logstash-filter-checksum 0.1.0

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.
@@ -0,0 +1,15 @@
1
+ ---
2
+ !binary "U0hBMQ==":
3
+ metadata.gz: !binary |-
4
+ YzU0MzgyYTY5NjBmMTVhNGEwZTdlMjkyZjEwMGU4NGJjYTZlMjBhMA==
5
+ data.tar.gz: !binary |-
6
+ ZWUyZjg2OTNiZWI0NmY2MjE0MmNiNzcwZDZiMWJlOTAwNDYxYWFlYQ==
7
+ SHA512:
8
+ metadata.gz: !binary |-
9
+ YjEyOTAyYzZlYmUzOWE3YzQ3ODc4YjgwODBmMWUyYzg4OTllZTI5OWJmOWEw
10
+ ZTk1ZTExNDNhNmJjM2JmMWQzYTkwOGI5YWIxYWZiOGY5MzRlY2UyNmUyZGEy
11
+ M2QwZWU2MTVhNDY1MDFkYzU5YjE5MGMxZjYwYTljYmI4ZTU1NmI=
12
+ data.tar.gz: !binary |-
13
+ MzI4MmIyNjE2YTg1NDg2YmU5NjZlMGMwZmE4M2JlYzc4YWMwNzI1ZTM4ZWI3
14
+ ODNkZjQyOTYyYTQyY2YzNDg3NDMyMmVhM2E0NGE2ZDA0ODcxODMxYzVjOTE5
15
+ NjFhMmRiY2RhNWU5M2MxMzBlODY4ZTBlNDMzODAwYmE5ZWY1ODQ=
@@ -0,0 +1,4 @@
1
+ *.gem
2
+ Gemfile.lock
3
+ .bundle
4
+ vendor
data/Gemfile ADDED
@@ -0,0 +1,3 @@
1
+ source 'http://rubygems.org'
2
+ gem 'rake'
3
+ gem 'gem_publisher'
@@ -0,0 +1,6 @@
1
+ @files=[]
2
+
3
+ task :default do
4
+ system("rake -T")
5
+ end
6
+
@@ -0,0 +1,52 @@
1
+ # encoding: utf-8
2
+ require "logstash/filters/base"
3
+ require "logstash/namespace"
4
+
5
+ # This filter let's you create a checksum based on various parts
6
+ # of the logstash event.
7
+ # This can be useful for deduplication of messages or simply to provide
8
+ # a custom unique identifier.
9
+ #
10
+ # This is VERY experimental and is largely a proof-of-concept
11
+ class LogStash::Filters::Checksum < LogStash::Filters::Base
12
+
13
+ config_name "checksum"
14
+ milestone 1
15
+
16
+ ALGORITHMS = ["md5", "sha", "sha1", "sha256", "sha384",]
17
+
18
+ # A list of keys to use in creating the string to checksum
19
+ # Keys will be sorted before building the string
20
+ # keys and values will then be concatenated with pipe delimeters
21
+ # and checksummed
22
+ config :keys, :validate => :array, :default => ["message", "@timestamp", "type"]
23
+
24
+ config :algorithm, :validate => ALGORITHMS, :default => "sha256"
25
+
26
+ public
27
+ def register
28
+ require 'openssl'
29
+ @to_checksum = ""
30
+ end
31
+
32
+ public
33
+ def filter(event)
34
+ return unless filter?(event)
35
+
36
+ @logger.debug("Running checksum filter", :event => event)
37
+
38
+ @keys.sort.each do |k|
39
+ @logger.debug("Adding key to string", :current_key => k)
40
+ @to_checksum << "|#{k}|#{event[k]}"
41
+ end
42
+ @to_checksum << "|"
43
+ @logger.debug("Final string built", :to_checksum => @to_checksum)
44
+
45
+
46
+ # in JRuby 1.7.11 outputs as ASCII-8BIT
47
+ digested_string = OpenSSL::Digest.hexdigest(@algorithm, @to_checksum).force_encoding(Encoding::UTF_8)
48
+
49
+ @logger.debug("Digested string", :digested_string => digested_string)
50
+ event['logstash_checksum'] = digested_string
51
+ end
52
+ end # class LogStash::Filters::Checksum
@@ -0,0 +1,27 @@
1
+ Gem::Specification.new do |s|
2
+
3
+ s.name = 'logstash-filter-checksum'
4
+ s.version = '0.1.0'
5
+ s.licenses = ['Apache License (2.0)']
6
+ s.summary = "This filter let's you create a checksum based on various parts of the logstash event."
