startsWith("intersect")) oper="intersect";
|
||||
if (test.startsWith("intersectSize")) oper="intersectSize";
|
||||
if (test.startsWith("intersectAndSize")) oper="intersectSize";
|
||||
|
||||
|
||||
if (oper!=null) {
|
||||
for (int it=0; it<iter; it++) {
|
||||
int idx1 = rand.nextInt(numSets);
|
||||
int idx2 = rand.nextInt(numSets);
|
||||
DocSet a=null,b=null;
|
||||
|
||||
if (type=="B") {
|
||||
a=bset[idx1]; b=bset[idx2];
|
||||
} else if (type=="H") {
|
||||
a=hset[idx1]; b=bset[idx2];
|
||||
} else if (type=="M") {
|
||||
if (idx1 < idx2) {
|
||||
a=bset[idx1];
|
||||
b=hset[idx2];
|
||||
} else {
|
||||
a=hset[idx1];
|
||||
b=bset[idx2];
|
||||
}
|
||||
}
|
||||
|
||||
if (oper=="intersect") {
|
||||
DocSet res = a.intersection(b);
|
||||
ret += res.memSize();
|
||||
} else if (oper=="intersectSize") {
|
||||
ret += a.intersectionSize(b);
|
||||
} else if (oper=="intersectAndSize") {
|
||||
DocSet res = a.intersection(b);
|
||||
ret += res.size();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
|
||||
long end = System.currentTimeMillis();
|
||||
System.out.println("TIME="+(end-start));
|
||||
|
||||
// System.out.println("ret="+ret + " scratchsize="+scratch.size());
|
||||
System.out.println("ret="+ret);
|
||||
}
|
||||
|
||||
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,149 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.tst;
|
||||
|
||||
import org.apache.lucene.search.*;
|
||||
import org.apache.lucene.document.Document;
|
||||
|
||||
import java.util.List;
|
||||
import java.util.logging.Level;
|
||||
import java.io.IOException;
|
||||
import java.net.URL;
|
||||
|
||||
import org.apache.solr.util.StrUtils;
|
||||
import org.apache.solr.util.NamedList;
|
||||
import org.apache.solr.search.DocSlice;
|
||||
import org.apache.solr.search.QueryParsing;
|
||||
import org.apache.solr.core.SolrCore;
|
||||
import org.apache.solr.request.SolrRequestHandler;
|
||||
import org.apache.solr.request.SolrQueryResponse;
|
||||
import org.apache.solr.request.SolrQueryRequest;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: OldRequestHandler.java,v 1.7 2005/12/02 04:31:05 yonik Exp $
|
||||
*/
|
||||
|
||||
|
||||
public class OldRequestHandler implements SolrRequestHandler {
|
||||
|
||||
long numRequests;
|
||||
long numErrors;
|
||||
|
||||
public void init(NamedList args) {
|
||||
SolrCore.log.log(Level.INFO, "Unused request handler arguments:" + args);
|
||||
}
|
||||
|
||||
|
||||
public void handleRequest(SolrQueryRequest req, SolrQueryResponse rsp) {
|
||||
numRequests++;
|
||||
|
||||
Query query = null;
|
||||
Filter filter = null;
|
||||
|
||||
List<String> commands = StrUtils.splitSmart(req.getQueryString(),';');
|
||||
|
||||
String qs = commands.size() >= 1 ? commands.get(0) : "";
|
||||
query = QueryParsing.parseQuery(qs, req.getSchema());
|
||||
|
||||
// If the first non-query, non-filter command is a simple sort on an indexed field, then
|
||||
// we can use the Lucene sort ability.
