logstash-filter-csv 0.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    OTY1ZjIyMmUwNDhkYjk2NmMyYTM0NDA2Mzc5ZDJhMDczM2ZiNTBkZQ==
+  data.tar.gz: !binary |-
+    OTgyOGNiMGU4ZjcxNjUzZGQxNGNiYmQwZDQ5YWRjODIxNzM2N2NkZA==
+SHA512:
+  metadata.gz: !binary |-
+    YjhhNzg3YmViMjFiOWQ0OTE5NmI5MWViOTUxMDE0MWE3MTBlNWEwMmY1NjBi
+    NzU1MWNjOGQ4NWJjNDNiMDUzZTkyOWUyYTZmZmUwNjY5MzFiYzliZjc1OGNl
+    MmU2MDUwMDhlYmM4NWQ4MGRmZTdlZmEzNzMzZWRhYzZlMTA4MjE=
+  data.tar.gz: !binary |-
+    OGFlNWM4NWNkZWE1MzUxY2QxMjQ0YmM0NWQzNDVmMjhlMTBmOTgwOWVmNjkx
+    OGRkMmViN2ViZmYzODM5NThkZDBjNWFmYTU1MmY1ZjJkMzVmOTI3MmYwYmQ2
+    N2ExNGQ1ZTE2ODM5MTAzYWU3YWE5NDViZWM5NmQ2MDQ0MTExMDA=

data/.gitignore

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

data/Gemfile

@@ -0,0 +1,3 @@
+source 'http://rubygems.org'
+gem 'rake'
+gem 'gem_publisher'

data/Rakefile

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

data/lib/logstash/filters/csv.rb

@@ -0,0 +1,97 @@
+# encoding: utf-8
+require "logstash/filters/base"
+require "logstash/namespace"
+
+require "csv"
+
+# The CSV filter takes an event field containing CSV data, parses it,
+# and stores it as individual fields (can optionally specify the names).
+# This filter can also parse data with any separator, not just commas.
+class LogStash::Filters::CSV < LogStash::Filters::Base
+  config_name "csv"
+  milestone 2
+
+  # The CSV data in the value of the `source` field will be expanded into a
+  # data structure.
+  config :source, :validate => :string, :default => "message"
+
+  # Define a list of column names (in the order they appear in the CSV,
+  # as if it were a header line). If `columns` is not configured, or there
+  # are not enough columns specified, the default column names are
+  # "column1", "column2", etc. In the case that there are more columns
+  # in the data than specified in this column list, extra columns will be auto-numbered:
+  # (e.g. "user_defined_1", "user_defined_2", "column3", "column4", etc.)
+  config :columns, :validate => :array, :default => []
+
+  # Define the column separator value. If this is not specified, the default
+  # is a comma ','.
+  # Optional.
+  config :separator, :validate => :string, :default => ","
+
+  # Define the character used to quote CSV fields. If this is not specified
+  # the default is a double quote '"'.
+  # Optional.
+  config :quote_char, :validate => :string, :default => '"'
+
+  # Define target field for placing the data.
+  # Defaults to writing to the root of the event.
+  config :target, :validate => :string
+
+  public
+  def register
+
+    # Nothing to do here
+
+  end # def register
+
+  public
+  def filter(event)
+    return unless filter?(event)
+
+    @logger.debug("Running csv filter", :event => event)
+
+    matches = 0
+
+    if event[@source]
+      if event[@source].is_a?(String)
+        event[@source] = [event[@source]]
+      end
+
+      if event[@source].length > 1
+        @logger.warn("csv filter only works on fields of length 1",
+                     :source => @source, :value => event[@source],
+                     :event => event)
+        return
+      end
+
+      raw = event[@source].first
+      begin
+        values = CSV.parse_line(raw, :col_sep => @separator, :quote_char => @quote_char)
+
+        if @target.nil?
+          # Default is to write to the root of the event.
+          dest = event
+        else
+          dest = event[@target] ||= {}
+        end
+
+        values.each_index do |i|
+          field_name = @columns[i] || "column#{i+1}"
+          dest[field_name] = values[i]
+        end
+
+        filter_matched(event)
+      rescue => e
+        event.tag "_csvparsefailure"
+        @logger.warn("Trouble parsing csv", :source => @source, :raw => raw,
+                      :exception => e)
+        return
+      end # begin
+    end # if event
+
+    @logger.debug("Event after csv filter", :event => event)
+
+  end # def filter
+
+end # class LogStash::Filters::Csv
+

data/logstash-filter-csv.gemspec

@@ -0,0 +1,26 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-filter-csv'
+  s.version         = '0.1.0'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "The CSV filter takes an event field containing CSV data, parses it, and stores it as individual fields (can optionally specify the names)."
+  s.description     = "The CSV filter takes an event field containing CSV data, parses it, and stores it as individual fields (can optionally specify the names)."
+  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" => "filter" }
+
+  # Gem dependencies
+  s.add_runtime_dependency 'logstash', '>= 1.4.0', '< 2.0.0'
+
+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/filters/csv_spec.rb