7
+ s.description = "This filter let's you create a checksum based on various parts of the logstash event."
8
+ s.authors = ["Elasticsearch"]
9
+ s.email = 'richard.pijnenburg@elasticsearch.com'
10
+ s.homepage = "http://logstash.net/"
11
+ s.require_paths = ["lib"]
12
+
13
+ # Files
14
+ s.files = `git ls-files`.split($\)+::Dir.glob('vendor/*')
15
+
16
+ # Tests
17
+ s.test_files = s.files.grep(%r{^(test|spec|features)/})
18
+
19
+ # Special flag to let us know this is actually a logstash plugin
20
+ s.metadata = { "logstash_plugin" => "true", "group" => "filter" }
21
+
22
+ # Gem dependencies
23
+ s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
24
+ s.add_runtime_dependency 'jruby-openssl', ['0.8.7']
25
+
26
+ end
27
+
@@ -0,0 +1,9 @@
1
+ require "gem_publisher"
2
+
3
+ desc "Publish gem to RubyGems.org"
4
+ task :publish_gem do |t|
5
+ gem_file = Dir.glob(File.expand_path('../*.gemspec',File.dirname(__FILE__))).first
6
+ gem = GemPublisher.publish_if_updated(gem_file, :rubygems)
7
+ puts "Published #{gem}" if gem
8
+ end
9
+
@@ -0,0 +1,169 @@
1
+ require "net/http"
2
+ require "uri"
3
+ require "digest/sha1"
4
+
5
+ def vendor(*args)
6
+ return File.join("vendor", *args)
7
+ end
8
+
9
+ directory "vendor/" => ["vendor"] do |task, args|
10
+ mkdir task.name
11
+ end
12
+
13
+ def fetch(url, sha1, output)
14
+
15
+ puts "Downloading #{url}"
16
+ actual_sha1 = download(url, output)
17
+
18
+ if actual_sha1 != sha1
19
+ fail "SHA1 does not match (expected '#{sha1}' but got '#{actual_sha1}')"
20
+ end
21
+ end # def fetch
22
+
23
+ def file_fetch(url, sha1)
24
+ filename = File.basename( URI(url).path )
25
+ output = "vendor/#{filename}"
26
+ task output => [ "vendor/" ] do
27
+ begin
28
+ actual_sha1 = file_sha1(output)
29
+ if actual_sha1 != sha1
30
+ fetch(url, sha1, output)
31
+ end
32
+ rescue Errno::ENOENT
33
+ fetch(url, sha1, output)
34
+ end
35
+ end.invoke
36
+
37
+ return output
38
+ end
39
+
40
+ def file_sha1(path)
41
+ digest = Digest::SHA1.new
42
+ fd = File.new(path, "r")
43
+ while true
44
+ begin
45
+ digest << fd.sysread(16384)
46
+ rescue EOFError
47
+ break
48
+ end
49
+ end
50
+ return digest.hexdigest
51
+ ensure
52
+ fd.close if fd
53
+ end
54
+
55
+ def download(url, output)
56
+ uri = URI(url)
57
+ digest = Digest::SHA1.new
58
+ tmp = "#{output}.tmp"
59
+ Net::HTTP.start(uri.host, uri.port, :use_ssl => (uri.scheme == "https")) do |http|
60
+ request = Net::HTTP::Get.new(uri.path)
61
+ http.request(request) do |response|
62
+ fail "HTTP fetch failed for #{url}. #{response}" if [200, 301].include?(response.code)
63
+ size = (response["content-length"].to_i || -1).to_f
64
+ count = 0
65
+ File.open(tmp, "w") do |fd|
66
+ response.read_body do |chunk|
67
+ fd.write(chunk)
68
+ digest << chunk
69
+ if size > 0 && $stdout.tty?
