#2687 - Include mimeo python module

modules/adblockplus/files/mimeo.py

 #!/usr/bin/env python3
 
 import argparse
-import logging
+import re
 import sys
+import threading
+import traceback
 
 from http.server import BaseHTTPRequestHandler, HTTPServer
 from string import Template
 
-PUNCTUATION = """!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~ """
-PROXY_TOKEN = 'http_'
+# The token used for the headers passed by nginx is: http_
+REGEX = r'\$http_\w+\b'
+DEFAULT_LOG = '$remote_addr - - [$time_local] "$request" $status $bytes_sent'
+_lock = threading.Lock()
 
 
 class Handler(BaseHTTPRequestHandler):
     def get_header_values(self):
         values = {}
-        for var in self.log_format.split():
-            name = var.strip(PUNCTUATION)

[Vasily Kuznetsov, 2017/08/07 20:46:01]

You've added a space to PUNCTUATION above, but do you really need it? Since
`var` is coming out of `....split()` above, it should already have no spaces in
it, or am I missing something?

[f.lopez, 2017/08/08 02:48:17]

Done.

-            if name.startswith(PROXY_TOKEN):
-                new_var = name[len(PROXY_TOKEN):].title()
-                values[name] = self.headers.get(new_var, '-')
+        headers = re.findall(REGEX, self.format)
+        for name in headers:
+            new_var = name[6:].replace('_', '-')
+            values[name[1:]] = self.headers.get(new_var, '-')
         return values
 
-    def log_info(self, args):
-        message = Template(self.log_format)
-        logging.info(message.safe_substitute(args))
+    def send_simple_response(self, status, response=None):
+        self.send_response(status)
+        self.end_headers()
+        if response is None:
+            response = bytes(self.responses[status][0], 'UTF-8')
+        self.wfile.write(response)
+
+    def write_info(self, args):
+        message = Template(self.format).safe_substitute(args) + '\n'
+        with _lock:
+            self.output.write(message)
+            self.output.flush()
 
     def do_POST(self):
         status = 200
         content = bytes(self.response, 'UTF-8')
         values = {
             'remote_addr': self.address_string(),
             'time_local': self.log_date_time_string(),
             'request': self.requestline,
             'status': status,
             'bytes_sent': len(content),
-            'content-type': 'text/plain',

[Vasily Kuznetsov, 2017/08/07 20:46:01]

Some other variables, like 'time_local' and 'bytes_sent' use underscores and
here you use dashes. It's a bit inconsistent and could be surprising for the
person who configures the log format. Not a deal-breaker for me, but perhaps you
would want them to be consistent.

[f.lopez, 2017/08/08 02:48:17]

Done.

-            'content-length': len(content),
         }
         values.update(self.get_header_values())
-        self.log_info(values)
-        self.send_response(status)
-        self.send_header('Content-Type', values['content-type'])
-        self.send_header('Content-Length', values['content-length'])
-        self.end_headers()
-        self.wfile.write(content)
-        self.log_request(200)
+        try:
+            self.write_info(values)
+            self.send_simple_response(status, content)
+        except:
+            traceback.print_exc(file=sys.stderr)
+            self.send_simple_response(500)
 
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
     parser.add_argument('--port', action='store',
                         default=8000, type=int,
                         nargs='?',
                         help='Port to use [default: 8000]')
     parser.add_argument('--response', action='store',
                         type=str, nargs='?', default='OK',
                         help='The response send to the client')
-    parser.add_argument('--log_format', action='store',
+    parser.add_argument('--format', action='store',
                         type=str, nargs='?',
-                        default='$remote_addr - - [$time_local] "$request" $status $bytes_sent',

[Vasily Kuznetsov, 2017/08/07 20:46:01]

This line is too long now, PEP8 (and our style guide) says lines should be <80
characters. Perhaps you can make a constant for the default log format to avoid
wrapping lines too much here.

[f.lopez, 2017/08/08 02:48:17]

Done.

+                        default=DEFAULT_LOG,
                         help='Format of the log ouput')
-    parser.add_argument('log_file', action='store',
-                        type=str, nargs='?',
+    parser.add_argument('output', action='store',
+                        type=str, nargs='?', default='-',
                         help='The file where the logs will be written')
     args = parser.parse_args()
-    handler_class = Handler
-    server_class = HTTPServer
-    setattr(handler_class, 'log_format', args.log_format)
-    setattr(handler_class, 'response', args.response)
-    server_address = ('', args.port)
-    httpd = server_class(server_address, handler_class)
-    if args.log_file == None:
-        logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+    if args.output and args.output != '-':
+        fh = open(args.output, 'a')
     else:
-        logging.basicConfig(filename=args.log_file, level=logging.INFO)
-    httpd.serve_forever()
+        fh = open(sys.stdout.fileno(), 'w', closefd=False)
+    try:
+        Handler.output = fh
+        Handler.format = args.format
+        Handler.response = args.response
+        server_address = ('', args.port)
+        httpd = HTTPServer(server_address, Handler)
+        httpd.serve_forever()
+    finally:
+        fh.close()