ae_easy-core 0.2.0 → 0.2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CODE_OF_CONDUCT.md +1 -1
- data/Gemfile +1 -1
- data/LICENSE +1 -1
- data/README.md +8 -4
- data/Rakefile +0 -10
- data/ae_easy-core.gemspec +6 -13
- data/lib/ae_easy/core.rb +4 -256
- metadata +18 -125
- data/doc/AeEasy.html +0 -117
- data/doc/AeEasy/Core.html +0 -1590
- data/doc/AeEasy/Core/Config.html +0 -311
- data/doc/AeEasy/Core/Exception.html +0 -117
- data/doc/AeEasy/Core/Exception/OutdatedError.html +0 -135
- data/doc/AeEasy/Core/Helper.html +0 -117
- data/doc/AeEasy/Core/Helper/Cookie.html +0 -1070
- data/doc/AeEasy/Core/Mock.html +0 -282
- data/doc/AeEasy/Core/Mock/FakeDb.html +0 -3779
- data/doc/AeEasy/Core/Mock/FakeExecutor.html +0 -3289
- data/doc/AeEasy/Core/Mock/FakeFinisher.html +0 -160
- data/doc/AeEasy/Core/Mock/FakeParser.html +0 -160
- data/doc/AeEasy/Core/Mock/FakeSeeder.html +0 -160
- data/doc/AeEasy/Core/Plugin.html +0 -117
- data/doc/AeEasy/Core/Plugin/CollectionVault.html +0 -299
- data/doc/AeEasy/Core/Plugin/ConfigBehavior.html +0 -541
- data/doc/AeEasy/Core/Plugin/ContextIntegrator.html +0 -445
- data/doc/AeEasy/Core/Plugin/Executor.html +0 -259
- data/doc/AeEasy/Core/Plugin/ExecutorBehavior.html +0 -344
- data/doc/AeEasy/Core/Plugin/Finisher.html +0 -265
- data/doc/AeEasy/Core/Plugin/FinisherBehavior.html +0 -142
- data/doc/AeEasy/Core/Plugin/InitializeHook.html +0 -220
- data/doc/AeEasy/Core/Plugin/Parser.html +0 -270
- data/doc/AeEasy/Core/Plugin/ParserBehavior.html +0 -235
- data/doc/AeEasy/Core/Plugin/Seeder.html +0 -674
- data/doc/AeEasy/Core/Plugin/SeederBehavior.html +0 -142
- data/doc/AeEasy/Core/SmartCollection.html +0 -1087
- data/doc/_index.html +0 -364
- data/doc/class_list.html +0 -51
- data/doc/css/common.css +0 -1
- data/doc/css/full_list.css +0 -58
- data/doc/css/style.css +0 -496
- data/doc/file.README.html +0 -91
- data/doc/file_list.html +0 -56
- data/doc/frames.html +0 -17
- data/doc/index.html +0 -91
- data/doc/js/app.js +0 -303
- data/doc/js/full_list.js +0 -216
- data/doc/js/jquery.js +0 -4
- data/doc/method_list.html +0 -939
- data/doc/top-level-namespace.html +0 -110
- data/lib/ae_easy/core/config.rb +0 -27
- data/lib/ae_easy/core/exception.rb +0 -8
- data/lib/ae_easy/core/exception/outdated_error.rb +0 -9
- data/lib/ae_easy/core/helper.rb +0 -8
- data/lib/ae_easy/core/helper/cookie.rb +0 -209
- data/lib/ae_easy/core/mock.rb +0 -45
- data/lib/ae_easy/core/mock/fake_db.rb +0 -561
- data/lib/ae_easy/core/mock/fake_executor.rb +0 -373
- data/lib/ae_easy/core/mock/fake_finisher.rb +0 -28
- data/lib/ae_easy/core/mock/fake_parser.rb +0 -33
- data/lib/ae_easy/core/mock/fake_seeder.rb +0 -28
- data/lib/ae_easy/core/plugin.rb +0 -19
- data/lib/ae_easy/core/plugin/collection_vault.rb +0 -23
- data/lib/ae_easy/core/plugin/config_behavior.rb +0 -43
- data/lib/ae_easy/core/plugin/context_integrator.rb +0 -60
- data/lib/ae_easy/core/plugin/executor.rb +0 -19
- data/lib/ae_easy/core/plugin/executor_behavior.rb +0 -32
- data/lib/ae_easy/core/plugin/finisher.rb +0 -19
- data/lib/ae_easy/core/plugin/finisher_behavior.rb +0 -9
- data/lib/ae_easy/core/plugin/initialize_hook.rb +0 -17
- data/lib/ae_easy/core/plugin/parser.rb +0 -19
- data/lib/ae_easy/core/plugin/parser_behavior.rb +0 -17
- data/lib/ae_easy/core/plugin/seeder.rb +0 -44
- data/lib/ae_easy/core/plugin/seeder_behavior.rb +0 -9
- data/lib/ae_easy/core/smart_collection.rb +0 -236
- data/lib/ae_easy/core/version.rb +0 -6
@@ -1,110 +0,0 @@
|
|
1
|
-
<!DOCTYPE html>
|
2
|
-
<html>
|
3
|
-
<head>
|
4
|
-
<meta charset="utf-8">
|
5
|
-
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
6
|
-
<title>
|
7
|
-
Top Level Namespace
|
8
|
-
|
9
|
-
— Documentation by YARD 0.9.20
|
10
|
-
|
11
|
-
</title>
|
12
|
-
|
13
|
-
<link rel="stylesheet" href="css/style.css" type="text/css" charset="utf-8" />
|
14
|
-
|
15
|
-
<link rel="stylesheet" href="css/common.css" type="text/css" charset="utf-8" />
|
16
|
-
|
17
|
-
<script type="text/javascript" charset="utf-8">
|
18
|
-
pathId = "";
|
19
|
-
relpath = '';
|
20
|
-
</script>
|
21
|
-
|
22
|
-
|
23
|
-
<script type="text/javascript" charset="utf-8" src="js/jquery.js"></script>
|
24
|
-
|
25
|
-
<script type="text/javascript" charset="utf-8" src="js/app.js"></script>
|
26
|
-
|
27
|
-
|
28
|
-
</head>
