url_slicer 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/.gitignore +21 -0
- data/LICENSE +20 -0
- data/README.rdoc +57 -0
- data/Rakefile +53 -0
- data/VERSION +1 -0
- data/lib/url_slicer.rb +64 -0
- data/test/helper.rb +10 -0
- data/test/test_url_slicer.rb +139 -0
- metadata +74 -0
data/.document
ADDED
data/.gitignore
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2009 Simon Chiu
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,57 @@
|
|
1
|
+
= URL Slicer
|
2
|
+
|
3
|
+
I wanted a simple library to help me parse elements from a URL string, and thus I
|
4
|
+
hacked away for a few hours and came up with URL Slicer.
|
5
|
+
|
6
|
+
Acknowledgements:
|
7
|
+
My regex know-how is a bit rusty, and so bits and pieces of the regex code to
|
8
|
+
figure out the URL elements from the string are borrowed from various places
|
9
|
+
from the internet. Unfortunately I do not remember where I got what code snippets.
|
10
|
+
If you find parts of the regex that I've used here was what you have written, please e-mail me and I'll put your name down as a contributor.
|
11
|
+
|
12
|
+
= Installation
|
13
|
+
|
14
|
+
gem install url_slicer
|
15
|
+
|
16
|
+
If you haven't already set up Gemcutter, simply go to http://gemcutter.org to learn
|
17
|
+
what you need to do.
|
18
|
+
|
19
|
+
= Usage
|
20
|
+
|
21
|
+
require 'url_slicer'
|
22
|
+
include UrlSlicer
|
23
|
+
|
24
|
+
url = UrlSlicer.new("http://www.google.com")
|
25
|
+
|
26
|
+
url.valid? # true
|
27
|
+
|
28
|
+
url.host # "www.google.com"
|
29
|
+
|
30
|
+
url.domain # "google.com"
|
31
|
+
|
32
|
+
url.port # 80
|
33
|
+
|
34
|
+
url.ssl? # false
|
35
|
+
|
36
|
+
url.subdomain # "www"
|
37
|
+
|
38
|
+
url.protocol # "http"
|
39
|
+
|
40
|
+
If you've entered an invalid url, and subsequently try to call a method (eg. @instance_object.subdomain), it will raise UrlSlicer::InvalidUrlError, which you can
|
41
|
+
resolve in your code.
|
42
|
+
|
43
|
+
= Source Code
|
44
|
+
|
45
|
+
The source can be found at http://github.com/tolatomeow/URL-Slicer. Please feel free
|
46
|
+
to fork it and add your own features. Pull requests are welcomed.
|
47
|
+
|
48
|
+
= License
|
49
|
+
|
50
|
+
MIT license.
|
51
|
+
|
52
|
+
= Contact
|
53
|
+
skhchiu [at] gmail [dot] com
|
54
|
+
|
55
|
+
== Copyright
|
56
|
+
|
57
|
+
Copyright (c) 2009 Simon Chiu. See LICENSE for details.
|
data/Rakefile
ADDED
@@ -0,0 +1,53 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'rake'
|
3
|
+
|
4
|
+
begin
|
5
|
+
require 'jeweler'
|
6
|
+
Jeweler::Tasks.new do |gem|
|
7
|
+
gem.name = "url_slicer"
|
8
|
+
gem.summary = %Q{Slices and dices URL strings into their elements}
|
9
|
+
gem.description = %Q{Easy and convenient methods to determine URL elements from a string}
|
10
|
+
gem.email = "skhchiu@gmail.com"
|
11
|
+
gem.homepage = "http://github.com/tolatomeow/URL-Slicer"
|
12
|
+
gem.authors = ["Simon Chiu"]
|
13
|
+
gem.add_development_dependency "shoulda", ">= 0"
|
14
|
+
# gem is a Gem::Specification... see http://www.rubygems.org/read/chapter/20 for additional settings
|
15
