github-archive 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 +18 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +22 -0
- data/README.md +46 -0
- data/Rakefile +3 -0
- data/bin/github-archive +135 -0
- data/github-archive.gemspec +34 -0
- data/lib/github/archive.rb +29 -0
- data/lib/github/archive/archived_url.rb +9 -0
- data/lib/github/archive/connections.rb +85 -0
- data/lib/github/archive/create_archive.rb +30 -0
- data/lib/github/archive/destroy_archive.rb +17 -0
- data/lib/github/archive/event.rb +47 -0
- data/lib/github/archive/stat_collector.rb +39 -0
- data/lib/github/archive/version.rb +5 -0
- data/spec/factories/archived_url_factory.rb +6 -0
- data/spec/factories/event_factory.rb +5 -0
- data/spec/github/archive/archived_url_spec.rb +20 -0
- data/spec/github/archive/event_spec.rb +117 -0
- data/spec/github/archive/stat_collector_spec.rb +11 -0
- data/spec/spec_helper.rb +12 -0
- metadata +241 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 719058d828ae6865a67cbbff5e5cda3279e45b56
|
4
|
+
data.tar.gz: 97cf65cfe828103a18a85e10aee9927ee72c03bf
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 3c6d94565edff148cc3615e1e797419cfb49f5abff894b418fd4493c068ed40f853d15b67b5b754188888f360c07a6f2aa0356052ed9aaa594577bbf81b15f55
|
7
|
+
data.tar.gz: 62c802e31a2c62f82429416319104663c44c2e0abb61432365dbd53a0ba6273a2d7cd5fb44083154dfba4fab170dc1b529d05b423b8505d7bc5b8c63e7439947
|
data/.gitignore
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
Copyright (c) 2013 cparratto
|
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 +1,46 @@
|
|
1
|
+
# Github Archive
|
2
|
+
|
3
|
+
A command line utility for concurrent processing and management of github event archives.
|
4
|
+
|
5
|
+
## Dependencies
|
6
|
+
|
7
|
+
1. MYSQL (For storing replica data)
|
8
|
+
2. REDIS (For processing queue persistence)
|
9
|
+
|
10
|
+
## Installation
|
11
|
+
|
12
|
+
On a OSX:
|
13
|
+
|
14
|
+
$ brew install mysql (Follow instructions for launching)
|
15
|
+
$ brew install redis (Follow instructions for launching)
|
16
|
+
|
17
|
+
Get the gem:
|
18
|
+
|
19
|
+
$ gem install github-archive
|
20
|
+
|
21
|
+
## Setup Redis for Resque
|
22
|
+
|
23
|
+
$ github-archive setup_mysql --database=DATABASE --server=SERVER --username=USERNAME
|
24
|
+
$ github-archive setup_redis --port=PORT --server=SERVER
|
25
|
+
|
26
|
+
## Launch workers for processing github data
|
27
|
+
|
28
|
+
$ github-archive process_archives --proc-count=PROC_COUNT
|
29
|
+
|
30
|
+
## Get Stats
|
31
|
+
|
32
|
+
$ github-archive gh_repo_stats --after=AFTER --before=BEFORE --event=EVENT -n=N
|
33
|
+
|
34
|
+
Example:
|
35
|
+
|
36
|
+
$ github-archive gh_repo_stats --event=WatchEvent --after=2012-12-10T04:05:06+07:00 --before=2012-12-11T04:05:06+07:00 -n=20
|
37
|
+
|
38
|
+
##
|
39
|
+
|
40
|
+
## Contributing
|
41
|
+
|
42
|
+
1. Fork it
|
43
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
44
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
45
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
46
|
+
5. Create new Pull Request
|
data/Rakefile
ADDED
data/bin/github-archive
ADDED
@@ -0,0 +1,135 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'thor'
|
3
|
+
require 'thor/rake_compat'
|
4
|
+
require 'bundler'
|
5
|
+
require 'github/archive'
|
6
|
+
require 'resque/tasks'
|
7
|
+
|
8
|
+
module Github
|
9
|
+
module Archive
|
10
|
+
class CLI < Thor
|
11
|
+
Bundler::GemHelper.install_tasks
|
12
|
+
|
13
|
+
desc 'check_for_errors', "Checks resque for processing errors."
|
14
|
+
def check_for_errors
|
15
|
+
Rake::Task['resque:failures:sort'].execute
|
16
|
+
end
|
17
|
+
|
18
|
+
desc 'process_archives', "Starts resque work processes."