|
29
|
-
<body>
|
30
|
-
<div class="nav_wrap">
|
31
|
-
<iframe id="nav" src="class_list.html?1"></iframe>
|
32
|
-
<div id="resizer"></div>
|
33
|
-
</div>
|
34
|
-
|
35
|
-
<div id="main" tabindex="-1">
|
36
|
-
<div id="header">
|
37
|
-
<div id="menu">
|
38
|
-
|
39
|
-
<a href="_index.html">Index</a> »
|
40
|
-
|
41
|
-
|
42
|
-
<span class="title">Top Level Namespace</span>
|
43
|
-
|
44
|
-
</div>
|
45
|
-
|
46
|
-
<div id="search">
|
47
|
-
|
48
|
-
<a class="full_list_link" id="class_list_link"
|
49
|
-
href="class_list.html">
|
50
|
-
|
51
|
-
<svg width="24" height="24">
|
52
|
-
<rect x="0" y="4" width="24" height="4" rx="1" ry="1"></rect>
|
53
|
-
<rect x="0" y="12" width="24" height="4" rx="1" ry="1"></rect>
|
54
|
-
<rect x="0" y="20" width="24" height="4" rx="1" ry="1"></rect>
|
55
|
-
</svg>
|
56
|
-
</a>
|
57
|
-
|
58
|
-
</div>
|
59
|
-
<div class="clear"></div>
|
60
|
-
</div>
|
61
|
-
|
62
|
-
<div id="content"><h1>Top Level Namespace
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
</h1>
|
67
|
-
<div class="box_info">
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
</div>
|
80
|
-
|
81
|
-
<h2>Defined Under Namespace</h2>
|
82
|
-
<p class="children">
|
83
|
-
|
84
|
-
|
85
|
-
<strong class="modules">Modules:</strong> <span class='object_link'><a href="AeEasy.html" title="AeEasy (module)">AeEasy</a></span>
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
</p>
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
</div>
|
101
|
-
|
102
|
-
<div id="footer">
|
103
|
-
Generated on Fri Sep 27 02:01:30 2019 by
|
104
|
-
<a href="http://yardoc.org" title="Yay! A Ruby Documentation Tool" target="_parent">yard</a>
|
105
|
-
0.9.20 (ruby-2.5.3).
|
106
|
-
</div>
|
107
|
-
|
108
|
-
</div>
|
109
|
-
</body>
|
110
|
-
</html>
|
data/lib/ae_easy/core/config.rb
DELETED
@@ -1,27 +0,0 @@
|
|
1
|
-
module AeEasy
|
2
|
-
module Core
|
3
|
-
# Configuration manager tool useful for global configuration data accross
|
4
|
-
# the scraping process.
|
5
|
-
class Config
|
6
|
-
include AeEasy::Core::Plugin::InitializeHook
|
7
|
-
include AeEasy::Core::Plugin::ConfigBehavior
|
8
|
-
|
9
|
-
# {AeEasy::Core::Plugin::ConfigBehavior#config_collection_key}
|
10
|
-
alias :collection_key :config_collection_key
|
11
|
-
# {AeEasy::Core::Plugin::ConfigBehavior#config_collection}
|
12
|
-
alias :collection :config_collection
|
13
|
-
|
14
|
-
# Initialize config object
|
15
|
-
#
|
16
|
-
# @param [Hash] opts ({}) Configuration options.
|
17
|
-
#
|
18
|
-
# @see AeEasy::Core::Plugin::ConfigBehavior#initialize_hook_core_config_behavior
|
19
|
-
def initialize opts = {}
|
20
|
-
opts = opts.merge(
|
21
|
-
config_collection: opts[:collection]
|
22
|
-
)
|
23
|
-
initialize_hooks opts
|
24
|
-
end
|
25
|
-
end
|
26
|
-
end
|
27
|
-
end
|
data/lib/ae_easy/core/helper.rb
DELETED
@@ -1,209 +0,0 @@
|
|
1
|
-
module AeEasy
|
2
|
-
module Core
|
3
|
-
module Helper
|
4
|
-
# Helper used for lower level cookie management.
|
5
|
-
class Cookie
|
6
|
-
class << self
|
7
|
-
# Parse request cookies on different formats.
|
8
|
-
#
|
9
|
-
# @param [String,Hash,Array] cookies Cookies to parse.
|
10
|
-
# @param [Hash] cookie_hash ({}) External hash to store parsed cookies.
|
11
|
-
#
|
12
|
-
# @return [Hash]
|
13
|
-
#
|
14
|
-
# @example Parse from string.
|
15
|
-
# parse_from_request 'aaa=111; bbb=222'
|
16
|
-
# # => {'aaa' => 111, 'bbb' => 222}
|
17
|
-
#
|
18
|
-
# @example Parse from array.
|
19
|
-
# cookies = [
|
20
|
-
# 'aaa=111',
|
21
|
-
# 'bbb=222'
|
22
|
-
# ]
|
23
|
-
# parse_from_response cookies
|
24
|
-
# # => {'aaa' => 111, 'bbb' => 222}
|
25
|
-
#
|
26
|
-
# @example Parse with `cookie_hash`.
|
27
|
-
# cookie_hash = {'ccc' => 333}
|
28
|
-
# parse_from_request 'aaa=111; bbb=222', cookie_hash
|
29
|
-
# cookie_hash
|
30
|
-
# # => {'aaa' => 1, 'bbb' => 2, 'ccc' => 333}
|
31
|
-
def parse_from_request cookies, cookie_hash = {}
|
32
|
-
# Retrieve from hash
|
33
|
-
if cookies.is_a? Hash
|
34
|
-
cookie_hash.merge! cookies
|
35
|
-
return cookie_hash
|
36
|
-
end
|
37
|
-
|
38
|
-
# Extract from string
|
39
|
-
cookies = cookies.split '; ' if cookies.is_a? String
|
40
|
-
|
41
|
-
# Extract from array
|
42
|
-
cookies&.each do |raw_cookie|
|
43
|
-
key, value = raw_cookie.split('=', 2)
