right_scraper 1.0.0 → 1.0.1
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/lib/right_scraper/scraper.rb +13 -2
- data/lib/right_scraper/scraper_base.rb +23 -9
- data/lib/right_scraper/scrapers/download_scraper.rb +3 -3
- data/lib/right_scraper/scrapers/git_scraper.rb +6 -6
- data/lib/right_scraper/scrapers/svn_scraper.rb +5 -5
- data/right_scraper.gemspec +1 -1
- data/spec/download_scraper_spec.rb +2 -2
- data/spec/git_scraper_spec.rb +4 -4
- data/spec/scraper_base_spec.rb +6 -1
- data/spec/scraper_spec.rb +4 -4
- data/spec/svn_scraper_spec.rb +4 -4
- metadata +2 -2
@@ -34,7 +34,7 @@ module RightScale
|
|
34
34
|
|
35
35
|
# (String) Path to directory where remote repository was downloaded
|
36
36
|
# Note: This will be a subfolder of the scrape directory (directory given to initializer)
|
37
|
-
attr_reader :
|
37
|
+
attr_reader :last_repo_dir
|
38
38
|
|
39
39
|
# Initialize scrape destination directory
|
40
40
|
#
|
@@ -72,9 +72,20 @@ module RightScale
|
|
72
72
|
raise "Invalid repository type" unless SCRAPERS.include?(repo.repo_type)
|
73
73
|
@scraper = @scrapers[repo.repo_type] ||= SCRAPERS[repo.repo_type].new(@scrape_dir)
|
74
74
|
@scraper.scrape(repo, &callback)
|
75
|
-
@
|
75
|
+
@last_repo_dir = @scraper.current_repo_dir
|
76
76
|
@scraper.succeeded?
|
77
77
|
end
|
78
|
+
|
79
|
+
# Retrieve directory path where repo was or would be downloaded
|
80
|
+
#
|
81
|
+
# === Parameters
|
82
|
+
# repo(Hash|RightScale::Repository):: Remote repository corresponding to local directory
|
83
|
+
#
|
84
|
+
# === Return
|
85
|
+
# repo_dir(String):: Path to local directory that corresponds to given repository
|
86
|
+
def repo_dir(repo)
|
87
|
+
repo_dir = RightScale::ScraperBase.repo_dir(scrape_dir, repo)
|
88
|
+
end
|
78
89
|
|
79
90
|
# Error messages in case of failure
|
80
91
|
#
|
@@ -39,7 +39,7 @@ module RightScale
|
|
39
39
|
attr_reader :errors
|
40
40
|
|
41
41
|
# (String) Path to local directory where repository was downloaded
|
42
|
-
attr_reader :
|
42
|
+
attr_reader :current_repo_dir
|
43
43
|
|
44
44
|
# Set path to directory containing all scraped repos
|
45
45
|
#
|
@@ -54,17 +54,31 @@ module RightScale
|
|
54
54
|
# after this method initializes all the scraper attributes properly.
|
55
55
|
# See RightScale::Scraper#scrape
|
56
56
|
def scrape(repo, &callback)
|
57
|
-
@repo
|
58
|
-
@callback
|
59
|
-
@
|
60
|
-
@scrape_dir_path
|
61
|
-
@
|
62
|
-
@
|
63
|
-
@
|
64
|
-
FileUtils.rm_rf(@repo_dir) unless @incremental
|
57
|
+
@repo = repo
|
58
|
+
@callback = callback
|
59
|
+
@current_repo_dir = ScraperBase.repo_dir(root_dir, repo)
|
60
|
+
@scrape_dir_path = File.expand_path(File.join(@current_repo_dir, '..'))
|
61
|
+
@incremental = incremental_update?
|
62
|
+
@errors = []
|
63
|
+
FileUtils.rm_rf(@current_repo_dir) unless @incremental
|
65
64
|
scrape_imp
|
66
65
|
true
|
67
66
|
end
|
67
|
+
|
68
|
+
# Path to directory where given repo should be or was downloaded
|
69
|
+
#
|
70
|
+
# === Parameters
|
71
|
+
# root_dir(String):: Path to directory containing all scraped repositories
|
72
|
+
# repo(Hash|RightScale::Repository):: Remote repository corresponding to local directory
|
73
|
+
#
|
74
|
+
# === Return
|
75
|
+
# repo_dir(String):: Path to local directory that corresponds to given repository
|
76
|
+
def self.repo_dir(root_dir, repo)
|
77
|
+
repo = Repository.from_hash(repo) if repo.is_a?(Hash)
|
78
|
+
dir_name = Digest::MD5.hexdigest(repo.to_s)
|
79
|
+
dir_path = File.join(root_dir, dir_name)
|
80
|
+
repo_dir = "#{dir_path}/repo"
