aboutsummaryrefslogtreecommitdiff
path: root/src/hydrilla/item_infos.py
blob: 9638dab9c078c7b620ba5c683f8b9881463490e8 (about) (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
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
# SPDX-License-Identifier: GPL-3.0-or-later

# Reading resources, mappings and other JSON documents from the filesystem.
#
# This file is part of Hydrilla&Haketilo
#
# Copyright (C) 2021, 2022 Wojtek Kosior
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program.  If not, see <https://www.gnu.org/licenses/>.
#
#
# I, Wojtek Kosior, thereby promise not to sue for violation of this
# file's license. Although I request that you do not make use of this
# code in a proprietary program, I am not going to enforce this in
# court.

"""
.....
"""

# Enable using with Python 3.7.
from __future__ import annotations

import sys

if sys.version_info >= (3, 8):
    from typing import Protocol
else:
    from typing_extensions import Protocol

import enum
import typing as t
import dataclasses as dc

from pathlib import Path, PurePosixPath
from abc import ABC, abstractmethod

from immutables import Map

from . import versions, json_instances
from .url_patterns import parse_pattern, ParsedUrl, ParsedPattern
from .exceptions import HaketiloException
from .translations import smart_gettext as _


@dc.dataclass(frozen=True, unsafe_hash=True)
class ItemSpecifier:
    """...."""
    identifier: str

SpecifierObjs = t.Sequence[t.Mapping[str, t.Any]]

def make_item_specifiers_seq(spec_objs: SpecifierObjs) \
    -> tuple[ItemSpecifier, ...]:
    """...."""
    return tuple(ItemSpecifier(obj['identifier']) for obj in spec_objs)

def make_required_mappings(spec_objs: t.Any, schema_compat: int) \
    -> tuple[ItemSpecifier, ...]:
    """...."""
    if schema_compat < 2:
        return ()

    return make_item_specifiers_seq(spec_objs)

@dc.dataclass(frozen=True, unsafe_hash=True)
class FileSpecifier:
    """...."""
    name:   str
    sha256: str

def normalize_filename(name: str):
    """
    This function eliminated double slashes in file name and ensures it does not
    try to reference parent directories.
    """
    path = PurePosixPath(name)

    if '.' in path.parts or '..' in path.parts:
        msg = _('err.item_info.filename_invalid_{}').format(name)
        raise HaketiloException(msg)

    return str(path)

def make_file_specifiers_seq(spec_objs: SpecifierObjs) \
    -> tuple[FileSpecifier, ...]:
    """...."""
    return tuple(
        FileSpecifier(normalize_filename(obj['file']), obj['sha256'])
        for obj
        in spec_objs
    )

@dc.dataclass(frozen=True, unsafe_hash=True)
class GeneratedBy:
    """...."""
    name:    str
    version: t.Optional[str]

    @staticmethod
    def make(generated_by_obj: t.Optional[t.Mapping[str, t.Any]]) -> \
        t.Optional['GeneratedBy']:
        """...."""
        if generated_by_obj is None:
            return None

        return GeneratedBy(
            name    = generated_by_obj['name'],
            version = generated_by_obj.get('version')
        )


def make_eval_permission(perms_obj: t.Any, schema_compat: int) -> bool:
    if schema_compat < 2:
        return False

    return perms_obj.get('eval', False)


def make_cors_bypass_permission(perms_obj: t.Any, schema_compat: int) -> bool:
    if schema_compat < 2:
        return False

    return perms_obj.get('cors_bypass', False)


def make_version_constraint(
        ver:           t.Any,
        schema_compat: int,
        default:       versions.VerTuple
) -> versions.VerTuple:
    if schema_compat < 2 or ver is None:
        return default

    return versions.normalize(ver)


class Categorizable(Protocol):
    """...."""
    uuid:       t.Optional[str]
    identifier: str

@dc.dataclass(frozen=True, unsafe_hash=True)
class ItemIdentity:
    repo:           str
    repo_iteration: int
    version:        versions.VerTuple
    identifier:     str


