fluent-plugin-referer-parser 0.0.1
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/.travis.yml +4 -0
- data/Gemfile +3 -0
- data/LICENSE.txt +14 -0
- data/README.md +38 -0
- data/Rakefile +11 -0
- data/fluent-plugin-referer-parser.gemspec +21 -0
- data/lib/fluent/plugin/.rubocop.yml +9 -0
- data/lib/fluent/plugin/out_referer_parser.rb +79 -0
- data/test/helper.rb +28 -0
- data/test/plugin/.rubocop.yml +25 -0
- data/test/plugin/test_out_referer_parser.rb +131 -0
- metadata +103 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 56f8bf0b194d231cd18480ccb8eb565b3f96da29
|
4
|
+
data.tar.gz: 653fbea2b2c809b8c027070ef1f86be948b9f728
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: af9bd61a4764e99dbc3ee371650bed74c4d26cbea11affb67bd01d82731dcb1e642367dda4d9c6c872fcf0330b70bd50137d39af6f8533f9f79e3c9a5c047cdb
|
7
|
+
data.tar.gz: c8f624d327d091b6b55535c044e8de72dca2d349ca176dd92f925a348098ae676ef65254e173b7e74747b15d26572f8fa9c26db06b126866af2daae6aa55ec52
|
data/.gitignore
ADDED
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
Copyright (c) 2012- TAGOMORI Satoshi
|
2
|
+
Copyright (c) HARUYAMA Seigo
|
3
|
+
|
4
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
5
|
+
you may not use this file except in compliance with the License.
|
6
|
+
You may obtain a copy of the License at
|
7
|
+
|
8
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
9
|
+
|
10
|
+
Unless required by applicable law or agreed to in writing, software
|
11
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
12
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
13
|
+
See the License for the specific language governing permissions and
|
14
|
+
limitations under the License.
|
data/README.md
ADDED
@@ -0,0 +1,38 @@
|
|
1
|
+
# fluent-plugin-referer-parser
|
2
|
+
|
3
|
+
## WootheeOutput
|
4
|
+
|
5
|
+
'fluent-plugin-referer-parser' is a Fluentd plugin to parse Referer strings, based on [tagomoris/fluent-plugin-woothee](https://github.com/tagomoris/fluent-plugin-woothee).
|
6
|
+
'fluent-plugin-referer-parser' uses [snowplow/referer-parser](https://github.com/snowplow/referer-parser).
|
7
|
+
|
8
|
+
|
9
|
+
## Configuration
|
10
|
+
|
11
|
+
To add referer-parser result into matched messages:
|
12
|
+
|
13
|
+
<match input.**>
|
14
|
+
type referer_parser
|
15
|
+
key_name referer
|
16
|
+
remove_prefix input
|
17
|
+
add_prefix merged
|
18
|
+
</match>
|
19
|
+
|
20
|
+
Output messages with tag 'merged.**' has 'referer\_known', 'referer\_referer' and 'referer\_search\_term' attributes. If you want to change attribute names, write configurations as below:
|
21
|
+
|
22
|
+
<match input.**>
|
23
|
+
type referer_parser
|
24
|
+
key_name ref
|
25
|
+
remove_prefix input
|
26
|
+
add_prefix merged
|
27
|
+
out_key_known ref_known
|
28
|
+
out_key_referer ref_referer
|
29
|
+
out_key_search_term ref_search_term
|
30
|
+
</match>
|
31
|
+
|
32
|
+
|
33
|
+
## Copyright
|
34
|
+
|
35
|
+
* Copyright (c) 2012- TAGOMORI Satoshi (tagomoris)
|
36
|
+
* Copyright (c) HARUYAMA Seigo
|
37
|
+
* License
|
38
|
+
* Apache License, Version 2.0
|
data/Rakefile
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
|
3
|
+
Gem::Specification.new do |gem|
|
4
|
+
gem.name = 'fluent-plugin-referer-parser'
|
5
|
+