|
44
|
-
cookie_hash[key] = value
|
45
|
-
end
|
46
|
-
cookie_hash
|
47
|
-
end
|
48
|
-
|
49
|
-
# Parse response cookies on different formats.
|
50
|
-
#
|
51
|
-
# @param [String,Hash,Array] cookies Cookies to parse.
|
52
|
-
# @param [Hash] cookie_hash ({}) External hash to store parsed cookies.
|
53
|
-
#
|
54
|
-
# @return [Hash]
|
55
|
-
#
|
56
|
-
# @example Parse from string
|
57
|
-
# parse_from_response 'aaa=111; bbb=222'
|
58
|
-
# # => {'aaa' => 111, 'bbb' => 222}
|
59
|
-
#
|
60
|
-
# @example Parse from array.
|
61
|
-
# cookies = [
|
62
|
-
# 'aaa=111; Expires=Thu, Jan 01 1970 00:00:00 UTC; path=/',
|
63
|
-
# 'bbb=222; path=/',
|
64
|
-
# 'ccc=333; path=/; expires=Wed, Jan 01 3000 00:00:00 UTC'
|
65
|
-
# ]
|
66
|
-
# parse_from_response cookies
|
67
|
-
# # => {'bbb' => 222, 'ccc' => 333}
|
68
|
-
#
|
69
|
-
# @example Parse with `cookie_hash`.
|
70
|
-
# cookie_hash = {'ccc' => 333}
|
71
|
-
# parse_from_response 'aaa=111; bbb=222', cookie_hash
|
72
|
-
# cookie_hash
|
73
|
-
# # => {'aaa' => 111, 'bbb' => 222, 'ccc' => 333}
|
74
|
-
def parse_from_response cookies, cookie_hash = {}
|
75
|
-
# Retrieve from hash
|
76
|
-
if cookies.is_a? Hash
|
77
|
-
cookie_hash.merge! cookies
|
78
|
-
return cookie_hash
|
79
|
-
end
|
80
|
-
# Retrieve from String
|
81
|
-
cookies = cookies.split '; ' if cookies.is_a? String
|
82
|
-
|
83
|
-
# Extract from array
|
84
|
-
info = cookie = expires = key = value = nil
|
85
|
-
cookies&.each do |raw_cookie|
|
86
|
-
# Extract cookie data
|
87
|
-
key_pair = raw_cookie.scan(/(?:;\s+([^\=]+)=([^;]*))/i) || []
|
88
|
-
cookie = key_pair.inject(Hash.new){|h,i|h[i[0].to_s.downcase] = i[1]; h}
|
89
|
-
cookie[:key], cookie[:value] = raw_cookie.match(/^\s*(?<key>[^\=]+)\=(?<value>[^;]*)/i)&.captures
|
90
|
-
|
91
|
-
# Check cookie expire
|
92
|
-
expires = cookie['expires'].nil? ? nil : Time.parse(cookie['expires'])
|
93
|
-
if !expires.nil? && Time.now > expires
|
94
|
-
cookie_hash.delete cookie[:key]
|
95
|
-
next
|
96
|
-
end
|
97
|
-
|
98
|
-
# Save cookie
|
99
|
-
cookie_hash[cookie[:key]] = cookie[:value]
|
100
|
-
end
|
101
|
-
cookie_hash
|
102
|
-
end
|
103
|
-
|
104
|
-
# Apply request and response cookies as a hash.
|
105
|
-
#
|
106
|
-
# @param [String,Array,Hash] request_cookies Cookies to parse.
|
107
|
-
# @param [String,Array,Hash] response_cookies Cookies to parse.
|
108
|
-
#
|
109
|
-
# @return [Hash]
|
110
|
-
#
|
111
|
-
# @example
|
112
|
-
# request_cookies = 'aaa=111; ddd=444'
|
113
|
-
# response_cookies = [
|
114
|
-
# 'aaa=111; Expires=Thu, Jan 01 1970 00:00:00 UTC; path=/',
|
115
|
-
# 'bbb=222; path=/',
|
116
|
-
# 'ccc=333; path=/; expires=Wed, Jan 01 3000 00:00:00 UTC'
|
117
|
-
# ]
|
118
|
-
# update_as_hash , response_cookies
|
119
|
-
# # => {'bbb' => 222, 'ccc' => 333, 'ddd' => 444}
|
120
|
-
def update_as_hash request_cookies, response_cookies
|
121
|
-
cookie_hash = {}
|
122
|
-
parse_from_request request_cookies, cookie_hash
|
123
|
-
parse_from_response response_cookies, cookie_hash
|
124
|
-
cookie_hash
|
125
|
-
end
|
126
|
-
|
127
|
-
# Encode cookies as request cookie string.
|
128
|
-
#
|
129
|
-
# @param [Hash] cookie_hash Hash with cookies.
|
130
|
-
#
|
131
|
-
# @return [String]
|
132
|
-
#
|
133
|
-
# @example
|
134
|
-
# cookie_hash = {
|
135
|
-
# 'aaa' => 111,
|
136
|
-
# 'bbb' => 222
|
137
|
-
# }
|
138
|
-
# encode_to_header cookie_hash
|
139
|
-
# # => 'aaa=111; bbb=222'
|
140
|
-
def encode_to_header cookie_hash
|
141
|
-
cookie_hash.map{|k,v| "#{k}=#{v}"}.join '; '
