seo_report 0.1.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 0a0fa771b74ecf5037cc397b72df2e54bc651566
-  data.tar.gz: 3819ea29b3f5d13986927d1a33e57fcb95967b28
+  metadata.gz: c93527848fb421a0afa93d0a2776433d5fac964d
+  data.tar.gz: 1eb31dc4447df2f7502f57208999ec0bc408c759
 SHA512:
-  metadata.gz: d8b6a81345d083b7aaacc45986b0568644ae7f0f079ae4a4f6d73c68b576bf6fd5dd5fe1beafae2a8d006dc7b5f9b00fc330011aec169abec90cc45ffef4a393
-  data.tar.gz: cd899d9827fc44b60836846406bebf1a93e7e9431fad5d2e31b275a5315a2efe491d6012246ba0cf93e799e21b8dbbc138bd4d6ced69f933c65092d76b52b2e1
+  metadata.gz: 0813918a25958b5d67c16cd0ffef4b3274bfcf9f6ad61e97ac520a96aedb6b322be2fdcfcc51b4c2cc0e277867c43f1ea7f4a51a5865d3ac89a5b4cd88d4edec
+  data.tar.gz: e7240e062955eeb06985cf93bca25c9c87e30805eae910ba358ff3c403ed457f3303e17d01e0bd865d4f9b392fc0602cba59fe6620a5dbb94bab071f00c94709

data/CHANGELOG.md

@@ -0,0 +1,46 @@
+# Change Log
+
+This change log contains information about the changes introduced as part of
+specific releases. It adheres to the guidelines outlined by
+[keepachangelog](http://keepachangelog.com/en/0.3.0/).
+
+## [unreleased]
+
+## [0.1.3] — 2016-08-14
+### Added
+- Provide error message, without internal stacktrace information when the
+  command fails for unrecoverable reasons. Also introduces the
+  `SEO_REPORT_DEBUG` environment variable in order to show the stacktrace if
+  failure occurs, for... well debugging.
+- Add error-integration to json/internal-struct for microdata. This allows the
+  recognition and handling of errors regarding microdata in the document.
+- Specify minimum required ruby-version of **2.0.0**. It wouldn't really have
+  worked with anything less than /1.9.3/ before, but specifying it exactly makes
+  it easier to test for and to adhere to.
+- The starts of a real test-suite. Currrently there are only specs for the main
+  extractions, meaning SEO (canonical and robots meta) and HEAD (title and meta
+  description). But the start has been made and the test suite will grow over
+  the next releases up to 0.2.0, at which point there should be at least an 85%
+  coverage.
+### Fixed
+- Don't fail as easily when parsing microdata information. Seeing as this a
+  reporting-tool, that should also display information whether something is
+  valid (or *ok*) or not, we need to handle most errors in the html-document
+  gracefully in order to live to report about it.
+
+## [0.1.2] — 2016-08-10
+### Added
+- Always send an appropriate User-Agent: `seo-report/0.1.2 Net::HTTP`.
+  `Net::HTTP` is used as the underlying library to perform http-requests, which
+  is why it is listed. However the actual user-agent is seo-report itself. The
+  number specifies the version of seo-report that was used to perform the
+  request.
+  
+### Changed
+- Handle path-only redirects and mark them as warnings.
+  While they are supported they don't represent a full URL, which
+  is what is supposed to be present in the `LOCATION` header.
+
+## [0.1.1] — 2016-08-07
+This marks the first release of the seo_report gem, which provides the
+`seo-report` binary. This software is licensed under LGPL-3.0.

data/README.md

@@ -44,6 +44,13 @@ Or install it yourself as:
   example [jq](https://stedolan.github.io/jq/)). Be aware that the json
   format is currently not set in stone. It is most likely to change until
   at least version *0.2.0* is reached.
+  
+### environment variables
+
+Usually `seo-report` will in the case of an unrecoverable error, just provide
+a message and bug out. If you are a developer, or want to file an issue, you
+can run the command with `SEO_REPORT_DEBUG=1` set, which will provide
+backtrace information instead.
 
 ## development
 

data/lib/seo_report/extractions/head.rb

@@ -5,6 +5,7 @@ module SeoReport
         title = doc.xpath('//head/title').text
         description = doc.xpath('//head/meta[@name="description"]').
                       map { |node| node.attr("content") }
+        title = nil if title.empty?
         {
           title: title,
           description: unarray(description),

data/lib/seo_report/extractions/microdata.rb

@@ -12,10 +12,22 @@ module SeoReport::Extractions
       end
 
       def extract!
-        document.at_xpath('/html/body').children.each do |child|
-          process(child)
+        elements.each { |child| process(child) }
+        {
+          microdata: {
+            elements: result_set,
+            errors: errors,
+          }
+        }
+      end
+
+      def elements
+        body = document.at_xpath('/html/body')
+        if body
+          body.children
+        else
+          []
         end
-        {microdata: result_set}
       end
 
