logstash-output-csv 0.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    MjYxNjRjYWVjNGZkMDg2YzdhMGZhNzQ4YzExMjA3OTEwNjVjZTlhNA==
+  data.tar.gz: !binary |-
+    ZjNmNjY0YjAyYjdmNTkwZjEyNjRiMWJjZTdiYzY1NTNkODE5NzUxMw==
+SHA512:
+  metadata.gz: !binary |-
+    YjM1MTgzMTQwZDRhNTk5YTU2YWM3NjQ5ZGI1YWVmMjU4Y2I0NjhkMmQwZjM5
+    Mjc1YWQxMTRkMTdhNWEzNjNlNzc1YmJlZjc4YWI4NWU2ZjM2OTRmMWEyMDhi
+    NWNiNzg2MjA0MDBkYzVhM2FlMWQ5OWJhMzU1YTQ0ZTczNjQ2NDU=
+  data.tar.gz: !binary |-
+    N2E1MjFhZTljOGRlOWZjYmQzYjQwZTU1OGFlMGE5NWYwZjgyZDdkNTUxYWVi
+    ZjM2MjA4NGIwMDVkMGFkYTcwZWY3MjdhMWY0Nzg4OTFkZWQ3NmU3NTIxOWE4
+    OTQ4OTgzYWM1YjM5NDZkZDJjZWYxZWU5NjIxN2I1Mjg3YjY5OWU=

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/outputs/csv.rb

@@ -0,0 +1,51 @@
+require "csv"
+require "logstash/namespace"
+require "logstash/outputs/file"
+require "logstash/json"
+
+# CSV output.
+#
+# Write events to disk in CSV or other delimited format
+# Based on the file output, many config values are shared
+# Uses the Ruby csv library internally
+class LogStash::Outputs::CSV < LogStash::Outputs::File
+
+  config_name "csv"
+  milestone 1
+
+  # The field names from the event that should be written to the CSV file.
+  # Fields are written to the CSV in the same order as the array.
+  # If a field does not exist on the event, an empty string will be written.
+  # Supports field reference syntax eg: `fields => ["field1", "[nested][field]"]`.
+  config :fields, :validate => :array, :required => true
+
+  # Options for CSV output. This is passed directly to the Ruby stdlib to_csv function.
+  # Full documentation is available on the http://ruby-doc.org/stdlib-2.0.0/libdoc/csv/rdoc/index.html[Ruby CSV documentation page].
+  # A typical use case would be to use alternative column or row seperators eg: `csv_options => {"col_sep" => "\t" "row_sep" => "\r\n"}` gives tab seperated data with windows line endings
+  config :csv_options, :validate => :hash, :required => false, :default => Hash.new
+
+  public
+  def register
+    super
+    @csv_options = Hash[@csv_options.map{|(k, v)|[k.to_sym, v]}]
+  end
+
+  public
+  def receive(event)
+    return unless output?(event)
+    path = event.sprintf(@path)
+    fd = open(path)
+    csv_values = @fields.map {|name| get_value(name, event)}
+    fd.write(csv_values.to_csv(@csv_options))
+
+    flush(fd)
+    close_stale_files
+  end #def receive
+
+  private
+  def get_value(name, event)
+    val = event[name]
+    val.is_a?(Hash) ? LogStash::Json.dump(val) : val
+  end
+end # class LogStash::Outputs::CSV
+

data/logstash-output-csv.gemspec

@@ -0,0 +1,28 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-output-csv'
+  s.version         = '0.1.0'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "Write events to disk in CSV or other delimited format"
+  s.description     = "Write events to disk in CSV or other delimited format"
+  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" => "output" }
+
+  # Gem dependencies
+  s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
+
+  s.add_runtime_dependency 'logstash-output-file'
+  s.add_runtime_dependency 'logstash-filter-json'
+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/outputs/csv_spec.rb

