batched_query 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: cd2d283bc329bbab254c956269ad1c2d3fd65c29
+  data.tar.gz: 795174375fcc60ec9f0a2fc84e1ddbd1d727de12
+SHA512:
+  metadata.gz: a60627f3311c91736deee2da5fd00256a8de30e7afbff7f451f93bb444f2c713e18f8e57a523d3886026b40787adb7934661e7cad34f5a839f9f6104266c72c1
+  data.tar.gz: 723c80e1bec705245b80482bf045100b294f7b0f7aa0b803b54f6410ca7ccf5e3ad4f4b5c717fa8ae721514341366795a3398b9ad933cf4d893b048208b012b6

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--require spec_helper

data/Gemfile

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

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2015 Edmund Mai
+
+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 +1,29 @@
+# BatchedQuery
+
+TODO: Write a gem description
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'batched_query'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install batched_query
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Contributing
+
+1. Fork it ( http://github.com/<my-github-username>/batched_query/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 new Pull Request

data/Rakefile

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

data/batched_query.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'batched_query/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "batched_query"
+  spec.version       = BatchedQuery::VERSION
+  spec.authors       = ["Edmund Mai"]
+  spec.email         = ["edmundmai@gmail.com"]
+  spec.summary       = %q{Substitute for ActiveRecord's find_each and find_in_batches methods}
+  spec.description   = %q{Allows you to separate queries that return large results into several subsets to lower memory consumption}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+  spec.add_development_dependency "rspec"
+
+  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", "~> 1.5"
+  spec.add_development_dependency "rake"
+end

data/lib/batched_query.rb

@@ -0,0 +1,5 @@
+require "batched_query/version"
+require "batched_query/runner"
+
+module BatchedQuery
+end

data/lib/batched_query/runner.rb

@@ -0,0 +1,53 @@
+module BatchedQuery
+  class Runner
+    DEFAULT_LIMIT = 500
+
+    def self.limit=(limit)
+      @limit = limit
+    end
+
+    def self.limit
+      @limit || DEFAULT_LIMIT
+    end
+
+    def self.each_set(query, &block)
+      cached_ids = get_ordered_list_of_ids(query)
+
+      cached_ids.each_slice(limit).each do |batch_of_ids|
+        results = query.where(:id => batch_of_ids)
+        block.call results
+      end
+    end
+
+    def self.each_result(query, &block)
+      each_set(query) do |set|
+        set.each do |result|
+          block.call result
+        end
+      end
+    end
+
+    private
+
+    def self.get_ordered_list_of_ids(query)
+      query.pluck(:id)
+    end
+  end
+end
+
+# Any ActiveRecord query
+cars = Car.where("brand_name = 'Ferrari'")order("created_at desc")
+
+# Set the limit of each subquery
+BatchedQuery::Runner.limit = 100
+BatchedQuery::Runner.each_set(cars) do |batch_of_cars|
+  # process results in manageable subsets
+  batch_of_cars.map { |car| ... }
+end
+
+BatchedQuery::Runner.limit = 200
+BatchedQuery::Runner.each_result(cars) do |car|
+  # access each car as if you loaded all of the records at once
+  car.start!
+end
+end

data/lib/batched_query/version.rb

@@ -0,0 +1,3 @@
+module BatchedQuery
+  VERSION = "0.0.1"
+end

data/spec/batched_query/runner_spec.rb

@@ -0,0 +1,58 @@
+require 'spec_helper'
+
+describe BatchedQuery::Runner do
+  describe ".each_set" do
+    let(:query) do
+      double("User", pluck: [1,2], where: [1, 2])
+    end
+
+    before do
+      BatchedQuery::Runner.limit = 1
+    end
+
+    it "calls the block twice" do
+      expect { |b| BatchedQuery::Runner.each_set(query, &b) }.to yield_control.exactly(2).times
+    end
+
+    it "splits the query into two parts" do
+      BatchedQuery::Runner.each_set(query) do |current_number|
+        #do nothing
+      end
+
+      expect(query).to have_received(:where).with(:id => [1])
+      expect(query).to have_received(:where).with(:id => [2])
+    end
+
+    it "calls block with each query subset" do
+      total = []
+      BatchedQuery::Runner.each_set(query) do |current_subset|
+        total = total + current_subset
+      end
+
+      expect(total).to eq([1, 2, 1, 2])
+    end
+  end
+
+  describe ".each_result" do
+    let(:query) do
+      double("User", pluck: [1,2], where: [1, 2])
+    end
+
+    before do
+      BatchedQuery::Runner.limit = 2
+    end
+
+    it "calls the block twice" do
+      expect { |b| BatchedQuery::Runner.each_result(query, &b) }.to yield_control.exactly(2).times
+    end
+
+    it "calls block with each query result" do
+      total = 0
+      BatchedQuery::Runner.each_result(query) do |current_result|
+        total = total + current_result
+      end
+
+      expect(total).to eq(3)
+    end
+  end
+end

data/spec/batched_query_spec.rb

@@ -0,0 +1,4 @@
+require 'spec_helper'
+
+describe BatchedQuery do
+end

data/spec/spec_helper.rb

@@ -0,0 +1,99 @@
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# The generated `.rspec` file contains `--require spec_helper` which will cause
+# this file to always be loaded, without a need to explicitly require it in any
+# files.
+#
+# Given that it is always loaded, you are encouraged to keep this file as
+# light-weight as possible. Requiring heavyweight dependencies from this file
+# will add to the boot time of your test suite on EVERY test run, even for an
+# individual file that may not need all of that loaded. Instead, consider making
+# a separate helper file that requires the additional dependencies and performs
+# the additional setup, and require it from the spec files that actually need
+# it.
+#
+# The `.rspec` file also contains a few flags that are not defaults but that
+# users commonly want.
+#
+$LOAD_PATH << '../lib'
+require "batched_query/runner"
+require "batched_query/runner_spec"
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    #     be_bigger_than(2).and_smaller_than(4).description
+    #     # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #     # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # These two settings work together to allow you to limit a spec run
+  # to individual examples or groups you care about by tagging them with
+  # `:focus` metadata. When nothing is tagged with `:focus`, all examples
+  # get run.
+  config.filter_run :focus
+  config.run_all_when_everything_filtered = true
+
+  # Allows RSpec to persist some state between runs in order to support
+  # the `--only-failures` and `--next-failure` CLI options. We recommend
+  # you configure your source control system to ignore this file.
+  config.example_status_persistence_file_path = "spec/examples.txt"
+
+  # Limits the available syntax to the non-monkey patched syntax that is
+  # recommended. For more details, see:
+  #   - http://myronmars.to/n/dev-blog/2012/06/rspecs-new-expectation-syntax
+  #   - http://www.teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
+  #   - http://myronmars.to/n/dev-blog/2014/05/notable-changes-in-rspec-3#new__config_option_to_disable_rspeccore_monkey_patching
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = 'doc'
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+=end
+end

metadata

@@ -0,0 +1,103 @@
+--- !ruby/object:Gem::Specification
+name: batched_query
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Edmund Mai
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-06-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rspec
+  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: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.5'
+- !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'
+description: Allows you to separate queries that return large results into several
+  subsets to lower memory consumption
+email:
+- edmundmai@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- batched_query.gemspec
+- lib/batched_query.rb
+- lib/batched_query/runner.rb
+- lib/batched_query/version.rb
+- spec/batched_query/runner_spec.rb
+- spec/batched_query_spec.rb
+- spec/spec_helper.rb
+homepage: ''
+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: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Substitute for ActiveRecord's find_each and find_in_batches methods
+test_files:
+- spec/batched_query/runner_spec.rb
+- spec/batched_query_spec.rb
+- spec/spec_helper.rb