ExtensionCrawler/create-db

#!/usr/bin/env python3.5
#
# Copyright (C) 2016,2017 The University of Sheffield, UK
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program 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 this program.  If not, see <http://www.gnu.org/licenses/>.
#

import getopt
import os
import sys
import tarfile
import time
import tempfile
import fnmatch
from multiprocessing import Pool
import logging
import datetime

from ExtensionCrawler.archive import update_db_incremental
from ExtensionCrawler.config import *
from ExtensionCrawler.util import log_info, log_warning, log_error, log_exception


def help():
    print("create-db [OPTION]")
    print("    -h                  print this help text")
    print("    -a <DIR>            archive directory")
    print("    -p <PREFIX>         three-letter-prefix")
    print("    -e <EXTIDFILELIST>  file with extension ids")
    print("    -t <THREADS>        number of parallel threads")
    print("    -n <TASKID>         process chunk n where n in [1,N]")
    print("    -N <MAXTASKID>      ")


def process_id(path):
    start = time.time()
    with tempfile.TemporaryDirectory() as tmpdir:
        with tarfile.open(path) as t:
            t.extractall(tmpdir)

            extid = os.listdir(tmpdir)[0]
            log_info("Start processing extension", 0, extid)
            iddir = os.path.join(tmpdir, extid)

            for date in sorted(os.listdir(iddir)):
                try:
                    update_db_incremental(iddir, extid, date)
                except Exception:
                    log_exception(
                        "Exception when handling data from {}".format(date), 0,
                        extid)
    log_info(
        "Finished extension in {}".format(
            str(datetime.timedelta(seconds=int(time.time() - start)))),
        0,
        extid)


def find(archive, pattern):
    for root, _, files in os.walk(os.path.join(archive, "data")):
        for file in files:
            if fnmatch.fnmatch(file, pattern + ".tar"):
                yield os.path.join(root, file)


def find_from_file(archive, extidlistfile):
    with open(extidlistfile, 'r') as f:
        extids = [l.strip() for l in f.readlines()]

    for root, _, files in os.walk(os.path.join(archive, "data")):
        for file in files:
            for extid in extids:
                if fnmatch.fnmatch(file, extid + ".tar"):
                    yield os.path.join(root, file)


def parse_args(argv):
    archive = "archive"
    parallel = 8
    taskid = 1
    maxtaskid = 1

    paths = []

    try:
        opts, args = getopt.getopt(argv, "ha:p:e:t:n:N:", [
            "archive=", "prefix=", "extidlistfile=", "threads=", "taskid=",
            "maxtaskid="
        ])
    except getopt.GetoptError:
        help()
        sys.exit(2)
    for opt, arg in opts:
        if opt == '-h':
            help()
            sys.exit()
        elif opt in ("-a", "--archive"):
            archive = arg
        elif opt in ("-p", "--prefix"):
            paths += find(archive, arg + "*")
        elif opt in ("-e", "--extidlistfile"):
            paths += find_from_file(archive, arg)
        elif opt in ("-t", "--threads"):
            parallel = int(arg)
        elif opt in ("-n", "--taskid"):
            taskid = int(arg)
        elif opt in ("-N", "--maxtaskid"):
            maxtaskid = int(arg)

    if paths == []:
        paths = list(find(archive, "*"))

    chunksize = int(len(paths) / maxtaskid)
    if taskid == maxtaskid:
        paths = paths[(taskid - 1) * chunksize:]
    else:
        paths = paths[(taskid - 1) * chunksize:taskid * chunksize]

    return paths, parallel


def main(argv):
    logging.basicConfig(level=logging.INFO, format=const_log_format())

    paths, parallel = parse_args(argv)

    with Pool(processes=parallel) as p:
        p.map(process_id, paths)


if __name__ == "__main__":
    main(sys.argv[1:])