70
+ count += chunk.bytesize
71
+ $stdout.write(sprintf("\r%0.2f%%", count/size * 100))
72
+ end
73
+ end
74
+ end
75
+ $stdout.write("\r \r") if $stdout.tty?
76
+ end
77
+ end
78
+
79
+ File.rename(tmp, output)
80
+
81
+ return digest.hexdigest
82
+ rescue SocketError => e
83
+ puts "Failure while downloading #{url}: #{e}"
84
+ raise
85
+ ensure
86
+ File.unlink(tmp) if File.exist?(tmp)
87
+ end # def download
88
+
89
+ def untar(tarball, &block)
90
+ require "archive/tar/minitar"
91
+ tgz = Zlib::GzipReader.new(File.open(tarball))
92
+ # Pull out typesdb
93
+ tar = Archive::Tar::Minitar::Input.open(tgz)
94
+ tar.each do |entry|
95
+ path = block.call(entry)
96
+ next if path.nil?
97
+ parent = File.dirname(path)
98
+
99
+ mkdir_p parent unless File.directory?(parent)
100
+
101
+ # Skip this file if the output file is the same size
102
+ if entry.directory?
103
+ mkdir path unless File.directory?(path)
104
+ else
105
+ entry_mode = entry.instance_eval { @mode } & 0777
106
+ if File.exists?(path)
107
+ stat = File.stat(path)
108
+ # TODO(sissel): Submit a patch to archive-tar-minitar upstream to
109
+ # expose headers in the entry.
110
+ entry_size = entry.instance_eval { @size }
111
+ # If file sizes are same, skip writing.
112
+ next if stat.size == entry_size && (stat.mode & 0777) == entry_mode
113
+ end
114
+ puts "Extracting #{entry.full_name} from #{tarball} #{entry_mode.to_s(8)}"
115
+ File.open(path, "w") do |fd|
116
+ # eof? check lets us skip empty files. Necessary because the API provided by
117
+ # Archive::Tar::Minitar::Reader::EntryStream only mostly acts like an
118
+ # IO object. Something about empty files in this EntryStream causes
119
+ # IO.copy_stream to throw "can't convert nil into String" on JRuby
120
+ # TODO(sissel): File a bug about this.
121
+ while !entry.eof?
122
+ chunk = entry.read(16384)
123
+ fd.write(chunk)
124
+ end
125
+ #IO.copy_stream(entry, fd)
126
+ end
127
+ File.chmod(entry_mode, path)
128
+ end
129
+ end
130
+ tar.close
131
+ File.unlink(tarball) if File.file?(tarball)
132
+ end # def untar
133
+
134
+ def ungz(file)
135
+
136
+ outpath = file.gsub('.gz', '')
137
+ tgz = Zlib::GzipReader.new(File.open(file))
138
+ begin
139
+ File.open(outpath, "w") do |out|
140
+ IO::copy_stream(tgz, out)
141
+ end
142
+ File.unlink(file)
143
+ rescue
144
+ File.unlink(outpath) if File.file?(outpath)
145
+ raise
146
+ end
147
+ tgz.close
148
+ end
149
+
150
+ desc "Process any vendor files required for this plugin"
151
+ task "vendor" do |task, args|
152
+
153
+ @files.each do |file|
154
+ download = file_fetch(file['url'], file['sha1'])
155
+ if download =~ /.tar.gz/
156
+ prefix = download.gsub('.tar.gz', '').gsub('vendor/', '')
157
+ untar(download) do |entry|
158
+ if !file['files'].nil?