|
142
|
-
end
|
143
|
-
|
144
|
-
# Apply request and response cookies as a string with request format.
|
145
|
-
#
|
146
|
-
# @param [String,Array,Hash] request_cookies Cookies to parse.
|
147
|
-
# @param [String,Array,Hash] response_cookies Cookies to parse.
|
148
|
-
#
|
149
|
-
# @return [String]
|
150
|
-
#
|
151
|
-
# @example
|
152
|
-
# request_cookies = 'aaa=111; ddd=444'
|
153
|
-
# response_cookies = [
|
154
|
-
# 'aaa=111; Expires=Thu, Jan 01 1970 00:00:00 UTC; path=/',
|
155
|
-
# 'bbb=222; path=/',
|
156
|
-
# 'ccc=333; path=/; expires=Wed, Jan 01 3000 00:00:00 UTC'
|
157
|
-
# ]
|
158
|
-
# update_as_hash , response_cookies
|
159
|
-
# # => 'bbb=222; ccc=333; ddd=444'
|
160
|
-
def update request_cookies, response_cookies
|
161
|
-
cookie_hash = update_as_hash request_cookies, response_cookies
|
162
|
-
encode_to_header cookie_hash
|
163
|
-
end
|
164
|
-
|
165
|
-
# Compare if cookie is included into base cookie
|
166
|
-
#
|
167
|
-
# @param [Hash] base_cookie_hash Hash that represent universe.
|
168
|
-
# @param [Hash] cookie_hash Hash that represents to compare.
|
169
|
-
#
|
170
|
-
# @return [Boolean]
|
171
|
-
#
|
172
|
-
# @example Check a success match.
|
173
|
-
# base_cookie_hash = {
|
174
|
-
# 'aaa' => 111,
|
175
|
-
# 'bbb' => 222,
|
176
|
-
# 'ccc' => 333,
|
177
|
-
# 'ddd' => 444
|
178
|
-
# }
|
179
|
-
# cookie_hash = {
|
180
|
-
# 'bbb' => 222,
|
181
|
-
# 'ddd' => 444
|
182
|
-
# }
|
183
|
-
# include? base_cookie_hash, cookie_hash
|
184
|
-
# # => true
|
185
|
-
#
|
186
|
-
# @example Check with fail match.
|
187
|
-
# base_cookie_hash = {
|
188
|
-
# 'aaa' => 111,
|
189
|
-
# 'bbb' => 222,
|
190
|
-
# 'ccc' => 333,
|
191
|
-
# 'ddd' => 444
|
192
|
-
# }
|
193
|
-
# cookie_hash = {
|
194
|
-
# 'bbb' => 555,
|
195
|
-
# 'ddd' => 444
|
196
|
-
# }
|
197
|
-
# include? base_cookie_hash, cookie_hash
|
198
|
-
# # => false
|
199
|
-
def include? base_cookie_hash, cookie_hash
|
200
|
-
cookie_hash.each do |key, value|
|
201
|
-
return false unless base_cookie_hash.has_key?(key) && base_cookie_hash[key] == value
|
202
|
-
end
|
203
|
-
true
|
204
|
-
end
|
205
|
-
end
|
206
|
-
end
|
207
|
-
end
|
208
|
-
end
|
209
|
-
end
|
data/lib/ae_easy/core/mock.rb
DELETED
@@ -1,45 +0,0 @@
|
|
1
|
-
require 'ae_easy/core/mock/fake_db'
|
2
|
-
require 'ae_easy/core/mock/fake_executor'
|
3
|
-
require 'ae_easy/core/mock/fake_parser'
|
4
|
-
require 'ae_easy/core/mock/fake_seeder'
|
5
|
-
require 'ae_easy/core/mock/fake_finisher'
|
6
|
-
|
7
|
-
module AeEasy
|
8
|
-
module Core
|
9
|
-
module Mock
|
10
|
-
# Generate a context and message queue from a list of exposed methods.
|
11
|
-
#
|
12
|
-
# @param [Array] exposed_methods List of exposed methods.
|
13
|
-
#
|
14
|
-
# @example
|
15
|
-
# exposed_methods = [:boo, :bar]
|
16
|
-
# context, message_queue = AeEasy::Core::Mock.context_vars exposed_methods
|
17
|
-
# context.boo 1, 2
|
18
|
-
# context.bar 'A', 'B'
|
19
|
-
# context.bar '111', '222'
|
20
|
-
# message_queue
|
21
|
-
# # => [
|
22
|
-
# # [:boo, [1, 2]],
|
23
|
-
# # [:bar, ['A', 'B']],
|
24
|
-
# # [:bar, ['111', '222']]
|
25
|
-
# # ]
|
26
|
-
#
|
27
|
-
# @return [Array] `[context, message_queue]` being:
|
28
|
-
# * `context`: Object implementing exposed methods.
|
29
|
-
# * `[Array] message_queue`: Array to store messages.
|
30
|
-
def self.context_vars exposed_methods
|
31
|
-
context = Object.new
|
32
|
-
metaclass = class << context; self; end
|
33
|
-
message_queue = [] # Beat reference bug
|
34
|
-
exposed_methods = exposed_methods
|
35
|
-
exposed_methods.each do |key|
|
36
|
-
metaclass.send(:define_method, key) do |*args|
|
37
|
-
# Record all method calls into message queue for easy access
|
38
|
-
message_queue << [key, args]
|
39
|
-
end
|
40
|
-
end
|
41
|
-
[context, message_queue]
|
42
|
-
end
|
43
|
-
end
|
44
|
-
end
|
45
|
-
end
|
@@ -1,561 +0,0 @@
|
|
1
|
-
module AeEasy
|
2
|
-
module Core
|
3
|
-
module Mock
|
4
|
-
# Fake in memory database that emulates `Answersengine` database objects' black box behavior.
|
5
|
-
class FakeDb
|
6
|
-
# Page id keys, analog to primary keys.
|
7
|
-
PAGE_KEYS = ['gid'].freeze
|
8
|
-
# Output id keys, analog to primary keys.
|
9
|
-
OUTPUT_KEYS = ['_id', '_collection'].freeze
|
10
|
-
# Job id keys, analog to primary keys.
|
11
|
-
JOB_KEYS = ['job_id'].freeze
|
12
|
-
# Job available status.
|
13
|
-
JOB_STATUSES = {
|
14
|
-
active: 'active',
|
15
|
-
done: 'done',
|
16
|
-
cancelled: 'cancelled',
|
17
|
-
paused: 'paused'
|
18
|
-
}
|
19
|
-
# Default collection for saved outputs
|
20
|
-
DEFAULT_COLLECTION = 'default'
