rivalry 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +17 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.markdown +53 -0
- data/Rakefile +1 -0
- data/bin/rivalry +11 -0
- data/lib/rivalry.rb +27 -0
- data/lib/rivalry/base.rb +5 -0
- data/lib/rivalry/display.rb +86 -0
- data/lib/rivalry/file_path.rb +6 -0
- data/lib/rivalry/files_with_data.rb +7 -0
- data/lib/rivalry/find_files.rb +63 -0
- data/lib/rivalry/hash_files.rb +32 -0
- data/lib/rivalry/scanner.rb +57 -0
- data/lib/rivalry/version.rb +3 -0
- data/rivalry.gemspec +19 -0
- metadata +63 -0
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 Anthony Cook
|
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.markdown
ADDED
@@ -0,0 +1,53 @@
|
|
1
|
+
# Rivalry
|
2
|
+
|
3
|
+
Rivalry is the (fast!) duplicate file finder written in Ruby.
|
4
|
+
|
5
|
+
It supports specifically targeting audio and image files and ignores SCM folders such as `.git` and `.hg` by default.
|
6
|
+
|
7
|
+
## Installation
|
8
|
+
|
9
|
+
Using rubygems just:
|
10
|
+
|
11
|
+
$ gem install rivalry
|
12
|
+
|
13
|
+
If you wish to use Rivalry's functionality inside your app your can instead add this line to your application's Gemfile:
|
14
|
+
|
15
|
+
gem 'rivalry'
|
16
|
+
|
17
|
+
And then execute:
|
18
|
+
|
19
|
+
$ bundle
|
20
|
+
|
21
|
+
## Usage
|
22
|
+
|
23
|
+
On the commandline the most basic usage is:
|
24
|
+
|
25
|
+
```bash
|
26
|
+
$ rivalry ~/directory/with/duplicates
|
27
|
+
```
|
28
|
+
|
29
|
+
It will display the duplicate files on the screen, which can then be grepped or otherwise used to remove the unwanted duplicates.
|
30
|
+
|
31
|
+
Example output:
|
32
|
+
|
33
|
+
```bash
|
34
|
+
$ rivalry ..
|
35
|
+
Scanning all files...
|
36
|
+
-- Total Size : 173 MB
|
37
|
+
-- Total Count : 95 files
|
38
|
+
-- Similar : 34 files with the same size
|
39
|
+
|
40
|
+
Determining duplicates...
|
41
|
+
-- Dupes Count : 2 files
|
42
|
+
|
43
|
+
/Users/acook/Dropbox/Projects/Negutyv Xeiro/Audio/Cytokine Storm/Negutyv Xeiro - Cytokine Storm [Mørch Mix].mp3
|
44
|
+
/Users/acook/Dropbox/Projects/Negutyv Xeiro/Audio/Cytokine Storm/alexcyto/Cytokine Storm m.mp3
|
45
|
+
```
|
46
|
+
|
47
|
+
## Contributing
|
48
|
+
|
49
|
+
1. Fork it
|
50
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
51
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
52
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
53
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require "bundler/gem_tasks"
|
data/bin/rivalry
ADDED
data/lib/rivalry.rb
ADDED
@@ -0,0 +1,27 @@
|
|
1
|
+
require 'pry' rescue LoadError
|
2
|
+
|
3
|
+
require 'rivalry/version'
|
4
|
+
require 'rivalry/display'
|
5
|
+
require 'rivalry/base'
|
6
|
+
require 'rivalry/scanner'
|
7
|
+
require 'rivalry/file_path'
|
8
|
+
require 'rivalry/files_with_data'
|
9
|
+
require 'rivalry/find_files'
|
10
|
+
require 'rivalry/hash_files'
|
11
|
+
|
12
|
+
module Rivalry
|
13
|
+
extend Display
|
14
|
+
module_function
|
15
|
+
|
16
|
+
def run args
|
17
|
+
path = args.first || usage
|
18
|
+
|
19
|
+
scanner = Rivalry::Scanner.new path
|
20
|
+
files = scanner.scan
|
21
|
+
|
22
|
+
out
|
23
|
+
files.each do |file|
|
24
|
+
puts file.to_s
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
data/lib/rivalry/base.rb
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
module Rivalry
|
2
|
+
module Display
|
3
|
+
def self.included object
|
4
|
+
unless $silent then
|
5
|
+
object.send :include, Methods
|
6
|
+
else
|
7
|
+
object.send :include, NoopMethods
|
8
|
+
end
|
9
|
+
end
|
10
|
+
|
11
|
+
def self.extended object
|
12
|
+
unless $silent then
|
13
|
+
object.send :extend, Methods
|
14
|
+
else
|
15
|
+
object.send :extend, NoopMethods
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
module Methods
|
20
|
+
|
21
|
+
def usage
|
22
|
+
puts "usage: #{$0} path/to/search/for/duplicates"
|
23
|
+
exit 1
|
24
|
+
end
|
25
|
+
|
26
|
+
def out text = ''
|
27
|
+
if $verbose then
|
28
|
+
puts text
|
29
|
+
else
|
30
|
+
puts text[0..(width - 1)]
|
31
|
+
end
|
32
|
+
end
|
33
|
+
|
34
|
+
def progress type, file, count = nil, total = nil
|
35
|
+
if count && total then
|
36
|
+
tally = " (#{count}/#{total})"
|
37
|
+
elsif count then
|
38
|
+
tally = " (#{count})"
|
39
|
+
else
|
40
|
+
tally = ''
|
41
|
+
end
|
42
|
+
|
43
|
+
text = "-- #{type}#{tally}: #{file}"
|
44
|
+
|
45
|
+
if $verbose then
|
46
|
+
puts text
|
47
|
+
else
|
48
|
+
clear_line
|
49
|
+
print text[0..(width - 1)]
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
def clear_line
|
54
|
+
clear_line = "\e[2K"
|
55
|
+
start_of_line = "\e[0G"
|
56
|
+
print start_of_line, clear_line
|
57
|
+
end
|
58
|
+
|
59
|
+
def width
|
60
|
+
tiocgwinsz = 0x40087468
|
61
|
+
str = [0, 0, 0, 0].pack('SSSS')
|
62
|
+
if $stdin.ioctl(tiocgwinsz, str) >= 0 then
|
63
|
+
str.unpack('SSSS')[1]
|
64
|
+
else
|
65
|
+
80
|
66
|
+
end
|
67
|
+
end
|
68
|
+
|
69
|
+
BYTE_UNITS =[[1073741824, 'GB'], [1048576, 'MB'], [1024, 'KB'], [-1, 'B']]
|
70
|
+
|
71
|
+
def humanize bytes
|
72
|
+
unit = BYTE_UNITS.find{|u| bytes > u[0] }
|
73
|
+
"#{bytes / unit[0]} #{unit[1]}"
|
74
|
+
end
|
75
|
+
|
76
|
+
end
|
77
|
+
|
78
|
+
module NoopMethods
|
79
|
+
def noop; end
|
80
|
+
|
81
|
+
Methods.instance_methods(false).each do |method|
|
82
|
+
alias_method method, :noop
|
83
|
+
end
|
84
|
+
end
|
85
|
+
end
|
86
|
+
end