       protected
@@ -50,21 +62,18 @@ module SeoReport::Extractions
       end
 
       def provide_data_for_itemprop(element)
-        data =
-          if element.name == "meta"
-            element["content"]
-          elsif %w(audio embed iframe img source track video).include?(element.name)
-            element["src"]
-          elsif %w(a area link).include?(element.name)
-            element["href"]
-          elsif element.name == "object"
-            element["data"]
-          elsif %w(data meter).include?(element.name)
-            element["value"]
-          else
-            element.text
-          end
-        current_scope[element["itemprop"]] = data
+        data = microdata_itemprop_value(element)
+        if current_scope
+          current_scope[element["itemprop"]] = data
+        else
+          error = {
+            tag: element.name,
+            itemprop: element["itemprop"],
+            value: data,
+          }
+          error.merge!(id: element["id"]) if element["id"]
+          (errors[:scopeless_elements] ||= []) << error
+        end
       end
 
       def push_scope(element)
@@ -93,6 +102,10 @@ module SeoReport::Extractions
         @result_set ||= []
       end
 
+      def errors
+        @errors ||= {}
+      end
+
       def microdata_element?(element)
         %w(itemscope itemtype itemprop).
           any? { |attr| element.has_attribute?(attr) }
@@ -105,6 +118,22 @@ module SeoReport::Extractions
       def microdata_prop?(element)
         element.has_attribute?("itemprop")
       end
+
+      def microdata_itemprop_value(element)
+        if element.name == "meta"
+          element["content"]
+        elsif %w(audio embed iframe img source track video).include?(element.name)
+          element["src"]
+        elsif %w(a area link).include?(element.name)
+          element["href"]
+        elsif element.name == "object"
+          element["data"]
+        elsif %w(data meter).include?(element.name)
+          element["value"]
+        else
+          element.text
+        end
+      end
     end
 
     SeoReport::Report.register_extraction(:html, Microdata, :extract_microdata)

data/lib/seo_report/report.rb

@@ -11,7 +11,7 @@ module SeoReport
     end
 
     def self.extractions
-      @extractions ||= Hash.new([])
+      @extractions ||= {}
     end
 
     def initialize(start_url)
@@ -24,10 +24,8 @@ module SeoReport
 
     protected
     def generate_report
-      chain = RequestChain.new(start_url)
-      chain.perform
       {
-        requests: chain.request_chain.map do |request|
+        requests: request_chain.request_chain.map do |request|
           {
             request_url: request.url.to_s,
             response_code: request.response.code.to_i
@@ -36,6 +34,14 @@ module SeoReport
       }
     end
 
+    def request_chain
+      @request_chain ||= build_request_chain
+    end
+
+    def build_request_chain
+      RequestChain.new(start_url).tap(&:perform)
+    end
+
     def generate_html_report(request)
       if request.response.is_a?(Net::HTTPOK)
         doc = Nokogiri::HTML(request.response.body)
@@ -50,7 +56,7 @@ module SeoReport
     end
 
     def content_through_extractions(base, document, type: :html)
-      self.class.extractions[type].reduce(base) do |current, method_name|
+      self.class.extractions.fetch(type, []).reduce(base) do |current, method_name|
         current.merge(send(method_name, document))
       end
     end

data/lib/seo_report/representation/base.rb

@@ -11,6 +11,13 @@ module SeoReport::Representation
       report = SeoReport::Report.new(url)
       report.produce
       new(report).represent
+    rescue StandardError => _error
+      debug = ENV["SEO_REPORT_DEBUG"]
+      if debug.to_i > 0
+        raise
+      else
+        abort("-- Sorry, something went wrong when creating the report.")
+      end
     end
 
     def initialize(report)

data/lib/seo_report/version.rb

@@ -1,3 +1,3 @@
 module SeoReport
-  VERSION = "0.1.2"
+  VERSION = "0.1.3"
 end

data/seo_report.gemspec

@@ -19,11 +19,14 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
+  spec.required_ruby_version = '>= 2.0.0'
+
   spec.add_dependency "nokogiri", "~> 1.6", ">= 1.6.8"
   spec.add_dependency "json", "~> 2.0", ">= 2.0.1"
 
   spec.add_development_dependency "bundler", "~> 1.10"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "rspec", "~> 3.5"
+  spec.add_development_dependency "webmock", "~> 2.1"
   spec.add_development_dependency "pry", "~> 0.10"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: seo_report
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - Tim Reddehase
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-08-10 00:00:00.000000000 Z
+date: 2016-08-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -92,6 +92,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3.5'
+- !ruby/object:Gem::Dependency
+  name: webmock
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
 - !ruby/object:Gem::Dependency
   name: pry
   requirement: !ruby/object:Gem::Requirement
@@ -118,6 +132,7 @@ files:
 - ".gitignore"
 - ".rspec"
 - ".travis.yml"
+- CHANGELOG.md
 - Gemfile
 - LICENSE
 - README.md
@@ -153,7 +168,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 2.0.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="