| OLD | NEW | 
|---|
| 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 """Parser for ABP filterlist format.""" | 16 """Parser for ABP filterlist format.""" | 
| 17 | 17 | 
| 18 from __future__ import unicode_literals | 18 from __future__ import unicode_literals | 
| 19 | 19 | 
| 20 import re | 20 import re | 
| 21 from collections import namedtuple | 21 from collections import namedtuple | 
| 22 | 22 | 
| 23 __all__ = [ | 23 __all__ = [ | 
| 24     'FILTER_ACTION', | 24     'FilterAction', | 
| 25     'FILTER_OPTION', | 25     'FilterOption', | 
| 26     'SELECTOR_TYPE', | 26     'SelectorType', | 
| 27     'ParseError', | 27     'ParseError', | 
| 28     'parse_filterlist', | 28     'parse_filterlist', | 
| 29     'parse_line', | 29     'parse_line', | 
| 30 ] | 30 ] | 
| 31 | 31 | 
| 32 | 32 | 
| 33 class ParseError(Exception): | 33 class ParseError(Exception): | 
| 34     """Exception thrown by the parser when it encounters invalid input. | 34     """Exception thrown by the parser when it encounters invalid input. | 
| 35 | 35 | 
| 36     Parameters | 36     Parameters | 
| 37     ---------- | 37     ---------- | 
| 38     error : str | 38     error : str | 
| 39         Description of the error. | 39         Description of the error. | 
| 40     text : str | 40     text : str | 
| 41         The source text that caused an error. | 41         The source text that caused an error. | 
| 42 | 42 | 
| 43     """ | 43     """ | 
| 44 | 44 | 
| 45     def __init__(self, error, text): | 45     def __init__(self, error, text): | 
| 46         Exception.__init__(self, '{} in "{}"'.format(error, text)) | 46         Exception.__init__(self, '{} in "{}"'.format(error, text)) | 
| 47         self.text = text | 47         self.text = text | 
| 48         self.error = error | 48         self.error = error | 
| 49 | 49 | 
| 50 | 50 | 
| 51 # Constants related to filters (see https://adblockplus.org/filters). | 51 # Constants related to filters (see https://adblockplus.org/filters). | 
| 52 class SELECTOR_TYPE:  # flake8: noqa (this is a namespace of constants). | 52 class SelectorType: | 
| 53     """Selector type constants.""" | 53     """Selector type constants.""" | 
| 54 | 54 | 
| 55     URL_PATTERN = 'url-pattern'  # Normal URL patterns. | 55     URL_PATTERN = 'url-pattern'  # Normal URL patterns. | 
| 56     URL_REGEXP = 'url-regexp'    # Regular expressions for URLs. | 56     URL_REGEXP = 'url-regexp'    # Regular expressions for URLs. | 
| 57     CSS = 'css'                  # CSS selectors for hiding filters. | 57     CSS = 'css'                  # CSS selectors for hiding filters. | 
| 58     XCSS = 'extended-css'        # Extended CSS selectors (to emulate CSS4). | 58     XCSS = 'extended-css'        # Extended CSS selectors (to emulate CSS4). | 
| 59     ABP_SIMPLE = 'abp-simple'    # Simplified element hiding syntax. | 59     ABP_SIMPLE = 'abp-simple'    # Simplified element hiding syntax. | 
| 60 | 60 | 
| 61 | 61 | 
| 62 class FILTER_ACTION:  # flake8: noqa (this is a namespace of constants). | 62 class FilterAction: | 
| 63     """Filter action constants.""" | 63     """Filter action constants.""" | 
| 64 | 64 | 
| 65     BLOCK = 'block'              # Block the request. | 65     BLOCK = 'block'              # Block the request. | 
| 66     ALLOW = 'allow'              # Allow the request (whitelist). | 66     ALLOW = 'allow'              # Allow the request (whitelist). | 
| 67     HIDE = 'hide'                # Hide selected element(s). | 67     HIDE = 'hide'                # Hide selected element(s). | 