|
19
|
+
method_option :proc_count, :type => :string, :default => '4', :required => true
|
20
|
+
def process_archives
|
21
|
+
ENV['QUEUE'] = StatCollector.queue.to_s
|
22
|
+
ENV['COUNT'] = options[:proc_count]
|
23
|
+
Rake::Task['resque:workers'].execute
|
24
|
+
end
|
25
|
+
|
26
|
+
desc "setup_mysql", "Sets connection params for mysql."
|
27
|
+
method_option :username, :type => :string, :default => 'root', :required => true
|
28
|
+
method_option :password, :type => :string, :default => ''
|
29
|
+
method_option :server, :type => :string, :default => 'localhost', :required => true
|
30
|
+
method_option :database, :type => :string, :default => 'github-archive', :required => true
|
31
|
+
def setup_mysql
|
32
|
+
Connections.config_mysql(options[:server],
|
33
|
+
options[:username],
|
34
|
+
options[:password],
|
35
|
+
options[:database])
|
36
|
+
|
37
|
+
Connections.write_settings
|
38
|
+
end
|
39
|
+
|
40
|
+
desc "create_archive", "Creates all Tables"
|
41
|
+
def create_archive
|
42
|
+
CreateArchive.do
|
43
|
+
end
|
44
|
+
|
45
|
+
desc "destroy_archive", "Destroys all Tables"
|
46
|
+
def destroy_archive
|
47
|
+
DestroyArchive.do
|
48
|
+
end
|
49
|
+
|
50
|
+
desc "setup_redis", "Sets connection params for redis."
|
51
|
+
method_option :server, :type => :string, :default => 'localhost', :required => true
|
52
|
+
method_option :port, :type => :string, :default => '6379', :required => true
|
53
|
+
method_option :password, :type => :string, :default => nil
|
54
|
+
def setup_redis
|
55
|
+
Connections.config_redis(options[:server],
|
56
|
+
options[:port],
|
57
|
+
options[:password])
|
58
|
+
|
59
|
+
Connections.write_settings
|
60
|
+
end
|
61
|
+
|
62
|
+
|
63
|
+
desc "gh_repo_stats", "Lists the most active repositories for a given time range."
|
64
|
+
method_option :after, :type => :string, :default => '2013-02-03T04:05:06+07:00', :required => true
|
65
|
+
method_option :before, :type => :string, :default => '2013-03-03T04:05:06+07:00', :required => true
|
66
|
+
method_option :event, :type => :string, :default => 'GollumEvent', :required => true
|
67
|
+
method_option :n, :type => :numeric, :default => 100, :required => true
|
68
|
+
def gh_repo_stats
|
69
|
+
date_from = build_date_time(options[:after])
|
70
|
+
date_to = build_date_time(options[:before])
|
71
|
+
date_array = (date_from.to_date..date_to.to_date).to_a
|
72
|
+
urls = build_url_array_from_dates(date_array)
|
73
|
+
|
74
|
+
if urls.nil?
|
75
|
+
puts "Bad time range. Please enter a correct time range."
|
76
|
+
exit 0
|
77
|
+
end
|
78
|
+
|
79
|
+
hour_count = urls.count
|
80
|
+
|
81
|
+
urls.each do |url|
|
82
|
+
archived = ArchivedUrl.where(url: url).first
|
83
|
+
|
84
|
+
if archived && archived.finished_processing
|
85
|
+
hour_count -= 1
|
86
|
+
elsif archived.nil?
|
87
|
+
ArchivedUrl.create(url: url, finished_processing: false)
|
88
|
+
Resque.enqueue(StatCollector, url)
|
89
|
+
end
|
90
|
+
end
|
91
|
+
|
92
|
+
if hour_count == 0
|
93
|
+
results = Event.results_for_range_and_type(date_from..date_to,
|
94
|
+
options[:event],
|
95
|
+
options[:n])
|
96
|
+
|
97
|
+
results.each do |url, count|
|
98
|
+
puts "#{url} - #{count} \n"
|
99
|
+
end
|
100
|
+
else
|
101
|
+
puts "You still need #{hour_count} hours of data to calculate this.."
