forked from schemaorg/schemaorg
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathapirdflib.py
executable file
·379 lines (331 loc) · 11.2 KB
/
apirdflib.py
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
#!/usr/bin/env python
# -*- coding: UTF-8 -*-
import sys
sys.path.append('lib')
import rdflib
from rdflib import Literal
from rdflib.term import URIRef
from rdflib.parser import Parser
from rdflib.serializer import Serializer
from rdflib.plugins.sparql import prepareQuery
import threading
import api
from apimarkdown import Markdown
import StringIO
rdflib.plugin.register("json-ld", Parser, "rdflib_jsonld.parser", "JsonLDParser")
rdflib.plugin.register("json-ld", Serializer, "rdflib_jsonld.serializer", "JsonLDSerializer")
import logging
logging.basicConfig(level=logging.INFO) # dev_appserver.py --log_level debug .
log = logging.getLogger(__name__)
VOCAB = "http://schema.org"
STORE = rdflib.Dataset()
#Namespace mapping#############
nss = {'core': 'http://schema.org/'}
revNss = {}
NSSLoaded = False
allLayersList = []
context_data = "data/internal-context" #Local file containing context to be used loding .jsonld files
RDFLIBLOCK = threading.Lock() #rdflib uses generators which are not threadsafe
from rdflib.namespace import RDFS, RDF, OWL
SCHEMA = rdflib.Namespace('http://schema.org/')
QUERYGRAPH = None
def queryGraph():
global QUERYGRAPH
if not QUERYGRAPH:
try:
RDFLIBLOCK.acquire()
if not QUERYGRAPH:
QUERYGRAPH = rdflib.Graph()
gs = list(STORE.graphs())
for g in gs:
id = str(g.identifier)
if not id.startswith("http://"):#skip some internal graphs
continue
QUERYGRAPH += g
QUERYGRAPH.bind('owl', 'http://www.w3.org/2002/07/owl#')
QUERYGRAPH.bind('rdfa', 'http://www.w3.org/ns/rdfa#')
QUERYGRAPH.bind('dct', 'http://purl.org/dc/terms/')
QUERYGRAPH.bind('schema', 'http://schema.org/')
finally:
RDFLIBLOCK.release()
return QUERYGRAPH
def loadNss():
global NSSLoaded
global nss
global revNss
if not NSSLoaded:
NSSLoaded = True
#log.info("allLayersList: %s"% allLayersList)
for i in allLayersList:
if i != "core":
#log.info("Setting %s to %s" % (i, "http://%s.schema.org/" % i))
nss.update({i:"http://%s.schema.org/" % i})
revNss = {v: k for k, v in nss.items()}
def getNss(val):
global nss
loadNss()
try:
return nss[val]
except KeyError:
return ""
def getRevNss(val):
global revNss
loadNss()
try:
return revNss[val]
except KeyError:
return ""
##############################
GETTRIPS = prepareQuery("SELECT ?g ?p ?o WHERE {GRAPH ?g {?sub ?p ?o }}")
GGETALL = prepareQuery("SELECT ?g ?s ?p ?o WHERE {GRAPH ?g {?s ?p ?o }}")
GETALL = prepareQuery("SELECT ?s ?p ?o WHERE {?s ?p ?o }")
GETP = prepareQuery("SELECT DISTINCT ?p WHERE {GRAPH ?g { ?s ?p ?o }} ORDER BY ?p")
def load_graph(context, files):
"""Read/parse/ingest schemas from data/*.rdfa."""
import os.path
import glob
import re
log.debug("Loading %s graph." % context)
for f in files:
if(f[-5:] == ".rdfa"):
format = "rdfa"
elif(f[-7:] == ".jsonld"):
format = "json-ld"
else:
log.info("Unrecognised file format: %s" % f)
return
if(format == "rdfa"):
uri = getNss(context)
g = STORE.graph(URIRef(uri))
g.parse(file=open(full_path(f),"r"),format=format)
STORE.bind(context,uri)
elif(format == "json-ld"):
STORE.parse(file=open(full_path(f),"r"),format=format, context=context_data)
QUERYGRAPH = None #In case we have loaded graphs since the last time QUERYGRAPH was set
def rdfGetTriples(id):
"""All triples with node as subject."""