|
+
end
|
16
|
+
Jeweler::GemcutterTasks.new
|
17
|
+
rescue LoadError
|
18
|
+
puts "Jeweler (or a dependency) not available. Install it with: gem install jeweler"
|
19
|
+
end
|
20
|
+
|
21
|
+
require 'rake/testtask'
|
22
|
+
Rake::TestTask.new(:test) do |test|
|
23
|
+
test.libs << 'lib' << 'test'
|
24
|
+
test.pattern = 'test/**/test_*.rb'
|
25
|
+
test.verbose = true
|
26
|
+
end
|
27
|
+
|
28
|
+
begin
|
29
|
+
require 'rcov/rcovtask'
|
30
|
+
Rcov::RcovTask.new do |test|
|
31
|
+
test.libs << 'test'
|
32
|
+
test.pattern = 'test/**/test_*.rb'
|
33
|
+
test.verbose = true
|
34
|
+
end
|
35
|
+
rescue LoadError
|
36
|
+
task :rcov do
|
37
|
+
abort "RCov is not available. In order to run rcov, you must: sudo gem install spicycode-rcov"
|
38
|
+
end
|
39
|
+
end
|
40
|
+
|
41
|
+
task :test => :check_dependencies
|
42
|
+
|
43
|
+
task :default => :test
|
44
|
+
|
45
|
+
require 'rake/rdoctask'
|
46
|
+
Rake::RDocTask.new do |rdoc|
|
47
|
+
version = File.exist?('VERSION') ? File.read('VERSION') : ""
|
48
|
+
|
49
|
+
rdoc.rdoc_dir = 'rdoc'
|
50
|
+
rdoc.title = "url_slicer #{version}"
|
51
|
+
rdoc.rdoc_files.include('README*')
|
52
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
53
|
+
end
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.1.0
|
data/lib/url_slicer.rb
ADDED
@@ -0,0 +1,64 @@
|
|
1
|
+
class UrlSlicer
|
2
|
+
|
3
|
+
class InvalidUrlError < StandardError; end;
|
4
|
+
|
5
|
+
attr_reader :url
|
6
|
+
def initialize(url)
|
7
|
+
@url = url
|
8
|
+
end
|
9
|
+
|
10
|
+
def valid?
|
11
|
+
regex = /\A(https?|ftp|file):\/\/.+\Z/
|
12
|
+
@valid ||= url.scan(regex).length > 0 ? true : false
|
13
|
+
end
|
14
|
+
|
15
|
+
def host
|
16
|
+
raise InvalidUrlError unless valid?
|
17
|
+
regex = /\A[a-z][a-z0-9+\-.]*:\/\/([a-z0-9\-._~%!$&'()*+,;=]+@)?([a-z0-9\-._~%]+|\[[a-z0-9\-._~%!$&'()*+,;=:]+\])/
|
18
|
+
@host ||= url.scan(regex).flatten.compact.to_s
|
19
|
+
end
|
20
|
+
|
21
|
+
def domain
|
22
|
+
raise InvalidUrlError unless valid?
|
23
|
+
regex = /^(?:(?>[a-z0-9-]*\.)+?|)([a-z0-9-]+\.(?>[a-z]*(?>\.[a-z]{2})?))$/i
|
24
|
+
@domain ||= host.scan(regex).to_s
|
25
|
+
end
|
26
|
+
|
27
|
+
def subdomain
|
28
|
+
raise InvalidUrlError unless valid?
|
29
|
+
@subdomain ||= host.gsub(domain, '').gsub('.', '')
|
30
|
+
end
|
31
|
+
|
32
|
+
def port
|
33
|
+
raise InvalidUrlError unless valid?
|
34
|
+
regex = /^[a-z][a-z0-9+\-.]*:\/\/([a-z0-9\-._~%!$&'()*+,;=]+@)?([a-z0-9\-._~%]+|\[[a-z0-9\-._~%!$&'()*+,;=:]+\]):([0-9]+)/
|
35
|
+
@port ||= url.scan(regex).flatten.compact[1].to_i
|
36
|
+
|
37
|
+
@port == 0 ? default_port : @port
|
38
|
+
end
|
39
|
+
|
40
|
+
def default_port
|
41
|
+
case protocol
|
42
|
+
when "http"
|
43
|
+
80
|
44
|
+
when "https"
|
45
|
+
443
|
46
|
+
when "ftp"
|
47
|
+
21
|
48
|
+
else
|
49
|
+
nil
|
50
|
+
end
|
51
|
+
end
|
52
|
+
|
53
|
+
def protocol
|
54
|
+
raise InvalidUrlError unless valid?
|
55
|
+
regex = /^(https|http|ftp|file)/
|
56
|
+
@protocol ||= url.scan(regex).flatten[0]
|
57
|
+
end
|
58
|
+
|
59
|
+
def ssl?
|
60
|
+
raise InvalidUrlError unless valid?
