twingly-url 5.1.0 → 6.0.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: f0bb0970331402234b1d3670fc4e59cdba2ea452
-  data.tar.gz: f5287068f3f37c04f8df13c18b9c93afb51ca81c
+SHA256:
+  metadata.gz: e39c685acc5000907b03195ce1c08a1a3628263aa64860257f88cde5c44be042
+  data.tar.gz: 6f4573e38a72d7943e872fb4a7714619e08f624eedaa73f6a51e432d3ddecfbe
 SHA512:
-  metadata.gz: 7819736f7aea13732739ea633844c8929dc4e1efdb59125e96a06de8563510caee46140c90f8b40fa88092dbcda836681a16934f682e12d87a3c139d7ace7d58
-  data.tar.gz: c190ec9d959568e829ccd7a62a34607c90317b772e0c8aebd98d2ed4b4e5b2881a214a601f0b242af01ec89c63d136a1bf457eb0747f1092234acf5328d1ea08
+  metadata.gz: ab988985a16a53990d91be9c81c440a8baf878181ff2149cecc72eb1d52b753efa1edef701d1578d87b1bc26a0ea5700bd56e4735a5393f446d37fb4c393436e
+  data.tar.gz: 64947df33fd987b6e446037fdf841a885ac9d8292cea92ca9dfb71b3f518d107d7dcead1344b49fd53a81dcec62abc2355ea76c6ed28a625a97ab2408267528f

data/README.md

@@ -11,7 +11,6 @@ Twingly URL tools.
     * `Twingly::URL::Hasher.blogstream_hash(url)` - MD5 hexdigest
     * `Twingly::URL::Hasher.documentdb_hash(url)` - SHA256 unsigned long, native endian digest
     * `Twingly::URL::Hasher.autopingdb_hash(url)` - SHA256 64-bit signed, native endian digest
-    * `Twingly::URL::Hasher.pingloggerdb_hash(url)` - SHA256 64-bit unsigned, native endian digest
 * `twingly/url/utilities` - Utilities to work with URLs
     * `Twingly::URL::Utilities.extract_valid_urls` - Returns Array of valid `Twingly::URL`
 
@@ -175,13 +174,13 @@ Run tests with
 
 ### Profiling
 
-You can get some profiling by running
+There's some profiling tasks available through Rake
 
     cd profile/
-    bundle
-    bundle exec rake
+    bundle # Install dependencies
+    bundle exec rake -T # Show available tasks
 
-Note that this isn't a benchmark, we're using [ruby-prof] which will slow things down.
+Note that this isn't a benchmark, we're using [ruby-prof] and [memory_profiler] which will slow things down.
 
 ## Release workflow
 
@@ -191,16 +190,17 @@ Note that this isn't a benchmark, we're using [ruby-prof] which will slow things
 
 * Bump the version in `lib/twingly/version.rb` in a commit, no need to push (the release task does that).
 
+* Ensure you are signed in to RubyGems.org as [twingly][twingly-rubygems] with `gem signin`.
+
 * Build and [publish](http://guides.rubygems.org/publishing/) the gem. This will create the proper tag in git, push the commit and tag and upload to RubyGems.
 
         bundle exec rake release
 
-    * If you are not logged in as [twingly][twingly-rubygems] with ruby gems, the rake task will fail and tell you to set credentials via `gem push`, do that and run the `release` task again. It will be okay.
-
-* Update the changelog with [GitHub Changelog Generator](https://github.com/skywinder/github-changelog-generator/) (`gem install github_changelog_generator` if you don't have it, set `CHANGELOG_GITHUB_TOKEN` to a personal access token to avoid rate limiting by GitHub). This command will update `CHANGELOG.md`, commit and push manually.
+* Update the changelog with [GitHub Changelog Generator](https://github.com/skywinder/github-changelog-generator/) (`gem install github_changelog_generator` if you don't have it, set `CHANGELOG_GITHUB_TOKEN` to a personal access token to avoid rate limiting by GitHub). This command will update `CHANGELOG.md`. You need to commit and push manually.
 
