Arthur de Jong

Open Source / Free Software developer

summaryrefslogtreecommitdiffstats
path: root/django/core/urlresolvers.py
blob: d37a40157dfb6073cd79428909982f94bd672b21 (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
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
"""
This module converts requested URLs to callback view functions.

RegexURLResolver is the main class here. Its resolve() method takes a URL (as
a string) and returns a ResolverMatch object which provides access to all
attributes of the resolved URL match.
"""
from __future__ import unicode_literals

import functools
import re
from importlib import import_module
from threading import local

from django.core.exceptions import ImproperlyConfigured, ViewDoesNotExist
from django.http import Http404
from django.utils import lru_cache, six
from django.utils.datastructures import MultiValueDict
from django.utils.encoding import force_str, force_text, iri_to_uri
from django.utils.functional import cached_property, lazy
from django.utils.http import RFC3986_SUBDELIMS, urlquote
from django.utils.module_loading import module_has_submodule
from django.utils.regex_helper import normalize
from django.utils.six.moves.urllib.parse import urlsplit, urlunsplit
from django.utils.translation import get_language, override

# SCRIPT_NAME prefixes for each thread are stored here. If there's no entry for
# the current thread (which is the only one we ever access), it is assumed to
# be empty.
_prefixes = local()

# Overridden URLconfs for each thread are stored here.
_urlconfs = local()


class ResolverMatch(object):
    def __init__(self, func, args, kwargs, url_name=None, app_names=None, namespaces=None):
        self.func = func
        self.args = args
        self.kwargs = kwargs
        self.url_name = url_name

        # If a URLRegexResolver doesn't have a namespace or app_name, it passes
        # in an empty value.
        self.app_names = [x for x in app_names if x] if app_names else []
        self.app_name = ':'.join(self.app_names)

        if namespaces:
            self.namespaces = [x for x in namespaces if x]
        else:
            self.namespaces = []
        self.namespace = ':'.join(self.namespaces)

        if not hasattr(func, '__name__'):
            # A class-based view
            self._func_path = '.'.join([func.__class__.__module__, func.__class__.__name__])
        else:
            # A function-based view
            self._func_path = '.'.join([func.__module__, func.__name__])

        view_path = url_name or self._func_path
        self.view_name = ':'.join(self.namespaces + [view_path])

    def __getitem__(self, index):
        return (self.func, self.args, self.kwargs)[index]

    def __repr__(self):
        return "ResolverMatch(func=%s, args=%s, kwargs=%s, url_name=%s, app_names=%s, namespaces=%s)" % (
            self._func_path, self.args, self.kwargs, self.url_name, self.app_names, self.namespaces)


class Resolver404(Http404):
    pass


class NoReverseMatch(Exception):
    pass


@lru_cache.lru_cache(maxsize=None)
def get_callable(lookup_view):
    """
    Return a callable corresponding to lookup_view.

    * If lookup_view is already a callable, return it.
    * If lookup_view is a string import path that can be resolved to a callable,
      import that callable and return it, otherwise raise an exception
      (ImportError or ViewDoesNotExist).
    """
    if callable(lookup_view):
        return lookup_view

    if not isinstance(lookup_view, six.string_types):
        raise ViewDoesNotExist("'%s' is not a callable or a dot-notation path" % lookup_view)

    mod_name, func_name = get_mod_func(lookup_view)
    if not func_name:  # No '.' in lookup_view
        raise ImportError("Could not import '%s'. The path must be fully qualified." % lookup_view)

    try:
        mod = import_module(mod_name)
    except ImportError:
        parentmod, submod = get_mod_func(mod_name)
        if submod and not module_has_submodule(import_module(parentmod), submod):
            raise ViewDoesNotExist(
                "Could not import '%s'. Parent module %s does not exist." %
                (lookup_view, mod_name)
            )
        else:
            raise
    else:
        try:
            view_func = getattr(mod, func_name)
        except AttributeError:
            raise ViewDoesNotExist(
                "Could not import '%s'. View does not exist in module %s." %
                (lookup_view, mod_name)
            )
        else:
            if not callable(view_func):
                raise ViewDoesNotExist(
                    "Could not import '%s.%s'. View is not callable." %
                    (mod_name, func_name)
                )
            return view_func


