logstash-input-twitter 0.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    M2M0NzBkNDE3MmM3ZDY1ZmRiMzExNDczN2ZmMmMyM2QxMDVmZDU2OA==
+  data.tar.gz: !binary |-
+    MDEwNmEyNTdkMTc3MGQxNjBjNzhkNjRiZjkxNTczMGU4ODdmZjlhMA==
+SHA512:
+  metadata.gz: !binary |-
+    OTUxMzk5NTUzOThkZDQyNGJmMDhhMDQyYmRhZjk0MTIwZGJiYzc3ZmY5Y2Vh
+    NWFhODVmOGEyNTI2MDczZTFjZTFmZWM2ZTBiODg3ZTYzMjFlMjIzOGRiNzE4
+    NTY0MWIzYzY5M2IwZjk2OTM5YTIzZmFmZjgyMTg3YzZlOTc3OGY=
+  data.tar.gz: !binary |-
+    NGQwNjIxOGRlMjg5YWYzODg4ZjcxNjBmY2NmMWRmNDVjZTdjYzY0NTk4ZmMx
+    M2M4MzZkMzJiMTUyZjJkMmE3MWMwZTQ4MmNjODVhNzUyMzYyNzc3OGRlMWU1
+    MTQ2YzdhNjFmZjA3NGFlMWYxOThiYzA0ZGM4YTkxYmVkOWVmZTQ=

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/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/inputs/twitter.rb

@@ -0,0 +1,124 @@
+# encoding: utf-8
+require "logstash/inputs/base"
+require "logstash/namespace"
+require "logstash/timestamp"
+require "logstash/util"
+require "logstash/json"
+
+# Read events from the twitter streaming api.
+class LogStash::Inputs::Twitter < LogStash::Inputs::Base
+
+  config_name "twitter"
+  milestone 1
+
+  # Your twitter app's consumer key
+  #
+  # Don't know what this is? You need to create an "application"
+  # on twitter, see this url: <https://dev.twitter.com/apps/new>
+  config :consumer_key, :validate => :string, :required => true
+
+  # Your twitter app's consumer secret
+  #
+  # If you don't have one of these, you can create one by
+  # registering a new application with twitter:
+  # <https://dev.twitter.com/apps/new>
+  config :consumer_secret, :validate => :password, :required => true
+
+  # Your oauth token.
+  #
+  # To get this, login to twitter with whatever account you want,
+  # then visit <https://dev.twitter.com/apps>
+  #
+  # Click on your app (used with the consumer_key and consumer_secret settings)
+  # Then at the bottom of the page, click 'Create my access token' which
+  # will create an oauth token and secret bound to your account and that
+  # application.
+  config :oauth_token, :validate => :string, :required => true
+
+  # Your oauth token secret.
+  #
+  # To get this, login to twitter with whatever account you want,
+  # then visit <https://dev.twitter.com/apps>
+  #
+  # Click on your app (used with the consumer_key and consumer_secret settings)
+  # Then at the bottom of the page, click 'Create my access token' which
+  # will create an oauth token and secret bound to your account and that
+  # application.
+  config :oauth_token_secret, :validate => :password, :required => true
+
+  # Any keywords to track in the twitter stream
+  config :keywords, :validate => :array, :required => true
+
+  # Record full tweet object as given to us by the Twitter stream api.
+  config :full_tweet, :validate => :boolean, :default => false
+
+  public
+  def register
+    require "twitter"
+
+    # monkey patch twitter gem to ignore json parsing error.
+    # at the same time, use our own json parser
+    # this has been tested with a specific gem version, raise if not the same
+    raise("Invalid Twitter gem") unless Twitter::Version.to_s == "5.0.0.rc.1"
+    Twitter::Streaming::Response.module_eval do
+      def on_body(data)
+        @tokenizer.extract(data).each do |line|
+          next if line.empty?
+          begin
+            @block.call(LogStash::Json.load(line, :symbolize_keys => true))
+          rescue LogStash::Json::ParserError
+            # silently ignore json parsing errors
+          end
+        end
+      end
+    end
+
+    @client = Twitter::Streaming::Client.new do |c|
+      c.consumer_key = @consumer_key
+      c.consumer_secret = @consumer_secret.value
+      c.access_token = @oauth_token
+      c.access_token_secret = @oauth_token_secret.value
+    end
+  end
+
+  public
+  def run(queue)
+    @logger.info("Starting twitter tracking", :keywords => @keywords)
+    begin
+      @client.filter(:track => @keywords.join(",")) do |tweet|
+        if tweet.is_a?(Twitter::Tweet)
+          @logger.debug? && @logger.debug("Got tweet", :user => tweet.user.screen_name, :text => tweet.text)
+          if @full_tweet
+            event = LogStash::Event.new(LogStash::Util.stringify_symbols(tweet.to_hash))
+            event.timestamp = LogStash::Timestamp.new(tweet.created_at)
+          else
+            event = LogStash::Event.new(
+              LogStash::Event::TIMESTAMP => LogStash::Timestamp.new(tweet.created_at),
+              "message" => tweet.full_text,
+              "user" => tweet.user.screen_name,
+              "client" => tweet.source,
+              "retweeted" => tweet.retweeted?,
+              "source" => "http://twitter.com/#{tweet.user.screen_name}/status/#{tweet.id}"
+            )
+            event["in-reply-to"] = tweet.in_reply_to_status_id if tweet.reply?
+            unless tweet.urls.empty?
+              event["urls"] = tweet.urls.map(&:expanded_url).map(&:to_s)
+            end
+          end
+
+          decorate(event)
+          queue << event
+        end
+      end # client.filter
+    rescue LogStash::ShutdownSignal
+      return
+    rescue Twitter::Error::TooManyRequests => e
+      @logger.warn("Twitter too many requests error, sleeping for #{e.rate_limit.reset_in}s")
+      sleep(e.rate_limit.reset_in)
+      retry
+    rescue => e
+      @logger.warn("Twitter client error", :message => e.message, :exception => e, :backtrace => e.backtrace)
+      retry
+    end
+  end # def run
+end # class LogStash::Inputs::Twitter

data/logstash-input-twitter.gemspec

@@ -0,0 +1,28 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-input-twitter'
+  s.version         = '0.1.0'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "Read events from the twitter streaming api."
+  s.description     = "Read events from the twitter streaming api."
+  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 'twitter', ['5.12.0']
+
+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/twitter_spec.rb

@@ -0,0 +1,5 @@
+require 'spec_helper'
+require 'logstash/inputs/twitter'
+
+describe LogStash::Inputs::Twitter do
+end

metadata

@@ -0,0 +1,89 @@
+--- !ruby/object:Gem::Specification
+name: logstash-input-twitter
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Elasticsearch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-11-07 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: twitter
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 5.12.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 5.12.0
+description: Read events from the twitter streaming api.
+email: richard.pijnenburg@elasticsearch.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE
+- Rakefile
+- lib/logstash/inputs/twitter.rb
+- logstash-input-twitter.gemspec
+- rakelib/publish.rake
+- rakelib/vendor.rake
+- spec/inputs/twitter_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: Read events from the twitter streaming api.
+test_files:
+- spec/inputs/twitter_spec.rb