url_canonicalize 0.0.3 → 0.0.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5af7a447bc416a72583d21996065ce48fc29a0fd
-  data.tar.gz: 856b26e146eec5c85784908af73ff28a28977a6e
+  metadata.gz: 009ed3bccd9e756ada7d68450e7b78fa3e0a673d
+  data.tar.gz: 33ff979501b4e5583a6a782e926f46776ea1a3e3
 SHA512:
-  metadata.gz: 671fed9e62a503c7ba6797f8c501af6cb920c19145ec50690abbe1571a682467b914cb918210e960e91ce56b07e903bf15e17a77727b37f17030b6506b748b1d
-  data.tar.gz: 5714152d98bc8d7b21002c146fe9acabb2c549b72e49a093655b27b0997bc707e82e2a27e56f28cf4e65adafdd761f9d37ad7c6c284eada2864757aa0a012139
+  metadata.gz: a9d793abae4f70a91ff1f5fec5c79968078b0483e0045048a82fe5b1e2caac3962b7ea6c842d9daec5d59188ec2ded912160a518a2d0e3adc2d60070ca53e091
+  data.tar.gz: 928c6b774474831d33df54f4d214651e3fe7f65a93984d7dc1363ae274e888894f0a1d8dab6da51783e548a7bf3adf6bac9a6768ebeda184cb17306928d3f356

data/.gitignore

@@ -1,3 +1,4 @@
+Gemfile.lock
 *.local
 *.gem
 *.rbc

data/lib/url_canonicalize.rb

@@ -16,7 +16,7 @@ module URLCanonicalize
 
   class << self
     def canonicalize(url)
-      fetch(url).uri.to_s
+      fetch(url).url
     end
 
     def fetch(url)

data/lib/url_canonicalize/http.rb

@@ -14,8 +14,8 @@ module URLCanonicalize
       @uri = nil
     end
 
-    def request(request_object)
-      http.request request_object
+    def request(http_request)
+      http.request http_request
     end
 
     private
@@ -41,7 +41,7 @@ module URLCanonicalize
     # Parse the response
     def parse_response
       case response
-      when Net::HTTPSuccess
+      when URLCanonicalize::Response::Success
         handle_success
       when URLCanonicalize::Response::Redirect
         redirect_loop_detected? || max_redirects_reached?

data/lib/url_canonicalize/request.rb

@@ -25,7 +25,7 @@ module URLCanonicalize
     def handle_response
       case response
       when Net::HTTPSuccess
-        look_for_canonical
+        handle_success
       when Net::HTTPRedirection
         handle_redirection
       else
@@ -35,15 +35,14 @@ module URLCanonicalize
       handle_failure(e.class, e.message)
     end
 
-    def look_for_canonical
-      # Look in response Link header
-      if response['link'] =~ /<(?<url>.+)>\s*;\s*rel="canonical"/i
-        URLCanonicalize::Response::CanonicalFound.new($LAST_MATCH_INFO['url'])
-      elsif http_method == :head
+    def handle_success
+      @canonical_url = $LAST_MATCH_INFO['url'] if response['link'] =~ /<(?<url>.+)>\s*;\s*rel="canonical"/i
+
+      if http_method == :head
         self.http_method = :get
         fetch
       else
-        canonical_url ? URLCanonicalize::Response::CanonicalFound.new(canonical_url, response) : response
+        enhanced_response
       end
     end
 
@@ -61,6 +60,15 @@ module URLCanonicalize
       URLCanonicalize::Response::Failure.new(klass, message)
     end
 
+    def enhanced_response
+      if canonical_url
+        response_plus = URLCanonicalize::Response::Success.new(canonical_url, response, html)
+        URLCanonicalize::Response::CanonicalFound.new(canonical_url, response_plus)
+      else
+        URLCanonicalize::Response::Success.new(url, response, html)
+      end
+    end
+
     def html
       @html ||= Nokogiri::HTML response.body
     end
@@ -117,6 +125,7 @@ module URLCanonicalize
       @http_method = value
       @request = nil
       @response = nil
+      @html = nil
     end
 
     # Some sites treat HEAD requests as suspicious activity and block the

data/lib/url_canonicalize/response.rb

@@ -13,14 +13,28 @@ module URLCanonicalize
 
     Redirect = Class.new(Generic)
 
