1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
|
"""
Part of the bsfs test suite.
A copy of the license is provided with the project.
Author: Matthias Baumgartner, 2022
"""
# imports
import rdflib
import unittest
# bsie imports
from bsfs import schema
from bsfs.namespace import Namespace, ns
from bsfs.query import ast
from bsfs.utils import errors, URI
# objects to test
from bsfs.triple_store.sparql.parse_fetch import Fetch
## code ##
bsfs = Namespace('http://bsfs.ai/schema', fsep='/')
bse = Namespace('http://bsfs.ai/schema/Entity')
bst = Namespace('http://bsfs.ai/schema/Tag')
bsc = Namespace('http://bsfs.ai/schema/Collection')
class TestParseFetch(unittest.TestCase):
def setUp(self):
self.schema = schema.from_string('''
prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>
prefix xsd: <http://www.w3.org/2001/XMLSchema#>
prefix bsfs: <http://bsfs.ai/schema/>
prefix bse: <http://bsfs.ai/schema/Entity#>
prefix bst: <http://bsfs.ai/schema/Tag#>
prefix bsc: <http://bsfs.ai/schema/Collection#>
# nodes
bsfs:Entity rdfs:subClassOf bsfs:Node .
bsfs:Tag rdfs:subClassOf bsfs:Node .
bsfs:Collection rdfs:subClassOf bsfs:Node .
# literals
xsd:integer rdfs:subClassOf bsfs:Literal .
xsd:string rdfs:subClassOf bsfs:Literal .
# predicates
bse:tag rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsfs:Entity ;
rdfs:range bsfs:Tag .
bse:collection rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsfs:Entity ;
rdfs:range bsfs:Collection .
bse:filename rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsfs:Entity ;
rdfs:range xsd:string .
bse:rank rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsfs:Entity ;
rdfs:range xsd:integer .
bst:main rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsfs:Tag ;
rdfs:range bsfs:Entity .
bst:label rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsfs:Tag ;
rdfs:range xsd:string .
bsc:tag rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsfs:Collection ;
rdfs:range bsfs:Tag .
bsc:label rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsfs:Collection ;
rdfs:range xsd:string .
bsc:rating rdfs:subClassOf bsfs:Predicate ;
rdfs:domain bsfs:Collection ;
rdfs:range xsd:integer .
''')
# graph to test queries
self.graph = rdflib.Graph()
# schema hierarchies
self.graph.add((rdflib.URIRef('http://bsfs.ai/schema/Entity'), rdflib.RDFS.subClassOf, rdflib.URIRef('http://bsfs.ai/schema/Node')))
self.graph.add((rdflib.URIRef('http://bsfs.ai/schema/Collection'), rdflib.RDFS.subClassOf, rdflib.URIRef('http://bsfs.ai/schema/Node')))
self.graph.add((rdflib.URIRef('http://bsfs.ai/schema/Tag'), rdflib.RDFS.subClassOf, rdflib.URIRef('http://bsfs.ai/schema/Node')))
# entities
self.graph.add((rdflib.URIRef('http://example.com/entity#1234'), rdflib.RDF.type, rdflib.URIRef('http://bsfs.ai/schema/Entity')))
self.graph.add((rdflib.URIRef('http://example.com/entity#4321'), rdflib.RDF.type, rdflib.URIRef('http://bsfs.ai/schema/Entity')))
# tags
self.graph.add((rdflib.URIRef('http://example.com/tag#1234'), rdflib.RDF.type, rdflib.URIRef('http://bsfs.ai/schema/Tag')))
self.graph.add((rdflib.URIRef('http://example.com/tag#4321'), rdflib.RDF.type, rdflib.URIRef('http://bsfs.ai/schema/Tag')))
# collections
self.graph.add((rdflib.URIRef('http://example.com/collection#1234'), rdflib.RDF.type, rdflib.URIRef('http://bsfs.ai/schema/Collection')))
self.graph.add((rdflib.URIRef('http://example.com/collection#4321'), rdflib.RDF.type, rdflib.URIRef('http://bsfs.ai/schema/Collection')))
# entity literals
self.graph.add((rdflib.URIRef('http://example.com/entity#1234'), rdflib.URIRef(bse.rank), rdflib.Literal('1234', datatype=rdflib.XSD.integer)))
self.graph.add((rdflib.URIRef('http://example.com/entity#1234'), rdflib.URIRef(bse.filename), rdflib.Literal('filename_1234', datatype=rdflib.XSD.string)))
#self.graph.add((rdflib.URIRef('http://example.com/entity#4321'), rdflib.URIRef(bse.rank), rdflib.Literal('4321', datatype=rdflib.XSD.integer)))
self.graph.add((rdflib.URIRef('http://example.com/entity#4321'), rdflib.URIRef(bse.filename), rdflib.Literal('filename_4321', datatype=rdflib.XSD.string)))
