summaryrefslogtreecommitdiff
path: root/libre/iceweasel/process-json-files.py
blob: 69264dc94171b0662f9e86e8d120ae39734afb15 (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
#! /usr/bin/python3

#    Copyright (C) 2020, 2021  grizzlyuser <grizzlyuser@protonmail.com>
#    Based on: https://gitlab.trisquel.org/trisquel/wrapage-helpers/-/blob/81881d89b2bf7d502dd14fcccdb471fec6f6b206/helpers/DATA/firefox/reprocess-search-config.py
#    Below is the notice from the original author:
#
#    Copyright (C) 2020  Ruben Rodriguez <ruben@trisquel.info>
#
#    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 2 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, write to the Free Software
#    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301 USA

import json
import sys
import time
import copy
import argparse
import pathlib
from collections import namedtuple
from jsonschema import validate

parser = argparse.ArgumentParser()
parser.add_argument(
    'MAIN_PATH',
    type=pathlib.Path,
    help='path to main application source code directory')
parser.add_argument(
    'BRANDING_PATH',
    type=pathlib.Path,
    help='path to branding source code directory')
parser.add_argument(
    '-i',
    '--indent',
    type=int,
    default=2,
    help='indent for pretty printing of output files')
arguments = parser.parse_args()

File = namedtuple('File', ['path', 'content'])


class RemoteSettings:
    DUMPS_PATH_RELATIVE = 'services/settings/dumps'
    DUMPS_PATH_ABSOLUTE = arguments.MAIN_PATH / DUMPS_PATH_RELATIVE

    _WRAPPER_NAME = 'data'

    @classmethod
    def wrap(cls, processed):
        return File(processed.path, {cls._WRAPPER_NAME: processed.content})

    @classmethod
    def unwrap(cls, parsed_jsons):
        return [File(json.path, json.content[cls._WRAPPER_NAME])
                for json in parsed_jsons]

    @classmethod
    def should_modify_collection(cls, collection):
        return True

    @classmethod
    def process_raw(cls, unwrapped_jsons, parsed_schema):
        timestamps, result = [], []
        for collection in unwrapped_jsons:
            should_modify_collection = cls.should_modify_collection(collection)
            for record in collection.content:
                if should_modify_collection:
                    if cls.should_drop_record(record):
                        continue

                    clone = copy.deepcopy(record)

                    record = cls.process_record(record)

                    if clone != record:
                        timestamp = int(round(time.time_ns() / 10 ** 6))
                        while timestamp in timestamps:
                            timestamp += 1
                        timestamps.append(timestamp)
                        record['last_modified'] = timestamp

                if parsed_schema is not None:
                    validate(record, schema=parsed_schema)

                result.append(record)

        cls.OUTPUT_PATH.parent.mkdir(parents=True, exist_ok=True)

        return File(cls.OUTPUT_PATH, result)

    @classmethod
    def process(cls, parsed_jsons, parsed_schema):
        return cls.wrap(
            cls.process_raw(
                cls.unwrap(parsed_jsons),
                parsed_schema))


class Changes(RemoteSettings):
    JSON_PATHS = tuple(RemoteSettings.DUMPS_PATH_ABSOLUTE.glob('*/*.json'))
    OUTPUT_PATH = RemoteSettings.DUMPS_PATH_ABSOLUTE / 'monitor/changes.json'

    @classmethod
    def process_raw(cls, unwrapped_jsons, parsed_schema):
        changes = []

        for collection in unwrapped_jsons:
            if collection.path != RemoteSettings.DUMPS_PATH_ABSOLUTE / 'main/example.json':
                latest_change = {}
                latest_change['last_modified'] = max(
                    (record['last_modified'] for record in collection.content), default=0)
                latest_change['bucket'] = collection.path.parent.name
                latest_change['collection'] = collection.path.stem
                changes.append(latest_change)

        cls.OUTPUT_PATH.parent.mkdir(parents=True, exist_ok=True)

        return File(cls.OUTPUT_PATH, changes)


class SearchConfig(RemoteSettings):
    JSON_PATHS = (
        RemoteSettings.DUMPS_PATH_ABSOLUTE /
        'main/search-config.json',
    )
    SCHEMA_PATH = arguments.MAIN_PATH / \
        'toolkit/components/search/schema/search-engine-config-schema.json'
    OUTPUT_PATH = JSON_PATHS[0]

