logstash-output-webhdfs 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 9f37f22c7256c852597fc24ff4578a11503f68b7
+  data.tar.gz: 968727c576295ddb49f09f8230418e14828da865
+SHA512:
+  metadata.gz: 7d9f851d5b01629602616fdf58ad009bf09e3a8bf5befe8d0313e61eddaf10ce9b5ae2b196f38e2119f2f6098387547eda3b6f9f6af96af7685b45369efadb89
+  data.tar.gz: ee608a1e5f9876d0aa0df0d4bbc11192d62668ac97ca91b8a17434fc744730301b69472b020d0085efc3dfcded5bff68facc4c7b2c525e7ea6cefd89017fea6c

data/.gitignore

@@ -0,0 +1,19 @@
+*.gem
+*.rbc
+.bundle
+.config
+coverage
+InstalledFiles
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+.idea/
+# YARD artifacts
+.yardoc
+_yardoc
+doc/
+*.conf

data/Gemfile

@@ -0,0 +1,2 @@
+source 'https://rubygems.org'
+gemspec

data/LICENSE

@@ -0,0 +1,13 @@
+# Copyright 2014-2015 dbap GmbH. <http://www.dbap.de>
+#
+# 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/README.md

@@ -0,0 +1,86 @@
+# Logstash Plugin
+
+This is a plugin for [Logstash](https://github.com/elasticsearch/logstash).
+
+It is fully free and fully open source. The license is Apache 2.0, meaning you are pretty much free to use it however you want in whatever way.
+
+## Documentation
+
+Logstash provides infrastructure to automatically generate documentation for this plugin. We use the asciidoc format to write documentation so any comments in the source code will be first converted into asciidoc and then into html. All plugin documentation are placed under one [central location](http://www.elasticsearch.org/guide/en/logstash/current/).
+
+- For formatting code or config example, you can use the asciidoc `[source,ruby]` directive
+- For more asciidoc formatting tips, see the excellent reference here https://github.com/elasticsearch/docs#asciidoc-guide
+
+## Need Help?
+
+Need help? Try #logstash on freenode IRC or the logstash-users@googlegroups.com mailing list.
+
+## Developing
+
+### 1. Plugin Developement and Testing
+
+#### Code
+- To get started, you'll need JRuby with the Bundler gem installed.
+
+- Create a new plugin or clone and existing from the GitHub [logstash-plugins](https://github.com/logstash-plugins) organization. We also provide [example plugins](https://github.com/logstash-plugins?query=example).
+
+- Install dependencies
+```sh
+bundle install
+```
+
+#### Test
+
+- Update your dependencies
+
+```sh
+bundle install
+```
+
+- Run tests
+
+```sh
+bundle exec rspec
+```
+
+### 2. Running your unpublished Plugin in Logstash
+
+#### 2.1 Run in a local Logstash clone
+
+- Edit Logstash `Gemfile` and add the local plugin path, for example:
+```ruby
+gem "logstash-filter-awesome", :path => "/your/local/logstash-filter-awesome"
+```
+- Install plugin
+```sh
+bin/plugin install --no-verify
+```
+- Run Logstash with your plugin
+```sh
+bin/logstash -e 'filter {awesome {}}'
+```
+At this point any modifications to the plugin code will be applied to this local Logstash setup. After modifying the plugin, simply rerun Logstash.
+
+#### 2.2 Run in an installed Logstash
+
+You can use the same **2.1** method to run your plugin in an installed Logstash by editing its `Gemfile` and pointing the `:path` to your local plugin development directory or you can build the gem and install it using:
+
+- Build your plugin gem
+```sh
+gem build logstash-filter-awesome.gemspec
+```
+- Install the plugin from the Logstash home
+```sh
+bin/plugin install /your/local/plugin/logstash-filter-awesome.gem
+```
+- Start Logstash and proceed to test the plugin
+
+## Contributing
+
+All contributions are welcome: ideas, patches, documentation, bug reports, complaints, and even something you drew up on a napkin.
+
+Programming is not a required skill. Whatever you've seen about open source and maintainers or community members  saying "send patches or die" - you will not see that here.
+
+It is more important to the community that you are able to contribute.
+
+For more information about contributing, see the [CONTRIBUTING](https://github.com/elasticsearch/logstash/blob/master/CONTRIBUTING.md) file.

