url_regex 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: b54cf0655c5a8a50fa9fd49b1a2de6886a040f8b
+  data.tar.gz: ef1c34438f36acf88975b0ead1ce81bfd30b7982
+SHA512:
+  metadata.gz: c32d4b0eda559e9753d38432e63328989a38b7f6991ec978f3a854d21544f06df4a1a68e6f7cf91a11ac8e6b4f255b2405e010dd1b31dec21da74c71e32a07d6
+  data.tar.gz: 07718688349b9cebbc4a353db0d60e328d52acdfd9683eb0713e80697bb6ef044dd6a1e04ef471f31383a687ce6ef7bd6e7be59fb4e85cffee848a0add650e10

data/.gitignore

@@ -0,0 +1,23 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+*.bundle
+*.so
+*.o
+*.a
+mkmf.log
+.idea/

data/.rubocop.yml

@@ -0,0 +1,4 @@
+AllCops:
+  TargetRubyVersion: 2.0
+Metrics/LineLength:
+  Max: 120

data/.travis.yml

@@ -0,0 +1,5 @@
+language: ruby
+rvm:
+  - 2.0
+before_install:
+  - gem install bundler

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in url_regex.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2016 Alexey Mogilnikov
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,88 @@
+[![Build Status](https://travis-ci.org/amogil/url_regex.svg?branch=master)](https://travis-ci.org/amogil/url_regex)
+[![Code Climate](https://codeclimate.com/github/amogil/url_regex/badges/gpa.svg)](https://codeclimate.com/github/amogil/url_regex)
+[![GitHub version](https://badge.fury.io/gh/amogil%2Furl_regex.svg)](https://badge.fury.io/gh/amogil%2Furl_regex)
+[![Dependency Status](https://gemnasium.com/badges/github.com/amogil/url_regex.svg)](https://gemnasium.com/github.com/amogil/url_regex)
+
+# UrlRegex
+
+Provides the best known regex for validating and extracting URLs.
+It uses amazing job done by [Diego Perini](https://gist.github.com/dperini/729294) 
+and [Mathias Bynens](https://mathiasbynens.be/demo/url-regex).
+
+Why do we need a gem for this regex? 
+
+- You don't need to watch changes and improvements of original regex.
+- You have an ability to slightly customize the regex: a scheme can be optional, can get the regex for validation or parsing.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'url_regex'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install url_regex
+
+## Usage
+
+Get the regex:
+
+    UrlRegex.get(options)
+    
+where options are:
+
+- `scheme_required` indicates that schema is required, defaults to `true`.
+
+- `mode` can gets either `:validation` or `:parsing`, defaults to `:validation`.
+
+`:validation` asks to return the regex for validation, namely, with `\A` prefix, and with `\z` postfix.
+That means, it matches whole text:
+
+    UrlRegex.get(mode: :validation).match('https://www.google.com').nil?
+    # => false
+    UrlRegex.get(mode: :validation).match('link: https://www.google.com').nil?
+    # => true
+    
+`:parsing` asks to return the regex for parsing:
+
+    str = 'links: google.com https://google.com?t=1'
+    str.scan(UrlRegex.get(mode: :parsing))
+    # => ["https://google.com?t=1"]
+        
+    # schema is not required
+    str.scan(UrlRegex.get(scheme_required: false, mode: :parsing))
+    # => ["google.com", "https://google.com?t=1"]
+
+`UrlRegex.get` returns regular Ruby's [Regex](http://ruby-doc.org/core-2.0.0/Regexp.html) object,
+so you can use it as usual.
+
+All regexes are case-insensitive.
+
+## FAQ
+
+Q: Hey, I want to parse HTML, but it doesn't work:
+    
+    str = '<a href="http://google.com?t=1">Link</a>'
+    str.scan(UrlRegex.get(mode: :parsing))
+    # => "http://google.com?t=1">Link</a>"
+    
+A: Well, you probably know that parsing HTML with regex is 
+[a bad idea](https://stackoverflow.com/questions/1732348/regex-match-open-tags-except-xhtml-self-contained-tags).
+It requires matching corresponding open and close brackets, that makes the regex even more complicated.
+
+Q: How can I speed up processing?
+
+A: Generated regex depends only on options, so you can get the regex only once and cache it. 
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/url_regex/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1,6 @@
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new
+
+task default: :spec