|
102
|
+
end
|
103
|
+
end
|
104
|
+
|
105
|
+
desc "event_count", "Gets the current event count"
|
106
|
+
def event_count
|
107
|
+
puts Event.count
|
108
|
+
end
|
109
|
+
|
110
|
+
private
|
111
|
+
|
112
|
+
def build_date_time(time_str)
|
113
|
+
begin
|
114
|
+
date_time = DateTime.strptime(time_str, '%Y-%m-%dT%H:%M:%S%z')
|
115
|
+
return date_time
|
116
|
+
rescue
|
117
|
+
puts "Bad time format for #{time_str}. Please use something like 2013-02-03T04:05:06+07:00"
|
118
|
+
exit 0
|
119
|
+
end
|
120
|
+
end
|
121
|
+
|
122
|
+
def build_url_array_from_dates(date_array)
|
123
|
+
hour_array = (0..23).to_a
|
124
|
+
date_array.collect { |date|
|
125
|
+
hour_array.collect { |hour|
|
126
|
+
"http://data.githubarchive.org/#{date.strftime("%Y-%m-%d")}-#{hour}.json.gz"
|
127
|
+
}
|
128
|
+
}.flatten!
|
129
|
+
end
|
130
|
+
|
131
|
+
end
|
132
|
+
end
|
133
|
+
end
|
134
|
+
|
135
|
+
Github::Archive::CLI.start
|
@@ -0,0 +1,34 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'github/archive/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "github-archive"
|
8
|
+
spec.version = Github::Archive::VERSION
|
9
|
+
spec.authors = ["cparratto"]
|
10
|
+
spec.email = ["cparratto@gmail.com"]
|
11
|
+
spec.description = %q{Github Archive}
|
12
|
+
spec.summary = %q{A command line utility for concurrent processing and management of github event archives.}
|
13
|
+
spec.homepage = "https://github.com/cparratto/github-archive"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files`.split($/)
|
17
|
+
spec.executables = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
|
18
|
+
spec.test_files = spec.files.grep(%r{^(spec|features)/})
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_dependency 'thor'
|
22
|
+
spec.add_dependency 'mysql'
|
23
|
+
spec.add_dependency 'activerecord'
|
24
|
+
spec.add_dependency 'yajl-ruby'
|
25
|
+
spec.add_dependency 'resque'
|
26
|
+
|
27
|
+
spec.add_development_dependency "bundler", "~> 1.3"
|
28
|
+
spec.add_development_dependency "rake"
|
29
|
+
spec.add_development_dependency "rspec"
|
30
|
+
spec.add_development_dependency "factory_girl"
|
31
|
+
spec.add_development_dependency 'database_cleaner'
|
32
|
+
spec.add_development_dependency "mocha"
|
33
|
+
spec.add_development_dependency "pry"
|
34
|
+
end
|
@@ -0,0 +1,29 @@
|
|
1
|
+
require "github/archive/version"
|
2
|
+
require 'mysql'
|
3
|
+
require 'active_record'
|
4
|
+
require 'open-uri'
|
5
|
+
require 'zlib'
|
6
|
+
require 'yajl'
|
7
|
+
require 'resque'
|
8
|
+
require 'yaml'
|
9
|
+
require 'pry'
|
10
|
+
|
11
|
+
require 'github/archive/connections'
|
12
|
+
|
13
|
+
require 'github/archive/stat_collector'
|
14
|
+
|
15
|
+
require 'github/archive/archived_url'
|
16
|
+
require 'github/archive/event'
|
17
|
+
|
18
|
+
require 'github/archive/create_archive'
|
19
|
+
require 'github/archive/destroy_archive'
|
20
|
+
|
21
|
+
module Github
|
22
|
+
module Archive
|
23
|
+
::Github::Archive::Connections.init_settings
|
24
|
+
::Github::Archive::Connections.read_settings
|
25
|
+
|
26
|
+
::Github::Archive::Connections.connect_redis
|
27
|
+
::Github::Archive::Connections.connect_mysql
|
28
|
+
end
|
29
|
+
end
|
@@ -0,0 +1,85 @@
|
|
1
|
+
module Github
|
2
|
+
module Archive
|
3
|
+
class Connections
|
4
|
+
class << self
|
5
|
+
SETTINGS = {}
|
6
|
+
|
7
|
+
def connect_mysql
|
8
|
+
::ActiveRecord::Base.establish_connection( adapter: 'mysql',
|
9
|
+
server: SETTINGS['GHA']['MYSQL']['SERVER'],
|
10
|
+
username: SETTINGS['GHA']['MYSQL']['USERNAME'],
|
11
|
+
password: SETTINGS['GHA']['MYSQL']['PASSWORD'],
|
12
|
+
database: SETTINGS['GHA']['MYSQL']['DATABASE']
|
13
|
+
)
|
14
|
+
end
|
15
|
+
|
16
|
+
def config_mysql(server, user, password, database)
|
17
|
+
SETTINGS['GHA']['MYSQL']['SERVER'] = server
|
18
|
+
SETTINGS['GHA']['MYSQL']['USERNAME'] = user
|
19
|
+
SETTINGS['GHA']['MYSQL']['PASSWORD'] = password
|
20
|
+
SETTINGS['GHA']['MYSQL']['DATABASE'] = database
|
21
|
+
end
|
22
|
+
|
23
|
+
def connect_redis
|
24
|
+
if SETTINGS['GHA']['REDIS']['PASSWORD'].nil?
