summaryrefslogtreecommitdiffhomepage
path: root/libs/tld/utils.py
blob: e49794e8eb16cdd4b7293461b3c3060a42029df4 (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
641
642
643
644
645
646
647
648
from __future__ import unicode_literals

import argparse
import sys
from codecs import open as codecs_open
from functools import lru_cache
from os.path import isabs
from typing import Dict, List, Optional, Tuple, Type, Union
from urllib.parse import SplitResult, urlsplit

from .base import BaseTLDSourceParser, Registry
from .exceptions import (
    TldBadUrl,
    TldDomainNotFound,
    TldImproperlyConfigured,
    TldIOError,
)
from .helpers import project_dir
from .result import Result
from .trie import Trie

# codecs_open = open


__author__ = "Artur Barseghyan"
__copyright__ = "2013-2023 Artur Barseghyan"
__license__ = "MPL-1.1 OR GPL-2.0-only OR LGPL-2.1-or-later"
__all__ = (
    "BaseMozillaTLDSourceParser",
    "get_fld",
    "get_tld",
    "get_tld_names",
    "get_tld_names_container",
    "is_tld",
    "MozillaTLDSourceParser",
    "MozillaPublicOnlyTLDSourceParser",
    "parse_tld",
    "pop_tld_names_container",
    "process_url",
    "reset_tld_names",
    "Result",
    "tld_names",
    "update_tld_names",
    "update_tld_names_cli",
    "update_tld_names_container",
)

tld_names: Dict[str, Trie] = {}


def get_tld_names_container() -> Dict[str, Trie]:
    """Get container of all tld names.

    :return:
    :rtype dict:
    """
    global tld_names
    return tld_names


def update_tld_names_container(
    tld_names_local_path: str, trie_obj: Trie
) -> None:
    """Update TLD Names container item.

    :param tld_names_local_path:
    :param trie_obj:
    :return:
    """
    global tld_names
    # tld_names.update({tld_names_local_path: trie_obj})
    tld_names[tld_names_local_path] = trie_obj


def pop_tld_names_container(tld_names_local_path: str) -> None:
    """Remove TLD names container item.

    :param tld_names_local_path:
    :return:
    """
    global tld_names
    tld_names.pop(tld_names_local_path, None)


@lru_cache(maxsize=128, typed=True)
def update_tld_names(
    fail_silently: bool = False, parser_uid: str = None
) -> bool:
    """Update TLD names.

    :param fail_silently:
    :param parser_uid:
    :return:
    """
    results: List[bool] = []
    results_append = results.append
    if parser_uid:
        parser_cls = Registry.get(parser_uid, None)
        if parser_cls and parser_cls.source_url:
            results_append(
                parser_cls.update_tld_names(fail_silently=fail_silently)
            )
    else:
        for parser_uid, parser_cls in Registry.items():
            if parser_cls and parser_cls.source_url:
                results_append(
                    parser_cls.update_tld_names(fail_silently=fail_silently)
                )

    return all(results)


def update_tld_names_cli() -> int:
    """CLI wrapper for update_tld_names.

    Since update_tld_names returns True on success, we need to negate the
    result to match CLI semantics.
    """
    parser = argparse.ArgumentParser(description="Update TLD names")
    parser.add_argument(
        "parser_uid",
        nargs="?",
        default=None,
        help="UID of the parser to update TLD names for.",
    )
    parser.add_argument(
        "--fail-silently",
        dest="fail_silently",
        default=False,
        action="store_true",
        help="Fail silently",
    )
    args = parser.parse_args(sys.argv[1:])
    parser_uid = args.parser_uid
    fail_silently = args.fail_silently
    return int(
        not update_tld_names(parser_uid=parser_uid, fail_silently=fail_silently)
    )


def get_tld_names(
    fail_silently: bool = False,
    retry_count: int = 0,
    parser_class: Type[BaseTLDSourceParser] = None,
) -> Dict[str, Trie]:
    """Build the ``tlds`` list if empty. Recursive.