| 68     SHOW = 'show'                # Show selected element(s) (whitelist). | 68     SHOW = 'show'                # Show selected element(s) (whitelist). | 
| 69 | 69 | 
| 70 | 70 | 
| 71 class FILTER_OPTION:  # flake8: noqa (this is a namespace of constants). | 71 class FilterOption: | 
| 72     """Filter option constants.""" | 72     """Filter option constants.""" | 
| 73 | 73 | 
| 74     # Resource types. | 74     # Resource types. | 
| 75     OTHER = 'other' | 75     OTHER = 'other' | 
| 76     SCRIPT = 'script' | 76     SCRIPT = 'script' | 
| 77     IMAGE = 'image' | 77     IMAGE = 'image' | 
| 78     STYLESHEET = 'stylesheet' | 78     STYLESHEET = 'stylesheet' | 
| 79     OBJECT = 'object' | 79     OBJECT = 'object' | 
| 80     SUBDOCUMENT = 'subdocument' | 80     SUBDOCUMENT = 'subdocument' | 
| 81     DOCUMENT = 'document' | 81     DOCUMENT = 'document' | 
| (...skipping 82 matching lines...) Expand 10 before | Expand all | Expand 10 after  Loading... | 
| 164         return option.split('=', 1) | 164         return option.split('=', 1) | 
| 165     if option.startswith('~'): | 165     if option.startswith('~'): | 
| 166         return option[1:], False | 166         return option[1:], False | 
| 167     return option, True | 167     return option, True | 
| 168 | 168 | 
| 169 | 169 | 
| 170 def _parse_filter_option(option): | 170 def _parse_filter_option(option): | 
| 171     name, value = _parse_option(option) | 171     name, value = _parse_option(option) | 
| 172 | 172 | 
| 173     # Handle special cases of multivalued options. | 173     # Handle special cases of multivalued options. | 
| 174     if name == FILTER_OPTION.DOMAIN: | 174     if name == FilterOption.DOMAIN: | 
| 175         value = [_parse_option(o) for o in value.split('|')] | 175         value = [_parse_option(o) for o in value.split('|')] | 
| 176     elif name == FILTER_OPTION.SITEKEY: | 176     elif name == FilterOption.SITEKEY: | 
| 177         value = value.split('|') | 177         value = value.split('|') | 
| 178 | 178 | 
| 179     return name, value | 179     return name, value | 
| 180 | 180 | 
| 181 | 181 | 
| 182 def _parse_filter_options(options): | 182 def _parse_filter_options(options): | 
| 183     return [_parse_filter_option(o) for o in options.split(',')] | 183     return [_parse_filter_option(o) for o in options.split(',')] | 
| 184 | 184 | 
| 185 | 185 | 
| 186 def _parse_blocking_filter(text): | 186 def _parse_blocking_filter(text): | 
| 187     # Based on RegExpFilter.fromText in lib/filterClasses.js | 187     # Based on RegExpFilter.fromText in lib/filterClasses.js | 
| 188     # in https://hg.adblockplus.org/adblockpluscore. | 188     # in https://hg.adblockplus.org/adblockpluscore. | 
| 189     action = FILTER_ACTION.BLOCK | 189     action = FilterAction.BLOCK | 
| 190     options = [] | 190     options = [] | 
| 191     selector = text | 191     selector = text | 
| 192 | 192 | 
| 193     if selector.startswith('@@'): | 193     if selector.startswith('@@'): | 
| 194         action = FILTER_ACTION.ALLOW | 194         action = FilterAction.ALLOW | 
| 195         selector = selector[2:] | 195         selector = selector[2:] | 
| 196 | 196 | 
| 197     if '$' in selector: | 197     if '$' in selector: | 
| 198         opt_match = FILTER_OPTIONS_REGEXP.search(selector) | 198         opt_match = FILTER_OPTIONS_REGEXP.search(selector) | 
| 199         if opt_match: | 199         if opt_match: | 
