Left: | ||
Right: |
OLD | NEW |
---|---|
1 # This file is part of the Adblock Plus web scripts, | 1 # This file is part of the Adblock Plus web scripts, |
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 from __future__ import print_function | |
17 | |
18 import os | |
16 import mimetypes | 19 import mimetypes |
17 import os | 20 from argparse import ArgumentParser |
Vasily Kuznetsov
2018/10/22 14:36:47
In some cases we get easier to follow code by impo
Tudor Avram
2018/10/22 17:29:38
Well, basically the idea was to make the entire th
Vasily Kuznetsov
2018/10/23 10:16:14
I see. Well, at the moment there's no standard abo
Tudor Avram
2018/10/23 16:44:33
I guess it's more important to make it obvious whe
| |
18 import sys | |
19 import argparse | |
20 | 21 |
21 import jinja2 | 22 import jinja2 |
22 | 23 |
24 from cms.converters import converters | |
23 from cms.utils import process_page | 25 from cms.utils import process_page |
24 from cms.sources import create_source | 26 from cms.sources import create_source |
25 from cms.converters import converters | |
26 | |
27 source = None | |
28 address = None | |
29 port = None | |
30 | 27 |
31 UNICODE_ENCODING = 'utf-8' | 28 UNICODE_ENCODING = 'utf-8' |
32 | 29 |
33 ERROR_TEMPLATE = ''' | 30 ERROR_TEMPLATE = ''' |
34 <html> | 31 <html> |
35 <head> | 32 <head> |
36 <title>{{status}}</title> | 33 <title>{{status}}</title> |
37 </head> | 34 </head> |
38 <body> | 35 <body> |
39 <h1>{{status}}</h1> | 36 <h1>{{status}}</h1> |
40 {% set code = status.split()|first|int %} | 37 {% set code = status.split()|first|int %} |
41 {% if code == 404 %} | 38 {% if code == 404 %} |
42 <p>No page found for the address {{uri}}.</p> | 39 <p>No page found for the address {{uri}}.</p> |
43 {% elif code == 500 %} | 40 {% elif code == 500 %} |
44 <p>An error occurred while processing the request for {{uri}}:</p> | 41 <p>An error occurred while processing the request for {{uri}}:</p> |
45 <pre>{{error}}</pre> | 42 <pre>{{error}}</pre> |
46 {% endif %} | 43 {% endif %} |
47 </body> | 44 </body> |
48 </html>''' | 45 </html>''' |
49 | 46 |
50 # Initilize the mimetypes modules manually for consistent behavior, | 47 # Initialize the mimetypes modules manually for consistent behavior, |
51 # ignoring local files and Windows Registry. | 48 # ignoring local files and Windows Registry. |
52 mimetypes.init([]) | 49 mimetypes.init([]) |
53 | 50 |
54 | 51 |
55 def get_page(path): | 52 class DynamicServerHandler: |
56 path = path.strip('/') | 53 """General-purpose WSGI server handler that generates pages on request. |
57 if path == '': | 54 |
58 path = source.read_config().get('general', 'defaultlocale') | 55 Parameters |
59 if '/' in path: | 56 ---------- |
60 locale, page = path.split('/', 1) | 57 host: str |
61 else: | 58 The host where the server will run. |
62 locale, page = path, '' | 59 port: int |
63 | 60 The TCP port the server will run on. |
64 default_page = source.read_config().get('general', 'defaultpage') | 61 source_dir: str |
65 alternative_page = '/'.join([page, default_page]).lstrip('/') | 62 The path to the website contents. |
66 | 63 |
67 for format in converters.iterkeys(): | 64 """ |
68 for p in (page, alternative_page): | 65 |
69 if source.has_page(p, format): | 66 def __init__(self, host, port, source_dir): |
70 site_url = 'http://{}:{}'.format(address, port) | 67 self.host = host |
71 return (p, process_page(source, locale, p, format, site_url)) | 68 self.port = port |
72 if source.has_localizable_file(locale, page): | 69 self.source = create_source(source_dir) |
73 return (page, source.read_localizable_file(locale, page)) | 70 self.full_url = 'http://{0}:{1}'.format(host, port) |
74 | 71 |
75 return (None, None) | 72 def _get_data(self, path): |
76 | 73 """Read the data corresponding to a website path. |
77 | 74 |
78 def has_conflicting_pages(page): | 75 Parameters |
79 pages = [p for p, _ in source.list_pages()] | 76 ---------- |
80 pages.extend(source.list_localizable_files()) | 77 path: str |
81 | 78 The path to the page to get the data for. |
82 if pages.count(page) > 1: | 79 |
83 return True | 80 Returns |
84 if any(p.startswith(page + '/') or page.startswith(p + '/') for p in pages): | 81 ------- |
85 return True | 82 str/ bytes |
Vasily Kuznetsov
2018/10/22 14:36:46
Numpy docstring standard [1], that we use here see
Tudor Avram
2018/10/23 16:44:32
Done.