# tag literals
self.graph.add((rdflib.URIRef('http://example.com/tag#1234'), rdflib.URIRef(bst.label), rdflib.Literal('tag_label_1234', datatype=rdflib.XSD.string)))
self.graph.add((rdflib.URIRef('http://example.com/tag#4321'), rdflib.URIRef(bst.label), rdflib.Literal('tag_label_4321', datatype=rdflib.XSD.string)))
# collection literals
self.graph.add((rdflib.URIRef('http://example.com/collection#1234'), rdflib.URIRef(bsc.label), rdflib.Literal('collection_label_1234', datatype=rdflib.XSD.string)))
self.graph.add((rdflib.URIRef('http://example.com/collection#1234'), rdflib.URIRef(bsc.rating), rdflib.Literal('1234', datatype=rdflib.XSD.integer)))
self.graph.add((rdflib.URIRef('http://example.com/collection#4321'), rdflib.URIRef(bsc.label), rdflib.Literal('collection_label_4321', datatype=rdflib.XSD.string)))
self.graph.add((rdflib.URIRef('http://example.com/collection#4321'), rdflib.URIRef(bsc.rating), rdflib.Literal('4321', datatype=rdflib.XSD.integer)))
# entity-tag links
self.graph.add((rdflib.URIRef('http://example.com/entity#1234'), rdflib.URIRef(bse.tag), rdflib.URIRef('http://example.com/tag#1234')))
self.graph.add((rdflib.URIRef('http://example.com/entity#4321'), rdflib.URIRef(bse.tag), rdflib.URIRef('http://example.com/tag#4321')))
# entity-collection links
self.graph.add((rdflib.URIRef('http://example.com/entity#1234'), rdflib.URIRef(bse.collection), rdflib.URIRef('http://example.com/collection#1234')))
self.graph.add((rdflib.URIRef('http://example.com/entity#4321'), rdflib.URIRef(bse.collection), rdflib.URIRef('http://example.com/collection#4321')))
# collection-tag links
self.graph.add((rdflib.URIRef('http://example.com/collection#1234'), rdflib.URIRef(bsc.tag), rdflib.URIRef('http://example.com/tag#1234')))
self.graph.add((rdflib.URIRef('http://example.com/collection#4321'), rdflib.URIRef(bsc.tag), rdflib.URIRef('http://example.com/tag#4321')))
# tag-entity links # NOTE: cross-over
self.graph.add((rdflib.URIRef('http://example.com/tag#1234'), rdflib.URIRef(bst.main), rdflib.URIRef('http://example.com/entity#4321')))
self.graph.add((rdflib.URIRef('http://example.com/tag#4321'), rdflib.URIRef(bst.main), rdflib.URIRef('http://example.com/entity#1234')))
# default parser
self.parser = Fetch(self.schema)
self.ent = self.schema.node(ns.bsfs.Entity)
def test_call(self):
# NOTE: The individual ast components are considered in the respective tests. Here, we test __call__ specifics.
# __call__ requires a valid root type
self.assertRaises(errors.BackendError, self.parser, self.schema.literal(ns.bsfs.Literal), ast.fetch.This('this'))
self.assertRaises(errors.ConsistencyError, self.parser, self.schema.node(ns.bsfs.Node).child(ns.bsfs.Invalid), ast.fetch.This('this'))
# __call__ requires a parseable root
self.assertRaises(errors.BackendError, self.parser, self.ent, ast.filter.FilterExpression())
# __call__ returns an executable query
q = self.parser(self.ent, ast.fetch.Fetch(bse.tag, ast.fetch.Value(bst.label, 'label')))
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.Literal('tag_label_1234', datatype=rdflib.XSD.string)),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.Literal('tag_label_4321', datatype=rdflib.XSD.string)),
})
def test_routing(self):
self.assertRaises(errors.BackendError, self.parser._parse_fetch_expression, self.ent, ast.fetch.FetchExpression(), '?head')
def test_all(self):
# multiple values query
q = self.parser(self.ent, ast.fetch.All(
ast.fetch.Value(bse.filename, name='filename'),
ast.fetch.Value(bse.rank, name='rank')),
)
self.assertSetEqual(set(q.names), {'filename', 'rank'})
if q.names == ('filename', 'rank'):
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.Literal('filename_1234', datatype=rdflib.XSD.string), rdflib.Literal('1234', datatype=rdflib.XSD.integer)),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.Literal('filename_4321', datatype=rdflib.XSD.string), None),
})
else:
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.Literal('1234', datatype=rdflib.XSD.integer), rdflib.Literal('filename_1234', datatype=rdflib.XSD.string)),
(rdflib.URIRef('http://example.com/entity#4321'), None, rdflib.Literal('filename_4321', datatype=rdflib.XSD.string)),
})
