elasticrawl 1.1.4 → 1.1.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.travis.yml +4 -3
- data/Cheffile +7 -10
- data/Cheffile.lock +20 -27
- data/README.md +29 -29
- data/Vagrantfile +20 -13
- data/elasticrawl.gemspec +12 -12
- data/lib/elasticrawl/cluster.rb +7 -2
- data/lib/elasticrawl/version.rb +1 -1
- data/spec/spec_helper.rb +3 -0
- data/spec/unit/crawl_segment_spec.rb +1 -1
- data/spec/unit/crawl_spec.rb +1 -1
- data/spec/unit/job_spec.rb +1 -1
- data/spec/unit/job_step_spec.rb +1 -1
- metadata +55 -55
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: a7a988f505c699d078fa4cc15981b77f7924e907
|
4
|
+
data.tar.gz: db7ee7ae05ccec51b0ffde16900656c859523001
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 12949f3230c3a0f7d08d4e02a9b296968616fa634072db882fe26809c58791d06ebf48d21fbc3c703ab1f858fdf12cfa9c324a6a97a7e896a5916679c7d6de06
|
7
|
+
data.tar.gz: ab9ec066ecb469707241751087ff6d25ff89e9013fdb0a8505bca904fcaa3fed2b331ef289fa0ffb71dd970261ec7c0028ca955d94642fad7093191723d8c4e3
|
data/.travis.yml
CHANGED
data/Cheffile
CHANGED
@@ -1,14 +1,11 @@
|
|
1
1
|
#!/usr/bin/env ruby
|
2
2
|
#^syntax detection
|
3
3
|
|
4
|
-
site "
|
4
|
+
site "https://supermarket.getchef.com/api/v1"
|
5
5
|
|
6
|
-
cookbook "apt",
|
7
|
-
|
8
|
-
cookbook "
|
9
|
-
cookbook "
|
10
|
-
cookbook "
|
11
|
-
|
12
|
-
:ref => "v0.7.2"
|
13
|
-
cookbook "ruby_build"
|
14
|
-
cookbook "vim"
|
6
|
+
cookbook "apt", "2.9.2"
|
7
|
+
cookbook "build-essential", "2.2.4"
|
8
|
+
cookbook "git", "4.3.5"
|
9
|
+
cookbook "ruby_rbenv", "1.0.1"
|
10
|
+
cookbook "ruby_build", "0.8.0"
|
11
|
+
cookbook "vim", "2.0.0"
|
data/Cheffile.lock
CHANGED
@@ -1,37 +1,30 @@
|
|
1
1
|
SITE
|
2
|
-
remote:
|
2
|
+
remote: https://supermarket.getchef.com/api/v1
|
3
3
|
specs:
|
4
|
-
apt (2.2
|
5
|
-
build-essential (
|
6
|
-
chef_handler (1.
|
7
|
-
dmg (2.0
|
8
|
-
git (
|
4
|
+
apt (2.9.2)
|
5
|
+
build-essential (2.2.4)
|
6
|
+
chef_handler (1.2.0)
|
7
|
+
dmg (2.3.0)
|
8
|
+
git (4.3.5)
|
9
9
|
build-essential (>= 0.0.0)
|
10
10
|
dmg (>= 0.0.0)
|
11
|
-
runit (>= 1.0.0)
|
12
11
|
windows (>= 0.0.0)
|
13
|
-
yum (>= 0.0.0)
|
12
|
+
yum-epel (>= 0.0.0)
|
14
13
|
ruby_build (0.8.0)
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
19
|
-
windows (1.11.0)
|
14
|
+
ruby_rbenv (1.0.1)
|
15
|
+
ruby_build (>= 0.0.0)
|
16
|
+
vim (2.0.0)
|
17
|
+
windows (1.39.0)
|
20
18
|
chef_handler (>= 0.0.0)
|
21
|
-
yum (
|
22
|
-
|
23
|
-
|
24
|
-
remote: https://github.com/fnichol/chef-rbenv.git
|
25
|
-
ref: v0.7.2
|
26
|
-
sha: f2b53292e810dd2b43f6121f9958f5f29979dcb1
|
27
|
-
specs:
|
28
|
-
rbenv (0.7.2)
|
19
|
+
yum (3.8.2)
|
20
|
+
yum-epel (0.6.5)
|
21
|
+
yum (~> 3.2)
|
29
22
|
|
30
23
|
DEPENDENCIES
|
31
|
-
apt (
|
32
|
-
build-essential (
|
33
|
-
git (
|
34
|
-
|
35
|
-
|
36
|
-
vim (
|
24
|
+
apt (= 2.9.2)
|
25
|
+
build-essential (= 2.2.4)
|
26
|
+
git (= 4.3.5)
|
27
|
+
ruby_build (= 0.8.0)
|
28
|
+
ruby_rbenv (= 1.0.1)
|
29
|
+
vim (= 2.0.0)
|
37
30
|
|
data/README.md
CHANGED
@@ -1,20 +1,11 @@
|
|
1
1
|
# Elasticrawl
|
2
2
|
|
3
|
-
Command line tool for launching Hadoop jobs using AWS EMR (Elastic MapReduce) to process Common Crawl data.
