public_suffix 1.5.3 → 2.0.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: c5e75fe3c5d642adeeae60366174f25b99844b90
-  data.tar.gz: 1dc35267a417747ab37e1997434d5e219839a391
+  metadata.gz: eaa67d1cb0c7a21070e9b0bc56d3f83950efddb3
+  data.tar.gz: 6c15669d468bf25585e7381127adc4670b147879
 SHA512:
-  metadata.gz: 05477a5b192b451131723a039815127c0c12cc89b2c911f3f162e1fc20a2a596cf7639d46f521d1a17fb7f1db7a9ad29d2181809e952a581d68f530369cdff54
-  data.tar.gz: 16bf8bf394f1efca171596991c4d3039a09b658932dc7c45c00277b0fb482a917b203a53f640d83185497f2bb6e535554f69333be777d36807e1cd7699e5d98c
+  metadata.gz: 7ad8bbd99caed951de6db31c58e6597e928af763aadb92a284533c2f64e9c6e6652a43cb2f890839ca052a7358d46fd35f87f7402334f3776955a3abdea4f609
+  data.tar.gz: c59285a5c3c31f617f3e935202a7058d733629fb77fe1b3b9797e554de837810986b26a3e00f328a9d1511a00836a0de696d6bad1df899bf606a7e28c573988b

data/.rubocop.yml

@@ -0,0 +1,8 @@
+inherit_from:
+  - .rubocop_defaults.yml
+
+Style/ClassAndModuleChildren:
+  Exclude:
+    - 'spec/**/*_spec.rb'
+    - 'test/**/*_test.rb'
+

data/.rubocop_defaults.yml

@@ -0,0 +1,127 @@
+AllCops:
+  Exclude:
+    # Exclude .gemspec files because they are generally auto-generated
+    - '*.gemspec'
+    # Exclude vendored folders
+    - 'tmp/**/*'
+    - 'vendor/**/*'
+
+Lint/AmbiguousRegexpLiteral:
+  Enabled: false
+
+# [codesmell]
+Metrics/AbcSize:
+  Enabled: false
+  Exclude:
+    - 'spec/**/*_spec.rb'
+    - 'test/**/*_test.rb'
+
+# [codesmell]
+Metrics/ClassLength:
+  Exclude:
+    - 'spec/**/*_spec.rb'
+    - 'test/**/*_test.rb'
+
+# [codesmell]
+Metrics/MethodLength:
+  Exclude:
+    - 'spec/**/*_spec.rb'
+    - 'test/**/*_test.rb'
+  Max: 15
+
+# [codesmell]
+Metrics/LineLength:
+  Enabled: false
+  Exclude:
+    - 'spec/**/*_spec.rb'
+    - 'test/**/*_test.rb'
+  Max: 100
+
+# Do not use "and" or "or" in conditionals, but for readability we can use it
+# to chain executions. Just beware of operator order.
+Style/AndOr:
+  EnforcedStyle: conditionals
+
+Style/Documentation:
+  Exclude:
+    - 'spec/**/*'
+    - 'test/**/*'
+
+# Double empty lines are useful to separate conceptually different methods
+# in the same class or module.
+Style/EmptyLines:
+  Enabled: false
+
+# In most cases, a space is nice. Sometimes, it's not.
+# Just be consistent with the rest of the surrounding code.
+Style/EmptyLinesAroundClassBody:
+  Enabled: false
+
+# In most cases, a space is nice. Sometimes, it's not.
+# Just be consistent with the rest of the surrounding code.
+Style/EmptyLinesAroundModuleBody:
+  Enabled: false
+
+# I personally don't care about the format style.
+# In most cases I like to use %, but not at the point I want to enforce it
+# as a convention in the entire code.
+Style/FormatString:
+  Enabled: false
+
+# Prefer the latest Hash syntax
+Style/HashSyntax:
+  Exclude:
+    # But Rakefiles generally have some definition like
+    #   :default => :test
+    # that looks nicer with the old rocket syntax.
+    - 'Rakefile'
+
+# Array indentation should be considered like MultilineMethodCallIndentation indentation
+# and use 4 spaces instead of 2.
+Style/IndentArray:
+  IndentationWidth: 4
+
+# Hash indentation should be considered like MultilineMethodCallIndentation indentation
+# and use 4 spaces instead of 2.
+Style/IndentHash:
+  IndentationWidth: 4
+
+# Multi-line differs from standard indentation, they are indented twice.
+Style/MultilineMethodCallIndentation:
+  EnforcedStyle: indented
+  IndentationWidth: 4
+
+Style/IfUnlessModifier:
+  Enabled: false
+
+# unless is not always cool.
+Style/NegatedIf:
+  Enabled: false
+
+# There are cases were the inline rescue is ok. We can either downgrade the severity,
+# or rely on the developer judgement on a case-by-case basis.
+Style/RescueModifier:
+  Enabled: false
+
+# Hate It or Love It, I prefer double quotes as this is more consistent
+# with several other programming languages and the output of puts and inspect.
+Style/StringLiterals:
+  EnforcedStyle: double_quotes
+
+# It's nice to be consistent. The trailing comma also allows easy reordering,
+# and doesn't cause a diff in Git when you add a line to the bottom.
+Style/TrailingCommaInLiteral:
+  EnforcedStyleForMultiline: consistent_comma
+
+Style/TrivialAccessors:
+  # IgnoreClassMethods because I want to be able to define class-level accessors
+  # that sets an instance variable on the metaclass, such as:
+  #
+  #    def self.default=(value)
+  #      @default = value
+  #    end
+  #
+  IgnoreClassMethods: true
+
+Style/WordArray:
+  Enabled: false

