Querying¶

from kgforge.core import KnowledgeGraphForge

forge = KnowledgeGraphForge("../../configurations/forge.yml")

from kgforge.core import Resource
from kgforge.specializations.resources import Dataset
from kgforge.core.wrappings.paths import Filter, FilterOperator

jane = Resource(type="Person", name="Jane Doe", award=["Nobel"])

resource = forge.retrieve(jane.id)

jane = Resource(type="Person", name="Jane Doe", award=["Nobel"])

jane.email = ["jane.doe@epfl.ch", "jane.doe@example.org"]

jane_v1 = forge.retrieve(jane.id, version=1)

jane_v1_tag = forge.retrieve(jane.id, version="v1")

jane_v1_rev = forge.retrieve(jane.id+"?rev=1")

resource = forge.retrieve(jane.id, cross_bucket=True) # cross_bucket defaults to False

import copy

other_resource = copy.deepcopy(resource)

other_resource.id = "https://myincreadibleid-987654321"

url = other_resource._store_metadata['_self']

same_resource_url = forge.retrieve(id=url)
same_resource_id = forge.retrieve(id=other_resource.id)

resource = forge.retrieve(jane.id, retrieve_source=False) # retrieve_source defaults to True

jane = Resource(type="Person", name="Jane Doe")
contribution_jane = Resource(type="Contribution", agent=jane)

john = Resource(type="Person", name="John Smith")
contribution_john = Resource(type="Contribution", agent=john)

dataset = Dataset(forge, type="Dataset", contribution=[contribution_jane, contribution_john])
dataset.add_distribution("../../data/associations.tsv")

p = forge.paths("Dataset")

resources = forge.search(p.type.id=="Person", limit=3)

# Search for resources of type Dataset and with text/tab-separated-values as distribution.encodingFormat
resources = forge.search(p.type.id == "Dataset", p.distribution.encodingFormat == "text/tab-separated-values", limit=3)

# Search for resources of type Dataset and with text/tab-separated-values as distribution.encodingFormat
# and created a given dateTime (by default, dateTime values should be signaled by the suffix "^^xsd:dateTime")
filters = {
           "type": "Dataset", 
           "distribution":{"encodingFormat":"text/tab-separated-values"},
           "_createdAt":dataset._store_metadata._createdAt+"^^xsd:dateTime"
          }
resources = forge.search(filters, limit=3)

# Search for resources of type Dataset and with text/tab-separated-values as distribution.encodingFormat
# and created a given dateTime (dateTime values should be signaled by the suffix "^^xsd:dateTime")
filter_1 = Filter(operator=FilterOperator.EQUAL, path=["type"], value="Dataset")
filter_2 = Filter(operator=FilterOperator.EQUAL, path=["distribution","encodingFormat"], value="text/tab-separated-values")
filter_3 = Filter(operator=FilterOperator.LOWER_OR_Equal_Than, path=["_createdAt"], value=dataset._store_metadata._createdAt+"^^xsd:dateTime")

resources = forge.search(filter_1, filter_2, filter_3, limit=3)

# Search for resources of type Person
filters = {"type": "Person"}
resources = forge.search(filters, limit=3, search_endpoint='sparql')

# Search for resources of type Person and retrieve their ids and names.
filters = {"@type": "http://schema.org/Person"}
resources = forge.search(filters, limit=3, 
                         search_endpoint='elastic', 
                         includes=["@id", "@type"]) # fields can also be excluded with 'excludes'

resources = forge.search(p.type.id == "Association", limit=3, cross_bucket=True)  # cross_bucket defaults to False

#Furthermore it is possible to filter by bucket when cross_bucket is set to True. Setting a bucket value when cross_bucket is False will trigger a not_supported exception.
resources = forge.search(p.type.id == "Person", limit=3, cross_bucket=True, bucket="dke/kgforge")  # add a bucket

resources = forge.search(p.type.id == "Association", limit=3, retrieve_source=False)  # retrieve_source defaults to True

jane = Resource(type="Person", name="Jane Doe")
contribution_jane = Resource(type="Contribution", agent=jane)

john = Resource(type="Person", name="John Smith")
contribution_john = Resource(type="Contribution", agent=john)

association = Resource(type="Dataset", contribution=[contribution_jane, contribution_john])

query = """
    SELECT ?id ?name ?contributor
    WHERE {
        ?id a Dataset ;
        contribution/agent ?contributor.
        ?contributor name ?name.
    }
"""