|
4
|
-
Elasticrawl can be used with [crawl data](http://commoncrawl.org/the-data/get-started/) from April 2014 onwards.
|
3
|
+
* Command line tool for launching Hadoop jobs using AWS EMR (Elastic MapReduce) to process Common Crawl data.
|
4
|
+
* Elasticrawl can be used with [crawl data](http://commoncrawl.org/the-data/get-started/) from April 2014 onwards.
|
5
|
+
* A list of crawls released by Common Crawl is maintained on the [wiki](https://github.com/rossf7/elasticrawl/wiki).
|
6
|
+
* Common Crawl announce new crawls on their [blog](http://blog.commoncrawl.org/).
|
5
7
|
|
6
|
-
|
7
|
-
| -------------- |:---------:|:----------:|:-------:
|
8
|
-
| [CC-MAIN-2015-06](http://blog.commoncrawl.org/2015/03/january-2015-crawl-archive-available/) | January 2015 | ~ 1.82 billion | 98
|
9
|
-
| [CC-MAIN-2014-52](http://blog.commoncrawl.org/2015/01/december-2014-crawl-archive-available/) | December 2014 | ~ 2.08 billion | 314
|
10
|
-
| [CC-MAIN-2014-49](http://blog.commoncrawl.org/2014/12/november-2014-crawl-archive-available/) | November 2014 | ~ 1.95 billion | 136
|
11
|
-
| [CC-MAIN-2014-35](http://blog.commoncrawl.org/2014/09/august-2014-crawl-data-available/) | August 2014 | ~ 2.8 billion | 111
|
12
|
-
| [CC-MAIN-2014-23](http://blog.commoncrawl.org/2014/08/july-2014-crawl-data-available/) | July 2014 | ~ 3.6 billion | 253
|
13
|
-
| [CC-MAIN-2014-15](http://blog.commoncrawl.org/2014/07/april-2014-crawl-data-available/) | April 2014 | ~ 2.3 billion | 70
|
14
|
-
|
15
|
-
Common Crawl announce new crawls on their [blog](http://blog.commoncrawl.org/).
|
16
|
-
|
17
|
-
Ships with a default configuration that launches the
|
8
|
+
* Ships with a default configuration that launches the
|
18
9
|
[elasticrawl-examples](https://github.com/rossf7/elasticrawl-examples) jobs.
|
19
10
|
This is an implementation of the standard Hadoop Word Count example.
|
20
11
|
|
@@ -25,18 +16,27 @@ This [blog post](https://rossfairbanks.com/2015/01/03/parsing-common-crawl-using
|
|
25
16
|
Deployment packages are available for Linux and OS X, unfortunately Windows isn't supported yet. Download the package, extract it and run the elasticrawl command from the package directory.