|
21
|
-
|
22
|
-
# Generate a smart collection with keys and initial values.
|
23
|
-
#
|
24
|
-
# @param [Array] keys Analog to primary keys, combination will be uniq.
|
25
|
-
# @param [Hash] opts Configuration options (see AeEasy::Core::SmartCollection#initialize).
|
26
|
-
#
|
27
|
-
# @return [AeEasy::Core::SmartCollection]
|
28
|
-
def self.new_collection keys, opts = {}
|
29
|
-
AeEasy::Core::SmartCollection.new keys, opts
|
30
|
-
end
|
31
|
-
|
32
|
-
# Generate a fake UUID.
|
33
|
-
#
|
34
|
-
# @param seed (nil) Object to use as seed for uuid.
|
35
|
-
#
|
36
|
-
# @return [String]
|
37
|
-
def self.fake_uuid seed = nil
|
38
|
-
seed ||= (Time.new.to_f + rand)
|
39
|
-
Digest::SHA1.hexdigest seed.to_s
|
40
|
-
end
|
41
|
-
|
42
|
-
# Generate a fake UUID based on output fields without `_` prefix.
|
43
|
-
#
|
44
|
-
# @param [Hash] data Output data.
|
45
|
-
#
|
46
|
-
# @return [String]
|
47
|
-
def self.output_uuid data
|
48
|
-
seed = data.select{|k,v|k.to_s =~ /^[^_]/}.hash
|
49
|
-
fake_uuid seed
|
50
|
-
end
|
51
|
-
|
52
|
-
# Build a page with defaults by using FakeDb engine.
|
53
|
-
#
|
54
|
-
# @param [Hash] page Page initial values.
|
55
|
-
# @param [Hash] opts ({}) Configuration options (see #initialize).
|
56
|
-
#
|
57
|
-
# @return [Hash]
|
58
|
-
def self.build_page page, opts = {}
|
59
|
-
opts = {
|
60
|
-
allow_page_gid_override: true,
|
61
|
-
allow_job_id_override: true
|
62
|
-
}.merge opts
|
63
|
-
temp_db = AeEasy::Core::Mock::FakeDb.new opts
|
64
|
-
temp_db.pages << page
|
65
|
-
temp_db.pages.first
|
66
|
-
end
|
67
|
-
|
68
|
-
# Build a fake page by using FakeDb engine.
|
69
|
-
#
|
70
|
-
# @param [Hash] opts ({}) Configuration options (see #initialize).
|
71
|
-
# @option opts [String] :url ('https://example.com') Page url.
|
72
|
-
#
|
73
|
-
# @return [Hash]
|
74
|
-
def self.build_fake_page opts = {}
|
75
|
-
page = {
|
76
|
-
'url' => (opts[:url] || 'https://example.com')
|
77
|
-
}
|
78
|
-
build_page page, opts
|
79
|
-
end
|
80
|
-
|
81
|
-
# Clean an URL to remove fragment, lowercase schema and host, and sort
|
82
|
-
# query string.
|
83
|
-
#
|
84
|
-
# @param [String] raw_url URL to clean.
|
85
|
-
#
|
86
|
-
# @return [String]
|
87
|
-
def self.clean_uri raw_url
|
88
|
-
url = URI.parse(raw_url)
|
89
|
-
url.hostname = url.hostname.downcase
|
90
|
-
url.fragment = nil
|
91
|
-
|
92
|
-
# Sort query string keys
|
93
|
-
unless url.query.nil?
|
94
|
-
query_string = CGI.parse(url.query)
|
95
|
-
keys = query_string.keys.sort
|
96
|
-
data = []
|
97
|
-
keys.each do |key|
|
98
|
-
query_string[key].each do |value|
|
99
|
-
data << "#{URI.encode key}=#{URI.encode value}"
|
100
|
-
end
|
101
|
-
end
|
102
|
-
url.query = data.join('&')
|
103
|
-
end
|
104
|
-
url.to_s
|
105
|
-
end
|
106
|
-
|
107
|
-
# Format headers for gid generation.
|
108
|
-
# @private
|
109
|
-
#
|
110
|
-
# @param [Hash,nil] headers Headers hash.
|
111
|
-
#
|
112
|
-
# @return [Hash]
|
113
|
-
def self.format_headers headers
|
114
|
-
return {} if headers.nil?
|
115
|
-
data = {}
|
116
|
-
headers.each do |key, value|
|
117
|
-
unless value.is_a? Array
|
118
|
-
data[key] = value
|
119
|
-
next
|
120
|
-
end
|
121
|
-
data[key] = value.sort
|
122
|
-
end
|
123
|
-
data
|
124
|
-
end
|
125
|
-
|
126
|
-
# Build a job with defaults by using FakeDb engine.
|
127
|
-
#
|
128
|
-
# @param [Hash] job Job initial values.
|
129
|
-
# @param [Hash] opts ({}) Configuration options (see #initialize).
|
130
|
-
#
|
131
|
-
# @return [Hash]
|
132
|
-
def self.build_job job, opts = {}
|
133
|
-
temp_db = AeEasy::Core::Mock::FakeDb.new opts
|
134
|
-
temp_db.jobs << job
|
135
|
-
temp_db.jobs.last
|
136
|
-
end
|
137
|
-
|
138
|
-
# Build a fake job by using FakeDb engine.
|
139
|
-
#
|
140
|
-
# @param [Hash] opts ({}) Configuration options (see #initialize).
|
141
|
-
# @option opts [String] :scraper_name (nil) Scraper name.
|
142
|
-
# @option opts [Integer] :job_id (nil) Job id.
|
143
|
-
# @option opts [String] :status ('done').
|
144
|
-
#
|
145
|
-
# @return [Hash]
|
146
|
-
def self.build_fake_job opts = {}
|
147
|
-
job = {
|
148
|
-
'job_id' => opts[:job_id],
|
149
|
-
'scraper_name' => opts[:scraper_name],
|
150
|
-
'status' => (opts[:status] || 'done')
|
151
|
-
}
|
152
|
-
build_job job, opts
|
153
|
-
end
|
154
|
-
|
155
|
-
# Return a timestamp
|
156
|
-
#
|
157
|
-
# @param [Time] time (nil) Time from which to get time stamp.
|
158
|
-
#
|
159
|
-
# @return [String]
|
160
|
-
def self.time_stamp time = nil
|
161
|
-
time = Time.new if time.nil?
|
162
|
-
time.utc.strftime('%Y-%m-%dT%H:%M:%SZ')
|
163
|
-
end
|
164
|
-
|
165
|
-
# Get current job or create new one from values.
|
166
|
-
#
|
167
|
-
# @param [Integer] target_job_id (nil) Job id to ensure existance.
|
168
|
-
#
|
169
|
-
# @return [Hash]
|
170
|
-
def ensure_job target_job_id = nil
|
171
|
-
target_job_id = job_id if target_job_id.nil?
