kinesis-aggregation 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 821942e8c524497425129ef5635c5ed100eb242633f3c7fb23cd50c532d0420c
+  data.tar.gz: e87ba1b471301ecf3af12d0560541ac492fc812355993c9dde6d6fd8e9bd017f
+SHA512:
+  metadata.gz: f400c84e734a0fae10df8b3605ba33b65ddd34d1c793a350119662588dc24dc1d1ad2beebc7b38e670fa6ac090bd05b65eee929c5f9306f25857f27c7e2e617f
+  data.tar.gz: 467f392079b81abd6e5269c25ab075bdd29e7a6a3e473fa6a4ecba1f7158b88ab9eebb1039dff6d52dbcaa0c9ef72cfb0b3d2b612cdc23394980aea8ef514a6e

data/.gitignore

@@ -0,0 +1,12 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/spec/examples.txt
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.travis.yml

@@ -0,0 +1,6 @@
+---
+language: ruby
+cache: bundler
+rvm:
+  - 2.7.1
+before_install: gem install bundler -v 2.1.4

data/Gemfile

@@ -0,0 +1,7 @@
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in kinesis-aggregation.gemspec
+gemspec
+
+gem "rake", "~> 12.0"
+gem "rspec", "~> 3.0"

data/Gemfile.lock

@@ -0,0 +1,49 @@
+PATH
+  remote: .
+  specs:
+    kinesis-aggregation (0.1.0)
+      activesupport (>= 4.0)
+      google-protobuf (~> 3.13)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    activesupport (4.2.11.3)
+      i18n (~> 0.7)
+      minitest (~> 5.1)
+      thread_safe (~> 0.3, >= 0.3.4)
+      tzinfo (~> 1.1)
+    concurrent-ruby (1.1.7)
+    diff-lcs (1.4.4)
+    google-protobuf (3.13.0)
+    i18n (0.9.5)
+      concurrent-ruby (~> 1.0)
+    minitest (5.14.2)
+    rake (12.3.3)
+    rspec (3.9.0)
+      rspec-core (~> 3.9.0)
+      rspec-expectations (~> 3.9.0)
+      rspec-mocks (~> 3.9.0)
+    rspec-core (3.9.3)
+      rspec-support (~> 3.9.3)
+    rspec-expectations (3.9.2)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.9.0)
+    rspec-mocks (3.9.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.9.0)
+    rspec-support (3.9.3)
+    thread_safe (0.3.6)
+    tzinfo (1.2.8)
+      thread_safe (~> 0.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  kinesis-aggregation!
+  rake (~> 12.0)
+  rspec (~> 3.0)
+
+BUNDLED WITH
+   2.1.4

data/README.md

@@ -0,0 +1,76 @@
+# Kinesis::Aggregation
+
+This gem knows how to read and write kinesis aggregated messages.  This is most useful when writing a ruby lambda that consumes kinesis aggregated messages.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'kinesis-aggregation'
+```
+
+And then execute:
+
+    $ bundle install
+
+Or install it yourself as:
+
+    $ gem install kinesis-aggregation
+
+## Usage
+
+### Aggregation
+
+```ruby
+aggregator = Kinesis::Aggregation::Aggregator.new
+
+# explicit_hash_key is optional
+aggregator.add_user_record(partition_key: 'fc03dd88-3e79-448a-b01a-7cf1bd47b784',
+                           explicit_hash_key: '38486495867508399078159723846051807020',
+                           data: "RECORD 22 peeobhczbzdmskboupgyq\n")
+
+aggregator.add_user_record(partition_key: 'cae41b1c-ea61-43f2-90be-b8755ebf88e2',
+                           explicit_hash_key: '193787600037681706952143357071916352604',
+                           data: "RECORD 23 uswkxftxroeusscxsjhno\n")
+
+aggregator.add_user_record(partition_key: 'd490690c-e74d-4db2-a3c8-d8f2f184fd23',
+                           explicit_hash_key: '266880436964932424265466916734068684439',
+                           data: "RECORD 24 casehdgivfaxeustlyszy\n")
+
+aggregator.add_user_record(partition_key: 'c924bc09-b85e-47f1-b32e-336522ee53c8',
+                           explicit_hash_key: '339606600942967391854603552402021847292',
+                           data: "RECORD 25 nvffvpmuogdopjhamevrk\n")
+aggregated_record = aggregator.aggregate!
+```
+
+### Deaggregatoin
+
+```ruby
+deaggregated_records = Kinesis::Aggregation::Deaggregator.new(aggregated_record).deaggregate
+```
+
+### Use from within a lambda
+
+```ruby
+require 'kinesis/aggregation'
+
+def handler(event:, context:)
+  event['Records'].each do |aggregated_record|
+    records = Kinesis::Aggregation::Deaggregator.new(aggregated_record).deaggregate
+
+    # interesting code goes here
+  end
+end
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` 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 on GitHub at https://github.com/hawknewton/ruby-kinesis-aggregation.
+