|
26
17
|
|
27
18
|
```bash
|
28
|
-
# OS X https://d2ujrnticqzebc.cloudfront.net/elasticrawl-1.1.
|
29
|
-
# Linux (64-bit) https://d2ujrnticqzebc.cloudfront.net/elasticrawl-1.1.
|
30
|
-
# Linux (32-bit) https://d2ujrnticqzebc.cloudfront.net/elasticrawl-1.1.
|
19
|
+
# OS X https://d2ujrnticqzebc.cloudfront.net/elasticrawl-1.1.5-osx.tar.gz
|
20
|
+
# Linux (64-bit) https://d2ujrnticqzebc.cloudfront.net/elasticrawl-1.1.5-linux-x86_64.tar.gz
|
21
|
+
# Linux (32-bit) https://d2ujrnticqzebc.cloudfront.net/elasticrawl-1.1.5-linux-x86.tar.gz
|
31
22
|
|
32
23
|
# e.g.
|
33
24
|
|
34
|
-
curl -O https://d2ujrnticqzebc.cloudfront.net/elasticrawl-1.1.
|
35
|
-
tar -xzf elasticrawl-1.1.
|
36
|
-
cd elasticrawl-1.1.
|
25
|
+
curl -O https://d2ujrnticqzebc.cloudfront.net/elasticrawl-1.1.5-osx.tar.gz
|
26
|
+
tar -xzf elasticrawl-1.1.5-osx.tar.gz
|
27
|
+
cd elasticrawl-1.1.5-osx/
|
37
28
|
./elasticrawl --help
|
38
29
|
```
|
39
30
|
|
31
|
+
### Troubleshooting
|
32
|
+
|
33
|
+
If you get the error "EMR service role arn:aws:iam::156793023547:role/EMR_DefaultRole is invalid" when launching a cluster then you don't have the necessary IAM roles.
|
34
|
+
To fix this install the [AWS CLI](https://aws.amazon.com/cli/) and run the command below.
|
35
|
+
|
36
|
+
```
|
37
|
+
aws emr create-default-roles
|
38
|
+
```
|
39
|
+
|
40
40
|
## Commands
|
41
41
|
|
42
42
|
### elasticrawl init
|
@@ -62,13 +62,13 @@ Config complete
|
|
62
62
|
The parse command takes in the crawl name and an optional number of segments and files to parse.
|
63
63
|
|
64
64
|
```bash
|
65
|
-
~$ ./elasticrawl parse CC-MAIN-
|
65
|
+
~$ ./elasticrawl parse CC-MAIN-2015-48 --max-segments 2 --max-files 3
|
66
66
|
Segments
|
67
67
|
Segment: 1416400372202.67 Files: 150
|
68
68
|
Segment: 1416400372490.23 Files: 124
|
69
69
|
|
70
70
|
Job configuration
|
71
|
-
Crawl: CC-MAIN-
|
71
|
+
Crawl: CC-MAIN-2015-48 Segments: 2 Parsing: 3 files per segment
|
72
72
|
|
73
73
|
Cluster configuration
|
74
74
|
Master: 1 m1.medium (Spot: 0.12)
|
@@ -106,10 +106,10 @@ The status command shows crawls and your job history.
|
|
106
106
|
```bash
|
107
107
|
~$ ./elasticrawl status
|
108
108
|
Crawl Status
|
109
|
-
CC-MAIN-
|
109
|
+
CC-MAIN-2015-48 Segments: to parse 98, parsed 2, total 100
|
110
110
|
|
111
111
|
Job History (last 10)
|
112
|
-
1420124830792 Launched: 2015-01-01 15:07:10 Crawl: CC-MAIN-
|
112
|
+
1420124830792 Launched: 2015-01-01 15:07:10 Crawl: CC-MAIN-2015-48 Segments: 2 Parsing: 3 files per segment
|
113
113
|
```
|
114
114
|
|
115
115
|
### elasticrawl reset
|
@@ -117,10 +117,10 @@ Job History (last 10)
|
|
117
117
|
The reset comment resets a crawl so it is parsed again.