|
172
|
-
job = jobs.find{|v|v['job_id'] == target_job_id}
|
173
|
-
return job unless job.nil?
|
174
|
-
job = {
|
175
|
-
'job_id' => target_job_id,
|
176
|
-
'scraper_name' => scraper_name,
|
177
|
-
}
|
178
|
-
job['status'] = 'active' unless target_job_id != job_id
|
179
|
-
jobs << job
|
180
|
-
jobs.last
|
181
|
-
end
|
182
|
-
|
183
|
-
# Fake scraper_name.
|
184
|
-
# @return [String,nil]
|
185
|
-
def scraper_name
|
186
|
-
@scraper_name ||= 'my_scraper'
|
187
|
-
end
|
188
|
-
|
189
|
-
# Set fake scraper_name value.
|
190
|
-
def scraper_name= value
|
191
|
-
job = ensure_job
|
192
|
-
@scraper_name = value
|
193
|
-
job['scraper_name'] = scraper_name
|
194
|
-
end
|
195
|
-
|
196
|
-
# Fake job id.
|
197
|
-
# @return [Integer,nil]
|
198
|
-
def job_id
|
199
|
-
@job_id ||= generate_job_id
|
200
|
-
end
|
201
|
-
|
202
|
-
# Set fake job id value.
|
203
|
-
def job_id= value
|
204
|
-
@job_id = value
|
205
|
-
ensure_job
|
206
|
-
job_id
|
207
|
-
end
|
208
|
-
|
209
|
-
# Current fake page gid.
|
210
|
-
# @return [Integer,nil]
|
211
|
-
def page_gid
|
212
|
-
@page_gid ||= self.class.fake_uuid
|
213
|
-
end
|
214
|
-
|
215
|
-
# Set current fake page gid value.
|
216
|
-
def page_gid= value
|
217
|
-
@page_gid = value
|
218
|
-
end
|
219
|
-
|
220
|
-
# Enable page gid override on page or output insert.
|
221
|
-
def enable_page_gid_override
|
222
|
-
@allow_page_gid_override = true
|
223
|
-
end
|
224
|
-
|
225
|
-
# Disable page gid override on page or output insert.
|
226
|
-
def disable_page_gid_override
|
227
|
-
@allow_page_gid_override = false
|
228
|
-
end
|
229
|
-
|
230
|
-
# Specify whenever page gid overriding by user is allowed on page or
|
231
|
-
# output insert.
|
232
|
-
#
|
233
|
-
# @return [Boolean] `true` when allowed, else `false`.
|
234
|
-
def allow_page_gid_override?
|
235
|
-
@allow_page_gid_override ||= false
|
236
|
-
end
|
237
|
-
|
238
|
-
# Enable job id override on page or output insert.
|
239
|
-
def enable_job_id_override
|
240
|
-
@allow_job_id_override = true
|
241
|
-
end
|
242
|
-
|
243
|
-
# Disable job id override on page or output insert.
|
244
|
-
def disable_job_id_override
|
245
|
-
@allow_job_id_override = false
|
246
|
-
end
|
247
|
-
|
248
|
-
# Specify whenever job id overriding by user is allowed on page or
|
249
|
-
# output insert.
|
250
|
-
#
|
251
|
-
# @return [Boolean] `true` when allowed, else `false`.
|
252
|
-
def allow_job_id_override?
|
253
|
-
@allow_job_id_override ||= false
|
254
|
-
end
|
255
|
-
|
256
|
-
# Initialize fake database.
|
257
|
-
#
|
258
|
-
# @param [Hash] opts ({}) Configuration options.
|
259
|
-
# @option opts [Integer,nil] :job_id Job id default value.
|
260
|
-
# @option opts [String,nil] :scraper_name Scraper name default value.
|
261
|
-
# @option opts [String,nil] :page_gid Page gid default value.
|
262
|
-
# @option opts [Boolean, nil] :allow_page_gid_override (false) Specify
|
263
|
-
# whenever page gid can be overrided on page or output insert.
|
264
|
-
# @option opts [Boolean, nil] :allow_job_id_override (false) Specify
|
265
|
-
# whenever job id can be overrided on page or output insert.
|
266
|
-
def initialize opts = {}
|
267
|
-
self.job_id = opts[:job_id]
|
268
|
-
self.scraper_name = opts[:scraper_name]
|
269
|
-
self.page_gid = opts[:page_gid]
|
270
|
-
@allow_page_gid_override = opts[:allow_page_gid_override].nil? ? false : !!opts[:allow_page_gid_override]
|
271
|
-
@allow_job_id_override = opts[:allow_job_id_override].nil? ? false : !!opts[:allow_job_id_override]
|
272
|
-
end
|
273
|
-
|
274
|
-
# Generate a fake scraper name.
|
275
|
-
#
|
276
|
-
# @return [String]
|
277
|
-
def generate_scraper_name
|
278
|
-
Faker::Internet.unique.slug
|
279
|
-
end
|
280
|
-
|
281
|
-
# Generate a fake job_id.
|
282
|
-
#
|
283
|
-
# @return [Integer]
|
284
|
-
def generate_job_id
|
285
|
-
jobs.count < 1 ? 1 : (jobs.max{|a,b|a['job_id'] <=> b['job_id']}['job_id'] + 1)
|
286
|
-
end
|
287
|
-
|
288
|
-
# Get output keys with key generators to emulate saving on db.
|
289
|
-
# @private
|
290
|
-
#
|
291
|
-
# @return [Hash]
|
292
|
-
def job_defaults
|
293
|
-
@job_defaults ||= {
|
294
|
-
'job_id' => lambda{|job| generate_job_id},
|
295
|
-
'scraper_name' => lambda{|job| generate_scraper_name},
|
296
|
-
'status' => 'done',
|
297
|
-
'created_at' => lambda{|job| Time.now}
|
298
|
-
}
|
299
|
-
end
|
300
|
-
|
301
|
-
# Stored job collection
|
302
|
-
#
|
303
|
-
# @return [AeEasy::Core::SmartCollection]
|
304
|
-
def jobs
|
305
|
-
return @jobs unless @jobs.nil?
