site-inspector 1.0.2 → 3.2.0

data/package.json

@@ -0,0 +1,23 @@
+{
+  "name": "site-inspector",
+  "version": "2.0.0",
+  "description": "Returns information about a domain's technology and capabilities",
+  "main": "site-inspector",
+  "dependencies": {
+    "pa11y": "^5.0.0"
+  },
+  "devDependencies": {},
+  "scripts": {
+    "test": "script/cibuild"
+  },
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/benbalter/site-inspector.git"
+  },
+  "author": "",
+  "license": "MIT",
+  "bugs": {
+    "url": "https://github.com/benbalter/site-inspector/issues"
+  },
+  "homepage": "https://github.com/benbalter/site-inspector#readme"
+}

data/script/bootstrap

@@ -0,0 +1,2 @@
+bundle install
+npm install

data/script/cibuild

@@ -0,0 +1,11 @@
+#!/bin/sh
+
+set -e
+
+script/pa11y-version
+
+bundle exec rake spec
+
+bundle exec rubocop 
+
+gem build site-inspector.gemspec

data/script/console

@@ -0,0 +1,3 @@
+#! /bin/sh
+
+DEBUG=1 bundle exec pry -r './lib/site-inspector'

data/script/pa11y-version

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require './lib/site-inspector'
+
+if SiteInspector::Endpoint::Accessibility.pa11y?
+  puts "Pa11y version: #{SiteInspector::Endpoint::Accessibility.pa11y_version}"
+else
+  puts '**RUNNING TESTS WITHOUT PA11Y**'
+end

data/script/release

@@ -0,0 +1,38 @@
+#!/bin/sh
+# Tag and push a release.
+
+set -e
+
+# Make sure we're in the project root.
+
+cd $(dirname "$0")/..
+
+# Build a new gem archive.
+
+rm -rf site-inspector-*.gem
+gem build -q site-inspector.gemspec
+
+# Make sure we're on the master branch.
+
+(git branch | grep -q '* master') || {
+  echo "Only release from the master branch."
+  exit 1
+}
+
+# Figure out what version we're releasing.
+
+tag=v`ls site-inspector-*.gem | sed 's/^site-inspector-\(.*\)\.gem$/\1/'`
+
+# Make sure we haven't released this version before.
+
+git fetch -t origin
+
+(git tag -l | grep -q "$tag") && {
+  echo "Whoops, there's already a '${tag}' tag."
+  exit 1
+}
+
+# Tag it and bag it.
+
+gem push site-inspector-*.gem && git tag "$tag" &&
+  git push origin master && git push origin "$tag"

data/site-inspector.gemspec

@@ -0,0 +1,42 @@
+# frozen_string_literal: true
+
+require File.expand_path './lib/site-inspector/version', File.dirname(__FILE__)
+
+Gem::Specification.new do |s|
+  s.name                  = 'site-inspector'
+  s.version               = SiteInspector::VERSION
+  s.summary               = 'A Ruby port and v2 of Site Inspector (https://github.com/benbalter/site-inspector)'
+  s.description           = "Returns information about a domain's technology and capabilities"
+  s.authors               = 'Ben Balter'
+  s.email                 = 'ben@balter.com'
+  s.homepage              = 'https://github.com/benbalter/site-inspector'
+  s.license               = 'MIT'
+
+  s.files                 = `git ls-files -z`.split("\x0")
+  s.executables           = s.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  s.test_files            = s.files.grep(%r{^(test|spec|features)/})
+  s.require_paths         = ['lib']
+
+  s.add_dependency('cliver', '~> 0.0')
+  s.add_dependency('colorator', '~> 1.1')
+  s.add_dependency('dnsruby', '~> 1.0')
+  s.add_dependency('dotenv', '~> 2.0')
+  s.add_dependency('gman', '~> 7.0', '>= 7.0.4')
+  s.add_dependency('mercenary', '~> 0.0')
+  s.add_dependency('nokogiri', '~> 1.0')
+  s.add_dependency('oj', '~> 3.0')
+  s.add_dependency('parallel', '~> 1.0')
+  s.add_dependency('public_suffix', '~> 4.0')
+  s.add_dependency('sniffles', '~> 0.0')
+  s.add_dependency('typhoeus', '~> 1.0')
+  s.add_dependency('urlscan', '~> 0.6')
+  s.add_dependency('whois', '~> 5.0')
+
+  s.add_development_dependency('pry', '~> 0.0')
+  s.add_development_dependency('rake', '~> 13.0')
+  s.add_development_dependency('rspec', '~> 3.0')
+  s.add_development_dependency('rubocop', '~> 1.0')
+  s.add_development_dependency('rubocop-performance', '~> 1.5')
+  s.add_development_dependency('rubocop-rspec', '~> 2.0')
+  s.add_development_dependency('webmock', '~> 3.0')
+end