|
25
|
+
::Resque.redis = Redis.new(:host => SETTINGS['GHA']['REDIS']['SERVER'],
|
26
|
+
:port => SETTINGS['GHA']['REDIS']['PORT'],
|
27
|
+
:thread_safe => true)
|
28
|
+
else
|
29
|
+
::Resque.redis = Redis.new(:host => SETTINGS['GHA']['REDIS']['SERVER'],
|
30
|
+
:port => SETTINGS['GHA']['REDIS']['PORT'],
|
31
|
+
:password => SETTINGS['GHA']['REDIS']['PASSWORD'],
|
32
|
+
:thread_safe => true)
|
33
|
+
end
|
34
|
+
end
|
35
|
+
|
36
|
+
def config_redis(server, port, password)
|
37
|
+
SETTINGS['GHA']['REDIS']['SERVER'] = server
|
38
|
+
SETTINGS['GHA']['REDIS']['PORT'] = port
|
39
|
+
SETTINGS['GHA']['REDIS']['PASSWORD'] = password
|
40
|
+
end
|
41
|
+
|
42
|
+
def init_settings
|
43
|
+
SETTINGS['GHA'] ||= {}
|
44
|
+
SETTINGS['GHA']['MYSQL'] ||= {}
|
45
|
+
SETTINGS['GHA']['MYSQL']['SERVER'] ||= 'localhost'
|
46
|
+
SETTINGS['GHA']['MYSQL']['USERNAME'] ||= 'root'
|
47
|
+
SETTINGS['GHA']['MYSQL']['PASSWORD'] ||= nil
|
48
|
+
SETTINGS['GHA']['MYSQL']['DATABASE'] ||= 'github_archive'
|
49
|
+
|
50
|
+
SETTINGS['GHA']['REDIS'] ||= {}
|
51
|
+
SETTINGS['GHA']['REDIS']['SERVER'] ||= 'localhost'
|
52
|
+
SETTINGS['GHA']['REDIS']['PASSWORD'] ||= nil
|
53
|
+
SETTINGS['GHA']['REDIS']['PORT'] ||= '6379'
|
54
|
+
end
|
55
|
+
|
56
|
+
def read_settings
|
57
|
+
if File.exist?(setting_path)
|
58
|
+
settings = YAML::load_file setting_path
|
59
|
+
|
60
|
+
config_mysql settings['MYSQL']['SERVER'],
|
61
|
+
settings['MYSQL']['USERNAME'],
|
62
|
+
settings['MYSQL']['PASSWORD'],
|
63
|
+
settings['MYSQL']['DATABASE']
|
64
|
+
|
65
|
+
config_redis settings['REDIS']['SERVER'],
|
66
|
+
settings['REDIS']['PORT'],
|
67
|
+
settings['REDIS']['PASSWORD']
|
68
|
+
end
|
69
|
+
end
|
70
|
+
|
71
|
+
def write_settings
|
72
|
+
File.open(setting_path, "w") do |file|
|
73
|
+
file.write SETTINGS['GHA'].to_yaml
|
74
|
+
end
|
75
|
+
end
|
76
|
+
|
77
|
+
private
|
78
|
+
|
79
|
+
def setting_path
|
80
|
+
"#{File.expand_path('~')}/.github-archive"
|
81
|
+
end
|
82
|
+
end
|
83
|
+
end
|
84
|
+
end
|
85
|
+
end
|
@@ -0,0 +1,30 @@
|
|
1
|
+
module Github
|
2
|
+
module Archive
|
3
|
+
module CreateArchive
|
4
|
+
def self.do
|
5
|
+
ActiveRecord::Schema.define do
|
6
|
+
unless Github::Archive::ArchivedUrl.table_exists?
