Extended characters

[Robert Brown]

Hi,

I have a text field in my index containing extended characters, which 
I'd like to match against when searching without the extended characters.

e.g.  field contains "Ensō" which I want to match when searching for 
just "enso".

My current config for that field (type) is given below:


    <fieldType name="text" class="solr.TextField" 
positionIncrementGap="100" autoGeneratePhraseQueries="true">

        <analyzer type="index">

            <tokenizer class="solr.WhitespaceTokenizerFactory"/>

            <filter class="solr.SynonymFilterFactory" 
synonyms="index_synonyms.txt" ignoreCase="true" expand="true" />

            <!-- Case insensitive stop word removal -->
            <filter class="solr.StopFilterFactory" ignoreCase="true" 
words="lang/stopwords_en.txt" />

            <!-- see 
https://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters -->
            <filter class="solr.WordDelimiterFilterFactory"
                splitOnCaseChange="1"
                splitOnNumerics="1"
                stemEnglishPossessive="1"
                generateWordParts="1"
                generateNumberParts="1"
                catenateWords="1"
                catenateNumbers="1"
                catenateAll="1"
                preserveOriginal="1"
                protected="lang/protwords_en.txt"
            />

            <filter class="solr.LowerCaseFilterFactory"/>

            <!--
            <filter class="solr.KeywordMarkerFilterFactory" 
protected="protwords.txt"/>
            -->

            <filter class="solr.PorterStemFilterFactory"/>

        </analyzer>

        <analyzer type="query">

            <tokenizer class="solr.WhitespaceTokenizerFactory"/>

            <!-- we deal with synonyms at index time only
            <filter class="solr.SynonymFilterFactory" 
synonyms="synonyms.txt" ignoreCase="true" expand="true"/>
            -->

            <filter class="solr.StopFilterFactory" ignoreCase="true" 
words="lang/stopwords_en.txt" />

            <!-- see 
https://wiki.apache.org/solr/AnalyzersTokenizersTokenFilters -->
            <filter class="solr.WordDelimiterFilterFactory"
                splitOnCaseChange="1"
                splitOnNumerics="1"
                stemEnglishPossessive="1"
                generateWordParts="1"
                generateNumberParts="1"
                catenateWords="1"
                catenateNumbers="1"
                catenateAll="1"
                preserveOriginal="1"
                protected="lang/protwords_en.txt"
            />

            <filter class="solr.LowerCaseFilterFactory"/>

            <!--
            <filter class="solr.KeywordMarkerFilterFactory" 
protected="protwords.txt"/>
            -->

            <filter class="solr.PorterStemFilterFactory"/>

        </analyzer>

    </fieldType>

</schema>