GitHub Access Token became invalid

It seems like the GitHub access token used for retrieving details about this repository from GitHub became invalid. This might prevent certain types of inspections from being run (in particular, everything related to pull requests).
Please ask an admin of your repository to re-new the access token on this website.

Issues (503)

tools/log_watcher.py (3 issues)

1
#!/usr/bin/env python2.7
2
# Licensed to the StackStorm, Inc ('StackStorm') under one or more
3
# contributor license agreements.  See the NOTICE file distributed with
4
# this work for additional information regarding copyright ownership.
5
# The ASF licenses this file to You under the Apache License, Version 2.0
6
# (the "License"); you may not use this file except in compliance with
7
# the License.  You may obtain a copy of the License at
8
#
9
#     http://www.apache.org/licenses/LICENSE-2.0
10
#
11
# Unless required by applicable law or agreed to in writing, software
12
# distributed under the License is distributed on an "AS IS" BASIS,
13
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
# See the License for the specific language governing permissions and
15
# limitations under the License.
16
17
from __future__ import print_function
18
import collections
19
import fnmatch
20
import os
21
import re
22
import sys
23
24
from tabulate import tabulate
25
import six
26
27
LOG_ALERT_PERCENT = 5  # default.
28
29
EVILS = [
30
    'info',
31
    'debug',
32
    'warning',
33
    'exception',
34
    'error',
35
    'audit'
36
]
37
38
LOG_VARS = [
39
    'LOG',
40
    'Log',
41
    'log',
42
    'LOGGER',
43
    'Logger',
44
    'logger',
45
    'logging',
46
    'LOGGING'
47
]
48
49
FILE_LOG_COUNT = collections.defaultdict()
50
FILE_LINE_COUNT = collections.defaultdict()
51
52
53
def _parse_args(args):
54
    global LOG_ALERT_PERCENT
0 ignored issues
show
Usage of the global statement should be avoided.

Usage of global can make code hard to read and test, its usage is generally not recommended unless you are dealing with legacy code.

Loading history...
55
    params = {}
56
    if len(args) > 1:
57
        params['alert_percent'] = args[1]
58
        LOG_ALERT_PERCENT = int(args[1])
59
    return params
60
61
62
def _skip_file(filename):
63
    if filename.startswith('.') or filename.startswith('_'):
64
        return True
65
66
67
def _get_files(dir_path):
68
    if not os.path.exists(dir_path):
69
        print('Directory %s doesn\'t exist.' % dir_path)
70
71
    files = []
72
    exclude = set(['virtualenv', 'build', '.tox'])
73
    for root, dirnames, filenames in os.walk(dir_path):
74
        dirnames[:] = [d for d in dirnames if d not in exclude]
75
        for filename in fnmatch.filter(filenames, '*.py'):
76
            if not _skip_file(filename):
77
                files.append(os.path.join(root, filename))
78
    return files
79
80
81
# TODO: Regex compiling will be faster but I cannot get it to work :(
82
def _build_regex():
83
    regex_strings = {}
84
    regexes = {}
85
    for level in EVILS:
86
        regex_string = '|'.join(['\.'.join([log, level]) for log in LOG_VARS])
0 ignored issues
show
A suspicious escape sequence \. was found. Did you maybe forget to add an r prefix?

Escape sequences in Python are generally interpreted according to rules similar to standard C. Only if strings are prefixed with r or R are they interpreted as regular expressions.

The escape sequence that was used indicates that you might have intended to write a regular expression.

Learn more about the available escape sequences. in the Python documentation.

Loading history...
87
        regex_strings[level] = regex_string
88
        # print('Level: %s, regex_string: %s' % (level, regex_strings[level]))
89
        regexes[level] = re.compile(regex_strings[level])
90
    return regexes
91
92
93
def _regex_match(line, regexes):
94
    pass
95
96
97
def _build_str_matchers():
98
    match_strings = {}
99
    for level in EVILS:
100
        match_strings[level] = ['.'.join([log, level]) for log in LOG_VARS]
101
    return match_strings
102
103
104
def _get_log_count_dict():
105
    return [(level, 0) for level in EVILS]
106
107
108
def _alert(fil, lines, logs, logs_level):
109
    print('WARNING: Too many logs!!!: File: %s, total lines: %d, log lines: %d, percent: %f, '
110
          'logs: %s' % (fil, lines, logs, float(logs) / lines * 100, logs_level))
111
112
113
def _match(line, match_strings):
114
    for level, match_strings in six.iteritems(match_strings):
115
        for match_string in match_strings:
116
            if line.startswith(match_string):
117
                # print('Line: %s, match: %s' % (line, match_string))
118
                return True, level, line
119
    return False, 'UNKNOWN', line
120
121
122
def _detect_log_lines(fil, matchers):
123
    global FILE_LOG_COUNT
0 ignored issues
show
The variable FILE_LOG_COUNT was imported from global scope, but was never written to.
Loading history...
124
    FILE_LOG_COUNT[fil] = dict(_get_log_count_dict())
125
    # print('Working on file: %s' % fil)
126
    with open(fil) as f:
127
        lines = f.readlines()
128
        FILE_LINE_COUNT[fil] = len(lines)
129
130
        ln = 0
131
        for line in lines:
132
            line = line.strip()
133
            ln += 1
134
            matched, level, line = _match(line, matchers)
135
            if matched:
136
                # print('File: %s, Level: %s, Line: %d:%s' % (fil, level, ln, line.strip()))
137
                FILE_LOG_COUNT[fil][level] += 1
138
139
140
def _post_process(file_dir):
141
    alerts = []
142
    for fil, lines in six.iteritems(FILE_LINE_COUNT):
143
        log_lines_count_level = FILE_LOG_COUNT[fil]
144
        total_log_count = 0
145
        for level, count in six.iteritems(log_lines_count_level):
146
            total_log_count += count
147
        if total_log_count > 0:
148
            if float(total_log_count) / lines * 100 > LOG_ALERT_PERCENT:
149
                if file_dir in fil:
150
                    fil = fil[len(file_dir) + 1:]
151
                alerts.append([fil, lines, total_log_count, float(total_log_count) / lines * 100,
152
                               log_lines_count_level['audit'],
153
                               log_lines_count_level['exception'],
154
                               log_lines_count_level['error'],
155
                               log_lines_count_level['warning'],
156
                               log_lines_count_level['info'],
157
                               log_lines_count_level['debug']])
158
    # sort by percent
159
    alerts.sort(key=lambda alert: alert[3], reverse=True)
160
    print(tabulate(alerts, headers=['File', 'Lines', 'Logs', 'Percent', 'adt', 'exc', 'err', 'wrn',
161
                                    'inf', 'dbg']))
162
163
164
def main(args):
165
    params = _parse_args(args)
166
    file_dir = params.get('dir', os.getcwd())
167
    files = _get_files(file_dir)
168
    matchers = _build_str_matchers()
169
    for f in files:
170
        _detect_log_lines(f, matchers)
171
    _post_process(file_dir)
172
173
174
if __name__ == '__main__':
175
    main(sys.argv)
176