ftp_multipart_download 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: c4379d1fc77c729e633e71db43bb0d15073733499196b3b5d17879003bbd0f0a
+  data.tar.gz: f3b4d39c38786ee80860eb5fcf77848087a5fe70c92db7a6e7b5cf043019c10e
+SHA512:
+  metadata.gz: 2ae6a727e6ba89a6547b26beb194fb786725db887cfd8f452da3468c8327f7155797b7eb8898941e1a0a5c543ff21f958dbc908a5ebcbbd8404a656d2867e356
+  data.tar.gz: 8aa22cac4da25975aa817fc4478ca85401dffb9e522cc4a9f90f87ac971b3f539b6ab9fe5197b1f48b8800344b36ab91fb61c9a856d046dff00d625717771d5a

data/.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

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

data/.rubocop.yml

@@ -0,0 +1,2 @@
+Metrics/LineLength:
+  Max: 128

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.5.1
+before_install: gem install bundler -v 1.16.2

data/Gemfile

@@ -0,0 +1,6 @@
+source 'https://rubygems.org'
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in ftp_multipart_download.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,59 @@
+PATH
+  remote: .
+  specs:
+    ftp_multipart_download (0.1.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    ast (2.4.0)
+    coderay (1.1.2)
+    diff-lcs (1.3)
+    jaro_winkler (1.5.1)
+    method_source (0.9.0)
+    parallel (1.12.1)
+    parser (2.5.1.0)
+      ast (~> 2.4.0)
+    powerpack (0.1.2)
+    pry (0.11.3)
+      coderay (~> 1.1.0)
+      method_source (~> 0.9.0)
+    rainbow (3.0.0)
+    rake (10.5.0)
+    rspec (3.7.0)
+      rspec-core (~> 3.7.0)
+      rspec-expectations (~> 3.7.0)
+      rspec-mocks (~> 3.7.0)
+    rspec-core (3.7.1)
+      rspec-support (~> 3.7.0)
+    rspec-expectations (3.7.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.7.0)
+    rspec-mocks (3.7.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.7.0)
+    rspec-support (3.7.1)
+    rubocop (0.57.2)
+      jaro_winkler (~> 1.5.1)
+      parallel (~> 1.10)
+      parser (>= 2.5)
+      powerpack (~> 0.1)
+      rainbow (>= 2.2.2, < 4.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (~> 1.0, >= 1.0.1)
+    ruby-progressbar (1.9.0)
+    unicode-display_width (1.4.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.16)
+  ftp_multipart_download!
+  pry (~> 0.11.3)
+  rake (~> 10.0)
+  rspec (~> 3.0)
+  rubocop (~> 0.57.2)
+
+BUNDLED WITH
+   1.16.2

data/README.md

@@ -0,0 +1,35 @@
+# FtpMultipartDownload
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'ftp_multipart_download'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install ftp_multipart_download
+
+## Usage
+
+```ruby
+$ bin/console
+downloader = FtpMultipartDownload::Downloader.new('ftp.riken.go.jp', username: 'anonymous', debug_mode: true)
+downloader.download('/Linux/centos/7/isos/x86_64/CentOS-7-x86_64-NetInstall-1804.iso')
+```
+
+## 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/koshigoe/ftp_multipart_download.

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 'ftp_multipart_download'
+
+# 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 'pry'
+Pry.start

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/ftp_multipart_download.gemspec

@@ -0,0 +1,31 @@
+lib = File.expand_path('lib', __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'ftp_multipart_download/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'ftp_multipart_download'
+  spec.version       = FtpMultipartDownload::VERSION
+  spec.authors       = %w[koshigoe]
+  spec.email         = %w[koshigoeb@gmail.com]
+
+  spec.summary       = 'This gem allows to concurrent multipart download via FTP.'
+  spec.description   = 'This gem allows to concurrent multipart download via FTP.'
+  spec.homepage      = 'https://github.com/koshigoe/ftp_multipart_download'
+
+  # 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(__dir__)) 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 = %w[lib]
+
+  spec.required_ruby_version = '~> 2.5.1'
+
+  spec.add_development_dependency 'bundler', '~> 1.16'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+  spec.add_development_dependency 'rubocop', '~> 0.57.2'
+  spec.add_development_dependency 'pry', '~> 0.11.3'
+end

data/lib/ftp_multipart_download.rb

@@ -0,0 +1,20 @@
+require 'ftp_multipart_download/version'
+require 'ftp_multipart_download/connection_pool'
+require 'ftp_multipart_download/downloader'
+require 'ftp_multipart_download/part'
+require 'ftp_multipart_download/scheduler'
+require 'net/ftp'
+
+module FtpMultipartDownload
+  class Error < StandardError; end
+  class ConnectionError < Error
+    attr_reader :errors
+
+    def initialize(error_message = nil, errors: [])
+      super(error_message)
+      @errors = errors
+    end
+  end
+
+  DEFAULT_BLOCKSIZE = Net::FTP::DEFAULT_BLOCKSIZE
+end

data/lib/ftp_multipart_download/connection_pool.rb

@@ -0,0 +1,29 @@
+require 'net/ftp'
+
+module FtpMultipartDownload
+  class ConnectionPool
+    attr_reader :errors
+
+    # @param [Integer] size number of connections.
+    # @param [Array] argv argument values for Net::FTP#initialize.
+    #
+    def initialize(size, *argv)
+      @errors = []
+      @connection_pool = Array.new(size) do
+        Net::FTP.new(*argv).yield_self { |c| c.closed? ? nil : c }
+      rescue => e
+        errors << e
+        nil
+      end.compact
+    end
+
+    include ::Enumerable
+
+    # @yield [connection] gives an instance of Net::FTP which connected
+    # @yieldparam [Net::FTP] an instance of Net::FTP which connected
+    #
+    def each(&block)
+      @connection_pool.each(&block)
+    end
+  end
+end