@lru_cache.lru_cache(maxsize=None)
def get_resolver(urlconf=None):
    if urlconf is None:
        from django.conf import settings
        urlconf = settings.ROOT_URLCONF
    return RegexURLResolver(r'^/', urlconf)


@lru_cache.lru_cache(maxsize=None)
def get_ns_resolver(ns_pattern, resolver):
    # Build a namespaced resolver for the given parent URLconf pattern.
    # This makes it possible to have captured parameters in the parent
    # URLconf pattern.
    ns_resolver = RegexURLResolver(ns_pattern, resolver.url_patterns)
    return RegexURLResolver(r'^/', [ns_resolver])


def get_mod_func(callback):
    # Converts 'django.views.news.stories.story_detail' to
    # ['django.views.news.stories', 'story_detail']
    try:
        dot = callback.rindex('.')
    except ValueError:
        return callback, ''
    return callback[:dot], callback[dot + 1:]


class LocaleRegexProvider(object):
    """
    A mixin to provide a default regex property which can vary by active
    language.
    """
    def __init__(self, regex):
        # regex is either a string representing a regular expression, or a
        # translatable string (using ugettext_lazy) representing a regular
        # expression.
        self._regex = regex
        self._regex_dict = {}

    @property
    def regex(self):
        """
        Returns a compiled regular expression, depending upon the activated
        language-code.
        """
        language_code = get_language()
        if language_code not in self._regex_dict:
            if isinstance(self._regex, six.string_types):
                regex = self._regex
            else:
                regex = force_text(self._regex)
            try:
                compiled_regex = re.compile(regex, re.UNICODE)
            except re.error as e:
                raise ImproperlyConfigured(
                    '"%s" is not a valid regular expression: %s' %
                    (regex, six.text_type(e)))

            self._regex_dict[language_code] = compiled_regex
        return self._regex_dict[language_code]


class RegexURLPattern(LocaleRegexProvider):
    def __init__(self, regex, callback, default_args=None, name=None):
        LocaleRegexProvider.__init__(self, regex)
        self.callback = callback  # the view
        self.default_args = default_args or {}
        self.name = name

    def __repr__(self):
        return force_str('<%s %s %s>' % (self.__class__.__name__, self.name, self.regex.pattern))

    def resolve(self, path):
        match = self.regex.search(path)
        if match:
            # If there are any named groups, use those as kwargs, ignoring
            # non-named groups. Otherwise, pass all non-named arguments as
            # positional arguments.
            kwargs = match.groupdict()
            if kwargs:
                args = ()
            else:
                args = match.groups()
            # In both cases, pass any extra_kwargs as **kwargs.
            kwargs.update(self.default_args)

            return ResolverMatch(self.callback, args, kwargs, self.name)

    @cached_property
    def lookup_str(self):
        """
        A string that identifies the view (e.g. 'path.to.view_function' or
        'path.to.ClassBasedView').
        """
        callback = self.callback
        if isinstance(callback, functools.partial):
            callback = callback.func
        if not hasattr(callback, '__name__'):
            return callback.__module__ + "." + callback.__class__.__name__
        else:
            return callback.__module__ + "." + callback.__name__


class RegexURLResolver(LocaleRegexProvider):
    def __init__(self, regex, urlconf_name, default_kwargs=None, app_name=None, namespace=None):
        LocaleRegexProvider.__init__(self, regex)
        # urlconf_name is the dotted Python path to the module defining
        # urlpatterns. It may also be an object with an urlpatterns attribute
        # or urlpatterns itself.
        self.urlconf_name = urlconf_name
        self.callback = None
        self.default_kwargs = default_kwargs or {}
        self.namespace = namespace
        self.app_name = app_name
        self._reverse_dict = {}
        self._namespace_dict = {}
        self._app_dict = {}
        # set of dotted paths to all functions and classes that are used in
        # urlpatterns
        self._callback_strs = set()
        self._populated = False