    :param fail_silently: If set to True, no exceptions are raised and None
        is returned on failure.
    :param retry_count: If greater than 1, we raise an exception in order
        to avoid infinite loops.
    :param parser_class:
    :type fail_silently: bool
    :type retry_count: int
    :type parser_class: BaseTLDSourceParser
    :return: List of TLD names
    :rtype: obj:`tld.utils.Trie`
    """
    if not parser_class:
        parser_class = MozillaTLDSourceParser

    return parser_class.get_tld_names(
        fail_silently=fail_silently, retry_count=retry_count
    )


# **************************************************************************
# **************************** Parser classes ******************************
# **************************************************************************


class BaseMozillaTLDSourceParser(BaseTLDSourceParser):
    @classmethod
    def get_tld_names(
        cls, fail_silently: bool = False, retry_count: int = 0
    ) -> Optional[Dict[str, Trie]]:
        """Parse.

        :param fail_silently:
        :param retry_count:
        :return:
        """
        if retry_count > 1:
            if fail_silently:
                return None
            else:
                raise TldIOError

        global tld_names
        _tld_names = tld_names
        # _tld_names = get_tld_names_container()

        # If already loaded, return
        if (
            cls.local_path in _tld_names
            and _tld_names[cls.local_path] is not None
        ):
            return _tld_names

        try:
            # Load the TLD names file
            if isabs(cls.local_path):
                local_path = cls.local_path
            else:
                local_path = project_dir(cls.local_path)
            local_file = codecs_open(local_path, "r", encoding="utf8")
            trie = Trie()
            trie_add = trie.add  # Performance opt
            # Make a list of it all, strip all garbage
            private_section = False
            include_private = cls.include_private

            for line in local_file:
                if "===BEGIN PRIVATE DOMAINS===" in line:
                    private_section = True

                if private_section and not include_private:
                    break

                # Puny code TLD names
                if "// xn--" in line:
                    line = line.split()[1]

                if line[0] in ("/", "\n"):
                    continue

                trie_add(f"{line.strip()}", private=private_section)

            update_tld_names_container(cls.local_path, trie)

            local_file.close()
        except IOError:
            # Grab the file
            cls.update_tld_names(fail_silently=fail_silently)
            # Increment ``retry_count`` in order to avoid infinite loops
            retry_count += 1
            # Run again
            return cls.get_tld_names(
                fail_silently=fail_silently, retry_count=retry_count
            )
        except Exception as err:
            if fail_silently:
                return None
            else:
                raise err
        finally:
            try:
                local_file.close()
            except Exception:
                pass

        return _tld_names


class MozillaTLDSourceParser(BaseMozillaTLDSourceParser):
    """Mozilla TLD source."""

    uid: str = "mozilla"
    source_url: str = "https://publicsuffix.org/list/public_suffix_list.dat"
    local_path: str = "res/effective_tld_names.dat.txt"


class MozillaPublicOnlyTLDSourceParser(BaseMozillaTLDSourceParser):
    """Mozilla TLD source."""

    uid: str = "mozilla_public_only"
    source_url: str = (
        "https://publicsuffix.org/list/public_suffix_list.dat?publiconly"
    )
    local_path: str = "res/effective_tld_names_public_only.dat.txt"
    include_private: bool = False


# **************************************************************************
# **************************** Core functions ******************************
# **************************************************************************


def process_url(
    url: Union[str, SplitResult],
    fail_silently: bool = False,
    fix_protocol: bool = False,
    search_public: bool = True,
    search_private: bool = True,
    parser_class: Type[BaseTLDSourceParser] = MozillaTLDSourceParser,
) -> Union[Tuple[List[str], int, SplitResult], Tuple[None, None, SplitResult]]:
    """Process URL.

    :param parser_class:
    :param url:
    :param fail_silently:
    :param fix_protocol:
    :param search_public:
    :param search_private:
    :return:
    """
    if not (search_public or search_private):
        raise TldImproperlyConfigured(
            "Either `search_public` or `search_private` (or both) shall be "
            "set to True."
        )

    # Init
    _tld_names = get_tld_names(
        fail_silently=fail_silently, parser_class=parser_class
    )

    if not isinstance(url, SplitResult):
        if fix_protocol and not url.startswith(("//", "http://", "https://")):
            url = f"https://{url}"

        # Get parsed URL as we might need it later
        try:
            parsed_url = urlsplit(url)
        except ValueError as e:
            if fail_silently:
                return None, None, url
            else:
                raise e
    else:
        parsed_url = url

    # Get (sub) domain name
    domain_name = parsed_url.hostname

    if not domain_name:
        if fail_silently:
            return None, None, parsed_url
        else:
            raise TldBadUrl(url=url)

    domain_name = domain_name.lower()

    # This will correctly handle dots at the end of domain name in URLs like
    # https://github.com............/barseghyanartur/tld/
    if domain_name.endswith("."):
        domain_name = domain_name.rstrip(".")