data/.travis.yml

@@ -3,9 +3,16 @@ rvm:
   - 2.0
   - 2.1
   - 2.2
+  - 2.3.0
+  - jruby-9.0.5.0
   - ruby-head
-  - jruby-19mode
-  - rbx-19mode
+
+sudo: false
+cache:
+  - bundler
+
+env:
+  - COVERALL=1
 
 notifications:
   recipients:
@@ -13,7 +20,5 @@ notifications:
 
 matrix:
   allow_failures:
-    - rvm: rbx-19mode
-    - rvm: jruby-19mode
     - rvm: ruby-head
-
+    - rvm: jruby-9.0.5.0

data/2.0-Upgrade.md

@@ -0,0 +1,35 @@
+# Welcome to PublicSuffix 2.0!
+
+PublicSuffix 2.0 contains a rewritten internal representation and comparison logic, that drastically increases the lookup performance. The new version also changes several internal and external API.
+
+This document documents the most relevant changes to help you upgrading from PublicSuffix 1.0 to 2.0.
+
+## What's New
+
+- The library is now 100% compliants with the official PublicSuffix tests. The major breaking change you may experience, is that if a domain passed as input doesn't match any rule, the rule `*` is assumed. You can override this behavior by passing a custom default rule with the `default_rule` option.
+- `PublicSuffix.domain` is a new method that parses the input and returns the domain (combination of second level domain + suffix). This is a convenient helper to parse a domain name, for example when you need to determine the cookie or SSL scope.
+- Added the ability to disable the use of private domains either at runtime, in addition to the ability to not load the private domains section when reading the list (`private_domains: false`). This feature also superseded the `private_domains` class-level attribute, that is no longer available.
+
+## Upgrade
+
+When upgrading, here's the most relevant changes to keep an eye on:
+
+- Several futile utility helpers were removed, such as `Domain#rule`, `Domain#is_a_domain?`, `Domain#is_a_subdomain?`, `Domain#valid?`. You can easily obtain the same result by having a custom method that reconstructs the logic, and/or calling `PublicSuffix.{domain|parse}(domain.to_s)`.
+- `PublicSuffix::List.private_domains` is no longer available. Instead, you now have two ways to enable/disable the private domains:
+
+    1. At runtime, by using the `ignore_private` option
+    
+    ```ruby
+    PublicSuffix.domain("something.blogspot.com", ignore_private: true)
+    ```
+
+    1. Loading a filtered list:
+
+    ```ruby
+    # Disable support for private TLDs
+    PublicSuffix::List.default = Public::Suffix.parse(File.read(Public::Suffix::DEFAULT_LIST_PATH), private_domains: false)
+    # => "blogspot.com"
+    PublicSuffix.domain("something.blogspot.com")
+    # => "blogspot.com"
+    ```
+