|
118
118
|
|
119
119
|
```bash
|
120
|
-
~$ ./elasticrawl reset CC-MAIN-
|
120
|
+
~$ ./elasticrawl reset CC-MAIN-2015-48
|
121
121
|
Reset crawl? (y/n)
|
122
122
|
y
|
123
|
-
CC-MAIN-
|
123
|
+
CC-MAIN-2015-48 Segments: to parse 100, parsed 0, total 100
|
124
124
|
```
|
125
125
|
|
126
126
|
### elasticrawl destroy
|
@@ -158,13 +158,13 @@ stores your S3 bucket name and the config for the parse and combine jobs
|
|
158
158
|
|
159
159
|
## Development
|
160
160
|
|
161
|
-
Elasticrawl is developed in Ruby and requires Ruby 2.0.0 or later (Ruby 2.
|
161
|
+
Elasticrawl is developed in Ruby and requires Ruby 2.0.0 or later (Ruby 2.2 is recommended). The sqlite3 and nokogiri gems have C extensions which mean you may need to install development headers.
|
162
162
|
|
163
163
|
[![Gem Version](https://badge.fury.io/rb/elasticrawl.png)](http://badge.fury.io/rb/elasticrawl)
|
164
164
|
[![Code Climate](https://codeclimate.com/github/rossf7/elasticrawl.png)](https://codeclimate.com/github/rossf7/elasticrawl)
|
165
|
-
[![Build Status](https://travis-ci.org/rossf7/elasticrawl.png?branch=master)](https://travis-ci.org/rossf7/elasticrawl) 2.0.0, 2.1.
|
165
|
+
[![Build Status](https://travis-ci.org/rossf7/elasticrawl.png?branch=master)](https://travis-ci.org/rossf7/elasticrawl) 2.0.0, 2.1.8, 2.2.4, 2.3.0
|
166
166
|
|
167
|
-
The deployment packages are created using [Traveling Ruby](http://phusion.github.io/traveling-ruby/). The deploy packages contain a Ruby 2.
|
167
|
+
The deployment packages are created using [Traveling Ruby](http://phusion.github.io/traveling-ruby/). The deploy packages contain a Ruby 2.2 interpreter, Gems and the compiled C extensions. The [traveling-elasticrawl](https://github.com/rossf7/traveling-elasticrawl) repository has a Rake task that automates building the deployment packages.
|
168
168
|
|
169
169
|
## TODO
|
170
170
|
|
data/Vagrantfile
CHANGED
@@ -6,17 +6,17 @@ Vagrant.configure("2") do |config|
|
|
6
6
|
# options are documented and commented below. For a complete reference,
|
7
7
|
# please see the online documentation at vagrantup.com.
|
8
8
|
|
9
|
-
#
|
9
|
+
# Increase RAM to 1 GB
|
10
10
|
config.vm.provider "virtualbox" do |vbox|
|
11
|
-
vbox.customize ["modifyvm", :id, "--
|
11
|
+
vbox.customize ["modifyvm", :id, "--memory", 1024]
|
12
12
|
end
|
13
13
|
|
14
14
|
# Elasticrawl launches Hadoop jobs for the CommonCrawl dataset using the AWS EMR service.
|
15
15
|
config.vm.define :elasticrawl do |elasticrawl|
|
16
16
|
elasticrawl.vm.box = "elasticrawl"
|
17
17
|
|
18
|
-
# Ubuntu Server
|
19
|
-
elasticrawl.vm.
|
18
|
+
# Ubuntu Server 14.04 LTS
|
19
|
+
elasticrawl.vm.box = "ubuntu/trusty64"
|
20
20
|
|
21
21
|
# Network config
|
22
22
|
elasticrawl.vm.network :public_network
|
@@ -30,7 +30,7 @@ Vagrant.configure("2") do |config|
|
|
30
30
|
chef.add_recipe "apt"
|
31
31
|
chef.add_recipe "build-essential"
|
32
32
|
chef.add_recipe "ruby_build"
|
33
|
-
chef.add_recipe "
|
33
|
+
chef.add_recipe "ruby_rbenv::user"
|
34
34
|
chef.add_recipe "git"
|
35
35
|
chef.add_recipe "vim"
|
36
36
|
|
@@ -39,17 +39,24 @@ Vagrant.configure("2") do |config|
|
|
39
39
|
"user_installs" => [
|
40
40
|
{
|
41
41
|
"user" => "vagrant",
|
42
|
-
"rubies" => ["2.0.0-
|
43
|
-
"global" => "2.