data/lib/url_regex/version.rb

@@ -0,0 +1,3 @@
+module UrlRegex
+  VERSION = '0.0.2'.freeze
+end

data/lib/url_regex.rb

@@ -0,0 +1,60 @@
+require 'url_regex/version'
+
+# Provides the best known regex for validating and extracting URLs.
+# It uses amazing job done by [Diego Perini](https://gist.github.com/dperini/729294)
+# and [Mathias Bynens](https://mathiasbynens.be/demo/url-regex).
+
+module UrlRegex
+  # Returns the regex for URLs parsing or validating.
+  #
+  # @param scheme_required [Boolean] will the regex require scheme presence, defaults to true
+  # @param mode [Symbol] purpose of the regex, `:validation` or `parsing`, defaults to `:validation`
+  # @return [Regex] regex for parsing or validating
+  def self.get(scheme_required: true, mode: :validation)
+    raise ArgumentError, "wrong mode: #{mode}" if MODES.index(mode).nil?
+    scheme = scheme_required ? PROTOCOL_IDENTIFIER : PROTOCOL_IDENTIFIER_OPTIONAL
+    mode == :validation ? /\A#{scheme} #{BASE}\z/xi : /#{scheme} #{BASE}/xi
+  end
+
+  BASE = '
+    # user:pass authentication
+    (?:\S+(?::\S*)?@)?
+
+    (?:
+      # IP address exclusion
+      # private & local networks
+      (?!(?:10|127)(?:\.\d{1,3}){3})
+      (?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})
+      (?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})
+      # IP address dotted notation octets
+      # excludes loopback network 0.0.0.0
+      # excludes reserved space >= 224.0.0.0
+      # excludes network & broadcast addresses
+      # (first & last IP address of each class)
+      (?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])
+      (?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}
+      (?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))
+      |
+      # host name
+      (?:(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)
+      # domain name
+      (?:\.(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)*
+      # TLD identifier
+      (?:\.(?:[a-z\u00a1-\uffff]{2,}))
+      # TLD may end with dot
+      \.?
+    )
+
+    # port number
+    (?::\d{2,5})?
+
+    # resource path
+    (?:[/?#]\S*)?
+  '.freeze
+
+  PROTOCOL_IDENTIFIER = '(?:(?:https?|ftp)://)'.freeze
+  PROTOCOL_IDENTIFIER_OPTIONAL = '(?:(?:https?|ftp)://)?'.freeze
+  MODES = [:validation, :parsing].freeze
+
+  private_constant :BASE, :PROTOCOL_IDENTIFIER, :PROTOCOL_IDENTIFIER_OPTIONAL, :MODES
+end

