logfile_interval 1.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/Gemfile.lock +35 -0
- data/LICENSE.txt +22 -0
- data/README.md +94 -0
- data/Rakefile +1 -0
- data/docs/design.rb +91 -0
- data/docs/design2.rb +77 -0
- data/docs/design3.rb +177 -0
- data/lib/logfile_interval.rb +12 -0
- data/lib/logfile_interval/file_backward.rb +49 -0
- data/lib/logfile_interval/interval.rb +42 -0
- data/lib/logfile_interval/interval_builder.rb +34 -0
- data/lib/logfile_interval/interval_length.rb +47 -0
- data/lib/logfile_interval/line_parser/aggregator.rb +61 -0
- data/lib/logfile_interval/line_parser/base.rb +94 -0
- data/lib/logfile_interval/line_parser/counter.rb +27 -0
- data/lib/logfile_interval/logfile.rb +33 -0
- data/lib/logfile_interval/logfile_set.rb +47 -0
- data/lib/logfile_interval/version.rb +3 -0
- data/logfile_interval.gemspec +25 -0
- data/spec/lib/interval_builder_spec.rb +49 -0
- data/spec/lib/interval_spec.rb +73 -0
- data/spec/lib/line_parser/aggregator_spec.rb +47 -0
- data/spec/lib/line_parser/base_spec.rb +84 -0
- data/spec/lib/logfile_set_spec.rb +39 -0
- data/spec/lib/logfile_spec.rb +39 -0
- data/spec/spec_helper.rb +9 -0
- data/spec/support/lib/access_log.rb +22 -0
- data/spec/support/lib/timing_log.rb +19 -0
- data/spec/support/logfiles/access.log +7 -0
- data/spec/support/logfiles/access.log.1 +3 -0
- data/spec/support/logfiles/access.log.2 +3 -0
- data/spec/support/logfiles/timing.log +3 -0
- data/spec/support/logfiles/timing.log.1 +3 -0
- metadata +149 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 304480b4bf3c9525f74bf9b835b3ec7fe72b64be
|
4
|
+
data.tar.gz: ca5f34f5a987aca00b22ea838e083c744793c545
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: e36b8d0c42fbaafed596dcb5c2770450bf7e10ce68d92326f3f04eab197bbb4faa8ea8fa0f7706b55883fd2d65a876435ab689533222148151787c3c58861ba6
|
7
|
+
data.tar.gz: 34bd857fd154d29703959693c7b33b0e15b4ab0824f97e84f4362aad1e009a332e8f0b1c96fdcde1321f3462666e3bd862c9f53cb15aab41807f6321346551b0
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
logfile_interval (0.0.1)
|
5
|
+
|
6
|
+
GEM
|
7
|
+
remote: https://rubygems.org/
|
8
|
+
specs:
|
9
|
+
columnize (0.3.6)
|
10
|
+
debugger (1.6.2)
|
11
|
+
columnize (>= 0.3.1)
|
12
|
+
debugger-linecache (~> 1.2.0)
|
13
|
+
debugger-ruby_core_source (~> 1.2.3)
|
14
|
+
debugger-linecache (1.2.0)
|
15
|
+
debugger-ruby_core_source (1.2.4)
|
16
|
+
diff-lcs (1.2.5)
|
17
|
+
rake (10.1.0)
|
18
|
+
rspec (2.14.1)
|
19
|
+
rspec-core (~> 2.14.0)
|
20
|
+
rspec-expectations (~> 2.14.0)
|
21
|
+
rspec-mocks (~> 2.14.0)
|
22
|
+
rspec-core (2.14.7)
|
23
|
+
rspec-expectations (2.14.4)
|
24
|
+
diff-lcs (>= 1.1.3, < 2.0)
|
25
|
+
rspec-mocks (2.14.4)
|
26
|
+
|
27
|
+
PLATFORMS
|
28
|
+
ruby
|
29
|
+
|
30
|
+
DEPENDENCIES
|
31
|
+
bundler (~> 1.3)
|
32
|
+
debugger
|
33
|
+
logfile_interval!
