url_canonicalize 0.1.9 → 0.1.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 1493f185d340eabc6a80605d684beab885d5801f
-  data.tar.gz: fdaf73d4b81441aea7bacb84ce0319fca52f7c68
+  metadata.gz: 68f190eb361435b21097c512aaf3abcbca61e6f6
+  data.tar.gz: e3249038d7bbade9c294a940479a5586b23771ca
 SHA512:
-  metadata.gz: a838ce734c8d63474f7673ada3e027724042ab16651f6608178dafbdff8f695bc979e1177b057f926ad2c7f04de4d0006d803c663f03bfc93945ecc62ecff0d6
-  data.tar.gz: df6a62963d4d43adab2df50bacf771351a9ee4f788a3ff1e0e7f6144aeee945ed21a22368511d141235f49646a44e653faf7bff99e37cc76f78f7b729448b6e1
+  metadata.gz: 9ce00418601cdfcc99841836790d0ac81e4e1e542b811d4e07615674c57687a7f3a8b0c2b1dcfdea1f65596d43674105d2b5dbf40c609a0892e550e764b65d9f
+  data.tar.gz: d76b899fcf9989c6a05a39f4f6a950905f7fb003dc43037c8c0c66809fdf081d73ffdbe3247b76dd37ce0772e582748a3cee6573c506ab91bb6cd324acad720b

data/.codeclimate.yml

@@ -0,0 +1,25 @@
+---
+engines:
+  duplication:
+    enabled: true
+    config:
+      languages:
+      - ruby
+      - javascript
+      - python
+      - php
+  fixme:
+    enabled: true
+  rubocop:
+    enabled: true
+ratings:
+  paths:
+  - "**.inc"
+  - "**.js"
+  - "**.jsx"
+  - "**.module"
+  - "**.php"
+  - "**.py"
+  - "**.rb"
+exclude_paths:
+  - spec/

data/.travis.yml

@@ -0,0 +1,6 @@
+---
+language: ruby
+rvm:
+  - 2.4.0
+script:
+  - rspec

data/README.md

@@ -3,7 +3,7 @@
 [![Gem downloads](https://img.shields.io/gem/dt/url_canonicalize.svg)](https://rubygems.org/gems/url_canonicalize)
 [![Build status](https://img.shields.io/circleci/project/dominicsayers/url_canonicalize/master.svg)](https://circleci.com/gh/dominicsayers/url_canonicalize)
 [![Code quality](http://img.shields.io/codeclimate/github/dominicsayers/url_canonicalize.svg?style=flat)](https://codeclimate.com/github/dominicsayers/url_canonicalize)
-[![Coverage Status](https://coveralls.io/repos/github/Xenapto/url_canonicalize/badge.svg?branch=master)](https://coveralls.io/github/Xenapto/url_canonicalize?branch=master)
+[![Coverage Status](https://coveralls.io/repos/github/dominicsayers/url_canonicalize/badge.svg?branch=master)](https://coveralls.io/github/dominicsayers/url_canonicalize?branch=master)
 [![Dependency Status](https://dependencyci.com/github/dominicsayers/url_canonicalize/badge)](https://dependencyci.com/github/dominicsayers/url_canonicalize)
 [![Security](https://hakiri.io/github/dominicsayers/url_canonicalize/master.svg)](https://hakiri.io/github/dominicsayers/url_canonicalize/master)
 
@@ -23,7 +23,9 @@ gem 'url_canonicalize'
 
 ```ruby
 'http://www.twitter.com'.canonicalize # => 'https://twitter.com/'
+
 URI('http://www.twitter.com').canonicalize # => #<URI::HTTP:0x00000008767908 URL:https://twitter.com/>
+
 Addressable::URI.canonicalize('http://www.twitter.com') # => #<Addressable::URI:0x43c9 URI:https://twitter.com/>
 ```
 

data/lib/url_canonicalize/exception.rb

@@ -3,8 +3,9 @@
 module URLCanonicalize
   # Local exception classes to make handling exceptions easier
   class Exception < RuntimeError
-    URI = Class.new(self)
-    Redirect = Class.new(self)
     Failure = Class.new(self)
+    Redirect = Class.new(self)
+    Request = Class.new(self)
+    URI = Class.new(self)
   end
 end

data/lib/url_canonicalize/http.rb

@@ -15,7 +15,7 @@ module URLCanonicalize
       @uri = nil
     end
 
-    def request(http_request)
+    def do_request(http_request)
       http.request http_request
     end
 
@@ -29,13 +29,26 @@ module URLCanonicalize
 
     # Fetch the response
     def response
-      @response ||= Request.new(self).fetch
+      @response ||= fetch_response
+    end
+
+    def response_url
+      @response_url ||= response.url
+    end
+
+    def request
+      @request ||= Request.new(self)
+    end
+
+    def fetch_response
+      request.with_uri(uri).fetch
     end
 