gem.version = '0.0.1'
|
6
|
+
gem.authors = ['TAGOMORI Satoshi', 'HARUYAMA Seigo']
|
7
|
+
gem.email = ['tagomoris@gmail.com', 'haruyama@unixuser.org']
|
8
|
+
gem.description = %q{parsing by referer-parser. See: https://github.com/snowplow/referer-parser}
|
9
|
+
gem.summary = %q{Fluentd plugin to parse UserAgent strings}
|
10
|
+
gem.homepage = 'https://github.com/haruyama/fluent-plugin-referer-parser'
|
11
|
+
gem.license = 'APLv2'
|
12
|
+
|
13
|
+
gem.files = `git ls-files`.split($\)
|
14
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
15
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
16
|
+
gem.require_paths = ['lib']
|
17
|
+
|
18
|
+
gem.add_development_dependency 'rake'
|
19
|
+
gem.add_runtime_dependency 'fluentd'
|
20
|
+
gem.add_runtime_dependency 'referer-parser', '>= 0.2.0'
|
21
|
+
end
|
@@ -0,0 +1,79 @@
|
|
1
|
+
require 'ostruct'
|
2
|
+
|
3
|
+
# referer parser output
|
4
|
+
class Fluent::RefererParserOutput < Fluent::Output
|
5
|
+
Fluent::Plugin.register_output('referer_parser', self)
|
6
|
+
|
7
|
+
config_param :tag, :string, default: nil
|
8
|
+
config_param :remove_prefix, :string, default: nil
|
9
|
+
config_param :add_prefix, :string, default: nil
|
10
|
+
|
11
|
+
config_param :key_name, :string
|
12
|
+
|
13
|
+
config_param :merge_referer_info, :bool, default: false
|
14
|
+
config_param :out_key_known, :string, default: 'referer_known'
|
15
|
+
config_param :out_key_referer, :string, default: 'referer_referer'
|
16
|
+
config_param :out_key_search_term, :string, default: 'referer_search_term'
|
17
|
+
|
18
|
+
UNKOWWN_STRING = 'UNKNOWN'
|
19
|
+
PARSE_ERROR_STRUCT = OpenStruct.new(known: false)
|
20
|
+
|
21
|
+
def initialize
|
22
|
+
super
|
23
|
+
require 'referer-parser'
|
24
|
+
end
|
25
|
+
|
26
|
+
def configure(conf)
|
27
|
+
super
|
28
|
+
|
29
|
+
if !@tag && !@remove_prefix && !@add_prefix
|
30
|
+
fail Fluent::ConfigError, 'missing both of remove_prefix and add_prefix'
|
31
|
+
end
|
32
|
+
if @tag && (@remove_prefix || @add_prefix)
|
33
|
+
fail Fluent::ConfigError, 'both of tag and remove_prefix/add_prefix must not be specified'
|
34
|
+
end
|
35
|
+
if @remove_prefix
|
36
|
+
@removed_prefix_string = @remove_prefix + '.'
|
37
|
+
@removed_length = @removed_prefix_string.length
|
38
|
+
end
|
39
|
+
@added_prefix_string = @add_prefix + '.' if @add_prefix
|
40
|
+
end
|
41
|
+
|
42
|
+
def tag_mangle(tag)
|
43
|
+
if @tag
|
44
|
+
@tag
|
45
|
+
else
|
46
|
+
if @remove_prefix &&
|
47
|
+
( (tag.start_with?(@removed_prefix_string) && tag.length > @removed_length) || tag == @remove_prefix)
|
48
|
+
tag = tag[@removed_length..-1]
|
49
|
+
end
|
50
|
+
if @add_prefix
|
51
|
+
tag = if tag && tag.length > 0
|
52
|
+
@added_prefix_string + tag
|
53
|
+
else
|
54
|
+
@add_prefix
|
55
|
+
end
|
56
|
+
end
|
57
|
+
tag
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
def emit(tag, es, chain)
|
62
|
+
tag = tag_mangle(tag)
|
63
|
+
es.each do |time, record|
|
64
|
+
parsed =
|
65
|
+
begin
|
66
|
+
RefererParser::Referer.new(record[@key_name])
|
67
|
+
rescue
|
68
|
+
PARSE_ERROR_STRUCT
|
69
|
+
end
|
70
|
+
record.merge!(
|
71
|
+
@out_key_known => parsed.known,
|
72
|
+
@out_key_referer => parsed.referer || UNKOWWN_STRING,
|
73
|
+