|
7
|
+
create_table :archived_urls do |table|
|
8
|
+
table.column :url, :string
|
9
|
+
table.column :finished_processing, :boolean
|
10
|
+
end
|
11
|
+
|
12
|
+
add_index :archived_urls,:url
|
13
|
+
end
|
14
|
+
|
15
|
+
unless Github::Archive::Event.table_exists?
|
16
|
+
create_table :events do |table|
|
17
|
+
table.column :url, :string
|
18
|
+
table.column :event_type, :string
|
19
|
+
table.column :gh_created_at, :datetime
|
20
|
+
end
|
21
|
+
|
22
|
+
add_index :events, :url
|
23
|
+
add_index :events, :event_type
|
24
|
+
add_index :events, :gh_created_at
|
25
|
+
end
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
module Github
|
2
|
+
module Archive
|
3
|
+
module DestroyArchive
|
4
|
+
def self.do
|
5
|
+
ActiveRecord::Schema.define do
|
6
|
+
unless !Github::Archive::Event.table_exists?
|
7
|
+
drop_table :events
|
8
|
+
end
|
9
|
+
|
10
|
+
unless !Github::Archive::ArchivedUrl.table_exists?
|
11
|
+
drop_table :archived_urls
|
12
|
+
end
|
13
|
+
end
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
@@ -0,0 +1,47 @@
|
|
1
|
+
module Github
|
2
|
+
module Archive
|
3
|
+
class Event < ::ActiveRecord::Base
|
4
|
+
scope :in_time_range, ->(range) { where(:gh_created_at => range) }
|
5
|
+
scope :with_event_type, ->(type) { where(:event_type => type) }
|
6
|
+
|
7
|
+
class << self
|
8
|
+
def create_with_json(raw_json)
|
9
|
+
json = raw_json.with_indifferent_access
|
10
|
+
|
11
|
+
if related_event?(json[:type])
|
12
|
+
url = "UNKNOWN"
|
13
|
+
|
14
|
+
if json[:repo]
|
15
|
+
url = json[:repo][:url]
|
16
|
+
elsif json[:repository]
|
17
|
+
url = json[:repository][:url]
|
18
|
+
end
|
19
|
+
|
20
|
+
self.create(
|
21
|
+
url: url,
|
22
|
+
event_type: json[:type],
|
23
|
+
gh_created_at: json[:created_at]
|
24
|
+
)
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
def results_for_range_and_type(range, type, limit)
|
29
|
+
self.in_time_range(range)
|
30
|
+
.with_event_type(type)
|
31
|
+
.group(:url)
|
32
|
+
.limit(limit)
|
33
|
+
.order('count(*) DESC')
|
34
|
+
.count(:url)
|
35
|
+
end
|
36
|
+
|
37
|
+
private
|
38
|
+
|
39
|
+
def related_event?(event_type)
|
40
|
+
event_type != "GistEvent" &&
|
41
|
+
event_type != "FollowEvent" &&
|
42
|
+
event_type != "TeamAddEvent"
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
46
|
+
end
|
47
|
+
end
|
@@ -0,0 +1,39 @@
|
|
1
|
+
module Github
|
2
|
+
module Archive
|
3
|
+
class StatCollector
|
4
|
+
@queue = :github_archive
|
5
|
+
|
6
|
+
class << self
|
7
|
+
attr_reader :queue
|
8
|
+
|
9
|
+
def perform(stat_url)
|
10
|
+
archived = ArchivedUrl.where(url: stat_url).first
|
11
|
+
|
12
|
+
if archived.nil?