    domain_parts = domain_name.split(".")
    tld_names_local_path = parser_class.local_path

    # Now we query our Trie iterating on the domain parts in reverse order
    node = _tld_names[tld_names_local_path].root
    current_length = 0
    tld_length = 0
    match = None
    len_domain_parts = len(domain_parts)
    for i in range(len_domain_parts - 1, -1, -1):
        part = domain_parts[i]

        # Cannot go deeper
        if node.children is None:
            break

        # Exception
        if part == node.exception:
            break

        child = node.children.get(part)

        # Wildcards
        if child is None:
            child = node.children.get("*")

        # If the current part is not in current node's children, we can stop
        if child is None:
            break

        # Else we move deeper and increment our tld offset
        current_length += 1
        node = child

        if node.leaf:
            tld_length = current_length
            match = node

    # Checking the node we finished on is a leaf and is one we allow
    if (
        (match is None)
        or (not match.leaf)
        or (not search_public and not match.private)
        or (not search_private and match.private)
    ):
        if fail_silently:
            return None, None, parsed_url
        else:
            raise TldDomainNotFound(domain_name=domain_name)

    if len_domain_parts == tld_length:
        non_zero_i = -1  # hostname = tld
    else:
        non_zero_i = max(1, len_domain_parts - tld_length)

    return domain_parts, non_zero_i, parsed_url


def get_fld(
    url: Union[str, SplitResult],
    fail_silently: bool = False,
    fix_protocol: bool = False,
    search_public: bool = True,
    search_private: bool = True,
    parser_class: Type[BaseTLDSourceParser] = None,
    **kwargs,
) -> Optional[str]:
    """Extract the first level domain.

    Extract the top level domain based on the mozilla's effective TLD names
    dat file. Returns a string. May throw ``TldBadUrl`` or
    ``TldDomainNotFound`` exceptions if there's bad URL provided or no TLD
    match found respectively.

    :param url: URL to get top level domain from.
    :param fail_silently: If set to True, no exceptions are raised and None
        is returned on failure.
    :param fix_protocol: If set to True, missing or wrong protocol is
        ignored (https is appended instead).
    :param search_public: If set to True, search in public domains.
    :param search_private: If set to True, search in private domains.
    :param parser_class:
    :type url: str | SplitResult
    :type fail_silently: bool
    :type fix_protocol: bool
    :type search_public: bool
    :type search_private: bool
    :return: String with top level domain (if ``as_object`` argument
        is set to False) or a ``tld.utils.Result`` object (if ``as_object``
        argument is set to True); returns None on failure.
    :rtype: str
    """
    if "as_object" in kwargs:
        raise TldImproperlyConfigured(
            "`as_object` argument is deprecated for `get_fld`. Use `get_tld` "
            "instead."
        )

    if not parser_class:
        parser_class = (
            MozillaTLDSourceParser
            if search_private
            else MozillaPublicOnlyTLDSourceParser
        )

    domain_parts, non_zero_i, parsed_url = process_url(
        url=url,
        fail_silently=fail_silently,
        fix_protocol=fix_protocol,
        search_public=search_public,
        search_private=search_private,
        parser_class=parser_class,
    )

    if domain_parts is None:
        return None

    # This should be None when domain_parts is None
    # but mypy isn't quite smart enough to figure that out yet
    assert non_zero_i is not None
    if non_zero_i < 0:
        # hostname = tld
        return parsed_url.hostname

    return ".".join(domain_parts[non_zero_i - 1 :])


def get_tld(
    url: Union[str, SplitResult],
    fail_silently: bool = False,
    as_object: bool = False,
    fix_protocol: bool = False,
    search_public: bool = True,
    search_private: bool = True,
    parser_class: Type[BaseTLDSourceParser] = None,
) -> Optional[Union[str, Result]]:
    """Extract the top level domain.

    Extract the top level domain based on the mozilla's effective TLD names
    dat file. Returns a string. May throw ``TldBadUrl`` or
    ``TldDomainNotFound`` exceptions if there's bad URL provided or no TLD
    match found respectively.