|
81
|
+
end
|
68
82
|
|
69
83
|
# Was last call to scrapesuccessful?
|
70
84
|
# Call errors to get error messages if false
|
@@ -34,8 +34,8 @@ module RightScale
|
|
34
34
|
@callback.call(msg, is_step=true) if @callback
|
35
35
|
filename = @repo.url.split('/').last
|
36
36
|
user_opt = @repo.first_credential && @repo.second_credential ? "--user #{@repo.first_credential}:#{@repo.second_credential}" : ''
|
37
|
-
cmd = "curl --fail --silent --show-error --insecure --location #{user_opt} --output '#{@
|
38
|
-
FileUtils.mkdir_p(@
|
37
|
+
cmd = "curl --fail --silent --show-error --insecure --location #{user_opt} --output '#{@current_repo_dir}/#{filename}' '#{@repo.url}' 2>&1"
|
38
|
+
FileUtils.mkdir_p(@current_repo_dir)
|
39
39
|
res = `#{cmd}`
|
40
40
|
@errors << res if $? != 0
|
41
41
|
if succeeded?
|
@@ -44,7 +44,7 @@ module RightScale
|
|
44
44
|
when 'tgz', 'gzip' then 'z'
|
45
45
|
else ''
|
46
46
|
end
|
47
|
-
Dir.chdir(@
|
47
|
+
Dir.chdir(@current_repo_dir) do
|
48
48
|
cmd = "tar x#{unzip_opt}f #{filename} 2>&1"
|
49
49
|
res = `#{cmd}`
|
50
50
|
@errors << res if $? != 0
|
@@ -32,8 +32,8 @@ module RightScale
|
|
32
32
|
# incremental updates
|
33
33
|
# false:: Otherwise
|
34
34
|
def incremental_update?
|
35
|
-
return false unless File.directory?(@
|
36
|
-
Dir.chdir(@
|
35
|
+
return false unless File.directory?(@current_repo_dir)
|
36
|
+
Dir.chdir(@current_repo_dir) do
|
37
37
|
remote_url = `git config --get remote.origin.url`.chomp
|
38
38
|
$?.success? && remote_url == @repo.url
|
39
39
|
end
|
@@ -53,7 +53,7 @@ module RightScale
|
|
53
53
|
is_branch = nil
|
54
54
|
|
55
55
|
if @incremental
|
56
|
-
Dir.chdir(@
|
56
|
+
Dir.chdir(@current_repo_dir) do
|
57
57
|
is_tag, is_branch, res = git_tag_kind(ssh_cmd)
|
58
58
|
if !is_tag && !is_branch
|
59
59
|
@callback.call("Nothing to update: repo tag refers to neither a branch nor a tag", is_step=false)
|
@@ -66,17 +66,17 @@ module RightScale
|
|
66
66
|
res += `#{ssh_cmd} git pull --quiet --depth 1 origin #{tag} 2>&1`
|
67
67
|
if $? != 0
|
68
68
|
@callback.call("Failed to pull repo: #{res}, falling back to cloning", is_step=false) if @callback
|
69
|
-
FileUtils.rm_rf(@
|
69
|
+
FileUtils.rm_rf(@current_repo_dir)
|
70
70
|
@incremental = false
|
71
71
|
end
|
72
72
|
end
|
73
73
|
end
|
74
74
|
end
|
75
75
|
if !@incremental
|
76
|
-
res += `#{ssh_cmd} git clone --quiet --depth 1 #{@repo.url} #{@
|
76
|
+
res += `#{ssh_cmd} git clone --quiet --depth 1 #{@repo.url} #{@current_repo_dir} 2>&1`
|
77
77
|
@errors << res if $? != 0
|
78
78
|
if !@repo.tag.nil? && !@repo.tag.empty? && @repo.tag != 'master' && succeeded?
|
79
|
-
Dir.chdir(@
|
79
|
+
Dir.chdir(@current_repo_dir) do
|
80
80
|
if is_tag.nil?
|
81
81
|
is_tag, is_branch, out = git_tag_kind(ssh_cmd)
|
82
82
|
res += out
|
@@ -32,8 +32,8 @@ module RightScale
|
|
32
32
|
# incremental updates
|
33
33
|
# false:: Otherwise
|
34
34
|
def incremental_update?
