feat: Use full-text index for GTM (#1127)

* using new GTM ontology (more schema.org) and lucene-index * GTM ontology from skos to schema.org * used more efficient STRSTARTS instead of CONTAINS thanks for the suggestion @ddeboer
netwerk-digitaal-erfgoed · Oct 8, 2023 · e6046ba · e6046ba
1 parent 8ed839b
commit e6046ba
Show file tree

Hide file tree

Showing 2 changed files with 30 additions and 29 deletions.
diff --git a/packages/network-of-terms-catalog/catalog/queries/lookup/goudatijdmachine-straten.rq b/packages/network-of-terms-catalog/catalog/queries/lookup/goudatijdmachine-straten.rq
@@ -1,4 +1,4 @@
-PREFIX dcterms: <http://purl.org/dc/terms/>
+PREFIX sdo: <https://schema.org/>
 PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
 PREFIX gtm: <https://www.goudatijdmachine.nl/def#>
 PREFIX schema: <https://schema.org/>
@@ -17,21 +17,18 @@ CONSTRUCT {
     # Kapelstraat: <https://n2t.net/ark:/60537/b4ApaO>
     VALUES ?uri { ?uris }
     ?uri a gtm:Straat ;
-         dcterms:identifier ?identifier ;
-         skos:prefLabel ?prefLabel .
-    FILTER (CONTAINS(STR(?uri), "ark:"))
+         sdo:identifier ?identifier ;
+         sdo:name ?prefLabel .
+    FILTER (STRSTARTS(STR(?uri), "https://n2t.net/ark:/60537/"))
     OPTIONAL {
-        ?uri skos:altLabel ?altLabel
-    }
-    OPTIONAL {
-        ?uri hg:liesIn/schema:sameAs <http://sws.geonames.org/2755419/> # Gouda
-        BIND("Straat in Gouda" AS ?scopeNote)
+        ?uri sdo:alternateName ?altLabel
     }
+    BIND ( CONCAT( IF ( EXISTS { ?entity omeka:item_set <https://n2t.net/ark:/60537/bd75pg> }, "Verdwenen straat", "Straat" )," in Gouda") AS ?scopeNote )
     OPTIONAL {
         ?uri hg:absorbedBy|hg:absorbed ?related_uri .
         ?related_uri a gtm:Straat ;
-                     skos:prefLabel ?related_prefLabel .
-        FILTER (CONTAINS(STR(?related_uri), "ark:") && ?uri !=  ?related_uri )
+                     sdo:name ?related_prefLabel .
+        FILTER (STRSTARTS(STR(?related_uri), "https://n2t.net/ark:/60537/") && ?uri != ?related_uri )
     }
 }
 LIMIT 100
diff --git a/packages/network-of-terms-catalog/catalog/queries/search/goudatijdmachine-straten.rq b/packages/network-of-terms-catalog/catalog/queries/search/goudatijdmachine-straten.rq
@@ -1,8 +1,10 @@
-PREFIX dcterms: <http://purl.org/dc/terms/>
 PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
 PREFIX gtm: <https://www.goudatijdmachine.nl/def#>
-PREFIX schema: <https://schema.org/>
+PREFIX sdo: <https://schema.org/>
 PREFIX hg: <http://rdf.histograph.io/>
+PREFIX luc: <http://www.ontotext.com/connectors/lucene#>
+PREFIX luc-index: <http://www.ontotext.com/connectors/lucene/instance#>
+PREFIX omeka: <http://omeka.org/s/vocabs/o#>
 
 CONSTRUCT {
     ?uri a skos:Concept ;
@@ -11,23 +13,25 @@ CONSTRUCT {
         skos:scopeNote ?scopeNote ;
         skos:related ?related_uri .
     ?related_uri skos:prefLabel ?related_prefLabel .
-}
-WHERE {
-    ?uri a gtm:Straat ;
-         dcterms:identifier ?identifier ;
-         skos:prefLabel ?prefLabel .
-    OPTIONAL { ?uri skos:altLabel ?altLabel . }
-    OPTIONAL {
-        ?uri hg:liesIn/schema:sameAs <http://sws.geonames.org/2755419/> # Gouda
-        BIND("Straat in Gouda" AS ?scopeNote)
-    }
+} WHERE {
+    ?search a luc-index:straten_index ;
+        luc:query ?query ;
+        luc:entities ?uri .
+
+    FILTER (STRSTARTS(STR(?uri), "https://n2t.net/ark:/60537/"))
+
+    ?uri sdo:identifier ?identifier ;
+        sdo:name ?prefLabel ;
+        luc:score ?score .
+
+    BIND ( CONCAT( IF ( EXISTS { ?entity omeka:item_set <https://n2t.net/ark:/60537/bd75pg> }, "Verdwenen straat", "Straat" )," in Gouda") AS ?scopeNote )
+
+    OPTIONAL { ?uri sdo:alternateName ?altLabel . }
+
     OPTIONAL {
         ?uri hg:absorbedBy|hg:absorbed ?related_uri .
         ?related_uri a gtm:Straat ;
-                skos:prefLabel ?related_prefLabel .
-        FILTER (CONTAINS(STR(?related_uri), "ark:") && ?uri !=  ?related_uri )
+                sdo:name ?related_prefLabel .
+        FILTER (STRSTARTS(STR(?related_uri), "https://n2t.net/ark:/60537/") && ?uri != ?related_uri )
     }
-    FILTER (CONTAINS(STR(?uri), "ark:"))
-    FILTER (CONTAINS(LCASE(?prefLabel),?query) || CONTAINS(LCASE(?altLabel),?query) )
-}
-LIMIT 100
+} ORDER BY DESC(?score) LIMIT 100