smart_s3_sync 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.
- checksums.yaml +7 -0
- data/Gemfile +4 -0
- data/Gemfile.lock +52 -0
- data/LICENSE.txt +22 -0
- data/README.md +29 -0
- data/Rakefile +1 -0
- data/bin/s5 +41 -0
- data/lib/smart_s3_sync.rb +35 -0
- data/lib/smart_s3_sync/file_table.rb +40 -0
- data/lib/smart_s3_sync/file_target.rb +110 -0
- data/lib/smart_s3_sync/version.rb +3 -0
- data/smart_s3_sync.gemspec +26 -0
- metadata +112 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 04cc107694aecec62f525ff7afd6f5b51610f39d
|
4
|
+
data.tar.gz: 31fbf52ab4201430ab60e81827dafca121bf468e
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 14ffb04946ac2294b21ea0641d4f67c6e490b4137760f9f332ad8984ac6d686256b5eb0861f96a55a3f212ee3831ef713816914cfb67f549182e56685f5995c3
|
7
|
+
data.tar.gz: feebb0f4f47a06cbc869588cc6a4c46226513c19f4eeb6d3e70994a4acfa870e72177d233a990e8a7d1e4b9086f57d65ceb50ef540373ed1eb5e74067b0866f2
|
data/Gemfile
ADDED
data/Gemfile.lock
ADDED
@@ -0,0 +1,52 @@
|
|
1
|
+
PATH
|
2
|
+
remote: .
|
3
|
+
specs:
|
4
|
+
smart_s3_sync (0.0.1)
|
5
|
+
fog
|
6
|
+
sqlite3
|
7
|
+
|
8
|
+
GEM
|
9
|
+
remote: https://rubygems.org/
|
10
|
+
specs:
|
11
|
+
builder (3.2.2)
|
12
|
+
excon (0.37.0)
|
13
|
+
fog (1.22.1)
|
14
|
+
fog-brightbox
|
15
|
+
fog-core (~> 1.22)
|
16
|
+
fog-json
|
17
|
+
ipaddress (~> 0.5)
|
18
|
+
nokogiri (~> 1.5, >= 1.5.11)
|
19
|
+
fog-brightbox (0.1.1)
|
20
|
+
fog-core (~> 1.22)
|
21
|
+
fog-json
|
22
|
+
inflecto
|
23
|
+
fog-core (1.22.0)
|
24
|
+
builder
|
25
|
+
excon (~> 0.33)
|
26
|
+
formatador (~> 0.2)
|
27
|
+
mime-types
|
28
|
+
net-scp (~> 1.1)
|
29
|
+
net-ssh (>= 2.1.3)
|
30
|
+
fog-json (1.0.0)
|
31
|
+
multi_json (~> 1.0)
|
32
|
+
formatador (0.2.5)
|
33
|
+
inflecto (0.0.2)
|
34
|
+
ipaddress (0.8.0)
|
35
|
+
mime-types (2.3)
|
36
|
+
mini_portile (0.6.0)
|
37
|
+
multi_json (1.10.1)
|
38
|
+
net-scp (1.2.1)
|
39
|
+
net-ssh (>= 2.6.5)
|
40
|
+
net-ssh (2.9.1)
|
41
|
+
nokogiri (1.6.2.1)
|
42
|
+
mini_portile (= 0.6.0)
|
43
|
+
rake (10.3.2)
|
44
|
+
sqlite3 (1.3.9)
|
45
|
+
|
46
|
+
PLATFORMS
|
47
|
+
ruby
|
48
|
+
|
49
|
+
DEPENDENCIES
|
50
|
+
bundler (~> 1.3)
|
51
|
+
rake
|
52
|
+
smart_s3_sync!