# mypy needs to be corrected:
# https://stackoverflow.com/questions/70999513/conflict-between-mix-ins-for-abstract-dataclasses/70999704#70999704
@dc.dataclass(frozen=True) # type: ignore[misc]
class ItemInfoBase(ABC, ItemIdentity, Categorizable):
    """...."""
    source_name:        str                       = dc.field(hash=False, compare=False)
    source_copyright:   tuple[FileSpecifier, ...] = dc.field(hash=False, compare=False)
    uuid:               t.Optional[str]           = dc.field(hash=False, compare=False)
    long_name:          str                       = dc.field(hash=False, compare=False)
    description:        str                       = dc.field(hash=False, compare=False)
    allows_eval:        bool                      = dc.field(hash=False, compare=False)
    allows_cors_bypass: bool                      = dc.field(hash=False, compare=False)
    min_haketilo_ver:   versions.VerTuple         = dc.field(hash=False, compare=False)
    max_haketilo_ver:   versions.VerTuple         = dc.field(hash=False, compare=False)
    required_mappings:  tuple[ItemSpecifier, ...] = dc.field(hash=False, compare=False)
    generated_by:       t.Optional[GeneratedBy]   = dc.field(hash=False, compare=False)

    @property
    def version_string(self) -> str:
        return versions.version_string(self.version)

    @property
    def versioned_identifier(self) -> str:
        """...."""
        return f'{self.identifier}-{self.version_string}'

    @property
    def files(self) -> tuple[FileSpecifier, ...]:
        return self.source_copyright

    @property
    def compatible(self) -> bool:
        return (self.min_haketilo_ver <= versions.haketilo_version and
                self.max_haketilo_ver >= versions.haketilo_version)

    @staticmethod
    def _get_base_init_kwargs(
            item_obj:       t.Mapping[str, t.Any],
            schema_compat:  int,
            repo:           str,
            repo_iteration: int
    ) -> t.Mapping[str, t.Any]:
        """...."""
        source_copyright = make_file_specifiers_seq(
            item_obj['source_copyright']
        )

        version = versions.normalize(item_obj['version'])

        perms_obj = item_obj.get('permissions', {})

        eval_perm        = make_eval_permission(perms_obj, schema_compat)
        cors_bypass_perm = make_cors_bypass_permission(perms_obj, schema_compat)

        min_haketilo_ver = make_version_constraint(
            ver           = item_obj.get('min_haketilo_version'),
            schema_compat = schema_compat,
            default       = versions.int_ver_min
        )
        max_haketilo_ver = make_version_constraint(
            ver           = item_obj.get('max_haketilo_version'),
            schema_compat = schema_compat,
            default       = versions.int_ver_max
        )

        required_mappings = make_required_mappings(
            item_obj.get('required_mappings', []),
            schema_compat
        )

        generated_by = GeneratedBy.make(item_obj.get('generated_by'))

        return Map(
            repo               = repo,
            repo_iteration     = repo_iteration,
            source_name        = item_obj['source_name'],
            source_copyright   = source_copyright,
            version            = version,
            identifier         = item_obj['identifier'],
            uuid               = item_obj.get('uuid'),
            long_name          = item_obj['long_name'],
            description        = item_obj['description'],
            allows_eval        = eval_perm,
            allows_cors_bypass = cors_bypass_perm,
            min_haketilo_ver   = min_haketilo_ver,
            max_haketilo_ver   = max_haketilo_ver,
            required_mappings  = required_mappings,
            generated_by       = generated_by
        )


class ItemType(enum.Enum):
    RESOURCE = 'resource'
    MAPPING  = 'mapping'

    @property
    def info_class(self) -> t.Type[AnyInfo]:
        if self == ItemType.RESOURCE:
            return ResourceInfo
        else:
            return MappingInfo

    @property
    def alt_name(self) -> str:
        if self == ItemType.RESOURCE:
            return 'library'
        else:
            return 'package'

    @property
    def alt_name_plural(self) -> str:
        if self == ItemType.RESOURCE:
            return 'libraries'
        else:
            return 'packages'

@dc.dataclass(frozen=True, unsafe_hash=True)
class CorrespondsToResourceDCMixin:
    type: t.ClassVar[ItemType] = ItemType.RESOURCE

