metainspector 5.1.3 → 5.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f3d01cdc6e285149cbb1bdb8cf65ebab808da8c1
-  data.tar.gz: 15c37998971b8f63e6829e75049c0f1a819d570d
+  metadata.gz: 4d6981fee7a5b3c01045c6e152d20fb2c788c549
+  data.tar.gz: 4f0ff717747c9b1bdc5abae2eae1696bc4138033
 SHA512:
-  metadata.gz: 24e87ba552861135cd0e5cbf98a4f29fbe4d99b27ba4365aec9f5f5902751bda8b7e299c30a83bea3517b4efc18d8677f2278166d95f4adfff673633cf3a4408
-  data.tar.gz: 7585f94e0ba3639da3c2d0d534803b63929987cc43c466135a68b6c6aa0424131b33954e0e72dbec68240e9a33d369368345ced37b70d6fb74c67ee806823e62
+  metadata.gz: 782597ff87e03b177d73302efb5dcfa0713e7a27367fe93b43579960e89824caa8331a88c95d96410597d03ba0849fa4c4cf3fcf2caeb02d63bf2aa606aa4c08
+  data.tar.gz: 268e91699c34b9649e6441450ccb244fc1b49c6c06a3c1e6787f73fa04332b8172886228ce8a20ad714c727ee45cfa2665308aaa79b33eeef3ded7ac01225722

data/.travis.yml

@@ -2,3 +2,4 @@ rvm:
 - 2.0.0
 - 2.1.8
 - 2.2.4
+- 2.3.0

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 # MetaInpector Changelog
 
+## [Changes in 5.2](https://github.com/jaimeiniesta/metainspector/compare/v5.1.0...v5.2.0)
+
+Removes the deprecated `html_content_only` option, and replaces it by `allow_non_html_content`, by default `false`.
+
 ## [Changes in 5.1](https://github.com/jaimeiniesta/metainspector/compare/v5.0.0...v5.1.0)
 
 Deprecates the `html_content_only` option, and turns it on by default.

data/README.md

@@ -326,24 +326,22 @@ MetaInspector.new('https://example.com', faraday_options: { ssl: { verify: false
 # Now we can access the page
 ```
 
-### HTML Content Only
+### Allow non-HTML content type
 
-MetaInspector will try to parse all URLs by default. By default, it will raise an exception when trying to parse a non-html URL (one that has a content-type different than text/html). You can disable this behaviour with:
+MetaInspector will by default raise an exception when trying to parse a non-HTML URL (one that has a content-type different than text/html). You can disable this behaviour with:
 
 ```ruby
-page = MetaInspector.new('sitevalidator.com', :html_content_only => false)
+page = MetaInspector.new('sitevalidator.com', :allow_non_html_content => true)
 ```
 
-This option is deprecated since 5.1.0 and will be removed in 5.2.0.
-
 ```ruby
 page = MetaInspector.new('http://example.com/image.png')
 page.content_type  # "image/png"
-page.description   # will returned a garbled string
+page.description   # will raise an exception
 