|
34
|
+
rake
|
35
|
+
rspec (~> 2.14.0)
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Philippe Le Rohellec
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,94 @@
|
|
1
|
+
# LogfileInterval
|
2
|
+
|
3
|
+
Logfile parser and aggregator
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'logfile_interval'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install logfile_interval
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
### Write a LineParser class
|
22
|
+
```ruby
|
23
|
+
module LogfileInterval
|
24
|
+
module LineParser
|
25
|
+
class AccessLog < Base
|
26
|
+
# Example line:
|
27
|
+
# 74.75.19.145 - - [31/Mar/2013:06:54:12 -0700] "GET /ppa/google_chrome HTTP/1.1" 200 7855 "https://www.google.com/" "Mozilla/5.0 Chrome/25.0.1364.160"
|
28
|
+
|
29
|
+
set_regex /^([\d\.]+)\s+\S+\s+\S+\s+\[(\d\d.*\d\d)\]\s+"(?:GET|POST|PUT|HEAD|DELETE)\s+(\S+)\s+HTTP\S+"\s+(\d+)\s+(\d+)\s+"([^"]*)"\s+"([^"]+)"$/
|
30
|
+
|
31
|
+
add_column :name => 'ip', :pos => 1, :agg_function => :group
|
32
|
+
add_column :name => 'timestamp', :pos => 2, :agg_function => :timestamp
|
33
|
+
add_column :name => 'code', :pos => 4, :agg_function => :group
|
34
|
+
add_column :name => 'length', :pos => 5, :agg_function => :average, :conversion => :integer
|
35
|
+
|
36
|
+
def time
|
37
|
+
Time.strptime(self.timestamp, '%d/%b/%Y:%H:%M:%S %z')
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
41
|
+
end
|
42
|
+
```
|
43
|
+
|
44
|
+
### Iterate through lines of a single file
|
45
|
+
And get a parsed record for each line.
|
46
|
+
```ruby
|
47
|
+
logfile = 'access.log'
|
48
|
+
parser = LineParser::AccessLog
|
49
|
+
|
50
|
+
log = LogfileInterval::Logfile.new(logfile, parser)
|
51
|
+
log.each_line do |line|
|
52
|
+
puts line.class # String
|
53
|
+
puts line
|
54
|
+
end
|
55
|
+
|
56
|
+
parser = LineParser::AccessLog
|
57
|
+
log.each_parsed_line do |record|
|
58
|
+
puts record.class # LineParser::AccessLog
|
59
|
+
puts record.ip
|
60
|
+
puts record.time
|
61
|
+
end
|
62
|
+
```
|
63
|
+
|
64
|
+
### Iterate through lines of multiples files
|
65
|
+
And get a parsed record for each line.
|
66
|
+
```ruby
|
67
|
+
logfiles = [ 'access.log', 'access.log.1', 'access.log.2' ]
|
68
|
+
set = LogfileInterval::LogfileSet.new(logfiles, parser)
|
69
|
+
set.each_parsed_line do |record|
|
70
|
+
puts record.class # LineParser::AccessLog
|
71
|
+
end
|
72
|
+
```
|
73
|
+
### Aggregate lines into intervals
|
74
|
+
```ruby
|
75
|
+
length = 5.minutes
|
76
|
+
interval_builder = LogfileInterval::IntervalBuilder.new(logfiles, length)
|
77
|
+
interval_builder.each_interval do |interval|
|
78
|
+
puts interval.class # LogfileInterval::Interval
|
79
|
+
puts interval.start_time
|
80
|
+
puts interval.length
|
81
|
+
interval[:ip].each do |ip, count|
|
82
|
+
puts "#{ip}, #{count}"
|
83
|
+
end
|
84
|
+
end
|
85
|
+
```
|
86
|
+
|
87
|
+
|
88
|
+
## Contributing
|
89
|
+
|
90
|
+
1. Fork it
|
91
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
92
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
93
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
94
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/docs/design.rb
ADDED
@@ -0,0 +1,91 @@
|
|
1
|
+
module LogfileInterval
|
2
|
+
class Logfile
|
3
|
+
end
|
4
|
+
|
5
|
+
class LogfileSet
|
6
|
+
end
|
7
|
+
|
8
|
+
class Interval
|
9
|
+
end
|
10
|
+
|
11
|
+
