summaryrefslogtreecommitdiff
path: root/rdflib/parser.py
blob: 8116877c522ffaf554301f09feae4cc91c063c70 (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
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
"""
Parser plugin interface.

This module defines the parser plugin interface and contains other
related parser support code.

The module is mainly useful for those wanting to write a parser that
can plugin to rdflib. If you are wanting to invoke a parser you likely
want to do so through the Graph class parse method.

"""

import codecs
import os
import pathlib
import sys

from io import BytesIO, TextIOBase, TextIOWrapper, StringIO, BufferedIOBase
from typing import Any, Dict, Optional, Union

from urllib.request import Request
from urllib.request import url2pathname
from urllib.request import urlopen
from urllib.error import HTTPError

from xml.sax import xmlreader

from rdflib import __version__
from rdflib.term import URIRef
from rdflib.namespace import Namespace

__all__ = [
    "Parser",
    "InputSource",
    "StringInputSource",
    "URLInputSource",
    "FileInputSource",
    "PythonInputSource",
]


class Parser(object):
    __slots__ = ()

    def __init__(self):
        pass

    def parse(self, source, sink):
        pass


class BytesIOWrapper(BufferedIOBase):
    __slots__ = ("wrapped", "encoded", "encoding")

    def __init__(self, wrapped: str, encoding="utf-8"):
        super(BytesIOWrapper, self).__init__()
        self.wrapped = wrapped
        self.encoding = encoding
        self.encoded = None

    def read(self, *args, **kwargs):
        if self.encoded is None:
            b, blen = codecs.getencoder(self.encoding)(self.wrapped)
            self.encoded = BytesIO(b)
        return self.encoded.read(*args, **kwargs)

    def read1(self, *args, **kwargs):
        if self.encoded is None:
            b = codecs.getencoder(self.encoding)(self.wrapped)
            self.encoded = BytesIO(b)
        return self.encoded.read1(*args, **kwargs)

    def readinto(self, *args, **kwargs):
        raise NotImplementedError()

    def readinto1(self, *args, **kwargs):
        raise NotImplementedError()

    def write(self, *args, **kwargs):
        raise NotImplementedError()


class InputSource(xmlreader.InputSource, object):
    """
    TODO:
    """

    def __init__(self, system_id=None):
        xmlreader.InputSource.__init__(self, system_id=system_id)
        self.content_type = None
        self.auto_close = False  # see Graph.parse(), true if opened by us

    def close(self):
        c = self.getCharacterStream()
        if c and hasattr(c, "close"):
            try:
                c.close()
            except Exception:
                pass
        f = self.getByteStream()
        if f and hasattr(f, "close"):
            try:
                f.close()
            except Exception:
                pass


class PythonInputSource(InputSource):
    """
    Constructs an RDFLib Parser InputSource from a Python data structure,
    for example, loaded from JSON with json.load or json.loads:

    >>> import json
    >>> as_string = \"\"\"{
    ...   "@context" : {"ex" : "http://example.com/ns#"},
    ...   "@graph": [{"@type": "ex:item", "@id": "#example"}]
    ... }\"\"\"
    >>> as_python = json.loads(as_string)
    >>> source = create_input_source(data=as_python)
    >>> isinstance(source, PythonInputSource)
    True
    """

    def __init__(self, data, system_id=None):
        self.content_type = None
        self.auto_close = False  # see Graph.parse(), true if opened by us
        self.public_id = None
        self.system_id = system_id
        self.data = data

    def getPublicId(self):
        return self.public_id

    def setPublicId(self, public_id):
        self.public_id = public_id

    def getSystemId(self):
        return self.system_id

    def setSystemId(self, system_id):
        self.system_id = system_id

    def close(self):
        self.data = None


class StringInputSource(InputSource):
    """
    Constructs an RDFLib Parser InputSource from a Python String or Bytes
    """

    def __init__(self, value, encoding="utf-8", system_id=None):
        super(StringInputSource, self).__init__(system_id)
        if isinstance(value, str):
            stream = StringIO(value)
            self.setCharacterStream(stream)
            self.setEncoding(encoding)
            b_stream = BytesIOWrapper(value, encoding)
            self.setByteStream(b_stream)
        else:
            stream = BytesIO(value)
            self.setByteStream(stream)
            c_stream = TextIOWrapper(stream, encoding)
            self.setCharacterStream(c_stream)
            self.setEncoding(c_stream.encoding)


headers = {
    "User-agent": "rdflib-%s (http://rdflib.net/; eikeon@eikeon.com)" % __version__
}


class URLInputSource(InputSource):
    """
    TODO:
    """

    def __init__(self, system_id=None, format=None):
        super(URLInputSource, self).__init__(system_id)
        self.url = system_id

        # copy headers to change
        myheaders = dict(headers)
        if format == "xml":
            myheaders["Accept"] = "application/rdf+xml, */*;q=0.1"
        elif format == "n3":
            myheaders["Accept"] = "text/n3, */*;q=0.1"
        elif format in ["turtle", "ttl"]:
            myheaders["Accept"] = "text/turtle, application/x-turtle, */*;q=0.1"
        elif format == "nt":
            myheaders["Accept"] = "text/plain, */*;q=0.1"
        elif format == "trig":
            myheaders["Accept"] = "application/trig, */*;q=0.1"
        elif format == "trix":
            myheaders["Accept"] = "application/trix, */*;q=0.1"
        elif format == "json-ld":
            myheaders[
                "Accept"
            ] = "application/ld+json, application/json;q=0.9, */*;q=0.1"
        else:
            # if format not given, create an Accept header from all registered
            # parser Media Types
            from rdflib.parser import Parser
            from rdflib.plugin import plugins

