Hi Grant,
Here are solr config files (attached) and java code (included below) to
recreate the test case.
Jason
List<Pair<String, Integer>> terms = new ArrayList<Pair<String,
Integer>>();
terms.add(new Pair<String, Integer>("chanel", 834));
terms.add(new Pair<String, Integer>("chant", 10));
terms.add(new Pair<String, Integer>("chang", 8));
terms.add(new Pair<String, Integer>("chani", 4));
terms.add(new Pair<String, Integer>("chand", 1));
terms.add(new Pair<String, Integer>("chana", 1));
terms.add(new Pair<String, Integer>("charl", 1));
terms.add(new Pair<String, Integer>("chane", 1));
terms.add(new Pair<String, Integer>("chan", 106));
terms.add(new Pair<String, Integer>("chair", 1950));
int id = 0;
final CommonsHttpSolrServer client = new CommonsHttpSolrServer("
http://solr:8080/solr/";);
client.setParser(new XMLResponseParser());
for (Pair<String, Integer> term : terms) {
final int freq = term.getSecond().intValue();
for (int i = 0; i < freq; ++i) {
SolrInputDocument doc = new SolrInputDocument();
doc.addField("id", String.valueOf(++id));
doc.addField("description", term.getFirst());
client.add(doc);
}
}
client.optimize();
Here's a Pair class:
public class Pair<S, T> {
S first;
T second;
public Pair(S _first, T _second) {
this.first = _first;
this.second = _second;
}
public S getFirst() {
return this.first;
}
public T getSecond() {
return this.second;
}
}
<?xml version="1.0" ?>
<config>
<abortOnConfigurationError>${solr.abortOnConfigurationError:true}</abortOnConfigurationError>
<dataDir>${solr.data.dir:./solr/data}</dataDir>
<indexDefaults>
<useCompoundFile>false</useCompoundFile>
<mergeFactor>10</mergeFactor>
<ramBufferSizeMB>32</ramBufferSizeMB>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<writeLockTimeout>1000</writeLockTimeout>
<commitLockTimeout>10000</commitLockTimeout>
<lockType>single</lockType>
</indexDefaults>
<mainIndex>
<useCompoundFile>false</useCompoundFile>
<ramBufferSizeMB>32</ramBufferSizeMB>
<mergeFactor>10</mergeFactor>
<maxMergeDocs>2147483647</maxMergeDocs>
<maxFieldLength>10000</maxFieldLength>
<unlockOnStartup>false</unlockOnStartup>
</mainIndex>
<updateHandler class="solr.DirectUpdateHandler2" />
<query>
<maxBooleanClauses>1024</maxBooleanClauses>
<filterCache
class="solr.LRUCache"
size="1024"
initialSize="512"
autowarmCount="256"/>
<queryResultCache
class="solr.LRUCache"
size="16384"
initialSize="4096"
autowarmCount="256"/>
<documentCache
class="solr.LRUCache"
size="16384"
initialSize="4096"
autowarmCount="0"/>
<enableLazyFieldLoading>true</enableLazyFieldLoading>
<useFilterForSortedQuery>true</useFilterForSortedQuery>
<queryResultWindowSize>50</queryResultWindowSize>
<queryResultMaxDocsCached>200</queryResultMaxDocsCached>
<HashDocSet maxSize="3000" loadFactor="0.75"/>
<boolTofilterOptimizer enabled="true" cacheSize="32" threshold=".05"/>
<maxWarmingSearchers>4</maxWarmingSearchers>
</query>
<requestDispatcher handleSelect="true" >
<requestParsers enableRemoteStreaming="false" multipartUploadLimitInKB="2048" />
<httpCaching lastModifiedFrom="openTime" etagSeed="Solr" />
</requestDispatcher>
<requestHandler name="standard" class="solr.StandardRequestHandler" default="true">
<lst name="defaults">
<str name="echoParams">explicit</str>
<int name="rows">10</int>
<str name="fl">*</str>
</lst>
</requestHandler>
<requestHandler name="dismax" class="solr.DisMaxRequestHandler" >
<str name="qf">description</str>
<str name="fl">id description</str>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
<searchComponent name="spellcheck" class="org.apache.solr.handler.component.SpellCheckComponent">
<lst name="defaults">
<str name="spellcheck.onlyMorePopular">true</str>
<str name="spellcheck.extendedResults">true</str>
<str name="spellcheck.count">10</str>
</lst>
<lst name="spellchecker">
<str name="name">default</str>
<str name="field">spellField</str>
<str name="spellcheckIndexDir">./spellchecker</str>
<str name="accuracy">0.5</str>
<str name="buildOnCommit">true</str>
</lst>
<str name="queryAnalyzerFieldType">textSpell</str>
</searchComponent>
<queryConverter name="queryConverter" class="org.apache.solr.spelling.SpellingQueryConverter"/>
<requestHandler name="/mlt" class="solr.MoreLikeThisHandler">
