Apache Solr search against different combinations of text entered. - apache

Question

I am new to this Apache Solr. I want to do a search against different combinations of text entered. For example, if the text is 'hello' , it should return records having hello,llo,hel,ollhe, he and so on..Is this possible with solr ? if so, how we can do this? Please help me.

Answer 1

This is possible in solr. You can use the EdgeNGramFilterFactory in your fieldType. here is the example of it.
Here word hello will have tokens like he, hel, hell and hello
<fieldType name="text" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
</analyzer>
</fieldType>
or you can try NGramTokenizerFactory instead of EdgeNGramFilterFactory.
<tokenizer class="solr.NGramTokenizerFactory" minGramSize="2" maxGramSize="10"/>
Which will give the output like
for hello it would generate token like
he, hel, hell, hello, el, ell, and so..

Answer 2

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<schema name="autoSolrSchema" version="1.5">
<types>
<fieldType class="org.apache.solr.schema.StrField" name="StrField"/>
<fieldType name="StrTokenizer" class="solr.TextField">
<analyzer>
<tokenizer class="solr.NGramTokenizerFactory" minGramSize="2" maxGramSize="5"/>
</analyzer>
</fieldType>
<fieldType class="org.apache.solr.schema.TrieFloatField" name="TrieFloatField"/>
<fieldType class="org.apache.solr.schema.TextField" name="TextField">
<analyzer>
<tokenizer class="solr.StandardTokenizerFactory"/>
<filter class="solr.LowerCaseFilterFactory"/>
</analyzer>
</fieldType>
<fieldType name="user_id" class="solr.TextField" positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.KeywordTokenizerFactory"/>
<filter class="solr.EdgeNGramFilterFactory" minGramSize="2" maxGramSize="15"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.KeywordTokenizerFactory"/>
</analyzer>
</fieldType>
</types>
<fields>
<field indexed="true" multiValued="false" name="user_id" stored="true" type="StrField"/>
<field indexed="true" multiValued="false" name="company" stored="true" type="StrField"/>
<field indexed="true" multiValued="false" name="tins" stored="true" type="TrieFloatField"/>
<field indexed="true" multiValued="false" name="user_standard" stored="true" type="StrTokenizer"/>
<field indexed="true" multiValued="false" name="requests" stored="true" type="TrieFloatField"/>
<field indexed="true" multiValued="false" name="include" stored="true" type="TextField"/>
</fields>
<uniqueKey>(user_id,company,user_standard)</uniqueKey>
</schema>