fluent-funplus-s3 0.3.6
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.travis.yml +17 -0
- data/AUTHORS +1 -0
- data/ChangeLog +91 -0
- data/Gemfile +3 -0
- data/README.rdoc +110 -0
- data/Rakefile +14 -0
- data/VERSION +1 -0
- data/fluent-funplus-s3.gemspec +25 -0
- data/lib/fluent/plugin/out_s3.rb +202 -0
- data/test/out_s3.rb +295 -0
- metadata +139 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: ea37f19916d904dc2e085f55d4f34b077909fdc5
|
4
|
+
data.tar.gz: 34e39dc79062fdab3af1f3747a1c85168cfd2021
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: cd83b78d9b901871d06ad07a3166fbb3ecc1bff5dea479b70448cb20633cd7f1b91b80f85def159a84b2546dc7d1d3ed09388ae36f4f8fd38d343c877391384d
|
7
|
+
data.tar.gz: 6171413759442726c3ed7a6b2b1480c535d47b3ebb59aef094c7cc2f491659d07f78cec8068230283b4d6888a6a57c0fe02e7b0ce4ed636cf200c2a39f859d97
|
data/.travis.yml
ADDED
data/AUTHORS
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
FURUHASHI Sadayuki <frsyuki _at_ gmail.com>
|
data/ChangeLog
ADDED
@@ -0,0 +1,91 @@
|
|
1
|
+
Release 0.3.5 - 2013/12/05
|
2
|
+
|
3
|
+
* Add 'reduced_redundancy' option to store logs in reduced redundancy
|
4
|
+
https://github.com/fluent/fluent-plugin-s3/pull/33
|
5
|
+
|
6
|
+
|
7
|
+
Release 0.3.4 - 2013/07/31
|
8
|
+
|
9
|
+
* Add dynamic path slicing by time formatted string
|
10
|
+
https://github.com/fluent/fluent-plugin-s3/pull/24
|
11
|
+
|
12
|
+
|
13
|
+
Release 0.3.3 - 2013/06/18
|
14
|
+
|
15
|
+
* Fix require bug on case-sensitive environment
|
16
|
+
|
17
|
+
|
18
|
+
Release 0.3.2 - 2013/06/18
|
19
|
+
|
20
|
+
* Support lzo mime-type
|
21
|
+
https://github.com/fluent/fluent-plugin-s3/pull/29
|
22
|
+
* Add proxy_uri option
|
23
|
+
https://github.com/fluent/fluent-plugin-s3/issues/25
|
24
|
+
* Add check_apikey_on_start option
|
25
|
+
https://github.com/fluent/fluent-plugin-s3/pull/28
|
26
|
+
|
27
|
+
|
28
|
+
Release 0.3.1 - 2013/03/28
|
29
|
+
|
30
|
+
* Support json and text mime-types
|
31
|
+
https://github.com/fluent/fluent-plugin-s3/pull/20
|
32
|
+
|
33
|
+
|
34
|
+
Release 0.3.0 - 2013/02/19
|
35
|
+
|
36
|
+
* Enable dynamic and configurable S3 object kyes
|
37
|
+
https://github.com/fluent/fluent-plugin-s3/pull/12
|
38
|
+
* Fix a lot of temporary files were left on /tmp when the plugin failed to write to S3
|
39
|
+
https://github.com/fluent/fluent-plugin-s3/pull/15
|
40
|
+
* Enable fluent-mixin-config-placeholders to support hostname, uuid and other parameters in configuration
|
41
|
+
https://github.com/fluent/fluent-plugin-s3/pull/19
|
42
|
+
* Update 'aws-sdk' version requirement to '~> 1.8.2'
|
43
|
+
https://github.com/fluent/fluent-plugin-s3/pull/21
|
44
|
+
* Create new S3 bucket if not exists
|
45
|
+
https://github.com/fluent/fluent-plugin-s3/pull/22
|
46
|
+
* Check the permission and bucket existence at start method, not write method.
|
47
|
+
|
48
|
+
|
49
|
+
Release 0.2.6 - 2013/01/15
|
50
|
+
|
51
|
+
* Add use_ssl option
|
52
|
+
|
53
|
+
|
54
|
+
Release 0.2.5 - 2012/12/06
|
55
|
+
|
56
|
+
* Add format_json and time/tag mixin options [#9]
|
57
|
+
|
58
|
+
|
59
|
+
Release 0.2.4 - 2012/11/21
|
60
|
+
|
61
|
+
* Set content type when writing file to s3
|
62
|
+
|
63
|
+
|
64
|
+
Release 0.2.3 - 2012/11/19
|
65
|
+
|
66
|
+
* Loosen 'aws-sdk' version requirement from "~> 1.1.3" to "~> 1.1"
|
67
|
+
* Support aws-sdk facility to load credentials from ENV vars or IAM Instance Profile by making the credentials non-mandatory
|
68
|
+
* Use Yajl instead of to_json not to raise exceptions when it got invalid bytes as UTF-8.