|
35
|
-
return false unless File.directory?(@
|
36
|
-
Dir.chdir(@
|
35
|
+
return false unless File.directory?(@current_repo_dir)
|
36
|
+
Dir.chdir(@current_repo_dir) do
|
37
37
|
info = `svn info`
|
38
38
|
$?.success? && info =~ (/^URL: (.*)$/) && $1 == @repo.url
|
39
39
|
end
|
@@ -52,17 +52,17 @@ module RightScale
|
|
52
52
|
(@repo.first_credential ? " --username #{@repo.first_credential}" : '') +
|
53
53
|
(@repo.second_credential ? " --password #{@repo.second_credential}" : '') +
|
54
54
|
' 2>&1'
|
55
|
-
Dir.chdir(@
|
55
|
+
Dir.chdir(@current_repo_dir) do
|
56
56
|
res = `#{svn_cmd}`
|
57
57
|
if $? != 0
|
58
58
|
@callback.call("Failed to update repo: #{res}, falling back to checkout", is_step=false) if @callback
|
59
|
-
FileUtils.rm_rf(@
|
59
|
+
FileUtils.rm_rf(@current_repo_dir)
|
60
60
|
@incremental = false
|
61
61
|
end
|
62
62
|
end
|
63
63
|
end
|
64
64
|
if !@incremental
|
65
|
-
svn_cmd = "svn checkout #{@repo.url} #{@
|
65
|
+
svn_cmd = "svn checkout #{@repo.url} #{@current_repo_dir} --non-interactive --quiet" +
|
66
66
|
(!@repo.tag.nil? && !@repo.tag.empty? ? " --revision #{@repo.tag}" : '') +
|
67
67
|
(@repo.first_credential ? " --username #{@repo.first_credential}" : '') +
|
68
68
|
(@repo.second_credential ? " --password #{@repo.second_credential}" : '') +
|
data/right_scraper.gemspec
CHANGED
@@ -23,7 +23,7 @@ require 'rubygems'
|
|
23
23
|
|
24
24
|
spec = Gem::Specification.new do |spec|
|
25
25
|
spec.name = 'right_scraper'
|
26
|
-
spec.version = '1.0.
|
26
|
+
spec.version = '1.0.1'
|
27
27
|
spec.authors = ['Raphael Simon']
|
28
28
|
spec.email = 'raphael@rightscale.com'
|
29
29
|
spec.homepage = 'https://github.com/rightscale/right_scraper'
|
@@ -78,8 +78,8 @@ describe RightScale::DownloadScraper do
|
|
78
78
|
puts "\n **ERRORS: #{@scraper.error_message}\n" unless @scraper.succeeded?
|
79
79
|
@scraper.succeeded?.should be_true
|
80
80
|
messages.size.should == 1
|
81
|
-
File.directory?(@scraper.
|
82
|
-
extract_file_layout(@scraper.
|
81
|
+
File.directory?(@scraper.current_repo_dir.should be_true)
|
82
|
+
extract_file_layout(@scraper.current_repo_dir).should == @repo_content
|
83
83
|
end
|
84
84
|
|
85
85
|
end
|
data/spec/git_scraper_spec.rb
CHANGED
@@ -86,8 +86,8 @@ describe RightScale::GitScraper do
|
|
86
86
|
puts "\n **ERRORS: #{@scraper.error_message}\n" unless @scraper.succeeded?
|
87
87
|
@scraper.succeeded?.should be_true
|
88
88
|
messages.size.should == 1
|
89
|
-
File.directory?(@scraper.
|
90
|
-
extract_file_layout(@scraper.
|
89
|
+
File.directory?(@scraper.current_repo_dir.should be_true)
|
90
|
+
extract_file_layout(@scraper.current_repo_dir, [ '.git', '.ssh' ]).should == @repo_content
|
91
91
|
end
|
92
92
|
|
93
93
|
it 'should scrape incrementally' do
|
@@ -99,8 +99,8 @@ describe RightScale::GitScraper do
|
|
99
99
|
puts "\n **ERRORS: #{@scraper.error_message}\n" unless @scraper.succeeded?
|
100
100
|
@scraper.succeeded?.should be_true
|
101
101
|
messages.size.should == 1
|
102
|
-
File.directory?(@scraper.
|
103
|
-
extract_file_layout(@scraper.