module LineParser
|
12
|
+
class Base
|
13
|
+
class << self
|
14
|
+
def set_regex(regex)
|
15
|
+
end
|
16
|
+
|
17
|
+
def add_column(name, options)
|
18
|
+
end
|
19
|
+
|
20
|
+
def parse(line)
|
21
|
+
@data = {}
|
22
|
+
|
23
|
+
match_data = regex.match(line)
|
24
|
+
columns.each do |name, options|
|
25
|
+
val = match_data[options[:pos]]
|
26
|
+
@data[name] = convert(val, options[:conversion])
|
27
|
+
end
|
28
|
+
@data
|
29
|
+
end
|
30
|
+
|
31
|
+
def convert(val, conversion)
|
32
|
+
case options[:conversion]
|
33
|
+
when :integer then val.to_i
|
34
|
+
else val
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
38
|
+
|
39
|
+
end
|
40
|
+
|
41
|
+
class AccessLog < Base
|
42
|
+
set_regex /blah/
|
43
|
+
add_column :name => :foo, :pos => 1, :conversion => integer, :agg_function => :average
|
44
|
+
|
45
|
+
end
|
46
|
+
end
|
47
|
+
|
48
|
+
class Record
|
49
|
+
def initialize(parser, line)
|
50
|
+
@parser = parser
|
51
|
+
@data = parser.parse(line)
|
52
|
+
end
|
53
|
+
|
54
|
+
def valid_columns
|
55
|
+
@parser.columns.keys
|
56
|
+
end
|
57
|
+
|
58
|
+
def method_missing(meth, *args)
|
59
|
+
if valid_columns.include?(meth) && args.none
|
60
|
+
self[meth]
|
61
|
+
else
|
62
|
+
super
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
logfiles = [ 'access.log', 'access.log.1', 'access.log.2' ]
|
69
|
+
logfile = logfiles.first
|
70
|
+
parser = LineParser::AccessLog.new
|
71
|
+
|
72
|
+
logfile_iterator = LogfileInterval::Logfile.new(parser, logfile)
|
73
|
+
|
74
|
+
logfile_iterator.each_line do |line|
|
75
|
+
puts line
|
76
|
+
end
|
77
|
+
|
78
|
+
logfile_iterator.each_parsed_line do |record|
|
79
|
+
puts record.ip
|
80
|
+
puts record.time
|
81
|
+
end
|
82
|
+
|
83
|
+
interval_builder = LogfileInterval::Interval.new(parser, logfiles)
|
84
|
+
|
85
|
+
interval_builder.each_interval do |interval|
|
86
|
+
puts interval.start_time
|
87
|
+
puts interval.length
|
88
|
+
interval[:ip].each do |ip, count|
|
89
|
+
puts "#{ip}, #{count}"
|
90
|
+
end
|
91
|
+
end
|
data/docs/design2.rb
ADDED
@@ -0,0 +1,77 @@
|
|
1
|
+
module LogfileInterval
|
2
|
+
class Logfile
|
3
|
+
end
|
4
|
+
|
5
|
+
class LogfileSet
|
6
|
+
end
|
7
|
+
|
8
|
+
class Interval
|
9
|
+
end
|
10
|
+
|
11
|
+
class LineParser
|
12
|
+
def initialize(regex, columns)
|
13
|
+
end
|
14
|
+
|
15
|
+
def parse(line)
|
16
|
+
@data = {}
|
17
|
+
|
18
|
+
match_data = regex.match(line)
|
19
|
+
columns.each do |name, options|
|
20
|
+
val = match_data[options[:pos]]
|
21
|
+
@data[name] = convert(val, options[:conversion])
|
22
|
+
end
|
23
|
+
@data
|
24
|
+
end
|
25
|
+
|
26
|
+
def convert(val, conversion)
|
27
|
+
case options[:conversion]
|
28
|
+
when :integer then val.to_i
|
29
|
+
else val
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
class Record
|
35
|
+
def initialize(parser, line)
|
36
|
+
@parser = parser
|
37
|
+
@data = parser.parse(line)
|
38
|
+
end
|
39
|
+
|
40
|
+
def valid_columns
|
41
|
+
@parser.columns.keys
|
42
|
+
end
|
43
|
+
|
44
|
+
def method_missing(meth, *args)
|
45
|
+
if valid_columns.include?(meth) && args.none
|
46
|
+
self[meth]
|
47
|
+
else
|
48
|
+
super
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
logfiles = [ 'access.log', 'access.log.1', 'access.log.2' ]
|
55
|
+
logfile = logfiles.first
|
56
|
+
parser = LineParser.new(/blah/, [ { :name=>:ip , :pos => 1 }, ...])
