aboutsummaryrefslogtreecommitdiff
path: root/src/hydrilla/proxy/state_impl/base.py
blob: 92833ddf19e43ab42add19a1094342b42897a4ad (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
# SPDX-License-Identifier: GPL-3.0-or-later

# Haketilo proxy data and configuration (definition of fields of a class that
# will implement HaketiloState).
#
# This file is part of Hydrilla&Haketilo.
#
# Copyright (C) 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 this code
# in a proprietary program, I am not going to enforce this in court.

"""
This module defines fields that will later be part of a concrete HaketiloState
subtype.
"""

# Enable using with Python 3.7.
from __future__ import annotations

import sqlite3
import secrets
import threading
import dataclasses as dc
import typing as t

from pathlib import Path
from contextlib import contextmanager
from abc import abstractmethod

from immutables import Map

from ... import url_patterns
from ... import pattern_tree
from .. import simple_dependency_satisfying as sds
from .. import state as st
from .. import policies


PolicyTree = pattern_tree.PatternTree[policies.PolicyFactory]
PayloadsData = t.Mapping[st.PayloadRef, st.PayloadData]

@dc.dataclass(frozen=True, unsafe_hash=True)
class ConcretePayloadRef(st.PayloadRef):
    state: 'HaketiloStateWithFields' = dc.field(hash=False, compare=False)

    def get_data(self) -> st.PayloadData:
        try:
            return self.state.payloads_data[self]
        except KeyError:
            raise st.MissingItemError()

    def get_mapping(self) -> st.MappingVersionRef:
        raise NotImplementedError()

    def get_script_paths(self) \
        -> t.Iterable[t.Sequence[str]]:
        with self.state.cursor() as cursor:
            cursor.execute(
                '''
                SELECT
                        i.identifier, fu.name
                FROM
                                  payloads                    AS p
                        LEFT JOIN resolved_depended_resources AS rdd
                                USING (payload_id)
                        LEFT JOIN item_versions               AS iv
                                ON rdd.resource_item_id = iv.item_version_id
                        LEFT JOIN items                       AS i
                                USING (item_id)
                        LEFT JOIN file_uses                   AS fu
                                USING (item_version_id)
                WHERE
                        fu.type = 'W'    AND
                        p.payload_id = ? AND
                        (fu.idx IS NOT NULL OR rdd.idx IS NULL)
                ORDER BY
                        rdd.idx, fu.idx;
                ''',
                (self.id,)
            )

            paths: list[t.Sequence[str]] = []
            for resource_identifier, file_name in cursor.fetchall():
                if resource_identifier is None:
                    # payload found but it had no script files
                    return ()

                paths.append((resource_identifier, *file_name.split('/')))

        if paths == []:
            # payload not found
            raise st.MissingItemError()

        return paths

    def get_file_data(self, path: t.Sequence[str]) \
        -> t.Optional[st.FileData]:
        if len(path) == 0:
            raise st.MissingItemError()

        resource_identifier, *file_name_segments = path

        file_name = '/'.join(file_name_segments)

        with self.state.cursor() as cursor:
            cursor.execute(
                '''
                SELECT
                        f.data, fu.mime_type
                FROM
                             payloads                    AS p
                        JOIN resolved_depended_resources AS rdd
                                USING (payload_id)
                        JOIN item_versions               AS iv
                                ON rdd.resource_item_id = iv.item_version_id
                        JOIN items                       AS i
                                USING (item_id)
                        JOIN file_uses                   AS fu
                                USING (item_version_id)
                        JOIN files                       AS f
                                USING (file_id)
                WHERE
                        p.payload_id = ? AND
                        i.identifier = ? AND
                        fu.name = ?      AND
                        fu.type = 'W';
                ''',
                (self.id, resource_identifier, file_name)
            )

            result = cursor.fetchall()

        if result == []:
            return None

        (data, mime_type), = result

        return st.FileData(type=mime_type, name=file_name, contents=data)

def register_payload(
        policy_tree: PolicyTree,
        pattern:     url_patterns.ParsedPattern,
        payload_key: st.PayloadKey,
        token:       str
) -> PolicyTree:
    """...."""
    payload_policy_factory = policies.PayloadPolicyFactory(
        builtin     = False,
        payload_key = payload_key
    )

