sitemap_check 0.1.9 → 0.1.10

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 07fb389a6948c70ac99957f07ff3d282bebe3f5b
-  data.tar.gz: 16adc730dd074592d72653e1279329331e4e8206
+  metadata.gz: 301e1ef8730ab4b8171e6720d17642e84a940ea2
+  data.tar.gz: bd043c3da703584c5cff25e8853d63b8c93f0035
 SHA512:
-  metadata.gz: 9c5ace737441c9d359cd8ae81d639afa65063090040a7d10812244a3001634fa501f34bcf2b6c6fcfecabbf70ade628d237515f20970a7cadbd8f6a80dfad53f
-  data.tar.gz: 8782ada9abd33b3c8a69254ae24a4c7d19a51a99425d52b724120ec748fd88cb07504c55b6adf0ddfdaf8bec9b2b6fcd4e91b1bcf85e70271cb8c2ab386ef5de
+  metadata.gz: 193b088cff5eaefbc56806c7204428fb3426821bea58b76437fdd57da59e950da5d07a2939aff472f26f7402cf4448c7c3e4ad8a1f61e9da5202c193ced47cbb
+  data.tar.gz: d108143a6fd8552d52ec9c8a8c6dbcbfb55b11afd6036685742c60ed8f6d55d3e00443541c5651f01ba29ad901bf97e665e1456d443f8b5f0e66485a2f8ad7eb

data/.jrubyrc

@@ -0,0 +1 @@
+debug.fullTrace=true

data/.travis.yml

@@ -5,7 +5,8 @@ rvm:
   - 2.2.6
   - 2.1.10
   - ruby-head
-  - jruby-1.7.19
+  - jruby-9.0.5.0
+  - jruby-9.1.7.0
 before_install: gem update --system && gem install bundler
 after_success: bundle exec codeclimate-test-reporter
 sudo: false

data/CODE_OF_CONDUCT.md

@@ -1,3 +1,73 @@
-# Contributor Code of Conduct
+# Contributor Covenant Code of Conduct
 
-Matz is Nice And So We Are Nice
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at devops@reevoo.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Dockerfile

@@ -1,6 +1,6 @@
 FROM quay.io/assemblyline/alpine:3.5
 
-MAINTAINER ed@reevoo.com
+MAINTAINER devops@reevoo.com
 ARG VERSION
 RUN apk add --no-cache --virtual .builddeps \
       build-base \

data/Gemfile

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 source "https://rubygems.org"
 
 # Specify your gem's dependencies in sitemap_check.gemspec

data/README.md

@@ -1,5 +1,6 @@
 # Sitemap Check
 
+[![Docker Repository on Quay](https://quay.io/repository/reevoo/sitemap_check/status "Docker Repository on Quay")](https://quay.io/repository/reevoo/sitemap_check)
 [![Build Status](https://travis-ci.org/reevoo/sitemap_check.svg?branch=master)](https://travis-ci.org/reevoo/sitemap_check)
 [![Code Climate](https://codeclimate.com/github/reevoo/sitemap_check/badges/gpa.svg)](https://codeclimate.com/github/reevoo/sitemap_check)
 [![Test Coverage](https://codeclimate.com/github/reevoo/sitemap_check/badges/coverage.svg)](https://codeclimate.com/github/reevoo/sitemap_check/coverage)
@@ -21,6 +22,14 @@ $ CHECK_URL=http://www.reevoo.com/sitemap_index.xml sitemap_check
 $ sitemap_check http://www.reevoo.com/sitemap_index.xml
 ```
 
+You can also run `sitemap_check` in validation mode:
+
+```bash
+$ VALIDATE=1 sitemap_check http://www.reevoo.com/sitemap_index.xml
+```
+
+This will validate response bodies with W3C's validation service.
+
 # Docker
 
 ```bash

data/Rakefile

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require "bundler/gem_tasks"
 require "reevoocop/rake_task"
 require "rspec/core/rake_task"
@@ -7,9 +8,9 @@ RSpec::Core::RakeTask.new(:spec)
 
 DOCKER_REPO = "quay.io/reevoo/sitemap_check"
 
-task default: [:spec, :reevoocop]
-task release: [:spec, :reevoocop]
-task build:   [:spec, :reevoocop]
+task default: %i[spec reevoocop]
+task release: %i[spec reevoocop]
+task build:   %i[spec reevoocop]
 
 task :release do
   sh "docker build --build-arg VERSION=#{SitemapCheck::VERSION} -t #{DOCKER_REPO}:#{SitemapCheck::VERSION} ."

data/bin/sitemap_check

@@ -1,4 +1,5 @@
 #!/usr/bin/env ruby
+# frozen_string_literal: true
 
 require "sitemap_check"
 SitemapCheck.check ENV.fetch("CHECK_URL", ARGV[0])

data/lib/sitemap_check.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require "colorize"
 require "sitemap_check/sitemap"
 require "sitemap_check/version"

data/lib/sitemap_check/logger.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 class SitemapCheck
   class Logger
     def initialize(stream = $stdout)

data/lib/sitemap_check/page.rb

@@ -1,5 +1,7 @@
+# frozen_string_literal: true
 require "typhoeus"
 require "sitemap_check/logger"
+require "sitemap_check/validator"
 require "colorize"
 require "uri"
 