@dc.dataclass(frozen=True, unsafe_hash=True)
class CorrespondsToMappingDCMixin:
    type: t.ClassVar[ItemType] = ItemType.MAPPING


@dc.dataclass(frozen=True, unsafe_hash=True)
class ResourceInfo(ItemInfoBase, CorrespondsToResourceDCMixin):
    """...."""
    revision:     int                       = dc.field(hash=False, compare=False)
    dependencies: tuple[ItemSpecifier, ...] = dc.field(hash=False, compare=False)
    scripts:      tuple[FileSpecifier, ...] = dc.field(hash=False, compare=False)

    @property
    def version_string(self) -> str:
        return f'{super().version_string}-{self.revision}'

    @property
    def files(self) -> tuple[FileSpecifier, ...]:
        return tuple((*self.source_copyright, *self.scripts))

    @staticmethod
    def make(
            item_obj:       t.Mapping[str, t.Any],
            schema_compat:  int,
            repo:           str,
            repo_iteration: int
    ) -> 'ResourceInfo':
        """...."""
        base_init_kwargs = ItemInfoBase._get_base_init_kwargs(
            item_obj,
            schema_compat,
            repo,
            repo_iteration
        )

        dependencies = make_item_specifiers_seq(
            item_obj.get('dependencies', [])
        )

        scripts = make_file_specifiers_seq(
            item_obj.get('scripts', [])
        )

        return ResourceInfo(
            **base_init_kwargs,

            revision     = item_obj['revision'],
            dependencies = dependencies,
            scripts      = scripts
        )

    @staticmethod
    def load(
            instance_source: json_instances.InstanceSource,
            repo:            str = '<dummyrepo>',
            repo_iteration:  int = -1
    ) -> 'ResourceInfo':
        """...."""
        return _load_item_info(
            ResourceInfo,
            instance_source,
            repo,
            repo_iteration
        )

    def __lt__(self, other: 'ResourceInfo') -> bool:
        """...."""
        return (
            self.identifier,
            other.version,
            other.revision,
            self.repo,
            other.repo_iteration
        ) < (
            other.identifier,
            self.version,
            self.revision,
            other.repo,
            self.repo_iteration
        )

def make_payloads(payloads_obj: t.Mapping[str, t.Any]) \
    -> t.Mapping[ParsedPattern, ItemSpecifier]:
    """...."""
    mapping: list[tuple[ParsedPattern, ItemSpecifier]] = []

    for pattern, spec_obj in payloads_obj.items():
        ref = ItemSpecifier(spec_obj['identifier'])
        mapping.extend((parsed, ref) for parsed in parse_pattern(pattern))

    return Map(mapping)

@dc.dataclass(frozen=True, unsafe_hash=True)
class MappingInfo(ItemInfoBase, CorrespondsToMappingDCMixin):
    """...."""
    payloads: t.Mapping[ParsedPattern, ItemSpecifier] = \
        dc.field(hash=False, compare=False)

    @staticmethod
    def make(
            item_obj:       t.Mapping[str, t.Any],
            schema_compat:  int,
            repo:           str,
            repo_iteration: int
    ) -> 'MappingInfo':
        """...."""
        base_init_kwargs = ItemInfoBase._get_base_init_kwargs(
            item_obj,
            schema_compat,
            repo,
            repo_iteration
        )

        return MappingInfo(
            **base_init_kwargs,

            payloads = make_payloads(item_obj.get('payloads', {}))
        )

    @staticmethod
    def load(
            instance_source: json_instances.InstanceSource,
            repo:            str = '<dummyrepo>',
            repo_iteration:  int = -1
    ) -> 'MappingInfo':
        """...."""
        return _load_item_info(
            MappingInfo,
            instance_source,
            repo,
            repo_iteration
        )

    def __lt__(self, other: 'MappingInfo') -> bool:
        """...."""
        return (
            self.identifier,
            other.version,
            self.repo,
            other.repo_iteration
        ) < (
            other.identifier,
            self.version,
            other.repo,
            self.repo_iteration
        )


AnyInfo = t.Union[ResourceInfo, MappingInfo]


