Dynamic Queries

We are working towards a dynamic query

My vision is that there is a set of PREFIX, then a the basic query that returns the information needed for the

PREFIX
...

SELECT ....
WHERE {
values ?sosType {
        sschema:Dataset
        #               sschema:DataCatalog
        schema:Dataset
        #               schema:DataCatalog
    }
    ?subj a ?sosType .
    values (?type ?resourceType_u) {
        (schema:Dataset "data")
        (sschema:Dataset "data")
     
        (schema:DataCatalog "DataCatalog")
        (sschema:DataCatalog "DataCatalog")
        #(UNDEF "other")  # assume it's data. At least we should get  name.
    }
    ?subj a ?type .
    ?subj ?o ?item .
# ?item is used in the filters.

  GRAPH ?g {
# required elements
    schema:name
    schema:description
# OPTIONAL

  }
}
GROUP BY ...
LIMIT {{N}}
OFFSET {{O}}

This will return records with no filters. This query needs to be performant. There are optional clauses that will kill this.

Then we add filters after the WHERE before the graph.

PREFIX
...

SELECT ....

WHERE {
values ?sosType {
        sschema:Dataset
        #               sschema:DataCatalog
        schema:Dataset
        #               schema:DataCatalog
    }
    ?subj a ?sosType .
    values (?type ?resourceType_u) {
        (schema:Dataset "data")
        (sschema:Dataset "data")
        (schema:DataCatalog "DataCatalog")
        (sschema:DataCatalog "DataCatalog")
        #(UNDEF "other")  # assume it's data. At least we should get  name.
    }
    ?subj a ?type .
    ?subj ?o ?item .
#FILTERS HERE
  GRAPH ?g {
# required elements
    schema:name
    schema:description
# OPTIONAL

  }
}
GROUP BY ...
LIMIT {{N}}
OFFSET {{O}}

This should return a list of datasets

PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
prefix schema: <http://schema.org/>
prefix sschema: <https://schema.org/>
PREFIX ql: <http://qlever.cs.uni-freiburg.de/builtin-functions/>

SELECT distinct ?g  ?subj ?type  ?name ?description ?pubname (GROUP_CONCAT(DISTINCT ?placename; SEPARATOR=", ") AS ?placenames)
    (GROUP_CONCAT(DISTINCT ?kwu; SEPARATOR=", ") AS ?kw)
    ?datep  (GROUP_CONCAT(DISTINCT ?url; SEPARATOR=", ") AS ?disurl)
    (COUNT(?text) AS ?score) (SAMPLE(?text) AS ?example_text)
    (GROUP_CONCAT(DISTINCT ?resourceType_u; SEPARATOR=", ") as ?resourceType )   (MAX(?lat) as ?maxlat) (Min(?lat) as ?minlat) (MAX(?lon) as ?maxlon) (Min(?lon) as ?minlon)
    ?maxDepth ?minDepth ?temporalCoverage (GROUP_CONCAT(DISTINCT ?variableMeasured_a; SEPARATOR=", ") as ?variableMeasured  )
    ?bbox

WHERE {
    values ?sosType {
        sschema:Dataset
        #               sschema:DataCatalog
        schema:Dataset
        #               schema:DataCatalog
    }
    ?subj a ?sosType .
    values (?type ?resourceType_u) {
        (schema:Dataset "data")
        (sschema:Dataset "data")
 
        (schema:DataCatalog "DataCatalog")
        (sschema:DataCatalog "DataCatalog")
        #(UNDEF "other")  # assume it's data. At least we should get  name.
    }
    ?subj a ?type .
    ?subj ?o ?item .
    graph ?g {

        ?subj schema:name|sschema:name ?name .
        ?subj schema:description|sschema:description ?description .

        OPTIONAL { ?subj schema:publisher/schema:legalName|sschema:publisher/sschema:legalName ?legalName . }
        OPTIONAL { ?subj schema:publisher/schema:name|sschema:publisher/sschema:name ?publisher . }
        bind (COALESCE(?publisher,?legalName, "No Publisher") As ?pubname)
        OPTIONAL { ?subj schema:datePublished|sschema:datePublished ?datep1 . }
        OPTIONAL { ?subj schema:dateCreated|sschema:dateCreated ?datec . }
        OPTIONAL { ?subj schema:dateModified|sschema:dateModified ?datem . }
        bind (COALESCE(?datec,?datem,?datep1) As ?datep)
        OPTIONAL { ?subj schema:temporalCoverage|sschema:temporalCoverage ?temporalCoverage . }
        .
        OPTIONAL {
            ?subj schema:spatialCoverage/schema:name|sschema:spatialCoverage/sschema:name|sschema:sdPublisher
                    ?place_name .
        }
        BIND (IF (BOUND(?place_name), ?place_name, "No Placenames") as ?placename) .
        optional {
            ?subj
                sschema:distribution/sschema:url|sschema:subjectOf/sschema:url|schema:distribution/schema:url|schema:subjectOf/schema:url
                    ?url .
        }
        OPTIONAL { ?subj schema:keywords|sschema:keywords ?kwu . }

        # OPTIONAL {?subj schema:spatialCoverage/schema:geo/schema:latitude|sschema:spatialCoverage/sschema:geo/sschema:latitude ?lat .}
        # OPTIONAL {?subj sschema:spatialCoverage/sschema:geo ?geo .
        #         ?geo a sschema:GeoCoordinates .
        #		 ?geo sschema:longitude ?lon .
        #		 ?geo sschema:llatitude ?lat .}

        #OPTIONAL {?subj sschema:spatialCoverage/sschema:geo ?geo .
        #         ?geo a sschema:GeoShape .
        #		 ?geo sschema:box ?box .}
        #     bind ( COALESCE(?box) As ?bbox)

        OPTIONAL {
                ?subj sschema:variableMeasured ?vm .
                ?vm a sschema:PropertyValue .
                ?vm sschema:name ?variableMeasured_a .
        }
        # if there is more than one location, then coallese to get the versions.
        OPTIONAL {
            ?subj sschema:variableMeasured ?vmd .
            ?vmd a sschema:PropertyValue .
            ?vmd sschema:name ?namedepth .
            FILTER (LCASE(?namedepth) IN ( "cmpdep",  "package_depth", "collection_depth", "Bottle Depth","sample depth","tow depth") ) .
            ?vmd sschema:maxValue ?maxDepth_d .
            ?vmd sschema:minValue ?minDepth_d
            bind (COALESCE(?maxDepth_d) As ?maxDepth)
            bind (COALESCE(?minDepth_d) As ?minDepth)
        }

    }
}
GROUP BY ?g ?subj   ?name ?description ?type ?pubname ?placename  ?datep ?maxDepth ?minDepth ?temporalCoverage ?url ?bbox
LIMIT 100
OFFSET 0

Then filters to be added: