dimsum 0.0.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE +22 -0
- data/README.md +31 -0
- data/Rakefile +2 -0
- data/bin/dimsum +39 -0
- data/dimsum.gemspec +19 -0
- data/lib/dimsum.rb +5 -0
- data/lib/dimsum/version.rb +3 -0
- metadata +66 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2012 Aaron Olson, Steven Noble, Camilo Lopez
|
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 +1,31 @@
|
|
1
|
+
# Dimsum
|
2
|
+
|
3
|
+
Dimsum takes a file and a number of lines and prints a reservoir sample of the
|
4
|
+
file to stadard output
|
5
|
+
|
6
|
+
## Installation
|
7
|
+
|
8
|
+
Add this line to your application's Gemfile:
|
9
|
+
|
10
|
+
gem 'dimsum'
|
11
|
+
|
12
|
+
And then execute:
|
13
|
+
|
14
|
+
$ bundle
|
15
|
+
|
16
|
+
Or install it yourself as:
|
17
|
+
|
18
|
+
$ gem install dimsum
|
19
|
+
|
20
|
+
## Usage
|
21
|
+
```sh
|
22
|
+
sample.rb filename
|
23
|
+
-n, --number [Fixnum]
|
24
|
+
```
|
25
|
+
## Contributing
|
26
|
+
|
27
|
+
1. Fork it
|
28
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
29
|
+
3. Commit your changes (`git commit -am 'Added some feature'`)
|
30
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
31
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/bin/dimsum
ADDED
@@ -0,0 +1,39 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'optparse'
|
4
|
+
|
5
|
+
options = {}
|
6
|
+
|
7
|
+
OptionParser.new do |opts|
|
8
|
+
opts.banner = "Usage: sample.rb [options]"
|
9
|
+
opts.on("-n [Fixnum]", "--number [Fixnum]", "") do |n|
|
10
|
+
options[:lines] = n
|
11
|
+
end
|
12
|
+
end.parse!
|
13
|
+
|
14
|
+
filename = ARGV[0]
|
15
|
+
lines = options[:lines].to_i
|
16
|
+
raise ArgumentError, "The filename is required" unless filename
|
17
|
+
|
18
|
+
file_size = `wc -l #{filename}`.strip.to_i
|
19
|
+
|
20
|
+
last_2 = `tail -c2 #{filename}`
|
21
|
+
if last_2 == "\n\n"
|
22
|
+
file_size -= 1
|
23
|
+
end
|
24
|
+
|
25
|
+
random = Random.new
|
26
|
+
|
27
|
+
File.open(filename, "r").lines do |line|
|
28
|
+
if file_size == 0
|
29
|
+
next
|
30
|
+
end
|
31
|
+
r = random.rand(0 .. file_size - 1)
|
32
|
+
if r < lines
|
33
|
+
STDOUT.print line
|
34
|
+
STDOUT.flush
|
35
|
+
lines -= 1
|
36
|
+
end
|
37
|
+
file_size -= 1
|
38
|
+
end
|
39
|
+
|
data/dimsum.gemspec
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
require File.expand_path('../lib/dimsum/version', __FILE__)
|
3
|
+
|
4
|
+
Gem::Specification.new do |gem|
|
5
|
+
gem.authors = ["Aaron Olson", "Steven Noble", "Camilo Lopez"]
|
6
|
+
gem.email = ["aaron.olson@shopify.com", "steven.noble@shopify.com", "camilo.lopez@shopify.com"]
|
7
|
+
gem.description = %q{dimsum is a very simple ruby script that performs reservoir sampling on the input file.}
|
8
|
+
gem.summary = %q{reservoir sampling}
|
9
|
+
gem.homepage = ""
|
10
|
+
|
11
|
+
gem.files = `git ls-files`.split($\)
|
12
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
13
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
14
|
+
gem.name = "dimsum"
|
15
|
+
gem.require_paths = ["lib"]
|
16
|
+
gem.bindir = 'bin'
|
17
|
+
gem.executables << 'dimsum'
|
18
|
+
gem.version = Dimsum::VERSION
|
19
|
+
end
|
data/lib/dimsum.rb
ADDED
metadata
ADDED
@@ -0,0 +1,66 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: dimsum
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Aaron Olson
|
9
|
+
- Steven Noble
|
10
|
+
- Camilo Lopez
|
11
|
+
autorequire:
|
12
|
+
bindir: bin
|
13
|
+
cert_chain: []
|
14
|
+
date: 2012-06-30 00:00:00.000000000 Z
|
15
|
+
dependencies: []
|
16
|
+
description: dimsum is a very simple ruby script that performs reservoir sampling
|
17
|
+
on the input file.
|
18
|
+
email:
|
19
|
+
- aaron.olson@shopify.com
|
20
|
+
- steven.noble@shopify.com
|
21
|
+
- camilo.lopez@shopify.com
|
22
|
+
executables:
|
23
|
+
- dimsum
|
24
|
+
extensions: []
|
25
|
+
extra_rdoc_files: []
|
26
|
+
files:
|
27
|
+
- .gitignore
|
28
|
+
- Gemfile
|
29
|
+
- LICENSE
|
30
|
+
- README.md
|
31
|
+
- Rakefile
|
32
|
+
- bin/dimsum
|
33
|
+
- dimsum.gemspec
|
34
|
+
- lib/dimsum.rb
|
35
|
+
- lib/dimsum/version.rb
|
36
|
+
homepage: ''
|
37
|
+
licenses: []
|
38
|
+
post_install_message:
|
39
|
+
rdoc_options: []
|
40
|
+
require_paths:
|
41
|
+
- lib
|
42
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
43
|
+
none: false
|
44
|
+
requirements:
|
45
|
+
- - ! '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
segments:
|
49
|
+
- 0
|
50
|
+
hash: -1291815841305852171
|
51
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
52
|
+
none: false
|
53
|
+
requirements:
|
54
|
+
- - ! '>='
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '0'
|
57
|
+
segments:
|
58
|
+
- 0
|
59
|
+
hash: -1291815841305852171
|
60
|
+
requirements: []
|
61
|
+
rubyforge_project:
|
62
|
+
rubygems_version: 1.8.11
|
63
|
+
signing_key:
|
64
|
+
specification_version: 3
|
65
|
+
summary: reservoir sampling
|
66
|
+
test_files: []
|