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
|
"""Sparql queries to get metadata about WIKI and RIF metadata.
NOTE: In the CONSTRUCT queries below, we manually sort the arrays from
the result of a CONSTRUCT. This is because the SPARQL engine does
not provide a guarantee that it will support an ORDER BY clause in a
CONSTRUCT. Using ORDER BY on a solution sequence for a CONSTRUCT or
DESCRIBE query has no direct effect because only SELECT returns a
sequence of results. See:
<https://stackoverflow.com/questions/78186393>
<https://www.w3.org/TR/rdf-sparql-query/#modOrderBy>
"""
from string import Template
from gn3.db.rdf import BASE_CONTEXT, RDF_PREFIXES, query_frame_and_compact, sparql_query
from gn3.db.wiki import MissingDBDataException
WIKI_CONTEXT = BASE_CONTEXT | {
"foaf": "http://xmlns.com/foaf/0.1/",
"dct": "http://purl.org/dc/terms/",
"categories": "gnt:belongsToCategory",
"web_url": "foaf:homepage",
"version": "gnt:hasVersion",
"symbol": "rdfs:label",
"reason": "gnt:reason",
"species": "gnt:species",
"pubmed_ids": "dct:references",
"email": "foaf:mbox",
"initial": "gnt:initial",
"comment": "rdfs:comment",
"created": "dct:created",
"id": "dct:identifier",
}
def __sanitize_result(result: dict) -> dict:
"""Make sure `categories` and `pubmed_ids` are always arrays"""
if not result:
return {}
categories = result.get("categories")
if isinstance(categories, str):
result["categories"] = [categories] if categories else []
pmids = result.get("pubmed_ids")
if isinstance(pmids, str):
result["pubmed_ids"] = [pmids] if pmids else []
if isinstance(pmids, int):
result["pubmed_ids"] = [pmids]
result["pubmed_ids"] = [
int(pmid.split("/")[-1]) if isinstance(pmid, str) else pmid
for pmid in result["pubmed_ids"]
]
return result
def get_wiki_entries_by_symbol(
symbol: str, sparql_uri: str, graph: str = "<http://genenetwork.org>"
) -> dict:
"""Fetch all the Wiki entries using the symbol"""
# This query uses a sub-query to fetch the latest comment by the
# version id.
query = Template(
"""
$prefix
CONSTRUCT {
?comment rdfs:label ?symbol;
gnt:reason ?reason ;
gnt:species ?species ;
dct:references ?pmid ;
foaf:homepage ?weburl ;
rdfs:comment ?text ;
foaf:mbox ?email ;
gnt:initial ?usercode ;
gnt:belongsToCategory ?category ;
gnt:hasVersion ?max ;
dct:created ?created ;
dct:identifier ?id_ .
} FROM $graph WHERE {
?comment rdfs:label ?text_ ;
gnt:symbol ?symbol ;
rdf:type gnc:GNWikiEntry ;
dct:identifier ?id_ ;
dct:created ?createTime .
FILTER ( LCASE(?symbol) = LCASE('$symbol') ) .
{
SELECT (MAX(?vers) AS ?max) ?id_ WHERE {
?comment dct:identifier ?id_ ;
dct:hasVersion ?vers .
}
}
?comment dct:hasVersion ?max .
OPTIONAL { ?comment gnt:reason ?reason_ } .
OPTIONAL {
?comment gnt:belongsToSpecies ?speciesId .
?speciesId gnt:shortName ?species .
} .
OPTIONAL { ?comment dct:references ?pmid_ } .
OPTIONAL { ?comment foaf:homepage ?weburl_ } .
OPTIONAL { ?comment gnt:initial ?usercode_ } .
OPTIONAL { ?comment foaf:mbox ?email_ } .
OPTIONAL { ?comment gnt:belongsToCategory ?category_ } .
BIND (str(?createTime) AS ?created) .
BIND (str(?text_) AS ?text) .
BIND (str(?version) AS ?versionId) .