|
69
|
+
|
70
|
+
|
71
|
+
Release 0.2.2 - 2011/12/15
|
72
|
+
|
73
|
+
* Add s3_endpoint option
|
74
|
+
|
75
|
+
|
76
|
+
Release 0.2.1 - 2011/10/24
|
77
|
+
|
78
|
+
* Add sequential number to the file to avoid overwriting
|
79
|
+
* Use bundler instead of jeweler for packaging
|
80
|
+
* Updated README
|
81
|
+
|
82
|
+
|
83
|
+
Release 0.2.0 - 2011/10/16
|
84
|
+
|
85
|
+
* Updated to fluentd-0.10.0
|
86
|
+
|
87
|
+
|
88
|
+
Release 0.1.1 - 2011/09/27
|
89
|
+
|
90
|
+
* First release
|
91
|
+
|
data/Gemfile
ADDED
data/README.rdoc
ADDED
@@ -0,0 +1,110 @@
|
|
1
|
+
= Amazon S3 output plugin for Fluent event collector
|
2
|
+
|
3
|
+
== Overview
|
4
|
+
|
5
|
+
*s3* output plugin buffers event logs in local file and upload it to S3 periodically.
|
6
|
+
|
7
|
+
This plugin splits files exactly by using the time of event logs (not the time when the logs are received). For example, a log '2011-01-02 message B' is reached, and then another log '2011-01-03 message B' is reached in this order, the former one is stored in "20110102.gz" file, and latter one in "20110103.gz" file.
|
8
|
+
|
9
|
+
|
10
|
+
== Installation
|
11
|
+
|
12
|
+
Simply use RubyGems:
|
13
|
+
|
14
|
+
gem install fluent-plugin-s3
|
15
|
+
|
16
|
+
== Configuration
|
17
|
+
|
18
|
+
<match pattern>
|
19
|
+
type s3
|
20
|
+
|
21
|
+
aws_key_id YOUR_AWS_KEY_ID
|
22
|
+
aws_sec_key YOUR_AWS_SECRET/KEY
|
23
|
+
s3_bucket YOUR_S3_BUCKET_NAME
|
24
|
+
s3_endpoint s3-ap-northeast-1.amazonaws.com
|
25
|
+
s3_object_key_format %{path}%{time_slice}_%{index}.%{file_extension}
|
26
|
+
path logs/
|
27
|
+
buffer_path /var/log/fluent/s3
|
28
|
+
|
29
|
+
time_slice_format %Y%m%d-%H
|
30
|
+
time_slice_wait 10m
|
31
|
+
utc
|
32
|
+
</match>
|
33
|
+
|
34
|
+
[aws_key_id] AWS access key id. This parameter is required when your agent is not running on EC2 instance with an IAM Instance Profile.
|
35
|
+
|
36
|
+
[aws_sec_key] AWS secret key. This parameter is required when your agent is not running on EC2 instance with an IAM Instance Profile.
|
37
|
+
|
38
|
+
[s3_bucket (required)] S3 bucket name.
|
39
|
+
|
40
|
+
[s3_endpoint] s3 endpoint name. For example, US West (Oregon) Region is "s3-us-west-2.amazonaws.com". The full list of endpoints are available here. > http://docs.aws.amazon.com/general/latest/gr/rande.html#s3_region
|
41
|
+
|
42
|
+
[s3_object_key_format] The format of S3 object keys. You can use several built-in variables:
|
43
|
+
|
44
|
+
- %{path}
|
45
|
+
- %{time_slice}
|
46
|
+
- %{index}
|
47
|
+
- %{file_extension}
|
48
|
+
|
49
|
+
to decide keys dynamically.
|
50
|
+
|
51
|
+
%{path} is exactly the value of *path* configured in the configuration file. E.g., "logs/" in the example configuration above.
|
52
|
+
%{time_slice} is the time-slice in text that are formatted with *time_slice_format*.
|
53
|
+
%{index} is the sequential number starts from 0, increments when multiple files are uploaded to S3 in the same time slice.
|
54
|
+
%{file_extention} is always "gz" for now.
|
55
|
+
|
56
|
+
The default format is "%{path}%{time_slice}_%{index}.%{file_extension}".
|
57
|
+
|
58
|
+
For instance, using the example configuration above, actual object keys on S3 will be something like:
|
59
|
+
|
60
|
+
"logs/20130111-22_0.gz"
|
61
|
+
"logs/20130111-23_0.gz"
|
62
|
+
"logs/20130111-23_1.gz"
|
63
|
+
"logs/20130112-00_0.gz"
|
64
|
+
|
65
|
+
With the configuration:
|
66
|
+
|
67
|
+
s3_object_key_format %{path}/events/ts=%{time_slice}/events_%{index}.%{file_extension}
|
68
|
+
path log
|
69
|
+
time_slice_format %Y%m%d-%H
|
70
|
+
|
71
|
+
You get:
|
72
|
+
|
73
|
+
"log/events/ts=20130111-22/events_0.gz"
|
74
|
+
"log/events/ts=20130111-23/events_0.gz"
|
75
|
+
"log/events/ts=20130111-23/events_1.gz"
|
76
|
+
"log/events/ts=20130112-00/events_0.gz"
|
77
|
+
|
78
|
+
The {fluent-mixin-config-placeholders}[https://github.com/tagomoris/fluent-mixin-config-placeholders] mixin is also incorporated, so additional variables such as %{hostname}, %{uuid}, etc. can be used in the s3_object_key_format. This could prove useful in preventing filename conflicts when writing from multiple servers.