data/spec/checks/site_inspector_endpoint_accessibility_spec.rb

@@ -0,0 +1,84 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe SiteInspector::Endpoint::Accessibility do
+  subject do
+    endpoint = SiteInspector::Endpoint.new('http://example.com')
+    described_class.new(endpoint)
+  end
+
+  it "retrieve's pa11y's version" do
+    pending('Pa11y not installed') unless described_class.pa11y?
+    expect(subject.class.pa11y_version).to match(/\d\.\d\.\d/)
+  end
+
+  it 'responds to valid standards' do
+    expect(subject.respond_to?(:section508)).to be(true)
+  end
+
+  it 'knows the level' do
+    expect(subject.level).to be(:error)
+  end
+
+  it 'allows the user to set the level' do
+    subject.level = :warning
+    expect(subject.level).to be(:warning)
+  end
+
+  it 'errors on invalid levels' do
+    expect { subject.level = 'foo' }.to raise_error(ArgumentError)
+  end
+
+  it 'knows the standard' do
+    expect(subject.standard).to be(:wcag2a)
+  end
+
+  it 'allows the user to set the standard' do
+    subject.standard = :wcag2a
+    expect(subject.standard).to be(:wcag2a)
+  end
+
+  it 'errors on invalid standards' do
+    expect { subject.standard = :foo }.to raise_error(ArgumentError)
+  end
+
+  context 'with pa11y installed' do
+    before do
+      stub_request(:head, 'http://example.com/').to_return(status: 200)
+    end
+  end
+
+  context "with pa11y stub'd" do
+    before do
+      output = '[{"code":"Section508.L.NoContentAnchor","context":"<a href=\"foo\"></a>","message":"Anchor element found with a valid href attribute, but no link content has been supplied.","selector":"html > body > a","type":"error","typeCode":1}]'
+      allow(subject).to receive(:run_command) { [output, 2] }
+    end
+
+    it 'knows if a site is valid' do
+      with_env 'SKIP_PA11Y_CHECK', 'true' do
+        expect(subject.valid?).to be(false)
+      end
+    end
+
+    it 'counts the errors' do
+      with_env 'SKIP_PA11Y_CHECK', 'true' do
+        expect(subject.errors).to be(1)
+      end
+    end
+
+    it 'runs the check' do
+      with_env 'SKIP_PA11Y_CHECK', 'true' do
+        expect(subject.check[:valid]).to be(false)
+        expect(subject.check[:results].first['code']).to eql('WCAG2A.Principle3.Guideline3_1.3_1_1.H57.2')
+      end
+    end
+
+    it 'runs a named check' do
+      with_env 'SKIP_PA11Y_CHECK', 'true' do
+        expect(subject.check[:valid]).to be(false)
+        expect(subject.check[:results].first['code']).to eql('WCAG2A.Principle3.Guideline3_1.3_1_1.H57.2')
+      end
+    end
+  end
+end

