logstash-codec-json_lines 0.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    OTMyYzAwN2RiODY4ZjllNjNlZGEwNDhhYzFkYTFhODU3YWNiMmUzZA==
+  data.tar.gz: !binary |-
+    Y2EwZDlkNjU5N2FmZmVmMzE4MjZiMWM2ZGYzNzRmMjZjMmJiMDY4ZQ==
+SHA512:
+  metadata.gz: !binary |-
+    M2Q3YzEwYWQ1ZmE2MDg5YzU2ZjIxOGE0N2JlMGQ0ZTBkODgxOWI4OWIyNjM2
+    MzYxM2ZhYjE0ZGY5OGY1ZTJiZTEzYjIzMjM5YmM3NTc5MjA1ZWNlOTVhNzMx
+    ZDkxOTlmNWQyYTAyNmQyMDk1YTk2MzZmMWVlMGVmMjY2NTRhYWY=
+  data.tar.gz: !binary |-
+    YjM2MTE0ZDFjMzc3NTAxYjM0YWE1Mzk2NmYyN2FhNGY0YzE2MzVlOGFhMjRm
+    NDc2ZjhlZGEwOGZhMTJjYThjZDdkMWQ4ODZjNTI3MTAwMTE3ZTJmMTRkZmQy
+    MTcxZTMwZTJiZjBjZGZkNWNhMjMwNWViYmRmNzI1MDg4ZWZhMTg=

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/Rakefile

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

data/lib/logstash/codecs/json_lines.rb

@@ -0,0 +1,53 @@
+# encoding: utf-8
+require "logstash/codecs/base"
+require "logstash/codecs/line"
+require "logstash/json"
+
+# This codec will decode streamed JSON that is newline delimited.
+# For decoding line-oriented JSON payload in the redis or file inputs,
+# for example, use the json codec instead.
+# Encoding will emit a single JSON string ending in a '\n'
+class LogStash::Codecs::JSONLines < LogStash::Codecs::Base
+  config_name "json_lines"
+
+  milestone 3
+
+  # The character encoding used in this codec. Examples include "UTF-8" and
+  # "CP1252"
+  #
+  # JSON requires valid UTF-8 strings, but in some cases, software that
+  # emits JSON does so in another encoding (nxlog, for example). In
+  # weird cases like this, you can set the charset setting to the
+  # actual encoding of the text and logstash will convert it for you.
+  #
+  # For nxlog users, you'll want to set this to "CP1252"
+  config :charset, :validate => ::Encoding.name_list, :default => "UTF-8"
+
+  public
+  def initialize(params={})
+    super(params)
+    @lines = LogStash::Codecs::Line.new
+    @lines.charset = @charset
+  end
+
+  public
+  def decode(data)
+
+    @lines.decode(data) do |event|
+      begin
+        yield LogStash::Event.new(LogStash::Json.load(event["message"]))
+      rescue LogStash::Json::ParserError => e
+        @logger.info("JSON parse failure. Falling back to plain-text", :error => e, :data => data)
+        yield LogStash::Event.new("message" => event["message"])
+      end
+    end
+  end # def decode
+
+  public
+  def encode(event)
+    # Tack on a \n for now because previously most of logstash's JSON
+    # outputs emitted one per line, and whitespace is OK in json.
+    @on_event.call(event.to_json + NL)
+  end # def encode
+
+end # class LogStash::Codecs::JSON

data/logstash-codec-json_lines.gemspec

@@ -0,0 +1,28 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-codec-json_lines'
+  s.version         = '0.1.0'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "This codec will decode streamed JSON that is newline delimited."
+  s.description     = "This codec will decode streamed JSON that is newline delimited."
+  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'
+
+  s.add_runtime_dependency 'logstash-codec-line'
+
+end
+

data/rakelib/publish.rake

@@ -0,0 +1,9 @@
+require "gem_publisher"
+
+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/json_lines_spec.rb

@@ -0,0 +1,78 @@
+require "logstash/codecs/json_lines"
+require "logstash/event"
+require "logstash/json"
+require "insist"
+
+describe LogStash::Codecs::JSONLines do
+  subject do
+    next LogStash::Codecs::JSONLines.new
+  end
+
+  context "#decode" do
+    it "should return an event from json data" do
+      data = {"foo" => "bar", "baz" => {"bah" => ["a","b","c"]}}
+      subject.decode(LogStash::Json.dump(data) + "\n") do |event|
+        insist { event.is_a? LogStash::Event }
+        insist { event["foo"] } == data["foo"]
+        insist { event["baz"] } == data["baz"]
+        insist { event["bah"] } == data["bah"]
+      end
+    end
+
+    it "should return an event from json data when a newline is recieved" do
+      data = {"foo" => "bar", "baz" => {"bah" => ["a","b","c"]}}
+      subject.decode(LogStash::Json.dump(data)) do |event|
+        insist {false}
+      end
+      subject.decode("\n") do |event|
+        insist { event.is_a? LogStash::Event }
+        insist { event["foo"] } == data["foo"]
+        insist { event["baz"] } == data["baz"]
+        insist { event["bah"] } == data["bah"]
+      end
+    end
+
+    context "processing plain text" do
+      it "falls back to plain text" do
+        decoded = false
+        subject.decode("something that isn't json\n") do |event|
+          decoded = true
+          insist { event.is_a?(LogStash::Event) }
+          insist { event["message"] } == "something that isn't json"
+        end
+        insist { decoded } == true
+      end
+    end
+
+    context "processing weird binary blobs" do
+      it "falls back to plain text and doesn't crash (LOGSTASH-1595)" do
+        decoded = false
+        blob = (128..255).to_a.pack("C*").force_encoding("ASCII-8BIT")
+        subject.decode(blob)
+        subject.decode("\n") do |event|
+          decoded = true
+          insist { event.is_a?(LogStash::Event) }
+          insist { event["message"].encoding.to_s } == "UTF-8"
+        end
+        insist { decoded } == true
+      end
+    end
+  end
+
+  context "#encode" do
+    it "should return json data" do
+      data = {"foo" => "bar", "baz" => {"bah" => ["a","b","c"]}}
+      event = LogStash::Event.new(data)
+      got_event = false
+      subject.on_event do |d|
+        insist { d } == "#{LogStash::Event.new(data).to_json}\n"
+        insist { LogStash::Json.load(d)["foo"] } == data["foo"]
+        insist { LogStash::Json.load(d)["baz"] } == data["baz"]
+        insist { LogStash::Json.load(d)["bah"] } == data["bah"]
+        got_event = true
+      end
+      subject.encode(event)
+      insist { got_event }
+    end
+  end
+end

metadata

@@ -0,0 +1,88 @@
+--- !ruby/object:Gem::Specification
+name: logstash-codec-json_lines
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Elasticsearch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-10-30 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: logstash
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.4.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: 1.4.0
+    - - <
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+- !ruby/object:Gem::Dependency
+  name: logstash-codec-line
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: This codec will decode streamed JSON that is newline delimited.
+email: richard.pijnenburg@elasticsearch.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- lib/logstash/codecs/json_lines.rb
+- logstash-codec-json_lines.gemspec
+- rakelib/publish.rake
+- rakelib/vendor.rake
+- spec/codecs/json_lines_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: 2.4.1
+signing_key: 
+specification_version: 4
+summary: This codec will decode streamed JSON that is newline delimited.
+test_files:
+- spec/codecs/json_lines_spec.rb