glib-web 4.34.4 → 4.34.5
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.
- checksums.yaml +4 -4
- data/lib/glib/json_crawler/router.rb +22 -1
- data/lib/glib/test_helpers.rb +4 -3
- metadata +15 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 71657e9b80c2a5759e3df0ee81e068470bb5dfb627b8339241703b948e72129f
|
4
|
+
data.tar.gz: 9b754b492975ebea6d3d5b2a18b667ae00398a2f1cebdd2a6b33fcca377b8b0f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 96e3dd7df23643cc4bdff6e7fd4d3cdc8ca0cb05c1a955686ffb94707569a16bccbd50d1ee9fcb0cb469d2c946cb96f0786c7b8590b6136d39f086848ab3350a
|
7
|
+
data.tar.gz: 6ca9a5ec915680ecc074c369807838e56541e3946ba928d751965198a984cee991232aa5d8be389d75fef64cd77c9502a90d6338e200cc4cfcb855746ca23391
|
@@ -1,10 +1,12 @@
|
|
1
|
+
require 'damerau-levenshtein'
|
2
|
+
|
1
3
|
module Glib
|
2
4
|
module JsonCrawler
|
3
5
|
class Router
|
4
6
|
attr_reader :read_only_actions # deprecated
|
5
7
|
attr_reader :logger, :last_log, :deferred_actions
|
6
8
|
attr_reader :http_actions
|
7
|
-
attr_accessor :host
|
9
|
+
attr_accessor :host, :skip_similar_page
|
8
10
|
|
9
11
|
def log(action, url, response = nil)
|
10
12
|
@last_log = [
|
@@ -53,6 +55,7 @@ module Glib
|
|
53
55
|
@host ||= 'localhost:3000'
|
54
56
|
@page_specs = []
|
55
57
|
@page_urls = []
|
58
|
+
@skip_similar_page = false
|
56
59
|
end
|
57
60
|
|
58
61
|
def step(http, args)
|
@@ -85,6 +88,8 @@ module Glib
|
|
85
88
|
assert_target_ids_exist(params)
|
86
89
|
|
87
90
|
if action.present?
|
91
|
+
return if similar_page?(params)
|
92
|
+
|
88
93
|
@depth += 1
|
89
94
|
case action
|
90
95
|
when 'initiate_navigation'
|
@@ -205,6 +210,22 @@ module Glib
|
|
205
210
|
regex = Regexp.new("#{host}.+(?<!\.pdf)$")
|
206
211
|
regex.match(url)
|
207
212
|
end
|
213
|
+
|
214
|
+
private
|
215
|
+
def similar_page?(params)
|
216
|
+
return false if http_actions.blank? || params['url'].blank?
|
217
|
+
return false if !skip_similar_page
|
218
|
+
|
219
|
+
result = false
|
220
|
+
http_actions.each do |http_action|
|
221
|
+
next if http_action[1].blank?
|
222
|
+
distance = ::DamerauLevenshtein.distance(http_action[1], params['url'])
|
223
|
+
result = (distance <= 1) && (http_action[0] == params['action'])
|
224
|
+
|
225
|
+
break if result
|
226
|
+
end
|
227
|
+
result
|
228
|
+
end
|
208
229
|
end
|
209
230
|
end
|
210
231
|
end
|
data/lib/glib/test_helpers.rb
CHANGED
@@ -7,10 +7,10 @@ module Glib
|
|
7
7
|
end
|
8
8
|
|
9
9
|
module ClassMethods
|
10
|
-
def define_crawler_test(user, crawled_at, dump_path
|
10
|
+
def define_crawler_test(user, crawled_at, dump_path: , skip_similar_page: false, &on_after_crawl)
|
11
11
|
test "crawl api for #{user[:email]} #{user[:device]} #{user[:version] || 'current'}" do
|
12
12
|
Timecop.freeze(crawled_at || user[:crawled_at]) do
|
13
|
-
router = crawl_json_pages(user, dump_actions: dump_path.present?, dump_path: dump_path)
|
13
|
+
router = crawl_json_pages(user, dump_actions: dump_path.present?, dump_path: dump_path, skip_similar_page: skip_similar_page)
|
14
14
|
on_after_crawl&.call(router)
|
15
15
|
end
|
16
16
|
|
@@ -36,10 +36,11 @@ module Glib
|
|
36
36
|
assert_equal JSON.parse(expected), JSON.parse(result), "Result mismatch! #{__git_is_available? ? `git diff #{__controller_log_dir}/#{__controller_log_file}` : ''}"
|
37
37
|
end
|
38
38
|
|
39
|
-
def crawl_json_pages(user, log_file: nil, dump_actions: false, dump_path: nil, &block)
|
39
|
+
def crawl_json_pages(user, log_file: nil, dump_actions: false, dump_path: nil, skip_similar_page: false, &block)
|
40
40
|
__execute_crawler(user, inspect_http: true) do |router, http|
|
41
41
|
path = user[:path] ? "#{user[:path]}?format=json" : '/users/me?format=json&redirect=default'
|
42
42
|
router.host = HOST
|
43
|
+
router.skip_similar_page = skip_similar_page
|
43
44
|
router.step(
|
44
45
|
http,
|
45
46
|
'onClick' => {
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: glib-web
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 4.34.
|
4
|
+
version: 4.34.5
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- ''
|
@@ -122,6 +122,20 @@ dependencies:
|
|
122
122
|
- - ">="
|
123
123
|
- !ruby/object:Gem::Version
|
124
124
|
version: '0'
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: damerau-levenshtein
|
127
|
+
requirement: !ruby/object:Gem::Requirement
|
128
|
+
requirements:
|
129
|
+
- - ">="
|
130
|
+
- !ruby/object:Gem::Version
|
131
|
+
version: '0'
|
132
|
+
type: :runtime
|
133
|
+
prerelease: false
|
134
|
+
version_requirements: !ruby/object:Gem::Requirement
|
135
|
+
requirements:
|
136
|
+
- - ">="
|
137
|
+
- !ruby/object:Gem::Version
|
138
|
+
version: '0'
|
125
139
|
description:
|
126
140
|
email: ''
|
127
141
|
executables: []
|