    def __repr__(self):
        if isinstance(self.urlconf_name, list) and len(self.urlconf_name):
            # Don't bother to output the whole list, it can be huge
            urlconf_repr = '<%s list>' % self.urlconf_name[0].__class__.__name__
        else:
            urlconf_repr = repr(self.urlconf_name)
        return str('<%s %s (%s:%s) %s>') % (
            self.__class__.__name__, urlconf_repr, self.app_name,
            self.namespace, self.regex.pattern)

    def _populate(self):
        lookups = MultiValueDict()
        namespaces = {}
        apps = {}
        language_code = get_language()
        for pattern in reversed(self.url_patterns):
            if isinstance(pattern, RegexURLPattern):
                self._callback_strs.add(pattern.lookup_str)
            p_pattern = pattern.regex.pattern
            if p_pattern.startswith('^'):
                p_pattern = p_pattern[1:]
            if isinstance(pattern, RegexURLResolver):
                if pattern.namespace:
                    namespaces[pattern.namespace] = (p_pattern, pattern)
                    if pattern.app_name:
                        apps.setdefault(pattern.app_name, []).append(pattern.namespace)
                else:
                    parent_pat = pattern.regex.pattern
                    for name in pattern.reverse_dict:
                        for matches, pat, defaults in pattern.reverse_dict.getlist(name):
                            new_matches = normalize(parent_pat + pat)
                            lookups.appendlist(
                                name,
                                (
                                    new_matches,
                                    p_pattern + pat,
                                    dict(defaults, **pattern.default_kwargs),
                                )
                            )
                    for namespace, (prefix, sub_pattern) in pattern.namespace_dict.items():
                        namespaces[namespace] = (p_pattern + prefix, sub_pattern)
                    for app_name, namespace_list in pattern.app_dict.items():
                        apps.setdefault(app_name, []).extend(namespace_list)
                    self._callback_strs.update(pattern._callback_strs)
            else:
                bits = normalize(p_pattern)
                lookups.appendlist(pattern.callback, (bits, p_pattern, pattern.default_args))
                if pattern.name is not None:
                    lookups.appendlist(pattern.name, (bits, p_pattern, pattern.default_args))
        self._reverse_dict[language_code] = lookups
        self._namespace_dict[language_code] = namespaces
        self._app_dict[language_code] = apps
        self._populated = True

    @property
    def reverse_dict(self):
        language_code = get_language()
        if language_code not in self._reverse_dict:
            self._populate()
        return self._reverse_dict[language_code]

    @property
    def namespace_dict(self):
        language_code = get_language()
        if language_code not in self._namespace_dict:
            self._populate()
        return self._namespace_dict[language_code]

    @property
    def app_dict(self):
        language_code = get_language()
        if language_code not in self._app_dict:
            self._populate()
        return self._app_dict[language_code]

    def _is_callback(self, name):
        if not self._populated:
            self._populate()
        return name in self._callback_strs

    def resolve(self, path):
        path = force_text(path)  # path may be a reverse_lazy object
        tried = []
        match = self.regex.search(path)
        if match:
            new_path = path[match.end():]
            for pattern in self.url_patterns:
                try:
                    sub_match = pattern.resolve(new_path)
                except Resolver404 as e:
                    sub_tried = e.args[0].get('tried')
                    if sub_tried is not None:
                        tried.extend([pattern] + t for t in sub_tried)
                    else:
                        tried.append([pattern])
                else:
                    if sub_match:
                        # Merge captured arguments in match with submatch
                        sub_match_dict = dict(match.groupdict(), **self.default_kwargs)
                        sub_match_dict.update(sub_match.kwargs)

                        # If there are *any* named groups, ignore all non-named groups.
                        # Otherwise, pass all non-named arguments as positional arguments.
                        sub_match_args = sub_match.args
                        if not sub_match_dict:
                            sub_match_args = match.groups() + sub_match.args

                        return ResolverMatch(
                            sub_match.func,
                            sub_match_args,
                            sub_match_dict,
                            sub_match.url_name,
                            [self.app_name] + sub_match.app_names,
                            [self.namespace] + sub_match.namespaces
                        )
                    tried.append([pattern])
            raise Resolver404({'tried': tried, 'path': new_path})
        raise Resolver404({'path': path})

    @cached_property
    def urlconf_module(self):
        if isinstance(self.urlconf_name, six.string_types):
            return import_module(self.urlconf_name)
        else:
            return self.urlconf_name