|
13
|
+
puts "cannot archive untracked url #{stat_url}"
|
14
|
+
elsif archived.finished_processing
|
15
|
+
puts "already processed #{stat_url}"
|
16
|
+
else
|
17
|
+
begin
|
18
|
+
ArchivedUrl.transaction do
|
19
|
+
puts "processing #{stat_url}"
|
20
|
+
gz = open(stat_url)
|
21
|
+
js = Zlib::GzipReader.new(gz).read
|
22
|
+
Yajl::Parser.parse(js) do |event|
|
23
|
+
Github::Archive::Event.create_with_json(event)
|
24
|
+
end
|
25
|
+
|
26
|
+
archived.finished_processing = true
|
27
|
+
archived.save
|
28
|
+
end
|
29
|
+
rescue
|
30
|
+
puts "There was some kind of error while parsing #{stat_url}"
|
31
|
+
archived.finished_processing = true
|
32
|
+
archived.save
|
33
|
+
end
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
37
|
+
end
|
38
|
+
end
|
39
|
+
end
|
@@ -0,0 +1,20 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
module Github
|
4
|
+
module Archive
|
5
|
+
describe ArchivedUrl do
|
6
|
+
after(:each) do
|
7
|
+
ArchivedUrl.delete_all
|
8
|
+
end
|
9
|
+
|
10
|
+
it "tracks processed urls" do
|
11
|
+
FactoryGirl.create(:archived_url, url: 'test_url')
|
12
|
+
ArchivedUrl.already_has?("test_url").should be_true
|
13
|
+
end
|
14
|
+
|
15
|
+
it "does not track unprocessed urls" do
|
16
|
+
ArchivedUrl.already_has?("test_url").should be_false
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,117 @@
|
|
1
|
+
require 'spec_helper'
|
2
|
+
|
3
|
+
module Github
|
4
|
+
module Archive
|
5
|
+
describe Event do
|
6
|
+
after(:each) do
|
7
|
+
Event.delete_all
|
8
|
+
end
|
9
|
+
|
10
|
+
let(:expected_results) {{"url1"=>2, "url2"=>1, "url3"=>1}}
|
11
|
+
let(:json_data){
|
12
|
+
{"payload"=>
|
13
|
+
{"head"=>"6234f9fcb61c7b03782cf32e232ae1d90bf3c772",
|
14
|
+
"size"=>1,
|
15
|
+
"shas"=>
|
16
|
+
[["6234f9fcb61c7b03782cf32e232ae1d90bf3c772",
|
17
|
+
"dev+commit-bot@koideploy.com",
|
18
|
+
"Display photo \"nuances\" from \"paul bica\"",
|
19
|
+
"Koi Deploy Commit Bot",
|
20
|
+
true]],
|
21
|
+
"ref"=>"refs/heads/master"},
|
22
|
+
"created_at"=>"2012-12-10T12:00:29-08:00",
|
23
|
+
"repository"=>
|
24
|
+
{"description"=>
|
25
|
+
"Deploy your Rails app straight from GitHub to Heroku in a single click, or continuously triggered by your CI. This is an example application for continuous deployment via Travis CI. ",
|
26
|
+
"stargazers"=>1,
|
27
|
+
"owner"=>"koideploy",
|
28
|
+
"url"=>"https://github.com/koideploy/showcase",
|
29
|
+
"has_downloads"=>true,
|
30
|
+
"language"=>"Ruby",
|
31
|
+
"pushed_at"=>"2012-12-10T12:00:21-08:00",
|
32
|
+
"forks"=>0,
|
33
|
+
"has_issues"=>true,
|
34
|
+
"organization"=>"koideploy",
|
35
|
+
"fork"=>false,
|
36
|
+
"size"=>4368,
|
37
|
+
"has_wiki"=>false,
|
38
|
+
"name"=>"showcase",
|
39
|
+
"id"=>6306116,
|
40
|
+
"homepage"=>"http://showcase.koideploy.com",
|
41
|
+
"private"=>false,
|
42
|
+
"open_issues"=>0,
|
43
|
+
"created_at"=>"2012-10-19T23:38:50-07:00",
|
44
|
+
"watchers"=>1},
|
45
|
+
"actor_attributes"=>
|
46
|
+
{"login"=>"koideploy-commit-bot",
|
47
|
+
"name"=>"KoiDeploy Commit Bot",
|
48
|
+
"location"=>"Brisbane, Australia",
|
49
|
+
"company"=>"KoiDeploy",
|
50
|
+
"blog"=>"https://koideploy.com",
|
51
|
+
"type"=>"User",
|
52
|
+
"gravatar_id"=>"a1aea43cf721ab953474a0e4c699bc90"},
|
53
|
+
"url"=>
|
54
|
+
"https://github.com/koideploy/showcase/compare/ec6f77514f...6234f9fcb6",
|
55
|
+
"public"=>true,
|
56
|
+
"actor"=>"koideploy-commit-bot",
|
57
|
+
"type"=>"PushEvent"}
|
58
|
+
}
|
59
|
+
|
60
|
+
context "when looking up events" do
|
61
|
+
it "returns events in the correct time range" do
|
62
|
+
FactoryGirl.create(:event, gh_created_at: 3.days.ago)
|
63
|
+
FactoryGirl.create(:event, gh_created_at: 2.days.ago)
|
64
|
+
FactoryGirl.create(:event, gh_created_at: 1.days.ago)
|
65
|
+
FactoryGirl.create(:event, gh_created_at: DateTime.now)
|
66
|
+
|
67
|
+
Event.count.should eq 4
|
68
|
+