| |
86 return False | 83 The data corresponding to the path we're trying to access. |
87 | 84 |
88 | 85 """ |
89 def get_data(path): | 86 if self.source.has_static(path): |
90 if source.has_static(path): | 87 return self.source.read_static(path) |
91 return source.read_static(path) | 88 |
92 | 89 page, data = self._get_page(path) |
93 page, data = get_page(path) | 90 |
94 if page and has_conflicting_pages(page): | 91 if page and self._has_conflicts(page): |
95 raise Exception('The requested page conflicts with another page') | 92 raise Exception('The requested page conflicts with another page.') |
96 return data | 93 |
97 | 94 return data |
98 | 95 |
99 def show_error(start_response, status, **kwargs): | 96 def _get_page(self, path): |
100 env = jinja2.Environment(autoescape=True) | 97 """Construct a page and return its contents. |
101 template = env.from_string(ERROR_TEMPLATE) | 98 |
102 mime = 'text/html; encoding=%s' % UNICODE_ENCODING | 99 Parameters |
103 start_response(status, [('Content-Type', mime)]) | 100 ---------- |
104 for fragment in template.stream(status=status, **kwargs): | 101 path: str |
105 yield fragment.encode(UNICODE_ENCODING) | 102 The path of the page we want to construct. |
106 | 103 |
107 | 104 Returns |
108 def handler(environ, start_response): | 105 ------- |
109 path = environ.get('PATH_INFO') | 106 (str, str) |
Vasily Kuznetsov
2018/10/22 14:36:46
Numpy docstring standard (link in the previous com
Tudor Avram
2018/10/23 16:44:32
Done.
| |
110 | 107 With the following format: |
111 data = get_data(path) | 108 <page_name, page_contents> |
112 if data is None: | 109 |
113 return show_error(start_response, '404 Not Found', uri=path) | 110 """ |
114 | 111 path = path.strip('/') |
115 mime = mimetypes.guess_type(path)[0] or 'text/html' | 112 if path == '': |
116 | 113 locale, page = self.source.read_config().get('general', |
117 if isinstance(data, unicode): | 114 'defaultlocale'), '' |
118 data = data.encode(UNICODE_ENCODING) | 115 elif '/' in path: |
119 mime = '%s; charset=%s' % (mime, UNICODE_ENCODING) | 116 locale, page = path.split('/', 1) |
120 | 117 else: |
121 start_response('200 OK', [('Content-Type', mime)]) | 118 locale, page = path, '' |
122 return [data] | 119 |
120 default_page = self.source.read_config().get('general', 'defaultpage') | |
121 possible_pages = [page, '/'.join([page, default_page]).lstrip('/')] | |
122 | |
123 for page_format in converters.iterkeys(): | |
124 for p in possible_pages: | |
125 if self.source.has_page(p, page_format): | |
126 return p, process_page(self.source, locale, p, page_format, | |
127 self.full_url) | |
128 | |
129 if self.source.has_localizable_file(locale, page): | |
130 return page, self.source.read_localizable_file(locale, page) | |
131 | |
132 return None, None | |
133 | |
134 def _has_conflicts(self, page): | |
135 """Check if a page has conflicts. | |
136 | |
137 A page has conflicts if there are other pages with the same name. | |
138 Parameters | |
Vasily Kuznetsov
2018/10/22 14:36:46
Nit: there should be an empty line before the head
Tudor Avram
2018/10/23 16:44:32
Done.
| |
139 ---------- | |
140 page: str | |
141 The path of the page we're checking for conflicts. | |
142 | |
143 Returns | |
144 ------- | |
145 bool | |
146 True - if the page has conflicts | |
147 False - otherwise | |
148 | |
149 """ | |
150 pages = [p for p, _ in self.source.list_pages()] | |
151 pages.extend(self.source.list_localizable_files()) | |
152 | |
153 if pages.count(page) > 1: | |
154 return True | |
155 if any(p.startswith(page + '/') or page.startswith(p + '/') for p in | |
156 pages): | |
157 return True | |
158 return False | |
159 | |
160 def get_error_page(self, start_response, status, **kw): | |
161 """Create and display an error page. | |
162 | |
163 Parameters | |
164 ---------- | |
165 start_response: function | |
166 It will be called before constructing the error page, to setup | |
167 things like the status of the response and the headers. | |
168 status: str | |
169 The status of the response we're sending the error page with. | |
170 Needs to have the following format: "<status_code> | |
Vasily Kuznetsov
2018/10/22 14:36:47
It would be better to not break the line the middl
Tudor Avram
2018/10/23 16:44:30
Done.
| |
171 <status_message>" | |
172 kw: dict | |
173 Any additional arguments that will be passed onto the `stream` | |
174 method | |
175 of a `jinja2 Template`. | |
Vasily Kuznetsov
2018/10/22 14:36:47
Nit: redundant line break above?