data/CHANGELOG.md

@@ -1,6 +1,31 @@
 # Changelog
 
 
+#### Release 2.0.0
+
+- NEW: Added PublicSuffix.domain # => sld.tld
+
+- NEW: Added the ability to disable the use of private domains either at runtime, in addition to the ability to not load the private domains section when reading the list (`private_domains: false`). This feature also superseded the `private_domains` class-level attribute, that is no longer available.
+
+- CHANGED: Considerable performance improvements (GH-92)
+
+- CHANGED: Updated definitions.
+
+- CHANGED: Removed deprecated PublicSuffix::InvalidDomain exception
+
+- CHANGED: If the suffix is now listed, then the prevaling rule is "*" as defined by the PSL algorithm (GH-91)
+
+- CHANGED: Input validation is performed only if you call `PublicSuffix.parse` or `PublicSuffix.list`
+
+- CHANGED: Input with leading dot is invalid per PSL acceptance tests
+
+- CHANGED: Removed `private_domains` class-level attribute. It is replaced by the `private_domains: false` option in the list parse method.
+
+- CHANGED: The default list now assumes you use UTF-8 for reading the input (GH-94),
+
+- REMOVED: Removed futile utility helpers such as `Domain#rule`, `Domain#is_a_domain?`, `Domain#is_a_subdomain?`, `Domain#valid?`. You can easily obtain the same result by having a custom method that reconstructs the logic, and/or calling `PublicSuffix.{domain|parse}(domain.to_s)`.
+
+
 #### Release 1.5.3
 
 - FIXED: Don't duplicate rule indices when creating index (GH-77). [Thanks @ags]

data/Gemfile

@@ -2,4 +2,10 @@ source "http://rubygems.org"
 
 gemspec
 
-gem 'minitest'
+gem "rake", "< 11"
+gem "minitest"
+gem "minitest-reporters"
+gem "coveralls", require: false
+gem "rubocop", require: false
+
+gem "memory_profiler", require: false if !RUBY_VERSION.start_with?("2.0")

data/LICENSE.txt

@@ -1,4 +1,4 @@
-Copyright (c) 2009-2015 Simone Carletti <weppos@weppos.net>
+Copyright (c) 2009-2016 Simone Carletti <weppos@weppos.net>
 
 MIT License
 

data/README.md

@@ -1,55 +1,47 @@
-# Public Suffix List
+# Public Suffix <small>Ruby</small>
 
-<tt>PublicSuffix</tt> is a Ruby domain name parser based on the [Public Suffix List](http://publicsuffix.org/).
+<tt>PublicSuffix</tt> is a Ruby domain name parser based on the [Public Suffix List](https://publicsuffix.org/).
 
-[![Build Status](https://secure.travis-ci.org/weppos/publicsuffix-ruby.png)](http://travis-ci.org/weppos/publicsuffix-ruby)
-
-
-## What is the Public Suffix List?
-
-The Public Suffix List is a cross-vendor initiative to provide an accurate list of domain name suffixes.
-
-The Public Suffix List is an initiative of the Mozilla Project, but is maintained as a community resource. It is available for use in any software, but was originally created to meet the needs of browser manufacturers.
-
-A "public suffix" is one under which Internet users can directly register names. Some examples of public suffixes are ".com", ".co.uk" and "pvt.k12.wy.us". The Public Suffix List is a list of all known public suffixes.
-
-Source: http://publicsuffix.org
-
-
-## Why the Public Suffix List is better than any available Regular Expression parser?
-
-Previously, browsers used an algorithm which basically only denied setting wide-ranging cookies for top-level domains with no dots (e.g. com or org). However, this did not work for top-level domains where only third-level registrations are allowed (e.g. co.uk). In these cases, websites could set a cookie for co.uk which will be passed onto every website registered under co.uk.
-
-Clearly, this was a security risk as it allowed websites other than the one setting the cookie to read it, and therefore potentially extract sensitive information.
-
-Since there is no algorithmic method of finding the highest level at which a domain may be registered for a particular top-level domain (the policies differ with each registry), the only method is to create a list of all top-level domains and the level at which domains can be registered. This is the aim of the effective TLD list.
-
-As well as being used to prevent cookies from being set where they shouldn't be, the list can also potentially be used for other applications where the registry controlled and privately controlled parts of a domain name need to be known, for example when grouping by top-level domains.
-
-Source: https://wiki.mozilla.org/Public_Suffix_List
-
-Not convinced yet? Check out [this real world example](http://stackoverflow.com/q/288810/123527).
+[![Build Status](https://travis-ci.org/weppos/publicsuffix-ruby.svg?branch=master)](https://travis-ci.org/weppos/publicsuffix-ruby)
 