targets = []
fullId = id
# log.info("rdfgetTriples(%s)" % fullId)
if ':' in id: #Includes full path or namespaces
fullId = id
else:
fullId = VOCAB + "/" + id
source = URIRef(fullId)
#log.info("rdfgetTriples(%s)" % source)
first = True
unit = None
homeSetTo = None
typeOfInLayers = []
try:
RDFLIBLOCK.acquire()
res = list(STORE.query(GETTRIPS, initBindings={'sub':source}))
finally:
RDFLIBLOCK.release()
for row in res:
# if source == "http://meta.schema.org/":
# log.info("Triple: %s %s %s %s" % (source, row.p, row.o, row.g))
layer = str(getRevNss(str(row.g)))
if first:
first = False
unit = api.Unit.GetUnitNoLoad(id,True)
s = stripID(source)
p = stripID(row.p)
if p == "rdf:type":
typeOfInLayers.append(layer)
elif(p == "isPartOf"):
if(unit.home != None and unit.home != layer):
log.info("WARNING Cannot set %s home to %s - already set to: %s" % (s,layer,unit.home))
unit.home = layer
homeSetTo = layer
elif(p == "category"):
unit.category = row.o
prop = api.Unit.GetUnit(p,True)
if isinstance(row.o,rdflib.Literal):
api.Triple.AddTripleText(unit, prop, row.o, layer)
else:
api.Triple.AddTriple(unit, prop, api.Unit.GetUnit(stripID(row.o),True), layer)
""" Default Unit.home to core if not specificly set with an 'isPartOf' triple """
if(unit and homeSetTo == None):
if('core' in typeOfInLayers or len(typeOfInLayers) == 0):
unit.home = 'core'
else:
log.info("WARNING: %s defined in extensions %s but has no 'isPartOf' triple - cannot default home to core!" % (id,typeOfInLayers))
return unit
def rdfGetSourceTriples(target):
"""All source nodes for a specified arc pointing to a specified node (within any of the specified layers)."""
id = target.id
target.sourced = True
sources = []
fullId = id
if ':' in id: #Includes full path or namespaces
fullId = id
else:
fullId = VOCAB + "/" + id
targ = fullId
if fullId.startswith('http://'):
targ = "<%s>" % fullId
q = "SELECT ?g ?s ?p WHERE {GRAPH ?g {?s ?p %s }}" % targ
try:
RDFLIBLOCK.acquire()
res = list(STORE.query(q))
#log.info("RESCOUNT %s" % len(res))
finally:
RDFLIBLOCK.release()
for row in res:
layer = str(getRevNss(str(row.g)))
unit = api.Unit.GetUnit(stripID(row.s))
p = stripID(row.p)
prop = api.Unit.GetUnit(p,True)
obj = api.Unit.GetUnit(stripID(fullId),True)
api.Triple.AddTriple(unit, prop, obj, layer)
def serializeSingleTermGrapth(node,format="json-ld",excludeAttic=True,markdown=True):
graph = buildSingleTermGraph(node=node,excludeAttic=excludeAttic,markdown=markdown)
file = StringIO.StringIO()
kwargs = {'sort_keys': True}
file.write(graph.serialize(format=format,**kwargs))
data = file.getvalue()
file.close()
return data
def buildSingleTermGraph(node,excludeAttic=True,markdown=True):
g = rdflib.Graph()
g.bind('owl', 'http://www.w3.org/2002/07/owl#')
g.bind('rdfa', 'http://www.w3.org/ns/rdfa#')
g.bind('dct', 'http://purl.org/dc/terms/')
g.bind('schema', 'http://schema.org/')
full = "http://schema.org/" + node
#n = URIRef(full)
n = SCHEMA.term(node)
n = n
full = str(n)
q = queryGraph()
ret = None
#log.info("NAME %s %s"% (n,full))
atts = None
try:
RDFLIBLOCK.acquire()
atts = list(q.triples((n,SCHEMA.isPartOf,URIRef("http://attic.schema.org"))))
finally:
RDFLIBLOCK.release()
if len(atts):
#log.info("ATTIC TERM %s" % n)
excludeAttic = False
#Outgoing triples
try:
RDFLIBLOCK.acquire()
ret = list(q.triples((n,None,None)))
finally:
RDFLIBLOCK.release()
for (s,p,o) in ret:
log.info("adding %s %s %s" % (s,p,o))
g.add((s,p,o))
#Incoming triples
ret = list(q.triples((None,None,n)))
for (s,p,o) in ret:
log.info("adding %s %s %s" % (s,p,o))
g.add((s,p,o))
#super classes
query='''select * where {
?term (^rdfs:subClassOf*) <%s>.
