cangrejo 0.1.5 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/cangrejo/errors.rb +19 -0
- data/lib/cangrejo/modes/local.rb +62 -9
- data/lib/cangrejo/session.rb +19 -4
- data/lib/cangrejo/version.rb +1 -1
- metadata +116 -28
- data/lib/cangrejo/support/launcher.rb +0 -79
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 654c44f4ed8700ac8dbb214f8fd3006540ee31cb
|
4
|
+
data.tar.gz: cdf70051e44adbee2ca3291061ddd2ac71155571
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 847580c48eb860475720e652e7ee83dbb66f91aa7c88c2a15635296f0aa9471b7d63b67209a60b532a7ed421331aa8fc98b5c3721e68e6b913a2bc1edaf98b5d
|
7
|
+
data.tar.gz: e42eda249f094f9eca98b8a67f2f1bf77de681fe4c20e8538872ec46977a8cd5f255b9c96d2907cbc0dc72baddb71eb8d1664df1d30a92caa2d2238c66ff6984
|
data/lib/cangrejo/errors.rb
CHANGED
@@ -4,4 +4,23 @@ module Cangrejo
|
|
4
4
|
|
5
5
|
class ConfigurationError < Error; end
|
6
6
|
|
7
|
+
class LaunchTimeout < Error
|
8
|
+
def initialize(_msg)
|
9
|
+
super "Timed out trying to start crawler"
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
class CrawlerError < Error
|
14
|
+
|
15
|
+
def initialize(_msg, _backtrace)
|
16
|
+
super _msg
|
17
|
+
@original_bt = _backtrace
|
18
|
+
end
|
19
|
+
|
20
|
+
def set_backtrace(_backtrace)
|
21
|
+
super @original_bt + _backtrace
|
22
|
+
end
|
23
|
+
|
24
|
+
end
|
25
|
+
|
7
26
|
end
|
data/lib/cangrejo/modes/local.rb
CHANGED
@@ -1,41 +1,94 @@
|
|
1
1
|
require "cangrejo/restclient/request_extensions"
|
2
2
|
require "cangrejo/restclient/json_resource"
|
3
|
-
require "
|
3
|
+
require "childprocess"
|
4
4
|
|
5
5
|
module Cangrejo
|
6
6
|
module Modes
|
7
7
|
class Local
|
8
8
|
|
9
|
+
attr_reader :process, :path
|
10
|
+
|
9
11
|
def initialize(_path)
|
10
12
|
@path = _path
|
11
13
|
end
|
12
14
|
|
13
15
|
def setup
|
14
|
-
|
16
|
+
select_socket_file
|
17
|
+
start_process
|
18
|
+
wait_for_socket
|
15
19
|
init_rest_client
|
16
20
|
end
|
17
21
|
|
18
22
|
def release
|
19
|
-
|
23
|
+
process.stop unless process.nil?
|
20
24
|
end
|
21
25
|
|
22
26
|
private
|
23
27
|
|
24
|
-
def
|
25
|
-
|
26
|
-
|
28
|
+
def cmd_enviroment
|
29
|
+
{
|
30
|
+
'BUNDLE_GEMFILE' => gem_path
|
31
|
+
}
|
32
|
+
end
|
33
|
+
|
34
|
+
def cmd_arguments
|
35
|
+
[
|
36
|
+
'--no-reload'
|
37
|
+
]
|
27
38
|
end
|
28
39
|
|
29
40
|
def launch_timeout
|
30
41
|
5.0
|
31
42
|
end
|
32
43
|
|
33
|
-
def
|
34
|
-
|
44
|
+
def start_process
|
45
|
+
@process = prepare_process
|
46
|
+
@process.start
|
47
|
+
end
|
48
|
+
|
49
|
+
def prepare_process
|
50
|
+
cmd = [ "bin/crabfarm", "s", "--host=#{host}" ]
|
51
|
+
cmd += cmd_arguments
|
52
|
+
|
53
|
+
puts cmd.join(' ')
|
54
|
+
|
55
|
+
cp = ChildProcess.build(*cmd)
|
56
|
+
cp.environment.merge! cmd_enviroment
|
57
|
+
cp.cwd = @path
|
58
|
+
cp.leader = true
|
59
|
+
cp.io.inherit!