    @cached_property
    def url_patterns(self):
        # urlconf_module might be a valid set of patterns, so we default to it
        patterns = getattr(self.urlconf_module, "urlpatterns", self.urlconf_module)
        try:
            iter(patterns)
        except TypeError:
            msg = (
                "The included URLconf '{name}' does not appear to have any "
                "patterns in it. If you see valid patterns in the file then "
                "the issue is probably caused by a circular import."
            )
            raise ImproperlyConfigured(msg.format(name=self.urlconf_name))
        return patterns

    def resolve_error_handler(self, view_type):
        callback = getattr(self.urlconf_module, 'handler%s' % view_type, None)
        if not callback:
            # No handler specified in file; use default
            # Lazy import, since django.urls imports this file
            from django.conf import urls
            callback = getattr(urls, 'handler%s' % view_type)
        return get_callable(callback), {}

    def _reverse_with_prefix(self, lookup_view, _prefix, *args, **kwargs):
        if args and kwargs:
            raise ValueError("Don't mix *args and **kwargs in call to reverse()!")
        text_args = [force_text(v) for v in args]
        text_kwargs = {k: force_text(v) for (k, v) in kwargs.items()}

        if not self._populated:
            self._populate()

        possibilities = self.reverse_dict.getlist(lookup_view)

        for possibility, pattern, defaults in possibilities:
            for result, params in possibility:
                if args:
                    if len(args) != len(params):
                        continue
                    candidate_subs = dict(zip(params, text_args))
                else:
                    if (set(kwargs.keys()) | set(defaults.keys()) != set(params) |
                            set(defaults.keys())):
                        continue
                    matches = True
                    for k, v in defaults.items():
                        if kwargs.get(k, v) != v:
                            matches = False
                            break
                    if not matches:
                        continue
                    candidate_subs = text_kwargs
                # WSGI provides decoded URLs, without %xx escapes, and the URL
                # resolver operates on such URLs. First substitute arguments
                # without quoting to build a decoded URL and look for a match.
                # Then, if we have a match, redo the substitution with quoted
                # arguments in order to return a properly encoded URL.
                candidate_pat = _prefix.replace('%', '%%') + result
                if re.search('^%s%s' % (re.escape(_prefix), pattern), candidate_pat % candidate_subs, re.UNICODE):
                    # safe characters from `pchar` definition of RFC 3986
                    url = urlquote(candidate_pat % candidate_subs, safe=RFC3986_SUBDELIMS + str('/~:@'))
                    # Don't allow construction of scheme relative urls.
                    if url.startswith('//'):
                        url = '/%%2F%s' % url[2:]
                    return url
        # lookup_view can be URL name or callable, but callables are not
        # friendly in error messages.
        m = getattr(lookup_view, '__module__', None)
        n = getattr(lookup_view, '__name__', None)
        if m is not None and n is not None:
            lookup_view_s = "%s.%s" % (m, n)
        else:
            lookup_view_s = lookup_view

        patterns = [pattern for (possibility, pattern, defaults) in possibilities]
        raise NoReverseMatch("Reverse for '%s' with arguments '%s' and keyword "
                "arguments '%s' not found. %d pattern(s) tried: %s" %
                             (lookup_view_s, args, kwargs, len(patterns), patterns))


class LocaleRegexURLResolver(RegexURLResolver):
    """
    A URL resolver that always matches the active language code as URL prefix.

    Rather than taking a regex argument, we just override the ``regex``
    function to always return the active language-code as regex.
    """
    def __init__(self, urlconf_name, default_kwargs=None, app_name=None, namespace=None):
        super(LocaleRegexURLResolver, self).__init__(
            None, urlconf_name, default_kwargs, app_name, namespace)