data/spec/checks/site_inspector_endpoint_check_spec.rb

@@ -0,0 +1,42 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe SiteInspector::Endpoint::Check do
+  subject do
+    stub_request(:head, 'http://example.com/').to_return(status: 200)
+    endpoint = SiteInspector::Endpoint.new('http://example.com')
+    described_class.new(endpoint)
+  end
+
+  it 'returns the endpoint' do
+    expect(subject.endpoint.class).to eql(SiteInspector::Endpoint)
+  end
+
+  it 'returns the response' do
+    expect(subject.response.class).to eql(Typhoeus::Response)
+  end
+
+  it 'returns the request' do
+    expect(subject.request.class).to eql(Typhoeus::Request)
+  end
+
+  it 'returns the host' do
+    expect(subject.host).to eql('example.com')
+  end
+
+  it 'returns its name' do
+    expect(subject.name).to be(:check)
+  end
+
+  it 'returns the instance name' do
+    expect(described_class.name).to be(:check)
+  end
+
+  it 'enables and disables the check' do
+    expect(described_class.enabled?).to be(true)
+    described_class.enabled = false
+    expect(described_class.enabled?).to be(false)
+    described_class.enabled = true
+  end
+end

data/spec/checks/site_inspector_endpoint_content_spec.rb

@@ -0,0 +1,117 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe SiteInspector::Endpoint::Content do
+  subject do
+    body = <<-BODY
+    <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+      <html>
+        <head>
+          <meta name="generator" content="Jekyll v3.8.5" />
+        </head>
+        <body>
+          <h1>Some page</h1>
+        </body>
+      </html>
+    BODY
+
+    stub_request(:get, 'http://example.com/')
+      .to_return(status: 200, body: body)
+    stub_request(:head, 'http://example.com/')
+      .to_return(status: 200)
+    endpoint = SiteInspector::Endpoint.new('http://example.com')
+    described_class.new(endpoint)
+  end
+
+  it 'returns the doc' do
+    expect(subject.document.class).to eql(Nokogiri::HTML::Document)
+    expect(subject.document.css('h1').text).to eql('Some page')
+  end
+
+  it 'returns the body' do
+    expect(subject.body).to match('<h1>Some page</h1>')
+  end
+
+  it 'returns the doctype' do
+    expect(subject.doctype).to eql('-//W3C//DTD XHTML 1.0 Transitional//EN')
+  end
+
+  it 'knows when robots.txt exists' do
+    stub_request(:head, %r{http://example.com/[a-z0-9]{32}}i).to_return(status: 404)
+
+    stub_request(:head, 'http://example.com/robots.txt')
+      .to_return(status: 200)
+    expect(subject.robots_txt?).to be(true)
+  end
+
+  it "knows when robots.txt doesn't exist" do
+    stub_request(:head, %r{http://example.com/[a-z0-9]{32}}i).to_return(status: 404)
+
+    stub_request(:head, 'http://example.com/robots.txt')
+      .to_return(status: 404)
+    expect(subject.robots_txt?).to be(false)
+  end
+
+  it 'knows when sitemap.xml exists' do
+    stub_request(:head, %r{http://example.com/[a-z0-9]{32}}i).to_return(status: 404)
+
+    stub_request(:head, 'http://example.com/sitemap.xml')
+      .to_return(status: 200)
+    expect(subject.sitemap_xml?).to be(true)
+  end
+
+  it 'knows when sitemap.xml exists' do
+    stub_request(:head, %r{http://example.com/[a-z0-9]{32}}i).to_return(status: 404)
+
+    stub_request(:head, 'http://example.com/sitemap.xml')
+      .to_return(status: 404)
+    expect(subject.sitemap_xml?).to be(false)
+  end
+
+  it 'knows when humans.txt exists' do
+    stub_request(:head, %r{http://example.com/[a-z0-9]{32}}i).to_return(status: 404)
+
+    stub_request(:head, 'http://example.com/humans.txt')
+      .to_return(status: 200)
+    expect(subject.humans_txt?).to be(true)
+  end
+
+  it "knows when humans.txt doesn't exist" do
+    stub_request(:head, %r{http://example.com/[a-z0-9]{32}}i).to_return(status: 404)
+
+    stub_request(:head, 'http://example.com/humans.txt')
+      .to_return(status: 200)
+    expect(subject.humans_txt?).to be(true)
+  end
+
+  it 'returns the generator' do
+    expect(subject.generator).to eql('Jekyll v3.8.5')
+  end
+
+  context '404s' do
+    it 'knows when an endpoint returns a proper 404' do
+      stub_request(:head, %r{http://example.com/.*})
+        .to_return(status: 404)
+      expect(subject.proper_404s?).to be(true)
+    end
+
+    it "knows when an endpoint doesn't return a proper 404" do
+      stub_request(:head, %r{http://example.com/[a-z0-9]{32}}i)
+        .to_return(status: 200)
+      expect(subject.proper_404s?).to be(false)
+    end
+
+    it 'generates a random path' do
+      path = subject.send(:random_path)
+      expect(path).to match(/[a-z0-9]{32}/i)
+      expect(subject.send(:random_path)).to eql(path)
+    end
+
+    it "doesn't say something exists when there are no 404s" do
+      stub_request(:head, %r{http://example.com/[a-z0-9]{32}}i).to_return(status: 200)
+      stub_request(:head, 'http://example.com/humans.txt').to_return(status: 200)
+      expect(subject.humans_txt?).to be(nil)
+    end
+  end
+end

