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 """ | 16 """ |
17 Functions for integrating with rPython. | 17 Functions for integrating with rPython. |
18 | 18 |
19 see: https://cran.r-project.org/web/packages/rPython/index.html | 19 see: https://cran.r-project.org/web/packages/rPython/index.html |
20 """ | 20 """ |
21 | 21 |
22 from __future__ import unicode_literals | |
23 | |
24 from abp.filters import parse_line | 22 from abp.filters import parse_line |
25 | 23 |
26 __all__ = ['line2dict'] | 24 __all__ = ['line2dict'] |
27 | 25 |
28 | 26 |
29 def option_list_to_dict(options): | 27 def option_list_to_dict(options): |
30 """Recursively parse filter options into dicts. | 28 """Recursively parse filter options into dicts. |
31 | 29 |
32 Parameters | 30 Parameters |
33 ---------- | 31 ---------- |
(...skipping 29 matching lines...) Expand all Loading... |
63 """ | 61 """ |
64 result = dict(data._asdict()) | 62 result = dict(data._asdict()) |
65 if 'options' in result: | 63 if 'options' in result: |
66 result['options'] = option_list_to_dict(result['options']) | 64 result['options'] = option_list_to_dict(result['options']) |
67 | 65 |
68 result['type'] = data.__class__.__name__ | 66 result['type'] = data.__class__.__name__ |
69 | 67 |
70 return result | 68 return result |
71 | 69 |
72 | 70 |
73 def strings2utf8(data): | |
74 """Convert strings in a data structure to utf8 byte strings. | |
75 | |
76 Parameters | |
77 ---------- | |
78 data: dict | |
79 The data to convert. Can include nested dicts, lists and tuples. | |
80 | |
81 Returns | |
82 ------- | |
83 dict | |
84 With all strings encoded as unicode. | |
85 | |
86 """ | |
87 if isinstance(data, dict): | |
88 return {strings2utf8(k): strings2utf8(v) for k, v in data.items()} | |
89 if isinstance(data, list): | |
90 return [strings2utf8(v) for v in data] | |
91 if isinstance(data, type('')): | |
92 # The condition is a Python 2/3 way of saying "unicode string". | |
93 return data.encode('utf-8') | |
94 return data | |
95 | |
96 | |
97 def line2dict(text, mode='body'): | 71 def line2dict(text, mode='body'): |
98 """Convert a filterlist line to a dictionary. | 72 """Convert a filterlist line to a dictionary. |
99 | 73 |
100 All strings in the output dictionary will be UTF8 byte strings. This is | 74 All strings in the output dictionary will be UTF8 byte strings. This is |
101 necessary to prevent unicode encoding errors in rPython conversion layer. | 75 necessary to prevent unicode encoding errors in rPython conversion layer. |
102 | 76 |
103 Parameters | 77 Parameters |
104 ---------- | 78 ---------- |
105 text: str | 79 text: str |
106 The filter text we want to parse | 80 The filter text we want to parse |
107 mode: str | 81 mode: str |
108 Parsing mode (see `abp.filters.parser.parse_line`). | 82 Parsing mode (see `abp.filters.parser.parse_line`). |
109 | 83 |
110 Returns | 84 Returns |
111 ------- | 85 ------- |
112 dict | 86 dict |
113 With the parsing results and all strings converted to utf8 byte | 87 With the parsing results and all strings converted to utf8 byte |
114 strings. | 88 strings. |
115 | 89 |
116 """ | 90 """ |
117 return strings2utf8(tuple2dict(parse_line(text, mode))) | 91 return tuple2dict(parse_line(text, mode)) |
118 | 92 |
119 | 93 |
120 def lines2dicts(string_list, mode='body'): | 94 def lines2dicts(string_list, mode='body'): |
121 """Convert a list of filterlist strings to a dictionary. | 95 """Convert a list of filterlist strings to a dictionary. |
122 | 96 |
123 All strings in the output dictionary will be UTF8 byte strings. This is | 97 All strings in the output dictionary will be UTF8 byte strings. This is |
124 necessary to prevent unicode encoding errors in rPython conversion layer. | 98 necessary to prevent unicode encoding errors in rPython conversion layer. |
125 | 99 |
126 Parameters | 100 Parameters |
127 ---------- | 101 ---------- |
128 string_list: iterable of str | 102 string_list: iterable of str |
129 Each string in the list can be an empty line, include instruction, or | 103 Each string in the list can be an empty line, include instruction, or |
130 filter. If the mode is 'start', headers and metadata can also be | 104 filter. If the mode is 'start', headers and metadata can also be |
131 parsed. | 105 parsed. |
132 mode: str | 106 mode: str |
133 Parsing mode (see `abp.filters.parser.parse_line`). | 107 Parsing mode (see `abp.filters.parser.parse_line`). |
134 | 108 |
135 Returns | 109 Returns |
136 ------- | 110 ------- |
137 list of dict | 111 list of dict |
138 With the parsing results and all strings converted to utf8 byte | 112 With the parsing results and all strings converted to utf8 byte |
139 strings. | 113 strings. |
140 | 114 |
141 """ | 115 """ |
142 result = [] | 116 result = [] |
143 for string in string_list: | 117 for string in string_list: |
144 result.append(line2dict(string, mode)) | 118 result.append(line2dict(string, mode)) |
145 return result | 119 return result |
OLD | NEW |