summaryrefslogtreecommitdiff
path: root/test/test_trig.py
blob: 30bff63423eb286213ecf335c2a6036e7d3ca941 (plain)
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
import re

import pytest

import rdflib

TRIPLE = (
    rdflib.URIRef("http://example.com/s"),
    rdflib.RDFS.label,
    rdflib.Literal("example 1"),
)


def test_empty():
    g = rdflib.Graph()
    s = g.serialize(format="trig")
    assert s is not None


def test_repeat_triples():
    g = rdflib.ConjunctiveGraph()
    g.get_context("urn:a").add(
        (rdflib.URIRef("urn:1"), rdflib.URIRef("urn:2"), rdflib.URIRef("urn:3"))
    )

    g.get_context("urn:b").add(
        (rdflib.URIRef("urn:1"), rdflib.URIRef("urn:2"), rdflib.URIRef("urn:3"))
    )

    assert len(g.get_context("urn:a")) == 1
    assert len(g.get_context("urn:b")) == 1

    s = g.serialize(format="trig", encoding="latin-1")
    assert b"{}" not in s  # no empty graphs!


def test_same_subject():
    g = rdflib.ConjunctiveGraph()
    g.get_context("urn:a").add(
        (rdflib.URIRef("urn:1"), rdflib.URIRef("urn:p1"), rdflib.URIRef("urn:o1"))
    )

    g.get_context("urn:b").add(
        (rdflib.URIRef("urn:1"), rdflib.URIRef("urn:p2"), rdflib.URIRef("urn:o2"))
    )

    assert len(g.get_context("urn:a")) == 1
    assert len(g.get_context("urn:b")) == 1

    s = g.serialize(format="trig", encoding="latin-1")

    assert len(re.findall(b"p1", s)) == 1
    assert len(re.findall(b"p2", s)) == 1

    assert b"{}" not in s  # no empty graphs!


def test_remember_namespace():
    g = rdflib.ConjunctiveGraph()
    g.add(TRIPLE + (rdflib.URIRef("http://example.com/graph1"),))
    # In 4.2.0 the first serialization would fail to include the
    # prefix for the graph but later serialize() calls would work.
    first_out = g.serialize(format="trig", encoding="latin-1")
    second_out = g.serialize(format="trig", encoding="latin-1")
    assert b"@prefix ns1: <http://example.com/> ." in second_out
    assert b"@prefix ns1: <http://example.com/> ." in first_out


def test_graph_qname_syntax():
    g = rdflib.ConjunctiveGraph()
    g.add(TRIPLE + (rdflib.URIRef("http://example.com/graph1"),))
    out = g.serialize(format="trig", encoding="latin-1")
    assert b"ns1:graph1 {" in out


def test_graph_uri_syntax():
    g = rdflib.ConjunctiveGraph()
    # getQName will not abbreviate this, so it should serialize as
    # a '<...>' term.
    g.add(TRIPLE + (rdflib.URIRef("http://example.com/foo."),))
    out = g.serialize(format="trig", encoding="latin-1")
    assert b"<http://example.com/foo.> {" in out


def test_blank_graph_identifier():
    g = rdflib.ConjunctiveGraph()
    g.add(TRIPLE + (rdflib.BNode(),))
    out = g.serialize(format="trig", encoding="latin-1")
    graph_label_line = out.splitlines()[-4]

    assert re.match(rb"^_:[a-zA-Z0-9]+ \{", graph_label_line)


def test_graph_parsing():
    # should parse into single default graph context
    data = """
<http://example.com/thing#thing_a> <http://example.com/knows> <http://example.com/thing#thing_b> .
"""
    g = rdflib.ConjunctiveGraph()
    g.parse(data=data, format="trig")
    assert len(list(g.contexts())) == 1

    # should parse into single default graph context
    data = """
<http://example.com/thing#thing_a> <http://example.com/knows> <http://example.com/thing#thing_b> .

{ <http://example.com/thing#thing_c> <http://example.com/knows> <http://example.com/thing#thing_d> . }
"""
    g = rdflib.ConjunctiveGraph()
    g.parse(data=data, format="trig")
    assert len(list(g.contexts())) == 1

    # should parse into 2 contexts, one default, one named
    data = """
<http://example.com/thing#thing_a> <http://example.com/knows> <http://example.com/thing#thing_b> .

{ <http://example.com/thing#thing_c> <http://example.com/knows> <http://example.com/thing#thing_d> . }

<http://example.com/graph#graph_a> {
    <http://example.com/thing/thing_e> <http://example.com/knows> <http://example.com/thing#thing_f> .
}
"""
    g = rdflib.ConjunctiveGraph()
    g.parse(data=data, format="trig")
    assert len(list(g.contexts())) == 2


@pytest.mark.xfail(
    raises=AssertionError,
    reason="""
    This is failing because conjuncitve graph assigns things in the default graph to
    a graph with a bnode as name. On every parse iteration a new BNode is generated
    resulting in the default graph content appearing multipile times in the output.""",
)
def test_round_trips():

    data = """
<http://example.com/thing#thing_a> <http://example.com/knows> <http://example.com/thing#thing_b> .

{ <http://example.com/thing#thing_c> <http://example.com/knows> <http://example.com/thing#thing_d> . }

<http://example.com/graph#graph_a> {
    <http://example.com/thing/thing_e> <http://example.com/knows> <http://example.com/thing#thing_f> .
}
"""
    g = rdflib.ConjunctiveGraph()
    for i in range(5):
        g.parse(data=data, format="trig")
        data = g.serialize(format="trig")

    # output should only contain 1 mention of each resource/graph name
    assert data.count("thing_a") == 1
    assert data.count("thing_b") == 1
    assert data.count("thing_c") == 1
    assert data.count("thing_d") == 1
    assert data.count("thing_e") == 1
    assert data.count("thing_f") == 1
    assert data.count("graph_a") == 1


def test_default_graph_serializes_without_name():
    data = """
<http://example.com/thing#thing_a> <http://example.com/knows> <http://example.com/thing#thing_b> .

{ <http://example.com/thing#thing_c> <http://example.com/knows> <http://example.com/thing#thing_d> . }
"""
    g = rdflib.ConjunctiveGraph()
    g.parse(data=data, format="trig")
    data = g.serialize(format="trig", encoding="latin-1")

    assert b"None" not in data


def test_prefixes():

    data = """
    @prefix ns1: <http://ex.org/schema#> .
    <http://ex.org/docs/document1> = {
        ns1:Person_A a ns1:Person ;
            ns1:TextSpan "Simon" .
    }
    <http://ex.org/docs/document2> = {
        ns1:Person_C a ns1:Person ;
            ns1:TextSpan "Agnes" .
    }
    """

    cg = rdflib.ConjunctiveGraph()
    cg.parse(data=data, format="trig")
    data = cg.serialize(format="trig", encoding="latin-1")

    assert "ns2: <http://ex.org/docs/".encode("latin-1") in data, data
    assert "<ns2:document1>".encode("latin-1") not in data, data
    assert "ns2:document1".encode("latin-1") in data, data


def test_issue_2154():
    ds = rdflib.Dataset()
    sg = ds.serialize(format="trig")
    assert "prefix" not in sg, sg