+    # Add HTML to a successful response
+    class Success < Generic
+      attr_reader :response, :html
+
+      private
+
+      def initialize(url, response, html)
+        @response = response
+        @html = html
+        super url
+      end
+    end
+
+    # We found a canonical URL!
     class CanonicalFound < Generic
       attr_reader :response
 
       private
 
       def initialize(url, response)
-        @url = url
         @response = response
+        super url
       end
     end
 

data/lib/url_canonicalize/version.rb

@@ -1,3 +1,3 @@
 module URLCanonicalize
-  VERSION = '0.0.3'.freeze
+  VERSION = '0.0.4'.freeze
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: url_canonicalize
 version: !ruby/object:Gem::Version
-  version: 0.0.3
+  version: 0.0.4
 platform: ruby
 authors:
 - Dominic Sayers
@@ -54,7 +54,6 @@ files:
 - ".ruby-version"
 - Gemfile
 - Gemfile.local.example
-- Gemfile.lock
 - Guardfile
 - LICENSE
 - README.md

data/Gemfile.lock

@@ -1,131 +0,0 @@
-PATH
-  remote: .
-  specs:
-    url_canonicalize (0.0.2)
-      addressable (~> 2)
-      nokogiri (~> 1)
-
-GEM
-  remote: https://rubygems.org/
-  specs:
-    addressable (2.4.0)
-    ast (2.3.0)
-    builder (3.2.2)
-    coderay (1.1.1)
-    coveralls (0.8.15)
-      json (>= 1.8, < 3)
-      simplecov (~> 0.12.0)
-      term-ansicolor (~> 1.3)
-      thor (~> 0.19.1)
-      tins (>= 1.6.0, < 2)
-    crack (0.4.3)
-      safe_yaml (~> 1.0.0)
-    diff-lcs (1.2.5)
-    docile (1.1.5)
-    ffi (1.9.14)
-    formatador (0.2.5)
-    gem-release (0.7.4)
-    guard (2.14.0)
-      formatador (>= 0.2.4)
-      listen (>= 2.7, < 4.0)
-      lumberjack (~> 1.0)
-      nenv (~> 0.1)
-      notiffany (~> 0.0)
-      pry (>= 0.9.12)
-      shellany (~> 0.0)
-      thor (>= 0.18.1)
-    guard-compat (1.2.1)
-    guard-rspec (4.7.3)
-      guard (~> 2.1)
-      guard-compat (~> 1.1)
-      rspec (>= 2.99.0, < 4.0)
-    guard-rubocop (1.2.0)
-      guard (~> 2.0)
-      rubocop (~> 0.20)
-    hashdiff (0.3.0)
-    json (2.0.2)
-    listen (3.0.8)
-      rb-fsevent (~> 0.9, >= 0.9.4)
-      rb-inotify (~> 0.9, >= 0.9.7)
-    lumberjack (1.0.10)
-    method_source (0.8.2)
-    mini_portile2 (2.1.0)
-    nenv (0.3.0)
-    nokogiri (1.6.8.1)
-      mini_portile2 (~> 2.1.0)
-    notiffany (0.1.1)
-      nenv (~> 0.1)
-      shellany (~> 0.0)
-    parser (2.3.1.4)
-      ast (~> 2.2)
-    powerpack (0.1.1)
-    pry (0.10.4)
-      coderay (~> 1.1.0)
-      method_source (~> 0.8.1)
-      slop (~> 3.4)
-    rainbow (2.1.0)
-    rake (11.3.0)
-    rb-fsevent (0.9.7)
-    rb-inotify (0.9.7)
-      ffi (>= 0.5.0)
-    rspec (3.5.0)
-      rspec-core (~> 3.5.0)
-      rspec-expectations (~> 3.5.0)
-      rspec-mocks (~> 3.5.0)
-    rspec-core (3.5.4)
-      rspec-support (~> 3.5.0)
-    rspec-expectations (3.5.0)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.5.0)
-    rspec-mocks (3.5.0)
-      diff-lcs (>= 1.2.0, < 2.0)
-      rspec-support (~> 3.5.0)
-    rspec-support (3.5.0)
-    rspec_junit_formatter (0.2.3)
-      builder (< 4)
-      rspec-core (>= 2, < 4, != 2.12.0)
-    rubocop (0.44.1)
-      parser (>= 2.3.1.1, < 3.0)
-      powerpack (~> 0.1)
-      rainbow (>= 1.99.1, < 3.0)
-      ruby-progressbar (~> 1.7)
-      unicode-display_width (~> 1.0, >= 1.0.1)
-    ruby-progressbar (1.8.1)
-    safe_yaml (1.0.4)
-    shellany (0.0.1)
-    simplecov (0.12.0)
-      docile (~> 1.1.0)
-      json (>= 1.8, < 3)
-      simplecov-html (~> 0.10.0)
-    simplecov-html (0.10.0)
-    slop (3.6.0)
-    term-ansicolor (1.4.0)
-      tins (~> 1.0)
-    thor (0.19.1)
-    tins (1.12.0)
-    unicode-display_width (1.1.1)
-    webmock (2.1.0)
-      addressable (>= 2.3.6)
-      crack (>= 0.3.2)
-      hashdiff
-
-PLATFORMS
-  ruby
-
-DEPENDENCIES
-  coveralls
-  gem-release
-  guard
-  guard-rspec
-  guard-rubocop
-  listen (~> 3.0, < 3.1)
-  rake
-  rspec
-  rspec_junit_formatter
-  rubocop
-  simplecov
-  url_canonicalize!
-  webmock
-
-BUNDLED WITH
-   1.13.5