rack-linkify 0.0.0
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.
- data/CHANGELOG +2 -0
- data/LICENSE +21 -0
- data/README.rdoc +20 -0
- data/Rakefile +32 -0
- data/lib/rack-linkify.rb +74 -0
- data/test/rackapp/app.rb +69 -0
- data/test/rackapp/config.ru +6 -0
- metadata +71 -0
data/CHANGELOG
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License
|
2
|
+
|
3
|
+
Copyright (c) 2009 Wyatt M. Greene
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
= Rack::Linkify
|
2
|
+
|
3
|
+
== Description
|
4
|
+
|
5
|
+
Dead links (like this one http://you.cant.click.this.com/) are magically
|
6
|
+
transformed into live links! Rack::Linkify is very generous in what it
|
7
|
+
considers a link; it will turn http://www.google.com, www.google.com, and
|
8
|
+
just plain google.com into a link.
|
9
|
+
|
10
|
+
Rack::Linkify can also turn text that looks like @this into a twitter link.
|
11
|
+
|
12
|
+
== Usage
|
13
|
+
|
14
|
+
URLs only:
|
15
|
+
|
16
|
+
use Rack::Linkify
|
17
|
+
|
18
|
+
Enable Twitter links, too:
|
19
|
+
|
20
|
+
use Rack::Linkify, :twitter => true
|
data/Rakefile
ADDED
@@ -0,0 +1,32 @@
|
|
1
|
+
require 'rake'
|
2
|
+
require 'rubygems'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |s|
|
7
|
+
s.name = "rack-linkify"
|
8
|
+
s.version = "0.0.0"
|
9
|
+
s.add_dependency 'rack-plastic', '>= 0.0.3'
|
10
|
+
s.author = "Wyatt Greene"
|
11
|
+
s.email = "techiferous@gmail.com"
|
12
|
+
s.summary = "Rack middleware that adds anchor tags to URLs in text."
|
13
|
+
s.description = %Q{
|
14
|
+
Any URLs that occur in the text of the web page are automatically surrounded
|
15
|
+
by an anchor tag.
|
16
|
+
}
|
17
|
+
s.require_path = "lib"
|
18
|
+
s.files = []
|
19
|
+
s.files << "README.rdoc"
|
20
|
+
s.files << "LICENSE"
|
21
|
+
s.files << "CHANGELOG"
|
22
|
+
s.files << "Rakefile"
|
23
|
+
s.files += Dir.glob("lib/**/*")
|
24
|
+
s.files += Dir.glob("test/**/*")
|
25
|
+
s.homepage = "http://github.com/techiferous/rack-linkify"
|
26
|
+
s.requirements << "none"
|
27
|
+
s.has_rdoc = false
|
28
|
+
end
|
29
|
+
Jeweler::GemcutterTasks.new
|
30
|
+
rescue LoadError
|
31
|
+
puts "Jeweler (or a dependency) not available. Install it with: sudo gem install jeweler"
|
32
|
+
end
|
data/lib/rack-linkify.rb
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
require 'rack-plastic'
|
2
|
+
|
3
|
+
module Rack
|
4
|
+
class Linkify < Plastic
|
5
|
+
|
6
|
+
def change_nokogiri_doc(doc)
|
7
|
+
find_candidate_links(doc)
|
8
|
+
doc
|
9
|
+
end
|
10
|
+
|
11
|
+
def change_html_string(html)
|
12
|
+
linkify(html)
|
13
|
+
end
|
14
|
+
|
15
|
+
private
|
16
|
+
|
17
|
+
def find_candidate_links(doc)
|
18
|
+
doc.at_css("body").traverse do |node|
|
19
|
+
if node.text?
