postgres_to_redshift 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 32377367b67f4405e131d319f810bbc38fbc2ac5
+  data.tar.gz: 97facb3cae58afb4c65b6cb8c17415e1e6e79f23
+SHA512:
+  metadata.gz: bb62207056a659dce0b1cc6ceac28ee92af14794510b7c59150e5fe61d19e7f4e4c79fa8a1601989dfba3b097b0e0702bac67b258058a93f57d5f1c1dffd959f
+  data.tar.gz: e8f4cffccd43dbd33748c49b24bd4a0dadc670077ac798b2d5533da7cb144faa8ee60829fdbd60fcd34549c2af70b63d40edb05b71f730af9108680420140bde

data/.gitignore

@@ -0,0 +1,15 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log
+*swp

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2015 Kitchensurfing
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,38 @@
+# PostgresToRedshift
+
+This gem copies data from postgres to redshift. It's especially useful to copy data from postgres to redshift in heroku.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'postgres_to_redshift'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install postgres_to_redshift
+
+## Usage
+
+```bash
+export REDSHIFT_URI='postgres://username:password@host:port/database-name'
+export S3_DATABASE_EXPORT_ID='yourid'
+export S3_DATABASE_EXPORT_KEY='yourkey'
+export S3_DATABASE_EXPORT_BUCKET='some-bucket-to-use'
+
+postgres_to_redshift $MY_SOURCE_DATABASE
+```
+
+## Contributing
+
+1. Fork it ( https://github.com/kitchensurfing/postgres_to_redshift/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+

data/bin/postgres_to_redshift

@@ -0,0 +1,6 @@
+#!/usr/bin/env ruby
+
+require 'postgres_to_redshift'
+
+PostgresToRedshift.update_tables
+

