Differences

This shows you the differences between two versions of the page.

--- stepbystep:baseservices [2021/03/29 15:24]
giancarlo [Cantaloupe]
+++ stepbystep:baseservices [2021/07/15 16:23] (current)
giancarlo [SOLR]
@@ Line 438: / Line 438: @@
 \\
 \\
-[[#anchor]]
+[[#cantaupdate5|Update Cantaloupe to 5.0 as this version was released.]]
-<wrap #anchor>text or nothing</wrap>
+<wrap #cantaupdate5></wrap>
-Update Cantaloupe to 5.0 as this version was released.
 <code bash>
 wget https://github.com/cantaloupe-project/cantaloupe/releases/download/v5.0/cantaloupe-5.0.zip
@@ Line 585: / Line 584: @@
 sudo mv target/solr-ocrhighlighting-0.6.0-SNAPSHOT.jar /opt/solr/contrib/archipelago/lib/
 </code>
+We need last ocrhighlighting from master (0.7.0 SNAPSHOT)
+<code bash>
+$ wget https://github.com/dbmdz/solr-ocrhighlighting/archive/main.zip
+$ unzip main.zip
+$ cd solr-ocrhighlighting-main/
+$ JAVA_HOME=/usr/lib/jvm/java-14-openjdk-amd64 mvn package
+$ cd ..
+$ sudo mv /opt/solr/contrib/archipelago/lib/solr-ocrhighlighting-0.6.0-SNAPSHOT.jar ./
+$ sudo mv solr-ocrhighlighting-main/target/solr-ocrhighlighting-0.7.0-SNAPSHOT.jar /opt/solr/contrib/archipelago/lib/
+$ rm -R solr-ocrhighlighting-main
+Reload Solr
+</code>
+Update to ocrhighlighting 0.7.0 release
+<code bash>
+$ wget https://github.com/dbmdz/solr-ocrhighlighting/archive/refs/tags/0.7.0.zip
+$ unzip 0.7.0.zip
+$ cd solr-ocrhighlighting-0.7.0
+$ JAVA_HOME=/usr/lib/jvm/java-14-openjdk-amd64 mvn package
+$ cd ..
+$ sudo mv /opt/solr/contrib/archipelago/lib/solr-ocrhighlighting-0.7.0-SNAPSHOT.jar ./
+$ sudo mv solr-ocrhighlighting-0.7.0/target/solr-ocrhighlighting-0.7.0.jar /opt/solr/contrib/archipelago/lib/
+$ rm -R solr-ocrhighlighting-0.7.0
+Reload Solr
+</code>
 Create archipelago core
 <code bash>
@@ Line 610: / Line 636: @@
 $ sudo systemctl start solr
 </code>
-Edit Solr filters for Italian text language
+[[#solrita|Edit Solr filters for Italian text language]]
+<wrap #solrita></wrap>
 <code bash>
 $ sudo -u solr nano -w /srv/solr/data/archipelago/conf/schema_extra_types.xml
@@ Line 622: / Line 649: @@
     <filter class="solr.ElisionFilterFactory" articles="lang/contractions_it.txt"/>
     <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt"/>
+    <filter class="solr.KeywordMarkerFilterFactory" protected="protwords_und.txt" />
     <filter class="solr.SnowballPorterFilterFactory" language="Italian"/>
-    <filter class="solr.LengthFilterFactory" min="2" max="100"/>
+    <filter class="solr.LengthFilterFactory" min="3" max="100"/>
-    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
   </analyzer>
   <analyzer type="query">
@@ Line 632: / Line 659: @@
     <filter class="solr.ElisionFilterFactory" articles="lang/contractions_it.txt"/>
     <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt"/>
+    <filter class="solr.KeywordMarkerFilterFactory" protected="protwords_und.txt" />
     <filter class="solr.SnowballPorterFilterFactory" language="Italian"/>
-    <filter class="solr.LengthFilterFactory" min="2" max="100"/>
+    <filter class="solr.LengthFilterFactory" min="3" max="100"/>
-    <filter class="solr.RemoveDuplicatesTokenFilterFactory"/>
   </analyzer>
 </fieldType>
 <fieldType name="text_ocr_stored" class="solr.TextField" storeOffsetsWithPositions="true" termVectors="true">
   <analyzer type="index">
     <charFilter class="de.digitalcollections.solrocr.lucene.filters.OcrCharFilterFactory"/>
+    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
     <tokenizer class="solr.StandardTokenizerFactory"/>
     <filter class="solr.LowerCaseFilterFactory"/>
     <filter class="solr.ElisionFilterFactory" articles="lang/contractions_it.txt"/>
     <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt"/>
+    <filter class="solr.KeywordMarkerFilterFactory" protected="protwords_und.txt" />
     <filter class="solr.SnowballPorterFilterFactory" language="Italian"/>
-    <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="false" />
+    <filter class="solr.LengthFilterFactory" min="3" max="100"/>
   </analyzer>
   <analyzer type="query">
+    <charFilter class="solr.MappingCharFilterFactory" mapping="accents_und.txt"/>
     <tokenizer class="solr.StandardTokenizerFactory"/>
     <filter class="solr.LowerCaseFilterFactory"/>
     <filter class="solr.ElisionFilterFactory" articles="lang/contractions_it.txt"/>
     <filter class="solr.StopFilterFactory" ignoreCase="true" words="lang/stopwords_it.txt"/>
+    <filter class="solr.KeywordMarkerFilterFactory" protected="protwords_und.txt" />
     <filter class="solr.SnowballPorterFilterFactory" language="Italian"/>
-    <filter class="solr.ASCIIFoldingFilterFactory" preserveOriginal="false" />
+    <filter class="solr.LengthFilterFactory" min="3" max="100"/>
   </analyzer>
 </fieldType>
+</code>
+[[#solrsugg|Edit Solr schema for Suggester split on word without punctuation]]
+<wrap #solrsugg></wrap>
+<code bash>
+$ sudo -u solr nano -w /srv/solr/data/archipelago/conf/schema.xml
+</code>
+<code xml>
+    <fieldType name="text_ws" class="solr.TextField" omitNorms="true" positionIncrementGap="100">
+      <analyzer>
+<!--        <tokenizer class="solr.WhitespaceTokenizerFactory"/> -->
+        <tokenizer class="solr.WhitespaceTokenizerFactory"/>
+        <filter class="solr.LowerCaseFilterFactory"/>
+      </analyzer>
+    </fieldType>
 </code>