@out_key_search_term => parsed.search_term || UNKOWWN_STRING,
|
74
|
+
)
|
75
|
+
Fluent::Engine.emit(tag, time, record)
|
76
|
+
end
|
77
|
+
chain.next
|
78
|
+
end
|
79
|
+
end
|
data/test/helper.rb
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'bundler'
|
3
|
+
begin
|
4
|
+
Bundler.setup(:default, :development)
|
5
|
+
rescue Bundler::BundlerError => e
|
6
|
+
$stderr.puts e.message
|
7
|
+
$stderr.puts 'Run `bundle install` to install missing gems'
|
8
|
+
exit e.status_code
|
9
|
+
end
|
10
|
+
require 'test/unit'
|
11
|
+
|
12
|
+
$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
|
13
|
+
$LOAD_PATH.unshift(File.dirname(__FILE__))
|
14
|
+
require 'fluent/test'
|
15
|
+
unless ENV.key?('VERBOSE')
|
16
|
+
nulllogger = Object.new
|
17
|
+
nulllogger.instance_eval do |obj|
|
18
|
+
def method_missing(method, *args)
|
19
|
+
# pass
|
20
|
+
end
|
21
|
+
end
|
22
|
+
$log = nulllogger
|
23
|
+
end
|
24
|
+
|
25
|
+
require 'fluent/plugin/out_referer_parser'
|
26
|
+
|
27
|
+
class Test::Unit::TestCase
|
28
|
+
end
|
@@ -0,0 +1,25 @@
|
|
1
|
+
LineLength:
|
2
|
+
Enabled: false
|
3
|
+
|
4
|
+
MethodLength:
|
5
|
+
Enabled: true
|
6
|
+
CountComments: false # count full line comments?
|
7
|
+
Max: 50
|
8
|
+
|
9
|
+
FavorSprintf:
|
10
|
+
Enabled: false
|
11
|
+
|
12
|
+
MultilineBlocks:
|
13
|
+
Enabled: false
|
14
|
+
|
15
|
+
AvoidPerlBackrefs:
|
16
|
+
Enabled: false
|
17
|
+
|
18
|
+
PercentLiterals:
|
19
|
+
Enabled: false
|
20
|
+
|
21
|
+
BraceAfterPercent:
|
22
|
+
Enabled: false
|
23
|
+
|
24
|
+
ClassLength:
|
25
|
+
Enabled: false
|
@@ -0,0 +1,131 @@
|
|
1
|
+
require 'helper'
|
2
|
+
|
3
|
+
# RefererParserOutput test
|
4
|
+
class Fluent::RefererParserOutputTest < Test::Unit::TestCase
|
5
|
+
# through & merge
|
6
|
+
CONFIG1 = %[
|
7
|
+
type referer_parser
|
8
|
+
key_name referer
|
9
|
+
remove_prefix test
|
10
|
+
add_prefix merged
|
11
|
+
]
|
12
|
+
|
13
|
+
CONFIG2 = %[
|
14
|
+
type referer_parser
|
15
|
+
key_name ref
|
16
|
+
remove_prefix test
|
17
|
+
add_prefix merged
|
18
|
+
out_key_known ref_known
|
19
|
+
out_key_referer ref_referer
|
20
|
+
out_key_search_term ref_search_term
|
21
|
+
]
|
22
|
+
|
23
|
+
def create_driver(conf = CONFIG1, tag = 'test')
|
24
|
+
Fluent::Test::OutputTestDriver.new(Fluent::RefererParserOutput, tag).configure(conf)
|
25
|
+
end
|
26
|
+
|
27
|
+
def test_configure
|
28
|
+
# through & merge
|
29
|
+
d = create_driver CONFIG1
|
30
|
+
assert_equal 'referer', d.instance.key_name
|
31
|
+
assert_equal 'test', d.instance.remove_prefix
|
32
|
+
assert_equal 'merged', d.instance.add_prefix
|
33
|
+
|
34
|
+
assert_equal 'referer_known', d.instance.out_key_known
|
35
|
+
assert_equal 'referer_referer', d.instance.out_key_referer
|
36
|
+
assert_equal 'referer_search_term', d.instance.out_key_search_term
|
37
|
+
|
38
|
+
# filter & merge
|
39
|
+
d = create_driver CONFIG2
|
40
|
+
assert_equal 'ref', d.instance.key_name
|
41
|
+
assert_equal 'test', d.instance.remove_prefix
|
42
|
+
assert_equal 'merged', d.instance.add_prefix
|
43
|
+
|
44
|
+
assert_equal 'ref_known', d.instance.out_key_known
|
45
|
+
assert_equal 'ref_referer', d.instance.out_key_referer
|
46
|
+
assert_equal 'ref_search_term', d.instance.out_key_search_term
|
47
|
+