data/lib/postgres_to_redshift/version.rb

@@ -0,0 +1,3 @@
+class PostgresToRedshift
+  VERSION = "0.0.1"
+end

data/lib/postgres_to_redshift.rb

@@ -0,0 +1,123 @@
+require "postgres_to_redshift/version"
+require 'pg'
+require 'uri'
+require 'aws-sdk'
+
+class PostgresToRedshift
+  attr_reader :source_connection, :target_connection, :s3
+
+  def self.update_tables
+    update_tables = PostgresToRedshift.new(source_uri: ARGV[0])
+    update_tables.create_new_tables
+
+    # FIXME: BIG WARNING HERE: this order is important. We want the views to overwrite the tables. We should make it so the order doesn't matter later.
+    update_tables.copy_tables
+    update_tables.copy_views
+    update_tables.import_tables
+  end
+
+  def initialize(source_uri:)
+    source_uri = URI.parse(source_uri)
+    target_uri = URI.parse(ENV['REDSHIFT_URI'])
+    @source_connection = PG::Connection.new(host: source_uri.host, port: source_uri.port, user: source_uri.user, password: source_uri.password, dbname: source_uri.path[1..-1])
+    @source_connection.exec("SET SESSION CHARACTERISTICS AS TRANSACTION READ ONLY;")
+    @target_connection = PG::Connection.new(host: target_uri.host, port: target_uri.port, user: target_uri.user, password: target_uri.password, dbname: target_uri.path[1..-1])
+  end
+
+  def views
+    source_connection.exec("SELECT table_name FROM information_schema.tables WHERE table_schema = 'public' AND table_type = 'VIEW'").map { |row| row["table_name"] } - ["pg_stat_statements"]
+  end
+
+  def tables
+    source_connection.exec("SELECT table_name FROM information_schema.tables WHERE table_schema = 'public' AND table_type = 'BASE TABLE'").map { |row| row["table_name"] }
+  end
+
+  def table_columns(table_name)
+    source_connection.exec("SELECT column_name, data_type, character_maximum_length FROM information_schema.columns WHERE table_schema='public' AND table_name='#{table_name}'").map do |row| 
+      data_type = row["data_type"]
+      data_type.gsub!(/text/, 'character varying(max)')
+      data_type.gsub!(/json/, 'character varying(max)')
+      data_type.gsub!(/bytea/, 'character varying(max)')
+      data_type.gsub!(/money/, 'character varying(max)')
+
+      if row["character_maximum_length"].to_s.length > 0
+        %Q|"#{row["column_name"]}" #{data_type}(#{row["character_maximum_length"]})|
+      else
+        %Q|"#{row["column_name"]}" #{data_type}|
+      end
+    end.join(", ")
+  end
+
+  def s3
+    @s3 ||= AWS::S3.new(access_key_id: ENV['S3_DATABASE_EXPORT_ID'], secret_access_key: ENV['S3_DATABASE_EXPORT_KEY'])
+  end
+
+  def bucket
+    @bucket ||= s3.buckets[ENV['S3_DATABASE_EXPORT_BUCKET']]
+  end
+
+  def create_new_tables
+    tables.each do |table|
+      target_connection.exec("CREATE TABLE IF NOT EXISTS public.#{table} (#{table_columns(table)})")
+    end
+  end
+
+  def copy_table(source_table, target_table, is_view = false)
+    buffer = ""
+    puts "Downloading #{source_table}"
+    copy_command = 
+      if is_view
+        "COPY (SELECT * FROM #{source_table}) TO STDOUT WITH DELIMITER '|'"
+      else
+        "COPY #{source_table} TO STDOUT WITH DELIMITER '|'"
+      end
+
+    source_connection.copy_data(copy_command) do
+      while row = source_connection.get_copy_data
+        buffer << row
+      end
+    end
+    upload_table(target_table, buffer)
+  end
+
+  def upload_table(target_table, buffer)
+    puts "Uploading #{target_table}"
+    bucket.objects["export/#{target_table}.psv"].delete
+    bucket.objects["export/#{target_table}.psv"].write(buffer, acl: :authenticated_read)
+  end
+
+  def import_table(target_table)
+    puts "Importing #{target_table}"
+    target_connection.exec("DROP TABLE IF EXISTS public.#{target_table}_updating")
+
+    target_connection.exec("BEGIN;")
+
+    target_connection.exec("ALTER TABLE public.#{target_table} RENAME TO #{target_table}_updating")
+
+    target_connection.exec("CREATE TABLE public.#{target_table} (#{table_columns(target_table)})")
+
+    target_connection.exec("COPY public.#{target_table} FROM 's3://#{ENV['S3_DATABASE_EXPORT_BUCKET']}/export/#{target_table}.psv' CREDENTIALS 'aws_access_key_id=#{ENV['S3_DATABASE_EXPORT_ID']};aws_secret_access_key=#{ENV['S3_DATABASE_EXPORT_KEY']}' TRUNCATECOLUMNS ESCAPE DELIMITER as '|';")
+
+    target_connection.exec("COMMIT;")
+  end
+
+  def copy_tables
+    tables.each do |table|
+      copy_table(table, table)
+    end
+  end
+
+  def copy_views
+    views.each do |view|
+      table = view.gsub(/_view/, '')
+      copy_table(view, table, true)
+    end
+  end
+
+  # FIXME: This relies on views being uploaded after tables.
+  def import_tables
+    tables.each do |table|
+      import_table(table)
+    end
+  end
+end

data/postgres_to_redshift.gemspec

@@ -0,0 +1,25 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'postgres_to_redshift/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "postgres_to_redshift"
+  spec.version       = PostgresToRedshift::VERSION
+  spec.authors       = ["Alex Rakoczy"]
+  spec.email         = ["arakoczy@gmail.com"]
+  spec.summary       = %q{Load postgres databases into Amazon Redshift}
+  spec.description   = %q{Load postgres databases into Amazon Redshift. It's designed to work on Heroku Scheduler, or other *nix/BSD hosts.}
+  spec.homepage      = "https://github.com/kitchensurfing/postgres_to_redshift"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.7"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_dependency "pg", "~> 0.17.0"
+  spec.add_dependency "aws-sdk", "~> 1.54"
+end

metadata

@@ -0,0 +1,111 @@
+--- !ruby/object:Gem::Specification
+name: postgres_to_redshift
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Alex Rakoczy
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-01-20 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.7'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: pg
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.17.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.17.0
+- !ruby/object:Gem::Dependency
+  name: aws-sdk
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.54'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.54'
+description: Load postgres databases into Amazon Redshift. It's designed to work on
+  Heroku Scheduler, or other *nix/BSD hosts.
+email:
+- arakoczy@gmail.com
+executables:
+- postgres_to_redshift
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/postgres_to_redshift
+- lib/postgres_to_redshift.rb
+- lib/postgres_to_redshift/version.rb
+- postgres_to_redshift.gemspec
+homepage: https://github.com/kitchensurfing/postgres_to_redshift
+licenses:
+- MIT
+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
+signing_key: 
+specification_version: 4
+summary: Load postgres databases into Amazon Redshift
+test_files: []