?term rdfs:subClassOf ?super.
?super ?pred ?obj.
}''' % n
try:
RDFLIBLOCK.acquire()
ret = q.query(query)
finally:
RDFLIBLOCK.release()
for row in ret:
log.info("adding %s %s %s" % (row.term,RDFS.subClassOf,row.super))
g.add((row.term,RDFS.subClassOf,row.super))
g.add((row.super,row.pred,row.obj))
#poperties with superclasses in domain
query='''select * where{
?term (^rdfs:subClassOf*) <%s>.
?prop <http://schema.org/domainIncludes> ?term.
?prop ?pred ?obj.
}
''' % n
try:
RDFLIBLOCK.acquire()
ret = q.query(query)
finally:
RDFLIBLOCK.release()
for row in ret:
g.add((row.prop,SCHEMA.domainIncludes,row.term))
g.add((row.prop,row.pred,row.obj))
#super properties
query='''select * where {
?term (^rdfs:subPropertyOf*) <%s>.
?term rdfs:subPropertyOf ?super.
?super ?pred ?obj.
}''' % n
try:
RDFLIBLOCK.acquire()
ret = q.query(query)
finally:
RDFLIBLOCK.release()
for row in ret:
log.info("adding %s %s %s" % (row.term,RDFS.subPropertyOf,row.super))
g.add((row.term,RDFS.subPropertyOf,row.super))
g.add((row.super,row.pred,row.obj))
#Enumeration for an enumeration value
query='''select * where {
<%s> a ?type.
?type ?pred ?obj.
FILTER NOT EXISTS{?type a rdfs:class}.
}''' % n
try:
RDFLIBLOCK.acquire()
ret = q.query(query)
finally:
RDFLIBLOCK.release()
for row in ret:
log.info("adding %s %s %s" % (row.type,row.pred,row.obj))
g.add((row.type,row.pred,row.obj))
if excludeAttic: #Remove triples referencing terms part of http://attic.schema.org
trips = list(g.triples((None,None,None)))
try:
RDFLIBLOCK.acquire()
for (s,p,o) in trips:
atts = list(q.triples((s,SCHEMA.isPartOf,URIRef("http://attic.schema.org"))))
if isinstance(o, URIRef):
atts.extend(q.triples((o,SCHEMA.isPartOf,URIRef("http://attic.schema.org"))))
for (rs,rp,ro) in atts:
log.info("Removing %s" % rs)
g.remove((rs,None,None))
g.remove((None,None,rs))
finally:
RDFLIBLOCK.release()
if markdown:
try:
RDFLIBLOCK.acquire()
trips = list(g.triples((None,RDFS.comment,None)))
Markdown.setPre("http://schema.org/")
for (s,p,com) in trips:
mcom = Markdown.parse(com)
g.remove((s,p,com))
g.add((s,p,Literal(mcom)))
finally:
RDFLIBLOCK.release()
Markdown.setPre()
return g
def stripID (str):
l = len(str)
if (l > 17 and (str[:18] == 'http://schema.org/')):
return str[18:]
elif (l > 24 and (str[:25] == 'http://purl.org/dc/terms/')):
return "dc:" + str[25:]
elif (l > 36 and (str[:37] == 'http://www.w3.org/2000/01/rdf-schema#')):
return "rdfs:" + str[37:]
elif (l > 42 and (str[:43] == 'http://www.w3.org/1999/02/22-rdf-syntax-ns#')):
return "rdf:" + str[43:]
elif (l > 29 and (str[:30] == 'http://www.w3.org/2002/07/owl#')):
return "owl:" + str[30:]
else:
return str
def full_path(filename):
"""convert local file name to full path."""
import os.path
folder = os.path.dirname(os.path.realpath(__file__))
return os.path.join(folder, filename)