Code Challange

.rspec

@@ -0,0 +1,3 @@
+--require spec_helper
+--format documentation
+--color

Gemfile

@@ -0,0 +1,6 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+gem 'nokolexbor'
+gem 'rspec'

Gemfile.lock

@@ -0,0 +1,48 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    coderay (1.1.3)
+    diff-lcs (1.6.2)
+    io-console (0.8.2)
+    method_source (1.1.0)
+    nokolexbor (0.6.2)
+    nokolexbor (0.6.2-arm64-darwin)
+    nokolexbor (0.6.2-x86_64-darwin)
+    nokolexbor (0.6.2-x86_64-linux)
+    pry (0.16.0)
+      coderay (~> 1.1)
+      method_source (~> 1.0)
+      reline (>= 0.6.0)
+    reline (0.6.3)
+      io-console (~> 0.5)
+    rspec (3.13.2)
+      rspec-core (~> 3.13.0)
+      rspec-expectations (~> 3.13.0)
+      rspec-mocks (~> 3.13.0)
+    rspec-core (3.13.6)
+      rspec-support (~> 3.13.0)
+    rspec-expectations (3.13.5)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-mocks (3.13.7)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.6)
+
+PLATFORMS
+  aarch64-linux-gnu
+  aarch64-linux-musl
+  arm-linux-gnu
+  arm-linux-musl
+  arm64-darwin
+  x86_64-darwin
+  x86_64-linux-gnu
+  x86_64-linux-musl
+
+DEPENDENCIES
+  nokolexbor
+  pry
+  rspec
+
+BUNDLED WITH
+   2.7.2

lib/google_carousel_parser.rb

@@ -0,0 +1,59 @@
+require 'nokolexbor'
+
+class GoogleCarouselParser
+  attr_reader :html, :attr_id
+
+  ATTR_ID_REGEX = %r{kc:/\w*/\w*:\w*}
+
+  def initialize(html)
+    @attr_id = html.match(ATTR_ID_REGEX).to_a.first
+    @html = Nokolexbor::HTML(html)
+  end
+
+  def call
+    carousel_block = html.at_css("div[data-attrid='#{attr_id}']")
+    heading = html.at_css('[role="tab"][aria-selected="true"]')&.text&.downcase || extract_heading(carousel_block)
+    data = carousel_block.css('a').map { |el| parse_element(el) }.compact
+
+    { heading => data }
+  end
+
+  private
+
+  def parse_element(el)
+    img_attrs = el.at_css('img')&.attributes
+    return unless img_attrs
+    name, *extensions = el.css('::text').map(&:text)
+    img_src = img_attrs.key?('id') ? image_sources[img_attrs['id'].value] : img_attrs['data-src'].value
+
+    attrs = { 'link' => construct_link(el), 'name' => name, 'image' => img_src }
+    attrs.merge!('extensions' => extensions) unless extensions.empty?
+    attrs
+  end
+
+  def construct_link(el)
+    val = el.attributes['href'].value
+    val.start_with?('http') ? val : "https://www.google.com#{val}"
+  end
+
+  def extract_heading(carousel)
+    heading = carousel.parent.at_css("div[role='heading']")
+    return heading.css('::text').last.text.downcase if heading
+
+    extract_heading(carousel.parent)
+  end
+
+  def image_sources
+    @image_sources ||= begin
+      scripts = html.css('script').map(&:text).select { _1.include?('_setImagesSrc') }
+      scripts.each_with_object({}) do |script, acc|
+        src, id = script.match(/.*(data:image.*)';.*\['([\w-]*)'\];/)&.captures
+        acc[id] = replace_js_escape_sequences(src) if src && id
+      end
+    end
+  end
+
+  def replace_js_escape_sequences(src)
+    src.gsub(/\\x([0-9a-fA-F]{2})/) { |match| match[2..-1].hex.chr }
+  end
+end

