batched_query 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +17 -0
- data/.rspec +2 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +1 -0
- data/batched_query.gemspec +24 -0
- data/lib/batched_query.rb +5 -0
- data/lib/batched_query/runner.rb +53 -0
- data/lib/batched_query/version.rb +3 -0
- data/spec/batched_query/runner_spec.rb +58 -0
- data/spec/batched_query_spec.rb +4 -0
- data/spec/spec_helper.rb +99 -0
- metadata +103 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: cd2d283bc329bbab254c956269ad1c2d3fd65c29
|
4
|
+
data.tar.gz: 795174375fcc60ec9f0a2fc84e1ddbd1d727de12
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: a60627f3311c91736deee2da5fd00256a8de30e7afbff7f451f93bb444f2c713e18f8e57a523d3886026b40787adb7934661e7cad34f5a839f9f6104266c72c1
|
7
|
+
data.tar.gz: 723c80e1bec705245b80482bf045100b294f7b0f7aa0b803b54f6410ca7ccf5e3ad4f4b5c717fa8ae721514341366795a3398b9ad933cf4d893b048208b012b6
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2015 Edmund Mai
|
2
|
+
|
3
|
+
MIT License
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
6
|
+
a copy of this software and associated documentation files (the
|
7
|
+
"Software"), to deal in the Software without restriction, including
|
8
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
9
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
10
|
+
permit persons to whom the Software is furnished to do so, subject to
|
11
|
+
the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be
|
14
|
+
included in all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
17
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
18
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
19
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
20
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
21
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
22
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,29 @@
|
|
1
|
+
# BatchedQuery
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'batched_query'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install batched_query
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it ( http://github.com/<my-github-username>/batched_query/fork )
|
26
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
27
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
28
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
29
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
@@ -0,0 +1,24 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'batched_query/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "batched_query"
|
8
|
+
spec.version = BatchedQuery::VERSION
|
9
|
+
spec.authors = ["Edmund Mai"]
|
10
|
+
spec.email = ["edmundmai@gmail.com"]
|
11
|
+
spec.summary = %q{Substitute for ActiveRecord's find_each and find_in_batches methods}
|
12
|
+
spec.description = %q{Allows you to separate queries that return large results into several subsets to lower memory consumption}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
spec.add_development_dependency "rspec"
|
16
|
+
|
17
|
+
spec.files = `git ls-files -z`.split("\x0")
|
18
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
19
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
20
|
+
spec.require_paths = ["lib"]
|
21
|
+
|
22
|
+
spec.add_development_dependency "bundler", "~> 1.5"
|
23
|
+
spec.add_development_dependency "rake"
|
24
|
+
end
|
@@ -0,0 +1,53 @@
|
|
1
|
+
module BatchedQuery
|
2
|
+
class Runner
|
3
|
+
DEFAULT_LIMIT = 500
|
4
|
+
|
5
|
+
def self.limit=(limit)
|
6
|
+
@limit = limit
|
7
|
+
end
|
8
|
+
|
9
|
+
def self.limit
|
10
|
+
@limit || DEFAULT_LIMIT
|
11
|
+
end
|
12
|
+
|
13
|
+
def self.each_set(query, &block)
|
14
|
+
cached_ids = get_ordered_list_of_ids(query)
|
15
|
+
|
16
|
+
cached_ids.each_slice(limit).each do |batch_of_ids|
|
17
|
+
results = query.where(:id => batch_of_ids)
|
18
|
+
block.call results
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
def self.each_result(query, &block)
|
23
|
+
each_set(query) do |set|
|
24
|
+
set.each do |result|
|
25
|
+
block.call result
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
private
|
31
|
+
|
32
|
+
def self.get_ordered_list_of_ids(query)
|
33
|
+
query.pluck(:id)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
# Any ActiveRecord query
|
39
|
+
cars = Car.where("brand_name = 'Ferrari'")order("created_at desc")
|
40
|
+
|
41
|
+
# Set the limit of each subquery
|
42
|
+
BatchedQuery::Runner.limit = 100
|
43
|
+
BatchedQuery::Runner.each_set(cars) do |batch_of_cars|
|
44
|
+
# process results in manageable subsets
|
45
|
+
batch_of_cars.map { |car| ... }
|
46
|
+
end
|
47
|
+
|
48
|
+
BatchedQuery::Runner.limit = 200
|
49
|
+
BatchedQuery::Runner.each_result(cars) do |car|
|
50
|
+
# access each car as if you loaded all of the records at once
|
51
|
+
car.start!
|
52
|
+
end
|
53
|
+
end
|
@@ -0,0 +1,58 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
describe BatchedQuery::Runner do
|
4
|
+
describe ".each_set" do
|
5
|
+
let(:query) do
|
6
|
+
double("User", pluck: [1,2], where: [1, 2])
|
7
|
+
end
|
8
|
+
|
9
|
+
before do
|
10
|
+
BatchedQuery::Runner.limit = 1
|
11
|
+
end
|
12
|
+
|
13
|
+
it "calls the block twice" do
|
14
|
+
expect { |b| BatchedQuery::Runner.each_set(query, &b) }.to yield_control.exactly(2).times
|
15
|
+
end
|
16
|
+
|
17
|
+
it "splits the query into two parts" do
|
18
|
+
BatchedQuery::Runner.each_set(query) do |current_number|
|
19
|
+
#do nothing
|
20
|
+
end
|
21
|
+
|
22
|
+
expect(query).to have_received(:where).with(:id => [1])
|
23
|
+
expect(query).to have_received(:where).with(:id => [2])
|
24
|
+
end
|
25
|
+
|
26
|
+
it "calls block with each query subset" do
|
27
|
+
total = []
|
28
|
+
BatchedQuery::Runner.each_set(query) do |current_subset|
|
29
|
+
total = total + current_subset
|
30
|
+
end
|
31
|
+
|
32
|
+
expect(total).to eq([1, 2, 1, 2])
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
describe ".each_result" do
|
37
|
+
let(:query) do
|
38
|
+
double("User", pluck: [1,2], where: [1, 2])
|
39
|
+
end
|
40
|
+
|
41
|
+
before do
|
42
|
+
BatchedQuery::Runner.limit = 2
|
43
|
+
end
|
44
|
+
|
45
|
+
it "calls the block twice" do
|
46
|
+
expect { |b| BatchedQuery::Runner.each_result(query, &b) }.to yield_control.exactly(2).times
|
47
|
+
end
|
48
|
+
|
49
|
+
it "calls block with each query result" do
|
50
|
+
total = 0
|
51
|
+
BatchedQuery::Runner.each_result(query) do |current_result|
|
52
|
+
total = total + current_result
|
53
|
+
end
|
54
|
+
|
55
|
+
expect(total).to eq(3)
|
56
|
+
end
|
57
|
+
end
|
58
|
+
end
|
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,99 @@
|
|
1
|
+
# This file was generated by the `rspec --init` command. Conventionally, all
|
2
|
+
# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
|
3
|
+
# The generated `.rspec` file contains `--require spec_helper` which will cause
|
4
|
+
# this file to always be loaded, without a need to explicitly require it in any
|
5
|
+
# files.
|
6
|
+
#
|
7
|
+
# Given that it is always loaded, you are encouraged to keep this file as
|
8
|
+
# light-weight as possible. Requiring heavyweight dependencies from this file
|
9
|
+
# will add to the boot time of your test suite on EVERY test run, even for an
|
10
|
+
# individual file that may not need all of that loaded. Instead, consider making
|
11
|
+
# a separate helper file that requires the additional dependencies and performs
|
12
|
+
# the additional setup, and require it from the spec files that actually need
|
13
|
+
# it.
|
14
|
+
#
|
15
|
+
# The `.rspec` file also contains a few flags that are not defaults but that
|
16
|
+
# users commonly want.
|
17
|
+
#
|
18
|
+
$LOAD_PATH << '../lib'
|
19
|
+
require "batched_query/runner"
|
20
|
+
require "batched_query/runner_spec"
|
21
|
+
# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
|
22
|
+
RSpec.configure do |config|
|
23
|
+
# rspec-expectations config goes here. You can use an alternate
|
24
|
+
# assertion/expectation library such as wrong or the stdlib/minitest
|
25
|
+
# assertions if you prefer.
|
26
|
+
config.expect_with :rspec do |expectations|
|
27
|
+
# This option will default to `true` in RSpec 4. It makes the `description`
|
28
|
+
# and `failure_message` of custom matchers include text for helper methods
|
29
|
+
# defined using `chain`, e.g.:
|
30
|
+
# be_bigger_than(2).and_smaller_than(4).description
|
31
|
+
# # => "be bigger than 2 and smaller than 4"
|
32
|
+
# ...rather than:
|
33
|
+
# # => "be bigger than 2"
|
34
|
+
expectations.include_chain_clauses_in_custom_matcher_descriptions = true
|
35
|
+
end
|
36
|
+
|
37
|
+
# rspec-mocks config goes here. You can use an alternate test double
|
38
|
+
# library (such as bogus or mocha) by changing the `mock_with` option here.
|
39
|
+
config.mock_with :rspec do |mocks|
|
40
|
+
# Prevents you from mocking or stubbing a method that does not exist on
|
41
|
+
# a real object. This is generally recommended, and will default to
|
42
|
+
# `true` in RSpec 4.
|
43
|
+
mocks.verify_partial_doubles = true
|
44
|
+
end
|
45
|
+
|
46
|
+
# The settings below are suggested to provide a good initial experience
|
47
|
+
# with RSpec, but feel free to customize to your heart's content.
|
48
|
+
=begin
|
49
|
+
# These two settings work together to allow you to limit a spec run
|
50
|
+
# to individual examples or groups you care about by tagging them with
|
51
|
+
# `:focus` metadata. When nothing is tagged with `:focus`, all examples
|
52
|
+
# get run.
|
53
|
+
config.filter_run :focus
|
54
|
+
config.run_all_when_everything_filtered = true
|
55
|
+
|
56
|
+
# Allows RSpec to persist some state between runs in order to support
|
57
|
+
# the `--only-failures` and `--next-failure` CLI options. We recommend
|
58
|
+
# you configure your source control system to ignore this file.
|
59
|
+
config.example_status_persistence_file_path = "spec/examples.txt"
|
60
|
+
|
61
|
+
# Limits the available syntax to the non-monkey patched syntax that is
|
62
|
+
# recommended. For more details, see:
|
63
|
+
# - http://myronmars.to/n/dev-blog/2012/06/rspecs-new-expectation-syntax
|
64
|
+
# - http://www.teaisaweso.me/blog/2013/05/27/rspecs-new-message-expectation-syntax/
|
65
|
+
# - http://myronmars.to/n/dev-blog/2014/05/notable-changes-in-rspec-3#new__config_option_to_disable_rspeccore_monkey_patching
|
66
|
+
config.disable_monkey_patching!
|
67
|
+
|
68
|
+
# This setting enables warnings. It's recommended, but in some cases may
|
69
|
+
# be too noisy due to issues in dependencies.
|
70
|
+
config.warnings = true
|
71
|
+
|
72
|
+
# Many RSpec users commonly either run the entire suite or an individual
|
73
|
+
# file, and it's useful to allow more verbose output when running an
|
74
|
+
# individual spec file.
|
75
|
+
if config.files_to_run.one?
|
76
|
+
# Use the documentation formatter for detailed output,
|
77
|
+
# unless a formatter has already been configured
|
78
|
+
# (e.g. via a command-line flag).
|
79
|
+
config.default_formatter = 'doc'
|
80
|
+
end
|
81
|
+
|
82
|
+
# Print the 10 slowest examples and example groups at the
|
83
|
+
# end of the spec run, to help surface which specs are running
|
84
|
+
# particularly slow.
|
85
|
+
config.profile_examples = 10
|
86
|
+
|
87
|
+
# Run specs in random order to surface order dependencies. If you find an
|
88
|
+
# order dependency and want to debug it, you can fix the order by providing
|
89
|
+
# the seed, which is printed after each run.
|
90
|
+
# --seed 1234
|
91
|
+
config.order = :random
|
92
|
+
|
93
|
+
# Seed global randomization in this process using the `--seed` CLI option.
|
94
|
+
# Setting this allows you to use `--seed` to deterministically reproduce
|
95
|
+
# test failures related to randomization by passing the same `--seed` value
|
96
|
+
# as the one that triggered the failure.
|
97
|
+
Kernel.srand config.seed
|
98
|
+
=end
|
99
|
+
end
|
metadata
ADDED
@@ -0,0 +1,103 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: batched_query
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Edmund Mai
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-06-27 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: rspec
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - ">="
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ">="
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.5'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.5'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ">="
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
55
|
+
description: Allows you to separate queries that return large results into several
|
56
|
+
subsets to lower memory consumption
|
57
|
+
email:
|
58
|
+
- edmundmai@gmail.com
|
59
|
+
executables: []
|
60
|
+
extensions: []
|
61
|
+
extra_rdoc_files: []
|
62
|
+
files:
|
63
|
+
- ".gitignore"
|
64
|
+
- ".rspec"
|
65
|
+
- Gemfile
|
66
|
+
- LICENSE.txt
|
67
|
+
- README.md
|
68
|
+
- Rakefile
|
69
|
+
- batched_query.gemspec
|
70
|
+
- lib/batched_query.rb
|
71
|
+
- lib/batched_query/runner.rb
|
72
|
+
- lib/batched_query/version.rb
|
73
|
+
- spec/batched_query/runner_spec.rb
|
74
|
+
- spec/batched_query_spec.rb
|
75
|
+
- spec/spec_helper.rb
|
76
|
+
homepage: ''
|
77
|
+
licenses:
|
78
|
+
- MIT
|
79
|
+
metadata: {}
|
80
|
+
post_install_message:
|
81
|
+
rdoc_options: []
|
82
|
+
require_paths:
|
83
|
+
- lib
|
84
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
85
|
+
requirements:
|
86
|
+
- - ">="
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
version: '0'
|
89
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
90
|
+
requirements:
|
91
|
+
- - ">="
|
92
|
+
- !ruby/object:Gem::Version
|
93
|
+
version: '0'
|
94
|
+
requirements: []
|
95
|
+
rubyforge_project:
|
96
|
+
rubygems_version: 2.2.2
|
97
|
+
signing_key:
|
98
|
+
specification_version: 4
|
99
|
+
summary: Substitute for ActiveRecord's find_each and find_in_batches methods
|
100
|
+
test_files:
|
101
|
+
- spec/batched_query/runner_spec.rb
|
102
|
+
- spec/batched_query_spec.rb
|
103
|
+
- spec/spec_helper.rb
|