rdflib-hdt 3.3

PyPi installation (recommended)

# you can install using pip
pip install rdflib-hdt

# or you can use pipenv
pipenv install rdflib-hdt

Manual installation

Requirement: pipenv

git clone https://github.com/Callidon/pyHDT
cd pyHDT/
./install.sh

Graph usage (recommended)

from rdflib import Graph
from rdflib_hdt import HDTStore
from rdflib.namespace import FOAF

# Load an HDT file. Missing indexes are generated automatically
# You can provide the index file by putting them in the same directory than the HDT file.
store = HDTStore("test.hdt")

# Display some metadata about the HDT document itself
print(f"Number of RDF triples: {len(store)}")
print(f"Number of subjects: {store.nb_subjects}")
print(f"Number of predicates: {store.nb_predicates}")
print(f"Number of objects: {store.nb_objects}")
print(f"Number of shared subject-object: {store.nb_shared}")

Using the RDFlib API, you can also execute SPARQL queries over an HDT document. If you do so, we recommend that you first call the optimize_sparql function, which optimize the RDFlib SPARQL query engine in the context of HDT documents.

from rdflib import Graph
from rdflib_hdt import HDTStore, optimize_sparql

# Calling this function optimizes the RDFlib SPARQL engine for HDT documents
optimize_sparql()

graph = Graph(store=HDTStore("test.hdt"))

# You can execute SPARQL queries using the regular RDFlib API
qres = graph.query("""
PREFIX foaf: <http://xmlns.com/foaf/0.1/>
SELECT ?name ?friend WHERE {
   ?a foaf:knows ?b.
   ?a foaf:name ?name.
   ?b foaf:name ?friend.
}""")

for row in qres:
  print(f"{row.name} knows {row.friend}")

HDT Document usage

from rdflib_hdt import HDTDocument

# Load an HDT file. Missing indexes are generated automatically.
# You can provide the index file by putting them in the same directory than the HDT file.
document = HDTDocument("test.hdt")

# Display some metadata about the HDT document itself
print(f"Number of RDF triples: {document.total_triples}")
print(f"Number of subjects: {document.nb_subjects}")
print(f"Number of predicates: {document.nb_predicates}")
print(f"Number of objects: {document.nb_objects}")
print(f"Number of shared subject-object: {document.nb_shared}")

# Fetch all triples that matches { ?s foaf:name ?o }
# Use None to indicates variables
triples, cardinality = document.search_triples((None, FOAF("name"), None))

print(f"Cardinality of (?s foaf:name ?o): {cardinality}")
for s, p, o in triples:
  print(triple)

# The search also support limit and offset
triples, cardinality = document.search_triples((None, FOAF("name"), None), limit=10, offset=100)
# etc ...

An HDT document also provides support for evaluating joins over a set of triples patterns.

from rdflib_hdt import HDTDocument
from rdflib import Variable
from rdflib.namespace import FOAF, RDF

document = HDTDocument("test.hdt")

# find the names of two entities that know each other
tp_a = (Variable("a"), FOAF("knows"), Variable("b"))
tp_b = (Variable("a"), FOAF("name"), Variable("name"))
tp_c = (Variable("b"), FOAF("name"), Variable("friend"))
query = set([tp_a, tp_b, tp_c])

iterator = document.search_join(query)
print(f"Estimated join cardinality: {len(iterator)}")

# Join results are produced as ResultRow, like in the RDFlib SPARQL API
for row in iterator:
   print(f"{row.name} knows {row.friend}")