|
79
|
+
|
80
|
+
s3_object_key_format %{path}/events/ts=%{time_slice}/events_%{index}-%{hostname}.%{file_extension}
|
81
|
+
|
82
|
+
[store_as] archive format on S3. You can use serveral format:
|
83
|
+
|
84
|
+
- gzip (default)
|
85
|
+
- json
|
86
|
+
- text
|
87
|
+
- lzo (Need lzop command)
|
88
|
+
|
89
|
+
[auto_create_bucket] Create S3 bucket if it does not exists. Default is true.
|
90
|
+
|
91
|
+
[check_apikey_on_start] Check AWS key on start. Default is true.
|
92
|
+
|
93
|
+
[proxy_uri] uri of proxy environment.
|
94
|
+
|
95
|
+
[path] path prefix of the files on S3. Default is "" (no prefix).
|
96
|
+
|
97
|
+
[buffer_path (required)] path prefix of the files to buffer logs.
|
98
|
+
|
99
|
+
[time_slice_format] Format of the time used as the file name. Default is '%Y%m%d'. Use '%Y%m%d%H' to split files hourly.
|
100
|
+
|
101
|
+
[time_slice_wait] The time to wait old logs. Default is 10 minutes. Specify larger value if old logs may reache.
|
102
|
+
|
103
|
+
[utc] Use UTC instead of local time.
|
104
|
+
|
105
|
+
|
106
|
+
== Copyright
|
107
|
+
|
108
|
+
Copyright:: Copyright (c) 2011 Sadayuki Furuhashi
|
109
|
+
License:: Apache License, Version 2.0
|
110
|
+
|
data/Rakefile
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
|
2
|
+
require 'bundler'
|
3
|
+
Bundler::GemHelper.install_tasks
|
4
|
+
|
5
|
+
require 'rake/testtask'
|
6
|
+
|
7
|
+
Rake::TestTask.new(:test) do |test|
|
8
|
+
test.libs << 'lib' << 'test'
|
9
|
+
test.test_files = FileList['test/*.rb']
|
10
|
+
test.verbose = true
|
11
|
+
end
|
12
|
+
|
13
|
+
task :default => [:build]
|
14
|
+
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.3.6
|
@@ -0,0 +1,25 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
$:.push File.expand_path('../lib', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.name = "fluent-funplus-s3"
|
6
|
+
gem.description = "Amazon S3 output plugin for Fluentd event collector, comma seperated and timestamp format"
|
7
|
+
gem.homepage = "https://github.com/funplus/fluent-funplus-s3"
|
8
|
+
gem.summary = gem.description
|
9
|
+
gem.version = File.read("VERSION").strip
|
10
|
+
gem.authors = ["Sadayuki Furuhashi"]
|
11
|
+
gem.email = "frsyuki@gmail.com"
|
12
|
+
gem.has_rdoc = false
|
13
|
+
#gem.platform = Gem::Platform::RUBY
|
14
|
+
gem.files = `git ls-files`.split("\n")
|
15
|
+
gem.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
16
|
+
gem.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
17
|
+
gem.require_paths = ['lib']
|
18
|
+
|
19
|
+
gem.add_dependency "fluentd", "~> 0.10.0"
|
20
|
+
gem.add_dependency "aws-sdk", "~> 1.8.2"
|
21
|
+
gem.add_dependency "yajl-ruby", "~> 1.0"
|
22
|
+
gem.add_dependency "fluent-mixin-config-placeholders", "~> 0.2.0"
|
23
|
+
gem.add_development_dependency "rake", ">= 0.9.2"
|
24
|
+
gem.add_development_dependency "flexmock", ">= 1.2.0"
|
25
|
+
end
|
@@ -0,0 +1,202 @@
|
|
1
|
+
module Fluent
|
2
|
+
|
3
|
+
require 'fluent/mixin/config_placeholders'
|
4
|
+
|
5
|
+
class S3Output < Fluent::TimeSlicedOutput
|
6
|
+
Fluent::Plugin.register_output('s3', self)
|
7
|
+
|
8
|
+
def initialize
|
9
|
+
super
|
10
|
+
require 'aws-sdk'
|
11
|
+
require 'zlib'
|
12
|
+
require 'time'
|
13
|
+
require 'tempfile'
|
14
|
+
require 'open3'
|
15
|
+
|
16
|
+
@use_ssl = true
|
17
|
+
end
|
18
|
+
|
19
|
+
config_param :path, :string, :default => ""
|
20
|
+
config_param :time_format, :string, :default => nil
|
21
|
+
|
22
|
+
include SetTagKeyMixin
|
23
|
+
config_set_default :include_tag_key, false
|
24
|
+
|
25
|
+
include SetTimeKeyMixin
|
26
|
+
config_set_default :include_time_key, false
|
27
|
+
|
28
|
+
config_param :aws_key_id, :string, :default => nil
|
29
|
+
config_param :aws_sec_key, :string, :default => nil
|
30
|
+
config_param :s3_bucket, :string
|
31
|
+
config_param :s3_endpoint, :string, :default => nil
|
32
|
+
config_param :s3_object_key_format, :string, :default => "%{path}%{time_slice}_%{index}.%{file_extension}"
|
33
|
+
config_param :store_as, :string, :default => "gzip"
|
34
|
+
config_param :auto_create_bucket, :bool, :default => true
|
35
|
+
config_param :check_apikey_on_start, :bool, :default => true
|
36
|
+
config_param :proxy_uri, :string, :default => nil
|
37
|
+
config_param :reduced_redundancy, :bool, :default => false
|
38
|
+
config_param :data_separator, :string, :default => ","
|
39
|
+
config_param :use_timestamp, :bool, :default => true
|
40
|
+
|
41
|
+
attr_reader :bucket
|
42
|
+
|
43
|
+
include Fluent::Mixin::ConfigPlaceholders
|
44
|
+
|
45
|
+
def placeholders
|
46
|
+
[:percent]
|
47
|
+
end
|
48
|
+
|
49
|
+
def configure(conf)
|
50
|
+
super
|
51
|
+
|
52
|
+
if format_json = conf['format_json']
|
53
|
+
@format_json = true
|
54
|
+
else
|
55
|
+
@format_json = false
|
56
|
+
end
|
57
|
+
|
58
|
+
if use_ssl = conf['use_ssl']
|
59
|
+
if use_ssl.empty?