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "kinesis/aggregation"
+
+# 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(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/kinesis-aggregation.gemspec

@@ -0,0 +1,29 @@
+require_relative 'lib/kinesis/aggregation/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'kinesis-aggregation'
+  spec.version       = Kinesis::Aggregation::VERSION
+  spec.authors       = ['hawknewton']
+  spec.email         = ['hawk.newton@gmail.com']
+
+  spec.summary       = %q{Read and write AWS KPL aggregate messages}
+  spec.description   = %q{Read and write AWS KPL aggregate messages}
+  spec.homepage      = 'https://github.com/hawknewton/ruby-kinesis-aggregation'
+  spec.licenses      = ['Apache-2.0']
+  spec.required_ruby_version = Gem::Requirement.new('>= 2.3.0')
+
+  spec.metadata['homepage_uri'] = spec.homepage
+  spec.metadata['source_code_uri'] = 'https://github.com/hawknewton/ruby-kinesis-aggregation'
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_dependency('google-protobuf', '~> 3.13')
+  spec.add_dependency('activesupport', '>= 4.0')
+end

data/kpl.proto

@@ -0,0 +1,17 @@
+message AggregatedRecord {
+  repeated string partition_key_table     = 1;
+  repeated string explicit_hash_key_table = 2;
+  repeated Record records                 = 3;
+}
+
+message Tag {
+  required string key   = 1;
+  optional string value = 2;
+}
+
+message Record {
+  required uint64 partition_key_index     = 1;
+  optional uint64 explicit_hash_key_index = 2;
+  required bytes  data                    = 3;
+  repeated Tag    tags                    = 4;
+}

data/lib/kinesis/aggregation.rb

@@ -0,0 +1,12 @@
+require "kinesis/aggregation/version"
+require 'kinesis/aggregation/deaggregator'
+require 'kinesis/aggregation/aggregator'
+require 'kinesis/aggregation/kpl_pb'
+require 'kinesis/aggregation/kinesis_analytics_converter'
+
+module Kinesis
+  module Aggregation
+    class Error < StandardError; end
+    # Your code goes here...
+  end
+end

data/lib/kinesis/aggregation/aggregator.rb

@@ -0,0 +1,60 @@
+module Kinesis
+  module Aggregation
+    class Aggregator
+      MAGIC = "\xf3\x89\x9a\xc2".force_encoding('ASCII-8BIT').freeze
+
+      def initialize
+        @user_records = []
+      end
+
+      def add_user_record(user_record)
+        @user_records << user_record
+      end
+
+      def aggregate!
+        result = {
+          partition_key: @user_records.first[:partition_key],
+          explicit_hash_key: @user_records.first[:explicit_hash_key] || '',
+          data: Base64.encode64(data)
+        }
+        @user_records = []
+        result
+      end
+
+      def num_user_records
+        @user_records.length
+      end
+
+      private
+
+      def aggregated_record
+        AggregatedRecord.new(
+          partition_key_table: @user_records.map { |r| r[:partition_key] },
+          explicit_hash_key_table: explicit_hash_key_table,
+          records: records
+        )
+      end
+
+      def data
+        bytes = AggregatedRecord.encode(aggregated_record)
+        MAGIC + bytes + Digest::MD5.digest(bytes)
+      end
+
+      def explicit_hash_key_table
+        @user_records.map { |r| r[:explicit_hash_key] }.compact
+      end
+
+      def records
+        @user_records.map.with_index do |user_record, index|
+          record = Record.new(
+            partition_key_index: index,
+            data: user_record[:data]
+          )
+          record.explicit_hash_key_index = index if user_record[:explicit_hash_key]
+          record
+        end
+
+      end
+    end
+  end
+end

