Merge branch 'develop' into devel-work-experiments

* develop:
  #891 use better field analyzer for shelfmark
  ...and more formatting
  As usual, fix formatting
  Add more solr installation notes

2- INSTALL.rdoc

@@ -142,6 +142,36 @@ Muscat 7.1 now supports Solr 8.8 installed externally. This means for example th
 The internal Solr 5.5 server still works, but will not be supported anymore in the future since the bundled Solr unsupported and has problems with modern Java versions.
 The Muscat core should work with any installation of Solr, here a sample installation procedure is shown but it should be adapted for each installation.
 
+==== Installation using a "stock" solr using included setup script
+
+Grab a copy of the official distribution (8.8.2 at the time of writing) and unpack it in a suitable place
+
+  wget https://www.apache.org/dyn/closer.lua/lucene/solr/8.8.2/solr-8.8.2.tgz
+  tar -xvzf solr-8.8.2.tgz
+
+Solr needs two directories, one for data and one for the binaries. The latter is generally /opt/solr, and the data installation for this example will be /data/solr.
+Extract just the installation script:
+
+  tar xzf solr-8.8.2.tgz solr-8.8.2/bin/install_solr_service.sh --strip-components=2
+
+And execute it:
+
+  sudo ./install_solr_service.sh solr-8.8.2.tgz -d /data/solr -p 8983
+
+This will create the directory layout as above. It will also create a +solr+ user. For the complete reference see https://solr.apache.org/guide/8_8/taking-solr-to-production.html
+Now copy over the Muscat core:
+
+  cp -R $MUSCAT_HOME/solr-configuration/muscat /data/solr/data
+  cp $MUSCAT_HOME/solr-configuration/jar-8.8-linux/ThemaxQuery-1.0-SNAPSHOT.jar /data/solr/data/lib/
+
+Where +/data/solr/+ in the directory specified above with -d.
+Solr includes a startup script so 
+
+  systemctl daemon-reload
+  service solr start
+
+Should start it. The logfiles in this case are found in +/data/solr/logs+.
+
 ==== Installation using a "stock" solr
 
 Grab a copy of the official distribution (8.8.2 at the time of writing) and unpack it in a suitable place

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>
-

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>
-

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>