logstash-codec-fluent 0.1.0-java

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 90577a0bfcd1f71118c5bdd969c197f9ece5dce9
+  data.tar.gz: abfa5693f92d01280a81b2649bf302af86b9bd57
+SHA512:
+  metadata.gz: 88c8eae887ad0f8d798fccd43d888daaa9a0723fbaf2849c76f4ecd1475396d86f256d7a738a0c8497702e0d872ade5f8e905d64b93c1f1ee6df8e91cc00826d
+  data.tar.gz: 2cf85a0d2b99ecb411d3ffe4bcb7c1eb66bf7157ede96ae24f10622e17e1b8420c559e8ffbf4b10cdf37cc7cf1f0030a73fa66e7593ae76bf0f68e1d7460d5c7

data/.gitignore

@@ -0,0 +1,3 @@
+*.gem
+Gemfile.lock
+.bundle

data/Gemfile

@@ -0,0 +1,4 @@
+source 'http://rubygems.org'
+gem 'rake'
+gem 'gem_publisher'
+gem 'archive-tar-minitar'

data/LICENSE

@@ -0,0 +1,13 @@
+Copyright (c) 2012-2014 Elasticsearch <http://www.elasticsearch.org>
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

data/Rakefile

@@ -0,0 +1,6 @@
+@files=[]
+
+task :default do
+  system("rake -T")
+end
+

data/lib/logstash/codecs/fluent.rb

@@ -0,0 +1,63 @@
+# encoding: utf-8
+require "logstash/codecs/base"
+require "logstash/util/charset"
+require "logstash/timestamp"
+require "logstash/util"
+
+# This codec handles fluentd's msgpack schema.
+#
+# For example, you can receive logs from `fluent-logger-ruby` with:
+# [source,ruby]
+#     input {
+#       tcp {
+#         codec => fluent
+#         port => 4000
+#       }
+#     }
+#
+# And from your ruby code in your own application:
+# [source,ruby]
+#     logger = Fluent::Logger::FluentLogger.new(nil, :host => "example.log", :port => 4000)
+#     logger.post("some_tag", { "your" => "data", "here" => "yay!" })
+#
+# Notes:
+#
+# * the fluent uses a second-precision time for events, so you will never see
+#   subsecond precision on events processed by this codec.
+#
+class LogStash::Codecs::Fluent < LogStash::Codecs::Base
+  config_name "fluent"
+  milestone 1
+
+  public
+  def register
+    require "msgpack"
+    @decoder = MessagePack::Unpacker.new
+  end
+
+  public
+  def decode(data)
+    @decoder.feed(data)
+    @decoder.each do |tag, epochtime, map|
+      event = LogStash::Event.new(map.merge(
+        LogStash::Event::TIMESTAMP => LogStash::Timestamp.at(epochtime),
+        "tags" => tag
+      ))
+      yield event
+    end
+  end # def decode
+
+  public
+  def encode(event)
+    tag = event["tags"] || "log"
+    epochtime = event.timestamp.to_i
+
+    # use normalize to make sure returned Hash is pure Ruby for
+    # MessagePack#pack which relies on pure Ruby object recognition
+    data = LogStash::Util.normalize(event.to_hash)
+    # timestamp is serialized as a iso8601 string
+    # merge to avoid modifying data which could have side effects if multiple outputs
+    @on_event.call(MessagePack.pack([tag, epochtime, data.merge(LogStash::Event::TIMESTAMP => event.timestamp.to_iso8601)]))
+  end # def encode
+
+end # class LogStash::Codecs::Fluent