@@ -0,0 +1,266 @@
+require "csv"
+require "tempfile"
+require "spec_helper"
+require "logstash/outputs/csv"
+
+describe LogStash::Outputs::CSV do
+  
+
+  describe "Write a single field to a csv file" do
+    tmpfile = Tempfile.new('logstash-spec-output-csv')
+    config <<-CONFIG
+      input {
+        generator {
+          add_field => ["foo","bar"]
+          count => 1
+        }
+      }
+      output {
+        csv {
+          path => "#{tmpfile.path}"
+          fields => "foo"
+        }
+      }
+    CONFIG
+
+    agent do
+      lines = File.readlines(tmpfile.path)
+      insist {lines.count} == 1
+      insist {lines[0]} == "bar\n"
+    end
+  end
+
+  describe "write multiple fields and lines to a csv file" do
+    tmpfile = Tempfile.new('logstash-spec-output-csv')
+    config <<-CONFIG
+      input {
+        generator {
+          add_field => ["foo", "bar", "baz", "quux"]
+          count => 2
+        }
+      }
+      output {
+        csv {
+          path => "#{tmpfile.path}"
+          fields => ["foo", "baz"]
+        }
+      }
+    CONFIG
+
+    agent do
+      lines = File.readlines(tmpfile.path)
+      insist {lines.count} == 2
+      insist {lines[0]} == "bar,quux\n"
+      insist {lines[1]} == "bar,quux\n"
+    end
+  end
+
+  describe "missing event fields are empty in csv" do
+    tmpfile = Tempfile.new('logstash-spec-output-csv')
+    config <<-CONFIG
+      input {
+        generator {
+          add_field => ["foo","bar", "baz", "quux"]
+          count => 1
+        }
+      }
+      output {
+        csv {
+          path => "#{tmpfile.path}"
+          fields => ["foo", "not_there", "baz"]
+        }
+      }
+    CONFIG
+
+    agent do
+      lines = File.readlines(tmpfile.path)
+      insist {lines.count} == 1
+      insist {lines[0]} == "bar,,quux\n"
+    end
+  end
+
+  describe "commas are quoted properly" do
+    tmpfile = Tempfile.new('logstash-spec-output-csv')
+    config <<-CONFIG
+      input {
+        generator {
+          add_field => ["foo","one,two", "baz", "quux"]
+          count => 1
+        }
+      }
+      output {
+        csv {
+          path => "#{tmpfile.path}"
+          fields => ["foo", "baz"]
+        }
+      }
+    CONFIG
+
+    agent do
+      lines = File.readlines(tmpfile.path)
+      insist {lines.count} == 1
+      insist {lines[0]} == "\"one,two\",quux\n"
+    end
+  end
+
+  describe "new lines are quoted properly" do
+    tmpfile = Tempfile.new('logstash-spec-output-csv')
+    config <<-CONFIG
+      input {
+        generator {
+          add_field => ["foo","one\ntwo", "baz", "quux"]
+          count => 1
+        }
+      }
+      output {
+        csv {
+          path => "#{tmpfile.path}"
+          fields => ["foo", "baz"]
+        }
+      }
+    CONFIG
+
+    agent do
+      lines = CSV.read(tmpfile.path)
+      insist {lines.count} == 1
+      insist {lines[0][0]} == "one\ntwo"
+    end
+  end
+
+  describe "fields that are are objects are written as JSON" do
+    tmpfile = Tempfile.new('logstash-spec-output-csv')
+    config <<-CONFIG
+      input {
+        generator {
+          message => '{"foo":{"one":"two"},"baz": "quux"}'
+          count => 1
+        }
+      }
+      filter {
+        json { source => "message"}
+      }
+      output {
+        csv {
+          path => "#{tmpfile.path}"
+          fields => ["foo", "baz"]
+        }
+      }
+    CONFIG
+
+    agent do
+      lines = CSV.read(tmpfile.path)
+      insist {lines.count} == 1
+      insist {lines[0][0]} == '{"one":"two"}'
+    end
+  end
+
+  describe "can address nested field using field reference syntax" do
+    tmpfile = Tempfile.new('logstash-spec-output-csv')
+    config <<-CONFIG
+      input {
+        generator {
+          message => '{"foo":{"one":"two"},"baz": "quux"}'
+          count => 1
+        }
+      }
+      filter {
+        json { source => "message"}
+      }
+      output {
+        csv {
+          path => "#{tmpfile.path}"
+          fields => ["[foo][one]", "baz"]
+        }
+      }
+    CONFIG
+
+    agent do
+      lines = CSV.read(tmpfile.path)
+      insist {lines.count} == 1
+      insist {lines[0][0]} == "two"
+      insist {lines[0][1]} == "quux"
+    end
+  end
+
+  describe "missing nested field is blank" do
+    tmpfile = Tempfile.new('logstash-spec-output-csv')
+    config <<-CONFIG
+      input {
+        generator {
+          message => '{"foo":{"one":"two"},"baz": "quux"}'
+          count => 1
+        }
+      }
+      filter {
+        json { source => "message"}
+      }
+      output {
+        csv {
+          path => "#{tmpfile.path}"
+          fields => ["[foo][missing]", "baz"]
+        }
+      }
+    CONFIG
+
+    agent do
+      lines = File.readlines(tmpfile.path)
+      insist {lines.count} == 1
+      insist {lines[0]} == ",quux\n"
+    end
+  end
+
+  describe "can choose field seperator" do
+    tmpfile = Tempfile.new('logstash-spec-output-csv')
+    config <<-CONFIG
+      input {
+        generator {
+          message => '{"foo":"one","bar": "two"}'
+          count => 1
+        }
+      }
+      filter {
+        json { source => "message"}
+      }
+      output {
+        csv {
+          path => "#{tmpfile.path}"
+          fields => ["foo", "bar"]
+          csv_options => {"col_sep" => "|"}
+        }
+      }
+    CONFIG
+
+    agent do
+      lines = File.readlines(tmpfile.path)
+      insist {lines.count} == 1
+      insist {lines[0]} == "one|two\n"
+    end
+  end
+  describe "can choose line seperator" do
+    tmpfile = Tempfile.new('logstash-spec-output-csv')
+    config <<-CONFIG
+      input {
+        generator {
+          message => '{"foo":"one","bar": "two"}'
+          count => 2
+        }
+      }
+      filter {
+        json { source => "message"}
+      }
+      output {
+        csv {
+          path => "#{tmpfile.path}"
+          fields => ["foo", "bar"]
+          csv_options => {"col_sep" => "|" "row_sep" => "\t"}
+        }
+      }
+    CONFIG
+
+    agent do
+      lines = File.readlines(tmpfile.path)
+      insist {lines.count} == 1
+      insist {lines[0]} == "one|two\tone|two\t"
+    end
+  end
+end

metadata

@@ -0,0 +1,103 @@
+--- !ruby/object:Gem::Specification
+name: logstash-output-csv
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Elasticsearch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-11-10 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-output-file
+  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: logstash-filter-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'
+description: Write events to disk in CSV or other delimited format
+email: richard.pijnenburg@elasticsearch.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE
+- Rakefile
+- lib/logstash/outputs/csv.rb
+- logstash-output-csv.gemspec
+- rakelib/publish.rake
+- rakelib/vendor.rake
+- spec/outputs/csv_spec.rb
+homepage: http://logstash.net/
+licenses:
+- Apache License (2.0)
+metadata:
+  logstash_plugin: 'true'
+  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: 2.4.1
+signing_key: 
+specification_version: 4
+summary: Write events to disk in CSV or other delimited format
+test_files:
+- spec/outputs/csv_spec.rb