|
57
|
+
|
58
|
+
logfile_iterator = LogfileInterval::Logfile.new(parser, logfile)
|
59
|
+
|
60
|
+
logfile_iterator.each_line do |line|
|
61
|
+
puts line
|
62
|
+
end
|
63
|
+
|
64
|
+
logfile_iterator.each_parsed_line do |record|
|
65
|
+
puts record.ip
|
66
|
+
puts record.time
|
67
|
+
end
|
68
|
+
|
69
|
+
interval_builder = LogfileInterval::Interval.new(parser, logfiles)
|
70
|
+
|
71
|
+
interval_builder.each_interval do |interval|
|
72
|
+
puts interval.start_time
|
73
|
+
puts interval.length
|
74
|
+
interval[:ip].each do |ip, count|
|
75
|
+
puts "#{ip}, #{count}"
|
76
|
+
end
|
77
|
+
end
|
data/docs/design3.rb
ADDED
@@ -0,0 +1,177 @@
|
|
1
|
+
module LogfileInterval
|
2
|
+
module LineParser
|
3
|
+
class Base
|
4
|
+
class << self
|
5
|
+
def set_regex(regex)
|
6
|
+
end
|
7
|
+
|
8
|
+
def add_column(name, options)
|
9
|
+
aggregator = Aggregators.klass(agg_function)
|
10
|
+
@columns[name] = { :pos => pos, :agg_function => aggregator, :conversion => conversion }
|
11
|
+
define_method(name)
|
12
|
+
end
|
13
|
+
|
14
|
+
def parse(line)
|
15
|
+
match_data = regex.match(line)
|
16
|
+
@data = f(match_data)
|
17
|
+
end
|
18
|
+
|
19
|
+
def create_record(line)
|
20
|
+
record = new(line)
|
21
|
+
return record.valid? ? record : nil
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
end
|
26
|
+
|
27
|
+
class AccessLog < Base
|
28
|
+
set_regex /blah/
|
29
|
+
add_column :name => :foo, :pos => 1, :conversion => integer, :agg_function => :average
|
30
|
+
|
31
|
+
def initialize(line)
|
32
|
+
@data = self.class.parse(line)
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
module Aggregator
|
37
|
+
def self.klass(agg_function)
|
38
|
+
case agg_function
|
39
|
+
when :sum then Sum
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
class Sum
|
44
|
+
def initialize
|
45
|
+
@val = 0
|
46
|
+
end
|
47
|
+
|
48
|
+
def add(value)
|
49
|
+
@val += value
|
50
|
+
end
|
51
|
+
|
52
|
+
def value
|
53
|
+
@val
|
54
|
+
end
|
55
|
+
end
|
56
|
+
|
57
|
+
class Group
|
58
|
+
def initialize
|
59
|
+
@val = Counter.new
|
60
|
+
end
|
61
|
+
|
62
|
+
def add(value)
|
63
|
+
@val.increment(value)
|
64
|
+
end
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
class Logfile
|
70
|
+
def initialize(filename, parser)
|
71
|
+
end
|
72
|
+
|
73
|
+
def each_line
|
74
|
+
end
|
75
|
+
|
76
|
+
def each_parsed_line
|
77
|
+
each_line do |line|
|
78
|
+
record = parser.create_record(line)
|
79
|
+
yield record if record
|
80
|
+
end
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
class LogfileSet
|
85
|
+
def initialize(filenames_array, parser)
|
86
|
+
end
|
87
|
+