data/logstash-codec-fluent.gemspec

@@ -0,0 +1,33 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-codec-fluent'
+  s.version         = '0.1.0'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "This codec handles fluentd's msgpack schema."
+  s.description     = "This codec handles fluentd's msgpack schema."
+  s.authors         = ["Elasticsearch"]
+  s.email           = 'richard.pijnenburg@elasticsearch.com'
+  s.homepage        = "http://logstash.net/"
+  s.require_paths = ["lib"]
+
+  # Files
+  s.files = `git ls-files`.split($\)
+
+  # Tests
+  s.test_files = s.files.grep(%r{^(test|spec|features)/})
+
+  # Special flag to let us know this is actually a logstash plugin
+  s.metadata = { "logstash_plugin" => "true", "group" => "codec" }
+
+  # Gem dependencies
+  s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
+
+  if RUBY_PLATFORM == 'java'
+    s.platform = RUBY_PLATFORM
+    s.add_runtime_dependency 'msgpack-jruby'
+  else
+    s.add_runtime_dependency 'msgpack'
+  end
+
+end
+

data/rakelib/publish.rake

@@ -0,0 +1,23 @@
+require "gem_publisher"
+
+
+module GemPublisher
+  class CliFacade
+    def execute(*arguments)
+      cmd = Shellwords.join(arguments)
+      puts cmd
+      Open3.popen3(cmd) do |_i, stdout, stderr, thr|
+        output = [stderr.read, stdout.read].join.strip
+        raise Error, output if thr.value.exitstatus > 0
+        return output
+      end
+    end
+  end
+end
+
+desc "Publish gem to RubyGems.org"
+task :publish_gem do |t|
+  gem_file = Dir.glob(File.expand_path('../*.gemspec',File.dirname(__FILE__))).first
+  gem = GemPublisher.publish_if_updated(gem_file, :rubygems)
+  puts "Published #{gem}" if gem
+end

