Fixes 4969 - Add parsing of filters

tests/test_parser.py

 # This file is part of Adblock Plus <https://adblockplus.org/>,
-# Copyright (C) 2006-2017 eyeo GmbH
+# Copyright (C) 2006-present eyeo GmbH
 #
 # Adblock Plus is free software: you can redistribute it and/or modify
 # it under the terms of the GNU General Public License version 3 as
 # published by the Free Software Foundation.
 #
 # Adblock Plus 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 Adblock Plus.  If not, see <http://www.gnu.org/licenses/>.
 
 from __future__ import unicode_literals
 
 import pytest
 
-from abp.filters import parse_line, parse_filterlist
-from abp.filters.parser import InvalidLine, Comment, Metadata, ParseError
+from abp.filters import (
+    parse_line, parse_filterlist, ParseError,
+    SELECTOR_TYPE as ST, FILTER_ACTION as FA, FILTER_OPTION as OPT,
+)
+from abp.filters.parser import Comment, Metadata
 
 
 def test_parse_empty():
     line = parse_line('    ')
     assert line.type == 'emptyline'
 
 
 @pytest.mark.parametrize('filter_text, expected', {
-    '||example.com/banner.gif$image,~match-case,domain=abc.com|~def.org': {
+    # Blocking filters with patterns and regexps and blocking exceptions.
+    '*asdf*d**dd*': {
+        'selector': {'type': ST.URL_PATTERN, 'value': '*asdf*d**dd*'},
+        'action': FA.BLOCK,
+    },
+    '@@|*asd|f*d**dd*|': {
+        'selector': {'type': ST.URL_PATTERN, 'value': '|*asd|f*d**dd*|'},
+        'action': FA.ALLOW,
+    },
+    '/ddd|f?a[s]d/': {
+        'selector': {'type': ST.URL_REGEXP, 'value': 'ddd|f?a[s]d'},
+        'action': FA.BLOCK,
+    },
+    '@@/ddd|f?a[s]d/': {
+        'selector': {'type': ST.URL_REGEXP, 'value': 'ddd|f?a[s]d'},
+        'action': FA.ALLOW,
+    },
+    # Blocking filters with some options.
+    'bla$match-case,~script,domain=foo.com|~bar.com,sitekey=foo': {
+        'selector': {'type': ST.URL_PATTERN, 'value': 'bla'},
+        'action': FA.BLOCK,
+        'options': [
+            (OPT.MATCH_CASE, True),
+            (OPT.SCRIPT, False),
+            (OPT.DOMAIN, [('foo.com', True), ('bar.com', False)]),
+            (OPT.SITEKEY, ['foo']),
+        ],
+    },
+    '@@http://bla$~script,~other,sitekey=foo|bar': {
+        'selector': {'type': ST.URL_PATTERN, 'value': 'http://bla'},
+        'action': FA.ALLOW,
+        'options': [
+            (OPT.SCRIPT, False),
+            (OPT.OTHER, False),
+            (OPT.SITEKEY, ['foo', 'bar']),
+        ],
+    },
+    # Element hiding filters and exceptions.
+    '##ddd': {
+        'selector': {'type': ST.CSS, 'value': 'ddd'},
+        'action': FA.HIDE,
+        'options': [],
+    },
+    '#@#body > div:first-child': {
+        'selector': {'type': ST.CSS, 'value': 'body > div:first-child'},
+        'action': FA.SHOW,
+        'options': [],
+    },
+    'foo,~bar##ddd': {
+        'options': [(OPT.DOMAIN, [('foo', True), ('bar', False)])],
+    },
+    # Element hiding emulation filters (extended CSS).
+    'foo,~bar#?#:-abp-properties(abc)': {
+        'selector': {'type': ST.XCSS, 'value': ':-abp-properties(abc)'},
+        'action': FA.HIDE,
+        'options': [(OPT.DOMAIN, [('foo', True), ('bar', False)])],
+    },
+    'foo.com#?#aaa :-abp-properties(abc) bbb': {
         'selector': {
-            'type': 'url-pattern',
-            'value': '||example.com/banner.gif',
-        },
-        'action': 'block',
-        'options': {
-            'match-case': False,
-            'types-none': True,
-            'types-include': ['image'],
-            'domains-none': True,
-            'domains-include': ['abc.com'],
-            'domains-exclude': ['def.org'],
+            'type': ST.XCSS,
+            'value': 'aaa :-abp-properties(abc) bbb'
         },
     },
-    '/ab?c\\.com/$image': {
-        'selector': {'type': 'url-regexp', 'value': 'ab?c\\.com'},