data/Rakefile

@@ -0,0 +1,7 @@
+@files=[]
+
+task :default do
+  system("rake -T")
+end
+
+require "logstash/devutils/rake"

data/lib/logstash/outputs/webhdfs.rb

@@ -0,0 +1,275 @@
+# encoding: utf-8
+require "logstash/namespace"
+require "logstash/outputs/base"
+require "stud/buffer"
+
+# Summary: Plugin to send logstash events to to files in HDFS via webhdfs 
+# restapi.  
+#
+# This plugin only has a mandatory dependency on the webhdfs gem from 
+# Tagamori Satoshi (@see: https://github.com/kzk/webhdfs).
+# Optional dependencies are zlib and snappy gem. 
+# No jars from hadoop are needed, thus reducing configuration and compatibility
+# problems.
+#
+# USAGE:
+# This is an example of logstash config:
+#
+# [source,ruby]
+# ----------------------------------
+# webhdfs {
+#   server => "127.0.0.1:50070"         # (required)
+#   path => "/user/logstash/dt=%{+YYYY-MM-dd}/logstash-%{+HH}.log"  # (required)
+#   user => "hue"                       # (optional)
+#   message_format => "%{@source_host}" # (optional)
+#   idle_flush_time => 10               # (optional)
+#   flush_size => 50                    # (optional)
+#   open_timeout => 15                  # (optional)
+#   read_timeout => 15                  # (optional)
+#   use_httpfs => true                  # (optional)
+#   retry_interval => 1                 # (optional)
+#   retry_times => 3                    # (optional)
+#   compress => "snappy"                # (optional)
+#   remove_at_timestamp => false        # (optional)
+# }
+# ----------------------------------
+#
+# Author: Bjoern Puttmann <b.puttmann@dbap.de> - dbap GmbH, Münster, Germany.
+
+class LogStash::Outputs::WebHdfs < LogStash::Outputs::Base
+  include Stud::Buffer
+
+  config_name "webhdfs"
+  milestone 1
+
+  if RUBY_VERSION[0..2] == '1.8'
+    MAGIC = "\x82SNAPPY\x0"
+  else
+    MAGIC = "\x82SNAPPY\x0".force_encoding Encoding::ASCII_8BIT
+  end
+  DEFAULT_VERSION = 1
+  MINIMUM_COMPATIBLE_VERSION = 1
+
+  # The server name and port for webhdfs/httpfs connections.
+  config :server, :validate => :string, :required => true
+
+  # The Username for webhdfs.
+  config :user, :validate => :string, :required => false
+
+  # The path to the file to write to. Event fields can be used here,
+  # as well as date fields in the joda time format, e.g.:
+  # ....
+  #     "/user/logstash/dt=%{+YYYY-MM-dd}/%{@source_host}-%{+HH}.log"
+  # ....
+  config :path, :validate => :string, :required => true
+
+  # The format to use when writing events to the file. This value
+  # supports any string and can include %{name} and other dynamic
+  # strings.
+  #
+  # If this setting is omitted, the full json representation of the
+  # event will be written as a single line.
+  config :message_format, :validate => :string
+
+  # Sending data to webhdfs in x seconds intervals.
+  config :idle_flush_time, :validate => :number, :default => 1
+
+  # Sending data to webhdfs if event count is above, even if store_interval_in_secs is not reached.
+  config :flush_size, :validate => :number, :default => 500
+
+  # WebHdfs open timeout, default 30s (in ruby net/http).
+  config :open_timeout, :validate => :number, :default => 30
+
+  # The WebHdfs read timeout, default 30s (in ruby net/http).
+  config :read_timeout, :validate => :number, :default => 30
+
+  # Use httpfs mode if set to true, else webhdfs.
+  config :use_httpfs, :validate => :boolean, :default => false
+
+  # Retry some known webhdfs errors. These may be caused by race conditions when appending to same file, etc.
+  config :retry_known_errors, :validate => :boolean, :default => true
+
+  # How long should we wait between retries.
+  config :retry_interval, :validate => :number, :default => 0.5
+
+  # How many times should we retry.
+  config :retry_times, :validate => :number, :default => 5
+
+  # Compress output. One of [false, 'snappy', 'gzip']
+  config :compress, :validate => ["false", "snappy", "gzip"], :default => "false"
+
+  # Set snappy chunksize. Only neccessary for stream format. Defaults to 32k. Max is 65536
+  # @see http://code.google.com/p/snappy/source/browse/trunk/framing_format.txt
+  config :snappy_bufsize, :validate => :number, :default => 32768
+
+  # Set snappy format. One of "stream", "file". Set to stream to be hive compatible.
+  config :snappy_format, :validate => ["stream", "file"], :default => "stream"
+
+  # Remove @timestamp field. Hive does not like a leading "@", but we need @timestamp for path calculation.
+  config :remove_at_timestamp, :validate => :boolean, :default => true
+
+  public
+
+  def register
+    begin
+      require 'webhdfs'
+    rescue LoadError
+      @logger.error("Module webhdfs could not be loaded.")
+    end
+    if @compress == "gzip"
+      begin
+        require "zlib"
+      rescue LoadError