|
@@ -0,0 +1,63 @@
|
|
1
|
+
module Rivalry
|
2
|
+
class FindFiles < Base
|
3
|
+
def initialize pathname, do_want = {}, do_not_want = {}
|
4
|
+
@pathname = pathname
|
5
|
+
@do_want = do_want
|
6
|
+
@do_not_want = do_not_want
|
7
|
+
end
|
8
|
+
attr :pathname, :do_want, :do_not_want, :count, :size
|
9
|
+
|
10
|
+
def find
|
11
|
+
self.size = 0
|
12
|
+
self.count = 0
|
13
|
+
|
14
|
+
files_with_sizes = FilesWithData.new
|
15
|
+
|
16
|
+
pathname.find do |file|
|
17
|
+
|
18
|
+
if file.directory? then
|
19
|
+
if do_not_want? file then
|
20
|
+
progress 'SKIP DIR', file
|
21
|
+
Find.prune
|
22
|
+
else
|
23
|
+
progress 'DIRECTORY', file
|
24
|
+
end
|
25
|
+
elsif valid? file then
|
26
|
+
if do_want? file then
|
27
|
+
progress 'FILE', file
|
28
|
+
|
29
|
+
file_size = file.size
|
30
|
+
|
31
|
+
files_with_sizes[file_size] << file
|
32
|
+
|
33
|
+
self.size += file_size
|
34
|
+
self.count += 1
|
35
|
+
else
|
36
|
+
progress 'SKIP FILE', file
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
end
|
41
|
+
|
42
|
+
files_with_sizes
|
43
|
+
end
|
44
|
+
|
45
|
+
protected
|
46
|
+
|
47
|
+
attr_writer :count, :size
|
48
|
+
|
49
|
+
def do_want? path
|
50
|
+
extension = File.extname path
|
51
|
+
do_want.find{|name, pattern| extension =~ pattern} && true
|
52
|
+
end
|
53
|
+
|
54
|
+
def do_not_want? path
|
55
|
+
basename = File.basename path
|
56
|
+
do_not_want.find{|name, pattern| basename =~ pattern} && true
|
57
|
+
end
|
58
|
+
|
59
|
+
def valid? file
|
60
|
+
file.exists?
|
61
|
+
end
|
62
|
+
end
|
63
|
+
end
|
@@ -0,0 +1,32 @@
|
|
1
|
+
module Rivalry
|
2
|
+
class HashFiles < Base
|
3
|
+
def initialize similar_files
|
4
|
+
@similar_files = similar_files
|
5
|
+
end
|
6
|
+
attr :similar_files
|
7
|
+
|
8
|
+
def hash
|
9
|
+
out
|
10
|
+
out "Determining duplicates..."
|
11
|
+
|
12
|
+
similar_count = 0
|
13
|
+
file_hashes = FilesWithData.new
|
14
|
+
|
15
|
+
similar_files.each do |file|
|
16
|
+
similar_count += 1
|
17
|
+
|
18
|
+
progress 'HASHING', file, similar_count, total_similar
|
19
|
+
|
20
|
+
hash = Digest::SHA256.file(file).to_s
|
21
|
+
|
22
|
+
file_hashes[hash] << file
|
23
|
+
end
|
24
|
+
|
25
|
+
file_hashes
|
26
|
+
end
|
27
|
+
|
28
|
+
def total_similar
|
29
|
+
similar_files.length
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
@@ -0,0 +1,57 @@
|
|
1
|
+
require 'find'
|
2
|
+
require 'pathname'
|
3
|
+
require 'digest'
|
4
|
+
|
5
|
+
module Rivalry
|
6
|
+
class Scanner < Base
|
7
|
+
def initialize pathname
|
8
|
+
@pathname = FilePath.new File.expand_path(pathname)
|
9
|
+
end
|
10
|
+
attr :pathname
|
11
|
+
|
12
|
+
def scan
|
13
|
+
|
14
|
+
out "Scanning all files..."