BIND (STR(COALESCE(?pmid_, "")) AS ?pmid) .
BIND (COALESCE(?reason_, "") AS ?reason) .
BIND (STR(COALESCE(?weburl_, "")) AS ?weburl) .
BIND (COALESCE(?usercode_, "") AS ?usercode) .
BIND (STR(COALESCE(?email_, "")) AS ?email) .
BIND (COALESCE(?species_, "") AS ?species) .
BIND (COALESCE(?category_, "") AS ?category) .
}
"""
).substitute(
prefix=RDF_PREFIXES,
graph=graph,
symbol=symbol,
)
results = query_frame_and_compact(query, WIKI_CONTEXT, sparql_uri)
data = [__sanitize_result(result) for result in results.get("data", {})]
# See note above in the doc-string
results["data"] = sorted(data, key=lambda d: d["created"])
if not data:
return results
return results
def get_comment_history(
comment_id: int, sparql_uri: str, graph: str = "<http://genenetwork.org>"
) -> dict:
"""Get all the historical data for a given id"""
query = Template(
"""
$prefix
CONSTRUCT {
?comment rdfs:label ?symbolName ;
gnt:reason ?reason ;
gnt:species ?species ;
dct:references ?pmid ;
foaf:homepage ?weburl ;
rdfs:comment ?text ;
foaf:mbox ?email ;
gnt:initial ?usercode ;
gnt:belongsToCategory ?category ;
gnt:hasVersion ?version ;
dct:created ?created .
} FROM $graph WHERE {
?comment rdf:type gnc:GNWikiEntry ;
rdfs:label ?text_ ;
gnt:symbol ?symbol ;
dct:created ?createTime ;
dct:hasVersion ?version ;
dct:identifier $comment_id ;
dct:identifier ?id_ .
OPTIONAL { ?comment gnt:reason ?reason_ } .
OPTIONAL {
?comment gnt:belongsToSpecies ?speciesId .
?speciesId gnt:shortName ?species_ .
} .
OPTIONAL { ?comment dct:references ?pmid_ . } .
OPTIONAL { ?comment foaf:homepage ?weburl_ . } .
OPTIONAL { ?comment gnt:initial ?usercode_ . } .
OPTIONAL { ?comment foaf:mbox ?email_ . } .
OPTIONAL { ?comment gnt:belongsToCategory ?category_ . } .
BIND (str(?text_) AS ?text) .
BIND (str(?createTime) AS ?created) .
BIND (STR(COALESCE(?pmid_, "")) AS ?pmid) .
BIND (COALESCE(?reason_, "") AS ?reason) .
BIND (STR(COALESCE(?weburl_, "")) AS ?weburl) .
BIND (COALESCE(?usercode_, "") AS ?usercode) .
BIND (STR(COALESCE(?email_, "")) AS ?email) .
BIND (COALESCE(?species_, "") AS ?species) .
BIND (COALESCE(?category_, "") AS ?category) .
}
"""
).substitute(prefix=RDF_PREFIXES, graph=graph, comment_id=comment_id)
results = query_frame_and_compact(query, WIKI_CONTEXT, sparql_uri)
data = [__sanitize_result(result) for result in results.get("data", {})]
# See note above in the doc-string
results["data"] = sorted(data, key=lambda d: d["version"], reverse=True)
return results
def get_next_comment_version(
comment_id: int, sparql_uri: str, graph: str = "<http://genenetwork.org>"
) -> int:
"Find the next version to add"
query = Template(
"""
$prefix
SELECT MAX(?version) as ?max_version FROM $graph WHERE {
?comment rdf:type gnc:GNWikiEntry ;
dct:identifier "$comment_id"^^xsd:integer ;
dct:hasVersion ?version .
}
"""
).substitute(prefix=RDF_PREFIXES, graph=graph, comment_id=comment_id)
results = sparql_query(
query=query, endpoint=sparql_uri, format_type="json")[0]
if not results:
raise MissingDBDataException
return int(results["max_version"]["value"]) + 1
|
