rlinkextract 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/rlinkextract.rb +22 -0
- metadata +78 -0
data/lib/rlinkextract.rb
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
require "nokogiri"
|
2
|
+
class RLinkExtract
|
3
|
+
def self.extract(text)
|
4
|
+
re = Regexp.new("(?:\\@[_a-zA-Z0-9]{1,17})|(?:(?:(?:(?:http|https|irc)?:\\/\\/(?:(?:[!$&-.0-9;=?A-Z_a-z]|(?:\\%[a-fA-F0-9]{2}))+(?:\\:(?:[!$&-.0-9;=?A-Z_a-z]|(?:\\%[a-fA-F0-9]{2}))+)?\\@)?)?(?:(?:(?:[a-zA-Z0-9][-a-zA-Z0-9]*\\.)+(?:(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])|(?:biz|b[abdefghijmnorstvwyz])|(?:cat|com|coop|c[acdfghiklmnoruvxyz])|d[ejkmoz]|(?:edu|e[cegrstu])|f[ijkmor]|(?:gov|g[abdefghilmnpqrstuwy])|h[kmnrtu]|(?:info|int|i[delmnoqrst])|j[emop]|k[eghimnrwyz]|l[abcikrstuvy]|(?:mil|museum|m[acdeghklmnopqrstuvwxyz])|(?:name|net|n[acefgilopruz])|(?:org|om)|(?:pro|p[aefghklmnrstwy])|qa|r[eouw]|s[abcdeghijklmnortuvyz]|(?:tel|travel|t[cdfghjklmnoprtvwz])|u[agkmsyz]|v[aceginu]|w[fs]|y[etu]|z[amw]))|(?:(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])))(?:\\:\\d{1,5})?)(?:\\/(?:(?:[!#&-;=?-Z_a-z~])|(?:\\%[a-fA-F0-9]{2}))*)?)(?=\\b|\\s|$)")
|
5
|
+
|
6
|
+
if text.respond_to?(:xpath)
|
7
|
+
doc = text
|
8
|
+
else
|
9
|
+
doc = Nokogiri::HTML.parse(text)
|
10
|
+
end
|
11
|
+
|
12
|
+
doc.root.xpath('//text()[name(..) != "a"]').each do |textnode|
|
13
|
+
t = textnode.to_s
|
14
|
+
t.scan(re) do |replace|
|
15
|
+
t = t.sub(replace, "<a href=\"http://" + replace + "\">" + replace + "</a>")
|
16
|
+
end
|
17
|
+
textnode.replace t
|
18
|
+
end
|
19
|
+
|
20
|
+
return doc
|
21
|
+
end
|
22
|
+
end
|
metadata
ADDED
@@ -0,0 +1,78 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rlinkextract
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease: false
|
5
|
+
segments:
|
6
|
+
- 0
|
7
|
+
- 0
|
8
|
+
- 1
|
9
|
+
version: 0.0.1
|
10
|
+
platform: ruby
|
11
|
+
authors:
|
12
|
+
- Tom Morris
|
13
|
+
autorequire:
|
14
|
+
bindir: bin
|
15
|
+
cert_chain: []
|
16
|
+
|
17
|
+
date: 2012-10-23 00:00:00 +01:00
|
18
|
+
default_executable:
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: nokogiri
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
none: false
|
25
|
+
requirements:
|
26
|
+
- - ">="
|
27
|
+
- !ruby/object:Gem::Version
|
28
|
+
segments:
|
29
|
+
- 1
|
30
|
+
- 5
|
31
|
+
- 5
|
32
|
+
version: 1.5.5
|
33
|
+
type: :runtime
|
34
|
+
version_requirements: *id001
|
35
|
+
description: Expands URLs in text into full links.
|
36
|
+
email: tom@tommorris.org
|
37
|
+
executables: []
|
38
|
+
|
39
|
+
extensions: []
|
40
|
+
|
41
|
+
extra_rdoc_files: []
|
42
|
+
|
43
|
+
files:
|
44
|
+
- lib/rlinkextract.rb
|
45
|
+
has_rdoc: true
|
46
|
+
homepage: http://rubygems.org/gems/hola
|
47
|
+
licenses: []
|
48
|
+
|
49
|
+
post_install_message:
|
50
|
+
rdoc_options: []
|
51
|
+
|
52
|
+
require_paths:
|
53
|
+
- lib
|
54
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
55
|
+
none: false
|
56
|
+
requirements:
|
57
|
+
- - ">="
|
58
|
+
- !ruby/object:Gem::Version
|
59
|
+
segments:
|
60
|
+
- 0
|
61
|
+
version: "0"
|
62
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
63
|
+
none: false
|
64
|
+
requirements:
|
65
|
+
- - ">="
|
66
|
+
- !ruby/object:Gem::Version
|
67
|
+
segments:
|
68
|
+
- 0
|
69
|
+
version: "0"
|
70
|
+
requirements: []
|
71
|
+
|
72
|
+
rubyforge_project:
|
73
|
+
rubygems_version: 1.3.7
|
74
|
+
signing_key:
|
75
|
+
specification_version: 3
|
76
|
+
summary: Extract and automatically link URLs in HTML.
|
77
|
+
test_files: []
|
78
|
+
|