|
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2014 Chris Rhoden
|
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
|
+
# SmartS3Sync
|
2
|
+
|
3
|
+
TODO: Write a gem description
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
gem 'smart_s3_sync'
|
10
|
+
|
11
|
+
And then execute:
|
12
|
+
|
13
|
+
$ bundle
|
14
|
+
|
15
|
+
Or install it yourself as:
|
16
|
+
|
17
|
+
$ gem install smart_s3_sync
|
18
|
+
|
19
|
+
## Usage
|
20
|
+
|
21
|
+
TODO: Write usage instructions here
|
22
|
+
|
23
|
+
## Contributing
|
24
|
+
|
25
|
+
1. Fork it
|
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"
|
data/bin/s5
ADDED
@@ -0,0 +1,41 @@
|
|
1
|
+
#!/usr/bin/env ruby
|
2
|
+
|
3
|
+
require 'smart_s3_sync'
|
4
|
+
require 'uri'
|
5
|
+
|
6
|
+
def quit(message)
|
7
|
+
STDERR.puts message
|
8
|
+
exit 1
|
9
|
+
end
|
10
|
+
|
11
|
+
if ARGV.length != 2
|
12
|
+
quit "Usage: #{File.basename($0)} REMOTE_URI LOCAL_DIR"
|
13
|
+
end
|
14
|
+
|
15
|
+
remote_uri, local_dir = ARGV
|
16
|
+
|
17
|
+
remote_uri = URI.parse(remote_uri)
|
18
|
+
|
19
|
+
quit "Only s3 is currently supported" if remote_uri.scheme.downcase != 's3'
|
20
|
+
|
21
|
+
bucket = remote_uri.host
|
22
|
+
prefix = remote_uri.path.sub('/','')
|
23
|
+
|
24
|
+
if remote_uri.userinfo
|
25
|
+
access_key_id = URI.decode(remote_uri.user).to_s
|
26
|
+
access_key_secret = URI.decode(remote_uri.password).to_s
|
27
|
+
else
|
28
|
+
access_key_id = ENV['S3_ACCESS_KEY_ID']
|
29
|
+
access_key_secret = ENV['S3_SECRET_ACCESS_KEY']
|
30
|
+
end
|
31
|
+
|
32
|
+
if !(access_key_id && access_key_secret)
|
33
|
+
quit "S3_ACCESS_KEY_ID and S3_SECRET_ACCESS_KEY environment variables are required"
|
34
|
+
end
|
35
|
+
|
36
|
+
SmartS3Sync.sync(local_dir, bucket, {
|
37
|
+
provider: 'AWS',
|
38
|
+
aws_access_key_id: access_key_id,
|
39
|
+
aws_secret_access_key: access_key_secret,
|
40
|
+
endpoint: 'http://s3.amazonaws.com'
|
41
|
+
}, prefix)
|
@@ -0,0 +1,35 @@
|
|
1
|
+
require 'smart_s3_sync/version'
|
2
|
+
require 'smart_s3_sync/file_table'
|
3
|
+
require 'fog'
|
4
|
+
|
5
|
+
module SmartS3Sync
|
6
|
+
|
7
|
+
def self.sync(dir, remote_dir, connection_options, remote_prefix=nil)
|
8
|
+
table = FileTable.new(dir, remote_prefix)
|
9
|
+
|
10
|
+
bucket = Fog::Storage.new(connection_options).directories.
|
11
|
+
get(remote_dir, {:prefix => remote_prefix})
|
12
|
+
|
13
|
+
|
14
|
+
# Add all files in the cloud to our map.
|
15
|
+
bucket.files.each { |file| table.push(file) }
|
16
|
+
|
17
|
+
# And copy them to the right places
|
18
|
+
table.copy!(bucket)
|
19
|
+
|
20
|
+
# sweep through and remove all files not in the cloud
|
21
|
+
Dir[File.join(dir, '**/*')].each do |file|
|
22
|
+
if !File.directory?(file)
|
23
|
+
File.unlink(file) unless table.keep?(file)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
# and then all empty directories
|
28
|
+
Dir[File.join(dir, '**/*')].each do |file|
|
29
|
+
if File.directory?(file) && Dir.entries(file).length == 0
|
30
|
+
Dir.rmdir(file)
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|
34
|
+
|
35
|
+
end
|
@@ -0,0 +1,40 @@
|
|
1
|
+
require 'smart_s3_sync/file_target'
|
2
|
+
|
3
|
+
module SmartS3Sync
|
4
|
+
class FileTable
|
5
|
+
def initialize(root, prefix=nil)
|
6
|
+