Tudor Avram
2018/10/23 16:44:31
Done.
| |
176 | |
177 Returns | |
178 ------- | |
179 generator | |
180 of utf8 strings - fragments of the corresponding error HTML | |
Vasily Kuznetsov
2018/10/22 14:36:47
I think "of utf8 strings" should be part of the "t
Tudor Avram
2018/10/23 16:44:33
Done.
| |
181 template. | |
182 | |
183 """ | |
184 env = jinja2.Environment(autoescape=True) | |
185 page_template = env.from_string(ERROR_TEMPLATE) | |
186 mime = 'text/html; encoding={}'.format(UNICODE_ENCODING) | |
187 | |
188 start_response(status, [('Content-Type', mime)]) | |
189 | |
190 for fragment in page_template.stream(status=status, **kw): | |
191 yield fragment.encode(UNICODE_ENCODING) | |
192 | |
193 def __call__(self, environ, start_response): | |
194 """Execute the handler, according with the WSGI standards. | |
Vasily Kuznetsov
2018/10/22 14:36:47
Nit: according to the internet the normal form is
Tudor Avram
2018/10/23 16:44:33
Done.
| |
195 | |
196 Parameters | |
197 --------- | |
198 environ: dict | |
199 The environment under which the page is requested. | |
200 The requested page must be under the `PATH_INFO` key. | |
201 start_response: function | |
202 Used to initiate a response. Must take two arguments, in this | |
203 order: | |
204 - Response status, in the format "<code> <message>". | |
205 - Response headers, as a list of tuples. | |
206 | |
207 Returns | |
208 ------- | |
209 list | |
Vasily Kuznetsov
2018/10/22 14:36:46
It's "list of str", right? Perhaps we can add that
Tudor Avram
2018/10/23 16:44:31
Done.
| |
210 With the data for a specific page. | |
211 | |
212 """ | |
213 path = environ.get('PATH_INFO') | |
214 | |
215 data = self._get_data(path) | |
216 | |
217 if data is None: | |
218 return self.get_error_page(start_response, '404 Not Found', | |
219 uri=path) | |
220 | |
221 mime = mimetypes.guess_type(path)[0] or 'text/html' | |
222 | |
223 if isinstance(data, unicode): | |
224 data = data.encode(UNICODE_ENCODING) | |
225 mime = '{0}; charset={1}'.format(mime, UNICODE_ENCODING) | |
226 | |
227 start_response('200 OK', [('Content-Type', mime)]) | |
228 return [data] | |
229 | |
230 | |
231 def get_handler(): | |
Vasily Kuznetsov
2018/10/22 14:36:47
I was imagining a structure where we parse the arg
Tudor Avram
2018/10/23 16:44:30
Done.
| |
232 """Set the arguments required to run the script. | |
233 | |
234 Returns | |
235 ------- | |
236 TestServerHandler | |
237 Initialised with the script parameters. | |
238 | |
239 """ | |
240 parser = ArgumentParser(description='CMS development server created to ' | |
241 'test pages locally and on-the-fly') | |
242 | |
243 parser.add_argument('path', default=os.curdir, nargs='?', | |
244 help='Path to the website we intend to run. If not ' | |
245 'provided, defaults, to the current directory.') | |
246 parser.add_argument('--host', default='localhost', | |
247 help='Address of the host the server will listen on. ' | |
248 'Defaults to "localhost".') | |
249 parser.add_argument('--port', default=5000, type=int, | |
250 help='TCP port the server will listen on. Default ' | |
251 '5000.') | |
252 | |
253 args = parser.parse_args() | |
254 | |
255 return DynamicServerHandler(args.host, args.port, args.path) | |
256 | |
257 | |
258 def run_werkzeug_server(handler, **kw): | |
259 """Set up a server that uses `werkzeug`. | |
260 | |
261 Parameters | |
262 ---------- | |
263 handler: DynamicServerHandler | |
264 Defines the parameters and methods required to handle requests. | |
265 | |
266 Raises | |
267 ------ | |
268 ImportError | |
269 If the package `werkzeug` is not installed | |
270 | |
271 """ | |
272 from werkzeug.serving import run_simple | |
273 | |
274 def run(*args, **kwargs): | |
275 # The werkzeug logger must be configured before the | |
276 # root logger. Also we must prevent it from propagating | |
277 # messages, otherwise messages are logged twice. | |
278 import logging | |
Vasily Kuznetsov
2018/10/22 14:36:46
Is it necessary to import logging here and not at
Tudor Avram
2018/10/22 17:29:38
It's not used anywhere else in the script, that's
Vasily Kuznetsov
2018/10/23 10:16:14
I see. Importing `logging` is probably not a big d
Tudor Avram
2018/10/23 16:44:31
Done.
