wikipedia_parser 1.2.0 → 1.2.1

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.
Files changed (3) hide show
  1. checksums.yaml +8 -8
  2. data/lib/wikiParserPage.rb +6 -3
  3. metadata +1 -1
checksums.yaml CHANGED
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  !binary "U0hBMQ==":
3
3
  metadata.gz: !binary |-
4
- MDg2OTllOGVkNTYyYWM3ZDI1NzhmMmUzZjQyZGQ2ODQyMzNmY2FmOQ==
4
+ NGUzZmZkYjgyMjg2M2I2ZmU2N2ExMjEwMzJlYmRhOWUwNzg0NzYxMQ==
5
5
  data.tar.gz: !binary |-
6
- ZmEwOTlmMTg4NTU5OGIwMjY4ZDBkNGYxMjQ0YzYxOGQzMzFlZmJjOA==
6
+ NjIyOGY3ODExNmVkZTI1YTA0OTY1MGE4YjgyNzc2NjZjMDNkMjc4Yg==
7
7
  SHA512:
8
8
  metadata.gz: !binary |-
9
- ODRhMTk3YTg1ZjZjOTllMmM3NmNlOTcxMTgwZDNjNDg4YTY3YmI1MjA1YTk2
10
- MGMxMmJiYzFjZTRmYTI4MzlkODI3ZDYzMzE5ODgzNTdiZDhmYWYzMGJiY2Vk
11
- OTMzZWQyZGNiNmIxOTUwZDMyYTljMzM4NjNjMGEzM2MxMGQ4Yjc=
9
+ ZTZiM2ZiZTA5YTI1MTMxMGQ1MzA0YzcxNTc3ZjkyNjExZDBmMzBlMDg1YTUx
10
+ MWQ4YTk1OTFkNTc2MGVmMmI4YzYwODBiOWE1ZTUxNTYwZjUxOGI4OTY3YjI4
11
+ NjcxYmQ5NTdiZDQxMjVhY2QwYjE0YTM1YTdmZDNkMzAzMmE0NTc=
12
12
  data.tar.gz: !binary |-
13
- NWU4YzNhNTUwNjVkMWE3YTU4Yjk1ZjNjN2I4YTRjMzljMGNiMjZlMWJlNGNi
14
- NTZjOTVhZTc4NjUzNTQyOWY5NDczOGY0OTVjMDAxY2NlMThiYWU4ZGI0MDcy
15
- ZjAxOTE1OTYzNWNjNjcxNzgxMDYyMjc4ZjU2NDEyOGFlMWM3ZDg=
13
+ NzIyNWExY2E3YjAyNmU3NTkzOTI2NjA5MTAwNTg4M2ViZGI1MTE4NmU1Nzcy
14
+ YjA3YmVlZGVjYjI0YzVkMzI2YmY0NGFiMDRlZGQ0NTY5YzMwZTRkNGZjNTg4
15
+ NmEyMTNiZTg0Mjc5YmZmZGYxMjk5MGFiMmQwMzllYTBkNzc0ZDE=
@@ -1,10 +1,12 @@
1
+ #coding: utf-8
1
2
  class WikiParser
2
3
 
3
4
  # A Wikipedia article page object.
4
5
  class Page
5
6
 
6
7
  # The Wikipedia namespaces for all special pages {WikiParser::Page#special_page}, {#page_type}.
7
- Namespaces = %w(WP Help Talk User Template Wikipedia File Book Portal TimedText Module MediaWiki Special Media Category)
8
+ Namespaces = %w(WP Aide Help Talk User Template Wikipedia File Book Portal Portail TimedText Module MediaWiki Special Spécial Media Category Catégorie [^:]+)
9
+ Disambiguation = ["disambiguation","homonymie", "значения", "disambigua", "peker", "ujednoznacznienie", "olika betydelser", "Begriffsklärung", "desambiguación"]
8
10
  # Title of the Wikipedia article.
9
11
  attr_reader :title
10
12
  # The Wikipedia id of the article.
@@ -48,8 +50,9 @@ class WikiParser
48
50
  @id = node.content
49
51
  when 'title'
50
52
  @title = node.content
51
- if @title.match(/(#{Namespaces.join("|")}):.+/i) then @special_page = true and @page_type = $1 end
52
- if @title.match(/.+ \(disambiguation\)/i) then @disambiguation_page = true end
53
+
54
+ if @title.match(/(#{Namespaces.join("|")})|([^|+]):.+/i) then @special_page = true and @page_type = $1 end
55
+ if @title.match(/.+ \(#{Disambiguation.join("|")}\)/i) then @disambiguation_page = true end
53
56
  when 'redirect'
54
57
  @redirect = true
55
58
  @redirect_title = node["title"]
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: wikipedia_parser
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.2.0
4
+ version: 1.2.1
5
5
  platform: ruby
6
6
  authors:
7
7
  - Jonathan Raiman