|
42
|
+
"rubies" => ["2.0.0-p648", "2.1.8", "2.2.4", "2.3.0"],
|
43
|
+
"global" => "2.2.4",
|
44
44
|
"gems" => {
|
45
|
-
"2.0.0-
|
46
|
-
{ "name" => "bundler"
|
45
|
+
"2.0.0-p648" => [
|
46
|
+
{ "name" => "bundler",
|
47
|
+
"version" => "1.11.2" }
|
47
48
|
],
|
48
|
-
"2.1.
|
49
|
-
{ "name" => "bundler"
|
49
|
+
"2.1.8" => [
|
50
|
+
{ "name" => "bundler",
|
51
|
+
"version" => "1.11.2" }
|
50
52
|
],
|
51
|
-
"2.2.
|
52
|
-
{ "name" => "bundler"
|
53
|
+
"2.2.4" => [
|
54
|
+
{ "name" => "bundler",
|
55
|
+
"version" => "1.11.2" }
|
56
|
+
],
|
57
|
+
"2.3.0" => [
|
58
|
+
{ "name" => "bundler",
|
59
|
+
"version" => "1.11.2" }
|
53
60
|
]
|
54
61
|
}
|
55
62
|
}
|
data/elasticrawl.gemspec
CHANGED
@@ -18,17 +18,17 @@ Gem::Specification.new do |spec|
|
|
18
18
|
spec.test_files = spec.files.grep(%r{^(test|spec|features)/})
|
19
19
|
spec.require_paths = ['lib']
|
20
20
|
|
21
|
-
spec.add_dependency 'activerecord', '~> 4.2'
|
22
|
-
spec.add_dependency 'activesupport', '~> 4.2'
|
23
|
-
spec.add_dependency 'aws-sdk', '~> 1.
|
24
|
-
spec.add_dependency 'elasticity', '~>
|
25
|
-
spec.add_dependency 'highline', '~> 1.
|
26
|
-
spec.add_dependency 'sqlite3', '~> 1.3'
|
27
|
-
spec.add_dependency 'thor', '~> 0.19'
|
21
|
+
spec.add_dependency 'activerecord', '~> 4.2.5'
|
22
|
+
spec.add_dependency 'activesupport', '~> 4.2.5'
|
23
|
+
spec.add_dependency 'aws-sdk', '~> 1.66.0'
|
24
|
+
spec.add_dependency 'elasticity', '~> 6.0.5'
|
25
|
+
spec.add_dependency 'highline', '~> 1.7.8'
|
26
|
+
spec.add_dependency 'sqlite3', '~> 1.3.11'
|
27
|
+
spec.add_dependency 'thor', '~> 0.19.1'
|
28
28
|
|
29
|
-
spec.add_development_dependency 'rake'
|
30
|
-
spec.add_development_dependency 'bundler', '~> 1.
|
31
|
-
spec.add_development_dependency 'rspec', '~> 3.
|
32
|
-
spec.add_development_dependency 'database_cleaner', '~> 1.
|
33
|
-
spec.add_development_dependency 'shoulda-matchers', '~>
|
29
|
+
spec.add_development_dependency 'rake', '~> 10.4.2'
|
30
|
+
spec.add_development_dependency 'bundler', '~> 1.11.2'
|
31
|
+
spec.add_development_dependency 'rspec', '~> 3.4.0'
|
32
|
+
spec.add_development_dependency 'database_cleaner', '~> 1.5.1'
|
33
|
+
spec.add_development_dependency 'shoulda-matchers', '~> 3.0.1'