|
60
|
+
@use_ssl = true
|
61
|
+
else
|
62
|
+
@use_ssl = Config.bool_value(use_ssl)
|
63
|
+
if @use_ssl.nil?
|
64
|
+
raise ConfigError, "'true' or 'false' is required for use_ssl option on s3 output"
|
65
|
+
end
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
@ext, @mime_type = case @store_as
|
70
|
+
when 'gzip' then ['gz', 'application/x-gzip']
|
71
|
+
when 'lzo' then
|
72
|
+
begin
|
73
|
+
Open3.capture3('lzop -V')
|
74
|
+
rescue Errno::ENOENT
|
75
|
+
raise ConfigError, "'lzop' utility must be in PATH for LZO compression"
|
76
|
+
end
|
77
|
+
['lzo', 'application/x-lzop']
|
78
|
+
when 'json' then ['json', 'application/json']
|
79
|
+
else ['txt', 'text/plain']
|
80
|
+
end
|
81
|
+
|
82
|
+
@timef = TimeFormatter.new(@time_format, @localtime)
|
83
|
+
|
84
|
+
if @localtime
|
85
|
+
@path_slicer = Proc.new {|path|
|
86
|
+
Time.now.strftime(path)
|
87
|
+
}
|
88
|
+
else
|
89
|
+
@path_slicer = Proc.new {|path|
|
90
|
+
Time.now.utc.strftime(path)
|
91
|
+
}
|
92
|
+
end
|
93
|
+
|
94
|
+
end
|
95
|
+
|
96
|
+
def start
|
97
|
+
super
|
98
|
+
options = {}
|
99
|
+
if @aws_key_id && @aws_sec_key
|
100
|
+
options[:access_key_id] = @aws_key_id
|
101
|
+
options[:secret_access_key] = @aws_sec_key
|
102
|
+
end
|
103
|
+
options[:s3_endpoint] = @s3_endpoint if @s3_endpoint
|
104
|
+
options[:proxy_uri] = @proxy_uri if @proxy_uri
|
105
|
+
options[:use_ssl] = @use_ssl
|
106
|
+
|
107
|
+
@s3 = AWS::S3.new(options)
|
108
|
+
@bucket = @s3.buckets[@s3_bucket]
|
109
|
+
|
110
|
+
ensure_bucket
|
111
|
+
check_apikeys if @check_apikey_on_start
|
112
|
+
end
|
113
|
+
|
114
|
+
def format(tag, time, record)
|
115
|
+
if @include_time_key || !@format_json
|
116
|
+
if @use_timestamp
|
117
|
+
time_str = time.to_i
|
118
|
+
else
|
119
|
+
time_str = @timef.format(time)
|
120
|
+
end
|
121
|
+
end
|
122
|
+
|
123
|
+
# copied from each mixin because current TimeSlicedOutput can't support mixins.
|
124
|
+
if @include_tag_key
|
125
|
+
record[@tag_key] = tag
|
126
|
+
end
|
127
|
+
if @include_time_key
|
128
|
+
record[@time_key] = time_str
|
129
|
+
end
|
130
|
+
|
131
|
+
if @format_json
|
132
|
+
Yajl.dump(record) + "\n"
|
133
|
+
else
|
134
|
+
"#{time_str}#{@data_separator}#{tag}#{@data_separator}#{Yajl.dump(record)}\n"
|
135
|
+
end
|
136
|
+
end
|
137
|
+
|
138
|
+
def write(chunk)
|
139
|
+
i = 0
|
140
|
+
|
141
|
+
begin
|
142
|
+
path = @path_slicer.call(@path)
|
143
|
+
values_for_s3_object_key = {
|
144
|
+
"path" => path,
|
145
|
+
"time_slice" => chunk.key,
|
146
|
+
"file_extension" => @ext,
|
147
|
+
"index" => i
|
148
|
+
}
|
149
|
+
s3path = @s3_object_key_format.gsub(%r(%{[^}]+})) { |expr|
|
150
|
+
values_for_s3_object_key[expr[2...expr.size-1]]
|
151
|
+
}
|
152
|
+
i += 1
|
153
|
+
end while @bucket.objects[s3path].exists?