| 200             selector = selector[:opt_match.start(0)] | 200             selector = selector[:opt_match.start(0)] | 
| 201             options = _parse_filter_options(opt_match.group(1)) | 201             options = _parse_filter_options(opt_match.group(1)) | 
| 202 | 202 | 
| 203     if (len(selector) > 1 | 203     if (len(selector) > 1 | 
| 204             and selector.startswith('/') and selector.endswith('/')): | 204             and selector.startswith('/') and selector.endswith('/')): | 
| 205         selector = {'type': SELECTOR_TYPE.URL_REGEXP, 'value': selector[1:-1]} | 205         selector = {'type': SelectorType.URL_REGEXP, 'value': selector[1:-1]} | 
| 206     else: | 206     else: | 
| 207         selector = {'type': SELECTOR_TYPE.URL_PATTERN, 'value': selector} | 207         selector = {'type': SelectorType.URL_PATTERN, 'value': selector} | 
| 208 | 208 | 
| 209     return Filter(text, selector, action, options) | 209     return Filter(text, selector, action, options) | 
| 210 | 210 | 
| 211 | 211 | 
| 212 def _parse_hiding_filter(text, domain, type_flag, selector_value): | 212 def _parse_hiding_filter(text, domain, type_flag, selector_value): | 
| 213     selector = {'type': SELECTOR_TYPE.CSS, 'value': selector_value} | 213     selector = {'type': SelectorType.CSS, 'value': selector_value} | 
| 214     action = FILTER_ACTION.HIDE | 214     action = FilterAction.HIDE | 
| 215     options = [] | 215     options = [] | 
| 216 | 216 | 
| 217     if type_flag == '@': | 217     if type_flag == '@': | 
| 218         action = FILTER_ACTION.SHOW | 218         action = FilterAction.SHOW | 
| 219     elif type_flag == '?': | 219     elif type_flag == '?': | 
| 220         selector['type'] = SELECTOR_TYPE.XCSS | 220         selector['type'] = SelectorType.XCSS | 
| 221 | 221 | 
| 222     if domain: | 222     if domain: | 
| 223         domains = [_parse_option(d) for d in domain.split(',')] | 223         domains = [_parse_option(d) for d in domain.split(',')] | 
| 224         options.append((FILTER_OPTION.DOMAIN, domains)) | 224         options.append((FilterOption.DOMAIN, domains)) | 
| 225 | 225 | 
| 226     return Filter(text, selector, action, options) | 226     return Filter(text, selector, action, options) | 
| 227 | 227 | 
| 228 | 228 | 
| 229 def parse_filter(text): | 229 def parse_filter(text): | 
| 230     """Parse one filter. | 230     """Parse one filter. | 
| 231 | 231 | 
| 232     Parameters | 232     Parameters | 
| 233     ---------- | 233     ---------- | 
| 234     text : str | 234     text : str | 
| (...skipping 103 matching lines...) Expand 10 before | Expand all | Expand 10 after  Loading... | 
| 338     for line in lines: | 338     for line in lines: | 
| 339         parsed_line = parse_line(line, position) | 339         parsed_line = parse_line(line, position) | 
| 340         yield parsed_line | 340         yield parsed_line | 
| 341 | 341 | 
| 342         if position != 'body' and parsed_line.type in {'header', 'metadata'}: | 342         if position != 'body' and parsed_line.type in {'header', 'metadata'}: | 
| 343             # Continue parsing metadata until it's over... | 343             # Continue parsing metadata until it's over... | 
| 344             position = 'metadata' | 344             position = 'metadata' | 
| 345         else: | 345         else: | 
| 346             # ...then switch to parsing the body. | 346             # ...then switch to parsing the body. | 
| 347             position = 'body' | 347             position = 'body' | 
| OLD | NEW | 
|---|