    _DUCKDUCKGO_SEARCH_ENGINE_ID = 'ddg@search.mozilla.org'

    @classmethod
    def should_drop_record(cls, search_engine):
        return search_engine['webExtension']['id'] not in (
            cls._DUCKDUCKGO_SEARCH_ENGINE_ID, 'wikipedia@search.mozilla.org')

    @classmethod
    def process_record(cls, search_engine):
        [search_engine.pop(key, None)
         for key in ['extraParams', 'telemetryId']]

        general_specifier = {}
        for specifier in search_engine['appliesTo'].copy():
            if 'application' in specifier:
                if 'distributions' in specifier['application']:
                    search_engine['appliesTo'].remove(specifier)
                    continue
                specifier['application'].pop('extraParams', None)

            if 'included' in specifier and 'everywhere' in specifier[
                    'included'] and specifier['included']['everywhere']:
                general_specifier = specifier

        if not general_specifier:
            general_specifier = {'included': {'everywhere': True}}
            search_engine['appliesTo'].insert(0, general_specifier)
        if search_engine['webExtension']['id'] == cls._DUCKDUCKGO_SEARCH_ENGINE_ID:
            general_specifier['default'] = 'yes'

        return search_engine


class TippyTopSites:
    JSON_PATHS = (
        arguments.MAIN_PATH /
        'browser/components/newtab/data/content/tippytop/top_sites.json',
        arguments.BRANDING_PATH /
        'tippytop/top_sites.json')

    @classmethod
    def process(cls, parsed_jsons, parsed_schema):
        tippy_top_sites_main = parsed_jsons[0]
        tippy_top_sites_branding = parsed_jsons[1]
        result = tippy_top_sites_branding.content + \
            [site for site in tippy_top_sites_main.content if 'wikipedia.org' in site['domains']]
        return File(tippy_top_sites_main.path, result)


class TopSites(RemoteSettings):
    _TOP_SITES_JSON_PATH = 'main/top-sites.json'
    _TOP_SITES_PATH_MAIN = RemoteSettings.DUMPS_PATH_ABSOLUTE / _TOP_SITES_JSON_PATH

    JSON_PATHS = (
        arguments.BRANDING_PATH /
        RemoteSettings.DUMPS_PATH_RELATIVE /
        _TOP_SITES_JSON_PATH,
        _TOP_SITES_PATH_MAIN)
    OUTPUT_PATH = _TOP_SITES_PATH_MAIN

    @classmethod
    def should_modify_collection(cls, collection):
        return cls._TOP_SITES_PATH_MAIN == collection.path

    @classmethod
    def should_drop_record(cls, site):
        return site['url'] != 'https://www.wikipedia.org/'

    @classmethod
    def process_record(cls, site):
        site.pop('exclude_regions', None)
        return site


# To reflect the latest timestamps, Changes class should always come after
# all other RemoteSettings subclasses
processors = (TippyTopSites, SearchConfig, TopSites, Changes)

for processor in processors:
    parsed_jsons = []
    for json_path in processor.JSON_PATHS:
        with json_path.open() as file:
            parsed_jsons.append(File(json_path, json.load(file)))

    parsed_schema = None
    if hasattr(processor, "SCHEMA_PATH"):
        with processor.SCHEMA_PATH.open() as file:
            parsed_schema = json.load(file)

    processed = processor.process(parsed_jsons, parsed_schema)
    with processed.path.open('w') as file:
        json.dump(processed.content, file, indent=arguments.indent)