fluent-plugin-postgres-replicator 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 3ca7d5dc0cc16563d50a913c50da4d89f130ceb3
+  data.tar.gz: a12eaccf0624403b32359673935b6614ed367363
+SHA512:
+  metadata.gz: c5d817d1e75134379f26443e0106b28a1afc2e03de7b94467cc8a21660169365a6295da941e6bad9cf25373e066acfd3ec7628ce09c13a4c1d1f3fe749fd846e
+  data.tar.gz: 13db91bfb686ed5eeec844d50a68eb55f72f7e82495223191f27b2d2f9ee2b92e65ac7bcaeaf3923f20b65f9416069a69eaf825c77677c8840e6ad869c0c6b4d

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.travis.yml

@@ -0,0 +1,4 @@
+language: ruby
+rvm:
+  - 2.2.3
+before_install: gem install bundler -v 1.10.6

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in fluent-plugin-postgres-replicator.gemspec
+gemspec

data/README.md

@@ -0,0 +1,40 @@
+# Fluent::Plugin::Postgres::Replicator
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/fluent/plugin/postgres/replicator`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'fluent-plugin-postgres-replicator'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install fluent-plugin-postgres-replicator
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake false` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome.
+
+## License
+
+- Copyright (c) 2015 innossh
+- [Apache License, Version 2.0](http://www.apache.org/licenses/LICENSE-2.0)

data/Rakefile

@@ -0,0 +1,9 @@
+require 'bundler/gem_tasks'
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+task :default => :test

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "fluent/plugin/postgres/replicator"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/fluent-plugin-postgres-replicator.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+
+Gem::Specification.new do |gem|
+  gem.name          = "fluent-plugin-postgres-replicator"
+  gem.version       = "0.0.1"
+  gem.authors       = ["innossh"]
+  gem.email         = ["innossh@users.noreply.github.com"]
+
+  gem.summary       = %q{PostgreSQL replication input plugin for Fluent}
+  gem.homepage      = "https://github.com/innossh/fluent-plugin-postgres-replicator"
+  gem.license       = "Apache-2.0"
+
+  gem.files         = `git ls-files -z`.split("\x0")
+  gem.executables   = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+  gem.require_paths = ["lib"]
+
+  gem.add_runtime_dependency "fluentd"
+  gem.add_runtime_dependency "pg"
+  gem.add_development_dependency "rake"
+  gem.add_development_dependency "test-unit"
+end

