rlinkextract 0.0.1

data/lib/rlinkextract.rb

@@ -0,0 +1,22 @@
+require "nokogiri"
+class RLinkExtract
+  def self.extract(text)
+    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|$)")
+
+    if text.respond_to?(:xpath)
+      doc = text
+    else
+      doc = Nokogiri::HTML.parse(text)
+    end
+
+    doc.root.xpath('//text()[name(..) != "a"]').each do |textnode|
+      t = textnode.to_s
+      t.scan(re) do |replace|
+        t = t.sub(replace, "<a href=\"http://" + replace + "\">" + replace + "</a>")
+      end
+      textnode.replace t
+    end
+
+    return doc
+  end
+end

metadata

@@ -0,0 +1,78 @@
+--- !ruby/object:Gem::Specification 
+name: rlinkextract
+version: !ruby/object:Gem::Version 
+  prerelease: false
+  segments: 
+  - 0
+  - 0
+  - 1
+  version: 0.0.1
+platform: ruby
+authors: 
+- Tom Morris
+autorequire: 
+bindir: bin
+cert_chain: []
+
+date: 2012-10-23 00:00:00 +01:00
+default_executable: 
+dependencies: 
+- !ruby/object:Gem::Dependency 
+  name: nokogiri
+  prerelease: false
+  requirement: &id001 !ruby/object:Gem::Requirement 
+    none: false
+    requirements: 
+    - - ">="
+      - !ruby/object:Gem::Version 
+        segments: 
+        - 1
+        - 5
+        - 5
+        version: 1.5.5
+  type: :runtime
+  version_requirements: *id001
+description: Expands URLs in text into full links.
+email: tom@tommorris.org
+executables: []
+
+extensions: []
+
+extra_rdoc_files: []
+
+files: 
+- lib/rlinkextract.rb
+has_rdoc: true
+homepage: http://rubygems.org/gems/hola
+licenses: []
+
+post_install_message: 
+rdoc_options: []
+
+require_paths: 
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+required_rubygems_version: !ruby/object:Gem::Requirement 
+  none: false
+  requirements: 
+  - - ">="
+    - !ruby/object:Gem::Version 
+      segments: 
+      - 0
+      version: "0"
+requirements: []
+
+rubyforge_project: 
+rubygems_version: 1.3.7
+signing_key: 
+specification_version: 3
+summary: Extract and automatically link URLs in HTML.
+test_files: []
+