File: context.py

package info (click to toggle)
python-rdflib-jsonld 0.6.1-2
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,832 kB
  • sloc: python: 1,800; makefile: 132
file content (381 lines) | stat: -rw-r--r-- 11,567 bytes parent folder | download
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
# -*- coding: utf-8 -*-
"""
Implementation of the JSON-LD Context structure. See:

    http://json-ld.org/

"""
from collections import namedtuple
from rdflib.namespace import RDF

from ._compat import basestring, unicode
from .keys import (
    BASE,
    CONTAINER,
    CONTEXT,
    GRAPH,
    ID,
    INDEX,
    LANG,
    LIST,
    REV,
    SET,
    TYPE,
    VALUE,
    VOCAB,
)
from . import errors
from .util import source_to_json, urljoin, urlsplit, split_iri, norm_url


NODE_KEYS = set([LANG, ID, TYPE, VALUE, LIST, SET, REV, GRAPH])


class Defined(int):
    pass


UNDEF = Defined(0)


class Context(object):
    def __init__(self, source=None, base=None):
        self.language = None
        self.vocab = None
        self.base = base
        self.doc_base = base
        self.terms = {}
        # _alias maps NODE_KEY to list of aliases
        self._alias = {}
        self._lookup = {}
        self._prefixes = {}
        self.active = False
        if source:
            self.load(source)

    @property
    def base(self):
        return self._base

    @base.setter
    def base(self, base):
        if base:
            hash_index = base.find("#")
            if hash_index > -1:
                base = base[0:hash_index]
        self._base = (
            self.resolve_iri(base)
            if (hasattr(self, "_base") and base is not None)
            else base
        )
        self._basedomain = "%s://%s" % urlsplit(base)[0:2] if base else None

    def subcontext(self, source):
        # IMPROVE: to optimize, implement SubContext with parent fallback support
        ctx = Context()
        ctx.language = self.language
        ctx.vocab = self.vocab
        ctx.base = self.base
        ctx.doc_base = self.doc_base
        ctx._alias = self._alias.copy()
        ctx.terms = self.terms.copy()
        ctx._lookup = self._lookup.copy()
        ctx._prefixes = self._prefixes.copy()
        ctx.load(source)
        return ctx

    def get_id(self, obj):
        return self._get(obj, ID)

    def get_type(self, obj):
        return self._get(obj, TYPE)

    def get_language(self, obj):
        return self._get(obj, LANG)

    def get_value(self, obj):
        return self._get(obj, VALUE)

    def get_graph(self, obj):
        return self._get(obj, GRAPH)

    def get_list(self, obj):
        return self._get(obj, LIST)

    def get_set(self, obj):
        return self._get(obj, SET)

    def get_rev(self, obj):
        return self._get(obj, REV)

    def _get(self, obj, key):
        for alias in self._alias.get(key, []):
            if alias in obj:
                return obj.get(alias)
        return obj.get(key)

    def get_key(self, key):
        return self.get_keys(key)[0]

    def get_keys(self, key):
        return self._alias.get(key, [key])

    lang_key = property(lambda self: self.get_key(LANG))
    id_key = property(lambda self: self.get_key(ID))
    type_key = property(lambda self: self.get_key(TYPE))
    value_key = property(lambda self: self.get_key(VALUE))
    list_key = property(lambda self: self.get_key(LIST))
    rev_key = property(lambda self: self.get_key(REV))
    graph_key = property(lambda self: self.get_key(GRAPH))

    def add_term(
        self,
        name,
        idref,
        coercion=UNDEF,
        container=UNDEF,
        language=UNDEF,
        reverse=False,
    ):
        term = Term(idref, name, coercion, container, language, reverse)
        self.terms[name] = term
        self._lookup[(idref, coercion or language, container, reverse)] = term
        self._prefixes[idref] = name

    def find_term(
        self, idref, coercion=None, container=UNDEF, language=None, reverse=False
    ):
        lu = self._lookup
        if coercion is None:
            coercion = language
        if coercion is not UNDEF and container:
            found = lu.get((idref, coercion, container, reverse))
            if found:
                return found
        if coercion is not UNDEF:
            found = lu.get((idref, coercion, UNDEF, reverse))
            if found:
                return found
        if container:
            found = lu.get((idref, coercion, container, reverse))
            if found:
                return found
        elif language:
            found = lu.get((idref, UNDEF, LANG, reverse))
            if found:
                return found
        else:
            found = lu.get((idref, coercion or UNDEF, SET, reverse))
            if found:
                return found
        return lu.get((idref, UNDEF, UNDEF, reverse))

    def resolve(self, curie_or_iri):
        iri = self.expand(curie_or_iri, False)
        if self.isblank(iri):
            return iri
        return self.resolve_iri(iri)

    def resolve_iri(self, iri):
        return norm_url(self._base, iri)

    def isblank(self, ref):
        return ref.startswith("_:")

    def expand(self, term_curie_or_iri, use_vocab=True):
        if use_vocab:
            term = self.terms.get(term_curie_or_iri)
            if term:
                return term.id
        is_term, pfx, local = self._prep_expand(term_curie_or_iri)
        if pfx == "_":
            return term_curie_or_iri
        if pfx is not None:
            ns = self.terms.get(pfx)
            if ns and ns.id:
                return ns.id + local
        elif is_term and use_vocab:
            if self.vocab:
                return self.vocab + term_curie_or_iri
            return None
        return self.resolve_iri(term_curie_or_iri)

