Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
"ä" => "ae"
"Ä" => "Ae"
"ö" => "oe"
"Ö" => "Oe"
"ü" => "ue"
"Ü" => "Ue"
"ß" => "ss"
"ſ" => "s"
5 changes: 5 additions & 0 deletions Configuration/ApacheSolr/configsets/dlf/conf/schema.xml
Original file line number Diff line number Diff line change
Expand Up @@ -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>
Expand All @@ -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" />
Expand All @@ -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" />
Expand Down
Loading