            acc = []
            for p in plugins():
                if p.kind == Parser:  # only get parsers
                    if "/" in p.name:  # all Media Types known have a / in them
                        acc.append(p.name)

            myheaders["Accept"] = ", ".join(acc)

        req = Request(system_id, None, myheaders)

        def _urlopen(req: Request):
            try:
                return urlopen(req)
            except HTTPError as ex:
                # 308 (Permanent Redirect) is not supported by current python version(s)
                # See https://bugs.python.org/issue40321
                # This custom error handling should be removed once all
                # supported versions of python support 308.
                if ex.code == 308:
                    req.full_url = ex.headers.get("Location")
                    return _urlopen(req)
                else:
                    raise

        file = _urlopen(req)
        # Fix for issue 130 https://github.com/RDFLib/rdflib/issues/130
        self.url = file.geturl()  # in case redirections took place
        self.setPublicId(self.url)
        self.content_type = file.info().get("content-type")
        if self.content_type is not None:
            self.content_type = self.content_type.split(";", 1)[0]
        self.setByteStream(file)
        # TODO: self.setEncoding(encoding)
        self.response_info = file.info()  # a mimetools.Message instance

    def __repr__(self):
        return self.url


class FileInputSource(InputSource):
    def __init__(self, file):
        base = pathlib.Path.cwd().as_uri()
        system_id = URIRef(pathlib.Path(file.name).absolute().as_uri(), base=base)
        super(FileInputSource, self).__init__(system_id)
        self.file = file
        if isinstance(file, TextIOBase):  # Python3 unicode fp
            self.setCharacterStream(file)
            self.setEncoding(file.encoding)
            try:
                b = file.buffer
                self.setByteStream(b)
            except (AttributeError, LookupError):
                self.setByteStream(file)
        else:
            self.setByteStream(file)
            # We cannot set characterStream here because
            # we do not know the Raw Bytes File encoding.

    def __repr__(self):
        return repr(self.file)


def create_input_source(
    source=None,
    publicID=None,
    location=None,
    file=None,
    data: Optional[Union[str, bytes, bytearray, Dict[Any, Any]]] = None,
    format=None,
):
    """
    Return an appropriate InputSource instance for the given
    parameters.
    """

    # test that exactly one of source, location, file, and data is not None.
    non_empty_arguments = list(
        filter(
            lambda v: v is not None,
            [source, location, file, data],
        )
    )

    if len(non_empty_arguments) != 1:
        raise ValueError(
            "exactly one of source, location, file or data must be given",
        )

    input_source = None

    if source is not None:
        if isinstance(source, InputSource):
            input_source = source
        else:
            if isinstance(source, str):
                location = source
            elif isinstance(source, pathlib.PurePath):
                location = str(source)
            elif isinstance(source, bytes):
                data = source
            elif hasattr(source, "read") and not isinstance(source, Namespace):
                f = source
                input_source = InputSource()
                if hasattr(source, "encoding"):
                    input_source.setCharacterStream(source)
                    input_source.setEncoding(source.encoding)
                    try:
                        b = file.buffer
                        input_source.setByteStream(b)
                    except (AttributeError, LookupError):
                        input_source.setByteStream(source)
                else:
                    input_source.setByteStream(f)
                if f is sys.stdin:
                    input_source.setSystemId("file:///dev/stdin")
                elif hasattr(f, "name"):
                    input_source.setSystemId(f.name)
            else:
                raise Exception(
                    "Unexpected type '%s' for source '%s'" % (type(source), source)
                )

    absolute_location = None  # Further to fix for issue 130

    auto_close = False  # make sure we close all file handles we open

    if location is not None:
        (
            absolute_location,
            auto_close,
            file,
            input_source,
        ) = _create_input_source_from_location(
            file=file,
            format=format,
            input_source=input_source,
            location=location,
        )

    if file is not None:
        input_source = FileInputSource(file)

    if data is not None:
        if isinstance(data, dict):
            input_source = PythonInputSource(data)
            auto_close = True
        elif isinstance(data, (str, bytes, bytearray)):
            input_source = StringInputSource(data)
            auto_close = True
        else:
            raise RuntimeError(f"parse data can only str, or bytes. not: {type(data)}")

    if input_source is None:
        raise Exception("could not create InputSource")
    else:
        input_source.auto_close |= auto_close
        if publicID is not None:  # Further to fix for issue 130
            input_source.setPublicId(publicID)
        # Further to fix for issue 130
        elif input_source.getPublicId() is None:
            input_source.setPublicId(absolute_location or "")
        return input_source


def _create_input_source_from_location(file, format, input_source, location):
    # Fix for Windows problem https://github.com/RDFLib/rdflib/issues/145 and
    # https://github.com/RDFLib/rdflib/issues/1430
    # NOTE: using pathlib.Path.exists on a URL fails on windows as it is not a
    # valid path. However os.path.exists() returns false for a URL on windows
    # which is why it is being used instead.
    if os.path.exists(location):
        location = pathlib.Path(location).absolute().as_uri()

    base = pathlib.Path.cwd().as_uri()

    absolute_location = URIRef(location, base=base)

    if absolute_location.startswith("file:///"):
        filename = url2pathname(absolute_location.replace("file:///", "/"))
        file = open(filename, "rb")
    else:
        input_source = URLInputSource(absolute_location, format)

    auto_close = True
    # publicID = publicID or absolute_location  # Further to fix
    # for issue 130

    return absolute_location, auto_close, file, input_source