fluent-plugin-rewrite-tag-filter 0.0.7 → 0.0.8
Sign up to get free protection for your applications and to get access to all the features.
data/README.rdoc
CHANGED
@@ -14,13 +14,17 @@ user-agent, and request-uri and so on with regular expression.
|
|
14
14
|
gem install fluent-plugin-rewrite-tag-filter
|
15
15
|
|
16
16
|
# td-agent user
|
17
|
-
/usr/lib64/fluent/ruby/bin/gem install fluent-plugin-rewrite-tag-filter
|
17
|
+
/usr/lib64/fluent/ruby/bin/fluent-gem install fluent-plugin-rewrite-tag-filter
|
18
18
|
|
19
19
|
== Configuration
|
20
20
|
|
21
|
-
|
21
|
+
Syntax
|
22
22
|
|
23
23
|
rewruterule<num:1-200> <attribute> <regex_pattern> <new_tag>
|
24
|
+
|
25
|
+
# Option: Capitalize every matched regex backreference (ex: $1, $2).
|
26
|
+
# It has described on usage section below.
|
27
|
+
capitalize_regex_backreference <default:no>
|
24
28
|
|
25
29
|
Usage
|
26
30
|
|
@@ -36,10 +40,12 @@ Usage
|
|
36
40
|
|
37
41
|
<match td.apache.access>
|
38
42
|
type rewrite_tag_filter
|
43
|
+
capitalize_regex_backreference yes
|
39
44
|
rewriterule1 path \.(gif|jpe?g|png|pdf|zip)$ clear
|
40
|
-
rewriterule2 domain ^maps\.
|
41
|
-
rewriterule3 domain ^news\.
|
42
|
-
|
45
|
+
rewriterule2 domain ^maps\.example\.com$ site.ExampleMaps
|
46
|
+
rewriterule3 domain ^news\.example\.com$ site.ExampleNews
|
47
|
+
# "site.$2$1" to be "site.ExampleMail" by capitalize_regex_backreference option.
|
48
|
+
rewriterule4 domain ^(mail)\.(example)\.com$ site.$2$1
|
43
49
|
rewriterule5 domain .+ site.unmatched
|
44
50
|
</match>
|
45
51
|
|
@@ -60,13 +66,13 @@ Usage
|
|
60
66
|
Result
|
61
67
|
|
62
68
|
$ mongo
|
63
|
-
MongoDB shell version: 2.0
|
69
|
+
MongoDB shell version: 2.2.0
|
64
70
|
> use apache_access
|
65
71
|
switched to db apache_access
|
66
72
|
> show collections
|
67
|
-
|
68
|
-
|
69
|
-
|
73
|
+
ExampleMaps
|
74
|
+
ExampleNews
|
75
|
+
ExampleMail
|
70
76
|
unmatched
|
71
77
|
|
72
78
|
== Example
|
data/example2.conf
CHANGED
@@ -29,7 +29,7 @@
|
|
29
29
|
rewriterule1 path ^/(img|css|js|static|assets)/ clear
|
30
30
|
rewriterule2 status ^(?!200)$ clear
|
31
31
|
rewriterule3 method ^(?!GET)$ clear
|
32
|
-
rewriterule4 agent
|
32
|
+
rewriterule4 agent Mac\sOS\sX clear
|
33
33
|
rewriterule5 agent (spider|bot|crawler|\+http\:) clear
|
34
34
|
rewriterule6 path ^/(admin|api|backend) site.GoogleMap.backend
|
35
35
|
rewriterule7 path .+ site.GoogleMap.front
|
@@ -3,7 +3,7 @@ $:.push File.expand_path("../lib", __FILE__)
|
|
3
3
|
|
4
4
|
Gem::Specification.new do |s|
|
5
5
|
s.name = "fluent-plugin-rewrite-tag-filter"
|
6
|
-
s.version = "0.0.