|
34
34
|
end
|
data/lib/elasticrawl/cluster.rb
CHANGED
@@ -11,8 +11,13 @@ module Elasticrawl
|
|
11
11
|
# Returns a configured job flow to the calling job.
|
12
12
|
def create_job_flow(job, emr_config = nil)
|
13
13
|
config = Config.new
|
14
|
-
|
15
|
-
|
14
|
+
|
15
|
+
Elasticity.configure do |c|
|
16
|
+
c.access_key = config.access_key_id
|
17
|
+
c.secret_key = config.secret_access_key
|
18
|
+
end
|
19
|
+
|
20
|
+
job_flow = Elasticity::JobFlow.new
|
16
21
|
job_flow.name = "Job: #{job.job_name} #{job.job_desc}"
|
17
22
|
job_flow.log_uri = job.log_uri
|
18
23
|
|
data/lib/elasticrawl/version.rb
CHANGED
data/spec/spec_helper.rb
CHANGED
@@ -7,6 +7,9 @@ RSpec.configure do |config|
|
|
7
7
|
# Run each test in a transaction and rollback data on completion.
|
8
8
|
DatabaseCleaner.strategy = :transaction
|
9
9
|
|
10
|
+
# Use Shoulda matchers for schema tests.
|
11
|
+
config.include(Shoulda::Matchers::ActiveRecord, type: :model)
|
12
|
+
|
10
13
|
config.before(:each) do
|
11
14
|
# Stub S3 call to get WARC file paths
|
12
15
|
warc_paths = IO.read(File.join(File.dirname(__FILE__), 'fixtures', 'warc.paths'))
|
data/spec/unit/crawl_spec.rb
CHANGED
data/spec/unit/job_spec.rb
CHANGED
data/spec/unit/job_step_spec.rb
CHANGED
metadata
CHANGED
@@ -1,183 +1,183 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: elasticrawl
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.1.
|
4
|
+
version: 1.1.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Ross Fairbanks
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date:
|
11
|
+
date: 2016-01-05 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: activerecord
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - ~>
|
17
|
+
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version:
|
19
|
+
version: 4.2.5
|
20
20
|
type: :runtime
|
21
21
|
prerelease: false
|
22
22
|
version_requirements: !ruby/object:Gem::Requirement
|
23
23
|
requirements:
|
24
|
-
- - ~>
|
24
|
+
- - "~>"
|
25
25
|
- !ruby/object:Gem::Version
|
26
|
-
version:
|
26
|
+
version: 4.2.5
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: activesupport
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- - ~>
|
31
|
+
- - "~>"
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version:
|
33
|
+
version: 4.2.5
|
34
34
|
type: :runtime
|
35
35
|
prerelease: false
|
36
36
|
version_requirements: !ruby/object:Gem::Requirement
|
37
37
|
requirements:
|
38
|
-
- - ~>
|
38
|
+
- - "~>"
|
39
39
|
- !ruby/object:Gem::Version
|
40
|
-
version:
|
40
|
+
version: 4.2.5
|
41
41
|
- !ruby/object:Gem::Dependency
|
42
42
|
name: aws-sdk
|
43
43
|
requirement: !ruby/object:Gem::Requirement
|
44
44
|
requirements:
|
45
|
-
- - ~>
|
45
|
+
- - "~>"
|
46
46
|
- !ruby/object:Gem::Version
|
47
|
-
version:
|
47
|
+
version: 1.66.0
|
48
48
|
type: :runtime
|
49
49
|
prerelease: false
|
50
50
|
version_requirements: !ruby/object:Gem::Requirement
|
51
51
|
requirements:
|
52
|
-
- - ~>
|
52
|
+
- - "~>"
|
53
53
|
- !ruby/object:Gem::Version