|
||||
Sort sort = null;
|
||||
if (commands.size() >= 2) {
|
||||
QueryParsing.SortSpec sortSpec = QueryParsing.parseSort(commands.get(1), req.getSchema());
|
||||
if (sortSpec != null) {
|
||||
sort = sortSpec.getSort();
|
||||
// ignore the count for now... it's currently only controlled by start & limit on req
|
||||
// count = sortSpec.getCount();
|
||||
}
|
||||
}
|
||||
|
||||
Hits hits=null;
|
||||
|
||||
try {
|
||||
hits = req.getSearcher().search(query,filter,sort);
|
||||
|
||||
int numHits = hits.length();
|
||||
int startRow = Math.min(numHits, req.getStart());
|
||||
int endRow = Math.min(numHits,req.getStart()+req.getLimit());
|
||||
int numRows = endRow-startRow;
|
||||
|
||||
int[] ids = new int[numRows];
|
||||
Document[] data = new Document[numRows];
|
||||
for (int i=startRow; i<endRow; i++) {
|
||||
ids[i] = hits.id(i);
|
||||
data[i] = hits.doc(i);
|
||||
}
|
||||
|
||||
rsp.add(null, new DocSlice(0,numRows,ids,null,numHits,0.0f));
|
||||
|
||||
/***********************
|
||||
rsp.setResults(new DocSlice(0,numRows,ids,null,numHits));
|
||||
|
||||
// Setting the actual document objects is optional
|
||||
rsp.setResults(data);
|
||||
************************/
|
||||
} catch (IOException e) {
|
||||
rsp.setException(e);
|
||||
numErrors++;
|
||||
return;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
public String getName() {
|
||||
return OldRequestHandler.class.getName();
|
||||
}
|
||||
|
||||
public String getVersion() {
|
||||
return SolrCore.version;
|
||||
}
|
||||
|
||||
public String getDescription() {
|
||||
return "The original Hits based request handler";
|
||||
}
|
||||
|
||||
public Category getCategory() {
|
||||
return Category.QUERYHANDLER;
|
||||
}
|
||||
|
||||
public String getCvsId() {
|
||||
return "$Id: OldRequestHandler.java,v 1.7 2005/12/02 04:31:05 yonik Exp $";
|
||||
}
|
||||
|
||||
public String getCvsName() {
|
||||
return "$Name: $";
|
||||
}
|
||||
|
||||
public String getCvsSource() {
|
||||
return "$Source: /cvs/main/searching/solr/solarcore/src/solr/tst/OldRequestHandler.java,v $";
|
||||
}
|
||||
|
||||
public URL[] getDocs() {
|
||||
return null;
|
||||
}
|
||||
|
||||
public NamedList getStatistics() {
|
||||
NamedList lst = new NamedList();
|
||||
lst.add("requests", numRequests);
|
||||
lst.add("errors", numErrors);
|
||||
return lst;
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,300 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.tst;
|
||||
|
||||
import org.apache.lucene.search.*;
|
||||
import org.apache.lucene.document.Document;
|
||||
import org.apache.lucene.document.Field;
|
||||
import org.apache.lucene.index.IndexReader;
|
||||
|
||||
import java.util.*;
|
||||
import java.util.regex.Pattern;
|
||||
import java.util.logging.Logger;
|
||||
import java.util.logging.Level;
|
||||
import java.net.URL;
|
||||
|
||||
import org.apache.solr.util.StrUtils;
|
||||
import org.apache.solr.util.NamedList;
|
||||
import org.apache.solr.search.*;
|
||||
import org.apache.solr.core.SolrCore;
|
||||
import org.apache.solr.core.SolrException;
|
||||
import org.apache.solr.request.SolrRequestHandler;
|
||||
import org.apache.solr.request.SolrQueryRequest;
|
||||