-        'action': 'block',
-        'options': {
-            'types-none': True,
-            'types-include': ['image'],
+    '#?#:-abp-properties(|background-image: url(data:*))': {
+        'selector': {
+            'type': ST.XCSS,
+            'value': ':-abp-properties(|background-image: url(data:*))'
         },
-    },
-    'abc$~image': {
-        'selector': {'type': 'url-pattern', 'value': 'abc'},
-        'action': 'block',
-        'options': {
-            'types-exclude': ['image'],
-        },
-    },
-    '@@||example.com/good.gif': {
-        'selector': {'type': 'url-pattern', 'value': '||example.com/good.gif'},
-        'action': 'allow',
-        'options': {},
-    },
-    '@@/ab?c\\.com/': {
-        'selector': {'type': 'url-regexp', 'value': 'ab?c\\.com'},
-        'action': 'allow',
-        'options': {},
-    },
-    'abc.com,cdf.com##div#ad1': {
-        'selector': {'type': 'css', 'value': 'div#ad1'},
-        'action': 'hide',
-        'options': {
-            'domains-none': True,
-            'domains-include': ['abc.com', 'cdf.com'],
-        },
-    },
-    '#@#div#ad1': {
-        'selector': {'type': 'css', 'value': 'div#ad1'},
-        'action': 'show',
-        'options': {},
-    },
-    'abc.com,~cdf.abc.com#@##ad1': {
-        'selector': {'type': 'css', 'value': '#ad1'},
-        'action': 'show',
-        'options': {
-            'domains-none': True,
-            'domains-include': ['abc.com'],
-            'domains-exclude': ['cdf.abc.com'],
-        },
-    },
-    # Exception with a site key.
-    '@@||abc.com/ad?$subdocument,sitekey=foo': {
-        'selector': {'type': 'url-pattern', 'value': '||abc.com/ad?'},
-        'action': 'allow',
-        'options': {
-            'types-none': True,
-            'types-include': ['subdocument'],
-            'sitekeys': ['foo']
-        },
-    },
-    # Element hiding filter using old (a.k.a. simple) syntax.
-    'abc.com#div(foo)(name=bar)(value=baz)': {
-        'selector': {
-            'type': 'abp-simple',
-            'value': 'div(foo)(name=bar)(value=baz)',
-        },
-        'action': 'hide',
-        'options': {
-            'domains-none': True,
-            'domains-include': ['abc.com'],
-        },
-    },
-    # Exclude all types with "x|~x" trick.
-    'x$image,~image': {'options': {'types-none': True}},
-    # More tricky combos of type flags.
-    'x$~image,image': {'options': {}},
-    'x$~image,image,~image': {'options': {'types-exclude': ['image']}},
-    'x$image,~image,image': {
-        'options': {'types-none': True, 'types-include': ['image']},
+        'options': [],
     },
 }.items())
 def test_parse_filters(filter_text, expected):
     """Parametric test for filter parsing"""
     parsed = parse_line(filter_text)
     assert parsed.type == 'filter'
     assert parsed.text == filter_text
     for attribute, expected_value in expected.items():
         assert getattr(parsed, attribute) == expected_value
 
@@ skipping 36 matching lines @@
 def test_parse_bad_header():
     with pytest.raises(ParseError):
         parse_line('[Adblock 1.1]')
 
 
 def test_parse_filterlist():
     result = parse_filterlist(['! foo', '! Title: bar'])
     assert list(result) == [Comment('foo'), Metadata('Title', 'bar')]
 
 
-def test_invalid_lines():
-    result = parse_filterlist([
-        '[Bad header]',
-        '! Good comment',
-        '%Bad instruction%',
-    ])
-    assert list(result) == [
-        InvalidLine('[Bad header]', 'Malformed header'),
-        Comment('Good comment'),
-        InvalidLine('%Bad instruction%', 'Unrecognized instruction'),
-    ]
+def test_exception_timing():
+    result = parse_filterlist(['! good line', '%bad line%'])
+    assert next(result) == Comment('good line')
+    with pytest.raises(ParseError):
+        next(result)