LoadedType = t.TypeVar('LoadedType', ResourceInfo, MappingInfo)

def _load_item_info(
        info_type:       t.Type[LoadedType],
        instance_source: json_instances.InstanceSource,
        repo:            str,
        repo_iteration:  int
) -> LoadedType:
    """Read, validate and autocomplete a mapping/resource description."""
    instance = json_instances.read_instance(instance_source)

    schema_fmt = f'api_{info_type.type.value}_description-{{}}.schema.json'

    schema_compat = json_instances.validate_instance(instance, schema_fmt)

    # We know from successful validation that instance is a dict.
    return info_type.make(
        t.cast('dict[str, t.Any]', instance),
        schema_compat,
        repo,
        repo_iteration
    )


CategorizedInfoType = t.TypeVar(
    'CategorizedInfoType',
    ResourceInfo,
    MappingInfo
)

CategorizedType = t.TypeVar(
    'CategorizedType',
    bound=Categorizable
)

CategorizedUpdater = t.Callable[
    [t.Optional[CategorizedType]],
    t.Optional[CategorizedType]
]

CategoryKeyType = t.TypeVar('CategoryKeyType', bound=t.Hashable)

@dc.dataclass(frozen=True) # type: ignore[misc]
class CategorizedItemInfo(
        ABC,
        Categorizable,
        t.Generic[CategorizedInfoType, CategorizedType, CategoryKeyType]
):
    """...."""
    SelfType = t.TypeVar(
        'SelfType',
        bound = 'CategorizedItemInfo[CategorizedInfoType, CategorizedType, CategoryKeyType]'
    )

    uuid:         t.Optional[str]                       = None
    identifier:   str                                   = '<dummy>'
    items:        Map[CategoryKeyType, CategorizedType] = Map()
    _initialized: bool                                  = False

    def _update(
            self:   'SelfType',
            key:     CategoryKeyType,
            updater: CategorizedUpdater
    ) -> 'SelfType':
        """...... Perform sanity checks for uuid."""
        uuid = self.uuid

        items = self.items.mutate()

        updated = updater(items.get(key))
        if updated is None:
            items.pop(key, None)

            identifier = self.identifier
        else:
            items[key] = updated

            identifier = updated.identifier
            if self._initialized:
                assert identifier == self.identifier

            if uuid is not None:
                if updated.uuid is not None and uuid != updated.uuid:
                    raise HaketiloException(_('uuid_mismatch_{identifier}')
                                            .format(identifier=identifier))
            else:
                uuid = updated.uuid

        return dc.replace(
            self,
            identifier   = identifier,
            uuid         = uuid,
            items        = items.finish(),
            _initialized = self._initialized or updated is not None
        )

    @abstractmethod
    def register(self: 'SelfType', info: CategorizedInfoType) -> 'SelfType':
        ...

    @abstractmethod
    def get_all(self: 'SelfType') -> t.Sequence[CategorizedInfoType]:
        ...

    def is_empty(self) -> bool:
        return len(self.items) == 0


class VersionedItemInfo(
        CategorizedItemInfo[
            CategorizedInfoType,
            CategorizedInfoType,
            versions.VerTuple
        ],
        t.Generic[CategorizedInfoType]
):
    """Stores data of multiple versions of given resource/mapping."""
    SelfType = t.TypeVar(
        'SelfType',
        bound = 'VersionedItemInfo[CategorizedInfoType]'
    )

    def register(self: 'SelfType', item_info: CategorizedInfoType) \
        -> 'SelfType':
        """
        Make item info queryable by version. Perform sanity checks for uuid.
        """
        return self._update(item_info.version, lambda old_info: item_info)

    @property
    def newest_version(self) -> versions.VerTuple:
        """...."""
        assert not self.is_empty()

        return self.versions()[-1]

    @property
    def newest_info(self) -> CategorizedInfoType:
        """Find and return info of the newest version of item."""
        return self.items[self.newest_version]

    def versions(self, reverse: bool = False) -> t.Sequence[versions.VerTuple]:
        return sorted(self.items.keys(), reverse=reverse)

    def get_by_ver(self, ver: t.Sequence[int]) \
        -> t.Optional[CategorizedInfoType]:
        """
        Find and return info of the specified version of the item (or None if
        absent).
        """
        return self.items.get(versions.normalize(ver))

    def get_all(self, reverse_versions: bool = False) \
        -> t.Sequence[CategorizedInfoType]:
        """
        Generate item info for all its versions, from oldest to newest unless
        the opposite is requested.
        """
        versions = self.versions(reverse=reverse_versions)
        return [self.items[ver] for ver in versions]