|
6
|
+
s.version = "0.0.8"
|
7
7
|
s.authors = ["Kentaro Yoshida"]
|
8
8
|
s.email = ["y.ken.studio@gmail.com"]
|
9
9
|
s.homepage = "https://github.com/y-ken/fluent-plugin-rewrite-tag-filter"
|
@@ -7,6 +7,7 @@ class Fluent::RewriteTagFilterOutput < Fluent::Output
|
|
7
7
|
(2..PATTERN_MAX_NUM).each do |i|
|
8
8
|
config_param ('rewriterule' + i.to_s).to_sym, :string, :default => nil # NAME REGEXP
|
9
9
|
end
|
10
|
+
config_param :capitalize_regex_backreference, :bool, :default => false
|
10
11
|
|
11
12
|
def configure(conf)
|
12
13
|
super
|
@@ -16,23 +17,24 @@ class Fluent::RewriteTagFilterOutput < Fluent::Output
|
|
16
17
|
|
17
18
|
invalids = conf.keys.select{|k| k =~ /^rewriterule(\d+)$/}.select{|arg| arg =~ /^rewriterule(\d+)/ and not (1..PATTERN_MAX_NUM).include?($1.to_i)}
|
18
19
|
if invalids.size > 0
|
19
|
-
$log.warn "invalid number rewriterules (valid rewriterule number:1-{PATTERN_MAX_NUM}):
|
20
|
+
$log.warn "invalid number rewriterules (valid rewriterule number:1-{PATTERN_MAX_NUM}): #{invalids.join(",")}"
|
20
21
|
end
|
21
22
|
(1..PATTERN_MAX_NUM).each do |i|
|
22
23
|
next unless conf["rewriterule#{i}"]
|
23
|
-
rewritekey,regexp,rewritetag = conf["rewriterule#{i}"].
|
24
|
+
rewritekey,regexp,rewritetag = conf["rewriterule#{i}"].match(/([^ ]+)\s(.+)\s([^ ]+)/).captures
|
24
25
|
unless regexp != nil && rewritetag != nil
|
25
|
-
raise Fluent::ConfigError, "missing values at
|
26
|
+
raise Fluent::ConfigError, "missing values at rewriterule#{i} " + conf["rewriterule#{i}"].inspect
|
26
27
|
end
|
27
28
|
@rewriterules.push([i, rewritekey, Regexp.new(regexp), rewritetag])
|
28
29
|
rewriterule_names.push(rewritekey + regexp)
|
30
|
+
$log.info "register rewrite_tag_filter rule: #{@rewriterules.last}"
|
29
31
|
end
|
30
32
|
rewriterule_index_list = conf.keys.select{|s| s =~ /^rewriterule\d$/}.map{|v| (/^rewriterule(\d)$/.match(v))[1].to_i}
|
31
33
|
unless rewriterule_index_list.reduce(true){|v,i| v and @rewriterules[i - 1]}
|
32
|
-
raise Fluent::ConfigError, "jump of rewriterule index found
|
34
|
+
raise Fluent::ConfigError, "jump of rewriterule index found #{@rewriterules.inspect}"
|
33
35
|
end
|
34
36
|
unless @rewriterules.length == rewriterule_names.uniq.length
|
35
|
-
raise Fluent::ConfigError, "duplicated rewriterules found
|
37
|
+
raise Fluent::ConfigError, "duplicated rewriterules found #{@rewriterules.inspect}"
|
36
38
|
end
|
37
39
|
end
|
38
40
|
|
@@ -45,6 +47,9 @@ class Fluent::RewriteTagFilterOutput < Fluent::Output
|
|
45
47
|
if (regexp && regexp.match(rewritevalue))
|
46
48
|
rewrite = true
|
47
49
|
tag = rewritetag
|
50
|
+
if rewritetag.include?('$')
|
51
|
+
tag = rewritetag.gsub(/\$\d+/, map_regex_table($~.captures))
|
52
|
+
end
|
48
53
|
break
|
49
54
|
end
|
50
55
|
end
|
@@ -53,5 +58,15 @@ class Fluent::RewriteTagFilterOutput < Fluent::Output
|
|
53
58
|
|
54
59
|
chain.next
|
55
60
|
end
|
61
|
+
|
62
|
+
def map_regex_table(elements)
|
63
|
+
hash_table = Hash.new
|
64
|
+
index = 1
|
65
|
+
elements.each do |value|
|
66
|
+
hash_table["$#{index}"] = @capitalize_regex_backreference ? value.capitalize : value
|
67
|
+
index += 1
|
68
|
+
end
|
69
|
+
return hash_table
|
70
|
+
end
|
56
71
|
end
|
57
72
|
|
@@ -4,11 +4,20 @@ class RewriteTagFilterOutputTest < Test::Unit::TestCase
|
|
4
4
|
def setup
|
5
5
|
Fluent::Test.setup
|
6
6
|
end
|
7
|
-
|
7
|
+
|
8
8
|
CONFIG = %[
|
9
9
|
rewriterule1 domain ^www\.google\.com$ site.Google
|
10
10
|
rewriterule2 domain ^news\.google\.com$ site.GoogleNews
|
11
|
-
rewriterule3 agent
|
11
|
+
rewriterule3 agent Mac\sOS\sX agent.MacOSX
|
12
|
+
rewriterule4 agent (Googlebot|CustomBot)-([a-zA-Z]+) agent.$1-$2
|
13
|
+
]
|
14
|
+
|
15
|
+