@map = {} # map of hashes to file destinations
|
7
|
+
@files = [] # single list of files to keep
|
8
|
+
@root = File.expand_path(root) # root file destination
|
9
|
+
@prefix = prefix ? prefix.gsub(/(?:^\/)|(?:\/$)/,'') : ''
|
10
|
+
end
|
11
|
+
|
12
|
+
def push(fog_file)
|
13
|
+
digest = hash_key(fog_file) # pull cloud calculated hex digest from file
|
14
|
+
@map[digest] ||= FileTarget.new(digest, fog_file.key) # grab or create target
|
15
|
+
destination_filename = File.expand_path(strip_prefix(fog_file.key), @root) # calculate local path
|
16
|
+
@files.push destination_filename # add local path to global list of files to keep
|
17
|
+
@map[digest].add_destination(destination_filename) # and add local path to the target
|
18
|
+
end
|
19
|
+
|
20
|
+
def copy!(fog_dir)
|
21
|
+
@map.each do |(k, target)|
|
22
|
+
target.copy!(fog_dir)
|
23
|
+
end
|
24
|
+
end
|
25
|
+
|
26
|
+
def keep?(filename)
|
27
|
+
@files.include?(filename)
|
28
|
+
end
|
29
|
+
|
30
|
+
private
|
31
|
+
|
32
|
+
def hash_key(fog_file)
|
33
|
+
(fog_file.content_md5 || fog_file.etag).intern # these should be equivalent
|
34
|
+
end
|
35
|
+
|
36
|
+
def strip_prefix(key)
|
37
|
+
key.sub(/^#{@prefix}\/?/, '')
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
@@ -0,0 +1,110 @@
|
|
1
|
+
require 'tempfile'
|
2
|
+
|
3
|
+
module SmartS3Sync
|
4
|
+
class FileTarget
|
5
|
+
attr_reader :digest, :remote_filename, :local_source, :destinations
|
6
|
+
|
7
|
+
def initialize(digest, remote_filename)
|
8
|
+
@digest = digest
|
9
|
+
@remote_filename = remote_filename
|
10
|
+
@local_source = nil
|
11
|
+
@destinations = []
|
12
|
+
end
|
13
|
+
|
14
|
+
def add_destination(file)
|
15
|
+
unless destinations.include?(file)
|
16
|
+
# If we already have a local file with the right checksum,
|
17
|
+
# we don't add it to the list of destinations and instead
|
18
|
+
# mark it as a local source.
|
19
|
+
if File.exists?(file) && file_hash(file) == digest.to_s
|
20
|
+
puts "#{file} is up to date"
|
21
|
+
@local_source = file
|
22
|
+
else
|
23
|
+
destinations.push(file)
|
24
|
+
end
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
def copy!(fog_dir)
|
29
|
+
# If every copy in the cloud is already present, the
|
30
|
+
# number of destinations will be 0 - there is no work
|
31
|
+
# left to do.
|
32
|
+
if destinations.length > 0
|
33
|
+
if local_source.nil? # we prefer to not have to download
|
34
|
+
copy_from_fog(fog_dir)
|
35
|
+
else
|
36
|
+
copy_from_local(source)
|
37
|
+
end
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
private
|
42
|
+
|
43
|
+
def copy_from_fog(fog_dir)
|
44
|
+
puts "Downloading #{remote_filename}."
|
45
|
+
tries = 0
|
46
|
+
file = nil
|
47
|
+
begin
|
48
|
+
file = download(fog_dir) # basically, just try.
|
49
|
+
|
50
|
+
if file_hash(file.path) != digest.to_s
|
51
|
+
raise "Hash mismatch downloading #{remote_filename}"
|
52
|
+
end
|
53
|
+
|
54
|
+
copy_from_local(file.path) # with a copy locally, the job is the same
|
55
|
+
@local_source = destinations.shift # we now have a local copy!
|
56
|
+
rescue StandardError => e
|
57
|
+
if tries < 5
|
58
|
+
tries += 1
|
59
|
+
puts e
|
60
|
+
puts "retrying"
|
61
|
+
retry
|
62
|
+
else
|
63
|
+
raise e
|
64
|
+
end
|
65
|
+
ensure
|
66
|
+
file.close(true) unless file.nil?
