logstash-input-redis 0.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    YjRkY2M1Y2NlMGJjYjMyM2E3ODZhN2U4MWRiZDJhYWIzZjhmM2IzMA==
+  data.tar.gz: !binary |-
+    MWU2MGNlNDI0YTc3YjA4OWQyNzhlYzBkMTkzY2FkNTJlMTZkNDI0Yw==
+SHA512:
+  metadata.gz: !binary |-
+    ODgxMjRkYTc5MzMyOTNiMWVlNzRmZGUyMDRhNzc2NzA4ZmIwNzAzNDllNzVh
+    NzA5ZTU2Mzk1NmE5ZDc2ZmUzODgzZWI2OTBiYTQ4NmQzNGU5ZmE2ODJlY2Vj
+    YjE1ODAxNTI1NTk3MGE3MzEyNTVlNGE5OGIxMjRlNGMyZDJlNmQ=
+  data.tar.gz: !binary |-
+    YmRhZGMzZmUxODJiNDBlM2FkZDA2ZGJjZTI4NGQzNzdhNjk3NDJmMThhOTVj
+    NmZiZmQ0NjJjNThkMzc3MmQzM2RiZmQ3ZWUzYTVkMmE3NDA3ZjVhNGMxMTFm
+    N2MwYTBlMDJjMzFlNGM1MzQ0MmE5MGU5ODMwOTQyNWU4NmVlYmY=