|
102
|
+
File.directory?(@scraper.current_repo_dir.should be_true)
|
103
|
+
extract_file_layout(@scraper.current_repo_dir, [ '.git', '.ssh' ]).should == @repo_content
|
104
104
|
end
|
105
105
|
|
106
106
|
end
|
data/spec/scraper_base_spec.rb
CHANGED
@@ -38,4 +38,9 @@ describe RightScale::ScraperBase do
|
|
38
38
|
@base.send(:incremental_update?).should be_false
|
39
39
|
end
|
40
40
|
|
41
|
-
|
41
|
+
it 'should allow retrieving the download directory path' do
|
42
|
+
repo_dir = RightScale::ScraperBase.repo_dir('root_dir', { :repo_type => :git, :url => 'git://github.com/rightscale/right_scraper.git' })
|
43
|
+
repo_dir.should =~ /^root_dir\//
|
44
|
+
end
|
45
|
+
|
46
|
+
end
|
data/spec/scraper_spec.rb
CHANGED
@@ -45,22 +45,22 @@ describe RightScale::Scraper do
|
|
45
45
|
repo.repo_type = :mock
|
46
46
|
@mock_scraper.should_receive(:scrape).with(repo, Proc).and_return(true)
|
47
47
|
@mock_scraper.should_receive(:succeeded?).and_return(true)
|
48
|
-
@mock_scraper.should_receive(:
|
48
|
+
@mock_scraper.should_receive(:current_repo_dir).and_return('42')
|
49
49
|
@scraper.scrape(repo) { }.should be_true
|
50
|
-
@scraper.
|
50
|
+
@scraper.last_repo_dir.should == '42'
|
51
51
|
end
|
52
52
|
|
53
53
|
it 'should scrape from a hash' do
|
54
54
|
@mock_scraper.should_receive(:scrape).with(RightScale::Repository, Proc).and_return(true)
|
55
55
|
@mock_scraper.should_receive(:succeeded?).and_return(true)
|
56
|
-
@mock_scraper.should_receive(:
|
56
|
+
@mock_scraper.should_receive(:current_repo_dir).and_return('42')
|
57
57
|
@scraper.scrape({:repo_type => :mock}) { }.should be_true
|
58
58
|
end
|
59
59
|
|
60
60
|
it 'should report failures' do
|
61
61
|
@mock_scraper.should_receive(:scrape).with(RightScale::Repository, Proc).and_return(true)
|
62
62
|
@mock_scraper.should_receive(:succeeded?).and_return(false)
|
63
|
-
@mock_scraper.should_receive(:
|
63
|
+
@mock_scraper.should_receive(:current_repo_dir).and_return('42')
|
64
64
|
@scraper.scrape({:repo_type => :mock}) { }.should be_false
|
65
65
|
end
|
66
66
|
|
data/spec/svn_scraper_spec.rb
CHANGED
@@ -82,8 +82,8 @@ describe RightScale::SvnScraper do
|
|
82
82
|
puts "\n **ERRORS: #{@scraper.error_message}\n" unless @scraper.succeeded?
|
83
83
|
@scraper.succeeded?.should be_true
|
84
84
|
messages.size.should == 1
|
85
|
-
File.directory?(@scraper.
|
86
|
-
extract_file_layout(@scraper.
|
85
|
+
File.directory?(@scraper.current_repo_dir.should be_true)
|
86
|
+
extract_file_layout(@scraper.current_repo_dir, [ '.svn' ]).should == @repo_content
|
87
87
|
end
|
88
88
|
|
89
89
|
it 'should scrape incrementally' do
|
@@ -95,8 +95,8 @@ describe RightScale::SvnScraper do
|
|
95
95
|
puts "\n **ERRORS: #{@scraper.error_message}\n" unless @scraper.succeeded?
|
96
96
|
@scraper.succeeded?.should be_true
|
97
97
|
messages.size.should == 1
|
98
|
-
File.directory?(@scraper.
|
99
|
-
extract_file_layout(@scraper.
|
98
|
+
File.directory?(@scraper.current_repo_dir.should be_true)
|
99
|
+
extract_file_layout(@scraper.current_repo_dir, [ '.svn' ]).should == @repo_content
|
100
100
|
end
|
101
101
|
|
102
102
|
end
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: right_scraper
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.1
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Raphael Simon
|
@@ -9,7 +9,7 @@ autorequire:
|
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
11
|
|
12
|
-
date: 2010-01-
|
12
|
+
date: 2010-01-26 00:00:00 -08:00
|
13
13
|
default_executable:
|
14
14
|
dependencies: []
|
15
15
|
|