|
60
|
+
|
61
|
+
return cp
|
62
|
+
end
|
63
|
+
|
64
|
+
def wait_for_socket
|
65
|
+
Timeout::timeout(launch_timeout, LaunchTimeout) do
|
66
|
+
# TODO: detect if the process crashes before timeout
|
67
|
+
sleep 0.1 while not File.exist? @socket_file
|
68
|
+
end
|
35
69
|
end
|
36
70
|
|
37
71
|
def init_rest_client
|
38
|
-
RestClient::JsonResource.new Net::SocketUri.new(
|
72
|
+
RestClient::JsonResource.new Net::SocketUri.new(host, '/api/state')
|
73
|
+
end
|
74
|
+
|
75
|
+
def select_socket_file
|
76
|
+
@socket_file = random_filename while @socket_file.nil? or File.exist? @socket_file
|
77
|
+
end
|
78
|
+
|
79
|
+
def random_filename
|
80
|
+
File.join(Cangrejo.config.temp_path, "csocket-#{Random.rand(1000000)}.sock")
|
81
|
+
end
|
82
|
+
|
83
|
+
def gem_path
|
84
|
+
File.join(@path, 'Gemfile')
|
85
|
+
end
|
86
|
+
|
87
|
+
def host
|
88
|
+
# TODO: add posibility to use ports instead of unix sockets, it would also
|
89
|
+
# be nice to have a mechanism where the loaded process reports the port it
|
90
|
+
# binded to.
|
91
|
+
"unix://#{@socket_file}"
|
39
92
|
end
|
40
93
|
|
41
94
|
end
|
data/lib/cangrejo/session.rb
CHANGED
@@ -53,16 +53,22 @@ module Cangrejo
|
|
53
53
|
|
54
54
|
params = add_timestamp(_params)
|
55
55
|
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
56
|
+
begin
|
57
|
+
while_times_out do
|
58
|
+
@rest.put(name: _state, params: params, wait: WAIT_STEP)
|
59
|
+
@state_name = _state
|
60
|
+
@state_params = _params
|
61
|
+
end
|
62
|
+
rescue RestClient::InternalServerError => exc
|
63
|
+
raise unwrap_packed_exception exc
|
60
64
|
end
|
61
65
|
|
62
66
|
wrap_response_doc
|
63
67
|
self
|
64
68
|
end
|
65
69
|
|
70
|
+
alias :navigate :crawl
|
71
|
+
|
66
72
|
def release
|
67
73
|
@mode.release
|
68
74
|
@rest = nil
|
@@ -107,5 +113,14 @@ module Cangrejo
|
|
107
113
|
end
|
108
114
|
end
|
109
115
|
|
116
|
+
def unwrap_packed_exception(_exc)
|
117
|
+
begin
|
118
|
+
data = JSON.parse _exc.http_body
|
119
|
+
Cangrejo::CrawlerError.new data['exception'], data['backtrace']
|
120
|
+
rescue
|
121
|
+
_exc
|
122
|
+
end
|
123
|
+
end
|
124
|
+
|
110
125
|
end
|
111
126
|
end
|
data/lib/cangrejo/version.rb
CHANGED
metadata
CHANGED
@@ -1,92 +1,183 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: cangrejo
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.2.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Ignacio Baixas
|
8
8
|
autorequire:
|
9
9
|
bindir: bin
|
10
10
|
cert_chain: []
|
11
|
-
date: 2015-
|
11
|
+
date: 2015-09-28 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: rest-client
|
15
15
|
requirement: !ruby/object:Gem::Requirement
|
16
16
|
requirements:
|
17
|
-
- - ~>
|
17
|
+
- - "~>"
|
18
18
|
- !ruby/object:Gem::Version
|
19
|
-
version: 1.7
|
19
|
+
version: '1.7'
|
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: 1.7
|
26
|
+
version: '1.7'
|
27
27
|
- !ruby/object:Gem::Dependency
|
28
28
|
name: git
|
29
29
|
requirement: !ruby/object:Gem::Requirement
|
30
30
|
requirements:
|
31
|
-
- -
|
31
|
+
- - "~>"
|
32
32
|
- !ruby/object:Gem::Version
|
33
|
-
version: '
|
33
|
+
version: '1.2'
|
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: '1.2'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: childprocess
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '0.5'
|
48
|
+
type: :runtime
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0.5'
|
41
55
|
- !ruby/object:Gem::Dependency
|
42
56
|
name: bundler
|
43
57
|
requirement: !ruby/object:Gem::Requirement
|
44
58
|
requirements:
|
45
|
-
- - ~>
|
59
|
+
- - "~>"
|
46
60
|
- !ruby/object:Gem::Version
|
47
61
|
version: '1.6'
|
48
62
|
type: :development
|
49
63
|
prerelease: false
|
50
64
|
version_requirements: !ruby/object:Gem::Requirement
|
51
65
|
requirements:
|
52
|
-
- - ~>
|
66
|
+
- - "~>"
|
53
67
|
- !ruby/object:Gem::Version
|
54
68
|
version: '1.6'
|
55
69
|
- !ruby/object:Gem::Dependency
|
56
70
|
name: rake
|
57
71
|
requirement: !ruby/object:Gem::Requirement
|
58
72
|
requirements:
|
59
|
-
- -
|
73
|
+
