#891 use better field analyzer for shelfmark

rism-digital · Jun 28, 2021 · 572aed4 · 572aed4
1 parent 75873b9
commit 572aed4
Show file tree

Hide file tree

Showing 3 changed files with 2 additions and 52 deletions.
diff --git a/solr-configuration/muscat/schema.xml b/solr-configuration/muscat/schema.xml
@@ -189,30 +189,11 @@
             </analyzer>
         </fieldtype>
 
-        <fieldType name="text_alphanumeric_sort" class="solr.TextField" sortMissingLast="false" omitNorms="true">
-            <analyzer>
-                <tokenizer class="solr.KeywordTokenizerFactory"/>
-                <filter class="solr.LowerCaseFilterFactory"/>
-                <filter class="solr.TrimFilterFactory"/>
-                <filter class="solr.PatternReplaceFilterFactory"
-                        pattern="^(a |the |les |la |le |l'|de la |du |des )" replacement="" replace="all"
-                />
-                <filter class="solr.PatternReplaceFilterFactory"
-                        pattern="(\d+)" replacement="00000$1" replace="all"
-                />
-                <filter class="solr.PatternReplaceFilterFactory"
-                        pattern="0*([0-9]{6,})" replacement="$1" replace="all"
-                />
-                <filter class="solr.PatternReplaceFilterFactory"
-                        pattern="([^a-z0-9])" replacement="" replace="all"
-                />
-            </analyzer>
-        </fieldType>
+        <fieldType name="text_alphanumeric_sort" class="solr.ICUCollationField" locale="" numeric="true" strength="secondary" sortMissingLast="true" />
         <!-- END ADDED BY RZ FOR MUSCAT -->
     </types>
     <uniqueKey>id</uniqueKey>
 
     <copyField source="*_text" dest="textSpell"/>
     <copyField source="*_s" dest="textSpell"/>
 </schema>
-
diff --git a/solr-configuration/muscat/solrconfig.xml b/solr-configuration/muscat/solrconfig.xml
@@ -5,7 +5,6 @@
     <lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lib" regex="icu4j-\d.*\.jar"/>
     <lib dir="${solr.install.dir:../../../..}/contrib/analysis-extras/lucene-libs"
          regex="lucene-analyzers-icu-\d.*\.jar"/>
-    <lib dir="../../jar"/>
 
     <dataDir>${solr.data.dir:}</dataDir>
 
@@ -249,4 +248,3 @@
         </lst>
     </requestHandler>
 </config>
-
diff --git a/solr/configsets/sunspot/conf/schema.xml b/solr/configsets/sunspot/conf/schema.xml
@@ -112,36 +112,7 @@
       </analyzer>
     </fieldtype>
 
-    <fieldType name="text_alphanumeric_sort" class="solr.TextField" sortMissingLast="false" omitNorms="true">
-        <analyzer>
-            <!-- KeywordTokenizer does no actual tokenizing, so the entire
-                 input string is preserved as a single token
-              -->
-            <tokenizer class="solr.KeywordTokenizerFactory"/>
-            <!-- The LowerCase TokenFilter does what you expect, which can be
-                 when you want your sorting to be case insensitive
-              -->
-            <filter class="solr.LowerCaseFilterFactory" />
-            <!-- The TrimFilter removes any leading or trailing whitespace -->
-            <filter class="solr.TrimFilterFactory" />
-            <!-- Remove leading articles -->
-            <filter class="solr.PatternReplaceFilterFactory"
-                    pattern="^(a |the |les |la |le |l'|de la |du |des )" replacement="" replace="all"
-            />
-            <!-- Left-pad numbers with zeroes -->
-            <filter class="solr.PatternReplaceFilterFactory"
-                    pattern="(\d+)" replacement="00000$1" replace="all"
-            />
-            <!-- Left-trim zeroes to produce 6 digit numbers -->
-            <filter class="solr.PatternReplaceFilterFactory"
-                    pattern="0*([0-9]{6,})" replacement="$1" replace="all"
-            />
-            <!-- Remove all but alphanumeric characters -->
-            <filter class="solr.PatternReplaceFilterFactory"
-                    pattern="([^a-z0-9])" replacement="" replace="all"
-            />
-        </analyzer>
-    </fieldType>
+    <fieldType name="text_alphanumeric_sort" class="solr.ICUCollationField" locale="" numeric="true" strength="secondary" sortMissingLast="true" />
     <!-- END ADDED BY RZ FOR MUSCAT -->
 
   </types>