end
|
48
|
+
|
49
|
+
def test_tag_mangle
|
50
|
+
p = create_driver(CONFIG1).instance
|
51
|
+
assert_equal 'merged.data', p.tag_mangle('data')
|
52
|
+
assert_equal 'merged.data', p.tag_mangle('test.data')
|
53
|
+
assert_equal 'merged.test.data', p.tag_mangle('test.test.data')
|
54
|
+
assert_equal 'merged', p.tag_mangle('test')
|
55
|
+
end
|
56
|
+
|
57
|
+
def test_emit1
|
58
|
+
d = create_driver(CONFIG1, 'test.message')
|
59
|
+
time = Time.parse('2012-07-20 16:40:30').to_i
|
60
|
+
d.run do
|
61
|
+
d.emit({ 'value' => 0 }, time)
|
62
|
+
d.emit({ 'value' => 1, 'referer' => 'http://www.google.com/search?q=gateway+oracle+cards+denise+linn&hl=en&client=safari' }, time)
|
63
|
+
d.emit({ 'value' => 2, 'referer' => 'http://www.unixuser.org/' }, time)
|
64
|
+
end
|
65
|
+
|
66
|
+
emits = d.emits
|
67
|
+
assert_equal 3, emits.size
|
68
|
+
assert_equal 'merged.message', emits[0][0]
|
69
|
+
assert_equal time, emits[0][1]
|
70
|
+
|
71
|
+
m = emits[0][2]
|
72
|
+
assert_equal 0, m['value']
|
73
|
+
assert_equal false, m['referer_known']
|
74
|
+
assert_equal 'UNKNOWN', m['referer_referer']
|
75
|
+
assert_equal 'UNKNOWN', m['referer_search_term']
|
76
|
+
assert_equal 4, m.keys.size
|
77
|
+
|
78
|
+
m = emits[1][2]
|
79
|
+
assert_equal 1, m['value']
|
80
|
+
assert_equal true, m['referer_known']
|
81
|
+
assert_equal 'Google', m['referer_referer']
|
82
|
+
assert_equal 'gateway oracle cards denise linn', m['referer_search_term']
|
83
|
+
|
84
|
+
m = emits[2][2]
|
85
|
+
assert_equal 2, m['value']
|
86
|
+
assert_equal false, m['referer_known']
|
87
|
+
assert_equal 'UNKNOWN', m['referer_referer']
|
88
|
+
assert_equal 'UNKNOWN', m['referer_search_term']
|
89
|
+
end
|
90
|
+
|
91
|
+
def test_emit2
|
92
|
+
d = create_driver(CONFIG2, 'test.message')
|
93
|
+
time = Time.parse('2012-07-20 16:40:30').to_i
|
94
|
+
d.run do
|
95
|
+
d.emit({ 'value' => 0 }, time)
|
96
|
+
d.emit({ 'value' => 1, 'ref' => 'http://www.google.com/search?q=gateway+oracle+cards+denise+linn&hl=en&client=safari' }, time)
|
97
|
+
d.emit({ 'value' => 2, 'ref' => 'http://www.unixuser.org/' }, time)
|
98
|
+
d.emit({ 'value' => 3, 'ref' => 'https://www.google.com/search?q=%E3%81%BB%E3%81%92&ie=utf-8&oe=utf-8' }, time)
|
99
|
+
end
|
100
|
+
|
101
|
+
emits = d.emits
|
102
|
+
assert_equal 4, emits.size
|
103
|
+
assert_equal 'merged.message', emits[0][0]
|
104
|
+
assert_equal time, emits[0][1]
|
105
|
+
|
106
|
+
m = emits[0][2]
|
107
|
+
assert_equal 0, m['value']
|
108
|
+
assert_equal false, m['ref_known']
|
109
|
+
assert_equal 'UNKNOWN', m['ref_referer']
|
110
|
+
assert_equal 'UNKNOWN', m['ref_search_term']
|
111
|
+
assert_equal 4, m.keys.size
|
112
|
+
|
113
|
+
m = emits[1][2]
|
114
|
+
assert_equal 1, m['value']
|
115
|
+
assert_equal true, m['ref_known']
|
116
|
+
assert_equal 'Google', m['ref_referer']
|
117
|
+
assert_equal 'gateway oracle cards denise linn', m['ref_search_term']
|
118
|
+
|
119
|
+
m = emits[2][2]
|
120
|
+
assert_equal 2, m['value']
|
121
|
+
assert_equal false, m['ref_known']
|
122
|
+
assert_equal 'UNKNOWN', m['ref_referer']
|
123
|
+
assert_equal 'UNKNOWN', m['ref_search_term']
|
124
|
+
|
125
|
+
m = emits[3][2]
|
126
|
+
assert_equal 3, m['value']
|
127
|
+
assert_equal true, m['ref_known']
