unshorten 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/bin/unshorten +10 -0
- data/lib/unshorten.rb +86 -0
- data/test/test_unshorten.rb +16 -0
- metadata +50 -0
data/bin/unshorten
ADDED
data/lib/unshorten.rb
ADDED
@@ -0,0 +1,86 @@
|
|
1
|
+
require 'net/http'
|
2
|
+
require 'uri'
|
3
|
+
|
4
|
+
# Get original URLs from shortened ones.
|
5
|
+
class Unshorten
|
6
|
+
|
7
|
+
# Cache entities limit
|
8
|
+
CACHE_SIZE_LIMIT = 1024
|
9
|
+
|
10
|
+
# Default options for unshorten
|
11
|
+
DEFAULT_OPTIONS = {
|
12
|
+
:max_level => 10,
|
13
|
+
:timeout => 2,
|
14
|
+
:use_cache => true,
|
15
|
+
:add_missing_http => true
|
16
|
+
}
|
17
|
+
|
18
|
+
@@cache = { }
|
19
|
+
|
20
|
+
class << self
|
21
|
+
|
22
|
+
# Unshorten a URL
|
23
|
+
#
|
24
|
+
# @param url [String] A shortened URL
|
25
|
+
# @param options [Hash] A set of options
|
26
|
+
# @option options [Integer] :max_level Max redirect times
|
27
|
+
# @option options [Integer] :timeout Timeout in seconds, for every request
|
28
|
+
# @option options [Boolean] :use_cache Use cached result if available
|
29
|
+
# @option options [Boolean] :add_missing_http add 'http://' if missing
|
30
|
+
# @see DEFAULT_OPTIONS
|
31
|
+
#
|
32
|
+
# @return Original url, a url that does not redirect
|
33
|
+
def unshorten(url, options = {})
|
34
|
+
DEFAULT_OPTIONS.each { |k, v| (options[k] = v) unless options.has_key? k }
|
35
|
+
|
36
|
+
follow(url, options)
|
37
|
+
end
|
38
|
+
|
39
|
+
alias :'[]' :unshorten
|
40
|
+
|
41
|
+
private
|
42
|
+
|
43
|
+
def expire_cache #:nodoc:
|
44
|
+
@@cache = { }
|
45
|
+
end
|
46
|
+
|
47
|
+
def mix_options(old, *new) #:nodoc:
|
48
|
+
options = old.dup
|
49
|
+
new.each { |n| n.each { |k, v| options[k] = v } }
|
50
|
+
options
|
51
|
+
end
|
52
|
+
|
53
|
+
def add_missing_http(url) #:nodoc:
|
54
|
+
if url =~ /^https?:/i
|
55
|
+
url
|
56
|
+
else
|
57
|
+
"http://#{url}"
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
def follow(url, options = DEFAULT_OPTIONS, level = 0) #:nodoc:
|
62
|
+
return @@cache[url] if options[:use_cache] and @@cache[url]
|
63
|
+
|
64
|
+
url = add_missing_http(url) if options[:add_missing_http]
|
65
|
+
return url if level >= options[:max_level]
|
66
|
+
|
67
|
+
uri = URI.parse(url)
|
68
|
+
http = Net::HTTP.new(uri.host, uri.port)
|
69
|
+
http.read_timeout = options[:timeout]
|
70
|
+
|
71
|
+
response = http.request_head(uri.path.empty? ? '/' : uri.path) rescue nil
|
72
|
+
|
73
|
+
if response.is_a? Net::HTTPRedirection and response['location'] then
|
74
|
+
expire_cache if @@cache.size > CACHE_SIZE_LIMIT
|
75
|
+
@@cache[url] = follow(response['location'], options, level + 1)
|
76
|
+
else
|
77
|
+
url
|
78
|
+
end
|
79
|
+
end
|
80
|
+
|
81
|
+
end
|
82
|
+
|
83
|
+
end
|
84
|
+
|
85
|
+
# vim:et:ts=2 sw=2
|
86
|
+
|
@@ -0,0 +1,16 @@
|
|
1
|
+
require 'test/unit'
|
2
|
+
require 'unshorten'
|
3
|
+
|
4
|
+
class UnshortenTest < Test::Unit::TestCase
|
5
|
+
ORIGINAL_URL = 'http://dir.yahoo.com/Reference/Libraries/Library_and_Information_Science/Metadata/URIs___Universal_Resource_Identifiers/URLs___Uniform_Resource_Locators/URL_Shortening/'
|
6
|
+
SHORTENED_URL = 'http://tinyurl.com/j'
|
7
|
+
|
8
|
+
def test_unshorten_alias
|
9
|
+
assert_equal ORIGINAL_URL, Unshorten[SHORTENED_URL, :use_cache => false]
|
10
|
+
end
|
11
|
+
|
12
|
+
def test_option_max_level
|
13
|
+
assert_equal SHORTENED_URL, Unshorten.unshorten(SHORTENED_URL, :max_level => 0, :use_cache => false)
|
14
|
+
end
|
15
|
+
|
16
|
+
end
|
metadata
ADDED
@@ -0,0 +1,50 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: unshorten
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
prerelease:
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Wu Jun
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
date: 2011-12-10 00:00:00.000000000 Z
|
13
|
+
dependencies: []
|
14
|
+
description: Get original URLs from shortened ones
|
15
|
+
email: quark@lihdd.net
|
16
|
+
executables:
|
17
|
+
- unshorten
|
18
|
+
extensions: []
|
19
|
+
extra_rdoc_files: []
|
20
|
+
files:
|
21
|
+
- lib/unshorten.rb
|
22
|
+
- test/test_unshorten.rb
|
23
|
+
- bin/unshorten
|
24
|
+
homepage: https://github.com/quark-zju/unshorten
|
25
|
+
licenses: []
|
26
|
+
post_install_message:
|
27
|
+
rdoc_options: []
|
28
|
+
require_paths:
|
29
|
+
- lib
|
30
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
31
|
+
none: false
|
32
|
+
requirements:
|
33
|
+
- - ! '>='
|
34
|
+
- !ruby/object:Gem::Version
|
35
|
+
version: '0'
|
36
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
37
|
+
none: false
|
38
|
+
requirements:
|
39
|
+
- - ! '>='
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: '0'
|
42
|
+
requirements: []
|
43
|
+
rubyforge_project:
|
44
|
+
rubygems_version: 1.8.11
|
45
|
+
signing_key:
|
46
|
+
specification_version: 3
|
47
|
+
summary: Unshorten URLs
|
48
|
+
test_files:
|
49
|
+
- test/test_unshorten.rb
|
50
|
+
has_rdoc:
|