|
67
|
+
end
|
68
|
+
end
|
69
|
+
|
70
|
+
def copy_from_local(source)
|
71
|
+
destinations.each do |dest|
|
72
|
+
FileUtils.mkdir_p(File.dirname(dest))
|
73
|
+
FileUtils.ln(source, dest, :force => true)
|
74
|
+
end
|
75
|
+
end
|
76
|
+
|
77
|
+
def file_hash(path)
|
78
|
+
Digest::MD5.file(path).hexdigest
|
79
|
+
end
|
80
|
+
|
81
|
+
def download(fog_dir)
|
82
|
+
file = Tempfile.new(digest.to_s)
|
83
|
+
done = 0
|
84
|
+
now = Time.now.to_i
|
85
|
+
|
86
|
+
fog_dir.files.get(remote_filename) do |chunk, left, total|
|
87
|
+
if (chunk.bytes.size + left == total) # fog might restart in the middle
|
88
|
+
file.rewind
|
89
|
+
if done !=0
|
90
|
+
puts " ERROR ... retrying"
|
91
|
+
done = 0
|
92
|
+
end
|
93
|
+
end
|
94
|
+
|
95
|
+
file.write chunk
|
96
|
+
(((1 - (left.to_f / total)) * 50).to_i - done).times do
|
97
|
+
done += 1
|
98
|
+
print "#"
|
99
|
+
end
|
100
|
+
if done == 50
|
101
|
+
done = total / 1048576.to_f
|
102
|
+
end
|
103
|
+
end
|
104
|
+
|
105
|
+
puts " #{((done / [Time.now.to_i - now, 0.5].max) * 100).to_i / 100.0} MB/s"
|
106
|
+
file.close
|
107
|
+
file
|
108
|
+
end
|
109
|
+
end
|
110
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'smart_s3_sync/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "smart_s3_sync"
|
8
|
+
spec.version = SmartS3Sync::VERSION
|
9
|
+
spec.authors = ["Chris Rhoden"]
|
10
|
+
spec.email = ["chris@prx.org"]
|
11
|
+
spec.description = %q{Intelligent syncing from Cloud providers when duplicate content abounds.}
|
12
|
+
spec.summary = %q{Intelligent syncing from Cloud providers when duplicate content abounds.}
|
13
|
+
spec.homepage = ""
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_dependency "fog"
|
22
|
+
spec.add_dependency "sqlite3"
|
23
|
+
|
24
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
25
|
+
spec.add_development_dependency "rake"
|
26
|
+
end
|
metadata
ADDED
@@ -0,0 +1,112 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: smart_s3_sync
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Chris Rhoden
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2014-06-27 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: fog
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - '>='
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '0'
|
20
|
+
type: :runtime
|
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: sqlite3
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - '>='
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0'
|
34
|
+
type: :runtime
|
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: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - ~>
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.3'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ~>
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.3'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
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: Intelligent syncing from Cloud providers when duplicate content abounds.
|
70
|
+
email:
|
71
|
+
- chris@prx.org
|
72
|
+
executables:
|
73
|
+
- s5
|
74
|
+
extensions: []
|
75
|
+
extra_rdoc_files: []
|
76
|
+
files:
|
77
|
+
- Gemfile
|
78
|
+
- Gemfile.lock
|
79
|
+
- LICENSE.txt
|
80
|
+
- README.md
|
81
|
+
- Rakefile
|
82
|
+
- bin/s5
|
83
|
+
- lib/smart_s3_sync.rb
|
84
|
+
- lib/smart_s3_sync/file_table.rb
|
85
|
+
- lib/smart_s3_sync/file_target.rb
|
86
|
+
- lib/smart_s3_sync/version.rb
|
87
|
+
- smart_s3_sync.gemspec
|
88
|
+
homepage: ''
|
89
|
+
licenses:
|
90
|
+
- MIT
|
91
|
+
metadata: {}
|
92
|
+
post_install_message:
|
93
|
+
rdoc_options: []
|
94
|
+
require_paths:
|
95
|
+
- lib
|
96
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
97
|
+
requirements:
|
98
|
+
- - '>='
|
99
|
+
- !ruby/object:Gem::Version
|
100
|
+
version: '0'
|
101
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
102
|
+
requirements:
|
103
|
+
- - '>='
|
104
|
+
- !ruby/object:Gem::Version
|
105
|
+
version: '0'
|
106
|
+
requirements: []
|
107
|
+
rubyforge_project:
|
108
|
+
rubygems_version: 2.1.11
|
109
|
+
signing_key:
|
110
|
+
specification_version: 4
|
111
|
+
summary: Intelligent syncing from Cloud providers when duplicate content abounds.
|
112
|
+
test_files: []
|