logstash-codec-edn 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.
checksums.yaml ADDED
@@ -0,0 +1,15 @@
1
+ ---
2
+ !binary "U0hBMQ==":
3
+ metadata.gz: !binary |-
4
+ YzkwZDUxNWQ2MTYyMDkzMDAwMzJmMTIyZjJkYWY1MDJlYjA1ZmYyOQ==
5
+ data.tar.gz: !binary |-
6
+ OTdhZTkzMWM3OTY1ODE4NDc1OTU2YjdjMTlmODkxYzFjMGEzOWNkZQ==
7
+ SHA512:
8
+ metadata.gz: !binary |-
9
+ MTFmYzRhMThhMWVmNmNiYTQ5MzFhMDIwZjE1MDNmNzFlY2E0NzlhMzEzYTk0
10
+ YjQ1MmFlZWNiOTIxNTM4MzdkNDY5YTRhZWIxZWI0YzQwZThlYzZiYzVhY2U5
11
+ ODRhOWVlYjk3MWU5N2U4YTRkMjgzYzRiMGFmNzc4ZmVhYTBmMDc=
12
+ data.tar.gz: !binary |-
13
+ MTExMjkxOGRiYjljZjQ0NzljNzFmMWMyMzNjNzkxYmZjYTY5YTA2ZmU0OWFm
14
+ ZTVhOGVkNGNlNDVhMjBiNWYyNjZhNzU5MDdkYzdmNDM0MTM2YTg0YzNmYzlh
15
+ ZjE2ZjQ1YmE5MmUzMWE2MzE5ZWNiZjZiZjYwZTEzOWRhMDVmNjE=
data/.gitignore ADDED
@@ -0,0 +1,3 @@
1
+ *.gem
2
+ Gemfile.lock
3
+ .bundle
data/Gemfile ADDED
@@ -0,0 +1,4 @@
1
+ source 'http://rubygems.org'
2
+ gem 'rake'
3
+ gem 'gem_publisher'
4
+ gem 'archive-tar-minitar'
data/Rakefile ADDED
@@ -0,0 +1,6 @@
1
+ @files=[]
2
+
3
+ task :default do
4
+ system("rake -T")
5
+ end
6
+
@@ -0,0 +1,33 @@
1
+ require "logstash/codecs/base"
2
+ require "logstash/util"
3
+
4
+ class LogStash::Codecs::EDN < LogStash::Codecs::Base
5
+ config_name "edn"
6
+
7
+ milestone 1
8
+
9
+ def register
10
+ require "edn"
11
+ end
12
+
13
+ public
14
+ def decode(data)
15
+ begin
16
+ yield LogStash::Event.new(EDN.read(data))
17
+ rescue => e
18
+ @logger.warn("EDN parse failure. Falling back to plain-text", :error => e, :data => data)
19
+ yield LogStash::Event.new("message" => data)
20
+ end
21
+ end
22
+
23
+ public
24
+ def encode(event)
25
+ # use normalize to make sure returned Hash is pure Ruby
26
+ # #to_edn which relies on pure Ruby object recognition
27
+ data = LogStash::Util.normalize(event.to_hash)
28
+ # timestamp is serialized as a iso8601 string
29
+ # merge to avoid modifying data which could have side effects if multiple outputs
30
+ @on_event.call(data.merge(LogStash::Event::TIMESTAMP => event.timestamp.to_iso8601).to_edn)
31
+ end
32
+
33
+ end
@@ -0,0 +1,28 @@
1
+ Gem::Specification.new do |s|
2
+
3
+ s.name = 'logstash-codec-edn'
4
+ s.version = '0.1.0'
5
+ s.licenses = ['Apache License (2.0)']
6
+ s.summary = "Codec to process EDN data"
7
+ s.description = "Codec to process EDN data"
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($\)
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" => "codec" }
21
+
22
+ # Gem dependencies
23
+ s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
24
+
25
+ s.add_runtime_dependency 'edn'
26
+
27
+ end
28
+
@@ -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 +1,61 @@
1
+ require "logstash/codecs/edn"
2
+ require "logstash/event"
3
+ require "logstash/json"
4
+ require "insist"
5
+ require "edn"
6
+
7
+ describe LogStash::Codecs::EDN do
8
+ subject do
9
+ next LogStash::Codecs::EDN.new
10
+ end
11
+
12
+ context "#decode" do
13
+ it "should return an event from edn data" do
14
+ data = {"foo" => "bar", "baz" => {"bah" => ["a", "b", "c"]}, "@timestamp" => "2014-05-30T02:52:17.929Z"}
15
+ subject.decode(data.to_edn) do |event|
16
+ insist { event }.is_a?(LogStash::Event)
17
+ insist { event["foo"] } == data["foo"]
18
+ insist { event["baz"] } == data["baz"]
19
+ insist { event["bah"] } == data["bah"]