|
15
|
+
|
16
|
+
finder = FindFiles.new pathname, wants, ignores
|
17
|
+
files_with_sizes = finder.find
|
18
|
+
|
19
|
+
similar_files = dedup files_with_sizes
|
20
|
+
|
21
|
+
clear_line
|
22
|
+
out "-- Total Size : #{humanize finder.size}"
|
23
|
+
out "-- Total Count : #{finder.count} files"
|
24
|
+
out "-- Similar : #{similar_files.length} files with the same size"
|
25
|
+
|
26
|
+
hasher = HashFiles.new similar_files
|
27
|
+
files_with_hashes = hasher.hash
|
28
|
+
|
29
|
+
duplicate_files = dedup files_with_hashes
|
30
|
+
|
31
|
+
clear_line
|
32
|
+
out "-- Dupes Count : #{duplicate_files.length} files"
|
33
|
+
|
34
|
+
duplicate_files
|
35
|
+
end
|
36
|
+
|
37
|
+
def dedup files_with_data
|
38
|
+
files_with_data.map do |_, file_list|
|
39
|
+
file_list if file_list && file_list.length > 1
|
40
|
+
end.flatten.compact
|
41
|
+
end
|
42
|
+
|
43
|
+
def ignores
|
44
|
+
{
|
45
|
+
dir: /^\.$/,
|
46
|
+
scm: /^\.(git|hg|svn|gitkeep)$/
|
47
|
+
}
|
48
|
+
end
|
49
|
+
|
50
|
+
def wants
|
51
|
+
{
|
52
|
+
audio: /^\.(mp3|ogg|flac|wav|aiff|mid)$/i,
|
53
|
+
images: /^\.(png|jpg|gif|bmp|tga|jpeg|tif|tiff)/i
|
54
|
+
}
|
55
|
+
end
|
56
|
+
end
|
57
|
+
end
|
data/rivalry.gemspec
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'rivalry/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |gem|
|
7
|
+
gem.name = "rivalry"
|
8
|
+
gem.version = Rivalry::VERSION
|
9
|
+
gem.authors = ["Anthony Cook"]
|
10
|
+
gem.email = ["anthonymichaelcook@gmail.com"]
|
11
|
+
gem.description = %q{The (fast!) duplicate file finder for Ruby! Supports media file and ignoring SCM directories.}
|
12
|
+
gem.summary = %q{The (fast!) duplicate file finder for Ruby!}
|
13
|
+
gem.homepage = "https://github.com/acook/rivalry#readme"
|
14
|
+
|
15
|
+
gem.files = `git ls-files`.split($/)
|
16
|
+
gem.executables = gem.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
|
17
|
+
gem.test_files = gem.files.grep(%r{^(test|spec|features)/})
|
18
|
+
gem.require_paths = ["lib"]
|
19
|
+
end
|
metadata
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rivalry
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Anthony Cook
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2013-01-27 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: The (fast!) duplicate file finder for Ruby! Supports media file and ignoring
|
15
|
+
SCM directories.
|
16
|
+
email:
|
17
|
+
- anthonymichaelcook@gmail.com
|
18
|
+
executables:
|
19
|
+
- rivalry
|
20
|
+
extensions: []
|
21
|
+
extra_rdoc_files: []
|
22
|
+
files:
|
23
|
+
- .gitignore
|
24
|
+
- Gemfile
|
25
|
+
- LICENSE.txt
|
26
|
+
- README.markdown
|
27
|
+
- Rakefile
|
28
|
+
- bin/rivalry
|
29
|
+
- lib/rivalry.rb
|
30
|
+
- lib/rivalry/base.rb
|
31
|
+
- lib/rivalry/display.rb
|
32
|
+
- lib/rivalry/file_path.rb
|
33
|
+
- lib/rivalry/files_with_data.rb
|
34
|
+
- lib/rivalry/find_files.rb
|
35
|
+
- lib/rivalry/hash_files.rb
|
36
|
+
- lib/rivalry/scanner.rb
|
37
|
+
- lib/rivalry/version.rb
|
38
|
+
- rivalry.gemspec
|
39
|
+
homepage: https://github.com/acook/rivalry#readme
|
40
|
+
licenses: []
|
41
|
+
post_install_message:
|
42
|
+
rdoc_options: []
|
43
|
+
require_paths:
|
44
|
+
- lib
|
45
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
46
|
+
none: false
|
47
|
+
requirements:
|
48
|
+
- - ! '>='
|
49
|
+
- !ruby/object:Gem::Version
|
50
|
+
version: '0'
|
51
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
52
|
+
none: false
|
53
|
+
requirements:
|
54
|
+
- - ! '>='
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: '0'
|
57
|
+
requirements: []
|
58
|
+
rubyforge_project:
|
59
|
+
rubygems_version: 1.8.24
|
60
|
+
signing_key:
|
61
|
+
specification_version: 3
|
62
|
+
summary: The (fast!) duplicate file finder for Ruby!
|
63
|
+
test_files: []
|