|
61
|
+
protocol == "https" ? true : false
|
62
|
+
end
|
63
|
+
|
64
|
+
end
|
data/test/helper.rb
ADDED
@@ -0,0 +1,139 @@
|
|
1
|
+
require 'helper'
|
2
|
+
|
3
|
+
class TestUrlSlicer < Test::Unit::TestCase
|
4
|
+
context "validating URL" do
|
5
|
+
should "be valid if url is http://www.test.com" do
|
6
|
+
url = UrlSlicer.new("http://www.test.com")
|
7
|
+
assert url.valid?
|
8
|
+
end
|
9
|
+
|
10
|
+
should "be valid if url is ftp://ftp.test.com" do
|
11
|
+
url = UrlSlicer.new("ftp://ftp.test.com")
|
12
|
+
assert url.valid?
|
13
|
+
end
|
14
|
+
|
15
|
+
should "not be valid if url is www" do
|
16
|
+
url = UrlSlicer.new("www")
|
17
|
+
assert !url.valid?
|
18
|
+
end
|
19
|
+
|
20
|
+
should "not be valid if url is http://" do
|
21
|
+
url = UrlSlicer.new("http://")
|
22
|
+
assert !url.valid?
|
23
|
+
end
|
24
|
+
|
25
|
+
should "be valid if url is http://localhost:3000" do
|
26
|
+
url = UrlSlicer.new("http://localhost:3000")
|
27
|
+
assert url.valid?
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
context "returning host" do
|
32
|
+
should "return www.test.com if url is http://www.test.com" do
|
33
|
+
url = UrlSlicer.new("http://www.test.com")
|
34
|
+
assert_equal "www.test.com", url.host
|
35
|
+
end
|
36
|
+
|
37
|
+
should "return www.test.com if url is http://www.test.com:80" do
|
38
|
+
url = UrlSlicer.new("http://www.test.com")
|
39
|
+
assert_equal "www.test.com", url.host
|
40
|
+
end
|
41
|
+
|
42
|
+
should "return localhost if url is http://localhost:3000" do
|
43
|
+
url = UrlSlicer.new("http://localhost:3000")
|
44
|
+
assert_equal "localhost", url.host
|
45
|
+
end
|
46
|
+
|
47
|
+
should "raise error if invalid url http:/www.test.com is entered" do
|
48
|
+
url = UrlSlicer.new("http:/www.test.com")
|
49
|
+
assert_raise UrlSlicer::InvalidUrlError do
|
50
|
+
assert_equal "www.test.com", url.host
|
51
|
+
end
|
52
|
+
end
|
53
|
+
end
|
54
|
+
|
55
|
+
context "returning tld domain" do
|
56
|
+
should "return test.com if url is http://www.test.com" do
|
57
|
+
url = UrlSlicer.new("http://www.test.com")
|
58
|
+
assert_equal "test.com", url.domain
|
59
|
+
end
|
60
|
+
|
61
|
+
should "return bbc.co.uk if url is http://www.bbc.co.uk" do
|
62
|
+
url = UrlSlicer.new("http://www.bbc.co.uk")
|
63
|
+
assert_equal "bbc.co.uk", url.domain
|
64
|
+
end
|
65
|
+
|
66
|
+
should "return test.com if url is http://www.test.com:80" do
|
67
|
+
url = UrlSlicer.new("http://www.test.com")
|
68
|
+
assert_equal "test.com", url.domain
|
69
|
+
end
|
70
|
+
end
|
71
|
+
|
72
|
+
context "returning subdomain" do
|
73
|
+
should "return www if url is http://www.test.com" do
|
74
|
+
url = UrlSlicer.new("http://www.test.com")
|
75
|
+
assert_equal "www", url.subdomain
|
76
|
+
end
|
77
|
+
|
78
|
+
should "return blog if url is http://blog.somewhere.co.uk" do
|
79
|
+
url = UrlSlicer.new("http://blog.somewhere.co.uk")
|
80
|
+
assert_equal "blog", url.subdomain
|
81
|
+
end
|
82
|
+
end
|
83
|
+
|
84
|
+
context "returning port" do
|
85
|
+
should "return port 80 if url is http://www.test.com:80" do
|
86
|
+
url = UrlSlicer.new("http://www.test.com:80")
|
87
|
+
assert_equal 80, url.port
|
88
|
+
end
|
89
|
+
|
90
|
+
should "return port 8080 if url is http://www.bbc.co.uk:8080" do
|
91
|
+
url = UrlSlicer.new("http://www.bbc.co.uk:8080")
|
92
|
+
assert_equal 8080, url.port