spec/lib/google_carousel_parser_spec.rb

@@ -0,0 +1,17 @@
+require 'spec_helper'
+require_relative '../../lib/google_carousel_parser'
+
+RSpec.describe GoogleCarouselParser do
+  subject(:results) { described_class.new(html).call }
+
+  Dir[File.expand_path('files/*')].entries.each do |folder|
+    context "when carousel is #{folder.split('/').last}" do
+      let(:html) { File.read("#{folder}/index.html") }
+      let(:json){ JSON.parse(File.read("#{folder}/expected-array.json")) }
+
+      it 'parses correctly' do
+        expect(results).to eq json
+      end
+    end
+  end
+end

spec/spec_helper.rb

@@ -0,0 +1,85 @@
+require 'json'
+
+RSpec.configure do |config|
+  # rspec-expectations config goes here. You can use an alternate
+  # assertion/expectation library such as wrong or the stdlib/minitest
+  # assertions if you prefer.
+  config.expect_with :rspec do |expectations|
+    # This option will default to `true` in RSpec 4. It makes the `description`
+    # and `failure_message` of custom matchers include text for helper methods
+    # defined using `chain`, e.g.:
+    #     be_bigger_than(2).and_smaller_than(4).description
+    #     # => "be bigger than 2 and smaller than 4"
+    # ...rather than:
+    #     # => "be bigger than 2"
+    expectations.include_chain_clauses_in_custom_matcher_descriptions = true
+  end
+
+  # rspec-mocks config goes here. You can use an alternate test double
+  # library (such as bogus or mocha) by changing the `mock_with` option here.
+  config.mock_with :rspec do |mocks|
+    # Prevents you from mocking or stubbing a method that does not exist on
+    # a real object. This is generally recommended, and will default to
+    # `true` in RSpec 4.
+    mocks.verify_partial_doubles = true
+  end
+
+  # This option will default to `:apply_to_host_groups` in RSpec 4 (and will
+  # have no way to turn it off -- the option exists only for backwards
+  # compatibility in RSpec 3). It causes shared context metadata to be
+  # inherited by the metadata hash of host groups and examples, rather than
+  # triggering implicit auto-inclusion in groups with matching metadata.
+  config.shared_context_metadata_behavior = :apply_to_host_groups
+
+# The settings below are suggested to provide a good initial experience
+# with RSpec, but feel free to customize to your heart's content.
+=begin
+  # This allows you to limit a spec run to individual examples or groups
+  # you care about by tagging them with `:focus` metadata. When nothing
+  # is tagged with `:focus`, all examples get run. RSpec also provides
+  # aliases for `it`, `describe`, and `context` that include `:focus`
+  # metadata: `fit`, `fdescribe` and `fcontext`, respectively.
+  config.filter_run_when_matching :focus
+
+  # Allows RSpec to persist some state between runs in order to support
+  # the `--only-failures` and `--next-failure` CLI options. We recommend
+  # you configure your source control system to ignore this file.
+  config.example_status_persistence_file_path = "spec/examples.txt"
+
+  # Limits the available syntax to the non-monkey patched syntax that is
+  # recommended. For more details, see:
+  # https://rspec.info/features/3-12/rspec-core/configuration/zero-monkey-patching-mode/
+  config.disable_monkey_patching!
+
+  # This setting enables warnings. It's recommended, but in some cases may
+  # be too noisy due to issues in dependencies.
+  config.warnings = true
+
+  # Many RSpec users commonly either run the entire suite or an individual
+  # file, and it's useful to allow more verbose output when running an
+  # individual spec file.
+  if config.files_to_run.one?
+    # Use the documentation formatter for detailed output,
+    # unless a formatter has already been configured
+    # (e.g. via a command-line flag).
+    config.default_formatter = "doc"
+  end
+
+  # Print the 10 slowest examples and example groups at the
+  # end of the spec run, to help surface which specs are running
+  # particularly slow.
+  config.profile_examples = 10
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = :random
+
+  # Seed global randomization in this process using the `--seed` CLI option.
+  # Setting this allows you to use `--seed` to deterministically reproduce
+  # test failures related to randomization by passing the same `--seed` value
+  # as the one that triggered the failure.
+  Kernel.srand config.seed
+=end
+end