data/rakelib/vendor.rake

@@ -0,0 +1,169 @@
+require "net/http"
+require "uri"
+require "digest/sha1"
+
+def vendor(*args)
+  return File.join("vendor", *args)
+end
+
+directory "vendor/" => ["vendor"] do |task, args|
+  mkdir task.name
+end
+
+def fetch(url, sha1, output)
+
+  puts "Downloading #{url}"
+  actual_sha1 = download(url, output)
+
+  if actual_sha1 != sha1
+    fail "SHA1 does not match (expected '#{sha1}' but got '#{actual_sha1}')"
+  end
+end # def fetch
+
+def file_fetch(url, sha1)
+  filename = File.basename( URI(url).path )
+  output = "vendor/#{filename}"
+  task output => [ "vendor/" ] do
+    begin
+      actual_sha1 = file_sha1(output)
+      if actual_sha1 != sha1
+        fetch(url, sha1, output)
+      end
+    rescue Errno::ENOENT
+      fetch(url, sha1, output)
+    end
+  end.invoke
+
+  return output
+end
+
+def file_sha1(path)
+  digest = Digest::SHA1.new
+  fd = File.new(path, "r")
+  while true
+    begin
+      digest << fd.sysread(16384)
+    rescue EOFError
+      break
+    end
+  end
+  return digest.hexdigest
+ensure
+  fd.close if fd
+end
+
+def download(url, output)
+  uri = URI(url)
+  digest = Digest::SHA1.new
+  tmp = "#{output}.tmp"
+  Net::HTTP.start(uri.host, uri.port, :use_ssl => (uri.scheme == "https")) do |http|
+    request = Net::HTTP::Get.new(uri.path)
+    http.request(request) do |response|
+      fail "HTTP fetch failed for #{url}. #{response}" if [200, 301].include?(response.code)
+      size = (response["content-length"].to_i || -1).to_f
+      count = 0
+      File.open(tmp, "w") do |fd|
+        response.read_body do |chunk|
+          fd.write(chunk)
+          digest << chunk
+          if size > 0 && $stdout.tty?
+            count += chunk.bytesize
+            $stdout.write(sprintf("\r%0.2f%%", count/size * 100))
+          end
+        end
+      end
+      $stdout.write("\r      \r") if $stdout.tty?
+    end
+  end
+
+  File.rename(tmp, output)
+
+  return digest.hexdigest
+rescue SocketError => e
+  puts "Failure while downloading #{url}: #{e}"
+  raise
+ensure
+  File.unlink(tmp) if File.exist?(tmp)
+end # def download
+
+def untar(tarball, &block)
+  require "archive/tar/minitar"
+  tgz = Zlib::GzipReader.new(File.open(tarball))
+  # Pull out typesdb
+  tar = Archive::Tar::Minitar::Input.open(tgz)
+  tar.each do |entry|
+    path = block.call(entry)
+    next if path.nil?
+    parent = File.dirname(path)
+    
+    mkdir_p parent unless File.directory?(parent)
+
+    # Skip this file if the output file is the same size
+    if entry.directory?
+      mkdir path unless File.directory?(path)
+    else
+      entry_mode = entry.instance_eval { @mode } & 0777
+      if File.exists?(path)
+        stat = File.stat(path)
+        # TODO(sissel): Submit a patch to archive-tar-minitar upstream to
+        # expose headers in the entry.
+        entry_size = entry.instance_eval { @size }
+        # If file sizes are same, skip writing.
+        next if stat.size == entry_size && (stat.mode & 0777) == entry_mode
+      end
+      puts "Extracting #{entry.full_name} from #{tarball} #{entry_mode.to_s(8)}"
+      File.open(path, "w") do |fd|
+        # eof? check lets us skip empty files. Necessary because the API provided by
+        # Archive::Tar::Minitar::Reader::EntryStream only mostly acts like an
+        # IO object. Something about empty files in this EntryStream causes
+        # IO.copy_stream to throw "can't convert nil into String" on JRuby
+        # TODO(sissel): File a bug about this.
+        while !entry.eof?
+          chunk = entry.read(16384)
+          fd.write(chunk)
+        end
+          #IO.copy_stream(entry, fd)
+      end
+      File.chmod(entry_mode, path)
+    end
+  end
+  tar.close
+  File.unlink(tarball) if File.file?(tarball)
+end # def untar
+
+def ungz(file)
+
+  outpath = file.gsub('.gz', '')
+  tgz = Zlib::GzipReader.new(File.open(file))
+  begin
+    File.open(outpath, "w") do |out|
+      IO::copy_stream(tgz, out)
+    end
+    File.unlink(file)
+  rescue
+    File.unlink(outpath) if File.file?(outpath)
+   raise
+  end
+  tgz.close
+end
+
+desc "Process any vendor files required for this plugin"
+task "vendor" do |task, args|
+
+  @files.each do |file| 
+    download = file_fetch(file['url'], file['sha1'])
+    if download =~ /.tar.gz/
+      prefix = download.gsub('.tar.gz', '').gsub('vendor/', '')
+      untar(download) do |entry|
+        if !file['files'].nil?
+          next unless file['files'].include?(entry.full_name.gsub(prefix, ''))
+          out = entry.full_name.split("/").last
+        end
+        File.join('vendor', out)
+      end
+    elsif download =~ /.gz/
+      ungz(download)
+    end
+  end
+
+end

data/spec/codecs/fluent_spec.rb

@@ -0,0 +1 @@
+require 'spec_helper'

metadata

@@ -0,0 +1,89 @@
+--- !ruby/object:Gem::Specification
+name: logstash-codec-fluent
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: java
+authors:
+- Elasticsearch
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2014-11-14 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: logstash
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 1.4.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: 1.4.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+  prerelease: false
+  type: :runtime
+- !ruby/object:Gem::Dependency
+  name: msgpack-jruby
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  prerelease: false
+  type: :runtime
+description: This codec handles fluentd's msgpack schema.
+email: richard.pijnenburg@elasticsearch.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE
+- Rakefile
+- lib/logstash/codecs/fluent.rb
+- logstash-codec-fluent.gemspec
+- rakelib/publish.rake
+- rakelib/vendor.rake
+- spec/codecs/fluent_spec.rb
+homepage: http://logstash.net/
+licenses:
+- Apache License (2.0)
+metadata:
+  logstash_plugin: 'true'
+  group: codec
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project:
+rubygems_version: 2.1.9
+signing_key:
+specification_version: 4
+summary: This codec handles fluentd's msgpack schema.
+test_files:
+- spec/codecs/fluent_spec.rb