+        @logger.error("Gzip compression selected but zlib module could not be loaded.")
+      end
+    elsif @compress == "snappy"
+      begin
+        require "snappy"
+      rescue LoadError
+        @logger.error("Snappy compression selected but snappy module could not be loaded.")
+      end
+    end
+    @files = {}
+    @host, @port = @server.split(':')
+    @client = prepare_client(@host, @port, @user)
+    # Test client connection.
+    begin
+      @client.list('/')
+    rescue => e
+      @logger.error("Webhdfs check request failed. (namenode: #{@client.host}:#{@client.port}, Exception: #{e.message})")
+    end
+    buffer_initialize(
+    :max_items => @flush_size,
+    :max_interval => @idle_flush_time,
+    :logger => @logger
+    )
+  end # def register
+
+  public
+  def receive(event)
+    return unless output?(event)
+    buffer_receive(event)
+  end # def receive
+
+  def prepare_client(host, port, username)
+    client = WebHDFS::Client.new(host, port, username)
+    if @use_httpfs
+      client.httpfs_mode = true
+    end
+    client.open_timeout = @open_timeout
+    client.read_timeout = @read_timeout
+    if @retry_known_errors
+      client.retry_known_errors = true
+      client.retry_interval = @retry_interval if @retry_interval
+      client.retry_times = @retry_times if @retry_times
+    end
+    client
+  end
+
+  def flush(events=nil, teardown=false)
+    return if not events
+    # Avoid creating a new string for newline every time
+    newline = "\n".freeze
+    output_files = Hash.new { |hash, key| hash[key] = "" }
+    events.collect do |event|
+      path = event.sprintf(@path)
+      if @remove_at_timestamp
+        event.remove("@timestamp")
+      end
+      if @message_format
+        event_as_string = event.sprintf(@message_format)
+      else
+        event_as_string = event.to_json
+      end
+      event_as_string += newline unless event_as_string.end_with? newline
+      output_files[path] << event_as_string
+    end
+    output_files.each do |path, output|
+      if @compress == "gzip"
+        path += ".gz"
+        output = compress_gzip(output)
+      elsif @compress == "snappy"
+        path += ".snappy"
+        if @snappy_format == "file"
+          output = compress_snappy_file(output)
+        elsif
+        output = compress_snappy_stream(output)
+        end
+      end
+      write_tries = 0
+      while write_tries < @retry_times do
+        begin
+          write_data(path, output)
+          break
+        rescue => e
+          write_tries += 1
+          # Retry max_retry times. This can solve problems like leases being hold by another process. Sadly this is no
+          # KNOWN_ERROR in rubys webhdfs client.
+          if write_tries < @retry_times
+            @logger.warn("Retrying webhdfs write for multiple times. Maybe you should increase retry_interval or reduce number of workers.")
+            sleep(@retry_interval * write_tries)
+            next
+          else
+            # Issue error after max retries.
+            @logger.error("Max write retries reached. Exception: #{e.message}")
+          end
+        end
+      end
+    end
+  end
+
+  def compress_gzip(data)
+    buffer = StringIO.new('','w')
+    compressor = Zlib::GzipWriter.new(buffer)
+    begin
+      compressor.write data
+    ensure
+      compressor.close()
+    end
+    buffer.string
+  end
+
+  def compress_snappy_file(data)
+    # Encode data to ASCII_8BIT (binary)
+    data= data.encode(Encoding::ASCII_8BIT, "binary", :undef => :replace)
+    buffer = StringIO.new('', 'w')
+    buffer.set_encoding Encoding::ASCII_8BIT unless RUBY_VERSION =~ /^1\.8/
+    compressed = Snappy.deflate(chunk)
+    buffer << [compressed.size, compressed].pack("Na*")
+    buffer.string
+  end
+
+  def compress_snappy_stream(data)
+    # Encode data to ASCII_8BIT (binary)
+    data= data.encode(Encoding::ASCII_8BIT, "binary", :undef => :replace)
+    buffer = StringIO.new
+    buffer.set_encoding Encoding::ASCII_8BIT unless RUBY_VERSION =~ /^1\.8/
+    chunks = data.scan(/.{1,#{@snappy_bufsize}}/m)
+    chunks.each do |chunk|
+      compressed = Snappy.deflate(chunk)
+      buffer << [chunk.size, compressed.size, compressed].pack("NNa*")
+    end
+    return buffer.string
+  end
+
+  def get_snappy_header!
+    [MAGIC, DEFAULT_VERSION, MINIMUM_COMPATIBLE_VERSION].pack("a8NN")
+  end
+
+  def write_data(path, data)
+    begin
+      @client.append(path, data)
+    rescue WebHDFS::FileNotFoundError
+      # Add snappy header if format is "file".
+      if @snappy_format == "file"
+        @client.create(path, get_snappy_header! + data)
+      elsif
+        @client.create(path, data)
+      end
+    end
+  end
+
+  def teardown
+    buffer_flush(:final => true)
+  end # def teardown
+end