# mixed values and node query
q = self.parser(self.ent, ast.fetch.All(
ast.fetch.Value(bse.filename, name='filename'),
ast.fetch.Node(bse.tag, name='tag'),
))
self.assertSetEqual(set(q.names), {'filename', 'tag'})
if q.names == ('filename', 'tag'):
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.Literal('filename_1234', datatype=rdflib.XSD.string), rdflib.URIRef('http://example.com/tag#1234')),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.Literal('filename_4321', datatype=rdflib.XSD.string), rdflib.URIRef('http://example.com/tag#4321')),
})
else:
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.URIRef('http://example.com/tag#1234'), rdflib.Literal('filename_1234', datatype=rdflib.XSD.string)),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.URIRef('http://example.com/tag#4321'), rdflib.Literal('filename_4321', datatype=rdflib.XSD.string)),
})
# multiple values and second hop
q = self.parser(self.ent, ast.fetch.Fetch(bse.tag, ast.fetch.All(
ast.fetch.This(name='tag'),
ast.fetch.Value(bst.label, name='label'),
)))
self.assertSetEqual(set(q.names), {'tag', 'label'})
if q.names == ('tag', 'label'):
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.URIRef('http://example.com/tag#1234'), rdflib.Literal('tag_label_1234', datatype=rdflib.XSD.string)),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.URIRef('http://example.com/tag#4321'), rdflib.Literal('tag_label_4321', datatype=rdflib.XSD.string)),
})
else:
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.Literal('tag_label_1234', datatype=rdflib.XSD.string), rdflib.URIRef('http://example.com/tag#1234')),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.Literal('tag_label_4321', datatype=rdflib.XSD.string), rdflib.URIRef('http://example.com/tag#4321')),
})
def test_fetch(self):
# two-hop query
q = self.parser(self.ent, ast.fetch.Fetch(bse.tag, ast.fetch.Value(bst.label, 'tag_label')))
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.Literal('tag_label_1234', datatype=rdflib.XSD.string)),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.Literal('tag_label_4321', datatype=rdflib.XSD.string)),
})
# three-hop-query
q = self.parser(self.ent, ast.fetch.Fetch(bse.tag, ast.fetch.Fetch(bst.main, ast.fetch.Value(bse.rank, 'entity_rank'))))
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), None),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.Literal('1234', datatype=rdflib.XSD.integer)),
})
def test_node(self):
# cannot use the internal hop name
self.assertRaises(errors.BackendError, self.parser, self.ent, ast.fetch.Node(bse.tag, self.parser.ngen.prefix[1:] + '123'))
# a simple Node statement
q = self.parser(self.ent, ast.fetch.Node(bse.tag, 'tag'))
self.assertSetEqual(set(q.names), {'tag'})
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.URIRef('http://example.com/tag#1234')),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.URIRef('http://example.com/tag#4321')),
})
def test_value(self):
# cannot use the internal hop name
self.assertRaises(errors.BackendError, self.parser, self.schema.node(ns.bsfs.Entity), ast.fetch.Value(bse.filename, self.parser.ngen.prefix[1:] + '123'))
# a simple Value statement
q = self.parser(self.ent, ast.fetch.Value(bse.filename, 'filename'))
self.assertSetEqual(set(q.names), {'filename'})
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.Literal('filename_1234', datatype=rdflib.XSD.string)),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.Literal('filename_4321', datatype=rdflib.XSD.string)),
})
def test_this(self):
# cannot use the internal hop name
self.assertRaises(errors.BackendError, self.parser, self.ent, ast.fetch.This(self.parser.ngen.prefix[1:] + '123'))
# a simple This statement
self.assertEqual(self.parser._this(self.ent, ast.fetch.This('this'), '?head'),
({('?head', 'this')}, ''))
q = self.parser(self.ent, ast.fetch.This('this'))
self.assertSetEqual(set(q(self.graph)), {
(rdflib.URIRef('http://example.com/entity#1234'), rdflib.URIRef('http://example.com/entity#1234')),
(rdflib.URIRef('http://example.com/entity#4321'), rdflib.URIRef('http://example.com/entity#4321')),
})
## main ##
if __name__ == '__main__':
unittest.main()
## EOF ##
|