data/lib/ftp_multipart_download/downloader.rb

@@ -0,0 +1,33 @@
+module FtpMultipartDownload
+  class Downloader
+    attr_reader :argv
+
+    # see Net::FTP#initialize
+    #
+    # @param [String] host Host name.
+    # @param [Hash, String] user_or_options username or option as Hash.
+    # @param [String] passwd password
+    # @param [String] Account information for ACCT.
+    #
+    def initialize(host = nil, user_or_options = {}, passwd = nil, acct = nil)
+      @argv = [host, user_or_options, passwd, acct]
+    end
+
+    # concurrent multipart downloading.
+    #
+    # @param [Integer] concurrent number of concurrent download sessions.
+    # @param [String] remotefile remote file path.
+    # @param [String] localfile local file path.
+    # @param [Integer] blocksize block size.
+    # @raise [ConnectionError]
+    #
+    def download(concurrent, remotefile, localfile = File.basename(remotefile), blocksize = DEFAULT_BLOCKSIZE)
+      connection_pool = ConnectionPool.new(concurrent, *argv)
+      if connection_pool.count == 0
+        raise ConnectionError.new('Could not establish any connection.', errors: connection_pool.errors)
+      end
+
+      Scheduler.new(connection_pool).schedule(remotefile, localfile, blocksize)
+    end
+  end
+end

data/lib/ftp_multipart_download/part.rb

@@ -0,0 +1,35 @@
+module FtpMultipartDownload
+  class Part
+    attr_reader :connection
+
+    # @param [Net::FTP] connection an instance of Net::FTP.
+    #
+    def initialize(connection)
+      @connection = connection
+    end
+
+    # download a part of file.
+    #
+    # @param [String] remotefile remote file path.
+    # @param [String] localfile local file path.
+    # @param [Integer] blocksize block size.
+    # @param [Integer] offset offset
+    # @param [Integer] limit limit
+    #
+    def download(remotefile, localfile, blocksize, offset, limit)
+      old_resume, connection.resume = connection.resume, true
+
+      File.open(localfile, 'wb') do |f|
+        retrieved = 0
+        connection.retrbinary("RETR #{remotefile}", blocksize, offset) do |chunk|
+          retrievable = [limit - retrieved, chunk.bytesize].min
+          break if retrievable <= 0
+
+          retrieved += f.write(chunk[0, retrievable])
+        end
+      end
+    ensure
+      connection.resume = old_resume
+    end
+  end
+end

data/lib/ftp_multipart_download/scheduler.rb

@@ -0,0 +1,55 @@
+require 'thwait'
+require 'tmpdir'
+
+module FtpMultipartDownload
+  class Scheduler
+    attr_reader :connection_pool
+
+    # @param [Array<Net::FTP>] connection_pool an array of instance of Net::FTP.
+    #
+    def initialize(connection_pool)
+      @connection_pool = connection_pool
+    end
+
+    # concurrent multipart downloading.
+    #
+    # @param [String] remotefile remote file path.
+    # @param [String] localfile local file path.
+    # @param [Integer] blocksize block size.
+    #
+    def schedule(remotefile, localfile, blocksize)
+      total_size = connection_pool.first.size(remotefile)
+      part_size = (total_size.to_f / connection_pool.count).ceil
+
+      Dir.mktmpdir do |dir|
+        part_files = []
+        threads = connection_pool.map.with_index do |connection, i|
+          offset = part_size * i
+          next if offset >= total_size
+          part_files << "#{dir}/#{i}"
+          thread(connection, remotefile, part_files.last, blocksize, offset, part_size)
+        end.compact
+        ThreadsWait.all_waits(*threads)
+
+        concat_files(localfile, *part_files)
+      end
+    end
+
+    private
+
+    def thread(*args)
+      Thread.start(*args) do |connection, remotefile, partfile, blocksize, offset, limit|
+        Part.new(connection).download(remotefile, partfile, blocksize, offset, limit)
+      end
+    end
+
+    def concat_files(dest, *parts)
+      File.open(dest, 'wb') do |output|
+        parts.each do |part|
+          next unless File.exist?(part)
+          IO.copy_stream(part, output)
+        end
+      end
+    end
+  end
+end

data/lib/ftp_multipart_download/version.rb

@@ -0,0 +1,3 @@
+module FtpMultipartDownload
+  VERSION = '0.1.0'.freeze
+end

metadata

@@ -0,0 +1,130 @@
+--- !ruby/object:Gem::Specification
+name: ftp_multipart_download
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- koshigoe
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-06-24 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+- !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: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.57.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.57.2
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.11.3
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.11.3
+description: This gem allows to concurrent multipart download via FTP.
+email:
+- koshigoeb@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- ".travis.yml"
+- Gemfile
+- Gemfile.lock
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- ftp_multipart_download.gemspec
+- lib/ftp_multipart_download.rb
+- lib/ftp_multipart_download/connection_pool.rb
+- lib/ftp_multipart_download/downloader.rb
+- lib/ftp_multipart_download/part.rb
+- lib/ftp_multipart_download/scheduler.rb
+- lib/ftp_multipart_download/version.rb
+homepage: https://github.com/koshigoe/ftp_multipart_download
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - "~>"
+    - !ruby/object:Gem::Version
+      version: 2.5.1
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.7.6
+signing_key: 
+specification_version: 4
+summary: This gem allows to concurrent multipart download via FTP.
+test_files: []