|
306
|
-
collection = self.class.new_collection JOB_KEYS,
|
307
|
-
defaults: job_defaults
|
308
|
-
collection.bind_event(:before_defaults) do |collection, raw_item|
|
309
|
-
AeEasy::Core.deep_stringify_keys raw_item
|
310
|
-
end
|
311
|
-
collection.bind_event(:before_insert) do |collection, item, match|
|
312
|
-
item['job_id'] ||= generate_job_id
|
313
|
-
item
|
314
|
-
end
|
315
|
-
@jobs ||= collection
|
316
|
-
end
|
317
|
-
|
318
|
-
# Generate a fake UUID based on page data:
|
319
|
-
# * url
|
320
|
-
# * method
|
321
|
-
# * headers
|
322
|
-
# * fetch_type
|
323
|
-
# * cookie
|
324
|
-
# * no_redirect
|
325
|
-
# * body
|
326
|
-
# * ua_type
|
327
|
-
#
|
328
|
-
# @param [Hash] page_data Page data.
|
329
|
-
#
|
330
|
-
# @return [String]
|
331
|
-
def generate_page_gid page_data
|
332
|
-
fields = [
|
333
|
-
'url',
|
334
|
-
'method',
|
335
|
-
'headers',
|
336
|
-
'fetch_type',
|
337
|
-
'cookie',
|
338
|
-
'no_redirect',
|
339
|
-
'body',
|
340
|
-
'ua_type'
|
341
|
-
]
|
342
|
-
data = page_data.select{|k,v|fields.include? k}
|
343
|
-
data['url'] = self.class.clean_uri data['url']
|
344
|
-
data['headers'] = self.class.format_headers data['headers']
|
345
|
-
data['cookie'] = AeEasy::Core::Helper::Cookie.parse_from_request data['cookie'] unless data['cookie'].nil?
|
346
|
-
seed = data.select{|k,v|fields.include? k}.hash
|
347
|
-
checksum = self.class.fake_uuid seed
|
348
|
-
"#{URI.parse(data['url']).hostname}-#{checksum}"
|
349
|
-
end
|
350
|
-
|
351
|
-
# Get page keys with key generators to emulate saving on db.
|
352
|
-
# @private
|
353
|
-
#
|
354
|
-
# @return [Hash]
|
355
|
-
def page_defaults
|
356
|
-
@page_defaults ||= {
|
357
|
-
'url' => nil,
|
358
|
-
'status' => 'to_fetch',
|
359
|
-
'job_id' => lambda{|page| job_id},
|
360
|
-
'method' => 'GET',
|
361
|
-
'headers' => {},
|
362
|
-
'fetch_type' => 'standard',
|
363
|
-
'cookie' => nil,
|
364
|
-
'no_redirect' => false,
|
365
|
-
'body' => nil,
|
366
|
-
'ua_type' => 'desktop',
|
367
|
-
'no_url_encode' => false,
|
368
|
-
'http2' => false,
|
369
|
-
'vars' => {}
|
370
|
-
}
|
371
|
-
end
|
372
|
-
|
373
|
-
# Stored page collection.
|
374
|
-
#
|
375
|
-
# @return [AeEasy::Core::SmartCollection]
|
376
|
-
#
|
377
|
-
# @note Page gid will be replaced on insert by an auto generated uuid
|
378
|
-
# unless page gid overriding is enabled
|
379
|
-
# (see #allow_page_gid_override?)
|
380
|
-
def pages
|
381
|
-
return @pages unless @page.nil?
|
382
|
-
|
383
|
-
collection = self.class.new_collection PAGE_KEYS,
|
384
|
-
defaults: page_defaults
|
385
|
-
collection.bind_event(:before_defaults) do |collection, raw_item|
|
386
|
-
item = AeEasy::Core.deep_stringify_keys raw_item
|
387
|
-
item.delete 'job_id' unless allow_job_id_override?
|
388
|
-
item
|
389
|
-
end
|
390
|
-
collection.bind_event(:before_insert) do |collection, item, match|
|
391
|
-
if item['gid'].nil? || !allow_page_gid_override?
|
392
|
-
item['gid'] = generate_page_gid item
|
393
|
-
end
|
394
|
-
item
|
395
|
-
end
|
396
|
-
collection.bind_event(:after_insert) do |collection, item|
|
397
|
-
ensure_job item['job_id']
|
398
|
-
end
|
399
|
-
@pages ||= collection
|
400
|
-
end
|
401
|
-
|
402
|
-
# Generate a fake UUID for outputs.
|
403
|
-
#
|
404
|
-
# @param [Hash] data Output data.
|
405
|
-
#
|
406
|
-
# @return [String]
|
407
|
-
def generate_output_id data
|
408
|
-
# Generate random UUID to match AnswersEngine behavior
|
409
|
-
self.class.fake_uuid
|
410
|
-
end
|
411
|
-
|
412
|
-
# Get output keys with key generators to emulate saving on db.
|
413
|
-
# @private
|
414
|
-
#
|
415
|
-
# @return [Hash]
|
416
|
-
def output_defaults
|
417
|
-
@output_defaults ||= {
|
418
|
-
'_collection' => DEFAULT_COLLECTION,
|
419
|
-
'_job_id' => lambda{|output| job_id},
|
420
|
-
'_created_at' => lambda{|output| self.class.time_stamp},
|
421
|
-
'_gid' => lambda{|output| page_gid}
|
422
|
-
}
|
423
|
-
end
|
424
|
-
|
425
|
-
# Stored output collection
|
426
|
-
#
|
427
|
-
# @return [AeEasy::Core::SmartCollection]
|
428
|
-
def outputs
|
429
|
-
return @outputs unless @outputs.nil?
|
430
|
-
collection = self.class.new_collection OUTPUT_KEYS,
|
431
|
-
defaults: output_defaults
|
432
|
-
collection.bind_event(:before_defaults) do |collection, raw_item|
|
433
|
-
item = AeEasy::Core.deep_stringify_keys raw_item
|
434
|
-
item.delete '_job_id' unless allow_job_id_override?