|
20
|
+
update_text(node, mark_links(node.content))
|
21
|
+
end
|
22
|
+
end
|
23
|
+
end
|
24
|
+
|
25
|
+
def linkify(html)
|
26
|
+
html.gsub!('beginninganchor1', '<a href="')
|
27
|
+
html.gsub!('beginninganchor2', '">')
|
28
|
+
html.gsub!('endinganchor', '</a>')
|
29
|
+
# if an href URL doesn't start with http://, let's add it:
|
30
|
+
html.gsub!(/href="((?!http)\S+)/, 'href="http://\1')
|
31
|
+
html
|
32
|
+
end
|
33
|
+
|
34
|
+
def mark_links(text)
|
35
|
+
|
36
|
+
new_text = text
|
37
|
+
|
38
|
+
# A pattern-matching algorithm that would correctly detect URLs 100% of the time
|
39
|
+
# would be prohibitively complex. For example, if a URL in a sentence is followed
|
40
|
+
# by a comma, like http://www.google.com, we would want to match the URL but
|
41
|
+
# skip the comma. However, commas are allowed in URLs. So there are a lot
|
42
|
+
# of edge cases that make a complete solution very complex.
|
43
|
+
#
|
44
|
+
# The following strategy has the benefits of being relatively straightforword
|
45
|
+
# to implement as well as having high accuracy. Text is scanned for top-level
|
46
|
+
# domains, and if one is found it is assumed to be a URL.
|
47
|
+
|
48
|
+
common_gtlds = "com|net|org|edu|gov|info|mil|name|mobi|biz"
|
49
|
+
|
50
|
+
new_text.gsub!(/\b
|
51
|
+
(\S+\.(#{common_gtlds}|[a-z]{2})\S*) # match words that contain common
|
52
|
+
# top-level domains or country codes
|
53
|
+
#
|
54
|
+
(\.|\?|!|:|,\))* # if the URL ends in punctuation,
|
55
|
+
# assume the punction is grammatical
|
56
|
+
# and is not part of the URL
|
57
|
+
\b/x,
|
58
|
+
# We mark the text with phrases like "beginninganchor1". That's because it's
|
59
|
+
# much easier to replace these strings later with anchor tags rather than work within
|
60
|
+
# Nokogiri's document structure to add a new node in the middle of the text.
|
61
|
+
'beginninganchor1\0beginninganchor2\0\3endinganchor')
|
62
|
+
|
63
|
+
# text that looks like @foo can become a twitter link
|
64
|
+
if options[:twitter]
|
65
|
+
new_text.gsub!(/(^|\s)(@(\w+))(\.|\?|!|:|,\))*\b/,
|
66
|
+
'\1beginninganchor1http://twitter.com/\3beginninganchor2\2endinganchor')
|
67
|
+
end
|
68
|
+
|
69
|
+
new_text
|
70
|
+
|
71
|
+
end
|
72
|
+
|
73
|
+
end
|
74
|
+
end
|
data/test/rackapp/app.rb
ADDED
@@ -0,0 +1,69 @@
|
|
1
|
+
class App
|
2
|
+
|
3
|
+
def call(env)
|
4
|
+
response = Rack::Response.new
|
5
|
+
response['Content-Type'] = 'text/html'
|
6
|
+
response.write front_page
|
7
|
+
response.finish
|
8
|
+
end
|
9
|
+
|
10
|
+
def front_page
|
11
|
+
%Q{
|
12
|
+
<!DOCTYPE html
|
13
|
+
PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"
|
14
|
+
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">
|
15
|
+
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
|
16
|
+
<head>
|
17
|
+
<title>Testing Rack::Linkify</title>
|
18
|
+
</head>
|
19
|
+
<body>
|
20
|
+
<div id="container">
|
21
|
+
<h1>Testing Rack::Linkify</h1>
|
22
|
+
<p>
|
23
|
+
This is a test of links in free-flowing text. <br />
|
24
|
+
Test a typical URL http://www.google.com <br />
|
25
|
+
Test a URL followed by a period http://www.google.com. <br />
|
26
|
+
Test a URL without the http www.google.com <br />
|
27
|
+
Test a URL without http and ending in a period www.google.com. <br />
|
28
|
+
Test a URL without www and followed by a comma google.com, <br />
|
29
|
+
Test a URL followed by a bang google.com! <br />
|
30
|
+
Test a URL followed by a hook google.com? <br />
