summaryrefslogtreecommitdiff
path: root/libre/iceweasel/libre-process-json-files.py
blob: 2fdde62d4ecd5807def346b0a1cbcdad969f19dc (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
#! /usr/bin/python3

#    Copyright (C) 2020  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,
    help='indent for pretty printing of output files')
arguments = parser.parse_args()

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


class RemoteSettings:
    DUMPS_PATH = arguments.MAIN_PATH / 'services/settings/dumps'
    JSON_PATHS = tuple(DUMPS_PATH.glob('*/*.json'))
    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 process_raw(cls, unwrapped_jsons):
        changes = []
        output_path = cls.DUMPS_PATH / 'monitor/changes.json'

        for collection in unwrapped_jsons:
            if collection.path == cls.DUMPS_PATH / 'main/example.json':
                continue
            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)

        output_path.parent.mkdir(exist_ok=True)

        return File(output_path, changes)

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


class SearchConfig(RemoteSettings):
    JSON_PATHS = (RemoteSettings.DUMPS_PATH / 'main/search-config.json',)

    def _get_schema():
        PATH = arguments.MAIN_PATH / \
            'toolkit/components/search/schema/search-engine-config-schema.json'
        with PATH.open() as file:
            return json.load(file)

    @classmethod
    def process_raw(cls, unwrapped_jsons):
        _WHITELIST = ('ddg@search.mozilla.org', 'wikipedia@search.mozilla.org')
        SCHEMA = cls._get_schema()

        search_engines, timestamps = [], []
        search_config = unwrapped_jsons[0]

        for search_engine in search_config.content:
            if search_engine['webExtension']['id'] in _WHITELIST:
                clone = copy.deepcopy(search_engine)

                if 'telemetryId' in search_engine:
                    del search_engine['telemetryId']
                if 'extraParams' in search_engine:
                    del search_engine['extraParams']

                general_specifier = {}
                for specifier in search_engine['appliesTo'].copy():
                    if 'application' in specifier:
                        if 'distributions' in specifier['application']:
                            search_engine['appliesTo'].remove(specifier)
                            continue
                        if 'extraParams' in specifier['application']:
                            del specifier['application']['extraParams']

                    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'] == _WHITELIST[0]:
                    general_specifier['default'] = 'yes'

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

                validate(search_engine, schema=SCHEMA)

                search_engines.append(search_engine)

        return File(search_config.path, search_engines)


class TopSites:
    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):
        main_top_sites = parsed_jsons[0]
        branding_top_sites = parsed_jsons[1]
        result = branding_top_sites.content + \
            [site for site in main_top_sites.content if site['title'] == 'wikipedia']
        return File(main_top_sites.path, result)


processors = (SearchConfig, TopSites, RemoteSettings)

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)))

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