-page = MetaInspector.new('http://example.com/image.png', :html_content_only => true)
+page = MetaInspector.new('http://example.com/image.png', :allow_non_html_content => true)
 page.content_type  # "image/png"
-page.description   # raises an exception
+page.description   # will return a garbled string
 ```
 
 ### URL Normalization
@@ -438,6 +436,7 @@ You can also come to chat with us on our [Gitter room](https://gitter.im/jaimein
 
 * [go-metainspector](https://github.com/fern4lvarez/go-metainspector), a port of MetaInspector for Go.
 * [Node-MetaInspector](https://github.com/gabceb/node-metainspector), a port of MetaInspector for Node.
+* [MetaInvestigator](https://github.com/nekova/metainvestigator), a port of MetaInspector for Elixir.
 
 ## License
 MetaInspector is released under the [MIT license](MIT-LICENSE).

data/lib/meta_inspector/document.rb

@@ -1,7 +1,7 @@
 module MetaInspector
   # A MetaInspector::Document knows about its URL and its contents
   class Document
-    attr_reader :html_content_only, :allow_redirections, :headers
+    attr_reader :allow_non_html_content, :allow_redirections, :headers
 
     # Initializes a new instance of MetaInspector::Document, setting the URL
     # Options:
@@ -14,19 +14,14 @@ module MetaInspector
     # * normalize_url: true by default
     # * faraday_options: an optional hash of options to pass to Faraday on the request
     def initialize(initial_url, options = {})
-      unless options[:html_content_only].nil?
-        puts <<-EOS
-          DEPRECATION NOTICE: html_content_only is deprecated and turned on by default since 5.1.0,
-          this option will be removed in 5.2.0
-        EOS
-      end
       options             = defaults.merge(options)
       @connection_timeout = options[:connection_timeout]
       @read_timeout       = options[:read_timeout]
       @retries            = options[:retries]
-      @html_content_only  = options[:html_content_only]
 
-      @allow_redirections = options[:allow_redirections]
+      @allow_redirections     = options[:allow_redirections]
+      @allow_non_html_content = options[:allow_non_html_content]
+
       @document           = options[:document]
       @download_images    = options[:download_images]
       @headers            = options[:headers]
@@ -86,16 +81,16 @@ module MetaInspector
     private
 
     def defaults
-      { :timeout            => 20,
-        :retries            => 3,
-        :html_content_only  => true,
-        :headers            => {
-                                 'User-Agent'      => default_user_agent,
-                                 'Accept-Encoding' => 'identity'
-                               },
-        :allow_redirections => true,
-        :normalize_url      => true,
-        :download_images    => true }
+      { :timeout                => 20,
+        :retries                => 3,
+        :headers                => {
+                                     'User-Agent'      => default_user_agent,
+                                     'Accept-Encoding' => 'identity'
+                                  },
+        :allow_redirections     => true,
+        :allow_non_html_content => false,
+        :normalize_url          => true,
+        :download_images        => true }
     end
 
     def default_user_agent
@@ -103,7 +98,7 @@ module MetaInspector
     end
 
     def document
-      @document ||= if html_content_only && !content_type.nil? && content_type != 'text/html'
+      @document ||= if !allow_non_html_content && !content_type.nil? && content_type != 'text/html'
         fail MetaInspector::ParserError.new "The url provided contains #{content_type} content instead of text/html content"
       else
         @request.read

data/lib/meta_inspector/version.rb

@@ -1,3 +1,3 @@
 module MetaInspector
-  VERSION = '5.1.3'
+  VERSION = '5.2.0'
 end

data/meta_inspector.gemspec

@@ -21,7 +21,7 @@ Gem::Specification.new do |gem|
   gem.add_dependency 'faraday-http-cache', '~> 1.2'
   gem.add_dependency 'faraday-encoding', '~> 0.0.3'
   gem.add_dependency 'addressable', '~> 2.4'
-  gem.add_dependency 'fastimage', '~> 1.8.1'
+  gem.add_dependency 'fastimage', '~> 2.0'
   gem.add_dependency 'nesty', '~> 1.0'
 
   gem.add_development_dependency 'rspec', '~> 3.0'

data/spec/document_spec.rb

@@ -74,35 +74,26 @@ describe MetaInspector::Document do
                          })
   end
 
-  describe 'exception handling' do
-    it "should not parse images when parse_html_content_type_only is not specified" do
+  describe "allow_non_html_content option" do
+    it "should not allow non-html content type by default" do
       expect do
         image_url = MetaInspector::Document.new('http://pagerankalert.com/image.png')
         image_url.title
       end.to raise_error(MetaInspector::ParserError)
     end
 
-    it "should parse images when parse_html_content_type_only is false" do
+    it "should not allow non-html content type when explicitly disallowed" do
       expect do
-        image_url = MetaInspector::Document.new('http://pagerankalert.com/image.png', html_content_only: false)
-        image_url.title
-      end.to_not raise_error
-    end
-
-    it "should handle errors when content is image/jpeg and html_content_type_only is true" do
-      expect do
-        image_url = MetaInspector::Document.new('http://pagerankalert.com/image.png', html_content_only: true)
-
+        image_url = MetaInspector::Document.new('http://pagerankalert.com/image.png', allow_non_html_content: false)
         image_url.title
       end.to raise_error(MetaInspector::ParserError)
     end
 
-    it "should handle errors when content is not text/html and html_content_type_only is true" do
+    it "should allow non-html content type when explicitly allowed" do
       expect do
-        tar_url = MetaInspector::Document.new('http://pagerankalert.com/file.tar.gz', html_content_only: true)
-
-        tar_url.title
-      end.to raise_error(MetaInspector::ParserError)
+        image_url = MetaInspector::Document.new('http://pagerankalert.com/image.png', allow_non_html_content: true)
+        image_url.title
+      end.to_not raise_error(MetaInspector::ParserError)
     end
   end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: metainspector
 version: !ruby/object:Gem::Version
-  version: 5.1.3
+  version: 5.2.0
 platform: ruby
 authors:
 - Jaime Iniesta
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-04-12 00:00:00.000000000 Z
+date: 2016-04-21 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -114,14 +114,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.8.1
+        version: '2.0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.8.1
+        version: '2.0'
 - !ruby/object:Gem::Dependency
   name: nesty
   requirement: !ruby/object:Gem::Requirement