|
54
|
-
version:
|
54
|
+
version: 1.66.0
|
55
55
|
- !ruby/object:Gem::Dependency
|
56
56
|
name: elasticity
|
57
57
|
requirement: !ruby/object:Gem::Requirement
|
58
58
|
requirements:
|
59
|
-
- - ~>
|
59
|
+
- - "~>"
|
60
60
|
- !ruby/object:Gem::Version
|
61
|
-
version:
|
61
|
+
version: 6.0.5
|
62
62
|
type: :runtime
|
63
63
|
prerelease: false
|
64
64
|
version_requirements: !ruby/object:Gem::Requirement
|
65
65
|
requirements:
|
66
|
-
- - ~>
|
66
|
+
- - "~>"
|
67
67
|
- !ruby/object:Gem::Version
|
68
|
-
version:
|
68
|
+
version: 6.0.5
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: highline
|
71
71
|
requirement: !ruby/object:Gem::Requirement
|
72
72
|
requirements:
|
73
|
-
- - ~>
|
73
|
+
- - "~>"
|
74
74
|
- !ruby/object:Gem::Version
|
75
|
-
version:
|
75
|
+
version: 1.7.8
|
76
76
|
type: :runtime
|
77
77
|
prerelease: false
|
78
78
|
version_requirements: !ruby/object:Gem::Requirement
|
79
79
|
requirements:
|
80
|
-
- - ~>
|
80
|
+
- - "~>"
|
81
81
|
- !ruby/object:Gem::Version
|
82
|
-
version:
|
82
|
+
version: 1.7.8
|
83
83
|
- !ruby/object:Gem::Dependency
|
84
84
|
name: sqlite3
|
85
85
|
requirement: !ruby/object:Gem::Requirement
|
86
86
|
requirements:
|
87
|
-
- - ~>
|
87
|
+
- - "~>"
|
88
88
|
- !ruby/object:Gem::Version
|
89
|
-
version:
|
89
|
+
version: 1.3.11
|
90
90
|
type: :runtime
|
91
91
|
prerelease: false
|
92
92
|
version_requirements: !ruby/object:Gem::Requirement
|
93
93
|
requirements:
|
94
|
-
- - ~>
|
94
|
+
- - "~>"
|
95
95
|
- !ruby/object:Gem::Version
|
96
|
-
version:
|
96
|
+
version: 1.3.11
|
97
97
|
- !ruby/object:Gem::Dependency
|
98
98
|
name: thor
|
99
99
|
requirement: !ruby/object:Gem::Requirement
|
100
100
|
requirements:
|
101
|
-
- - ~>
|
101
|
+
- - "~>"
|
102
102
|
- !ruby/object:Gem::Version
|
103
|
-
version:
|
103
|
+
version: 0.19.1
|
104
104
|
type: :runtime
|
105
105
|
prerelease: false
|
106
106
|
version_requirements: !ruby/object:Gem::Requirement
|
107
107
|
requirements:
|
108
|
-
- - ~>
|
108
|
+
- - "~>"
|
109
109
|
- !ruby/object:Gem::Version
|
110
|
-
version:
|
110
|
+
version: 0.19.1
|
111
111
|
- !ruby/object:Gem::Dependency
|
112
112
|
name: rake
|
113
113
|
requirement: !ruby/object:Gem::Requirement
|
114
114
|
requirements:
|
115
|
-
- -
|
115
|
+
- - "~>"
|
116
116
|
- !ruby/object:Gem::Version
|
117
|
-
version:
|
117
|
+
version: 10.4.2
|
118
118
|
type: :development
|
119
119
|
prerelease: false
|
120
120
|
version_requirements: !ruby/object:Gem::Requirement
|
121
121
|
requirements:
|
122
|
-
- -
|
122
|
+
- - "~>"
|
123
123
|
- !ruby/object:Gem::Version
|
124
|
-
version:
|
124
|
+
version: 10.4.2
|
125
125
|
- !ruby/object:Gem::Dependency
|
126
126
|
name: bundler
|
127
127
|
requirement: !ruby/object:Gem::Requirement
|
128
128
|
requirements:
|
129
|
-
- - ~>
|
129
|
+
- - "~>"
|
130
130
|
- !ruby/object:Gem::Version
|
131
|
-
version:
|
131
|
+
version: 1.11.2
|
132
132
|
type: :development
|
133
133
|
prerelease: false
|
134
134
|