    :param url: URL to get top level domain from.
    :param fail_silently: If set to True, no exceptions are raised and None
        is returned on failure.
    :param as_object: If set to True, ``tld.utils.Result`` object is returned,
        ``domain``, ``suffix`` and ``tld`` properties.
    :param fix_protocol: If set to True, missing or wrong protocol is
        ignored (https is appended instead).
    :param search_public: If set to True, search in public domains.
    :param search_private: If set to True, search in private domains.
    :param parser_class:
    :type url: str | SplitResult
    :type fail_silently: bool
    :type as_object: bool
    :type fix_protocol: bool
    :type search_public: bool
    :type search_private: bool
    :return: String with top level domain (if ``as_object`` argument
        is set to False) or a ``tld.utils.Result`` object (if ``as_object``
        argument is set to True); returns None on failure.
    :rtype: str
    """
    if not parser_class:
        parser_class = (
            MozillaTLDSourceParser
            if search_private
            else MozillaPublicOnlyTLDSourceParser
        )

    domain_parts, non_zero_i, parsed_url = process_url(
        url=url,
        fail_silently=fail_silently,
        fix_protocol=fix_protocol,
        search_public=search_public,
        search_private=search_private,
        parser_class=parser_class,
    )

    if domain_parts is None:
        return None

    # This should be None when domain_parts is None
    # but mypy isn't quite smart enough to figure that out yet
    assert non_zero_i is not None

    if not as_object:
        if non_zero_i < 0:
            # hostname = tld
            return parsed_url.hostname
        return ".".join(domain_parts[non_zero_i:])

    if non_zero_i < 0:
        # hostname = tld
        subdomain = ""
        domain = ""
        # This is checked in `process_url`, but the type is
        # ambiguous (Optional[str]) so this assertion is just to satisfy mypy
        assert parsed_url.hostname is not None, "No hostname in URL"
        _tld = parsed_url.hostname
    else:
        subdomain = ".".join(domain_parts[: non_zero_i - 1])
        domain = ".".join(domain_parts[non_zero_i - 1 : non_zero_i])
        _tld = ".".join(domain_parts[non_zero_i:])

    return Result(
        subdomain=subdomain, domain=domain, tld=_tld, parsed_url=parsed_url
    )


def parse_tld(
    url: Union[str, SplitResult],
    fail_silently: bool = False,
    fix_protocol: bool = False,
    search_public: bool = True,
    search_private: bool = True,
    parser_class: Type[BaseTLDSourceParser] = None,
) -> Union[Tuple[None, None, None], Tuple[str, str, str]]:
    """Parse TLD into parts.

    :param url:
    :param fail_silently:
    :param fix_protocol:
    :param search_public:
    :param search_private:
    :param parser_class:
    :return: Tuple (tld, domain, subdomain)
    :rtype: tuple
    """
    if not parser_class:
        parser_class = (
            MozillaTLDSourceParser
            if search_private
            else MozillaPublicOnlyTLDSourceParser
        )

    try:
        obj = get_tld(
            url,
            fail_silently=fail_silently,
            as_object=True,
            fix_protocol=fix_protocol,
            search_public=search_public,
            search_private=search_private,
            parser_class=parser_class,
        )
        if obj is None:
            return None, None, None

        return obj.tld, obj.domain, obj.subdomain  # type: ignore

    except (TldBadUrl, TldDomainNotFound, TldImproperlyConfigured, TldIOError):
        pass

    return None, None, None


def is_tld(
    value: Union[str, SplitResult],
    search_public: bool = True,
    search_private: bool = True,
    parser_class: Type[BaseTLDSourceParser] = None,
) -> bool:
    """Check if given URL is tld.

    :param value: URL to get top level domain from.
    :param search_public: If set to True, search in public domains.
    :param search_private: If set to True, search in private domains.
    :param parser_class:
    :type value: str
    :type search_public: bool
    :type search_private: bool
    :return:
    :rtype: bool
    """
    if not parser_class:
        parser_class = (
            MozillaTLDSourceParser
            if search_private
            else MozillaPublicOnlyTLDSourceParser
        )

    _tld = get_tld(
        url=value,
        fail_silently=True,
        fix_protocol=True,
        search_public=search_public,
        search_private=search_private,
        parser_class=parser_class,
    )
    return value == _tld


def reset_tld_names(tld_names_local_path: str = None) -> None:
    """Reset the ``tld_names`` to empty value.

    If ``tld_names_local_path`` is given, removes specified
    entry from ``tld_names`` instead.

    :param tld_names_local_path:
    :type tld_names_local_path: str
    :return:
    """

    if tld_names_local_path:
        pop_tld_names_container(tld_names_local_path)
    else:
        global tld_names
        tld_names = {}