data/spec/checks/site_inspector_endpoint_cookies_spec.rb

@@ -0,0 +1,73 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe SiteInspector::Endpoint::Cookies do
+  context 'without cookies' do
+    subject do
+      stub_request(:head, 'http://example.com/')
+        .to_return(status: 200, body: '')
+      endpoint = SiteInspector::Endpoint.new('http://example.com')
+      described_class.new(endpoint)
+    end
+
+    it 'knows when there are no cookies' do
+      expect(subject.cookies?).to be(false)
+      expect(subject.all).to be(nil)
+    end
+  end
+
+  context 'with cookies' do
+    subject do
+      cookies = [
+        CGI::Cookie.new(
+          'name' => 'foo',
+          'value' => 'bar',
+          'domain' => 'example.com',
+          'path' => '/'
+        ),
+        CGI::Cookie.new(
+          'name' => 'foo2',
+          'value' => 'bar2',
+          'domain' => 'example.com',
+          'path' => '/'
+        )
+      ].map(&:to_s)
+
+      stub_request(:head, 'http://example.com/')
+        .to_return(status: 200, body: '', headers: { 'set-cookie' => cookies })
+      endpoint = SiteInspector::Endpoint.new('http://example.com')
+      described_class.new(endpoint)
+    end
+
+    it 'knows when there are cookies' do
+      expect(subject.cookies?).to be(true)
+      expect(subject.all.count).to be(2)
+    end
+
+    it 'returns a cookie by name' do
+      expect(subject['foo'].to_s).to match(/foo=bar/)
+    end
+
+    it "knows cookies aren't secure" do
+      expect(subject.secure?).to be(false)
+    end
+  end
+
+  context 'with secure cookies' do
+    subject do
+      cookies = [
+        'foo=bar; domain=example.com; path=/; secure; HttpOnly',
+        'foo2=bar2; domain=example.com; path=/'
+      ]
+      stub_request(:head, 'http://example.com/')
+        .to_return(status: 200, body: '', headers: { 'set-cookie' => cookies })
+      endpoint = SiteInspector::Endpoint.new('http://example.com')
+      described_class.new(endpoint)
+    end
+
+    it 'knows cookies are secure' do
+      expect(subject.secure?).to be(true)
+    end
+  end
+end