python - 使用本地 RDF 存储的 SPARQL 查询

Question

我正在尝试使用本地 RDF 图创建 SPARQL 查询。但它不起作用。我已经包含了我的代码，下面是我的代码。

我有两个类(class)，分别称为“学生”和“大学”。学生类有两个属性(enrolledOn 和 StudiesAt)。 University 类还有两个属性(UniversityLocation 和 UniversityRanking)。此外，我还输入了一些数据(RDF 三元组)。 Student 类和 University 类各有三个数据实体。

我的 SPARQL 查询位于底部。我想选择所有在排名前 10 的大学学习的学生。但目前，我的 SPARQL 查询没有返回任何内容。该查询应返回 Khalil 和 Ahmed。

任何帮助将不胜感激。谢谢。

我的代码:

import rdfextras
import rdflib
from rdflib.graph import Graph, Store, URIRef, Literal
from rdflib.namespace import Namespace, RDFS
from rdflib import plugin
from SPARQLWrapper import SPARQLWrapper, JSON

rdflib.plugin.register('sparql', rdflib.query.Processor,
                       'rdfextras.sparql.processor', 'Processor')
rdflib.plugin.register('sparql', rdflib.query.Result,
                       'rdfextras.sparql.query', 'SPARQLQueryResult')


#=====================data for STUDENT class==============================
rdf_xml_Student_data = """<?xml version="1.0"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:Student="http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/Person/Student#">

<rdf:Description rdf:about="http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/Person/Student/Harith">
  <Student:enrolledOn>MScComputerScience</Student:enrolledOn>
  <Student:studiesAt>Queen_Mary</Student:studiesAt>
</rdf:Description>

<rdf:Description rdf:about="http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/Person/Student/Khalil">
  <Student:enrolledOn>BScComputerScience</Student:enrolledOn>
  <Student:studiesAt>Oxford_University</Student:studiesAt>
</rdf:Description>

<rdf:Description rdf:about="http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/Person/Student/Ahmed">
  <Student:enrolledOn>BScComputerScience</Student:enrolledOn>
  <Student:studiesAt>Oxford_University</Student:studiesAt>
</rdf:Description>

</rdf:RDF>
"""


#=====================data for UNIVERSITY class==============================
rdf_xml_University_data = """<?xml version="1.0"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:University="http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/University#">

<rdf:Description rdf:about="http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/University/Queen_Mary">
  <University:UniversityLocation>London</University:UniversityLocation>
  <University:UniversityRanking>36</University:UniversityRanking>
</rdf:Description>

<rdf:Description rdf:about="http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/University/City_University">
  <University:UniversityLocation>London</University:UniversityLocation>
  <University:UniversityRanking>43</University:UniversityRanking>
</rdf:Description>

<rdf:Description rdf:about="http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/University/Oxford_University">
  <University:UniversityLocation>Oxford</University:UniversityLocation>
  <University:UniversityRanking>2</University:UniversityRanking>
</rdf:Description>

</rdf:RDF>
"""


# -- (part1) create and RDF store in memory --
memory_store = plugin.get('IOMemory', Store)()
graph_id = URIRef(u'http://example.com/foo')
g = Graph(store=memory_store, identifier=graph_id)
g.bind('ex','http://example.com/')   

g.parse(data=rdf_xml_Student_data, format="application/rdf+xml")
g.parse(data=rdf_xml_University_data, format="application/rdf+xml")




#===========================SPARQL QUERY====================================
# QUERY - select all students who study at top 10 ranked universities
results = g.query("""PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX student: <http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/Person/Student#>
PREFIX university: <http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/University#>

SELECT ?stu 
WHERE { ?uni university:UniversityRanking ?UniversityRanking.
        ?stu student:studiesAt ?uni.
        FILTER ( ?UniversityRanking < 10)
}
""")



print("\n============QUERY RESULTS===============\n")
for row in results.result:
    print(row)

这就是我运行上述代码后三元组在图中的存储方式:

=========================STUDENT class==================================
Subject         Predicate           Object
========================================================================
Harith          enrolledOn          MScComputerScience
Harith          studiesAt           Queen_Mary
Khalil          enrolledOn          BScComputerScience
Khalil          studiesAt           Oxford_University
Ahmed           enrolledOn          BScComputerScience
Ahmed           studiesAt           Oxford_University


=============================UNIVERSITY class=======================
Subject            Predicate           Object
===============================================================
Queen_Mary             UniversityLocation      London
Queen_Mary             UniversityRanking       36
City_University        UniversityLocation      London
City_University        UniversityRanking       43
Oxford_University        UniversityLocation    Oxford
Oxford_University        UniversityRanking     2

Answer 1

这并不是一个真正的答案，但除非您的 RDFLib 使用超过 3-4 年，否则您的代码可以简单得多:

from rdflib import Graph

#=====================data for STUDENT class==============================
rdf_xml_Student_data = """<?xml version="1.0"?> ... <snip>"""

#=====================data for UNIVERSITY class==============================
rdf_xml_University_data = """<?xml version="1.0"?> ... <snip>"""


# -- (part1) create and RDF store in memory --
g = Graph()

g.parse(data=rdf_xml_Student_data)
g.parse(data=rdf_xml_University_data)


#===========================SPARQL QUERY====================================
# QUERY - select all students who study at top 10 ranked universities
results = g.query("""PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX student: <http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/Person/Student#>
PREFIX university: <http://www.semanticweb.org/ontologies/2013/2/Coursework.owl/Thing/University#>

SELECT ?stu 
WHERE { ?uni university:UniversityRanking ?UniversityRanking.
    ?stu student:studiesAt ?uni.
    FILTER ( ?UniversityRanking < 10)
}
""")



print("\n============QUERY RESULTS===============\n")
for row in results.result:
    print(row)