data/lib/kinesis/aggregation/deaggregator.rb

@@ -0,0 +1,81 @@
+require 'base64'
+require 'digest'
+require 'active_support/core_ext/hash/indifferent_access'
+
+module Kinesis
+  module Aggregation
+    class Deaggregator
+      MAGIC = "\xf3\x89\x9a\xc2".force_encoding('ASCII-8BIT').freeze
+      DIGEST_SIZE = 16
+
+      def initialize(raw_record)
+        @raw_record = raw_record.with_indifferent_access
+      end
+
+      def deaggregate
+        return [kinesis_record] unless aggregated_record? && computed_md5 == kinesis_record_md5
+
+        aggregated_record.records.map do |record|
+          base_record.merge(
+            kinesis: {
+              kinesisSchemaVersion: kinesis_record[:kinesis][:kinesisSchemaVersion],
+              sequenceNumber: kinesis_record[:kinesis][:sequenceNumber],
+              approximateArrivalTimestamp: kinesis_record[:kinesis][:approximateArrivalTimestamp],
+              explicitHashKey: explicit_hash_for_for(record),
+              partitionKey: partition_key_for(record),
+              data: Base64.encode64(record.data),
+              recordId: kinesis_record[:kinesis][:recordId]
+            }
+          )
+        end
+      end
+
+      private
+      def aggregated_record?
+        data[0..MAGIC.length - 1] == MAGIC
+      end
+
+      def aggregated_record
+        @aggregated_record ||= AggregatedRecord.decode(kinesis_record_message_data)
+      end
+
+      def base_record
+        kinesis_record.reject { |k, _v| k == :kinesis }
+      end
+
+      def data
+        @data ||= Base64.decode64(kinesis_record[:kinesis][:data])
+      end
+
+      def explicit_hash_for_for(record)
+        aggregated_record.explicit_hash_key_table[record.explicit_hash_key_index]
+      end
+
+      def kinesis_record
+        @kinesis_record ||= begin
+                            if @raw_record.has_key?(:kinesisStreamRecordMetadata)
+                              KinesisAnalyticsConverter.new(@raw_record).convert
+                            else
+                              @raw_record
+                            end
+                          end
+      end
+
+      def partition_key_for(record)
+        aggregated_record.partition_key_table[record.partition_key_index]
+      end
+
+      def kinesis_record_md5
+        data[data.length - 16..-1]
+      end
+
+      def kinesis_record_message_data
+        data[MAGIC.length..-17]
+      end
+
+      def computed_md5
+        Digest::MD5.digest(kinesis_record_message_data)
+      end
+    end
+  end
+end

data/lib/kinesis/aggregation/kinesis_analytics_converter.rb

@@ -0,0 +1,19 @@
+class KinesisAnalyticsConverter
+  def initialize(kinesis_analytics_record)
+    @kinesis_analytics_record = kinesis_analytics_record
+  end
+
+  def convert
+    {
+      kinesis: {
+        kinesisSchemaVersion: '1.0',
+        sequenceNumber: @kinesis_analytics_record[:kinesisStreamRecordMetadata][:sequenceNumber],
+        partitionKey: @kinesis_analytics_record[:kinesisStreamRecordMetadata][:partitionKey],
+        approximateArrivalTimestamp: @kinesis_analytics_record[:kinesisStreamRecordMetadata][:approximateArrivalTimestamp],
+        shardId: @kinesis_analytics_record[:kinesisStreamRecordMetadata][:shardId],
+        data: @kinesis_analytics_record[:data],
+        recordId: @kinesis_analytics_record[:recordId]
+      }
+    }
+  end
+end

data/lib/kinesis/aggregation/kpl_pb.rb

@@ -0,0 +1,28 @@
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# source: kpl.proto
+
+require 'google/protobuf'
+
+Google::Protobuf::DescriptorPool.generated_pool.build do
+  add_file("kpl.proto", :syntax => :proto2) do
+    add_message "AggregatedRecord" do
+      repeated :partition_key_table, :string, 1
+      repeated :explicit_hash_key_table, :string, 2
+      repeated :records, :message, 3, "Record"
+    end
+    add_message "Tag" do
+      required :key, :string, 1
+      optional :value, :string, 2
+    end
+    add_message "Record" do
+      required :partition_key_index, :uint64, 1
+      optional :explicit_hash_key_index, :uint64, 2
+      required :data, :bytes, 3
+      repeated :tags, :message, 4, "Tag"
+    end
+  end
+end
+
+AggregatedRecord = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("AggregatedRecord").msgclass
+Tag = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("Tag").msgclass
+Record = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("Record").msgclass

data/lib/kinesis/aggregation/version.rb

@@ -0,0 +1,5 @@
+module Kinesis
+  module Aggregation
+    VERSION = "0.1.0"
+  end
+end

metadata

@@ -0,0 +1,90 @@
+--- !ruby/object:Gem::Specification
+name: kinesis-aggregation
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- hawknewton
+autorequire:
+bindir: exe
+cert_chain: []
+date: 2020-11-12 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: google-protobuf
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.13'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.13'
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '4.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '4.0'
+description: Read and write AWS KPL aggregate messages
+email:
+- hawk.newton@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- kinesis-aggregation.gemspec
+- kpl.proto
+- lib/kinesis/aggregation.rb
+- lib/kinesis/aggregation/aggregator.rb
+- lib/kinesis/aggregation/deaggregator.rb
+- lib/kinesis/aggregation/kinesis_analytics_converter.rb
+- lib/kinesis/aggregation/kpl_pb.rb
+- lib/kinesis/aggregation/version.rb
+homepage: https://github.com/hawknewton/ruby-kinesis-aggregation
+licenses:
+- Apache-2.0
+metadata:
+  homepage_uri: https://github.com/hawknewton/ruby-kinesis-aggregation
+  source_code_uri: https://github.com/hawknewton/ruby-kinesis-aggregation
+post_install_message:
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.3.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.2
+signing_key:
+specification_version: 4
+summary: Read and write AWS KPL aggregate messages
+test_files: []