import org.apache.solr.request.SolrQueryResponse;
|
||||
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id: TestRequestHandler.java,v 1.19 2005/12/02 04:31:05 yonik Exp $
|
||||
*/
|
||||
|
||||
public class TestRequestHandler implements SolrRequestHandler {
|
||||
private static Logger log = Logger.getLogger(SolrIndexSearcher.class.getName());
|
||||
|
||||
public void init(NamedList args) {
|
||||
SolrCore.log.log(Level.INFO, "Unused request handler arguments:" + args);
|
||||
}
|
||||
|
||||
|
||||
|
||||
// use test instead of assert since asserts may be turned off
|
||||
public void test(boolean condition) {
|
||||
try {
|
||||
if (!condition) {
|
||||
throw new RuntimeException("test requestHandler: assertion failed!");
|
||||
}
|
||||
} catch (RuntimeException e) {
|
||||
SolrException.log(log,e);
|
||||
throw(e);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
private long numRequests;
|
||||
private long numErrors;
|
||||
|
||||
private final Pattern splitList=Pattern.compile(",| ");
|
||||
|
||||
|
||||
public void handleRequest(SolrQueryRequest req, SolrQueryResponse rsp) {
|
||||
numRequests++;
|
||||
|
||||
// TODO: test if lucene will accept an escaped ';', otherwise
|
||||
// we need to un-escape them before we pass to QueryParser
|
||||
try {
|
||||
String sreq = req.getQueryString();
|
||||
if (sreq==null) throw new SolrException(400,"Missing queryString");
|
||||
List<String> commands = StrUtils.splitSmart(sreq,';');
|
||||
|
||||
String qs = commands.size() >= 1 ? commands.get(0) : "";
|
||||
Query query = QueryParsing.parseQuery(qs, req.getSchema());
|
||||
|
||||
// find fieldnames to return (fieldlist)
|
||||
String fl = req.getParam("fl");
|
||||
int flags=0;
|
||||
if (fl != null) {
|
||||
// TODO - this could become more efficient if widely used.
|
||||
// TODO - should field order be maintained?
|
||||
String[] flst = splitList.split(fl,0);
|
||||
if (flst.length > 0 && !(flst.length==1 && flst[0].length()==0)) {
|
||||
Set<String> set = new HashSet<String>();
|
||||
for (String fname : flst) {
|
||||
if ("score".equals(fname)) flags |= SolrIndexSearcher.GET_SCORES;
|
||||
set.add(fname);
|
||||
}
|
||||
rsp.setReturnFields(set);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// If the first non-query, non-filter command is a simple sort on an indexed field, then
|
||||
// we can use the Lucene sort ability.
|
||||
Sort sort = null;
|
||||
if (commands.size() >= 2) {
|
||||
QueryParsing.SortSpec sortSpec = QueryParsing.parseSort(commands.get(1), req.getSchema());
|
||||
if (sortSpec != null) {
|
||||
sort = sortSpec.getSort();
|
||||
// ignore the count for now... it's currently only controlled by start & limit on req
|
||||
// count = sortSpec.getCount();
|
||||
}
|
||||
}
|
||||
|
||||
SolrIndexSearcher searcher = req.getSearcher();
|
||||
|
||||
/***
|
||||
Object o = searcher.cacheLookup("dfllNode", query);
|
||||
if (o == null) {
|
||||
searcher.cacheInsert("dfllNode",query,"Hello Bob");
|
||||
} else {
|
||||
System.out.println("User Cache Hit On " + o);
|
||||
}
|
||||
***/
|
||||
|
||||
int start=req.getStart();
|
||||
int limit=req.getLimit();
|
||||
|
||||
Query filterQuery=null;
|
||||
DocSet filter=null;
|
||||
Filter lfilter=null;