    def shrink_iri(self, iri):
        ns, name = split_iri(unicode(iri))
        pfx = self._prefixes.get(ns)
        if pfx:
            return ":".join((pfx, name))
        elif self._base:
            if unicode(iri) == self._base:
                return ""
            elif iri.startswith(self._basedomain):
                return iri[len(self._basedomain) :]
        return iri

    def to_symbol(self, iri):
        iri = unicode(iri)
        term = self.find_term(iri)
        if term:
            return term.name
        ns, name = split_iri(iri)
        if ns == self.vocab:
            return name
        pfx = self._prefixes.get(ns)
        if pfx:
            return ":".join((pfx, name))
        return iri

    def load(self, source, base=None):
        self.active = True
        sources = []
        source = source if isinstance(source, list) else [source]
        self._prep_sources(base, source, sources)
        for source_url, source in sources:
            self._read_source(source, source_url)

    def _prep_sources(
        self, base, inputs, sources, referenced_contexts=None, in_source_url=None
    ):
        referenced_contexts = referenced_contexts or set()
        for source in inputs:
            if isinstance(source, basestring):
                source_url = urljoin(base, source)
                if source_url in referenced_contexts:
                    raise errors.RECURSIVE_CONTEXT_INCLUSION
                referenced_contexts.add(source_url)
                source = source_to_json(source_url)
                if CONTEXT not in source:
                    raise errors.INVALID_REMOTE_CONTEXT
            else:
                source_url = in_source_url

            if isinstance(source, dict):
                if CONTEXT in source:
                    source = source[CONTEXT]
                    source = source if isinstance(source, list) else [source]
            if isinstance(source, list):
                self._prep_sources(
                    base, source, sources, referenced_contexts, source_url
                )
            else:
                sources.append((source_url, source))

    def _read_source(self, source, source_url=None):
        self.vocab = source.get(VOCAB, self.vocab)
        for key, value in source.items():
            if key == LANG:
                self.language = value
            elif key == VOCAB:
                continue
            elif key == BASE:
                if source_url:
                    continue
                self.base = value
            else:
                self._read_term(source, key, value)

    def _read_term(self, source, name, dfn):
        idref = None
        if isinstance(dfn, dict):
            # term = self._create_term(source, key, value)
            rev = dfn.get(REV)
            idref = rev or dfn.get(ID, UNDEF)
            if idref == TYPE:
                idref = unicode(RDF.type)
            elif idref is not UNDEF:
                idref = self._rec_expand(source, idref)
            elif ":" in name:
                idref = self._rec_expand(source, name)
            elif self.vocab:
                idref = self.vocab + name
            coercion = dfn.get(TYPE, UNDEF)
            if coercion and coercion not in (ID, TYPE, VOCAB):
                coercion = self._rec_expand(source, coercion)
            self.add_term(
                name,
                idref,
                coercion,
                dfn.get(CONTAINER, UNDEF),
                dfn.get(LANG, UNDEF),
                bool(rev),
            )
        else:
            if isinstance(dfn, unicode):
                idref = self._rec_expand(source, dfn)
            self.add_term(name, idref)

        if idref in NODE_KEYS:
            self._alias.setdefault(idref, []).append(name)

    def _rec_expand(self, source, expr, prev=None):
        if expr == prev or expr in NODE_KEYS:
            return expr

        is_term, pfx, nxt = self._prep_expand(expr)
        if pfx:
            iri = self._get_source_id(source, pfx)
            if iri is None:
                if pfx + ":" == self.vocab:
                    return expr
                else:
                    term = self.terms.get(pfx)
                    if term:
                        iri = term.id

            if iri is None:
                nxt = expr
            else:
                nxt = iri + nxt
        else:
            nxt = self._get_source_id(source, nxt) or nxt
            if ":" not in nxt and self.vocab:
                return self.vocab + nxt

        return self._rec_expand(source, nxt, expr)

    def _prep_expand(self, expr):
        if ":" not in expr:
            return True, None, expr
        pfx, local = expr.split(":", 1)
        if not local.startswith("//"):
            return False, pfx, local
        else:
            return False, None, expr

    def _get_source_id(self, source, key):
        # .. from source dict or if already defined
        term = source.get(key)
        if term is None:
            dfn = self.terms.get(key)
            if dfn:
                term = dfn.id
        elif isinstance(term, dict):
            term = term.get(ID)
        return term

    def _term_dict(self, term):
        tdict = {ID: self.shrink_iri(term.id)}
        if term.type != UNDEF:
            tdict[TYPE] = self.shrink_iri(term.type)
        if term.container != UNDEF:
            tdict[CONTAINER] = term.container
        if term.language != UNDEF:
            tdict[LANG] = term.language
        if term.reverse:
            tdict[REV] = term.reverse
        if len(tdict) == 1:
            return tdict[ID]
        return tdict

    def to_dict(self):
        r = {v: k for (k, v) in self._prefixes.items()}
        r.update({t.name: self._term_dict(t) for t in self._lookup.values()})
        if self.base:
            r[BASE] = self.base
        if self.language:
            r[LANG] = self.language
        return r


Term = namedtuple("Term", "id, name, type, container, language, reverse")
Term.__new__.__defaults__ = (UNDEF, UNDEF, UNDEF, False)