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
 #
 # 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, ParseError
-from abp.filters.parser import Comment, Metadata
+from abp.filters import parse_line, parse_filterlist
+from abp.filters.parser import InvalidLine, Comment, Metadata, ParseError
 
 
 def test_parse_empty():
     line = parse_line('    ')
     assert line.type == 'emptyline'
 
 
-def test_parse_filter():
-    line = parse_line('||example.com/banner.gif')
-    assert line.type == 'filter'
-    assert line.expression == '||example.com/banner.gif'
+@pytest.mark.parametrize('filter_text, expected', {
+    '||example.com/banner.gif$image,~match-case,domain=abc.com|~def.org': {
+        'selector': {
+            'type': 'url-pattern',
+            'value': '||example.com/banner.gif',
+        },
+        'action': 'block',
+        'options': {
+            'match-case': False,
+            'types-none': True,
+            'types-include': ['image'],
+            'domains-none': True,
+            'domains-include': ['abc.com'],
+            'domains-exclude': ['def.org'],
+        },
+    },
+    '/ab?c\\.com/$image': {
+        'selector': {'type': 'url-regexp', 'value': 'ab?c\\.com'},
+        'action': 'block',
+        'options': {
+            'types-none': True,
+            'types-include': ['image'],
+        },
+    },
+    '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']},
+    },
+}.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
 
 
 def test_parse_comment():
     line = parse_line('! Block foo')
     assert line.type == 'comment'
     assert line.text == 'Block foo'
 
 
 def test_parse_meta():
     line = parse_line('! Homepage  :  http://aaa.com/b')
@@ skipping 27 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_exception_timing():

[mathias, 2017/07/26 20:37:15]

This test vanishing seems unrelated as well.

[Vasily Kuznetsov, 2017/07/27 12:20:58]

`parse_filterlist` doesn't throw exceptions anymore, it now returns invalid
lines, so this test makes no sense.

You could probably say that this change is also unrelated, and it could be a
separate review.

-    result = parse_filterlist(['! good line', '%bad line%'])
-    assert next(result) == Comment('good line')
-    with pytest.raises(ParseError):
-        next(result)
+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'),
+    ]