wikipedia_parser 1.2.0 → 1.2.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +8 -8
- data/lib/wikiParserPage.rb +6 -3
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,15 +1,15 @@
|
|
1
1
|
---
|
2
2
|
!binary "U0hBMQ==":
|
3
3
|
metadata.gz: !binary |-
|
4
|
-
|
4
|
+
NGUzZmZkYjgyMjg2M2I2ZmU2N2ExMjEwMzJlYmRhOWUwNzg0NzYxMQ==
|
5
5
|
data.tar.gz: !binary |-
|
6
|
-
|
6
|
+
NjIyOGY3ODExNmVkZTI1YTA0OTY1MGE4YjgyNzc2NjZjMDNkMjc4Yg==
|
7
7
|
SHA512:
|
8
8
|
metadata.gz: !binary |-
|
9
|
-
|
10
|
-
|
11
|
-
|
9
|
+
ZTZiM2ZiZTA5YTI1MTMxMGQ1MzA0YzcxNTc3ZjkyNjExZDBmMzBlMDg1YTUx
|
10
|
+
MWQ4YTk1OTFkNTc2MGVmMmI4YzYwODBiOWE1ZTUxNTYwZjUxOGI4OTY3YjI4
|
11
|
+
NjcxYmQ5NTdiZDQxMjVhY2QwYjE0YTM1YTdmZDNkMzAzMmE0NTc=
|
12
12
|
data.tar.gz: !binary |-
|
13
|
-
|
14
|
-
|
15
|
-
|
13
|
+
NzIyNWExY2E3YjAyNmU3NTkzOTI2NjA5MTAwNTg4M2ViZGI1MTE4NmU1Nzcy
|
14
|
+
YjA3YmVlZGVjYjI0YzVkMzI2YmY0NGFiMDRlZGQ0NTY5YzMwZTRkNGZjNTg4
|
15
|
+
NmEyMTNiZTg0Mjc5YmZmZGYxMjk5MGFiMmQwMzllYTBkNzc0ZDE=
|
data/lib/wikiParserPage.rb
CHANGED
@@ -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
|
-
|
52
|
-
if @title.match(
|
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"]
|