Rietveld Code Review Tool
Help | Bug tracker | Discussion group | Source code

Side by Side Diff: sitescripts/filterhits/geometrical_mean.py

Issue 4615801646612480: Issue 395 - Filter hits statistics backend (Closed)
Patch Set: Rebased. Created March 2, 2015, 8:41 p.m.
Left:
Right:
Use n/p to move between diff chunks; N/P to move between comments.
Jump to:
View unified diff | Download patch
« no previous file with comments | « sitescripts/filterhits/db.py ('k') | sitescripts/filterhits/schema.sql » ('j') | no next file with comments »
Toggle Intra-line Diffs ('i') | Expand Comments ('e') | Collapse Comments ('c') | Show Comments Hide Comments ('s')
OLDNEW
(Empty)
1 # coding: utf-8
2
3 # This file is part of the Adblock Plus web scripts,
4 # Copyright (C) 2006-2015 Eyeo GmbH
5 #
6 # Adblock Plus is free software: you can redistribute it and/or modify
7 # it under the terms of the GNU General Public License version 3 as
8 # published by the Free Software Foundation.
9 #
10 # Adblock Plus is distributed in the hope that it will be useful,
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13 # GNU General Public License for more details.
14 #
15 # You should have received a copy of the GNU General Public License
16 # along with Adblock Plus. If not, see <http://www.gnu.org/licenses/>.
17
18 import itertools
19 from sitescripts.filterhits import db
20
21 def filter_hits(data):
22 """
23 Generator that provides all filter hits for the given data,
24 in tuples like (filter, domain, hits, latest).
25 """
26 for filter, filter_data in data['filters'].iteritems():
27 domains = itertools.chain(filter_data.get("thirdParty", {}).iteritems(),
28 filter_data.get("firstParty", {}).iteritems())
29 for domain, domain_data in domains:
30 yield (filter, domain, domain_data["hits"], domain_data["latest"] / 1000)
31
32 def update_query(interval, filter, domain, hits, latest):
33 """
34 Function that takes the fields for a filter hit and returns them arranged
35 as the update SQL requires along with the SQL itself.
36 """
37 return (("""INSERT IGNORE INTO `filters`
38 (filter, sha1) VALUES (%s, UNHEX(SHA1(filter)))""",
39 filter),
40 ("""INSERT INTO `geometrical_mean`
41 (filter_sha1, domain, hits, timestamp)
42 VALUES (UNHEX(SHA1(%s)), %s, %s, FROM_UNIXTIME(%s))
43 ON DUPLICATE KEY UPDATE
44 hits = (
45 POW(hits, 1 - (UNIX_TIMESTAMP(VALUES(timestamp)) -
46 UNIX_TIMESTAMP(timestamp)) / %s) *
47 POW(VALUES(hits), (UNIX_TIMESTAMP(VALUES(timestamp)) -
48 UNIX_TIMESTAMP(timestamp)) / %s)),
49 timestamp = VALUES(timestamp)""",
50 filter, domain, hits, int(latest), interval, interval))
51
52 def update(interval, data):
53 """
54 Returns an iterator of all the SQL and parameters needed to
55 update the aggregations for the given data + interval in the database.
56 """
57 for fields in filter_hits(data):
58 for query in update_query(interval, *fields):
59 yield query
OLDNEW
« no previous file with comments | « sitescripts/filterhits/db.py ('k') | sitescripts/filterhits/schema.sql » ('j') | no next file with comments »

Powered by Google App Engine
This is Rietveld