 
 ## Requirements
 
 - Ruby >= 2.0
 
-For an older versions of Ruby use a previous release. We also support several [Ruby implementations](http://simonecarletti.com/code/publicsuffix/#implementations).
+For an older versions of Ruby use a previous release.
 
 
 ## Installation
 
-The best way to install *PublicSuffix* is via [RubyGems](https://rubygems.org/).
+You can install the gem manually:
+
+```shell
+$ gem install public_suffix
+```
 
-    $ gem install public_suffix
+Or use Bundler and define it as a dependency in your `Gemfile`:
 
-You might need administrator privileges on your system to install the gem.
+```shell
+$ gem 'public_suffix'
+```
 
+If you are upgrading to 2.0, see [2.0-Upgrade.md](2.0-Upgrade.md).
 
-## Basic Usage
+## Usage
 
-Example domain without subdomains.
+Extract the domain out from a name:
+
+```ruby
+PublicSuffix.domain("google.com")
+# => "google.com"
+PublicSuffix.domain("www.google.com")
+# => "google.com"
+PublicSuffix.domain("www.google.co.uk")
+# => "google.co.uk"
+```
+
+Parse a domain without subdomains:
 
 ```ruby
 domain = PublicSuffix.parse("google.com")
@@ -66,7 +58,7 @@ domain.subdomain
 # => nil
 ```
 
-Example domain with subdomains.
+Parse a domain with subdomains:
 
 ```ruby
 domain = PublicSuffix.parse("www.google.com")
@@ -83,7 +75,7 @@ domain.subdomain
 # => "www.google.com"
 ```
 
-Simple validation example.
+Simple validation example:
 
 ```ruby
 PublicSuffix.valid?("google.com")
@@ -92,7 +84,8 @@ PublicSuffix.valid?("google.com")
 PublicSuffix.valid?("www.google.com")
 # => true
 
-PublicSuffix.valid?("x.yz")
+# Explicitly forbidden, it is listed as a private domain
+PublicSuffix.valid?("blogspot.com")
 # => false
 ```
 
@@ -102,38 +95,72 @@ This library automatically recognizes Fully Qualified Domain Names. A FQDN is a
 
 ```ruby
 # Parse a standard domain name
-domain = PublicSuffix.parse("www.google.com")
-# => #<PublicSuffix::Domain>
-domain.tld
-# => "com"
+PublicSuffix.domain("www.google.com")
+# => "domain.com"
 
 # Parse a fully qualified domain name
-domain = PublicSuffix.parse("www.google.com.")
-# => #<PublicSuffix::Domain>
-domain.tld
-# => "com"
+PublicSuffix.domain("www.google.com.")
+# => "domain.com"
 ```
 