|
435
|
-
item.delete '_gid_id' unless allow_page_gid_override?
|
436
|
-
item
|
437
|
-
end
|
438
|
-
collection.bind_event(:before_insert) do |collection, item, match|
|
439
|
-
item['_id'] ||= generate_output_id item
|
440
|
-
item
|
441
|
-
end
|
442
|
-
collection.bind_event(:after_insert) do |collection, item|
|
443
|
-
ensure_job item['_job_id']
|
444
|
-
end
|
445
|
-
@outputs ||= collection
|
446
|
-
end
|
447
|
-
|
448
|
-
# Match data to filters.
|
449
|
-
# @private
|
450
|
-
#
|
451
|
-
# @param data Hash containing data.
|
452
|
-
# @param filters Filters to apply on match.
|
453
|
-
#
|
454
|
-
# @return [Boolean]
|
455
|
-
#
|
456
|
-
# @note Missing and `nil` values on `data` will match when `filters`'
|
457
|
-
# field is `nil`.
|
458
|
-
def match? data, filters
|
459
|
-
filters.each do |key, value|
|
460
|
-
return false if data[key] != value
|
461
|
-
end
|
462
|
-
true
|
463
|
-
end
|
464
|
-
|
465
|
-
# Search items from a collection.
|
466
|
-
#
|
467
|
-
# @param [Symbol] collection Allowed values: `:outputs`, `:pages`.
|
468
|
-
# @param [Hash] filter Filters to query.
|
469
|
-
# @param [Integer] offset (0) Search results offset.
|
470
|
-
# @param [Integer,nil] limit (nil) Limit search results count. Set to `nil` for unlimited.
|
471
|
-
#
|
472
|
-
# @raise ArgumentError On unknown collection.
|
473
|
-
#
|
474
|
-
# @note _Warning:_ It uses table scan to filter and should be used on test suites only.
|
475
|
-
def query collection, filter, offset = 0, limit = nil
|
476
|
-
return [] unless limit.nil? || limit > 0
|
477
|
-
|
478
|
-
# Get collection items
|
479
|
-
items = case collection
|
480
|
-
when :outputs
|
481
|
-
outputs
|
482
|
-
when :pages
|
483
|
-
pages
|
484
|
-
when :jobs
|
485
|
-
jobs
|
486
|
-
else
|
487
|
-
raise ArgumentError.new "Unknown collection #{collection}."
|
488
|
-
end
|
489
|
-
|
490
|
-
# Search items
|
491
|
-
count = 0
|
492
|
-
matches = []
|
493
|
-
items.each do |item|
|
494
|
-
next unless match? item, filter
|
495
|
-
count += 1
|
496
|
-
|
497
|
-
# Skip until offset
|
498
|
-
next unless offset < count
|
499
|
-
# Break on limit reach
|
500
|
-
break unless limit.nil? || matches.count < limit
|
501
|
-
matches << item
|
502
|
-
end
|
503
|
-
matches
|
504
|
-
end
|
505
|
-
|
506
|
-
# Refetch a page.
|
507
|
-
#
|
508
|
-
# @param [Integer] job_id Page's job_id to refetch.
|
509
|
-
# @param [String] gid Page's gid to refetch.
|
510
|
-
def refetch job_id, gid
|
511
|
-
page = pages.find_match('gid' => gid, 'job_id' => job_id)
|
512
|
-
raise Exception.new("Page not found with job_id \"#{job_id}\" gid \"#{gid}\"") if page.nil?
|
513
|
-
page['status'] = 'to_fetch'
|
514
|
-
page['freshness'] = self.class.time_stamp
|
515
|
-
page['to_fetch'] = self.class.time_stamp
|
516
|
-
page['fetched_from'] = nil
|
517
|
-
page['fetching_at'] = '2001-01-01T00:00:00Z'
|
518
|
-
page['fetched_at'] = nil
|
519
|
-
page['fetching_try_count'] = 0
|
520
|
-
page['effective_url'] = nil
|
521
|
-
page['parsing_at'] = nil
|
522
|
-
page['parsing_failed_at'] = nil
|
523
|
-
page['parsed_at'] = nil
|
524
|
-
page['parsing_try_count'] = 0
|
525
|
-
page['parsing_fail_count'] = 0
|
526
|
-
page['parsing_updated_at'] = '2001-01-01T00:00:00Z'
|
527
|
-
page['response_checksum'] = nil
|
528
|
-
page['response_status'] = nil
|
529
|
-
page['response_status_code'] = nil
|
530
|
-
page['response_headers'] = nil
|
531
|
-
page['response_cookie'] = nil
|
532
|
-
page['response_proto'] = nil
|
533
|
-
page['content_type'] = nil
|
534
|
-
page['content_size'] = 0
|
535
|
-
page['failed_response_status_code'] = nil
|
536
|
-
page['failed_response_headers'] = nil
|
537
|
-
page['failed_response_cookie'] = nil
|
538
|
-
page['failed_effective_url'] = nil
|
539
|
-
page['failed_at'] = nil
|
540
|
-
page['failed_content_type'] = nil
|
541
|
-
end
|
542
|
-
|
543
|
-
# Reparse a page.
|
544
|
-
#
|
545
|
-
# @param [Integer] job_id Page's job_id to reparse.
|
546
|
-
# @param [String] gid Page's gid to reparse.
|
547
|
-
def reparse job_id, gid
|
548
|
-
page = pages.find_match('gid' => gid, 'job_id' => job_id)
|
549
|
-
raise Exception.new("Page not found with job_id \"#{job_id}\" gid \"#{gid}\"") if page.nil?
|
550
|
-
page['status'] = 'to_parse'
|
551
|
-
page['parsing_at'] = nil
|
552
|
-
page['parsing_failed_at'] = nil
|
553
|
-
page['parsing_updated_at'] = '2001-01-01T00:00:00Z'
|
554
|
-
page['parsed_at'] = nil
|
555
|
-
page['parsing_try_count'] = 0
|
556
|
-
page['parsing_fail_count'] = 0
|
557
|
-
end
|
558
|
-
end
|
559
|
-
end
|
560
|
-
end
|
561
|
-
end
|