Pastie now auto-senses if line-wrap is a bad or good idea. Feedback?
## mark a section (Learn more)
--- /Users/epugh/solr/solr2/LucidWorks/example/solr/conf/schema.xml 2010-01-27 11:52:43.000000000 -0500 +++ /Users/epugh/solr/solr2/LucidWorks/lucidworks/solr/conf/schema.xml 2010-01-27 11:52:39.000000000 -0500 @@ -212,6 +212,26 @@ </analyzer> </fieldType> + <!-- a basic general purpose text field utilizing KStemmer --> + <fieldType name="text_kstem" class="solr.TextField" positionIncrementGap="100"> + <analyzer type="index"> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" enablePositionIncrements="false" /> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="1" catenateNumbers="1" catenateAll="0" splitOnCaseChange="1"/> + <filter class="solr.LowerCaseFilterFactory"/> + <!-- The LucidKStemmer currently requires a lowercase filter somewhere before it. --> + <filter class="com.lucidimagination.solrworks.analysis.LucidKStemFilterFactory" protected="protwords.txt"/> + </analyzer> + <analyzer type="query"> + <tokenizer class="solr.WhitespaceTokenizerFactory"/> + <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt"/> + <filter class="solr.WordDelimiterFilterFactory" generateWordParts="1" generateNumberParts="1" catenateWords="0" catenateNumbers="0" catenateAll="0" splitOnCaseChange="1"/> + <filter class="solr.LowerCaseFilterFactory"/> + <!-- The LucidKStemmer currently requires a lowercase filter somewhere before it. --> + <filter class="com.lucidimagination.solrworks.analysis.LucidKStemFilterFactory" protected="protwords.txt"/> + </analyzer> + </fieldType> + <!-- A text field that uses WordDelimiterFilter to enable splitting and matching of words on case-change, alpha numeric boundaries, and non-alphanumeric chars, so that a query of "wifi" or "wi fi" could match a document containing "Wi-Fi". @@ -510,6 +530,8 @@ <dynamicField name="random_*" type="random" /> + <dynamicField name="*_kstem" type="text_kstem" indexed="true" stored="true" multiValued="true"/> + <!-- uncomment the following to ignore any fields that don't already match an existing field name or dynamic field, rather than reporting them as an error. alternately, change the type="ignored" to some other type e.g. "text" if you want
This paste will be private.
From the Design Piracy series on my blog: