redis_dedupe 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +22 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +40 -0
- data/Rakefile +3 -0
- data/lib/redis_dedupe.rb +64 -0
- data/lib/redis_dedupe/version.rb +3 -0
- data/redis_dedupe.gemspec +24 -0
- data/spec/redis_dedupe_spec.rb +56 -0
- data/spec/spec_helper.rb +0 -0
- data/tasks/rspec.rake +3 -0
- metadata +120 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 75665204b3b1c72866624a2cb948eea5e7ec59db
|
4
|
+
data.tar.gz: d8472403d0a7711f7255b3662697dc58aa2131c2
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 848327df6eb7833b69bc55575a0c33b5d0c82ae9d09fc3dcf2ab20cf35d6d24554fd82d23f71400e647a7e71201d480b6fd4572ee9e3168e6aa3f46921299b4c
|
7
|
+
data.tar.gz: 8672ea3ee0be153a2fe786d9143d23ef6e998eef2dd9501389d5dd0eb3f12df287e8f22810d3d61ca345465f14194feaf8226d993b79d0484c3e44a2b71df9bd
|
data/.gitignore
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
*.gem
|
2
|
+
*.rbc
|
3
|
+
.bundle
|
4
|
+
.config
|
5
|
+
.yardoc
|
6
|
+
Gemfile.lock
|
7
|
+
InstalledFiles
|
8
|
+
_yardoc
|
9
|
+
coverage
|
10
|
+
doc/
|
11
|
+
lib/bundler/man
|
12
|
+
pkg
|
13
|
+
rdoc
|
14
|
+
spec/reports
|
15
|
+
test/tmp
|
16
|
+
test/version_tmp
|
17
|
+
tmp
|
18
|
+
*.bundle
|
19
|
+
*.so
|
20
|
+
*.o
|
21
|
+
*.a
|
22
|
+
mkmf.log
|
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2015 Andy Huynh
|
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 +1,40 @@
|
|
1
|
+
# RedisDedupe
|
2
|
+
|
3
|
+
This is a weak deduper to make things like bulk email run safer. It is not a lock safe for financial/security needs because it uses a weak redis locking pattern that can have race conditions.
|
4
|
+
|
5
|
+
However, imagine a bulk email job that loops over 100 users, and enqueues a background email for each user. If the job fails at iteration 50, a retry would enqueue all the users again and many will receive dupes. This would continue multiple times as the parent job continued to rerun. By marking that a subjob has been enqueued, we can let that isolated job handle its own failures, and the batch enqueue job can run multiple times without re-enqueueing the same subjobs.
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Add this line to your application's Gemfile:
|
10
|
+
|
11
|
+
gem 'redis_dedupe'
|
12
|
+
|
13
|
+
And then execute:
|
14
|
+
|
15
|
+
$ bundle
|
16
|
+
|
17
|
+
Or install it yourself as:
|
18
|
+
|
19
|
+
$ gem install redis_dedupe
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
```ruby
|
24
|
+
comment_id = 42
|
25
|
+
dedupe = RedisDedupe::Set.new($redis, "comment:42:notification")
|
26
|
+
|
27
|
+
users.each do |user|
|
28
|
+
dedupe.check(user.id) do
|
29
|
+
send_email_to(user, comment_id)
|
30
|
+
end
|
31
|
+
end
|
32
|
+
```
|
33
|
+
|
34
|
+
## Contributing
|
35
|
+
|
36
|
+
1. Fork it ( https://github.com/[my-github-username]/redis_dedupe/fork )
|
37
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
38
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
39
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
40
|
+
5. Create a new Pull Request
|
data/Rakefile
ADDED
data/lib/redis_dedupe.rb
ADDED
@@ -0,0 +1,64 @@
|
|
1
|
+
require 'redis_dedupe/version'
|
2
|
+
|
3
|
+
module RedisDedupe
|
4
|
+
class<<self
|
5
|
+
attr_accessor :client
|
6
|
+
end
|
7
|
+
|
8
|
+
class Set
|
9
|
+
SEVEN_DAYS = 7 * 24 * 60 * 60
|
10
|
+
|
11
|
+
attr_reader :key, :expires_in
|
12
|
+
|
13
|
+
def initialize(redis, key, expires_in = Time.now + SEVEN_DAYS)
|
14
|
+
@redis = redis
|
15
|
+
@key = key
|
16
|
+
@expires_in = expires_in
|
17
|
+
end
|
18
|
+
|
19
|
+
def check(member)
|
20
|
+
results = redis.pipelined do
|
21
|
+
redis.sadd(key, member)
|
22
|
+
redis.expire(key, expires_in)
|
23
|
+
end
|
24
|
+
|
25
|
+
if results[0]
|
26
|
+
yield
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
def finish
|
31
|
+
redis.del(key)
|
32
|
+
end
|
33
|
+
|
34
|
+
private
|
35
|
+
|
36
|
+
def redis
|
37
|
+
@redis
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
module Helpers
|
42
|
+
private
|
43
|
+
|
44
|
+
def dedupe
|
45
|
+
@dedupe ||= RedisDedupe::Set.new(RedisDedupe.client, [dedupe_namespace, dedupe_id].join(':'))
|
46
|
+
end
|
47
|
+
|
48
|
+
# Implement in class, should return an integer or string:
|
49
|
+
#
|
50
|
+
# Ex.
|
51
|
+
#
|
52
|
+
# def dedupe_id
|
53
|
+
# @announcement.id # => 42
|
54
|
+
# end
|
55
|
+
#
|
56
|
+
def dedupe_id
|
57
|
+
raise NotImplementedError
|
58
|
+
end
|
59
|
+
|
60
|
+
def dedupe_namespace
|
61
|
+
self.class.name
|
62
|
+
end
|
63
|
+
end
|
64
|
+
end
|
@@ -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 'redis_dedupe/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "redis_dedupe"
|
8
|
+
spec.version = RedisDedupe::VERSION
|
9
|
+
spec.authors = ["Andy Huynh"]
|
10
|
+
spec.email = ["andy4thehuynh@gmail.com"]
|
11
|
+
spec.summary = %q{ A weak deduper to make things like bulk email run safer. }
|
12
|
+
spec.description = %q{ This is a weak deduper to make things like bulk email run safer. It is not a lock safe for financial/security needs because it uses a weak redis locking pattern that can have race conditions. However, imagine a bulk email job that loops over 100 users, and enqueues a background email for each user. If the job fails at iteration 50, a retry would enqueue all the users again and many will receive dupes. This would continue multiple times as the parent job continued to rerun. By marking that a subjob has been enqueued, we can let that isolated job handle its own failures, and the batch enqueue job can run multiple times without re-enqueueing the same subjobs. }
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0")
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.require_paths = ["lib"]
|
19
|
+
|
20
|
+
spec.add_development_dependency "bundler", "~> 1.6"
|
21
|
+
spec.add_development_dependency "rake"
|
22
|
+
spec.add_development_dependency "rspec"
|
23
|
+
spec.add_development_dependency "mock_redis"
|
24
|
+
end
|
@@ -0,0 +1,56 @@
|
|
1
|
+
require 'redis_dedupe'
|
2
|
+
require 'mock_redis'
|
3
|
+
require 'spec_helper'
|
4
|
+
|
5
|
+
describe RedisDedupe::Set do
|
6
|
+
it "is initialized with a redis client and key" do
|
7
|
+
dedupe = RedisDedupe::Set.new(:redis, :key)
|
8
|
+
expect(dedupe.key).to eq(:key)
|
9
|
+
end
|
10
|
+
|
11
|
+
it "defaults expires_in to 7 days" do
|
12
|
+
dedupe = RedisDedupe::Set.new(:redis, :key)
|
13
|
+
expect(dedupe.expires_in.to_i).to eq((Time.now + (7*24*60*60)).to_i)
|
14
|
+
end
|
15
|
+
|
16
|
+
it "optionally receives an expires_in time" do
|
17
|
+
dedupe = RedisDedupe::Set.new(:redis, :key, (Time.now + (7*24*60)).to_i)
|
18
|
+
expect(dedupe.expires_in.to_i).to eq((Time.now + (7*24*60)).to_i)
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
describe RedisDedupe::Set, "#check" do
|
23
|
+
it "prevents a block from yielding multiple times for the same member" do
|
24
|
+
dedupe1 = RedisDedupe::Set.new(MockRedis.new, 'spec_key:1')
|
25
|
+
dedupe2 = RedisDedupe::Set.new(MockRedis.new, 'spec_key:2')
|
26
|
+
|
27
|
+
@results = []
|
28
|
+
|
29
|
+
dedupe1.check('1') { @results << 'A' }
|
30
|
+
dedupe1.check('1') { @results << 'B' }
|
31
|
+
dedupe2.check('1') { @results << 'C' }
|
32
|
+
|
33
|
+
expect(@results).to eq(['A', 'C'])
|
34
|
+
end
|
35
|
+
|
36
|
+
it "sets the set to expire so it cleans up if the process never completes" do
|
37
|
+
redis = MockRedis.new
|
38
|
+
dedupe = RedisDedupe::Set.new(redis, 'spec_key:1', 10)
|
39
|
+
|
40
|
+
dedupe.check('1') { }
|
41
|
+
|
42
|
+
expect(redis.ttl 'spec_key:1').to be_within(1).of(10)
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
describe RedisDedupe::Set, "#finish" do
|
47
|
+
it "removes the set to free up memory" do
|
48
|
+
redis = MockRedis.new
|
49
|
+
dedupe = RedisDedupe::Set.new(redis, 'spec_key:1')
|
50
|
+
|
51
|
+
dedupe.check('1') { }
|
52
|
+
dedupe.finish
|
53
|
+
|
54
|
+
expect(redis.exists 'spec_key:1').to be(false)
|
55
|
+
end
|
56
|
+
end
|
data/spec/spec_helper.rb
ADDED
File without changes
|
data/tasks/rspec.rake
ADDED
metadata
ADDED
@@ -0,0 +1,120 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: redis_dedupe
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.2
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Andy Huynh
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-03-25 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: bundler
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.6'
|
20
|
+
type: :development
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.6'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: rake
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - ">="
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ">="
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rspec
|
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
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: mock_redis
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ">="
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
description: " This is a weak deduper to make things like bulk email run safer. It
|
70
|
+
is not a lock safe for financial/security needs because it uses a weak redis locking
|
71
|
+
pattern that can have race conditions. However, imagine a bulk email job that loops
|
72
|
+
over 100 users, and enqueues a background email for each user. If the job fails
|
73
|
+
at iteration 50, a retry would enqueue all the users again and many will receive
|
74
|
+
dupes. This would continue multiple times as the parent job continued to rerun.
|
75
|
+
By marking that a subjob has been enqueued, we can let that isolated job handle
|
76
|
+
its own failures, and the batch enqueue job can run multiple times without re-enqueueing
|
77
|
+
the same subjobs. "
|
78
|
+
email:
|
79
|
+
- andy4thehuynh@gmail.com
|
80
|
+
executables: []
|
81
|
+
extensions: []
|
82
|
+
extra_rdoc_files: []
|
83
|
+
files:
|
84
|
+
- ".gitignore"
|
85
|
+
- Gemfile
|
86
|
+
- LICENSE.txt
|
87
|
+
- README.md
|
88
|
+
- Rakefile
|
89
|
+
- lib/redis_dedupe.rb
|
90
|
+
- lib/redis_dedupe/version.rb
|
91
|
+
- redis_dedupe.gemspec
|
92
|
+
- spec/redis_dedupe_spec.rb
|
93
|
+
- spec/spec_helper.rb
|
94
|
+
- tasks/rspec.rake
|
95
|
+
homepage: ''
|
96
|
+
licenses:
|
97
|
+
- MIT
|
98
|
+
metadata: {}
|
99
|
+
post_install_message:
|
100
|
+
rdoc_options: []
|
101
|
+
require_paths:
|
102
|
+
- lib
|
103
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
104
|
+
requirements:
|
105
|
+
- - ">="
|
106
|
+
- !ruby/object:Gem::Version
|
107
|
+
version: '0'
|
108
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
109
|
+
requirements:
|
110
|
+
- - ">="
|
111
|
+
- !ruby/object:Gem::Version
|
112
|
+
version: '0'
|
113
|
+
requirements: []
|
114
|
+
rubyforge_project:
|
115
|
+
rubygems_version: 2.2.2
|
116
|
+
signing_key:
|
117
|
+
specification_version: 4
|
118
|
+
summary: A weak deduper to make things like bulk email run safer.
|
119
|
+
test_files: []
|
120
|
+
has_rdoc:
|