Event.in_time_range(2.days.ago..1.days.ago).count.should eq 2
|
69
|
+
end
|
70
|
+
|
71
|
+
it "returns events with the correct type" do
|
72
|
+
FactoryGirl.create(:event, event_type: "test_event")
|
73
|
+
FactoryGirl.create(:event, event_type: "test_event2")
|
74
|
+
|
75
|
+
Event.with_event_type("test_event").count.should eq 1
|
76
|
+
end
|
77
|
+
end
|
78
|
+
|
79
|
+
context "when creating events" do
|
80
|
+
it "creates repo events with json" do
|
81
|
+
Event.create_with_json(json_data)
|
82
|
+
event = Event.first
|
83
|
+
event.event_type.should == "PushEvent"
|
84
|
+
event.gh_created_at.to_s.should == "2012-12-10 12:00:29 UTC"
|
85
|
+
event.url.should == "https://github.com/koideploy/showcase"
|
86
|
+
end
|
87
|
+
|
88
|
+
|
89
|
+
["GistEvent", "FollowEvent" ,"TeamAddEvent"].each do |event_str|
|
90
|
+
it "does not create for #{event_str} events" do
|
91
|
+
test_json = json_data.dup
|
92
|
+
test_json["type"] = event_str
|
93
|
+
Event.create_with_json(test_json)
|
94
|
+
Event.count.should eq 0
|
95
|
+
end
|
96
|
+
end
|
97
|
+
end
|
98
|
+
|
99
|
+
context "when getting results" do
|
100
|
+
it "returns a result hash with the correct results" do
|
101
|
+
FactoryGirl.create(:event, gh_created_at: 3.days.ago, event_type: "test_event1", url: "url1")
|
102
|
+
FactoryGirl.create(:event, gh_created_at: 2.days.ago, event_type: "test_event1", url: "url1")
|
103
|
+
FactoryGirl.create(:event, gh_created_at: 2.days.ago, event_type: "test_event1", url: "url2")
|
104
|
+
FactoryGirl.create(:event, gh_created_at: 2.days.ago, event_type: "test_event1", url: "url3")
|
105
|
+
FactoryGirl.create(:event, gh_created_at: 1.days.ago, event_type: "test_event3", url: "url3")
|
106
|
+
FactoryGirl.create(:event, gh_created_at: DateTime.now, event_type: "test_event3", url: "url4")
|
107
|
+
|
108
|
+
range = (3.days.ago..2.days.ago)
|
109
|
+
|
110
|
+
results = Event.results_for_range_and_type(range, "test_event1", 4)
|
111
|
+
|
112
|
+
results.should == expected_results
|
113
|
+
end
|
114
|
+
end
|
115
|
+
end
|
116
|
+
end
|
117
|
+
end
|
data/spec/spec_helper.rb
ADDED
metadata
ADDED
@@ -0,0 +1,241 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: github-archive
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.1
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- cparratto
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
date: 2013-10-06 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: thor
|
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: mysql
|
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: activerecord
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - '>='
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0'
|
48
|
+
type: :runtime
|
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: yajl-ruby
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - '>='
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '0'
|
62
|
+
type: :runtime
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - '>='
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: resque
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - '>='
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '0'
|
76
|
+
type: :runtime
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - '>='
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: bundler
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ~>
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '1.3'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ~>
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '1.3'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: rake
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - '>='
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - '>='
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: rspec
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - '>='
