url_scrubber 0.8.6 → 0.8.7

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 CHANGED
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  !binary "U0hBMQ==":
3
3
  metadata.gz: !binary |-
4
- MDM4ZTYzMzA2NTRjNzhjOTI2MjI4MGI3MDdlZjIzYjZmYjQ4ZDUwOA==
4
+ MzRlZTdlZWY1OTRiMWZlMDY0NDI1MWNjNmM4ZmNlZjRhYjYxYWZkMQ==
5
5
  data.tar.gz: !binary |-
6
- NDczYzkxOTc4OGFkNmQzNTI2M2E4Y2E0MGM2NmRhZmQwNWRmZDYwNw==
6
+ ZTBjYjQ4NjBjYjllZGM2Y2I2NjgwY2U1ODliYWM5NjNiNTc4YTFjYw==
7
7
  SHA512:
8
8
  metadata.gz: !binary |-
9
- MmMxY2U0ZmMwMDYyZjUwYjQ4YjI3OTU2NDZiZjgzYTZhZDY5ODQ3ZTAzM2E4
10
- NTNkNWM0NWMwNTcyYTkwMDlkYzk2MzkyMDY1NjYzMTNlODg0Y2FhYWIxNmUy
11
- ZDgwMjUxNDI3YTk5ZTQ2MTdjZWJkNzcxZGViMzYyZTBjYTI5NDY=
9
+ YTFhMDdiZjhjNGZmY2RmODczYmIyNTYxNWM0YzM0MmEwYWIzNTUwYTFkMzM3
10
+ ZDMwOGYxNmZhMDYwMWIyOTNhODQ3MjdiNGE5NzY3Nzk0NGJhNTNiOGIwZTA2
11
+ YWJkZjAxOTQ1ODk3ODE4YmQ4MTUyMDJlYWY5NTc1MTIxNjBmMjk=
12
12
  data.tar.gz: !binary |-
13
- ZDRkYjJmNjY2ZWQ5N2IxNzE2MWYxNGNmODJhNDJmNjc0OTkyZjIzOTYxMzMx
14
- NGVkZjE4MTYzN2E4OWE2MTNhMDUzOGFiMWY1Mzg1MmNkNWUyNWQyNjlhYjE0
15
- M2NmYjY2ZDg3MzAxOTNkZTZmZTQ0NDFlY2FmODVjOWI1OTEyYzA=
13
+ MmQ2ZmUxZDViNWE4MjIyNmIzYzY0ODMwN2ZkNTBjYTFkOGFmOWVjNjAzZGVj
14
+ NjFiMDlhZTdhNTA2Yzg3NDJhZjhmZjY1ZTA1YWNkY2IzNDQ0YmZkNzlhZDZj
15
+ Y2YzZDQyZDM3ZDFkOGJmOGEyOTYzZWJlMzUwYTFlYTYzNGZiZWI=
data/lib/url_scrubber.rb CHANGED
@@ -20,7 +20,7 @@ module UrlScrubber
20
20
  url.sub!('#!/', '')
21
21
  url.sub!('%27', '\'')
22
22
  url = downcase_domain(url)
23
- remove_www!(url)
23
+ remove_subdomain!(url)
24
24
  remove_html_tags!(url)
25
25
  url = drop_anchor!(special_cases(url))
26
26
  url.sub!(/,+$/, "") # remove one or more trailing commas at the end of the URL
@@ -200,11 +200,13 @@ module UrlScrubber
200
200
  end
201
201
 
202
202
 
203
- def self.remove_www!(url)
203
+ def self.remove_subdomain!(url)
204
204
  # url.sub!(%r{://www\d*\.}, '://')
205
205
  url.sub!(%r{^https?://www?w?\d*\.}i, 'http://')
206
206
  url.sub!(%r{^https?://m\d*\.}i, 'http://')
207
207
  url.sub!(%r{^https?://mobile\d*\.}i, 'http://')
208
+ url.sub!(%r{^https?://touch\d*\.}i, 'http://')
209
+ url.sub!(%r{^https?://mbasic\.facebook\.com}i, 'http://facebook.com')
208
210
  url
209
211
  end
210
212
 
@@ -1,3 +1,3 @@
1
1
  module UrlScrubber
2
- VERSION = "0.8.6"
2
+ VERSION = "0.8.7"
3
3
  end
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: url_scrubber
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.8.6
4
+ version: 0.8.7
5
5
  platform: ruby
6
6
  authors:
7
7
  - Colin Langton
@@ -11,7 +11,7 @@ authors:
11
11
  autorequire:
12
12
  bindir: bin
13
13
  cert_chain: []
14
- date: 2016-12-10 00:00:00.000000000 Z
14
+ date: 2016-12-12 00:00:00.000000000 Z
15
15
  dependencies:
16
16
  - !ruby/object:Gem::Dependency
17
17
  name: rspec