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
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
|
from __future__ import absolute_import
import collections
import itertools
import datetime
from collections import Mapping, MutableMapping
import isodate
from six import text_type, iteritems
from rdflib.namespace import NamespaceManager
from rdflib import Variable, BNode, Graph, ConjunctiveGraph, URIRef, Literal
from rdflib.term import Node
from rdflib.plugins.sparql.parserutils import CompValue
import rdflib.plugins.sparql
class SPARQLError(Exception):
def __init__(self, msg=None):
Exception.__init__(self, msg)
class NotBoundError(SPARQLError):
def __init__(self, msg=None):
SPARQLError.__init__(self, msg)
class AlreadyBound(SPARQLError):
"""Raised when trying to bind a variable that is already bound!"""
def __init__(self):
SPARQLError.__init__(self)
class SPARQLTypeError(SPARQLError):
def __init__(self, msg):
SPARQLError.__init__(self, msg)
class Bindings(MutableMapping):
"""
A single level of a stack of variable-value bindings.
Each dict keeps a reference to the dict below it,
any failed lookup is propegated back
In python 3.3 this could be a collections.ChainMap
"""
def __init__(self, outer=None, d=[]):
self._d = dict(d)
self.outer = outer
def __getitem__(self, key):
try:
return self._d[key]
except KeyError:
if not self.outer:
raise
return self.outer[key]
def __contains__(self, key):
try:
self[key]
return True
except KeyError:
return False
def __setitem__(self, key, value):
self._d[key] = value
def __delitem__(self, key):
raise Exception("DelItem is not implemented!")
def __len__(self):
i = 0
for x in self:
i += 1
return i
def __iter__(self):
d = self
while d is not None:
for i in dict.__iter__(d._d):
yield i
d = d.outer
def __str__(self):
return "Bindings({"+", ".join((k, self[k]) for k in self)+"})"
def __repr__(self):
return text_type(self)
class FrozenDict(Mapping):
"""
An immutable hashable dict
Taken from http://stackoverflow.com/a/2704866/81121
"""
def __init__(self, *args, **kwargs):
self._d = dict(*args, **kwargs)
self._hash = None
def __iter__(self):
return iter(self._d)
def __len__(self):
return len(self._d)
def __getitem__(self, key):
return self._d[key]
def __hash__(self):
# It would have been simpler and maybe more obvious to
# use hash(tuple(sorted(self._d.iteritems()))) from this discussion
# so far, but this solution is O(n). I don't know what kind of
# n we are going to run into, but sometimes it's hard to resist the
# urge to optimize when it will gain improved algorithmic performance.
if self._hash is None:
self._hash = 0
for key, value in iteritems(self):
self._hash ^= hash(key)
self._hash ^= hash(value)
return self._hash
def project(self, vars):
return FrozenDict(
(x for x in iteritems(self) if x[0] in vars))
def disjointDomain(self, other):
return not bool(set(self).intersection(other))
def compatible(self, other):
for k in self:
try:
if self[k] != other[k]:
return False
except KeyError:
pass
return True
def merge(self, other):
res = FrozenDict(
itertools.chain(iteritems(self), iteritems(other)))
return res
def __str__(self):
return str(self._d)
def __repr__(self):
return repr(self._d)
class FrozenBindings(FrozenDict):
def __init__(self, ctx, *args, **kwargs):
FrozenDict.__init__(self, *args, **kwargs)
self.ctx = ctx
def __getitem__(self, key):
if not isinstance(key, Node):
key = Variable(key)
if not type(key) in (BNode, Variable):
return key
return self._d[key]
def project(self, vars):
return FrozenBindings(
self.ctx, (x for x in iteritems(self) if x[0] in vars))
def merge(self, other):
res = FrozenBindings(
self.ctx, itertools.chain(iteritems(self), iteritems(other)))
return res
def _now(self):
return self.ctx.now
def _bnodes(self):
return self.ctx.bnodes
def _prologue(self):
return self.ctx.prologue
prologue = property(_prologue)
bnodes = property(_bnodes)
now = property(_now)
def forget(self, before, _except=None):
"""
return a frozen dict only of bindings made in self
since before
"""
if not _except:
_except = []
# bindings from initBindings are newer forgotten
return FrozenBindings(
self.ctx, (
x for x in iteritems(self) if (
x[0] in _except or
x[0] in self.ctx.initBindings or
before[x[0]] is None)))
def remember(self, these):
"""
return a frozen dict only of bindings in these
"""
return FrozenBindings(
self.ctx, (x for x in iteritems(self) if x[0] in these))
class QueryContext(object):
"""
Query context - passed along when evaluating the query
"""
def __init__(self, graph=None, bindings=None, initBindings=None):
self.initBindings = initBindings
self.bindings = Bindings(d=bindings or [])
if initBindings: self.bindings.update(initBindings)
if isinstance(graph, ConjunctiveGraph):
self._dataset = graph
if rdflib.plugins.sparql.SPARQL_DEFAULT_GRAPH_UNION:
self.graph = self.dataset
else:
self.graph = self.dataset.default_context
else:
self._dataset = None
self.graph = graph
self.prologue = None
self.now = datetime.datetime.now(isodate.tzinfo.UTC)
self.bnodes = collections.defaultdict(BNode)
def clone(self, bindings=None):
r = QueryContext(
self._dataset if self._dataset is not None else self.graph, bindings or self.bindings, initBindings=self.initBindings)
r.prologue = self.prologue
r.graph = self.graph
r.bnodes = self.bnodes
return r
def _get_dataset(self):
if self._dataset is None:
raise Exception(
'You performed a query operation requiring ' +
'a dataset (i.e. ConjunctiveGraph), but ' +
'operating currently on a single graph.')
