Index: sitescripts/filterhits/geometrical_mean.py |
diff --git a/sitescripts/filterhits/geometrical_mean.py b/sitescripts/filterhits/geometrical_mean.py |
index 00bd3e43cc83a91ae7b8be72f485e910fbb98285..f23b231e52770d7b2c022019fb5a1dff17e4a2bd 100644 |
--- a/sitescripts/filterhits/geometrical_mean.py |
+++ b/sitescripts/filterhits/geometrical_mean.py |
@@ -1,7 +1,7 @@ |
# coding: utf-8 |
# This file is part of the Adblock Plus web scripts, |
-# Copyright (C) 2006-2014 Eyeo GmbH |
+# Copyright (C) 2006-2015 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 |
@@ -19,34 +19,10 @@ import itertools |
import sitescripts.filterhits.db as db |
from functools import partial |
-def update_sql(interval, filter, domain, hits, timestamp): |
- """ |
- Returns the SQL required to insert / update the hits for a |
- given domain + filter combo and to insert the filter if required. |
- """ |
- filter = db.escape(filter) |
- |
- return ( |
- ("INSERT IGNORE INTO `filters` " + |
- "(filter, md5) VALUES ('%s', UNHEX(MD5(filter)));" + |
- "INSERT INTO `geometrical_mean` " + |
- "(filter_md5, domain, hits, timestamp) " + |
- "VALUES (UNHEX(MD5('%s')), '%s', %d, FROM_UNIXTIME(%d)) " + |
- "ON DUPLICATE KEY UPDATE " + |
- "hits = (" + |
- " POW(hits, 1 - (UNIX_TIMESTAMP(VALUES(timestamp)) - " + |
- " UNIX_TIMESTAMP(timestamp)) / %d) * " + |
- " POW(VALUES(hits), (UNIX_TIMESTAMP(VALUES(timestamp)) - " + |
- " UNIX_TIMESTAMP(timestamp)) / %d)), " + |
- "timestamp = VALUES(timestamp);") % ( |
- filter, |
- filter, db.escape(domain), int(hits), int(timestamp), |
- int(interval), int(interval))) |
- |
def filter_hits(data): |
""" |
- Generator that provides all filter hits for the given data, |
- in tuples like (filter, domain, hits, latest). |
+ Generator that provides all filter hits for the given data, |
+ in tuples like (filter, domain, hits, latest). |
""" |
for filter, filter_data in data['filters'].iteritems(): |
domains = itertools.chain(filter_data.get("thirdParty", {}).iteritems(), |
@@ -54,10 +30,31 @@ def filter_hits(data): |
for domain, domain_data in domains: |
yield (filter, domain, domain_data["hits"], domain_data["latest"] / 1000) |
+def update_query(interval, filter, domain, hits, latest): |
+ """ |
+ Function that takes the fields for a filter hit and returns them arranged |
+ as the update SQL requires along with the SQL itself. |
+ """ |
+ return (("""INSERT IGNORE INTO `filters` |
+ (filter, sha1) VALUES (%s, UNHEX(SHA1(filter)))""", |
+ filter), |
+ ("""INSERT INTO `geometrical_mean` |
+ (filter_sha1, domain, hits, timestamp) |
+ VALUES (UNHEX(SHA1(%s)), %s, %s, FROM_UNIXTIME(%s)) |
+ ON DUPLICATE KEY UPDATE |
+ hits = ( |
+ POW(hits, 1 - (UNIX_TIMESTAMP(VALUES(timestamp)) - |
+ UNIX_TIMESTAMP(timestamp)) / %s) * |
+ POW(VALUES(hits), (UNIX_TIMESTAMP(VALUES(timestamp)) - |
+ UNIX_TIMESTAMP(timestamp)) / %s)), |
+ timestamp = VALUES(timestamp)""", |
+ filter, domain, hits, int(latest), interval, interval)) |
+ |
def update(interval, data): |
""" |
- Returns an iterator of all the SQL statements needed to |
- update the aggregations for the given data + interval. |
+ Returns an iterator of all the SQL and parameters needed to |
+ update the aggregations for the given data + interval in the database. |
""" |
- return itertools.imap(lambda fields: apply(partial(update_sql, interval), fields), |
- filter_hits(data)) |
+ flatten = itertools.chain.from_iterable |
+ return flatten(itertools.imap(lambda fields: update_query(interval, *fields), |
Sebastian Noack
2015/02/17 14:59:17
I feel that you are kinda overusing itertools. A g
kzar
2015/02/24 18:05:11
Done.
|
+ filter_hits(data))) |