 ## Private domains
 
-This library has support for switching off support for private (non-ICANN) domains
+This library has support for switching off support for private (non-ICANN).
 
 ```ruby
-# Parse a domain on a private TLD
-domain = PublicSuffix.parse("something.blogspot.com")
-# => #<PublicSuffix::Domain>
-domain.tld
+# Extract a domain including private domains (by default)
+PublicSuffix.domain("something.blogspot.com")
+# => "something.blogspot.com"
+
+# Extract a domain excluding private domains
+PublicSuffix.domain("something.blogspot.com", ignore_private: true)
 # => "blogspot.com"
 
+# It also works for #parse and #valid?
+PublicSuffix.parse("something.blogspot.com", ignore_private: true)
+PublicSuffix.valid?("something.blogspot.com", ignore_private: true)
+```
+
+If you don't care about private domains at all, it's more efficient to exclude them when the list is parsed:
+
+```ruby
 # Disable support for private TLDs
-PublicSuffix::List.private_domains = false
-# => #<PublicSuffix::List>
-domain = PublicSuffix.parse("something.blogspot.com")
-# => #<PublicSuffix::Domain>
-domain.tld
-# => "com"
+PublicSuffix::List.default = Public::Suffix.parse(File.read(Public::Suffix::DEFAULT_LIST_PATH), private_domains: false)
+# => "blogspot.com"
+PublicSuffix.domain("something.blogspot.com")
+# => "blogspot.com"
 ```
 
+
+## What is the Public Suffix List?
+
+The [Public Suffix List](https://publicsuffix.org) is a cross-vendor initiative to provide an accurate list of domain name suffixes.
+
+The Public Suffix List is an initiative of the Mozilla Project, but is maintained as a community resource. It is available for use in any software, but was originally created to meet the needs of browser manufacturers.
+
+A "public suffix" is one under which Internet users can directly register names. Some examples of public suffixes are ".com", ".co.uk" and "pvt.k12.wy.us". The Public Suffix List is a list of all known public suffixes.
+
+
+## Why the Public Suffix List is better than any available Regular Expression parser?
+
+Previously, browsers used an algorithm which basically only denied setting wide-ranging cookies for top-level domains with no dots (e.g. com or org). However, this did not work for top-level domains where only third-level registrations are allowed (e.g. co.uk). In these cases, websites could set a cookie for co.uk which will be passed onto every website registered under co.uk.
+
+Clearly, this was a security risk as it allowed websites other than the one setting the cookie to read it, and therefore potentially extract sensitive information.
+
+Since there is no algorithmic method of finding the highest level at which a domain may be registered for a particular top-level domain (the policies differ with each registry), the only method is to create a list of all top-level domains and the level at which domains can be registered. This is the aim of the effective TLD list.
+
+As well as being used to prevent cookies from being set where they shouldn't be, the list can also potentially be used for other applications where the registry controlled and privately controlled parts of a domain name need to be known, for example when grouping by top-level domains.
+
+Source: https://wiki.mozilla.org/Public_Suffix_List
+
+Not convinced yet? Check out [this real world example](https://stackoverflow.com/q/288810/123527).
+
+
+## Does <tt>PublicSuffix</tt> make requests to Public Suffix List website?
+
+No. <tt>PublicSuffix</tt> comes with a bundled list. It does not make any HTTP requests to parse or validate a domain.
+
+
 ## Feedback and bug reports
 
 If you use this library and find yourself missing any functionality, please [let me know](mailto:weppos@weppos.net).
@@ -145,10 +172,10 @@ Report issues or feature requests to [GitHub Issues](https://github.com/weppos/p
 
 ## More
 
-* [Homepage](http://simonecarletti.com/code/publicsuffix)
-* [Repository](https://github.com/weppos/publicsuffix-ruby)
-* [API Documentation](http://rubydoc.info/gems/public_suffix)
-* [Introducing the Public Suffix List library for Ruby](http://simonecarletti.com/blog/2010/06/public-suffix-list-library-for-ruby/)
+- [Homepage](https://simonecarletti.com/code/publicsuffix-ruby)
+- [Repository](https://github.com/weppos/publicsuffix-ruby)
+- [API Documentation](http://rubydoc.info/gems/public_suffix)
+- [Introducing the Public Suffix List library for Ruby](https://simonecarletti.com/blog/2010/06/public-suffix-list-library-for-ruby/)
 
 
 ## Changelog
@@ -158,4 +185,4 @@ See the [CHANGELOG.md](CHANGELOG.md) file for details.
 
 ## License
 
-Copyright (c) 2009-2015 Simone Carletti. This is Free Software distributed under the MIT license.
+Copyright (c) 2009-2016 Simone Carletti. This is Free Software distributed under the MIT license.