return self._dataset
dataset = property(_get_dataset, doc="current dataset")
def load(self, source, default=False, **kwargs):
def _load(graph, source):
try:
return graph.load(source, **kwargs)
except:
pass
try:
return graph.load(source, format='n3', **kwargs)
except:
pass
try:
return graph.load(source, format='nt', **kwargs)
except:
raise Exception(
"Could not load %s as either RDF/XML, N3 or NTriples" % (
source))
if not rdflib.plugins.sparql.SPARQL_LOAD_GRAPHS:
# we are not loading - if we already know the graph
# being "loaded", just add it to the default-graph
if default:
self.graph += self.dataset.get_context(source)
else:
if default:
_load(self.graph, source)
else:
_load(self.dataset, source)
def __getitem__(self, key):
# in SPARQL BNodes are just labels
if not type(key) in (BNode, Variable):
return key
try:
return self.bindings[key]
except KeyError:
return None
def get(self, key, default=None):
try:
return self[key]
except KeyError:
return default
def solution(self, vars=None):
"""
Return a static copy of the current variable bindings as dict
"""
if vars:
return FrozenBindings(
self, ((k, v)
for k, v in iteritems(self.bindings)
if k in vars))
else:
return FrozenBindings(self, iteritems(self.bindings))
def __setitem__(self, key, value):
if key in self.bindings and self.bindings[key] != value:
raise AlreadyBound()
self.bindings[key] = value
def pushGraph(self, graph):
r = self.clone()
r.graph = graph
return r
def push(self):
r = self.clone(Bindings(self.bindings))
return r
def clean(self):
return self.clone([])
# def pop(self):
# self.bindings = self.bindings.outer
# if self.bindings is None:
# raise Exception("We've bottomed out of the bindings stack!")
def thaw(self, frozenbindings):
"""
Create a new read/write query context from the given solution
"""
c = self.clone(frozenbindings)
return c
class Prologue(object):
"""
A class for holding prefixing bindings and base URI information
"""
def __init__(self):
self.base = None
self.namespace_manager = NamespaceManager(
Graph()) # ns man needs a store
def resolvePName(self, prefix, localname):
ns = self.namespace_manager.store.namespace(prefix or "")
if ns is None:
raise Exception('Unknown namespace prefix : %s' % prefix)
return URIRef(ns + (localname or ""))
def bind(self, prefix, uri):
self.namespace_manager.bind(prefix, uri, replace=True)
def absolutize(self, iri):
"""
Apply BASE / PREFIXes to URIs
(and to datatypes in Literals)
TODO: Move resolving URIs to pre-processing
"""
if isinstance(iri, CompValue):
if iri.name == 'pname':
return self.resolvePName(iri.prefix, iri.localname)
if iri.name == 'literal':
return Literal(
iri.string, lang=iri.lang,
datatype=self.absolutize(iri.datatype))
elif isinstance(iri, URIRef) and not ':' in iri:
return URIRef(iri, base=self.base)
return iri
class Query(object):
"""
A parsed and translated query
"""
def __init__(self, prologue, algebra):
self.prologue = prologue
self.algebra = algebra
|