|
||||
|
||||
DocList results = req.getSearcher().getDocList(query, null, sort, req.getStart(), req.getLimit(), flags);
|
||||
rsp.add(null, results);
|
||||
|
||||
|
||||
if (qs.startsWith("values")) {
|
||||
rsp.add("testname1","testval1");
|
||||
|
||||
rsp.add("testarr1",new String[]{"my val 1","my val 2"});
|
||||
|
||||
NamedList nl = new NamedList();
|
||||
nl.add("myInt", 333);
|
||||
nl.add("myNullVal", null);
|
||||
nl.add("myFloat",1.414213562f);
|
||||
nl.add("myDouble", 1e100d);
|
||||
nl.add("myBool", false);
|
||||
nl.add("myLong",999999999999L);
|
||||
|
||||
Document doc = new Document();
|
||||
doc.add(new Field("id","55",true,true,false));
|
||||
nl.add("myDoc",doc);
|
||||
|
||||
nl.add("myResult",results);
|
||||
nl.add("myStr","&wow! test escaping: a&b<c&");
|
||||
nl.add(null, "this value had a null name...");
|
||||
nl.add("myIntArray", new Integer[] { 100, 5, -10, 42 });
|
||||
nl.add("epoch", new Date(0));
|
||||
nl.add("currDate", new Date(System.currentTimeMillis()));
|
||||
rsp.add("myNamedList", nl);
|
||||
} else if (qs.startsWith("fields")) {
|
||||
NamedList nl = new NamedList();
|
||||
Collection flst;
|
||||
flst = searcher.getReader().getFieldNames(IndexReader.FieldOption.INDEXED);
|
||||
nl.add("indexed",flst);
|
||||
flst = searcher.getReader().getFieldNames(IndexReader.FieldOption.UNINDEXED);
|
||||
nl.add("unindexed",flst);
|
||||
rsp.add("fields", nl);
|
||||
}
|
||||
|
||||
test(results.size() <= limit);
|
||||
test(results.size() <= results.matches());
|
||||
// System.out.println("limit="+limit+" results.size()="+results.size()+" matches="+results.matches());
|
||||
test((start==0 && limit>=results.matches()) ? results.size()==results.matches() : true );
|
||||
|
||||
//
|
||||
// test against hits
|
||||
//
|
||||
Hits hits = searcher.search(query, lfilter, sort);
|
||||
test(hits.length() == results.matches());
|
||||
|
||||
|
||||
DocList rrr2 = results.subset(start,limit);
|
||||
test(rrr2 == results);
|
||||
|
||||
DocIterator iter=results.iterator();
|
||||
|
||||
|
||||
/***
|
||||
for (int i=0; i<hits.length(); i++) {
|
||||
System.out.println("doc="+hits.id(i) + " score="+hits.score(i));
|
||||
}
|
||||
***/
|
||||
|
||||
for (int i=0; i<results.size(); i++) {
|
||||
test( iter.nextDoc() == hits.id(i+results.offset()) );
|
||||
|
||||
// Document doesn't implement equals()
|
||||
// test( searcher.document(i).equals(hits.doc(i)));
|
||||
}
|
||||
|
||||
|
||||
DocList results2 = req.getSearcher().getDocList(query,query,sort,start,limit);
|
||||
test(results2.size()==results.size() && results2.matches()==results.matches());
|
||||
DocList results3 = req.getSearcher().getDocList(query,query,null,start,limit);
|
||||
test(results3.size()==results.size() && results3.matches()==results.matches());
|
||||
|
||||
//
|
||||
// getting both the list and set
|
||||
//
|
||||
DocListAndSet both = searcher.getDocListAndSet(query,filter,sort,start, limit);
|
||||
test( both.docList.equals(results) );
|
||||
test( both.docList.matches() == both.docSet.size() );
|
||||
test( (start==0 && both.docSet.size() <= limit) ? both.docSet.equals(both.docList) : true);
|
||||
|
||||
// use the result set as a filter itself...