|
154
|
+
|
155
|
+
tmp = Tempfile.new("s3-")
|
156
|
+
begin
|
157
|
+
if @store_as == "gzip"
|
158
|
+
w = Zlib::GzipWriter.new(tmp)
|
159
|
+
chunk.write_to(w)
|
160
|
+
w.close
|
161
|
+
elsif @store_as == "lzo"
|
162
|
+
w = Tempfile.new("chunk-tmp")
|
163
|
+
chunk.write_to(w)
|
164
|
+
w.close
|
165
|
+
tmp.close
|
166
|
+
# We don't check the return code because we can't recover lzop failure.
|
167
|
+
system "lzop -qf1 -o #{tmp.path} #{w.path}"
|
168
|
+
else
|
169
|
+
chunk.write_to(tmp)
|
170
|
+
tmp.close
|
171
|
+
end
|
172
|
+
@bucket.objects[s3path].write(Pathname.new(tmp.path), {:content_type => @mime_type,
|
173
|
+
:reduced_redundancy => @reduced_redundancy})
|
174
|
+
ensure
|
175
|
+
tmp.close(true) rescue nil
|
176
|
+
w.close rescue nil
|
177
|
+
w.unlink rescue nil
|
178
|
+
end
|
179
|
+
end
|
180
|
+
|
181
|
+
private
|
182
|
+
|
183
|
+
def ensure_bucket
|
184
|
+
if !@bucket.exists?
|
185
|
+
if @auto_create_bucket
|
186
|
+
$log.info "Creating bucket #{@s3_bucket} on #{@s3_endpoint}"
|
187
|
+
@s3.buckets.create(@s3_bucket)
|
188
|
+
else
|
189
|
+
raise "The specified bucket does not exist: bucket = #{@s3_bucket}"
|
190
|
+
end
|
191
|
+
end
|
192
|
+
end
|
193
|
+
|
194
|
+
def check_apikeys
|
195
|
+
@bucket.empty?
|
196
|
+
rescue
|
197
|
+
raise "aws_key_id or aws_sec_key is invalid. Please check your configuration"
|
198
|
+
end
|
199
|
+
end
|
200
|
+
|
201
|
+
|
202
|
+
end
|
data/test/out_s3.rb
ADDED
@@ -0,0 +1,295 @@
|
|
1
|
+
require 'fluent/test'
|
2
|
+
require 'fluent/plugin/out_s3'
|
3
|
+
|
4
|
+
require 'flexmock/test_unit'
|
5
|
+
require 'zlib'
|
6
|
+
|
7
|
+
class S3OutputTest < Test::Unit::TestCase
|
8
|
+
def setup
|
9
|
+
require 'aws-sdk'
|
10
|
+
Fluent::Test.setup
|
11
|
+
end
|
12
|
+
|
13
|
+
CONFIG = %[
|
14
|
+
aws_key_id test_key_id
|
15
|
+
aws_sec_key test_sec_key
|
16
|
+
s3_bucket test_bucket
|
17
|
+
path log
|
18
|
+
utc
|
19
|
+
buffer_type memory
|
20
|
+
]
|
21
|
+
|
22
|
+
def create_driver(conf = CONFIG)
|
23
|
+
Fluent::Test::BufferedOutputTestDriver.new(Fluent::S3Output) do
|
24
|
+
def write(chunk)
|
25
|
+
chunk.read
|
26
|
+
end
|
27
|
+
|
28
|
+
private
|
29
|
+
|
30
|
+
def check_apikeys
|
31
|
+
end
|
32
|
+
end.configure(conf)
|
33
|
+
end
|
34
|
+
|
35
|
+
def test_configure
|
36
|
+
d = create_driver
|
37
|
+
assert_equal 'test_key_id', d.instance.aws_key_id
|
38
|
+
assert_equal 'test_sec_key', d.instance.aws_sec_key
|
39
|
+
assert_equal 'test_bucket', d.instance.s3_bucket
|
40
|
+
assert_equal 'log', d.instance.path
|
41
|
+
assert d.instance.instance_variable_get(:@use_ssl)
|
42
|
+
assert_equal 'gz', d.instance.instance_variable_get(:@ext)
|
43
|
+
assert_equal 'application/x-gzip', d.instance.instance_variable_get(:@mime_type)
|
44
|
+
end
|
45
|
+
|
46
|
+
def test_configure_with_mime_type_json
|
47
|
+
conf = CONFIG.clone
|
48
|
+
conf << "\nstore_as json\n"
|
49
|
+
d = create_driver(conf)
|
50
|
+
assert_equal 'json', d.instance.instance_variable_get(:@ext)
|
51
|
+
assert_equal 'application/json', d.instance.instance_variable_get(:@mime_type)
|
52
|
+
end
|
53
|
+
|
54
|
+
def test_configure_with_mime_type_text
|
55
|
+
conf = CONFIG.clone
|
56
|
+
conf << "\nstore_as text\n"
|
57
|
+
d = create_driver(conf)
|
58
|
+
assert_equal 'txt', d.instance.instance_variable_get(:@ext)