data/spec/url_regex_spec.rb

@@ -0,0 +1,226 @@
+require 'url_regex'
+
+describe UrlRegex do
+  describe '.get' do
+    it 'should allow :parsing as mode values' do
+      expect(UrlRegex.get(mode: :parsing)).to be
+    end
+
+    it 'should raise ArgumentError if mode neither :validation nor :parsing' do
+      expect { UrlRegex.get(mode: nil) }.to raise_error ArgumentError
+    end
+  end
+
+  describe 'Full validation regex' do
+    [
+      'http://foo.com/blah_blah',
+      'http://foo.com/blah_blah/',
+      'http://foo.com/blah_blah_(wikipedia)',
+      'http://foo.com/blah_blah_(wikipedia)_(again)',
+      'http://www.example.com/wpstyle/?p=364',
+      'https://www.example.com/foo/?bar=baz&inga=42&quux',
+      'http://✪df.ws/123',
+      'http://userid:password@example.com:8080',
+      'http://userid:password@example.com:8080/',
+      'http://userid@example.com',
+      'http://userid@example.com/',
+      'http://userid@example.com:8080',
+      'http://userid@example.com:8080/',
+      'http://userid:password@example.com',
+      'http://userid:password@example.com/',
+      'http://142.42.1.1/',
+      'http://142.42.1.1:8080/',
+      'http://➡.ws/䨹',
+      'http://⌘.ws',
+      'http://⌘.ws/',
+      'http://foo.com/blah_(wikipedia)#cite-1',
+      'http://foo.com/blah_(wikipedia)_blah#cite-1',
+      'http://foo.com/unicode_(✪)_in_parens',
+      'http://foo.com/(something)?after=parens',
+      'http://☺.damowmow.com/',
+      'http://code.google.com/events/#&product=browser',
+      'http://j.mp',
+      'ftp://foo.bar/baz',
+      'http://foo.bar/?q=Test%20URL-encoded%20stuff',
+      'http://مثال.إختبار',
+      'http://例子.测试',
+      'http://उदाहरण.परीक्षा',
+      "http://-.~_!$&'()*+,;=:%40:80%2f::::::@example.com",
+      'http://1337.net',
+      'http://a.b-c.de',
+      'http://a.b--c.de/',
+      'http://www.foo.bar./',
+      'http://223.255.255.254',
+      'http://example.org?foo=bar'
+    ].each do |valid_url|
+      it "should match #{valid_url}" do
+        expect(UrlRegex.get(scheme_required: true)).to match valid_url
+      end
+    end
+
+    [
+      'http://',
+      'http://.',
+      'http://..',
+      'http://../',
+      'http://?',
+      'http://??',
+      'http://??/',
+      'http://#',
+      'http://##',
+      'http://##/',
+      'http://foo.bar?q=Spaces should be encoded',
+      '//',
+      '//a',
+      '///a',
+      '///',
+      'http:///a',
+      'foo.com',
+      'rdar://1234',
+      'h://test',
+      'http:// shouldfail.com',
+      ':// should fail',
+      'http://foo.bar/foo(bar)baz quux',
+      'ftps://foo.bar/',
+      'http://-error-.invalid/',
+      'http://-a.b.co',
+      'http://a.b-.co',
+      'http://0.0.0.0',
+      'http://10.1.1.0',
+      'http://10.1.1.255',
+      'http://224.1.1.1',
+      'http://1.1.1.1.1',
+      'http://123.123.123',
+      'http://3628126748',
+      'http://.www.foo.bar/',
+      'http://.www.foo.bar./',
+      'http://10.1.1.1',
+      'http://10.1.1.254'
+    ].each do |invalid_url|
+      it "should not match #{invalid_url}" do
+        expect(UrlRegex.get(scheme_required: true)).to_not match invalid_url
+      end
+    end
+  end
+
+  describe 'Optional scheme validation regex' do
+    [
+      'foo.com/blah_blah',
+      'foo.com/blah_blah/',
+      'foo.com/blah_blah_(wikipedia)',
+      'foo.com/blah_blah_(wikipedia)_(again)',
+      'www.example.com/wpstyle/?p=364',
+      'www.example.com/foo/?bar=baz&inga=42&quux',
+      '✪df.ws/123',
+      'userid:password@example.com:8080',
+      'userid:password@example.com:8080/',
+      'userid@example.com',
+      'userid@example.com/',
+      'userid@example.com:8080',
+      'userid@example.com:8080/',
+      'userid:password@example.com',
+      'userid:password@example.com/',
+      '142.42.1.1/',
+      '142.42.1.1:8080/',
+      '➡.ws/䨹',
+      '⌘.ws',
+      '⌘.ws/',
+      'foo.com/blah_(wikipedia)#cite-1',
+      'foo.com/blah_(wikipedia)_blah#cite-1',
+      'foo.com/unicode_(✪)_in_parens',
+      'foo.com/(something)?after=parens',
+      '☺.damowmow.com/',
+      'code.google.com/events/#&product=browser',
+      'j.mp',
+      'foo.bar/baz',
+      'foo.bar/?q=Test%20URL-encoded%20stuff',
+      'مثال.إختبار',
+      '例子.测试',
+      'उदाहरण.परीक्षा',
+      "-.~_!$&'()*+,;=:%40:80%2f::::::@example.com",
+      '1337.net',
+      'a.b-c.de',
+      'a.b--c.de/',
+      'www.foo.bar./',
+      '223.255.255.254',
+      'example.org?foo=bar',
+      'google.com?t=2">Link</a>'
+    ].each do |valid_url|
+      it "should match #{valid_url}" do
+        expect(UrlRegex.get(scheme_required: false)).to match valid_url
+      end
+    end
+
+    [
+      '',
+      '.',
+      '..',
+      '../',
+      '?',
+      '??',
+      '??/',
+      '#',
+      '##',
+      '##/',
+      'foo.bar?q=Spaces should be encoded',
+      '//',
+      '//a',
+      '///a',
+      '///',
+      '/a',
+      'rdar://1234',
+      'h://test',
+      ' shouldfail.com',
+      ':// should fail',
+      'foo.bar/foo(bar)baz quux',
+      '-error-.invalid/',
+      '-a.b.co',
+      'a.b-.co',
+      '0.0.0.0',
+      '10.1.1.0',
+      '10.1.1.255',
+      '224.1.1.1',
+      '1.1.1.1.1',
+      '123.123.123',
+      '3628126748',
+      '.www.foo.bar/',
+      '.www.foo.bar./',
+      '10.1.1.1',
+      '10.1.1.254'
+    ].each do |invalid_url|
+      it "should not match #{invalid_url}" do
+        expect(UrlRegex.get(scheme_required: false)).to_not match invalid_url
+      end
+    end
+  end
+
+  describe 'Required scheme parsing regex' do
+    let(:regex) { UrlRegex.get(scheme_required: true, mode: :parsing) }
+
+    {
+      'See here: http://google.com?a=1&b=2' => ['http://google.com?a=1&b=2'],
+      'google.com - search engine' => [],
+      '<a href="google.com?t=2">Link</a>' => [],
+      'This text has many links:www.go.com?mode#anchor and https://t.co' => ['https://t.co']
+    }.each do |text, valid_url|
+      it "should parse '#{valid_url}' from '#{text}'" do
+        expect(text.scan(regex)).to eq valid_url
+      end
+    end
+  end
+
+  describe 'Optional scheme parsing regex' do
+    let(:regex) { UrlRegex.get(scheme_required: false, mode: :parsing) }
+
+    {
+      'See here: http://google.com?a=1&b=2' => ['http://google.com?a=1&b=2'],
+      'google.com - search engine' => ['google.com'],
+      '<a href="google.com?t=2">Link</a>' => ['google.com?t=2">Link</a>'],
+      'This text has many links:www.go.com?mode#anchor and https://t.co' => ['www.go.com?mode#anchor', 'https://t.co']
+    }.each do |text, valid_url|
+      it "should parse '#{valid_url}' from '#{text}'" do
+        expect(text.scan(regex)).to eq valid_url
+      end
+    end
+  end
+end