|
88
|
+
def ordered_filenams
|
89
|
+
end
|
90
|
+
|
91
|
+
def each_line
|
92
|
+
end
|
93
|
+
|
94
|
+
def each_parsed_line
|
95
|
+
end
|
96
|
+
end
|
97
|
+
|
98
|
+
class IntervalBuilder
|
99
|
+
def initialize(logfile_set, length)
|
100
|
+
parser = logfile_set.parser
|
101
|
+
end
|
102
|
+
|
103
|
+
def each_interval
|
104
|
+
interval = Interval.new(now, length)
|
105
|
+
set.each_parsed_line(parser) do |record|
|
106
|
+
while record.time < interval.start_time do
|
107
|
+
yield interval
|
108
|
+
interval = Interval.new(interval.start_time, length)
|
109
|
+
end
|
110
|
+
interval.add(record)
|
111
|
+
end
|
112
|
+
end
|
113
|
+
end
|
114
|
+
|
115
|
+
class Counter < Hash
|
116
|
+
def increment(key)
|
117
|
+
self[key] = self[key] ? self[key] + 1 : 1
|
118
|
+
end
|
119
|
+
end
|
120
|
+
|
121
|
+
class Interval
|
122
|
+
def initialize(end_time, length, parser)
|
123
|
+
@data = {}
|
124
|
+
parser.columns.each do |name, options|
|
125
|
+
@data[name] = options[:aggregator].new
|
126
|
+
end
|
127
|
+
end
|
128
|
+
|
129
|
+
def [](name)
|
130
|
+
@data[name].value
|
131
|
+
end
|
132
|
+
|
133
|
+
def add_record(record)
|
134
|
+
return unless record.valid?
|
135
|
+
raise ParserMismatch unless record.class == parser
|
136
|
+
|
137
|
+
@size += 1
|
138
|
+
parser.columns.each do |name, options|
|
139
|
+
@data[name].add(record[name])
|
140
|
+
end
|
141
|
+
end
|
142
|
+
end
|
143
|
+
end
|
144
|
+
|
145
|
+
logfiles = [ 'access.log', 'access.log.1', 'access.log.2' ]
|
146
|
+
logfile = logfiles.first
|
147
|
+
|
148
|
+
parser = LineParser::AccessLog
|
149
|
+
|
150
|
+
logfile_iterator = LogfileInterval::Logfile.new(logfile, parser)
|
151
|
+
logfile_iterator.each_line do |line|
|
152
|
+
puts line.class # String
|
153
|
+
puts line
|
154
|
+
end
|
155
|
+
|
156
|
+
parser = LineParser::AccessLog
|
157
|
+
logfile_iterator.each_parsed_line do |record|
|
158
|
+
puts record.class # LineParser::AccessLog
|
159
|
+
puts record.ip
|
160
|
+
puts record.time
|
161
|
+
end
|
162
|
+
|
163
|
+
set_iterator = LogfileInterval::LogfileSet.new(logfiles, parser)
|
164
|
+
set_iterator.each_parsed_line do |record|
|
165
|
+
puts record.class # LineParser::AccessLog
|
166
|
+
end
|
167
|
+
|
168
|
+
length = 5.minutes
|
169
|
+
interval_builder = LogfileInterval::IntervalBuilder.new(logfiles, length)
|
170
|
+
interval_builder.each_interval do |interval|
|
171
|
+
puts interval.class # LogfileInterval::Interval
|
172
|
+
puts interval.start_time
|
173
|
+
puts interval.length
|
174
|
+
interval[:ip].each do |ip, count|
|
175
|
+
puts "#{ip}, #{count}"
|
176
|
+
end
|
177
|
+
end
|