- - "~>"
|
60
74
|
- !ruby/object:Gem::Version
|
61
|
-
version: '
|
75
|
+
version: '10.4'
|
62
76
|
type: :development
|
63
77
|
prerelease: false
|
64
78
|
version_requirements: !ruby/object:Gem::Requirement
|
65
79
|
requirements:
|
66
|
-
- -
|
80
|
+
- - "~>"
|
67
81
|
- !ruby/object:Gem::Version
|
68
|
-
version: '
|
82
|
+
version: '10.4'
|
69
83
|
- !ruby/object:Gem::Dependency
|
70
84
|
name: rspec
|
71
85
|
requirement: !ruby/object:Gem::Requirement
|
72
86
|
requirements:
|
73
|
-
- -
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '3.1'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '3.1'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: rspec-nc
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '0.2'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '0.2'
|
111
|
+
- !ruby/object:Gem::Dependency
|
112
|
+
name: guard
|
113
|
+
requirement: !ruby/object:Gem::Requirement
|
114
|
+
requirements:
|
115
|
+
- - "~>"
|
116
|
+
- !ruby/object:Gem::Version
|
117
|
+
version: '2.11'
|
118
|
+
type: :development
|
119
|
+
prerelease: false
|
120
|
+
version_requirements: !ruby/object:Gem::Requirement
|
121
|
+
requirements:
|
122
|
+
- - "~>"
|
123
|
+
- !ruby/object:Gem::Version
|
124
|
+
version: '2.11'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: guard-rspec
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - "~>"
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '4.5'
|
132
|
+
type: :development
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - "~>"
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '4.5'
|
139
|
+
- !ruby/object:Gem::Dependency
|
140
|
+
name: terminal-notifier-guard
|
141
|
+
requirement: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - "~>"
|
74
144
|
- !ruby/object:Gem::Version
|
75
|
-
version: '
|
145
|
+
version: '1.6'
|
146
|
+
- - ">="
|
147
|
+
- !ruby/object:Gem::Version
|
148
|
+
version: 1.6.1
|
76
149
|
type: :development
|
77
150
|
prerelease: false
|
78
151
|
version_requirements: !ruby/object:Gem::Requirement
|
79
152
|
requirements:
|
80
|
-
- -
|
153
|
+
- - "~>"
|
154
|
+
- !ruby/object:Gem::Version
|
155
|
+
version: '1.6'
|
156
|
+
- - ">="
|
157
|
+
- !ruby/object:Gem::Version
|
158
|
+
version: 1.6.1
|
159
|
+
- !ruby/object:Gem::Dependency
|
160
|
+
name: sys-proctable
|
161
|
+
requirement: !ruby/object:Gem::Requirement
|
162
|
+
requirements:
|
163
|
+
- - "~>"
|
81
164
|
- !ruby/object:Gem::Version
|
82
|
-
version: '0'
|
83
|
-
|
165
|
+
version: '0.9'
|
166
|
+
type: :development
|
167
|
+
prerelease: false
|
168
|
+
version_requirements: !ruby/object:Gem::Requirement
|
169
|
+
requirements:
|
170
|
+
- - "~>"
|
171
|
+
- !ruby/object:Gem::Version
|
172
|
+
version: '0.9'
|
173
|
+
description: Cangrejo lets you consume crabfarm crawlers using a simple DSL
|
84
174
|
email:
|
85
175
|
- ignacio@platan.us
|
86
176
|
executables: []
|
87
177
|
extensions: []
|
88
178
|
extra_rdoc_files: []
|
89
179
|
files:
|
180
|
+
- lib/cangrejo.rb
|
90
181
|
- lib/cangrejo/configurator.rb
|
91
182
|
- lib/cangrejo/errors.rb
|
92
183
|
- lib/cangrejo/modes/git.rb
|
@@ -97,10 +188,8 @@ files:
|
|
97
188
|
- lib/cangrejo/restclient/json_resource.rb
|
98
189
|
- lib/cangrejo/restclient/request_extensions.rb
|
99
190
|
- lib/cangrejo/session.rb
|
100
|
-
- lib/cangrejo/support/launcher.rb
|
101
191
|
- lib/cangrejo/version.rb
|
102
|
-
|
103
|
-
homepage: ''
|
192
|
+
homepage: https://github.com/platanus/cangrejo-gem
|
104
193
|
licenses:
|
105
194
|
- MIT
|
106
195
|
metadata: {}
|
@@ -110,19 +199,18 @@ require_paths:
|
|
110
199
|
- lib
|
111
200
|
required_ruby_version: !ruby/object:Gem::Requirement
|
112
201
|
requirements:
|
113
|
-
- -
|
202
|
+
- - ">="
|
114
203
|
- !ruby/object:Gem::Version
|
115
204
|
version: '0'
|
116
205
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
117
206
|
requirements:
|
118
|
-
- -
|
207
|
+
- - ">="
|
119
208
|
- !ruby/object:Gem::Version
|
120
209
|
version: '0'
|
121
210
|
requirements: []
|
122
211
|
rubyforge_project:
|
123
|
-
rubygems_version: 2.