data/url_regex.gemspec

@@ -0,0 +1,27 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'url_regex/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'url_regex'
+  spec.version       = UrlRegex::VERSION
+  spec.authors       = ['Alexey Mogilnikov']
+  spec.email         = ['alexey@mogilnikov.name']
+  spec.summary       = 'Provides the best regex for validating or extracting URLs.'
+  spec.description   = 'Provides the best regex for validating or extracting URLs.'
+  spec.homepage      = 'https://github.com/amogil/url_regex'
+  spec.license       = 'MIT'
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ['lib']
+
+  spec.required_ruby_version = '>= 2.0'
+
+  spec.add_development_dependency 'bundler', '~> 1.6'
+  spec.add_development_dependency 'rake', '~> 0'
+  spec.add_development_dependency 'rubocop', '~> 0'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+end

metadata

@@ -0,0 +1,112 @@
+--- !ruby/object:Gem::Specification
+name: url_regex
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- Alexey Mogilnikov
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2016-07-18 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: Provides the best regex for validating or extracting URLs.
+email:
+- alexey@mogilnikov.name
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rubocop.yml"
+- ".travis.yml"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- lib/url_regex.rb
+- lib/url_regex/version.rb
+- spec/url_regex_spec.rb
+- url_regex.gemspec
+homepage: https://github.com/amogil/url_regex
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '2.0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.2.2
+signing_key: 
+specification_version: 4
+summary: Provides the best regex for validating or extracting URLs.
+test_files:
+- spec/url_regex_spec.rb