data/logstash-output-webhdfs.gemspec

@@ -0,0 +1,27 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-output-webhdfs'
+  s.version         = '0.0.1'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "Plugin to write events to hdfs via webhdfs."
+  s.description     = "This gem is a logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/plugin install gemname. This gem is not a stand-alone program"
+  s.authors         = ["Björn Puttmann, loshkovskyi"]
+  s.email           = 'b.puttmann@dbap.de'
+  s.homepage        = "http://www.dbap.de"
+  s.require_paths = ["lib"]
+
+  # Files
+  s.files = `git ls-files`.split($\)+::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", "logstash_group" => "output" }
+
+  # Gem dependencies
+  s.add_runtime_dependency 'logstash-core', '>= 1.4.0', '< 2.0.0'
+  s.add_runtime_dependency 'webhdfs'
+  s.add_runtime_dependency 'snappy'
+  s.add_development_dependency 'logstash-devutils'
+end

data/spec/outputs/webhdfs_spec.rb

@@ -0,0 +1,49 @@
+# encoding: utf-8
+require 'logstash/devutils/rspec/spec_helper'
+require 'logstash/outputs/webhdfs'
+
+describe 'outputs/webhdfs' do
+
+  let(:event) do
+    LogStash::Event.new(
+        'message' => 'fanastic log entry',
+        'source' => 'someapp',
+        'type' => 'nginx',
+        '@timestamp' => LogStash::Timestamp.now)
+  end
+
+  context 'when initializing' do
+
+    it 'should fail to register without required values' do
+      configuration_error = false
+      begin
+        LogStash::Plugin.lookup("output", "webhdfs").new()
+      rescue LogStash::ConfigurationError
+        configuration_error = true
+      end
+      insist { configuration_error } == true
+    end
+
+    subject = LogStash::Plugin.lookup("output", "webhdfs").new('server' => '127.0.0.1:50070', 'path' => '/path/to/webhdfs.file')
+
+    it 'should register' do
+      expect { subject.register }.to_not raise_error
+    end
+
+    it 'should have default config values' do
+      insist { subject.idle_flush_time } == 1
+      insist { subject.flush_size } == 500
+      insist { subject.open_timeout } == 30
+      insist { subject.read_timeout } == 30
+      insist { subject.use_httpfs } == false
+      insist { subject.retry_known_errors } == true
+      insist { subject.retry_interval } == 0.5
+      insist { subject.retry_times } == 5
+      insist { subject.snappy_bufsize } == 32768
+      insist { subject.snappy_format } == 'stream'
+      insist { subject.remove_at_timestamp } == true
+    end
+
+  end
+
+end

metadata

@@ -0,0 +1,116 @@
+--- !ruby/object:Gem::Specification
+name: logstash-output-webhdfs
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Björn Puttmann, loshkovskyi
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2015-05-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: logstash-core
+  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: webhdfs
+  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
+- !ruby/object:Gem::Dependency
+  name: snappy
+  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
+- !ruby/object:Gem::Dependency
+  name: logstash-devutils
+  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: :development
+description: This gem is a logstash plugin required to be installed on top of the Logstash core pipeline using $LS_HOME/bin/plugin install gemname. This gem is not a stand-alone program
+email: b.puttmann@dbap.de
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- lib/logstash/outputs/webhdfs.rb
+- logstash-output-webhdfs.gemspec
+- spec/outputs/webhdfs_spec.rb
+homepage: http://www.dbap.de
+licenses:
+- Apache License (2.0)
+metadata:
+  logstash_plugin: 'true'
+  logstash_group: output
+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: 2.2.4
+signing_key:
+specification_version: 4
+summary: Plugin to write events to hdfs via webhdfs.
+test_files:
+- spec/outputs/webhdfs_spec.rb