     # Parse the response, and clear the response ready to follow the next redirect
     def handle_response
       result = parse_response
       @response = nil
+      @response_url = nil
       result
     end
 
@@ -56,12 +69,12 @@ module URLCanonicalize
     end
 
     def redirect_loop_detected?
-      if redirect_list.include?(response.url)
+      if redirect_list.include?(response_url)
         return true if last_known_good
         raise URLCanonicalize::Exception::Redirect, 'Redirect loop detected'
       end
 
-      redirect_list << response.url
+      redirect_list << response_url
       increment_redirects
       set_url_from_response
       false
@@ -87,13 +100,13 @@ module URLCanonicalize
 
     def handle_canonical_found
       self.last_known_good = response.response
-      return true if response.url == url || redirect_list.include?(response.url)
+      return true if response_url == url || redirect_list.include?(response_url)
       set_url_from_response
       false
     end
 
     def set_url_from_response
-      self.url = response.url
+      self.url = response_url
     end
 
     def handle_failure

data/lib/url_canonicalize/request.rb

@@ -6,6 +6,22 @@ module URLCanonicalize
       handle_response
     end
 
+    def location
+      @location ||= relative_to_absolute(response['location'])
+    end
+
+    def with_uri(uri)
+      @uri = uri
+
+      @url = nil
+      @host = nil
+      @response = nil
+      @location = nil
+      @html = nil
+
+      self
+    end
+
     private
 
     attr_reader :http, :http_method
@@ -16,7 +32,12 @@ module URLCanonicalize
     end
 
     def response
-      @response ||= http.request request # Some URLs can throw an exception here
+      @response ||= do_http_request
+    end
+
+    # We can stub this method in testing then call #response any number of times
+    def do_http_request #:nodoc: internal use only
+      http.do_request request # Some URLs can throw an exception here
     end
 
     def request
@@ -51,10 +72,10 @@ module URLCanonicalize
 
     def handle_redirection
       case response
-      when Net::HTTPFound, Net::HTTPMovedTemporarily, Net::HTTPTemporaryRedirect
+      when Net::HTTPFound, Net::HTTPMovedTemporarily, Net::HTTPTemporaryRedirect # Temporary redirection
         self.http_method = :get
         handle_success
-      else
+      else # Permanent redirection
         if location
           URLCanonicalize::Response::Redirect.new(location)
         else
@@ -105,10 +126,6 @@ module URLCanonicalize
       @host ||= uri.host
     end
 
-    def location
-      @location ||= relative_to_absolute(response['location'])
-    end
-
     def request_for_method
       r = base_request
       headers.each { |header_key, header_value| r[header_key] = header_value }
@@ -124,7 +141,7 @@ module URLCanonicalize
       when :get
         Net::HTTP::Get.new uri
       else
-        raise URLCanonicalize::Exception::Request, "Unknown method: #{method}"
+        raise URLCanonicalize::Exception::Request, "Unknown method: #{http_method}"
       end
     end
 
@@ -141,6 +158,7 @@ module URLCanonicalize
       @http_method = value
       @request = nil
       @response = nil
+      @location = nil
       @html = nil
     end
 

data/lib/url_canonicalize/uri.rb

@@ -4,8 +4,9 @@ module URLCanonicalize
   class URI
     class << self
       def parse(url)
-        uri = ::URI.parse(url)
-        uri if valid?(uri)
+        # uri = ::URI.parse decorate(url)
+        uri = ::URI.parse url
+        uri if valid? uri
       rescue ::URI::InvalidURIError => e
         new_exception = URLCanonicalize::Exception::URI.new("#{e.class}: #{e.message}")
         new_exception.set_backtrace e.backtrace
@@ -20,7 +21,13 @@ module URLCanonicalize
         true
       end
 
+      def decorate(url)
+        return url if url.include? COLON
+        "http://#{url}" # Add protocol if we just receive a host name
+      end
+
       VALID_CLASSES = [::URI::HTTP, ::URI::HTTPS].freeze
+      COLON = ':'
     end
   end
 end

data/lib/url_canonicalize/version.rb

@@ -1,4 +1,4 @@
 # frozen_string_literal: true
 module URLCanonicalize
-  VERSION = '0.1.9'
+  VERSION = '0.1.10'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: url_canonicalize
 version: !ruby/object:Gem::Version
-  version: 0.1.9
+  version: 0.1.10
 platform: ruby
 authors:
 - Dominic Sayers
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-03-06 00:00:00.000000000 Z
+date: 2017-03-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: addressable
@@ -46,11 +46,13 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".codeclimate.yml"
 - ".gitignore"
 - ".hound.yml"
 - ".rspec"
 - ".rubocop.yml"
 - ".ruby-gemset"
+- ".travis.yml"
 - Gemfile
 - Gemfile.local.example
 - Guardfile