@@ -7,9 +9,16 @@ class SitemapCheck
   class Page
     def initialize(url, logger = Logger.new)
       self.uri = URI(url)
-      replace_host
-      self.request = Typhoeus::Request.new(self.url, method: :head, followlocation: true)
       self.logger = logger
+
+      replace_host
+
+      self.request = Typhoeus::Request.new(
+        self.url,
+        method: request_method,
+        followlocation: true,
+      )
+
       setup_callbacks
     end
 
@@ -32,6 +41,7 @@ class SitemapCheck
     def setup_callbacks # rubocop:disable Metrics/AbcSize
       request.on_complete do |response|
         if response.success?
+          validate(response)
           @exists = true
         elsif response.timed_out?
           @exists = true
@@ -45,5 +55,17 @@ class SitemapCheck
         end
       end
     end
+
+    def request_method
+      validate? ? :get : :head
+    end
+
+    def validate(response)
+      Validator.new(response, logger).validate if validate?
+    end
+
+    def validate?
+      ENV["VALIDATE"]
+    end
   end
 end

data/lib/sitemap_check/sitemap.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 require "typhoeus"
 require "sitemap_check/page"
 require "sitemap_check/logger"
@@ -37,7 +38,7 @@ class SitemapCheck
       pages.select(&:error)
     end
 
-    def exists? # rubocop:disable Style/TrivialAccessors
+    def exists?
       @ok
     end
 

data/lib/sitemap_check/validator.rb

@@ -0,0 +1,61 @@
+# frozen_string_literal: true
+require "w3c_validators"
+
+class SitemapCheck
+  class Validator
+    LIMIT = 100
+
+    attr_accessor :logger, :response
+
+    class << self
+      attr_accessor :message_count
+    end
+
+    def initialize(response, logger = Logger.new)
+      self.logger = logger
+      self.response = response
+      self.class.message_count ||= 0
+    end
+
+    def validate
+      validator = W3CValidators::NuValidator.new
+      result = validator.validate_text(response.body)
+      return if result.errors.empty? && result.warnings.empty?
+
+      log_url
+      log_errors(result)
+      log_warnings(result)
+      fail_if_too_many_messages
+    end
+
+    private
+
+    def log_url
+      logger.log "-" * 80
+      logger.log response.effective_url.cyan
+    end
+
+    def log_errors(result)
+      result.errors.each do |e|
+        logger.log "  ERROR: #{e.message}".red
+        logger.log "         #{e.source.inspect}"
+
+        self.class.message_count += 1
+      end
+    end
+
+    def log_warnings(result)
+      result.warnings.each do |w|
+        logger.log "  WARNING: #{w.message}".yellow
+        logger.log "           #{w.source.inspect}"
+
+        self.class.message_count += 1
+      end
+    end
+
+    def fail_if_too_many_messages
+      error = "Stopping because there are more than #{LIMIT} messages."
+      fail error if self.class.message_count > LIMIT
+    end
+  end
+end

data/lib/sitemap_check/version.rb

@@ -1,3 +1,4 @@
+# frozen_string_literal: true
 class SitemapCheck
-  VERSION = "0.1.9"
+  VERSION = "0.1.10"
 end

data/sitemap_check.gemspec

@@ -1,4 +1,5 @@
 # coding: utf-8
+# frozen_string_literal: true
 lib = File.expand_path("../lib", __FILE__)
 $LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
 require "sitemap_check/version"
@@ -21,6 +22,7 @@ Gem::Specification.new do |spec|
   spec.add_dependency "nokogiri", "~> 1.7"
   spec.add_dependency "typhoeus", "~> 1.1"
   spec.add_dependency "colorize", "~> 0.8"
+  spec.add_dependency "w3c_validators", "~> 1.3"
   spec.add_development_dependency "bundler", "~> 1.14"
   spec.add_development_dependency "rake", "~> 12.0"
   spec.add_development_dependency "rspec", "~> 3.5"

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: sitemap_check
 version: !ruby/object:Gem::Version
-  version: 0.1.9
+  version: 0.1.10
 platform: ruby
 authors:
 - Ed Robinson
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-02-15 00:00:00.000000000 Z
+date: 2017-07-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -52,6 +52,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.8'
+- !ruby/object:Gem::Dependency
+  name: w3c_validators
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.3'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -145,6 +159,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - ".gitignore"
+- ".jrubyrc"
 - ".rspec"
 - ".ruby-version"
 - ".travis.yml"
@@ -159,6 +174,7 @@ files:
 - lib/sitemap_check/logger.rb
 - lib/sitemap_check/page.rb
 - lib/sitemap_check/sitemap.rb
+- lib/sitemap_check/validator.rb
 - lib/sitemap_check/version.rb
 - sitemap_check.gemspec
 homepage: https://github.com/reevoo/sitemap_check