|
59
|
+
assert_equal 'text/plain', d.instance.instance_variable_get(:@mime_type)
|
60
|
+
end
|
61
|
+
|
62
|
+
def test_configure_with_mime_type_lzo
|
63
|
+
conf = CONFIG.clone
|
64
|
+
conf << "\nstore_as lzo\n"
|
65
|
+
d = create_driver(conf)
|
66
|
+
assert_equal 'lzo', d.instance.instance_variable_get(:@ext)
|
67
|
+
assert_equal 'application/x-lzop', d.instance.instance_variable_get(:@mime_type)
|
68
|
+
rescue => e
|
69
|
+
# TODO: replace code with disable lzop command
|
70
|
+
assert(e.is_a?(Fluent::ConfigError))
|
71
|
+
end
|
72
|
+
|
73
|
+
def test_path_slicing
|
74
|
+
config = CONFIG.clone.gsub(/path\slog/, "path log/%Y/%m/%d")
|
75
|
+
d = create_driver(config)
|
76
|
+
path_slicer = d.instance.instance_variable_get(:@path_slicer)
|
77
|
+
path = d.instance.instance_variable_get(:@path)
|
78
|
+
slice = path_slicer.call(path)
|
79
|
+
assert_equal slice, Time.now.strftime("log/%Y/%m/%d")
|
80
|
+
end
|
81
|
+
|
82
|
+
def test_path_slicing_utc
|
83
|
+
config = CONFIG.clone.gsub(/path\slog/, "path log/%Y/%m/%d")
|
84
|
+
config << "\nutc\n"
|
85
|
+
d = create_driver(config)
|
86
|
+
path_slicer = d.instance.instance_variable_get(:@path_slicer)
|
87
|
+
path = d.instance.instance_variable_get(:@path)
|
88
|
+
slice = path_slicer.call(path)
|
89
|
+
assert_equal slice, Time.now.utc.strftime("log/%Y/%m/%d")
|
90
|
+
end
|
91
|
+
|
92
|
+
def test_format
|
93
|
+
d = create_driver
|
94
|
+
|
95
|
+
time = Time.parse("2011-01-02 13:14:15 UTC").to_i
|
96
|
+
d.emit({"a"=>1}, time)
|
97
|
+
d.emit({"a"=>2}, time)
|
98
|
+
|
99
|
+
d.expect_format %[2011-01-02T13:14:15Z\ttest\t{"a":1}\n]
|
100
|
+
d.expect_format %[2011-01-02T13:14:15Z\ttest\t{"a":2}\n]
|
101
|
+
|
102
|
+
d.run
|
103
|
+
end
|
104
|
+
|
105
|
+
def test_format_included_tag_and_time
|
106
|
+
config = [CONFIG, 'include_tag_key true', 'include_time_key true'].join("\n")
|
107
|
+
d = create_driver(config)
|
108
|
+
|
109
|
+
time = Time.parse("2011-01-02 13:14:15 UTC").to_i
|
110
|
+
d.emit({"a"=>1}, time)
|
111
|
+
d.emit({"a"=>2}, time)
|
112
|
+
|
113
|
+
d.expect_format %[2011-01-02T13:14:15Z\ttest\t{"a":1,"tag":"test","time":"2011-01-02T13:14:15Z"}\n]
|
114
|
+
d.expect_format %[2011-01-02T13:14:15Z\ttest\t{"a":2,"tag":"test","time":"2011-01-02T13:14:15Z"}\n]
|
115
|
+
|
116
|
+
d.run
|
117
|
+
end
|
118
|
+
|
119
|
+
def test_format_with_format_json
|
120
|
+
config = [CONFIG, 'format_json true'].join("\n")
|
121
|
+
d = create_driver(config)
|
122
|
+
|
123
|
+
time = Time.parse("2011-01-02 13:14:15 UTC").to_i
|
124
|
+
d.emit({"a"=>1}, time)
|
125
|
+
d.emit({"a"=>2}, time)
|
126
|
+
|
127
|
+
d.expect_format %[{"a":1}\n]
|
128
|
+
d.expect_format %[{"a":2}\n]
|
129
|
+
|
130
|
+
d.run
|
131
|
+
end
|
132
|
+
|
133
|
+
def test_format_with_format_json_included_tag
|
134
|
+
config = [CONFIG, 'format_json true', 'include_tag_key true'].join("\n")
|
135
|
+
d = create_driver(config)
|
136
|
+
|
137
|
+
time = Time.parse("2011-01-02 13:14:15 UTC").to_i
|
138
|
+
d.emit({"a"=>1}, time)
|
139
|
+
d.emit({"a"=>2}, time)
|
140
|
+
|
141
|
+
d.expect_format %[{"a":1,"tag":"test"}\n]
|
142
|
+
d.expect_format %[{"a":2,"tag":"test"}\n]
|
143
|
+
|
144
|
+
d.run
|
145
|
+
end
|
146
|
+
|
147
|
+
def test_format_with_format_json_included_time
