Noissue - Adapt quotes for compliance with our coding style in sitescripts

sitescripts/urlfixer/bin/topDomains.py

 # This file is part of the Adblock Plus web scripts,
 # Copyright (C) 2006-2016 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/>.
 
 import sys
 import os
 import re
 import math
 import MySQLdb
 from sitescripts.utils import get_config, setupStderr
 
-"""
+'''
 This script produces the list of top correct domain names currently in the
 database.
-"""
+'''
 
 STATUS_TYPED = 1
 STATUS_TYPO = 2
 STATUS_CORRECTION = 3
 STATUS_FALSE_POSITIVE = 4
 
 
 def getTopDomains(count=5000):
     db = _get_db()
     cursor = db.cursor(MySQLdb.cursors.DictCursor)
-    cursor.execute("SELECT id, domain, forceinclusion FROM domains")
+    cursor.execute('SELECT id, domain, forceinclusion FROM domains')
 
     domains = {}
     mandatory = []
     for result in cursor:
-        domain = result["domain"]
-        if "." not in domain or not re.search(r"[a-zA-Z]", domain):
+        domain = result['domain']
+        if '.' not in domain or not re.search(r'[a-zA-Z]', domain):
             continue
         if re.search(r"['\"_,<>:;!$%&/()*+#~]|^\.|\.$|\.\.", domain):

[Vasily Kuznetsov, 2016/05/30 10:01:41]

I now get A110 on this line. It seems that converting the regex to single quotes
is not really possible without changing it or dropping r and getting something
like the ugly automatic conversion that you replaced.

So it seems we have several options:
1. Leave it as is and add a # noqa to the line or include it into the config,
2. Revert to more ugly machine-translated version,
3. Change it to r'[\'"_,<>:;!$%&/()*+#~]|^\.|\.$|\.\.'

The third one will change the bytecode but it won't change the meaning of the
regex because backslash-escaped quotes in regexes are the same as unescaped
quotes (most likely the original regex escaped the double quote just to include
it in a double-quote-delimited string).

The third option seems to be the most "right" one but it's also the most scary
since we won't have the assurance of bytecode not changing.

What do you think?

[Sebastian Noack, 2016/05/30 10:27:18]

Well, there is also the fourth option to fix flake8-abp which I went for:
https://codereview.adblockplus.org/29345337/

Though, generally, I'd agree that this string should have been written as
r'[\'"_,<>:;!$%&/()*+#~]|^\.|\.$|\.\.' which while not the same string anymore
should theoretically behave exactly the same when used as regular expression.
But we still would have to retest the code.

Moreover, when using raw strings for something other than regular expressions,
moving backslashes around might not even be an option. So we have to relax
flake8-abp anyway.

[Vasily Kuznetsov, 2016/05/30 12:16:34]

I agree that moving the backslashes around is not always possible, so fixing
flake8-abp seems like the best solution.

             continue
 
-        typed = _get_weighted_count(db, result["id"], STATUS_TYPED)
-        correction = _get_weighted_count(db, result["id"], STATUS_CORRECTION)
-        typo = _get_weighted_count(db, result["id"], STATUS_TYPO)
-        fp = _get_weighted_count(db, result["id"], STATUS_FALSE_POSITIVE)
+        typed = _get_weighted_count(db, result['id'], STATUS_TYPED)
+        correction = _get_weighted_count(db, result['id'], STATUS_CORRECTION)
+        typo = _get_weighted_count(db, result['id'], STATUS_TYPO)
+        fp = _get_weighted_count(db, result['id'], STATUS_FALSE_POSITIVE)
         correctness = _calculate_correctness(typed + correction, typo + fp)
 
         domains[domain] = correctness
-        if result["forceinclusion"]:
+        if result['forceinclusion']:
             mandatory.append(domain)
     return sorted(domains.iterkeys(), key=lambda d: domains[d], reverse=True)[:count] + mandatory
 
 
 def _get_weighted_count(db, domain, status):
     cursor = db.cursor(MySQLdb.cursors.DictCursor)
-    cursor.execute("""SELECT curr_month * 0.4 + prev_month * 0.3 +
+    cursor.execute('''SELECT curr_month * 0.4 + prev_month * 0.3 +
                       curr_year * 0.2 + prev_year * 0.1 AS weighted_count
-                    FROM corrections WHERE domain = %s AND status = %s""",
+                    FROM corrections WHERE domain = %s AND status = %s''',
                    (domain, status))
     result = cursor.fetchone()
     if result == None:
         return 0
     else:
-        return result["weighted_count"]
+        return result['weighted_count']
 
 
 def _calculate_correctness(positive, negative):
     if positive + negative > 0:
         # Determine the correctness score with a confidence level of 0.95
         # (see http://www.evanmiller.org/how-not-to-sort-by-average-rating.html)
         fp = float(positive)
         fn = float(negative)
         total = fp + fn
         return ((fp + 1.9208) / total - 1.96 * math.sqrt((fp * fn) / total +
                                                          0.9604) / total) / (1 + 3.8416 / total)
     else:
         return 0
 
 
 def _get_db():
-    database = get_config().get("urlfixer", "database")
-    dbuser = get_config().get("urlfixer", "dbuser")
-    dbpasswd = get_config().get("urlfixer", "dbpassword")
-    if os.name == "nt":
+    database = get_config().get('urlfixer', 'database')
+    dbuser = get_config().get('urlfixer', 'dbuser')
+    dbpasswd = get_config().get('urlfixer', 'dbpassword')
+    if os.name == 'nt':
         return MySQLdb.connect(user=dbuser, passwd=dbpasswd, db=database,
-                               use_unicode=True, charset="utf8", named_pipe=True)
+                               use_unicode=True, charset='utf8', named_pipe=True)
     else:
         return MySQLdb.connect(user=dbuser, passwd=dbpasswd, db=database,
-                               use_unicode=True, charset="utf8")
+                               use_unicode=True, charset='utf8')
 
 if __name__ == '__main__':
     setupStderr()
 
     domains = getTopDomains()
     for domain in domains:
-        print domain.encode("utf-8")
+        print domain.encode('utf-8')