Left: | ||
Right: |
OLD | NEW |
---|---|
1 # This file is part of the Adblock Plus web scripts, | 1 # This file is part of the Adblock Plus web scripts, |
2 # Copyright (C) 2006-2017 eyeo GmbH | 2 # Copyright (C) 2006-2017 eyeo GmbH |
3 # | 3 # |
4 # Adblock Plus is free software: you can redistribute it and/or modify | 4 # Adblock Plus is free software: you can redistribute it and/or modify |
5 # it under the terms of the GNU General Public License version 3 as | 5 # it under the terms of the GNU General Public License version 3 as |
6 # published by the Free Software Foundation. | 6 # published by the Free Software Foundation. |
7 # | 7 # |
8 # Adblock Plus is distributed in the hope that it will be useful, | 8 # Adblock Plus is distributed in the hope that it will be useful, |
9 # but WITHOUT ANY WARRANTY; without even the implied warranty of | 9 # but WITHOUT ANY WARRANTY; without even the implied warranty of |
10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | 10 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
11 # GNU General Public License for more details. | 11 # GNU General Public License for more details. |
12 # | 12 # |
13 # You should have received a copy of the GNU General Public License | 13 # You should have received a copy of the GNU General Public License |
14 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. | 14 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>. |
15 | 15 |
16 from __future__ import unicode_literals | 16 from __future__ import unicode_literals |
17 | 17 |
18 import os | 18 import os |
19 import HTMLParser | 19 import HTMLParser |
20 import re | 20 import re |
21 import urlparse | 21 import urlparse |
22 import json | |
23 import collections | |
22 | 24 |
23 import jinja2 | 25 import jinja2 |
24 import markdown | 26 import markdown |
25 | 27 |
26 | 28 |
27 # Monkey-patch Markdown's isBlockLevel function to ensure that no paragraphs | 29 # Monkey-patch Markdown's isBlockLevel function to ensure that no paragraphs |
28 # are inserted into the <head> tag | 30 # are inserted into the <head> tag |
29 orig_isBlockLevel = markdown.util.isBlockLevel | 31 orig_isBlockLevel = markdown.util.isBlockLevel |
30 | 32 |
31 | 33 |
(...skipping 78 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... | |
110 # the document. | 112 # the document. |
111 self._append_text(data) | 113 self._append_text(data) |
112 | 114 |
113 def handle_entityref(self, name): | 115 def handle_entityref(self, name): |
114 self._append_text(self.unescape('&{};'.format(name))) | 116 self._append_text(self.unescape('&{};'.format(name))) |
115 | 117 |
116 def handle_charref(self, name): | 118 def handle_charref(self, name): |
117 self._append_text(self.unescape('&#{};'.format(name))) | 119 self._append_text(self.unescape('&#{};'.format(name))) |
118 | 120 |
119 | 121 |
122 def parse_json(json_data, parent_key='', sep='_'): | |
Vasily Kuznetsov
2017/08/16 18:34:56
This was not very clear from the ticket, but actua
rosie
2017/08/19 01:56:34
Done.
| |
123 result = [] | |
124 for key, value in json_data.items(): | |
125 new_key = parent_key + sep + key if parent_key else key | |
126 if isinstance(value, collections.MutableMapping): | |
127 result.extend(parse_json(value, new_key, sep=sep).items()) | |
128 else: | |
129 result.append((new_key, value)) | |
130 return dict(result) | |
131 | |
132 | |
120 def parse_page_content(page, data): | 133 def parse_page_content(page, data): |
121 """Separate page content into metadata (dict) and body text (str)""" | 134 """Separate page content into metadata (dict) and body text (str)""" |
122 page_data = {'page': page} | 135 page_data = {'page': page} |
123 lines = data.splitlines(True) | 136 try: |
124 for i, line in enumerate(lines): | 137 data = data.replace('<!--', '') |
Vasily Kuznetsov
2017/08/16 18:34:56
We need to be more careful here: this line (togeth
rosie
2017/08/19 01:56:34
Done.
| |
125 if line.strip() in {'<!--', '-->'}: | 138 data = data.replace('-->', '') |
126 lines[i] = '' | 139 decoder = json.JSONDecoder() |
127 continue | 140 json_data, index = decoder.raw_decode(data) |
128 if not re.search(r'^\s*[\w\-]+\s*=', line): | 141 json_data['page'] = page |
129 break | 142 return parse_json(json_data), data[index:] |
130 name, value = line.split('=', 1) | 143 except ValueError: |
131 value = value.strip() | 144 lines = data.splitlines(True) |
132 if value.startswith('[') and value.endswith(']'): | 145 for i, line in enumerate(lines): |
133 value = [element.strip() for element in value[1:-1].split(',')] | 146 if not re.search(r'^\s*[\w\-]+\s*=', line): |
134 lines[i] = '\n' | 147 break |
135 page_data[name.strip()] = value | 148 name, value = line.split('=', 1) |
136 return page_data, ''.join(lines) | 149 value = value.strip() |
150 if value.startswith('[') and value.endswith(']'): | |
151 value = [element.strip() for element in value[1:-1].split(',')] | |
152 lines[i] = '\n' | |
153 page_data[name.strip()] = value | |
154 return page_data, ''.join(lines) | |
137 | 155 |
138 | 156 |
139 class Converter: | 157 class Converter: |
140 whitelist = {'a', 'em', 'sup', 'strong', 'code', 'span'} | 158 whitelist = {'a', 'em', 'sup', 'strong', 'code', 'span'} |
141 missing_translations = 0 | 159 missing_translations = 0 |
142 total_translations = 0 | 160 total_translations = 0 |
143 | 161 |
144 def __init__(self, params, key='pagedata'): | 162 def __init__(self, params, key='pagedata'): |
145 self._params = params | 163 self._params = params |
146 self._key = key | 164 self._key = key |
(...skipping 409 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... | |
556 stack.pop() | 574 stack.pop() |
557 stack[-1]['subitems'].append(item) | 575 stack[-1]['subitems'].append(item) |
558 stack.append(item) | 576 stack.append(item) |
559 return structured | 577 return structured |
560 | 578 |
561 converters = { | 579 converters = { |
562 'html': RawConverter, | 580 'html': RawConverter, |
563 'md': MarkdownConverter, | 581 'md': MarkdownConverter, |
564 'tmpl': TemplateConverter, | 582 'tmpl': TemplateConverter, |
565 } | 583 } |
OLD | NEW |