data/lib/fluent/plugin/in_postgres_replicator.rb

@@ -0,0 +1,124 @@
+class Fluent::PostgresReplicatorInput < Fluent::Input
+  Fluent::Plugin.register_input('postgres_replicator', self)
+
+  config_param :host, :string, :default => 'localhost'
+  config_param :port, :integer, :default => 5432
+  config_param :username, :string, :default => 'root'
+  config_param :password, :string, :default => nil, :secret => true
+  config_param :database, :string, :default => nil
+  config_param :query, :string, :default => nil
+  config_param :primary_keys, :string, :default => nil
+  config_param :interval, :string, :default => '10s'
+  config_param :tag, :string, :default => nil
+
+  def initialize
+    super
+    require 'pg'
+    require 'digest/sha1'
+  end
+
+  def configure(conf)
+    super
+    @interval = Fluent::Config.time_value(@interval)
+    if @primary_keys.nil?
+      raise Fluent::ConfigError, "primary_keys MUST be specified"
+    end
+    if @tag.nil?
+      raise Fluent::ConfigError, "tag MUST be specified"
+    end
+    @primary_keys = @primary_keys.split(',')
+  end
+
+  def start
+    @thread = Thread.new(&method(:run))
+  end
+
+  def shutdown
+    Thread.kill(@thread)
+  end
+
+  def run
+    begin
+      poll
+    rescue StandardError => e
+      $log.error "failed to execute query. error: #{e.message}"
+      $log.error e.backtrace.join("\n")
+    end
+  end
+
+  def poll
+    hash_values = Hash.new
+    conn = get_connection()
+    loop do
+      rows_count = 0
+      start_time = Time.now
+      rows, conn = query(@query, conn)
+      rows.each do |row|
+        row_ids = Array.new
+        @primary_keys.each do |primary_key|
+          if row[primary_key].nil?
+            $log.error "primary_key value is not found. :tag=>#{@tag} :primary_key=>#{primary_key}"
+            break
+          end
+          row_ids << row[primary_key]
+        end
+
+        hash_value_id = row_ids.join('_')
+        hash_value = Digest::SHA1.hexdigest(row.flatten.join)
+        if !hash_values.include?(hash_value_id)
+          tag = format_tag(@tag, {:event => :insert})
+          emit_record(tag, row)
+        elsif hash_values[hash_value_id] != hash_value
+          tag = format_tag(@tag, {:event => :update})
+          emit_record(tag, row)
+        end
+        hash_values[hash_value_id] = hash_value
+        rows_count += 1
+      end
+      conn.close
+      elapsed_time = sprintf('%0.02f', Time.now - start_time)
+      $log.info "success to execute replicator. :tag=>#{@tag} :rows_count=>#{rows_count} :elapsed_time=>#{elapsed_time} sec"
+      sleep @interval
+    end
+
+  end
+
+  def query(query, conn = nil)
+    begin
+      conn = (conn.nil? || conn.finished?) ? get_connection : conn
+      return conn.query(query), conn
+    rescue Exception => e
+      $log.warn "failed to execute query and will retry. error: #{e}"
+      sleep @interval
+      retry
+    end
+  end
+
+  def format_tag(tag, param)
+    pattern = {'${event}' => param[:event].to_s, '${primary_keys}' => @primary_keys.join('_')}
+    tag.gsub(/(\${[a-z_]+})/) do
+      $log.warn "placeholder value is not found. :tag=>#{tag} :placeholder=>#{$1}" unless pattern.include?($1)
+      pattern[$1]
+    end
+  end
+
+  def emit_record(tag, record)
+    router.emit(tag, Fluent::Engine.now, record)
+  end
+
+  def get_connection
+    begin
+      return PG::Connection.new({
+        :host => @host,
+        :port => @port,
+        :user => @username,
+        :password => @password,
+        :dbname => @database
+      })
+    rescue Exception => e
+      $log.warn "failed to get connection and will retry. error: #{e}"
+      sleep @interval
+      retry
+    end
+  end
+end

data/test/plugin/test_in_postgres_replicator.rb

@@ -0,0 +1,33 @@
+require 'test/unit'
+require 'fluent/test'
+require 'fluent/plugin/in_postgres_replicator'
+
+class PostgresReplicatorTest < Test::Unit::TestCase
+  def setup
+    Fluent::Test.setup
+  end
+
+  CONFIG = %[
+    host 127.0.0.1
+    port 5432
+    primary_keys id
+    tag pgreplicator.db.table.${event}.${primary_keys}
+  ]
+
+  def create_driver(conf = CONFIG)
+    Fluent::Test::InputTestDriver.new(Fluent::PostgresReplicatorInput).configure(conf)
+  end
+
+  def test_configure
+    assert_raise(Fluent::ConfigError) {
+      create_driver('')
+    }
+
+    d = create_driver
+    assert_equal '127.0.0.1', d.instance.host
+    assert_equal 5432, d.instance.port
+    assert_equal [ 'id' ], d.instance.primary_keys
+    assert_equal 'pgreplicator.db.table.${event}.${primary_keys}', d.instance.tag
+  end
+
+end

metadata

@@ -0,0 +1,113 @@
+--- !ruby/object:Gem::Specification
+name: fluent-plugin-postgres-replicator
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- innossh
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-01-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: fluentd
+  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: pg
+  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: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: test-unit
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: 
+email:
+- innossh@users.noreply.github.com
+executables:
+- console
+- setup
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".travis.yml"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- fluent-plugin-postgres-replicator.gemspec
+- lib/fluent/plugin/in_postgres_replicator.rb
+- test/plugin/test_in_postgres_replicator.rb
+homepage: https://github.com/innossh/fluent-plugin-postgres-replicator
+licenses:
+- Apache-2.0
+metadata: {}
+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: 2.4.5.1
+signing_key: 
+specification_version: 4
+summary: PostgreSQL replication input plugin for Fluent
+test_files:
+- test/plugin/test_in_postgres_replicator.rb