version_requirements: !ruby/object:Gem::Requirement
|
135
135
|
requirements:
|
136
|
-
- - ~>
|
136
|
+
- - "~>"
|
137
137
|
- !ruby/object:Gem::Version
|
138
|
-
version:
|
138
|
+
version: 1.11.2
|
139
139
|
- !ruby/object:Gem::Dependency
|
140
140
|
name: rspec
|
141
141
|
requirement: !ruby/object:Gem::Requirement
|
142
142
|
requirements:
|
143
|
-
- - ~>
|
143
|
+
- - "~>"
|
144
144
|
- !ruby/object:Gem::Version
|
145
|
-
version:
|
145
|
+
version: 3.4.0
|
146
146
|
type: :development
|
147
147
|
prerelease: false
|
148
148
|
version_requirements: !ruby/object:Gem::Requirement
|
149
149
|
requirements:
|
150
|
-
- - ~>
|
150
|
+
- - "~>"
|
151
151
|
- !ruby/object:Gem::Version
|
152
|
-
version:
|
152
|
+
version: 3.4.0
|
153
153
|
- !ruby/object:Gem::Dependency
|
154
154
|
name: database_cleaner
|
155
155
|
requirement: !ruby/object:Gem::Requirement
|
156
156
|
requirements:
|
157
|
-
- - ~>
|
157
|
+
- - "~>"
|
158
158
|
- !ruby/object:Gem::Version
|
159
|
-
version: 1.
|
159
|
+
version: 1.5.1
|
160
160
|
type: :development
|
161
161
|
prerelease: false
|
162
162
|
version_requirements: !ruby/object:Gem::Requirement
|
163
163
|
requirements:
|
164
|
-
- - ~>
|
164
|
+
- - "~>"
|
165
165
|
- !ruby/object:Gem::Version
|
166
|
-
version: 1.
|
166
|
+
version: 1.5.1
|
167
167
|
- !ruby/object:Gem::Dependency
|
168
168
|
name: shoulda-matchers
|
169
169
|
requirement: !ruby/object:Gem::Requirement
|
170
170
|
requirements:
|
171
|
-
- - ~>
|
171
|
+
- - "~>"
|
172
172
|
- !ruby/object:Gem::Version
|
173
|
-
version:
|
173
|
+
version: 3.0.1
|
174
174
|
type: :development
|
175
175
|
prerelease: false
|
176
176
|
version_requirements: !ruby/object:Gem::Requirement
|
177
177
|
requirements:
|
178
|
-
- - ~>
|
178
|
+
- - "~>"
|
179
179
|
- !ruby/object:Gem::Version
|
180
|
-
version:
|
180
|
+
version: 3.0.1
|
181
181
|
description: Elasticrawl is a tool for launching AWS Elastic MapReduce jobs that process
|
182
182
|
Common Crawl data.
|
183
183
|
email:
|
@@ -187,8 +187,8 @@ executables:
|
|
187
187
|
extensions: []
|
188
188
|
extra_rdoc_files: []
|
189
189
|
files:
|
190
|
-
- .gitignore
|
191
|
-
- .travis.yml
|
190
|
+
- ".gitignore"
|
191
|
+
- ".travis.yml"
|
192
192
|
- CHANGELOG.md
|
193
193
|
- Cheffile
|
194
194
|
- Cheffile.lock
|
@@ -241,17 +241,17 @@ require_paths:
|
|
241
241
|
- lib
|
242
242
|
required_ruby_version: !ruby/object:Gem::Requirement
|
243
243
|
requirements:
|
244
|
-
- -
|
244
|
+
- - ">="
|
245
245
|
- !ruby/object:Gem::Version
|
246
246
|
version: '0'
|
247
247
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
248
248
|
requirements:
|
249
|
-
- -
|
249
|
+
- - ">="
|
250
250
|
- !ruby/object:Gem::Version
|
251
251
|
version: '0'
|
252
252
|
requirements: []
|
253
253
|
rubyforge_project:
|
254
|
-
rubygems_version: 2.
|
254
|
+
rubygems_version: 2.4.5.1
|
255
255
|
signing_key:
|
256
256
|
specification_version: 4
|
257
257
|
summary: Launch AWS Elastic MapReduce jobs that process Common Crawl data.
|