logstash-filter-punct 0.1.0

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    MTUzN2Q4YjcyZDM5ZGM5Nzc1NmEzM2Y5YWU3NmVhOTNhNTg3ZjNlMQ==
+  data.tar.gz: !binary |-
+    Y2IzMzIyZGY1OTU4Y2M2MjI2YTY0Yzc2ZDhlZDUwMGVlNDZhZWU3Yw==
+SHA512:
+  metadata.gz: !binary |-
+    ZDQ0MWJhZmRlOTIzNTk0MDBkYWZlYWExNmVjNmVhMTk5OGFjZDlkYzBmYTM2
+    YWI0NzY3MzY5ZDc2MzMyM2U5MjU3MTg5MjVmNDlhOGVlYmViMmVmMzFlYmY1
+    NTZkMmRiMzQyZWNmOTU1ZGU0YTQyMDEyNDljOTViMmU0ZjNiOWE=
+  data.tar.gz: !binary |-
+    NWUwNjg1NTAzNjc0MzZlMDk2OWRjOTAzMDhlMjg2YmJjMGY5OGYxZmE1YWMz
+    MDA3ZDM2MjEzNzY0NDM5ZThjMzJiYTZlODU2NTgyNDQ3ZjJjNTNmNjA5MjJl
+    YzUwZGZhYmNiYmNmNzk0YWI3NWJlOGExNjI1MzliNjMwMDM5NjA=

data/.gitignore

@@ -0,0 +1,3 @@
+*.gem
+Gemfile.lock
+.bundle

data/Gemfile

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

data/Rakefile

@@ -0,0 +1,12 @@
+require "gem_publisher"
+
+desc "Publish gem to RubyGems.org"
+task :publish_gem do |t|
+  gem = GemPublisher.publish_if_updated("logstash-filter-punct.gemspec", :rubygems)
+  puts "Published #{gem}" if gem
+end
+
+task :default do
+  system("rake -T")
+end
+

data/lib/logstash/filters/punct.rb

@@ -0,0 +1,33 @@
+# encoding: utf-8
+require "logstash/filters/base"
+require "logstash/namespace"
+
+
+# Strip everything but punctuation from a field and store the remainder in the
+# a separate field. This is often used for fingerprinting log events.
+class LogStash::Filters::Punct < LogStash::Filters::Base
+  config_name "punct"
+  milestone 1
+
+  # The field reference to use for punctuation stripping
+  config :source, :validate => :string, :default => "message"
+
+  # The field to store the result.
+  config :target, :validate => :string, :default => "punct"
+
+  public
+  def register
+    # Nothing to do
+  end # def register
+
+  public
+  def filter(event)
+    return unless filter?(event)
+
+    original_value = event[@source]
+
+    # If for some reason the field is an array of values, take the first only.
+    original_value = original_value.first if original_value.is_a?(Array)
+    event[@target] = original_value.tr('A-Za-z0-9 \t','').force_encoding(Encoding::UTF_8)
+  end # def filter
+end # class LogStash::Filters::Punct

data/logstash-filter-punct.gemspec

@@ -0,0 +1,26 @@
+Gem::Specification.new do |s|
+
+  s.name            = 'logstash-filter-punct'
+  s.version         = '0.1.0'
+  s.licenses        = ['Apache License (2.0)']
+  s.summary         = "Strip everything but punctuation from a field and store the remainder in a separate field. This is often used for fingerprinting log events."
+  s.description     = "Strip everything but punctuation from a field and store the remainder in a separate field. This is often used for fingerprinting log events."
+  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($\)
+
+  # 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/spec/filters/punct.rb

@@ -0,0 +1,18 @@
+require "test_utils"
+require "logstash/filters/punct"
+
+describe LogStash::Filters::Punct do
+  extend LogStash::RSpec
+
+  describe "all defaults" do
+    config <<-CONFIG
+      filter {
+        punct { }
+      }
+    CONFIG
+
+    sample "PHP Warning:  json_encode() [<a href='function.json-encode'>function.json-encode</a>]: Invalid UTF-8 sequence in argument in /var/www/htdocs/test.php on line 233" do
+      insist { subject["punct"] } == ":_()[<='.-'>.-</>]:-////."
+    end
+  end
+end

metadata

@@ -0,0 +1,76 @@
+--- !ruby/object:Gem::Specification
+name: logstash-filter-punct
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Elasticsearch
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-09-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: logstash
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MS40LjA=
+    - - <
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: !binary |-
+          MS40LjA=
+    - - <
+      - !ruby/object:Gem::Version
+        version: 2.0.0
+description: Strip everything but punctuation from a field and store the remainder
+  in a separate field. This is often used for fingerprinting log events.
+email: richard.pijnenburg@elasticsearch.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Rakefile
+- lib/logstash/filters/punct.rb
+- logstash-filter-punct.gemspec
+- spec/filters/punct.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: Strip everything but punctuation from a field and store the remainder in
+  a separate field. This is often used for fingerprinting log events.
+test_files:
+- spec/filters/punct.rb