VersionedResourceInfo = VersionedItemInfo[ResourceInfo]
VersionedMappingInfo  = VersionedItemInfo[MappingInfo]

VersionedItemInfoMap     = Map[str, VersionedItemInfo]
VersionedResourceInfoMap = Map[str, VersionedResourceInfo]
VersionedMappingInfoMap  = Map[str, VersionedMappingInfo]

def register_in_versioned_map(
        map:  Map[str, VersionedItemInfo[CategorizedInfoType]],
        info: CategorizedInfoType
) -> Map[str, VersionedItemInfo[CategorizedInfoType]]:
    versioned_info = map.get(info.identifier, VersionedItemInfo())

    return map.set(info.identifier, versioned_info.register(info))


class MultirepoItemInfo(
        CategorizedItemInfo[
            CategorizedInfoType,
            VersionedItemInfo[CategorizedInfoType],
            tuple[str, int]
        ],
        t.Generic[CategorizedInfoType]
):
    """
    Stores data of multiple versions of given resource/mapping that may come
    from multiple repositories.
    """
    SelfType = t.TypeVar(
        'SelfType',
        bound = 'MultirepoItemInfo[CategorizedInfoType]'
    )

    def register(self: 'SelfType', item_info: CategorizedInfoType) \
        -> 'SelfType':
        """
        Make item info queryable by repo and version. Perform sanity checks for
        uuid.
        """
        def update(
                versioned: t.Optional[VersionedItemInfo[CategorizedInfoType]]
        ) -> VersionedItemInfo[CategorizedInfoType]:
            if versioned is None:
                versioned = VersionedItemInfo()
            return versioned.register(item_info)

        return self._update((item_info.repo, item_info.repo_iteration), update)

    @property
    def default_info(self) -> CategorizedInfoType:
        """
        Find and return info of one of the available options for the newest
        version of item.
        """
        assert not self.is_empty()

        return self.get_all(reverse_repos=True)[-1]

    def options(self, reverse: bool = False) -> t.Sequence[tuple[str, int]]:
        return sorted(
            self.items.keys(),
            key     = (lambda tuple: (tuple[0], 1 - tuple[1])),
            reverse = reverse
        )

    def get_all(
            self,
            reverse_versions: bool = False,
            reverse_repos:    bool = False
    ) -> t.Sequence[CategorizedInfoType]:
        """
        Generate item info for all its versions and options, from oldest to
        newest version and from.
        """
        all_versions: set[versions.VerTuple] = set()
        for versioned in self.items.values():
            all_versions.update(versioned.versions())

        result = []

        for version in sorted(all_versions, reverse=reverse_versions):
            for option in self.options(reverse=reverse_repos):
                info = self.items[option].get_by_ver(version)
                if info is not None:
                    result.append(info)

        return result

MultirepoResourceInfo = MultirepoItemInfo[ResourceInfo]
MultirepoMappingInfo  = MultirepoItemInfo[MappingInfo]


MultirepoItemInfoMap     = Map[str, MultirepoItemInfo]
MultirepoResourceInfoMap = Map[str, MultirepoResourceInfo]
MultirepoMappingInfoMap  = Map[str, MultirepoMappingInfo]

def register_in_multirepo_map(
        map:  Map[str, MultirepoItemInfo[CategorizedInfoType]],
        info: CategorizedInfoType
) -> Map[str, MultirepoItemInfo[CategorizedInfoType]]:
    multirepo_info = map.get(info.identifier, MultirepoItemInfo())

    return map.set(info.identifier, multirepo_info.register(info))


def all_map_infos(
    map: Map[str, CategorizedItemInfo[CategorizedInfoType, t.Any, t.Any]]
) -> t.Iterator[CategorizedInfoType]:
    for versioned_info in map.values():
        for item_info in versioned_info.get_all():
            yield item_info