<lst name="defaults">
<str name="mlt.fl">manu,cat</str>
<int name="mlt.mindf">1</int>
</lst>
</requestHandler>
<requestHandler name="/search" class="org.apache.solr.handler.component.SearchHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
</lst>
</requestHandler>
<requestHandler name="/elevate" class="org.apache.solr.handler.component.SearchHandler" startup="lazy">
<lst name="defaults">
<str name="echoParams">explicit</str>
</lst>
<arr name="last-components">
<str>elevator</str>
</arr>
</requestHandler>
<requestHandler name="/update" class="solr.XmlUpdateRequestHandler" />
<requestHandler name="/analysis" class="solr.AnalysisRequestHandler" />
<requestHandler name="/update/csv" class="solr.CSVRequestHandler" startup="lazy" />
<requestHandler name="/admin/" class="org.apache.solr.handler.admin.AdminHandlers" />
<requestHandler name="/admin/ping" class="PingRequestHandler">
<lst name="defaults">
<str name="qt">standard</str>
<str name="q">solrpingquery</str>
<str name="echoParams">all</str>
</lst>
</requestHandler>
<highlighting>
<fragmenter name="gap" class="org.apache.solr.highlight.GapFragmenter" default="true">
<lst name="defaults">
<int name="hl.fragsize">100</int>
</lst>
</fragmenter>
<fragmenter name="regex" class="org.apache.solr.highlight.RegexFragmenter">
<lst name="defaults">
<int name="hl.fragsize">70</int>
<float name="hl.regex.slop">0.5</float>
<str name="hl.regex.pattern">[-\w ,/\n\"']{20,200}</str>
</lst>
</fragmenter>
<formatter name="html" class="org.apache.solr.highlight.HtmlFormatter" default="true">
<lst name="defaults">
<str name="hl.simple.pre"><![CDATA[<em>]]></str>
<str name="hl.simple.post"><![CDATA[</em>]]></str>
</lst>
</formatter>
</highlighting>
<queryResponseWriter name="xslt" class="org.apache.solr.request.XSLTResponseWriter">
<int name="xsltCacheLifetimeSeconds">5</int>
</queryResponseWriter>
<admin>
<defaultQuery>solr</defaultQuery>
</admin>
</config>
<?xml version="1.0" ?>
<schema name="example" version="1.1">
<types>
<fieldtype name="string" class="solr.StrField" sortMissingLast="true"/>
<fieldtype name="boolean" class="solr.BoolField" sortMissingLast="true"/>
<fieldtype name="integer" class="solr.IntField"/>
<fieldtype name="long" class="solr.LongField"/>
<fieldtype name="float" class="solr.FloatField"/>
<fieldtype name="double" class="solr.DoubleField"/>
<fieldtype name="sint" class="solr.SortableIntField" sortMissingLast="true"/>
<fieldtype name="slong" class="solr.SortableLongField" sortMissingLast="true"/>
<fieldtype name="sfloat" class="solr.SortableFloatField" sortMissingLast="true"/>
<fieldtype name="sdouble" class="solr.SortableDoubleField" sortMissingLast="true"/>
<fieldtype name="date" class="solr.DateField" sortMissingLast="true"/>
<fieldtype name="text_lu" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.StandardFilterFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.StopFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="text_ws" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="textSpell" class="solr.TextField" positionIncrementGap="100">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldtype>
<fieldtype name="textTight" class="solr.TextField" positionIncrementGap="100" >
<analyzer>
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.SynonymFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="false"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"/>
<filter class="solr.WordDelimiterFilterFactory" generateWordParts="0" generateNumberParts="0" catenateWords="1" catenateNumbers="1" catenateAll="0"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.EnglishPorterFilterFactory" protected="protwords.txt"/>
<filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
</analyzer>
</fieldtype>
</types>
<fields>
<field name="id" type="string" indexed="true" stored="true"/>
<field name="description" type="text" indexed="true" stored="true"/>
<field name="spellField" type="textSpell" indexed="true" stored="true" />
<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"/>
</fields>
<uniqueKey>id</uniqueKey>
<defaultSearchField>description</defaultSearchField>
<copyField source="description" dest="spellField" />
</schema>
