From 5485ac03995dfd04038fc397c4fcc900a129b86c Mon Sep 17 00:00:00 2001
From: Bernd Fallert <bernd.fallert@bib.uni-mannheim.de>
Date: Mon, 11 May 2026 13:18:14 +0200
Subject: [PATCH] =?UTF-8?q?Umlauts=20(e.g.,=20=C3=A4=20=E2=86=92=20ae),=20?=
 =?UTF-8?q?=C3=9F=20(=E2=86=92=20ss),=20and=20the=20long=20s=20(=C5=BF=20?=
 =?UTF-8?q?=E2=86=92=20s)?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../configsets/dlf/conf/mapping-UmlautLongS.txt           | 8 ++++++++
 Configuration/ApacheSolr/configsets/dlf/conf/schema.xml   | 5 +++++
 2 files changed, 13 insertions(+)
 create mode 100644 Configuration/ApacheSolr/configsets/dlf/conf/mapping-UmlautLongS.txt

diff --git a/Configuration/ApacheSolr/configsets/dlf/conf/mapping-UmlautLongS.txt b/Configuration/ApacheSolr/configsets/dlf/conf/mapping-UmlautLongS.txt
new file mode 100644
index 0000000000..6a2d0d14e4
--- /dev/null
+++ b/Configuration/ApacheSolr/configsets/dlf/conf/mapping-UmlautLongS.txt
@@ -0,0 +1,8 @@
+"ä" => "ae"
+"Ä" => "Ae"
+"ö" => "oe"
+"Ö" => "Oe"
+"ü" => "ue"
+"Ü" => "Ue"
+"ß" => "ss"
+"ſ" => "s"
diff --git a/Configuration/ApacheSolr/configsets/dlf/conf/schema.xml b/Configuration/ApacheSolr/configsets/dlf/conf/schema.xml
index a9aace4275..3518f4c207 100644
--- a/Configuration/ApacheSolr/configsets/dlf/conf/schema.xml
+++ b/Configuration/ApacheSolr/configsets/dlf/conf/schema.xml
@@ -43,16 +43,19 @@ limitations under the License.
         <fieldType name="geojson" class="solr.SpatialRecursivePrefixTreeFieldType" spatialContextFactory="Geo3D" geo="true" planetModel="WGS84" format="GeoJSON" />
         <fieldType name="standard" class="solr.TextField" positionIncrementGap="100">
             <analyzer>
+                <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-UmlautLongS.txt"/>
                 <tokenizer class="solr.StandardTokenizerFactory" />
                 <filter class="solr.LowerCaseFilterFactory" />
             </analyzer>
         </fieldType>
         <fieldType name="autocomplete" class="solr.TextField" positionIncrementGap="100">
             <analyzer type="index">
+                <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-UmlautLongS.txt"/>
                 <tokenizer class="solr.KeywordTokenizerFactory" />
                 <filter class="solr.LowerCaseFilterFactory" />
             </analyzer>
             <analyzer type="query">
+                <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-UmlautLongS.txt"/>
                 <tokenizer class="solr.WhitespaceTokenizerFactory" />
                 <filter class="solr.LowerCaseFilterFactory" />
             </analyzer>
@@ -62,6 +65,7 @@ limitations under the License.
             <analyzer type="index">
                 <!-- For converting OCR to plaintext -->
                 <charFilter class="solrocr.OcrCharFilterFactory" />
+                <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-UmlautLongS.txt"/>
 
                 <charFilter class="solr.HTMLStripCharFilterFactory" />
                 <tokenizer class="solr.WhitespaceTokenizerFactory" />
@@ -81,6 +85,7 @@ limitations under the License.
             <!-- TODO: which filters here are the character filters? -->
             <!-- TODO: check why some filters are outcommented -->
             <analyzer type="query">
+                <charFilter class="solr.MappingCharFilterFactory" mapping="mapping-UmlautLongS.txt"/>
                 <tokenizer class="solr.WhitespaceTokenizerFactory" />
                 <filter class="solr.SynonymGraphFilterFactory" synonyms="synonyms.txt" ignoreCase="true" expand="true" />
                 <filter class="solr.StopFilterFactory" ignoreCase="true" words="stopwords.txt" />