|
148
|
+
config = [CONFIG, 'format_json true', 'include_time_key true'].join("\n")
|
149
|
+
d = create_driver(config)
|
150
|
+
|
151
|
+
time = Time.parse("2011-01-02 13:14:15 UTC").to_i
|
152
|
+
d.emit({"a"=>1}, time)
|
153
|
+
d.emit({"a"=>2}, time)
|
154
|
+
|
155
|
+
d.expect_format %[{"a":1,"time":"2011-01-02T13:14:15Z"}\n]
|
156
|
+
d.expect_format %[{"a":2,"time":"2011-01-02T13:14:15Z"}\n]
|
157
|
+
|
158
|
+
d.run
|
159
|
+
end
|
160
|
+
|
161
|
+
def test_format_with_format_json_included_tag_and_time
|
162
|
+
config = [CONFIG, 'format_json true', 'include_tag_key true', 'include_time_key true'].join("\n")
|
163
|
+
d = create_driver(config)
|
164
|
+
|
165
|
+
time = Time.parse("2011-01-02 13:14:15 UTC").to_i
|
166
|
+
d.emit({"a"=>1}, time)
|
167
|
+
d.emit({"a"=>2}, time)
|
168
|
+
|
169
|
+
d.expect_format %[{"a":1,"tag":"test","time":"2011-01-02T13:14:15Z"}\n]
|
170
|
+
d.expect_format %[{"a":2,"tag":"test","time":"2011-01-02T13:14:15Z"}\n]
|
171
|
+
|
172
|
+
d.run
|
173
|
+
end
|
174
|
+
|
175
|
+
def test_chunk_to_write
|
176
|
+
d = create_driver
|
177
|
+
|
178
|
+
time = Time.parse("2011-01-02 13:14:15 UTC").to_i
|
179
|
+
d.emit({"a"=>1}, time)
|
180
|
+
d.emit({"a"=>2}, time)
|
181
|
+
|
182
|
+
# S3OutputTest#write returns chunk.read
|
183
|
+
data = d.run
|
184
|
+
|
185
|
+
assert_equal %[2011-01-02T13:14:15Z\ttest\t{"a":1}\n] +
|
186
|
+
%[2011-01-02T13:14:15Z\ttest\t{"a":2}\n],
|
187
|
+
data
|
188
|
+
end
|
189
|
+
|
190
|
+
CONFIG2 = %[
|
191
|
+
hostname testing.node.local
|
192
|
+
aws_key_id test_key_id
|
193
|
+
aws_sec_key test_sec_key
|
194
|
+
s3_bucket test_bucket
|
195
|
+
s3_object_key_format %{path}/events/ts=%{time_slice}/events_%{index}-%{hostname}.%{file_extension}
|
196
|
+
time_slice_format %Y%m%d-%H
|
197
|
+
path log
|
198
|
+
utc
|
199
|
+
buffer_type memory
|
200
|
+
auto_create_bucket false
|
201
|
+
]
|
202
|
+
|
203
|
+
def create_time_sliced_driver(additional_conf = '')
|
204
|
+
d = Fluent::Test::TimeSlicedOutputTestDriver.new(Fluent::S3Output) do
|
205
|
+
private
|
206
|
+
|
207
|
+
def check_apikeys
|
208
|
+
end
|
209
|
+
end.configure([CONFIG2, additional_conf].join("\n"))
|
210
|
+
d
|
211
|
+
end
|
212
|
+
|
213
|
+
def test_write_with_custom_s3_object_key_format
|
214
|
+
# Assert content of event logs which are being sent to S3
|
215
|
+
s3obj = flexmock(AWS::S3::S3Object)
|
216
|
+
s3obj.should_receive(:exists?).with_any_args.
|
217
|
+
and_return { false }
|
218
|
+
s3obj.should_receive(:write).with(
|
219
|
+
on { |pathname|
|
220
|
+
data = nil
|
221
|
+
# Event logs are compressed in GZip
|
222
|
+
pathname.open { |f|
|
223
|
+
gz = Zlib::GzipReader.new(f)
|
224
|
+
data = gz.read
|
225
|
+
gz.close
|
226
|
+
}
|
227
|
+
assert_equal %[2011-01-02T13:14:15Z\ttest\t{"a":1}\n] +
|
228
|
+
%[2011-01-02T13:14:15Z\ttest\t{"a":2}\n],
|
229
|
+
data
|
230
|
+
|
231
|
+
pathname.to_s.match(%r|s3-|)
|
232
|
+
},
|
233
|
+
{:content_type => "application/x-gzip", :reduced_redundancy => false})
|
234
|
+
|
235
|
+
# Assert the key of S3Object, which event logs are stored in
|
236
|
+
s3obj_col = flexmock(AWS::S3::ObjectCollection)
|
237
|
+
s3obj_col.should_receive(:[]).with(
|
238
|
+
on { |key|
|
239
|
+
key == "log/events/ts=20110102-13/events_0-testing.node.local.gz"
|
240
|
+
}).