@@ -0,0 +1,175 @@
+# encoding: utf-8
+
+require "spec_helper"
+require "logstash/filters/csv"
+
+describe LogStash::Filters::CSV do
+
+  describe "all defaults" do
+    # The logstash config goes here.
+    # At this time, only filters are supported.
+    config <<-CONFIG
+      filter {
+        csv { }
+      }
+    CONFIG
+
+    sample "big,bird,sesame street" do
+      insist { subject["column1"] } == "big"
+      insist { subject["column2"] } == "bird"
+      insist { subject["column3"] } == "sesame street"
+    end
+  end
+
+  describe "custom separator" do
+    config <<-CONFIG
+      filter {
+        csv {
+          separator => ";"
+        }
+      }
+    CONFIG
+
+    sample "big,bird;sesame street" do
+      insist { subject["column1"] } == "big,bird"
+      insist { subject["column2"] } == "sesame street"
+    end
+  end
+
+  describe "custom quote char" do
+    config <<-CONFIG
+      filter {
+        csv {
+          quote_char => "'"
+        }
+      }
+    CONFIG
+
+    sample "big,bird,'sesame street'" do
+      insist { subject["column1"] } == "big"
+      insist { subject["column2"] } == "bird"
+      insist { subject["column3"] } == "sesame street"
+    end
+  end
+
+  describe "default quote char" do
+    config <<-CONFIG
+      filter {
+        csv {
+        }
+      }
+    CONFIG
+
+    sample 'big,bird,"sesame, street"' do
+      insist { subject["column1"] } == "big"
+      insist { subject["column2"] } == "bird"
+      insist { subject["column3"] } == "sesame, street"
+    end
+  end
+  describe "null quote char" do
+    config <<-CONFIG
+      filter {
+        csv {
+          quote_char => "\x00"
+        }
+      }
+    CONFIG
+
+    sample 'big,bird,"sesame" street' do
+      insist { subject["column1"] } == 'big'
+      insist { subject["column2"] } == 'bird'
+      insist { subject["column3"] } == '"sesame" street'
+    end
+  end
+
+  describe "given columns" do
+    # The logstash config goes here.
+    # At this time, only filters are supported.
+    config <<-CONFIG
+      filter {
+        csv {
+          columns => ["first", "last", "address" ]
+        }
+      }
+    CONFIG
+
+    sample "big,bird,sesame street" do
+      insist { subject["first"] } == "big"
+      insist { subject["last"] } == "bird"
+      insist { subject["address"] } == "sesame street"
+    end
+  end
+
+  describe "parse csv with more data than defined column names" do
+    config <<-CONFIG
+      filter {
+        csv {
+          columns => ["custom1", "custom2"]
+        }
+      }
+    CONFIG
+
+    sample "val1,val2,val3" do
+      insist { subject["custom1"] } == "val1"
+      insist { subject["custom2"] } == "val2"
+      insist { subject["column3"] } == "val3"
+    end
+  end
+
+
+  describe "parse csv from a given source with column names" do
+    config <<-CONFIG
+      filter {
+        csv {
+          source => "datafield"
+          columns => ["custom1", "custom2", "custom3"]
+        }
+      }
+    CONFIG
+
+    sample("datafield" => "val1,val2,val3") do
+      insist { subject["custom1"] } == "val1"
+      insist { subject["custom2"] } == "val2"
+      insist { subject["custom3"] } == "val3"
+    end
+  end
+
+  describe "given target" do
+    # The logstash config goes here.
+    # At this time, only filters are supported.
+    config <<-CONFIG
+      filter {
+        csv {
+          target => "data"
+        }
+      }
+    CONFIG
+
+    sample "big,bird,sesame street" do
+      insist { subject["data"]["column1"] } == "big"
+      insist { subject["data"]["column2"] } == "bird"
+      insist { subject["data"]["column3"] } == "sesame street"
+    end
+  end
+
+  describe "given target and source" do
+    # The logstash config goes here.
+    # At this time, only filters are supported.
+    config <<-CONFIG
+      filter {
+        csv {
+          source => "datain"
+          target => "data"
+        }
+      }
+    CONFIG
+
+    sample("datain" => "big,bird,sesame street") do
+      insist { subject["data"]["column1"] } == "big"
+      insist { subject["data"]["column2"] } == "bird"
+      insist { subject["data"]["column3"] } == "sesame street"
+    end
+  end
+
+
+end

metadata

@@ -0,0 +1,76 @@
+--- !ruby/object:Gem::Specification
+name: logstash-filter-csv
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Elasticsearch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-11-02 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
+description: The CSV filter takes an event field containing CSV data, parses it, and
+  stores it as individual fields (can optionally specify the names).
+email: richard.pijnenburg@elasticsearch.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- lib/logstash/filters/csv.rb
+- logstash-filter-csv.gemspec
+- rakelib/publish.rake
+- rakelib/vendor.rake
+- spec/filters/csv_spec.rb
+homepage: http://logstash.net/
+licenses:
+- Apache License (2.0)
+metadata:
+  logstash_plugin: 'true'
+  group: filter
+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: The CSV filter takes an event field containing CSV data, parses it, and stores
+  it as individual fields (can optionally specify the names).
+test_files:
+- spec/filters/csv_spec.rb