I indexed an electronics e-commerce product catalog.
This is a typical document from my collection:
"docs": [
{
"prezzo_vendita_d": 39.9,
"codice_produttore_s": "DK00150020",
"codice_s": "5.BAT.27407",
"descrizione": "BATTERIA GO PRO HERO ",
"barcode_interno_s": "185323000958",
"categoria": "Batterie",
"prezzo_acquisto_d": 16.12,
"marchio": "GO PRO",
"data_aggiornamento_dt": "2012-06-21T00:00:00Z",
"id": "27407",
"_version_": 1491274123542790100
},
{
"codice_produttore_s": "DK0052043",
"codice_s": "05.SP.42760",
"id": "42760",
"marchio": "SP GADGETS",
"barcode_interno_s": "4028017520430",
"prezzo_acquisto_d": 34.4,
"data_aggiornamento_dt": "2014-11-04T00:00:00Z",
"descrizione": "SP POS CASE GOPRO OLIVE LARGE",
"prezzo_vendita_d": 59.95,
"_version_": 1491274406746390500
}
...]
I want my spellchecker to suggest "go pro" to users searching "gopro"
(without whitespace).
I also want users searching "go pro" to find "gopro" products, too.
Here's a little bit of my configuration:
*schema.xml*
<field name="marchio" type="string" indexed="true" stored="true"/>
<field name="categoria" type="string" indexed="true" stored="true"/>
<field name="fornitore" type="string" indexed="true" stored="true"/>
<field name="descrizione" type="string" indexed="true"
stored="true"/>
<field name="catch_all_original" type="text_general" indexed="true"
stored="false" multiValued="true" />
<field name="catch_all" type="text_it" indexed="true" stored="false"
multiValued="true" />
<copyField source="marchio" dest="catch_all" />
<copyField source="categoria" dest="catch_all" />
<copyField source="descrizione" dest="catch_all" />
<copyField source="fornitore" dest="catch_all" />
<copyField source="marchio" dest="catch_all_original" />
<copyField source="categoria" dest="catch_all_original" />
<copyField source="descrizione" dest="catch_all_original" />
<copyField source="fornitore" dest="catch_all_original" />
...
<fieldType name="text_it" class="solr.TextField"
positionIncrementGap="100">
<analyzer type="index">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"
preserveOriginal="1" />
<filter class="solr.ElisionFilterFactory" ignoreCase="true"
articles="lang/contractions_it.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ASCIIFoldingFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="lang/stopwords_it.txt" format="snowball" />
<filter class="solr.ItalianLightStemFilterFactory"/>
</analyzer>
<analyzer type="query">
<tokenizer class="solr.WhitespaceTokenizerFactory"/>
<filter class="solr.WordDelimiterFilterFactory"
generateWordParts="1" generateNumberParts="1" catenateWords="1"
catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"
preserveOriginal="1" />
<filter class="solr.ElisionFilterFactory" ignoreCase="true"
articles="lang/contractions_it.txt"/>
<filter class="solr.LowerCaseFilterFactory"/>
<filter class="solr.ASCIIFoldingFilterFactory"/>
<filter class="solr.StopFilterFactory" ignoreCase="true"
words="lang/stopwords_it.txt" format="snowball" />
<filter class="solr.ItalianLightStemFilterFactory"/>
<filter class="solr.SynonymFilterFactory"
synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
</analyzer>
</fieldType>
<br />
*solr-config.xml*
<requestHandler name="/select" class="solr.SearchHandler">
<lst name="defaults">
<str name="echoParams">explicit</str>
<int name="rows">10</int>
<str name="df">catch_all</str>
<str name="spellcheck">on</str>
<str name="spellcheck.dictionary">default</str>
<str name="spellcheck.dictionary">wordbreak</str>
<str name="spellcheck.extendedResults">false</str>
<str name="spellcheck.count">5</str>
<str name="spellcheck.alternativeTermCount">2</str>
<str name="spellcheck.maxResultsForSuggest">5</str>
<str name="spellcheck.collate">true</str>
<str name="spellcheck.collateExtendedResults">true</str>
<str name="spellcheck.maxCollationTries">5</str>
<str name="spellcheck.maxCollations">3</str>
</lst>
<arr name="last-components">
<str>spellcheck</str>
</arr>
</requestHandler>
...
<searchComponent name="spellcheck" class="solr.SpellCheckComponent">
<str name="queryAnalyzerFieldType">text_general</str>
<lst name="spellchecker">
<str name="name">default</str>
<str name="field">catch_all_original</str>
<str name="classname">solr.DirectSolrSpellChecker</str>
<str name="distanceMeasure">internal</str>
<float name="accuracy">0.5</float>
<int name="maxEdits">2</int>
<int name="minPrefix">1</int>
<int name="maxInspections">5</int>
<int name="minQueryLength">4</int>
<float name="maxQueryFrequency">0.01</float>
</lst>
<lst name="spellchecker">
<str name="name">wordbreak</str>
<str name="classname">solr.WordBreakSolrSpellChecker</str>
<str name="field">catch_all_original</str>
<str name="combineWords">true</str>
<str name="breakWords">true</str>
<int name="maxChanges">10</int>
<int name="minBreakLength">3</int>
</lst>
</searchComponent>
*Is the spellchecker the right solution or is this the case for something
else, like the "more like this" feature?*
Thank you
--
View this message in context:
http://lucene.472066.n3.nabble.com/Suggesting-broken-words-with-solr-WordBreakSolrSpellChecker-tp4182172.html
Sent from the Solr - User mailing list archive at Nabble.com.