data/.gitignore

@@ -0,0 +1,4 @@
+*.gem
+Gemfile.lock
+.bundle
+vendor

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/inputs/redis.rb

@@ -0,0 +1,266 @@
+# encoding: utf-8
+require "logstash/inputs/base"
+require "logstash/inputs/threadable"
+require "logstash/namespace"
+
+# This input will read events from a Redis instance; it supports both Redis channels and lists.
+# The list command (BLPOP) used by Logstash is supported in Redis v1.3.1+, and
+# the channel commands used by Logstash are found in Redis v1.3.8+. 
+# While you may be able to make these Redis versions work, the best performance
+# and stability will be found in more recent stable versions.  Versions 2.6.0+
+# are recommended.
+#
+# For more information about Redis, see <http://redis.io/>
+#
+# `batch_count` note: If you use the `batch_count` setting, you *must* use a Redis version 2.6.0 or
+# newer. Anything older does not support the operations used by batching.
+#
+class LogStash::Inputs::Redis < LogStash::Inputs::Threadable
+  config_name "redis"
+  milestone 2
+
+  default :codec, "json"
+
+  # The `name` configuration is used for logging in case there are multiple instances.
+  # This feature has no real function and will be removed in future versions.
+  config :name, :validate => :string, :default => "default", :deprecated => true
+
+  # The hostname of your Redis server.
+  config :host, :validate => :string, :default => "127.0.0.1"
+
+  # The port to connect on.
+  config :port, :validate => :number, :default => 6379
+
+  # The Redis database number.
+  config :db, :validate => :number, :default => 0
+
+  # Initial connection timeout in seconds.
+  config :timeout, :validate => :number, :default => 5
+
+  # Password to authenticate with. There is no authentication by default.
+  config :password, :validate => :password
+
+  # The name of the Redis queue (we'll use BLPOP against this).
+  # TODO: remove soon.
+  config :queue, :validate => :string, :deprecated => true
+
+  # The name of a Redis list or channel.
+  # TODO: change required to true
+  config :key, :validate => :string, :required => false
+
+  # Specify either list or channel.  If `redis\_type` is `list`, then we will BLPOP the
+  # key.  If `redis\_type` is `channel`, then we will SUBSCRIBE to the key.
+  # If `redis\_type` is `pattern_channel`, then we will PSUBSCRIBE to the key.
+  # TODO: change required to true
+  config :data_type, :validate => [ "list", "channel", "pattern_channel" ], :required => false
+
+  # The number of events to return from Redis using EVAL.
+  config :batch_count, :validate => :number, :default => 1
+
+  public
+  def register
+    require 'redis'
+    @redis = nil
+    @redis_url = "redis://#{@password}@#{@host}:#{@port}/#{@db}"
+
+    # TODO remove after setting key and data_type to true
+    if @queue
+      if @key or @data_type
+        raise RuntimeError.new(
+          "Cannot specify queue parameter and key or data_type"
+        )
+      end
+      @key = @queue
+      @data_type = 'list'
+    end
+
+    if not @key or not @data_type
+      raise RuntimeError.new(
+        "Must define queue, or key and data_type parameters"
+      )
+    end
+    # end TODO
+
+    @logger.info("Registering Redis", :identity => identity)
+  end # def register
+
+  # A string used to identify a Redis instance in log messages
+  # TODO(sissel): Use instance variables for this once the @name config
+  # option is removed.
+  private
+  def identity
+    @name || "#{@redis_url} #{@data_type}:#{@key}"
+  end
+
+  private
+  def connect
+    redis = Redis.new(
+      :host => @host,
+      :port => @port,
+      :timeout => @timeout,
+      :db => @db,
+      :password => @password.nil? ? nil : @password.value
+    )
+    load_batch_script(redis) if @data_type == 'list' && (@batch_count > 1)
+    return redis
+  end # def connect
+
+  private
+  def load_batch_script(redis)
+    #A Redis Lua EVAL script to fetch a count of keys
+    #in case count is bigger than current items in queue whole queue will be returned without extra nil values
+    redis_script = <<EOF
+          local i = tonumber(ARGV[1])
+          local res = {}
+          local length = redis.call('llen',KEYS[1])
+          if length < i then i = length end
+          while (i > 0) do
+            local item = redis.call("lpop", KEYS[1])
+            if (not item) then
+              break
+            end
+            table.insert(res, item)
+            i = i-1
+          end
+          return res
+EOF
+    @redis_script_sha = redis.script(:load, redis_script)
+  end
+
+  private
+  def queue_event(msg, output_queue)
+    begin
+      @codec.decode(msg) do |event|
+        decorate(event)
+        output_queue << event
+      end
+    rescue => e # parse or event creation error
+      @logger.error("Failed to create event", :message => msg, :exception => e,
+                    :backtrace => e.backtrace);
+    end
+  end
+
+  private
+  def list_listener(redis, output_queue)
+
+    # blpop returns the 'key' read from as well as the item result
+    # we only care about the result (2nd item in the list).
+    item = redis.blpop(@key, 0)[1]
+
+    # blpop failed or .. something?
+    # TODO(sissel): handle the error
+    return if item.nil?
+    queue_event(item, output_queue)
+
+    # If @batch_count is 1, there's no need to continue.
+    return if @batch_count == 1
+
+    begin
+      redis.evalsha(@redis_script_sha, [@key], [@batch_count-1]).each do |item|
+        queue_event(item, output_queue)
+      end
+
+      # Below is a commented-out implementation of 'batch fetch'
+      # using pipelined LPOP calls. This in practice has been observed to
+      # perform exactly the same in terms of event throughput as
+      # the evalsha method. Given that the EVALSHA implementation uses
+      # one call to Redis instead of N (where N == @batch_count) calls,
+      # I decided to go with the 'evalsha' method of fetching N items
+      # from Redis in bulk.
+      #redis.pipelined do
+        #error, item = redis.lpop(@key)
+        #(@batch_count-1).times { redis.lpop(@key) }
+      #end.each do |item|
+        #queue_event(item, output_queue) if item
+      #end
+      # --- End commented out implementation of 'batch fetch'
+    rescue Redis::CommandError => e
+      if e.to_s =~ /NOSCRIPT/ then
+        @logger.warn("Redis may have been restarted, reloading Redis batch EVAL script", :exception => e);
+        load_batch_script(redis)
+        retry
+      else
+        raise e
+      end
+    end
+  end
+
+  private
+  def channel_listener(redis, output_queue)
+    redis.subscribe @key do |on|
+      on.subscribe do |channel, count|
+        @logger.info("Subscribed", :channel => channel, :count => count)
+      end
+
+      on.message do |channel, message|
+        queue_event message, output_queue
+      end
+
+      on.unsubscribe do |channel, count|
+        @logger.info("Unsubscribed", :channel => channel, :count => count)
+      end
+    end
+  end
+
+  private
+  def pattern_channel_listener(redis, output_queue)
+    redis.psubscribe @key do |on|
+      on.psubscribe do |channel, count|
+        @logger.info("Subscribed", :channel => channel, :count => count)
+      end
+
+      on.pmessage do |ch, event, message|
+        queue_event message, output_queue
+      end
+
+      on.punsubscribe do |channel, count|
+        @logger.info("Unsubscribed", :channel => channel, :count => count)
+      end
+    end
+  end
+
+  # Since both listeners have the same basic loop, we've abstracted the outer
+  # loop.
+  private
+  def listener_loop(listener, output_queue)
+    while !finished?
+      begin
+        @redis ||= connect
+        self.send listener, @redis, output_queue
+      rescue Redis::CannotConnectError => e
+        @logger.warn("Redis connection problem", :exception => e)
+        sleep 1
+        @redis = connect
+      rescue => e # Redis error
+        @logger.warn("Failed to get event from Redis", :name => @name,
+                     :exception => e, :backtrace => e.backtrace)
+        raise e
+      end
+    end # while !finished?
+  end # listener_loop
+
+  public
+  def run(output_queue)
+    if @data_type == 'list'
+      listener_loop :list_listener, output_queue
+    elsif @data_type == 'channel'
+      listener_loop :channel_listener, output_queue
+    else
+      listener_loop :pattern_channel_listener, output_queue
+    end
+  end # def run
+
+  public
+  def teardown
+    if @data_type == 'channel' and @redis
+      @redis.unsubscribe
+      @redis.quit
+      @redis = nil
+    end
+    if @data_type == 'pattern_channel' and @redis
+      @redis.punsubscribe
+      @redis.quit
+      @redis = nil
+    end
+  end
+end # class LogStash::Inputs::Redis