         github_changelog_generator
 
 [twingly-rubygems]: https://rubygems.org/profiles/twingly
 [ruby-prof]: http://ruby-prof.rubyforge.org/
+[memory_profiler]: https://github.com/SamSaffron/memory_profiler
 [examples]: examples/url.rb

data/lib/twingly/public_suffix_list.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require "addressable/idna"
 require "public_suffix"
 
@@ -15,17 +17,15 @@ module Twingly
 
       punycoded_names(list).each do |punycoded_name|
         new_rule = PublicSuffix::Rule.factory(punycoded_name)
-        list.add(new_rule, reindex: false)
+        list.add(new_rule)
       end
 
-      list.reindex!
-
       list
     end
 
     private_class_method \
     def self.punycoded_names(list)
-      names = list.map { |rule| Addressable::IDNA.to_ascii(rule.value) }
+      names = list.each.map { |rule| Addressable::IDNA.to_ascii(rule.value) }
       names.select { |name| punycoded_name?(name) }
     end
 

data/lib/twingly/url.rb

@@ -1,37 +1,63 @@
+# frozen_string_literal: true
+
+require "addressable/idna/pure"
 require "addressable/uri"
 require "public_suffix"
 
-require_relative "public_suffix_list"
-require_relative "url/null_url"
-require_relative "url/error"
-require_relative "version"
+require "twingly/public_suffix_list"
+require "twingly/url/null_url"
+require "twingly/url/error"
+require "twingly/version"
 
 module Twingly
   class URL
     include Comparable
 
-    ACCEPTED_SCHEMES = /\Ahttps?\z/i
+    ACCEPTED_SCHEMES = /\Ahttps?\z/i.freeze
     CUSTOM_PSL = PublicSuffixList.with_punycoded_names
-    ENDS_WITH_SLASH = /\/+$/
+    ENDS_WITH_SLASH = /\/+$/.freeze
+    STARTS_WITH_WWW = /\Awww\./i.freeze
     ERRORS_TO_EXTEND = [
+      Addressable::IDNA::PunycodeBigOutput,
       Addressable::URI::InvalidURIError,
       PublicSuffix::DomainInvalid,
-    ]
+    ].freeze
+    CARRIAGE_RETURN = "\u000D"
+    LINE_FEED = "\u000A"
+    NBSP = "\u00A0"
+    SPACE = "\u0020"
+    WHITESPACE_CHARS = [
+      CARRIAGE_RETURN,
+      LINE_FEED,
+      NBSP,
+      SPACE,
+    ].join.freeze
+    LEADING_AND_TRAILING_WHITESPACE =
+      /\A[#{WHITESPACE_CHARS}]+|[#{WHITESPACE_CHARS}]+\z/.freeze
 
     private_constant :ACCEPTED_SCHEMES
     private_constant :CUSTOM_PSL
+    private_constant :STARTS_WITH_WWW
     private_constant :ENDS_WITH_SLASH
     private_constant :ERRORS_TO_EXTEND
+    private_constant :NBSP
+    private_constant :SPACE
+    private_constant :WHITESPACE_CHARS
+    private_constant :LEADING_AND_TRAILING_WHITESPACE
 
     class << self
       def parse(potential_url)
         internal_parse(potential_url)
       rescue Twingly::URL::Error, Twingly::URL::Error::ParseError => error
         NullURL.new
+      rescue Exception => error
+        error.extend(Twingly::URL::Error)
+        raise
       end
 
-      def internal_parse(potential_url)
-        addressable_uri = to_addressable_uri(potential_url)
+      def internal_parse(input)
+        potential_url   = clean_input(input)
+        addressable_uri = Addressable::URI.heuristic_parse(potential_url)
         raise Twingly::URL::Error::ParseError if addressable_uri.nil?
 
         scheme = addressable_uri.scheme
@@ -53,15 +79,16 @@ module Twingly
         raise
       end
 
-      def to_addressable_uri(potential_url)
-       if potential_url.is_a?(Addressable::URI)
-          potential_url
-        else
-          potential_url = String(potential_url)
-          potential_url = potential_url.scrub
+      def clean_input(input)
+        input = String(input)
+        input = input.scrub
+        input = strip_whitespace(input)
+      end
 