resources = forge.sparql(query, limit=3)

query = """
PREFIX dc: <http://purl.org/dc/elements/1.1/>
   PREFIX dcat: <http://www.w3.org/ns/dcat#>
   PREFIX dcterms: <http://purl.org/dc/terms/>
   PREFIX mba: <http://api.brain-map.org/api/v2/data/Structure/>
   PREFIX nsg: <https://neuroshapes.org/>
   PREFIX owl: <http://www.w3.org/2002/07/owl#>
   PREFIX prov: <http://www.w3.org/ns/prov#>
   PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
   PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
   PREFIX schema: <http://schema.org/>
   PREFIX sh: <http://www.w3.org/ns/shacl#>
   PREFIX shsh: <http://www.w3.org/ns/shacl-shacl#>
   PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
   PREFIX vann: <http://purl.org/vocab/vann/>
   PREFIX void: <http://rdfs.org/ns/void#>
   PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
   PREFIX : <https://neuroshapes.org/>
   SELECT ?id ?name
   WHERE {
       ?id a schema:Dataset ;
       nsg:contribution/prov:agent ?contributor.
       ?contributor schema:name ?name.
   }
   ORDER BY ?id
   LIMIT 1
   OFFSET 0
"""

query_without_limit = """
   PREFIX dc: <http://purl.org/dc/elements/1.1/>
   PREFIX dcat: <http://www.w3.org/ns/dcat#>
   PREFIX dcterms: <http://purl.org/dc/terms/>
   PREFIX mba: <http://api.brain-map.org/api/v2/data/Structure/>
   PREFIX nsg: <https://neuroshapes.org/>
   PREFIX owl: <http://www.w3.org/2002/07/owl#>
   PREFIX prov: <http://www.w3.org/ns/prov#>
   PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
   PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
   PREFIX schema: <http://schema.org/>
   PREFIX sh: <http://www.w3.org/ns/shacl#>
   PREFIX shsh: <http://www.w3.org/ns/shacl-shacl#>
   PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
   PREFIX vann: <http://purl.org/vocab/vann/>
   PREFIX void: <http://rdfs.org/ns/void#>
   PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
   PREFIX : <https://neuroshapes.org/>
   SELECT ?id ?name
   WHERE {
       ?id a schema:Dataset ;
       nsg:contribution/prov:agent ?contributor.
       ?contributor schema:name ?name.
   }
   ORDER BY ?id
"""

query_without_context = """
    SELECT ?id ?name ?contributor
    WHERE {
        ?id a Dataset ;
        contribution/agent ?contributor.
        ?contributor name ?name.
    }
"""

jane = Resource(type="Person", name="Jane Doe")
contribution_jane = Resource(type="Contribution", agent=jane)

john = Resource(type="Person", name="John Smith")
contribution_john = Resource(type="Contribution", agent=john)

association = Resource(type="Dataset", contribution=[contribution_jane, contribution_john])

query = """
        {
          "_source": {
            "includes": [
              "@id",
              "name"
            ]
          },
          "query": {
            "term": {
              "@type": "http://schema.org/Dataset"
            }
          }
        }
"""

# limit and offset (when provided in this method call) superseed 'size' and 'from' values provided in the query
resources = forge.elastic(query, limit=3)

jane = Resource(type="Person", name="Jane Doe")

distribution = forge.attach("../../data")

association = Resource(type="Association", agent=jane, distribution=distribution)

# By default, the downladable file urls are collected from the json path "distribution.contentUrl" (follow="distribution.contentUrl") and
# the files are downloaded in the current path (path="."). 
# The argument overwrite: bool can be provided to decide whether to overwrite (True) existing files with the same name or
# to create new ones (False) with their names suffixed with a timestamp.
# A cross_bucket argument can be provided to download data from the configured bucket (cross_bucket=False - the default value) 
# or from a bucket different than the configured one (cross_bucket=True). The configured store should support crossing buckets for this to work.
forge.download(association)

# Specific content type can be downloaded.
forge.download(association, content_type="text/tab-separated-values")

# The urls or the files to download can be collected from a different json path (by setting a value for "follow") and 
# the files downloaded to a different path (by setting a value for "path")
forge.download(association, follow="distribution.contentUrl", path="./downloaded/")

#! rm -R ./downloaded/