|
241
|
+
and_return {
|
242
|
+
s3obj
|
243
|
+
}
|
244
|
+
|
245
|
+
# Partial mock the S3Bucket, not to make an actual connection to Amazon S3
|
246
|
+
flexmock(AWS::S3::Bucket).new_instances do |bucket|
|
247
|
+
bucket.should_receive(:objects).with_any_args.
|
248
|
+
and_return {
|
249
|
+
s3obj_col
|
250
|
+
}
|
251
|
+
end
|
252
|
+
|
253
|
+
# We must use TimeSlicedOutputTestDriver instead of BufferedOutputTestDriver,
|
254
|
+
# to make assertions on chunks' keys
|
255
|
+
d = create_time_sliced_driver
|
256
|
+
|
257
|
+
time = Time.parse("2011-01-02 13:14:15 UTC").to_i
|
258
|
+
d.emit({"a"=>1}, time)
|
259
|
+
d.emit({"a"=>2}, time)
|
260
|
+
|
261
|
+
# Finally, the instance of S3Output is initialized and then invoked
|
262
|
+
d.run
|
263
|
+
end
|
264
|
+
|
265
|
+
def setup_mocks
|
266
|
+
s3bucket = flexmock(AWS::S3::Bucket)
|
267
|
+
s3bucket.should_receive(:exists?).with_any_args.and_return { false }
|
268
|
+
s3bucket_col = flexmock(AWS::S3::BucketCollection)
|
269
|
+
s3bucket_col.should_receive(:[]).with_any_args.and_return { s3bucket }
|
270
|
+
flexmock(AWS::S3).new_instances do |bucket|
|
271
|
+
bucket.should_receive(:buckets).with_any_args.and_return { s3bucket_col }
|
272
|
+
end
|
273
|
+
|
274
|
+
return s3bucket, s3bucket_col
|
275
|
+
end
|
276
|
+
|
277
|
+
def test_auto_create_bucket_false_with_non_existence_bucket
|
278
|
+
s3bucket, s3bucket_col = setup_mocks
|
279
|
+
|
280
|
+
d = create_time_sliced_driver('auto_create_bucket false')
|
281
|
+
assert_raise(RuntimeError, "The specified bucket does not exist: bucket = test_bucket") {
|
282
|
+
d.run
|
283
|
+
}
|
284
|
+
end
|
285
|
+
|
286
|
+
def test_auto_create_bucket_true_with_non_existence_bucket
|
287
|
+
s3bucket, s3bucket_col = setup_mocks
|
288
|
+
s3bucket_col.should_receive(:create).with_any_args.and_return { true }
|
289
|
+
|
290
|
+
d = create_time_sliced_driver('auto_create_bucket true')
|
291
|
+
assert_nothing_raised {
|
292
|
+
d.run
|
293
|
+
}
|
294
|
+
end
|
295
|
+
end
|
metadata
ADDED
@@ -0,0 +1,139 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: fluent-funplus-s3
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.3.6
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Sadayuki Furuhashi
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-01-13 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: fluentd
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ~>
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.10.0
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ~>
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.10.0
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: aws-sdk
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ~>
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: 1.8.2
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: 1.8.2
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: yajl-ruby
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.0'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: fluent-mixin-config-placeholders
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ~>
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: 0.2.0
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ~>
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: 0.2.0
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rake
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: 0.9.2
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: 0.9.2
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: flexmock
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - '>='
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: 1.2.0
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - '>='
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: 1.2.0
|
97
|
+
description: Amazon S3 output plugin for Fluentd event collector, comma seperated
|
98
|
+
and timestamp format
|
99
|
+
email: frsyuki@gmail.com
|
100
|
+
executables: []
|
101
|
+
extensions: []
|
102
|
+
extra_rdoc_files: []
|
103
|
+
files:
|
104
|
+
- .travis.yml
|
105
|
+
- AUTHORS
|
106
|
+
- ChangeLog
|
107
|
+
- Gemfile
|
108
|
+
- README.rdoc
|
109
|
+
- Rakefile
|
110
|
+
- VERSION
|
111
|
+
- fluent-funplus-s3.gemspec
|
112
|
+
- lib/fluent/plugin/out_s3.rb
|
113
|
+
- test/out_s3.rb
|
114
|
+
homepage: https://github.com/funplus/fluent-funplus-s3
|
115
|
+
licenses: []
|
116
|
+
metadata: {}
|
117
|
+
post_install_message:
|
118
|
+
rdoc_options: []
|
119
|
+
require_paths:
|
120
|
+
- lib
|
121
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
122
|
+
requirements:
|
123
|
+
- - '>='
|
124
|
+
- !ruby/object:Gem::Version
|
125
|
+
version: '0'
|
126
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
127
|
+
requirements:
|
128
|
+
- - '>='
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
version: '0'
|
131
|
+
requirements: []
|
132
|
+
rubyforge_project:
|
133
|
+
rubygems_version: 2.0.3
|
134
|
+
signing_key:
|
135
|
+
specification_version: 4
|
136
|
+
summary: Amazon S3 output plugin for Fluentd event collector, comma seperated and
|
137
|
+
timestamp format
|
138
|
+
test_files:
|
139
|
+
- test/out_s3.rb
|