|
93
|
+
end
|
94
|
+
|
95
|
+
should "return port 80 if url is http://www.test.com" do
|
96
|
+
url = UrlSlicer.new("http://www.test.com")
|
97
|
+
assert_equal 80, url.port
|
98
|
+
end
|
99
|
+
|
100
|
+
should "return port 21 if url is ftp://ftp.ucberkley.edu" do
|
101
|
+
url = UrlSlicer.new("ftp://ftp.ucberkley.edu")
|
102
|
+
assert_equal 21, url.port
|
103
|
+
end
|
104
|
+
|
105
|
+
should "return port 443 if url is https://gmail.com" do
|
106
|
+
url = UrlSlicer.new("https://gmail.com")
|
107
|
+
assert_equal 443, url.port
|
108
|
+
end
|
109
|
+
end
|
110
|
+
|
111
|
+
context "protocol" do
|
112
|
+
should "return http if url is http://www.test.com" do
|
113
|
+
url = UrlSlicer.new("http://www.test.com")
|
114
|
+
assert_equal "http", url.protocol
|
115
|
+
end
|
116
|
+
|
117
|
+
should "return https if url is https://gmail.com" do
|
118
|
+
url = UrlSlicer.new("https://gmail.com")
|
119
|
+
assert_equal "https", url.protocol
|
120
|
+
end
|
121
|
+
|
122
|
+
should "return ftp if url is ftp://ftp.ucberkley.edu" do
|
123
|
+
url = UrlSlicer.new("ftp://ftp.ucberkley.edu")
|
124
|
+
assert_equal "ftp", url.protocol
|
125
|
+
end
|
126
|
+
end
|
127
|
+
|
128
|
+
context "ssl" do
|
129
|
+
should "return true if url is https://www.test.com" do
|
130
|
+
url = UrlSlicer.new("https://www.test.com")
|
131
|
+
assert url.ssl?
|
132
|
+
end
|
133
|
+
|
134
|
+
should "return false if url is http://www.test.com" do
|
135
|
+
url = UrlSlicer.new("http://www.test.com")
|
136
|
+
assert !url.ssl?
|
137
|
+
end
|
138
|
+
end
|
139
|
+
end
|
metadata
ADDED
@@ -0,0 +1,74 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: url_slicer
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Simon Chiu
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-11-29 00:00:00 -05:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: shoulda
|
17
|
+
type: :development
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: "0"
|
24
|
+
version:
|
25
|
+
description: Easy and convenient methods to determine URL elements from a string
|
26
|
+
email: skhchiu@gmail.com
|
27
|
+
executables: []
|
28
|
+
|
29
|
+
extensions: []
|
30
|
+
|
31
|
+
extra_rdoc_files:
|
32
|
+
- LICENSE
|
33
|
+
- README.rdoc
|
34
|
+
files:
|
35
|
+
- .document
|
36
|
+
- .gitignore
|
37
|
+
- LICENSE
|
38
|
+
- README.rdoc
|
39
|
+
- Rakefile
|
40
|
+
- VERSION
|
41
|
+
- lib/url_slicer.rb
|
42
|
+
- test/helper.rb
|
43
|
+
- test/test_url_slicer.rb
|
44
|
+
has_rdoc: true
|
45
|
+
homepage: http://github.com/tolatomeow/URL-Slicer
|
46
|
+
licenses: []
|
47
|
+
|
48
|
+
post_install_message:
|
49
|
+
rdoc_options:
|
50
|
+
- --charset=UTF-8
|
51
|
+
require_paths:
|
52
|
+
- lib
|
53
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
54
|
+
requirements:
|
55
|
+
- - ">="
|
56
|
+
- !ruby/object:Gem::Version
|
57
|
+
version: "0"
|
58
|
+
version:
|
59
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
60
|
+
requirements:
|
61
|
+
- - ">="
|
62
|
+
- !ruby/object:Gem::Version
|
63
|
+
version: "0"
|
64
|
+
version:
|
65
|
+
requirements: []
|
66
|
+
|
67
|
+
rubyforge_project:
|
68
|
+
rubygems_version: 1.3.5
|
69
|
+
signing_key:
|
70
|
+
specification_version: 3
|
71
|
+
summary: Slices and dices URL strings into their elements
|
72
|
+
test_files:
|
73
|
+
- test/helper.rb
|
74
|
+
- test/test_url_slicer.rb
|