data/logstash-input-redis.gemspec

@@ -0,0 +1,29 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-input-redis'
+  s.version         = '0.1.0'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "This input will read events from a Redis instance"
+  s.description     = "This input will read events from a Redis instance; it supports both Redis channels and lists."
+  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($\)+::Dir.glob('vendor/*')
+
+  # 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" => "input" }
+
+  # Gem dependencies
+  s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
+
+  s.add_runtime_dependency 'logstash-codec-json'
+  s.add_runtime_dependency 'redis'
+
+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/inputs/redis_spec.rb

@@ -0,0 +1,63 @@
+require "spec_helper"
+require "redis"
+
+def populate(key, event_count)
+  require "logstash/event"
+  redis = Redis.new(:host => "localhost")
+  event_count.times do |value|
+    event = LogStash::Event.new("sequence" => value)
+    Stud::try(10.times) do
+      redis.rpush(key, event.to_json)
+    end
+  end
+end
+
+def process(pipeline, queue, event_count)
+  sequence = 0
+  Thread.new { pipeline.run }
+  event_count.times do |i|
+    event = queue.pop
+    insist { event["sequence"] } == i
+  end
+  pipeline.shutdown
+end # process
+
+describe "inputs/redis", :redis => true do
+  
+
+  describe "read events from a list" do
+    key = 10.times.collect { rand(10).to_s }.join("")
+    event_count = 1000 + rand(50)
+    config <<-CONFIG
+      input {
+        redis {
+          type => "blah"
+          key => "#{key}"
+          data_type => "list"
+        }
+      }
+    CONFIG
+
+    before(:each) { populate(key, event_count) }
+
+    input { |pipeline, queue| process(pipeline, queue, event_count) }
+  end
+
+  describe "read events from a list with batch_count=5" do
+    key = 10.times.collect { rand(10).to_s }.join("")
+    event_count = 1000 + rand(50)
+    config <<-CONFIG
+      input {
+        redis {
+          type => "blah"
+          key => "#{key}"
+          data_type => "list"
+          batch_count => #{rand(20)+1}
+        }
+      }
+    CONFIG
+
+    before(:each) { populate(key, event_count) }
+    input { |pipeline, queue| process(pipeline, queue, event_count) }
+  end
+end

metadata

@@ -0,0 +1,103 @@
+--- !ruby/object:Gem::Specification
+name: logstash-input-redis
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Elasticsearch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-11-03 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-json
+  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'
+- !ruby/object:Gem::Dependency
+  name: redis
+  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 input will read events from a Redis instance; it supports both Redis
+  channels and lists.
+email: richard.pijnenburg@elasticsearch.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- lib/logstash/inputs/redis.rb
+- logstash-input-redis.gemspec
+- rakelib/publish.rake
+- rakelib/vendor.rake
+- spec/inputs/redis_spec.rb
+homepage: http://logstash.net/
+licenses:
+- Apache License (2.0)
+metadata:
+  logstash_plugin: 'true'
+  group: input
+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 input will read events from a Redis instance
+test_files:
+- spec/inputs/redis_spec.rb