CONFIG2 = %[
|
16
|
+
capitalize_regex_backreference yes
|
17
|
+
rewriterule1 domain ^www\.google\.com$ site.Google
|
18
|
+
rewriterule2 domain ^(news)\.(google)\.com$ site.$2$1
|
19
|
+
rewriterule3 agent Mac\sOS\sX agent.MacOSX
|
20
|
+
rewriterule4 agent (Googlebot|CustomBot)-([a-zA-Z]+) agent.$1-$2
|
12
21
|
]
|
13
22
|
|
14
23
|
def create_driver(conf=CONFIG,tag='test')
|
@@ -35,13 +44,41 @@ class RewriteTagFilterOutputTest < Test::Unit::TestCase
|
|
35
44
|
d1.emit({'domain' => 'www.google.com', 'path' => '/foo/bar?key=value', 'agent' => 'Googlebot', 'response_time' => 1000000})
|
36
45
|
d1.emit({'domain' => 'news.google.com', 'path' => '/', 'agent' => 'Googlebot-Mobile', 'response_time' => 900000})
|
37
46
|
d1.emit({'domain' => 'map.google.com', 'path' => '/', 'agent' => 'Macintosh; Intel Mac OS X 10_7_4', 'response_time' => 900000})
|
47
|
+
d1.emit({'domain' => 'labs.google.com', 'path' => '/', 'agent' => 'Mozilla/5.0 Googlebot-FooBar/2.1', 'response_time' => 900000})
|
48
|
+
end
|
49
|
+
emits = d1.emits
|
50
|
+
assert_equal 4, emits.length
|
51
|
+
p emits[0]
|
52
|
+
assert_equal 'site.Google', emits[0][0] # tag
|
53
|
+
p emits[1]
|
54
|
+
assert_equal 'site.GoogleNews', emits[1][0] # tag
|
55
|
+
assert_equal 'news.google.com', emits[1][2]['domain']
|
56
|
+
p emits[2]
|
57
|
+
assert_equal 'agent.MacOSX', emits[2][0] #tag
|
58
|
+
p emits[3]
|
59
|
+
assert_equal 'agent.Googlebot-FooBar', emits[3][0] #tag
|
60
|
+
end
|
61
|
+
|
62
|
+
def test_emit2
|
63
|
+
d1 = create_driver(CONFIG2, 'input.access')
|
64
|
+
time = Time.parse("2012-01-02 13:14:15").to_i
|
65
|
+
d1.run do
|
66
|
+
d1.emit({'domain' => 'www.google.com', 'path' => '/foo/bar?key=value', 'agent' => 'Googlebot', 'response_time' => 1000000})
|
67
|
+
d1.emit({'domain' => 'news.google.com', 'path' => '/', 'agent' => 'Googlebot-Mobile', 'response_time' => 900000})
|
68
|
+
d1.emit({'domain' => 'map.google.com', 'path' => '/', 'agent' => 'Macintosh; Intel Mac OS X 10_7_4', 'response_time' => 900000})
|
69
|
+
d1.emit({'domain' => 'labs.google.com', 'path' => '/', 'agent' => 'Mozilla/5.0 Googlebot-FooBar/2.1', 'response_time' => 900000})
|
38
70
|
end
|
39
71
|
emits = d1.emits
|
40
|
-
assert_equal
|
72
|
+
assert_equal 4, emits.length
|
73
|
+
p emits[0]
|
41
74
|
assert_equal 'site.Google', emits[0][0] # tag
|
75
|
+
p emits[1]
|
42
76
|
assert_equal 'site.GoogleNews', emits[1][0] # tag
|
43
77
|
assert_equal 'news.google.com', emits[1][2]['domain']
|
78
|
+
p emits[2]
|
44
79
|
assert_equal 'agent.MacOSX', emits[2][0] #tag
|
80
|
+
p emits[3]
|
81
|
+
assert_equal 'agent.Googlebot-Foobar', emits[3][0] #tag
|
45
82
|
end
|
46
83
|
end
|
47
84
|
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: fluent-plugin-rewrite-tag-filter
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.8
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,11 +9,11 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-
|
12
|
+
date: 2012-09-15 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: fluentd
|
16
|
-
requirement: &
|
16
|
+
requirement: &20127680 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ! '>='
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: '0'
|
22
22
|
type: :development
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *20127680
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: fluentd
|
27
|
-
requirement: &
|
27
|
+
requirement: &20126860 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - ! '>='
|
@@ -32,7 +32,7 @@ dependencies:
|
|
32
32
|
version: '0'
|
33
33
|
type: :runtime
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *20126860
|
36
36
|
description:
|
37
37
|
email:
|
38
38
|
- y.ken.studio@gmail.com
|