| OLD | NEW | 
| (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 logging | 
 |  19 import MySQLdb | 
 |  20 import itertools | 
 |  21 import json | 
 |  22 import os | 
 |  23 import sys | 
 |  24  | 
 |  25 from sitescripts.utils import get_config | 
 |  26 from sitescripts.filterhits import db, geometrical_mean | 
 |  27  | 
 |  28 _last_log_file = None | 
 |  29  | 
 |  30 def log_files(dir): | 
 |  31   """ | 
 |  32   Provides a generator of filter hits log files for the given directory. | 
 |  33   Works recursively, relative path of log file is returned. | 
 |  34   """ | 
 |  35   for root, subdirs, files in os.walk(dir): | 
 |  36     for f in files: | 
 |  37       if os.path.splitext(f)[1] == ".log" and f[0].isdigit(): | 
 |  38         yield os.path.join(root, f) | 
 |  39  | 
 |  40 def read_data(log_file): | 
 |  41   """ | 
 |  42   Read, parse and return the JSON data for the given log file name. | 
 |  43   (As a side effect sets the global _last_log_file to the log file name.) | 
 |  44   """ | 
 |  45   global _last_log_file | 
 |  46   try: | 
 |  47     with open(log_file, "r") as f: | 
 |  48       f.readline() | 
 |  49       data = json.load(f) | 
 |  50       # Keep track of the current log file in global variable in case we need to | 
 |  51       # identify it later if there's a problem. (This works because the files ar
    e | 
 |  52       # processed lazily.) | 
 |  53       _last_log_file = log_file | 
 |  54   except IOError: | 
 |  55     sys.exit("Could not read log file %s" % log_file) | 
 |  56   return data | 
 |  57  | 
 |  58 if __name__ == "__main__": | 
 |  59   if not len(sys.argv) == 2: | 
 |  60     print "Usage: python -m sitescripts.filterhits.bin.reprocess_logs /path/to/l
    ogs" | 
 |  61     sys.exit(1) | 
 |  62  | 
 |  63   interval = get_config().get("filterhitstats", "interval") | 
 |  64  | 
 |  65   def read_update(f): | 
 |  66     return geometrical_mean.update(interval, read_data(f)) | 
 |  67  | 
 |  68   if sys.argv[1].endswith(".log"): | 
 |  69     sql = read_update(sys.argv[1]) | 
 |  70   else: | 
 |  71     sql = itertools.chain.from_iterable(itertools.imap(read_update, | 
 |  72                                                        log_files(sys.argv[1]))) | 
 |  73  | 
 |  74   db_connection = db.connect() | 
 |  75  | 
 |  76   try: | 
 |  77     db.write(db_connection, sql) | 
 |  78   except: | 
 |  79     logging.error("Failed to process file %s, all changes rolled back." % _last_
    log_file) | 
 |  80     raise | 
 |  81   finally: | 
 |  82     db_connection.close() | 
| OLD | NEW |