159
+ next unless file['files'].include?(entry.full_name.gsub(prefix, ''))
160
+ out = entry.full_name.split("/").last
161
+ end
162
+ File.join('vendor', out)
163
+ end
164
+ elsif download =~ /.gz/
165
+ ungz(download)
166
+ end
167
+ end
168
+
169
+ end
@@ -0,0 +1,42 @@
1
+ # encoding: utf-8
2
+
3
+ require "spec_helper"
4
+ require "logstash/filters/checksum"
5
+ require 'openssl'
6
+
7
+ describe LogStash::Filters::Checksum do
8
+
9
+ LogStash::Filters::Checksum::ALGORITHMS.each do |alg|
10
+ describe "#{alg} checksum with single field" do
11
+ config <<-CONFIG
12
+ filter {
13
+ checksum {
14
+ algorithm => "#{alg}"
15
+ keys => ["test"]
16
+ }
17
+ }
18
+ CONFIG
19
+
20
+ sample "test" => "foo bar" do
21
+ insist { !subject["logstash_checksum"].nil? }
22
+ insist { subject["logstash_checksum"] } == OpenSSL::Digest.hexdigest(alg, "|test|foo bar|")
23
+ end
24
+ end
25
+
26
+ describe "#{alg} checksum with multiple keys" do
27
+ config <<-CONFIG
28
+ filter {
29
+ checksum {
30
+ algorithm => "#{alg}"
31
+ keys => ["test1", "test2"]
32
+ }
33
+ }
34
+ CONFIG
35
+
36
+ sample "test1" => "foo", "test2" => "bar" do
37
+ insist { !subject["logstash_checksum"].nil? }
38
+ insist { subject["logstash_checksum"] } == OpenSSL::Digest.hexdigest(alg, "|test1|foo|test2|bar|")
39
+ end
40
+ end
41
+ end
42
+ end
metadata ADDED
@@ -0,0 +1,90 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: logstash-filter-checksum
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Elasticsearch
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2014-11-01 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: logstash
15
+ requirement: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - ! '>='
18
+ - !ruby/object:Gem::Version
19
+ version: 1.4.0
20
+ - - <
21
+ - !ruby/object:Gem::Version
22
+ version: 2.0.0
23
+ type: :runtime
24
+ prerelease: false
25
+ version_requirements: !ruby/object:Gem::Requirement
26
+ requirements:
27
+ - - ! '>='
28
+ - !ruby/object:Gem::Version
29
+ version: 1.4.0
30
+ - - <
31
+ - !ruby/object:Gem::Version
32
+ version: 2.0.0
33
+ - !ruby/object:Gem::Dependency
34
+ name: jruby-openssl
35
+ requirement: !ruby/object:Gem::Requirement
36
+ requirements:
37
+ - - '='
38
+ - !ruby/object:Gem::Version
39
+ version: 0.8.7
40
+ type: :runtime
41
+ prerelease: false
42
+ version_requirements: !ruby/object:Gem::Requirement
43
+ requirements:
44
+ - - '='
45
+ - !ruby/object:Gem::Version
46
+ version: 0.8.7
47
+ description: This filter let's you create a checksum based on various parts of the
48
+ logstash event.
49
+ email: richard.pijnenburg@elasticsearch.com
50
+ executables: []
51
+ extensions: []
52
+ extra_rdoc_files: []
53
+ files:
54
+ - .gitignore
55
+ - Gemfile
56
+ - Rakefile
57
+ - lib/logstash/filters/checksum.rb
58
+ - logstash-filter-checksum.gemspec
59
+ - rakelib/publish.rake
60
+ - rakelib/vendor.rake
61
+ - spec/filters/checksum_spec.rb
62
+ homepage: http://logstash.net/
63
+ licenses:
64
+ - Apache License (2.0)
65
+ metadata:
66
+ logstash_plugin: 'true'
67
+ group: filter
68
+ post_install_message:
69
+ rdoc_options: []
70
+ require_paths:
71
+ - lib
72
+ required_ruby_version: !ruby/object:Gem::Requirement
73
+ requirements:
74
+ - - ! '>='
75
+ - !ruby/object:Gem::Version
76
+ version: '0'
77
+ required_rubygems_version: !ruby/object:Gem::Requirement
78
+ requirements:
79
+ - - ! '>='
80
+ - !ruby/object:Gem::Version
81
+ version: '0'
82
+ requirements: []
83
+ rubyforge_project:
84
+ rubygems_version: 2.4.1
85
+ signing_key:
86
+ specification_version: 4
87
+ summary: This filter let's you create a checksum based on various parts of the logstash
88
+ event.
89
+ test_files:
90
+ - spec/filters/checksum_spec.rb