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '0'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - '>='
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '0'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: factory_girl
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - '>='
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '0'
|
132
|
+
type: :development
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - '>='
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '0'
|
139
|
+
- !ruby/object:Gem::Dependency
|
140
|
+
name: database_cleaner
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - '>='
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '0'
|
146
|
+
type: :development
|
147
|
+
prerelease: false
|
148
|
+
version_requirements: !ruby/object:Gem::Requirement
|
149
|
+
requirements:
|
150
|
+
- - '>='
|
151
|
+
- !ruby/object:Gem::Version
|
152
|
+
version: '0'
|
153
|
+
- !ruby/object:Gem::Dependency
|
154
|
+
name: mocha
|
155
|
+
requirement: !ruby/object:Gem::Requirement
|
156
|
+
requirements:
|
157
|
+
- - '>='
|
158
|
+
- !ruby/object:Gem::Version
|
159
|
+
version: '0'
|
160
|
+
type: :development
|
161
|
+
prerelease: false
|
162
|
+
version_requirements: !ruby/object:Gem::Requirement
|
163
|
+
requirements:
|
164
|
+
- - '>='
|
165
|
+
- !ruby/object:Gem::Version
|
166
|
+
version: '0'
|
167
|
+
- !ruby/object:Gem::Dependency
|
168
|
+
name: pry
|
169
|
+
requirement: !ruby/object:Gem::Requirement
|
170
|
+
requirements:
|
171
|
+
- - '>='
|
172
|
+
- !ruby/object:Gem::Version
|
173
|
+
version: '0'
|
174
|
+
type: :development
|
175
|
+
prerelease: false
|
176
|
+
version_requirements: !ruby/object:Gem::Requirement
|
177
|
+
requirements:
|
178
|
+
- - '>='
|
179
|
+
- !ruby/object:Gem::Version
|
180
|
+
version: '0'
|
181
|
+
description: Github Archive
|
182
|
+
email:
|
183
|
+
- cparratto@gmail.com
|
184
|
+
executables:
|
185
|
+
- github-archive
|
186
|
+
extensions: []
|
187
|
+
extra_rdoc_files: []
|
188
|
+
files:
|
189
|
+
- .gitignore
|
190
|
+
- Gemfile
|
191
|
+
- LICENSE.txt
|
192
|
+
- README.md
|
193
|
+
- Rakefile
|
194
|
+
- bin/github-archive
|
195
|
+
- github-archive.gemspec
|
196
|
+
- lib/github/archive.rb
|
197
|
+
- lib/github/archive/archived_url.rb
|
198
|
+
- lib/github/archive/connections.rb
|
199
|
+
- lib/github/archive/create_archive.rb
|
200
|
+
- lib/github/archive/destroy_archive.rb
|
201
|
+
- lib/github/archive/event.rb
|
202
|
+
- lib/github/archive/stat_collector.rb
|
203
|
+
- lib/github/archive/version.rb
|
204
|
+
- spec/factories/archived_url_factory.rb
|
205
|
+
- spec/factories/event_factory.rb
|
206
|
+
- spec/github/archive/archived_url_spec.rb
|
207
|
+
- spec/github/archive/event_spec.rb
|
208
|
+
- spec/github/archive/stat_collector_spec.rb
|
209
|
+
- spec/spec_helper.rb
|
210
|
+
homepage: https://github.com/cparratto/github-archive
|
211
|
+
licenses:
|
212
|
+
- MIT
|
213
|
+
metadata: {}
|
214
|
+
post_install_message:
|
215
|
+
rdoc_options: []
|
216
|
+
require_paths:
|
217
|
+
- lib
|
218
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
219
|
+
requirements:
|
220
|
+
- - '>='
|
221
|
+
- !ruby/object:Gem::Version
|
222
|
+
version: '0'
|
223
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
224
|
+
requirements:
|
225
|
+
- - '>='
|
226
|
+
- !ruby/object:Gem::Version
|
227
|
+
version: '0'
|
228
|
+
requirements: []
|
229
|
+
rubyforge_project:
|
230
|
+
rubygems_version: 2.0.3
|
231
|
+
signing_key:
|
232
|
+
specification_version: 4
|
233
|
+
summary: A command line utility for concurrent processing and management of github
|
234
|
+
event archives.
|
235
|
+
test_files:
|
236
|
+
- spec/factories/archived_url_factory.rb
|
237
|
+
- spec/factories/event_factory.rb
|
238
|
+
- spec/github/archive/archived_url_spec.rb
|
239
|
+
- spec/github/archive/event_spec.rb
|
240
|
+
- spec/github/archive/stat_collector_spec.rb
|
241
|
+
- spec/spec_helper.rb
|