-          Addressable::URI.heuristic_parse(potential_url)
-        end
+      def strip_whitespace(input)
+        return input unless input.encoding == Encoding::UTF_8
+
+        input.gsub(LEADING_AND_TRAILING_WHITESPACE, "")
       end
 
       # Workaround for the following bug in addressable:
@@ -78,7 +105,8 @@ module Twingly
 
       private :new
       private :internal_parse
-      private :to_addressable_uri
+      private :clean_input
+      private :strip_whitespace
       private :try_addressable_normalize
     end
 
@@ -184,6 +212,16 @@ module Twingly
       self.to_s <=> other.to_s
     end
 
+    def eql?(other)
+      return false unless other.is_a?(self.class)
+
+      self.hash == other.hash
+    end
+
+    def hash
+      self.to_s.hash
+    end
+
     def to_s
       addressable_uri.to_s
     end
@@ -198,7 +236,7 @@ module Twingly
 
     def normalize_blogspot(host, domain)
       if domain.sld.downcase == "blogspot"
-        host.sub(/\Awww\./i, "").sub(/#{domain.tld}\z/i, "com")
+        host.sub(STARTS_WITH_WWW, "").sub(/#{domain.tld}\z/i, "com")
       else
         host
       end

data/lib/twingly/url/error.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 module Twingly
   class URL
     module Error

data/lib/twingly/url/hasher.rb

@@ -1,6 +1,8 @@
+# frozen_string_literal: true
+
 require 'digest'
 
-require_relative "../url"
+require "twingly/url"
 
 module Twingly
   class URL
@@ -28,10 +30,6 @@ module Twingly
       def autopingdb_hash(url)
         SHA256_DIGEST.digest(url).unpack("q")[0]
       end
-
-      def pingloggerdb_hash(url)
-        SHA256_DIGEST.digest(url).unpack("Q")[0]
-      end
     end
   end
 end

data/lib/twingly/url/null_url.rb

@@ -1,4 +1,4 @@
-require_relative "../url"
+# frozen_string_literal: true
 
 module Twingly
   class URL
@@ -24,6 +24,16 @@ module Twingly
         self.to_s <=> other.to_s
       end
 
+      def eql?(other)
+        return false unless other.is_a?(self.class)
+
+        self.hash == other.hash
+      end
+
+      def hash
+        self.to_s.hash
+      end
+
       def to_s
         ""
       end

data/lib/twingly/url/utilities.rb

@@ -1,4 +1,6 @@
-require_relative "../url"
+# frozen_string_literal: true
+
+require "twingly/url"
 
 module Twingly
   class URL

data/lib/twingly/version.rb

@@ -1,5 +1,7 @@
+# frozen_string_literal: true
+
 module Twingly
   class URL
-    VERSION = "5.1.0"
+    VERSION = "6.0.3"
   end
 end

metadata

@@ -1,57 +1,63 @@
 --- !ruby/object:Gem::Specification
 name: twingly-url
 version: !ruby/object:Gem::Version
-  version: 5.1.0
+  version: 6.0.3
 platform: ruby
 authors:
 - Twingly AB
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2017-03-03 00:00:00.000000000 Z
+date: 2020-09-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.5.0
+        version: '2.6'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 2.5.0
+        version: '2.6'
 - !ruby/object:Gem::Dependency
   name: public_suffix
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
       - !ruby/object:Gem::Version
-        version: 2.0.3
+        version: 3.0.1
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '5.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 3.0.1
+    - - "<"
       - !ruby/object:Gem::Version
-        version: 2.0.3
+        version: '5.0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10'
+        version: '12'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10'
+        version: '12'
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
@@ -99,7 +105,7 @@ homepage: http://github.com/twingly/twingly-url
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -107,16 +113,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - "~>"
     - !ruby/object:Gem::Version
-      version: '2.2'
+      version: '2.5'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.4.5.1
-signing_key: 
+rubygems_version: 3.1.2
+signing_key:
 specification_version: 4
 summary: Ruby library for URL handling
 test_files: []