20
+ insist { event["@timestamp"].to_iso8601 } == data["@timestamp"]
21
+ end
22
+ end
23
+ end
24
+
25
+ context "#encode" do
26
+ it "should return edn data from pure ruby hash" do
27
+ data = {"foo" => "bar", "baz" => {"bah" => ["a","b","c"]}, "@timestamp" => "2014-05-30T02:52:17.929Z"}
28
+ event = LogStash::Event.new(data)
29
+ got_event = false
30
+ subject.on_event do |d|
31
+ insist { EDN.read(d)["foo"] } == data["foo"]
32
+ insist { EDN.read(d)["baz"] } == data["baz"]
33
+ insist { EDN.read(d)["bah"] } == data["bah"]
34
+ insist { EDN.read(d)["@timestamp"] } == "2014-05-30T02:52:17.929Z"
35
+ got_event = true
36
+ end
37
+ subject.encode(event)
38
+ insist { got_event }
39
+ end
40
+
41
+ # this is to test the case where the event data has been produced by json
42
+ # deserialization using JrJackson in :raw mode which creates Java LinkedHashMap
43
+ # and not Ruby Hash which will not be monkey patched with the #to_edn method
44
+ it "should return edn data from deserialized json with normalization" do
45
+ data = LogStash::Json.load('{"foo": "bar", "baz": {"bah": ["a","b","c"]}, "@timestamp": "2014-05-30T02:52:17.929Z"}')
46
+ event = LogStash::Event.new(data)
47
+ got_event = false
48
+ subject.on_event do |d|
49
+ insist { EDN.read(d)["foo"] } == data["foo"]
50
+ insist { EDN.read(d)["baz"] } == data["baz"]
51
+ insist { EDN.read(d)["bah"] } == data["bah"]
52
+ insist { EDN.read(d)["@timestamp"] } == "2014-05-30T02:52:17.929Z"
53
+ insist { EDN.read(d)["@timestamp"] } == event["@timestamp"].to_iso8601
54
+ got_event = true
55
+ end
56
+ subject.encode(event)
57
+ insist { got_event }
58
+ end
59
+ end
60
+
61
+ end
metadata ADDED
@@ -0,0 +1,88 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: logstash-codec-edn
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: 2014-10-30 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: edn
35
+ requirement: !ruby/object:Gem::Requirement
36
+ requirements:
37
+ - - ! '>='
38
+ - !ruby/object:Gem::Version
39
+ version: '0'
40
+ type: :runtime
41
+ prerelease: false
42
+ version_requirements: !ruby/object:Gem::Requirement
43
+ requirements:
44
+ - - ! '>='
45
+ - !ruby/object:Gem::Version
46
+ version: '0'
47
+ description: Codec to process EDN data
48
+ email: richard.pijnenburg@elasticsearch.com
49
+ executables: []
50
+ extensions: []
51
+ extra_rdoc_files: []
52
+ files:
53
+ - .gitignore
54
+ - Gemfile
55
+ - Rakefile
56
+ - lib/logstash/codecs/edn.rb
57
+ - logstash-codec-edn.gemspec
58
+ - rakelib/publish.rake
59
+ - rakelib/vendor.rake
60
+ - spec/codecs/edn_spec.rb
61
+ homepage: http://logstash.net/
62
+ licenses:
63
+ - Apache License (2.0)
64
+ metadata:
65
+ logstash_plugin: 'true'
66
+ group: codec
67
+ post_install_message:
68
+ rdoc_options: []
69
+ require_paths:
70
+ - lib
71
+ required_ruby_version: !ruby/object:Gem::Requirement
72
+ requirements:
73
+ - - ! '>='
74
+ - !ruby/object:Gem::Version
75
+ version: '0'
76
+ required_rubygems_version: !ruby/object:Gem::Requirement
77
+ requirements:
78
+ - - ! '>='
79
+ - !ruby/object:Gem::Version
80
+ version: '0'
81
+ requirements: []
82
+ rubyforge_project:
83
+ rubygems_version: 2.4.1
84
+ signing_key:
85
+ specification_version: 4
86
+ summary: Codec to process EDN data
87
+ test_files:
88
+ - spec/codecs/edn_spec.rb