Rietveld Code Review Tool
Help | Bug tracker | Discussion group | Source code

Side by Side Diff: abp/filters/renderer.py

Issue 29845767: Issue 6685 - Offer incremental filter list downloads (Closed) Base URL: https://hg.adblockplus.org/python-abp/
Patch Set: Store metadata in a dict Created Aug. 29, 2018, 10:51 p.m.
Left:
Right:
Use n/p to move between diff chunks; N/P to move between comments.
Jump to:
View unified diff | Download patch
OLDNEW
1 # This file is part of Adblock Plus <https://adblockplus.org/>, 1 # This file is part of Adblock Plus <https://adblockplus.org/>,
2 # Copyright (C) 2006-present eyeo GmbH 2 # Copyright (C) 2006-present 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 """Combine filter list fragments to produce filter lists.""" 16 """Combine filter list fragments to produce filter lists."""
17 17
18 from __future__ import unicode_literals 18 from __future__ import unicode_literals
19 19
20 import itertools 20 import itertools
21 import logging 21 import logging
22 import time 22 import time
23 23
24 from .parser import parse_filterlist, Comment, Metadata 24 from .parser import parse_filterlist, Comment, Metadata
25 from .sources import NotFound 25 from .sources import NotFound
26 26
27 __all__ = ['IncludeError', 'MissingHeader', 'render_filterlist'] 27 __all__ = ['IncludeError', 'MissingHeader', 'render_filterlist', 'render_diff']
28 28
29 _logger = logging.getLogger(__name__) 29 _logger = logging.getLogger(__name__)
30 30
31 31
32 class IncludeError(Exception): 32 class IncludeError(Exception):
33 """Error in processing include instruction.""" 33 """Error in processing include instruction."""
34 34
35 def __init__(self, error, stack): 35 def __init__(self, error, stack):
36 stack_str = ' from '.join(map("'{}'".format, reversed(stack))) 36 stack_str = ' from '.join(map("'{}'".format, reversed(stack)))
37 if stack_str: 37 if stack_str:
(...skipping 79 matching lines...) Expand 10 before | Expand all | Expand 10 after
117 """Insert metadata comment with version (a.k.a. date).""" 117 """Insert metadata comment with version (a.k.a. date)."""
118 first_line, rest = _first_and_rest(lines) 118 first_line, rest = _first_and_rest(lines)
119 version = Metadata('Version', time.strftime('%Y%m%d%H%M', time.gmtime())) 119 version = Metadata('Version', time.strftime('%Y%m%d%H%M', time.gmtime()))
120 return itertools.chain([first_line, version], rest) 120 return itertools.chain([first_line, version], rest)
121 121
122 122
123 def _remove_duplicates(lines): 123 def _remove_duplicates(lines):
124 """Remove duplicate metadata and headers.""" 124 """Remove duplicate metadata and headers."""
125 # Always remove checksum -- a checksum coming from a fragment 125 # Always remove checksum -- a checksum coming from a fragment
126 # will not match for the rendered list. 126 # will not match for the rendered list.
127 seen = {'Checksum'} 127 seen = {'checksum'}
128 for i, line in enumerate(lines): 128 for i, line in enumerate(lines):
129 if line.type == 'metadata': 129 if line.type == 'metadata':
130 if line.key not in seen: 130 key = line.key.lower()
131 seen.add(line.key) 131 if key not in seen:
132 seen.add(key)
132 yield line 133 yield line
133 elif line.type == 'header': 134 elif line.type == 'header':
134 if i == 0: 135 if i == 0:
135 yield line 136 yield line
136 else: 137 else:
137 yield line 138 yield line
138 139
139 140
140 def _validate(lines): 141 def _validate(lines):
141 """Validate the final list.""" 142 """Validate the final list."""
(...skipping 31 matching lines...) Expand 10 before | Expand all | Expand 10 after
173 lead to rendering an invalid filter list, so we immediately abort. 174 lead to rendering an invalid filter list, so we immediately abort.
174 175
175 """ 176 """
176 _logger.info('Rendering: %s', name) 177 _logger.info('Rendering: %s', name)
177 lines, default_source = _get_and_parse_fragment(name, sources, top_source) 178 lines, default_source = _get_and_parse_fragment(name, sources, top_source)
178 lines = _process_includes(sources, default_source, [name], lines) 179 lines = _process_includes(sources, default_source, [name], lines)
179 for proc in [_process_timestamps, _insert_version, _remove_duplicates, 180 for proc in [_process_timestamps, _insert_version, _remove_duplicates,
180 _validate]: 181 _validate]:
181 lines = proc(lines) 182 lines = proc(lines)
182 return lines 183 return lines
184
185
186 def _split_list_for_diff(list_in):
187 """Split a filter list into metadata, keys, and rules."""
188 metadata = {}
189 rules = set()
190 for line in parse_filterlist(list_in):
191 if line.type == 'metadata':
192 metadata[line.key.lower()] = line
193 elif line.type == 'filter':
194 rules.add(line.to_string())
195 return metadata, rules
196
197
198 def render_diff(base, latest):
199 """Return a diff between two filter lists.
200
201 Parameters
202 ----------
203 base : iterator of str
204 The base (old) list that we want to update to latest.
205 lastest : iterator of str
206 The latest (most recent) list that we want to update to.
207
208 Returns
209 -------
210 iterable of str
211 A diff between two lists (https://issues.adblockplus.org/ticket/6685)
212
213 """
214 latest_md, latest_rules = _split_list_for_diff(latest)
215 base_md, base_rules = _split_list_for_diff(base)
Sebastian Noack 2018/08/29 23:46:26 Nit: Is it necessary to abbreviate metadata to md
rhowell 2018/08/30 16:23:30 Done.
216 add_fl = latest_rules - base_rules
Sebastian Noack 2018/08/29 23:46:25 Nit: These expressions could be inlined below. Thi
rhowell 2018/08/30 16:23:30 Done.
217 remove_fl = base_rules - latest_rules
218
219 yield '[Adblock Plus Diff]'
220 for key, latest in latest_md.items():
221 base = base_md.get(key)
222 if not base or base.value != latest.value:
223 yield latest.to_string()
224 for key in set(base_md) - set(latest_md):
225 yield '! {}:'.format(base_md[key].key)
226 for item in remove_fl:
227 yield '- {}'.format(item)
228 for item in add_fl:
229 yield '+ {}'.format(item)
OLDNEW
« no previous file with comments | « abp/filters/parser.py ('k') | tests/test_differ.py » ('j') | tests/test_differ.py » ('J')

Powered by Google App Engine
This is Rietveld