    @property
    def regex(self):
        language_code = get_language()
        if language_code not in self._regex_dict:
            regex_compiled = re.compile('^%s/' % language_code, re.UNICODE)
            self._regex_dict[language_code] = regex_compiled
        return self._regex_dict[language_code]


def resolve(path, urlconf=None):
    if urlconf is None:
        urlconf = get_urlconf()
    return get_resolver(urlconf).resolve(path)


def reverse(viewname, urlconf=None, args=None, kwargs=None, current_app=None):
    if urlconf is None:
        urlconf = get_urlconf()
    resolver = get_resolver(urlconf)
    args = args or []
    kwargs = kwargs or {}

    prefix = get_script_prefix()

    if not isinstance(viewname, six.string_types):
        view = viewname
    else:
        parts = viewname.split(':')
        parts.reverse()
        view = parts[0]
        path = parts[1:]

        if current_app:
            current_path = current_app.split(':')
            current_path.reverse()
        else:
            current_path = None

        resolved_path = []
        ns_pattern = ''
        while path:
            ns = path.pop()
            current_ns = current_path.pop() if current_path else None

            # Lookup the name to see if it could be an app identifier
            try:
                app_list = resolver.app_dict[ns]
                # Yes! Path part matches an app in the current Resolver
                if current_ns and current_ns in app_list:
                    # If we are reversing for a particular app,
                    # use that namespace
                    ns = current_ns
                elif ns not in app_list:
                    # The name isn't shared by one of the instances
                    # (i.e., the default) so just pick the first instance
                    # as the default.
                    ns = app_list[0]
            except KeyError:
                pass

            if ns != current_ns:
                current_path = None

            try:
                extra, resolver = resolver.namespace_dict[ns]
                resolved_path.append(ns)
                ns_pattern = ns_pattern + extra
            except KeyError as key:
                if resolved_path:
                    raise NoReverseMatch(
                        "%s is not a registered namespace inside '%s'" %
                        (key, ':'.join(resolved_path)))
                else:
                    raise NoReverseMatch("%s is not a registered namespace" %
                                         key)
        if ns_pattern:
            resolver = get_ns_resolver(ns_pattern, resolver)

    return force_text(iri_to_uri(resolver._reverse_with_prefix(view, prefix, *args, **kwargs)))

reverse_lazy = lazy(reverse, six.text_type)


def clear_url_caches():
    get_callable.cache_clear()
    get_resolver.cache_clear()
    get_ns_resolver.cache_clear()


def set_script_prefix(prefix):
    """
    Sets the script prefix for the current thread.
    """
    if not prefix.endswith('/'):
        prefix += '/'
    _prefixes.value = prefix


def get_script_prefix():
    """
    Returns the currently active script prefix. Useful for client code that
    wishes to construct their own URLs manually (although accessing the request
    instance is normally going to be a lot cleaner).
    """
    return getattr(_prefixes, "value", '/')


def clear_script_prefix():
    """
    Unsets the script prefix for the current thread.
    """
    try:
        del _prefixes.value
    except AttributeError:
        pass


def set_urlconf(urlconf_name):
    """
    Sets the URLconf for the current thread (overriding the default one in
    settings). Set to None to revert back to the default.
    """
    if urlconf_name:
        _urlconfs.value = urlconf_name
    else:
        if hasattr(_urlconfs, "value"):
            del _urlconfs.value


def get_urlconf(default=None):
    """
    Returns the root URLconf to use for the current thread if it has been
    changed from the default one.
    """
    return getattr(_urlconfs, "value", default)


def is_valid_path(path, urlconf=None):
    """
    Returns True if the given path resolves against the default URL resolver,
    False otherwise.

    This is a convenience method to make working with "is this a match?" cases
    easier, avoiding unnecessarily indented try...except blocks.
    """
    try:
        resolve(path, urlconf)
        return True
    except Resolver404:
        return False


def translate_url(url, lang_code):
    """
    Given a URL (absolute or relative), try to get its translated version in
    the `lang_code` language (either by i18n_patterns or by translated regex).
    Return the original URL if no translated version is found.
    """
    parsed = urlsplit(url)
    try:
        match = resolve(parsed.path)
    except Resolver404:
        pass
    else:
        to_be_reversed = "%s:%s" % (match.namespace, match.url_name) if match.namespace else match.url_name
        with override(lang_code):
            try:
                url = reverse(to_be_reversed, args=match.args, kwargs=match.kwargs)
            except NoReverseMatch:
                pass
            else:
                url = urlunsplit((parsed.scheme, parsed.netloc, url, parsed.query, parsed.fragment))
    return url