fix(lucene): add info about diacritics analyzer

close #83

Author: duncdrum

src/main/xar-resources/data/lucene/listings/listing-23.xml

@@ -0,0 +1,12 @@
+<collection xmlns="http://exist-db.org/collection-config/1.0">
+  <index xmlns:xs="http://www.w3.org/2001/XMLSchema">
+    <lucene>
+      <analyzer class="org.exist.indexing.lucene.analyzers.NoDiacriticsStandardAnalyzer" id="nodiacritics"/>
+      <text qname="letter" analyzer="nodiacritics">
+        <field name="place" expression="place" analyzer="nodiacritics"/>
+        <field name="from" expression="from" store="no"/>
+        <field name="to" expression="to"/>
+      </text>
+    </lucene>
+  </index>
+</collection>

src/main/xar-resources/data/lucene/listings/listing-24.xml

@@ -0,0 +1,10 @@
+<collection xmlns="\"http://exist-db.org/collection-config/1.0\"">
+  <index>
+    <!-- Lucene indexes -->
+    <lucene diacritics='no'>
+      <analyzer class='org.apache.lucene.analysis.standard.StandardAnalyzer'/>
+      <text match="\"//title[@xml:lang='Sa-Ltn']\""/>\
+      <text match="\"/TEI/text\""><ignore qname="\"text\""/></text>
+    </lucene>
+  </index>
+</collection>

src/main/xar-resources/data/lucene/lucene.xml

@@ -288,7 +288,10 @@
                 the text at white space characters, but treats all other characters - including
                 punctuation - as part of the token. The tokens are not converted to lower case and
                 there's no stopword filter applied.</para>
-
+            <para>eXist-db provides a special analyzer for characters with diacrits based on the <literal>StandardAnalyzer</literal>. The <literal>NoDiacriticsStandardAnalyzer</literal> can be switched on and of by setting the <literal>diacritics</literal> attribute on the <tag>lucene</tag> of your index configuration file.</para>
+            <programlisting language="xml" xlink:href="listings/listing-24.xml"/>
+            <para>Without diacrits <literal>ä</literal>, <literal>å</literal>, <literal>ā</literal>, etc are will all be indexed as <literal>a</literal>. Alternatively, this analyzer can also be called by its full name. </para>
+            <programlisting language="xml" xlink:href="listings/listing-23.xml"/>
             <sect3 xml:id="conf">
                 <title>Configuring the Analyzer</title>