|
128
|
+
assert_equal 'Google', m['ref_referer']
|
129
|
+
assert_equal 'ほげ', m['ref_search_term']
|
130
|
+
end
|
131
|
+
end
|
metadata
ADDED
@@ -0,0 +1,103 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: fluent-plugin-referer-parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- TAGOMORI Satoshi
|
8
|
+
- HARUYAMA Seigo
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-12-30 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
15
|
+
name: rake
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
requirements:
|
18
|
+
- - '>='
|
19
|
+
- !ruby/object:Gem::Version
|
20
|
+
version: '0'
|
21
|
+
type: :development
|
22
|
+
prerelease: false
|
23
|
+
version_requirements: !ruby/object:Gem::Requirement
|
24
|
+
requirements:
|
25
|
+
- - '>='
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
version: '0'
|
28
|
+
- !ruby/object:Gem::Dependency
|
29
|
+
name: fluentd
|
30
|
+
requirement: !ruby/object:Gem::Requirement
|
31
|
+
requirements:
|
32
|
+
- - '>='
|
33
|
+
- !ruby/object:Gem::Version
|
34
|
+
version: '0'
|
35
|
+
type: :runtime
|
36
|
+
prerelease: false
|
37
|
+
version_requirements: !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - '>='
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: '0'
|
42
|
+
- !ruby/object:Gem::Dependency
|
43
|
+
name: referer-parser
|
44
|
+
requirement: !ruby/object:Gem::Requirement
|
45
|
+
requirements:
|
46
|
+
- - '>='
|
47
|
+
- !ruby/object:Gem::Version
|
48
|
+
version: 0.2.0
|
49
|
+
type: :runtime
|
50
|
+
prerelease: false
|
51
|
+
version_requirements: !ruby/object:Gem::Requirement
|
52
|
+
requirements:
|
53
|
+
- - '>='
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
version: 0.2.0
|
56
|
+
description: 'parsing by referer-parser. See: https://github.com/snowplow/referer-parser'
|
57
|
+
email:
|
58
|
+
- tagomoris@gmail.com
|
59
|
+
- haruyama@unixuser.org
|
60
|
+
executables: []
|
61
|
+
extensions: []
|
62
|
+
extra_rdoc_files: []
|
63
|
+
files:
|
64
|
+
- .gitignore
|
65
|
+
- .travis.yml
|
66
|
+
- Gemfile
|
67
|
+
- LICENSE.txt
|
68
|
+
- README.md
|
69
|
+
- Rakefile
|
70
|
+
- fluent-plugin-referer-parser.gemspec
|
71
|
+
- lib/fluent/plugin/.rubocop.yml
|
72
|
+
- lib/fluent/plugin/out_referer_parser.rb
|
73
|
+
- test/helper.rb
|
74
|
+
- test/plugin/.rubocop.yml
|
75
|
+
- test/plugin/test_out_referer_parser.rb
|
76
|
+
homepage: https://github.com/haruyama/fluent-plugin-referer-parser
|
77
|
+
licenses:
|
78
|
+
- APLv2
|
79
|
+
metadata: {}
|
80
|
+
post_install_message:
|
81
|
+
rdoc_options: []
|
82
|
+
require_paths:
|
83
|
+
- lib
|
84
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
85
|
+
requirements:
|
86
|
+
- - '>='
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: '0'
|
89
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
90
|
+
requirements:
|
91
|
+
- - '>='
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '0'
|
94
|
+
requirements: []
|
95
|
+
rubyforge_project:
|
96
|
+
rubygems_version: 2.2.0
|
97
|
+
signing_key:
|
98
|
+
specification_version: 4
|
99
|
+
summary: Fluentd plugin to parse UserAgent strings
|
100
|
+
test_files:
|
101
|
+
- test/helper.rb
|
102
|
+
- test/plugin/.rubocop.yml
|
103
|
+
- test/plugin/test_out_referer_parser.rb
|