|
31
|
+
Test a URL followed by an interrobang google.com?! <br />
|
32
|
+
Test another URL coderack.org <br />
|
33
|
+
Test a URL with a path google.com/foobar <br />
|
34
|
+
Test a longer URL google.com/foobar/index.html. <br />
|
35
|
+
Test a URL followed by a parenthesis google.com) <br />
|
36
|
+
Test a URL followed by a parenthesis and comma google.com), <br />
|
37
|
+
Test atypical gTLDs http://www.something.info, and http://del.icio.us <br />
|
38
|
+
Test more atypical gTLDs http://bit.ly/n0og http://www.wikio.co.uk <br />
|
39
|
+
</p>
|
40
|
+
<p>
|
41
|
+
Here are some more links:
|
42
|
+
<pre>
|
43
|
+
http://www.google.com
|
44
|
+
http://www.google.co.uk
|
45
|
+
www.google.com
|
46
|
+
google.com
|
47
|
+
http://localhost:3000/houses
|
48
|
+
http://oreilly.com/ruby/excerpts/ruby-learning-rails/ruby-guide-regular-expressions.html
|
49
|
+
http://www.regular-expressions.info/freespacing.html
|
50
|
+
http://www.perlmonks.org/?node_id=518444
|
51
|
+
localhost:3000/houses
|
52
|
+
oreilly.com/ruby/excerpts/ruby-learning-rails/ruby-guide-regular-expressions.html
|
53
|
+
www.regular-expressions.info/freespacing.html
|
54
|
+
www.perlmonks.org/?node_id=518444
|
55
|
+
http://maps.google.com/maps?f=q&source=s_q&hl=en&geocode=&q=375+Harvard+St,+Cambridge,+MA+02138&sll=42.398774,-71.117184&sspn=0.008097,0.019205&ie=UTF8&ll=42.372781,-71.112099&spn=0.008101,0.019205&z=16&iwloc=A
|
56
|
+
</pre>
|
57
|
+
<p>
|
58
|
+
here is a potential twitter address @techiferous <br />
|
59
|
+
here it is with punctuation @techiferous. <br />
|
60
|
+
will this work? @coderack?!?! <br />
|
61
|
+
and how about this? @techiferous) <br />
|
62
|
+
</p>
|
63
|
+
</div>
|
64
|
+
</body>
|
65
|
+
</html>
|
66
|
+
}
|
67
|
+
end
|
68
|
+
|
69
|
+
end
|
metadata
ADDED
@@ -0,0 +1,71 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: rack-linkify
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Wyatt Greene
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-12-03 00:00:00 -05:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: rack-plastic
|
17
|
+
type: :runtime
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 0.0.3
|
24
|
+
version:
|
25
|
+
description: "\n Any URLs that occur in the text of the web page are automatically surrounded\n by an anchor tag.\n "
|
26
|
+
email: techiferous@gmail.com
|
27
|
+
executables: []
|
28
|
+
|
29
|
+
extensions: []
|
30
|
+
|
31
|
+
extra_rdoc_files:
|
32
|
+
- LICENSE
|
33
|
+
- README.rdoc
|
34
|
+
files:
|
35
|
+
- CHANGELOG
|
36
|
+
- LICENSE
|
37
|
+
- README.rdoc
|
38
|
+
- Rakefile
|
39
|
+
- lib/rack-linkify.rb
|
40
|
+
- test/rackapp/app.rb
|
41
|
+
- test/rackapp/config.ru
|
42
|
+
has_rdoc: true
|
43
|
+
homepage: http://github.com/techiferous/rack-linkify
|
44
|
+
licenses: []
|
45
|
+
|
46
|
+
post_install_message:
|
47
|
+
rdoc_options:
|
48
|
+
- --charset=UTF-8
|
49
|
+
require_paths:
|
50
|
+
- lib
|
51
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
52
|
+
requirements:
|
53
|
+
- - ">="
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
version: "0"
|
56
|
+
version:
|
57
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: "0"
|
62
|
+
version:
|
63
|
+
requirements:
|
64
|
+
- none
|
65
|
+
rubyforge_project:
|
66
|
+
rubygems_version: 1.3.5
|
67
|
+
signing_key:
|
68
|
+
specification_version: 3
|
69
|
+
summary: Rack middleware that adds anchor tags to URLs in text.
|
70
|
+
test_files: []
|
71
|
+
|