| |
279 logger = logging.getLogger('werkzeug') | |
280 logger.propagate = False | |
281 logger.setLevel(logging.INFO) | |
282 logger.addHandler(logging.StreamHandler()) | |
283 | |
284 run_simple(threaded=True, *args, **kwargs) | |
285 | |
286 run(handler.host, handler.port, handler, **kw) | |
287 | |
288 | |
289 def run_builtins_server(handler, **kw): | |
290 """Configure a server that only uses builtin packages. | |
291 | |
292 Parameters | |
293 ---------- | |
294 handler: DynamicServerHandler | |
295 Defines the parameters and methods required to handle requests. | |
296 | |
297 """ | |
298 from SocketServer import ThreadingMixIn | |
299 from wsgiref.simple_server import WSGIServer, make_server | |
300 | |
301 class ThreadedWSGIServer(ThreadingMixIn, WSGIServer): | |
302 daemon_threads = True | |
303 | |
304 def run(host, port, app, **kwargs): | |
305 def wrapper(environ, start_response): | |
306 try: | |
307 return app(environ, start_response) | |
308 except Exception as e: | |
309 return handler.get_error_page( | |
310 start_response, '500 Internal Server Error', | |
311 uri=environ.get('PATH_INFO'), error=e, | |
312 ) | |
313 | |
314 server = make_server(host, port, wrapper, ThreadedWSGIServer) | |
315 print(' * Running on {0}:{1}'.format(*server.server_address)) | |
316 server.serve_forever() | |
317 | |
318 run(handler.host, handler.port, handler, **kw) | |
319 | |
320 | |
321 def main(): | |
322 handler = get_handler() | |
323 | |
324 try: | |
325 run_werkzeug_server(handler, use_reloader=True, use_debugger=True) | |
326 except ImportError: | |
327 run_builtins_server(handler) | |
123 | 328 |
124 | 329 |
125 if __name__ == '__main__': | 330 if __name__ == '__main__': |
126 | 331 main() |
127 parser = argparse.ArgumentParser(description='CMS development server created to test pages locally and on-the-fly') | |
128 parser.add_argument('path', nargs='?', default=os.curdir) | |
129 parser.add_argument('-a', '--address', default='localhost', help='Address of the interface the server will listen on') | |
130 parser.add_argument('-p', '--port', type=int, default=5000, help='TCP port t he server will listen on') | |
131 args = parser.parse_args() | |
132 | |
133 source = create_source(args.path) | |
134 address = args.address | |
135 port = args.port | |
136 | |
137 try: | |
138 from werkzeug.serving import ThreadedWSGIServer, run_simple | |
139 | |
140 # see https://github.com/mitsuhiko/werkzeug/pull/770 | |
141 ThreadedWSGIServer.daemon_threads = True | |
142 | |
143 def run(*args, **kwargs): | |
144 # The werkzeug logger must be configured before the | |
145 # root logger. Also we must prevent it from propagating | |
146 # messages, otherwise messages are logged twice. | |
147 import logging | |
148 logger = logging.getLogger('werkzeug') | |
149 logger.propagate = False | |
150 logger.setLevel(logging.INFO) | |
151 logger.addHandler(logging.StreamHandler()) | |
152 | |
153 run_simple(threaded=True, *args, **kwargs) | |
154 except ImportError: | |
155 from SocketServer import ThreadingMixIn | |
156 from wsgiref.simple_server import WSGIServer, make_server | |
157 | |
158 class ThreadedWSGIServer(ThreadingMixIn, WSGIServer): | |
159 daemon_threads = True | |
160 | |
161 def run(host, port, app, **kwargs): | |
162 def wrapper(environ, start_response): | |
163 try: | |
164 return app(environ, start_response) | |
165 except Exception as e: | |
166 return show_error(start_response, '500 Internal Server Error ', | |
167 uri=environ.get('PATH_INFO'), error=e) | |
168 | |
169 server = make_server(host, port, wrapper, ThreadedWSGIServer) | |
170 print ' * Running on http://%s:%i/' % server.server_address | |
171 server.serve_forever() | |
172 | |
173 run(address, port, handler, use_reloader=True, use_debugger=True) | |
OLD | NEW |