#2687 - Include mimeo python module

modules/adblockplus/files/mimeo.py

+#!/usr/bin/env python3
+
+import argparse
+import re
+import sys
+import threading
+
+from http.server import BaseHTTPRequestHandler, HTTPServer
+from string import Template
+
+PROXY_TOKEN = 'http_'
+REGEX = '\\$' + PROXY_TOKEN + '[a-z_0-9]+\\b'
+DEFAULT_LOG = '$remote_addr - - [$time_local] "$request" $status $bytes_sent'
+_lock = threading.Lock()
+
+
+class Handler(BaseHTTPRequestHandler):
+    def get_header_values(self):
+        values = {}
+        headers = re.findall(REGEX, self.format)
+        for name in headers:
+            new_var = name[len(PROXY_TOKEN)+1:]
+            values[name[1:]] = self.headers.get(new_var, '-')
+        return values
+
+    def write_info(self, args):
+        _lock.acquire()
+        message = Template(self.format)

[Vasily Kuznetsov, 2017/08/11 17:31:47]

You should probably use try/finally here with the locking. Otherwise one error
in formatting or writing will bring the whole thing down by not releasing the
lock.

+        self.info_file.write(message.safe_substitute(args))
+        if self.info_file is sys.stdout:
+            self.info_file.flush()
+        _lock.release()
+
+    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),
+        }
+        values.update(self.get_header_values())
+        self.write_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)
+
+
+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('--format', action='store',
+                        type=str, nargs='?',
+                        default=DEFAULT_LOG,
+                        help='Format of the log ouput')
+    parser.add_argument('info_file', action='store',

[Vasily Kuznetsov, 2017/08/11 17:31:47]

I'm not sure if "info_file" is the best name, it sounds a bit unclear. How about
"output_file"?

+                        type=str, nargs='?', default='-',
+                        help='The file where the logs will be written')
+    args = parser.parse_args()
+    setattr(Handler, 'format', args.format)
+    setattr(Handler, 'response', args.response)
+    server_address = ('', args.port)
+    httpd = HTTPServer(server_address, Handler)
+    if args.info_file and args.info_file != '-':
+        fh = open(args.info_file, 'a')
+    else:
+        fh = sys.stdout
+    setattr(Handler, 'info_file', fh)

[Vasily Kuznetsov, 2017/08/11 17:31:47]

I think it would be more clear to order the steps like this:

# parse args
# open the file
Handler.format = args.format
Handler.response = args.reponse
Handler.info_file = fh
httpd = HTTPServer(('', args.port), Handler)
try:
    httpd.serve_forever()
except:
    # close the file

What do you think?

+    try:
+        httpd.serve_forever()
+    except:
+        if args.info_file != '-':
+            fh.close()