    policy_tree = policy_tree.register(pattern, payload_policy_factory)

    resource_policy_factory = policies.PayloadResourcePolicyFactory(
        builtin     = False,
        payload_key = payload_key
    )

    policy_tree = policy_tree.register(
        pattern.path_append(token, '***'),
        resource_policy_factory
    )

    return policy_tree

# mypy needs to be corrected:
# https://stackoverflow.com/questions/70999513/conflict-between-mix-ins-for-abstract-dataclasses/70999704#70999704
@dc.dataclass # type: ignore[misc]
class HaketiloStateWithFields(st.HaketiloState):
    """...."""
    store_dir:      Path
    connection:     sqlite3.Connection
    current_cursor: t.Optional[sqlite3.Cursor] = None
    #settings:       st.HaketiloGlobalSettings

    policy_tree:   PolicyTree   = PolicyTree()
    payloads_data: PayloadsData = dc.field(default_factory=dict)

    lock: threading.RLock = dc.field(default_factory=threading.RLock)

    @contextmanager
    def cursor(self, transaction: bool = False) \
        -> t.Iterator[sqlite3.Cursor]:
        """...."""
        start_transaction = transaction and not self.connection.in_transaction

        with self.lock:
            if self.current_cursor is not None:
                yield self.current_cursor
                return

            try:
                self.current_cursor = self.connection.cursor()

                if start_transaction:
                    self.current_cursor.execute('BEGIN TRANSACTION;')

                try:
                    yield self.current_cursor

                    if start_transaction:
                        assert self.connection.in_transaction
                        self.current_cursor.execute('COMMIT TRANSACTION;')
                except:
                    if start_transaction:
                        self.current_cursor.execute('ROLLBACK TRANSACTION;')
                    raise
            finally:
                self.current_cursor = None

    def rebuild_structures(self) -> None:
        """
        Recreation of data structures as done after every recomputation of
        dependencies as well as at startup.
        """
        with self.cursor(transaction=True) as cursor:
            cursor.execute(
                '''
                SELECT
                        p.payload_id, p.pattern, p.eval_allowed,
                                p.cors_bypass_allowed,
                        ms.enabled,
                        i.identifier
                FROM
                             payloads         AS p
                        JOIN item_versions    AS iv
                                ON p.mapping_item_id = iv.item_version_id
                        JOIN items            AS i  USING (item_id)
                        JOIN mapping_statuses AS ms USING (item_id);
                '''
            )

        rows = cursor.fetchall()

        new_policy_tree = PolicyTree()

        ui_factory = policies.WebUIPolicyFactory(builtin=True)
        web_ui_pattern = 'http*://hkt.mitm.it/***'
        for parsed_pattern in url_patterns.parse_pattern(web_ui_pattern):
            new_policy_tree = new_policy_tree.register(
                parsed_pattern,
                ui_factory
            )

        new_payloads_data: dict[st.PayloadRef, st.PayloadData] = {}

        for row in rows:
            (payload_id_int, pattern, eval_allowed, cors_bypass_allowed,
             enabled_status,
             identifier) = row

            payload_ref = ConcretePayloadRef(str(payload_id_int), self)

            previous_data = self.payloads_data.get(payload_ref)
            if previous_data is not None:
                token = previous_data.unique_token
            else:
                token = secrets.token_urlsafe(8)

            payload_key = st.PayloadKey(payload_ref, identifier)

            for parsed_pattern in url_patterns.parse_pattern(pattern):
                new_policy_tree = register_payload(
                    new_policy_tree,
                    parsed_pattern,
                    payload_key,
                    token
                )

                pattern_path_segments = parsed_pattern.path_segments

            payload_data = st.PayloadData(
                payload_ref           = payload_ref,
                explicitly_enabled    = enabled_status == 'E',
                unique_token          = token,
                pattern_path_segments = pattern_path_segments,
                eval_allowed          = eval_allowed,
                cors_bypass_allowed   = cors_bypass_allowed
            )

            new_payloads_data[payload_ref] = payload_data

        self.policy_tree   = new_policy_tree
        self.payloads_data = new_payloads_data

    @abstractmethod
    def recompute_dependencies(
            self,
            requirements: t.Iterable[sds.MappingRequirement] = []
    ) -> None:
        """...."""
        ...