|
||||
DocListAndSet both2 = searcher.getDocListAndSet(query,both.docSet,sort,start, limit);
|
||||
test( both2.docList.equals(both.docList) );
|
||||
test( both2.docSet.equals(both.docSet) );
|
||||
|
||||
BitSet bits = both.docSet.getBits();
|
||||
BitSet neg = ((BitSet)bits.clone());
|
||||
neg.flip(0, bits.length());
|
||||
|
||||
// use the negative as a filter (should result in 0 matches)
|
||||
// todo - fix if filter is not null
|
||||
both2 = searcher.getDocListAndSet(query,new BitDocSet(neg),sort, start, limit);
|
||||
test( both2.docList.size() == 0 );
|
||||
test( both2.docList.matches() == 0 );
|
||||
test( both2.docSet.size() == 0 );
|
||||
|
||||
DocSet allResults=searcher.getDocSet(query,filter);
|
||||
test ( allResults.equals(both.docSet) );
|
||||
|
||||
if (filter != null) {
|
||||
DocSet res=searcher.getDocSet(query);
|
||||
test( res.size() >= results.size() );
|
||||
test( res.intersection(filter).equals(both.docSet));
|
||||
|
||||
test( res.intersectionSize(filter) == both.docSet.size() );
|
||||
if (filterQuery != null) {
|
||||
test( searcher.numDocs(filterQuery,res) == both.docSet.size() );
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
} catch (Exception e) {
|
||||
rsp.setException(e);
|
||||
numErrors++;
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
//////////////////////// SolrInfoMBeans methods //////////////////////
|
||||
|
||||
|
||||
public String getName() {
|
||||
return TestRequestHandler.class.getName();
|
||||
}
|
||||
|
||||
public String getVersion() {
|
||||
return SolrCore.version;
|
||||
}
|
||||
|
||||
public String getDescription() {
|
||||
return "A test handler that runs some sanity checks on results";
|
||||
}
|
||||
|
||||
public Category getCategory() {
|
||||
return Category.QUERYHANDLER;
|
||||
}
|
||||
|
||||
public String getCvsId() {
|
||||
return "$Id: TestRequestHandler.java,v 1.19 2005/12/02 04:31:05 yonik Exp $";
|
||||
}
|
||||
|
||||
public String getCvsName() {
|
||||
return "$Name: $";
|
||||
}
|
||||
|
||||
public String getCvsSource() {
|
||||
return "$Source: /cvs/main/searching/solr/solarcore/src/solr/tst/TestRequestHandler.java,v $";
|
||||
}
|
||||
|
||||
public URL[] getDocs() {
|
||||
return null;
|
||||
}
|
||||
|
||||
public NamedList getStatistics() {
|
||||
NamedList lst = new NamedList();
|
||||
lst.add("requests", numRequests);
|
||||
lst.add("errors", numErrors);
|
||||
return lst;
|
||||
}
|
||||
|
||||
|
||||
|
||||
}
|
||||
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.update;
|
||||
|
||||
import org.apache.lucene.document.Document;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class AddUpdateCommand extends UpdateCommand {
|
||||
public String id;
|
||||
public Document doc;
|
||||
public boolean allowDups;
|
||||
public boolean overwritePending;
|
||||
public boolean overwriteCommitted;
|
||||
|
||||
public AddUpdateCommand() {
|
||||
super("add");
|
||||
}
|
||||
|
||||
public String toString() {
|
||||
StringBuilder sb = new StringBuilder(commandName);
|
||||
sb.append(':');
|
||||
if (id!=null) sb.append("id=").append(id);
|
||||
sb.append(",allowDups=").append(allowDups);
|
||||
sb.append(",overwritePending=").append(overwritePending);
|
||||
sb.append(",overwriteCommitted=").append(overwriteCommitted);
|
||||
return sb.toString();
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,37 @@
|
|||
/**
|
||||
* Copyright 2006 The Apache Software Foundation
|
||||
*
|
||||
* Licensed under the Apache License, Version 2.0 (the "License");
|
||||
* you may not use this file except in compliance with the License.
|
||||
* You may obtain a copy of the License at
|
||||
*
|
||||
* http://www.apache.org/licenses/LICENSE-2.0
|
||||
*
|
||||
* Unless required by applicable law or agreed to in writing, software
|
||||
* distributed under the License is distributed on an "AS IS" BASIS,
|
||||
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
* See the License for the specific language governing permissions and
|
||||
* limitations under the License.
|
||||
*/
|
||||
|
||||
package org.apache.solr.update;
|
||||
/**
|
||||
* @author yonik
|
||||
* @version $Id$
|
||||
*/
|
||||
public class CommitUpdateCommand extends UpdateCommand {
|
||||
public boolean optimize;
|
||||
public boolean waitFlush;
|
||||
public boolean waitSearcher=true;
|
||||
|
||||
public CommitUpdateCommand(boolean optimize) {
|
||||
super("commit");
|
||||
this.optimize=optimize;
|
||||
}
|
||||
public String toString() {
|
||||
return "commit(optimize="+optimize
|
||||
+",waitFlush="+waitFlush
|
||||
+",waitSearcher="+waitSearcher
|
||||
+')';
|
||||
}
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue