Attachment 78598 Details for Bug 54110 – Refactor patch

[patch] Refactor patch

qawrangler_refactored.patch (text/plain), 7.23 KB, created by Marc Garcia on 2013-04-29 11:47:26 UTC

(hide)

Description:

Filename:

MIME Type:

Creator: Marc Garcia

Created: 2013-04-29 11:47:26 UTC

Size: 7.23 KB

patch

obsolete

>From 8550c8c222c0da1a5e502757ee5452702c8110d2 Mon Sep 17 00:00:00 2001
>From: Marc Garcia <garcia.marc@gmail.com>
>Date: Mon, 29 Apr 2013 12:40:37 +0200
>Subject: [PATCH] qa wranglers script file refactored
>
>---
> scripts/qawrangler-stats.py |  158 +++++++++++++++++++++++++++++++++++--------
> 1 files changed, 130 insertions(+), 28 deletions(-)
>
>diff --git a/scripts/qawrangler-stats.py b/scripts/qawrangler-stats.py
>index f73c38e..1270f64 100755
>--- a/scripts/qawrangler-stats.py
>+++ b/scripts/qawrangler-stats.py
>@@ -1,44 +1,146 @@
> #!/usr/bin/env python3
>+#
>+# This file is part of the LibreOffice project.
>+#
>+# This Source Code Form is subject to the terms of the Mozilla Public
>+# License, v. 2.0. If a copy of the MPL was not distributed with this
>+# file, You can obtain one at http://mozilla.org/MPL/2.0/.
>+#
>+# This file incorporates work covered by the following license notice:
>+#
>+#   Licensed to the Apache Software Foundation (ASF) under one or more
>+#   contributor license agreements. See the NOTICE file distributed
>+#   with this work for additional information regarding copyright
>+#   ownership. The ASF licenses this file to you under the Apache
>+#   License, Version 2.0 (the "License"); you may not use this file
>+#   except in compliance with the License. You may obtain a copy of
>+#   the License at http://www.apache.org/licenses/LICENSE-2.0 .
>+#
>+#
>+# qawrangler-stats.py
>+#
>+# Returns statistics of most active wranglers and reporters for a given
>+# month.
>+#
>+# For usage information, run:
>+#   qawrangler-stats.py -h
>+#
> 
>-import sys, re
>+import sys
>+import re
>+import datetime
> import gzip
>+import argparse
>+import csv
> from urllib.request import urlopen, URLError
> from io import BytesIO
>-from collections import Counter
>+from collections import Counter, OrderedDict
> 
>-month = ''
>-if len(sys.argv) >= 2:
>-    month = sys.argv[1]
>+URL = 'http://lists.freedesktop.org/archives/libreoffice-bugs/{}.txt.gz'
>+ENTITIES = OrderedDict({
>+    'changers': re.compile(r'^(.+)\schanged:$', re.MULTILINE),
>+    'reporters': re.compile(r'^\s*Reporter:\s(.+)$', re.MULTILINE),
>+    'commentators': re.compile(r'^--- Comment #\d+ from (.+) ---$',
>+        re.MULTILINE),
>+})
> 
>-url = 'http://lists.freedesktop.org/archives/libreoffice-bugs/' + month + '.txt.gz'
>-print('Downloading ' + url)
>+def get_parser():
>+    """Returns an argparse instance, setting the arguments for the script"""
>+    parser = argparse.ArgumentParser(
>+        description='LibreOffice contributor statistics')
>+    parser.add_argument('-m', '--month', dest='month', type=int,
>+        default=datetime.date.today().month,
>+        help='month to generate statistics from (default is current month)')
>+    parser.add_argument('-y', '--year', dest='year', type=int,
>+        default=datetime.date.today().year,
>+        help='year to generate statistics from (default is current year)')
>+    parser.add_argument('-n', '--num', dest='num', type=int, default=None,
>+        help='number of top contributors of each category (default is all)')
>+    parser.add_argument('--csv', dest='csv', action='store_true',
>+        help='output information in CSV format')
> 
>-try:
>-    response = urlopen(url)
>-    buf = BytesIO(response.read())
>-    gz = gzip.GzipFile(fileobj=buf)
>+    return parser
> 
>-    txt = gz.read().decode('us-ascii')
>-    gz.close()
>+def get_fname(date):
>+    """Returns the `Libreoffice-bugs Archives' file name for a given a @date
>+    datetime object. Note that only year and month are relevant, day is
>+    ignored"""
>+    return '{}-{}'.format(date.year, date.strftime('%B'))
> 
>-    reportedby = re.compile(r'^.*Reporter:.(.*)$', re.MULTILINE)
>-    reporters = re.findall(reportedby, txt)
>+def get_data(url):
>+    """Fetches and uncompresses the `Libreoffice-bugs Archives' file given its
>+    @url. The return of the function is the content of the gile as a string"""
>+    try:
>+        resp = urlopen(url)
>+    except URLError:
>+        sys.stderr.write('Error fetching {}'.format(url))
>+        sys.exit(1)
>+    else:
>+        with gzip.GzipFile(fileobj=BytesIO(resp.read())) as f:
>+            return f.read().decode('us-ascii')
> 
>-    wrangledby = re.compile(r'^.*<(.*)> changed:$', re.MULTILINE)
>-    wranglers = re.findall(wrangledby, txt)
>+def get_entity_values(data, pattern, num):
>+    """Returns the first @num matches of a @pattern in the @data string. If
>+    @num is None, all matches are returned"""
>+    values = re.findall(pattern, data)
>+    return Counter(values).most_common(num)
> 
>-    topreporters = Counter(reporters).most_common(30)
>-    topwranglers = Counter(wranglers).most_common(30)
>+def nice_print(values_dict, num_output, date):
>+    """Prints to stdout the output of the script in a human readable way.
>+    @values_dict is a dict containing a key for each entity (e.g. wranglers,
>+    reporters, etc), and as values, a list of tuples containing the name and
>+    the number of occurrences. An example:
> 
>-    print('\n=== ' + month[5:] + ' ' + month[:4] + '===')
>-    print('\n--- Top 30 reporters ---')
>-    for reporter in topreporters:
>-        print('{0:40}{1:5d}'.format(reporter[0], reporter[1]))
>+    >>> {
>+    >>>    'wranglers': [
>+    >>>        ('Wrangler 1 <wrangler1@his_email.com>', 30),
>+    >>>            # 30 is the number of times he wrangled
>+    >>>        ('Wrangler 2 <wrangler2@his_email.com>', 15),
>+    >>>    ]
>+    >>> }
> 
>-    print('\n--- Top 30 wranglers ---')
>-    for wrangler in topwranglers:
>-        print('{0:40}{1:5d}'.format(wrangler[0], wrangler[1]))
>+    @num_output is the number of top values in each categories are requested
>+    to be displayed (e.g. number of top wranglers), and @date is a datetime
>+    object containing the requested year and month"""
>+    print('=== {} ==='.format(date.strftime('%B %Y')))
>+    print()
>+    for name, values in values_dict.items():
>+        print('--- Top {} {} ---'.format(num_output or '', name))
>+        print('\n'.join('{0:75}{1:5d}'.format(*v) for v in values))
>+        print()
> 
>-except URLError:
>-    print('Unknown file - give an archive in the form YYYY-Month as argv[1]')
>+def csv_print(values_dict):
>+    """Print to stdout the output of the script in CSV format. @values_dict
>+    has the same format as for the `nice_print' function. The CSV file has
>+    the default format for Python's csv module (comma delimited, strings
>+    quoted when necessary)"""
>+    writer = csv.writer(sys.stdout)
>+    for entity_name, values in values_dict.items():
>+        for val_name, val_count in values:
>+            writer.writerow([entity_name, val_name, val_count])
>+
>+def main(args):
>+    """Main function of the program.
>+     * Fetches the file for the requested month and date
>+     * For each defined entity, gathers each match of its pattern,
>+        and counts the number of occurrences
>+     * Prints the retrieved information to stdout in the requested format
>+    """
>+    date = datetime.date(args.year, args.month, 1)
>+    fname = get_fname(date)
>+    url = URL.format(fname)
>+    data = get_data(url)
>+    values = OrderedDict()
>+    for name, regex in ENTITIES.items():
>+        values[name] = get_entity_values(data, regex, args.num)
>+
>+    if args.csv:
>+        csv_print(values)
>+    else:
>+        nice_print(values, args.num, date)
>+
>+if __name__ == '__main__':
>+    parser = get_parser()
>+    args = parser.parse_args()
>+    main(args)
> 
>-- 
>1.7.7.6
>

Actions: View

Attachments on bug 54110: 66182 | 66235 | 66241 | 66242 | 66244 | 66247 | 78586 | 78598