|
212
|
+
rubygems_version: 2.4.5
|
124
213
|
signing_key:
|
125
214
|
specification_version: 4
|
126
215
|
summary: Crabfarm client for ruby
|
127
216
|
test_files: []
|
128
|
-
has_rdoc:
|
@@ -1,79 +0,0 @@
|
|
1
|
-
require 'timeout'
|
2
|
-
|
3
|
-
module Cangrejo
|
4
|
-
module Support
|
5
|
-
class Launcher
|
6
|
-
|
7
|
-
class LaunchTimeout < Cangrejo::Error
|
8
|
-
def initialize(_msg)
|
9
|
-
super "Timed out trying to start crawler"
|
10
|
-
end
|
11
|
-
end
|
12
|
-
|
13
|
-
SPAWN_TIMEOUT = 5
|
14
|
-
KILL_TIMEOUT = 5
|
15
|
-
|
16
|
-
def initialize(_path, _options={})
|
17
|
-
@path = _path
|
18
|
-
@timeout = _options.fetch(:timeout, SPAWN_TIMEOUT)
|
19
|
-
@argv = _options.fetch(:argv, [])
|
20
|
-
select_socket_file
|
21
|
-
end
|
22
|
-
|
23
|
-
def host
|
24
|
-
"unix://#{@socket_file}"
|
25
|
-
end
|
26
|
-
|
27
|
-
def launch
|
28
|
-
gem_path = File.join(@path, 'Gemfile')
|
29
|
-
# TODO: for some reason, the gemfile path must be specified here, maybe because of rbenv?
|
30
|
-
@pid = Process.spawn({ 'BUNDLE_GEMFILE' => gem_path }, "bin/crabfarm s --host=#{host} #{@argv.join(' ')}", chdir: @path, pgroup: true)
|
31
|
-
wait_for_socket
|
32
|
-
end
|
33
|
-
|
34
|
-
def kill
|
35
|
-
safe_kill @pid unless @pid.nil?
|
36
|
-
end
|
37
|
-
|
38
|
-
private
|
39
|
-
|
40
|
-
def select_socket_file
|
41
|
-
@socket_file = random_filename while @socket_file.nil? or File.exist? @socket_file
|
42
|
-
end
|
43
|
-
|
44
|
-
def random_filename
|
45
|
-
File.join(Cangrejo.config.temp_path, "csocket-#{Random.rand(1000000)}.sock")
|
46
|
-
end
|
47
|
-
|
48
|
-
def wait_for_socket
|
49
|
-
Timeout::timeout(@timeout, LaunchTimeout) do
|
50
|
-
# TODO: detect if the process crashes before timeout
|
51
|
-
sleep 0.1 while not File.exist? @socket_file
|
52
|
-
end
|
53
|
-
end
|
54
|
-
|
55
|
-
def safe_kill _pid
|
56
|
-
begin
|
57
|
-
Timeout.timeout(KILL_TIMEOUT) do
|
58
|
-
Process.kill "INT", _pid
|
59
|
-
Process.wait _pid
|
60
|
-
end
|
61
|
-
rescue Timeout::Error
|
62
|
-
ensure
|
63
|
-
ensure_dead _pid
|
64
|
-
end
|
65
|
-
end
|
66
|
-
|
67
|
-
def ensure_dead _pid
|
68
|
-
begin
|
69
|
-
# Kill the entire process group to make sure childs aren't left hanging around
|
70
|
-
Process.kill(-9, _pid)
|
71
|
-
Process.wait _pid
|
72
|
-
rescue
|
73
|
-
nil
|
74
|
-
end
|
75
|
-
end
|
76
|
-
|
77
|
-
end
|
78
|
-
end
|
79
|
-
end
|