Alexander Glushkov's solution

.rspec

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

.rubocop.yml

@@ -0,0 +1,72 @@
+# human should be able to read 200 chars per line
+Layout/LineLength:
+  Max: 200
+
+# relax branch condition size, code can be too verbose
+Metrics/AbcSize:
+  Max: 40
+
+# short clear method name
+Metrics/MethodLength:
+  Max: 25
+
+# no performance implication
+Style/OptionalBooleanParameter:
+  Enabled: false
+
+# %i(array) is not common in Ruby
+Style/SymbolArray:
+  Enabled: false
+
+# too restrictive
+Style/FrozenStringLiteralComment:
+  Enabled: false
+
+# default complexity is low at 8
+Metrics/PerceivedComplexity:
+  Max: 12
+
+# if works as well as safe navigation (&.)
+Style/SafeNavigation:
+  Enabled: false
+
+# disable this cop, dont agree with it
+Style/FetchEnvVar:
+  Enabled: false
+
+# buggus check in Rubocop.
+# SerpApiClient constructor is rated to 9
+#  def initialize(params = {})
+Metrics/CyclomaticComplexity:
+  Max: 12
+
+# There is a tradeoff between line length and line count.
+Metrics/ClassLength:
+  Max: 140
+
+# Keyword args are readable.
+Metrics/ParameterLists:
+  CountKeywordArgs: false
+
+# this rule doesn't always work well with Ruby
+Layout/FirstHashElementIndentation:
+  Enabled: false
+
+# Dir glob is already sorted, but the explicit sort documents intent.
+Lint/RedundantDirGlobSort:
+  Enabled: false
+
+# RSpec describe/context blocks legitimately span many lines
+Metrics/BlockLength:
+  AllowedMethods:
+    - describe
+    - context
+
+AllCops:
+  # hide message
+  SuggestExtensions: false
+  # show new cops
+  NewCops: enable
+  Exclude:
+    - 'Gemfile'
+    - 'benchmark/**/*'

.ruby-version

@@ -0,0 +1 @@
+4.0.5

Gemfile

@@ -0,0 +1,10 @@
+# frozen_string_literal: true
+
+source "https://rubygems.org"
+
+gem "benchmark-ips", require: false
+gem "memory_profiler", require: false
+gem "nokogiri", require: false
+gem "nokolexbor"
+gem "rspec"
+gem "rubocop", require: false

Gemfile.lock

@@ -0,0 +1,93 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    ast (2.4.3)
+    benchmark-ips (2.15.1)
+    diff-lcs (1.6.2)
+    json (2.19.8)
+    language_server-protocol (3.17.0.5)
+    lint_roller (1.1.0)
+    memory_profiler (1.1.0)
+    nokogiri (1.19.3-x86_64-linux-gnu)
+      racc (~> 1.4)
+    nokolexbor (0.7.0-x86_64-linux)
+    parallel (2.1.0)
+    parser (3.3.11.1)
+      ast (~> 2.4.1)
+      racc
+    prism (1.9.0)
+    racc (1.8.1)
+    rainbow (3.1.1)
+    regexp_parser (2.12.0)
+    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 (3.13.8)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.13.0)
+    rspec-support (3.13.7)
+    rubocop (1.87.0)
+      json (~> 2.3)
+      language_server-protocol (~> 3.17.0.2)
+      lint_roller (~> 1.1.0)
+      parallel (>= 1.10)
+      parser (>= 3.3.0.2)
+      rainbow (>= 2.2.2, < 4.0)
+      regexp_parser (>= 2.9.3, < 3.0)
+      rubocop-ast (>= 1.49.0, < 2.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 2.4.0, < 4.0)
+    rubocop-ast (1.49.1)
+      parser (>= 3.3.7.2)
+      prism (~> 1.7)
+    ruby-progressbar (1.13.0)
+    unicode-display_width (3.2.0)
+      unicode-emoji (~> 4.1)
+    unicode-emoji (4.2.0)
+
+PLATFORMS
+  x86_64-linux
+
+DEPENDENCIES
+  benchmark-ips
+  memory_profiler
+  nokogiri
+  nokolexbor
+  rspec
+  rubocop
+
+CHECKSUMS
+  ast (2.4.3) sha256=954615157c1d6a382bc27d690d973195e79db7f55e9765ac7c481c60bdb4d383
+  benchmark-ips (2.15.1) sha256=07a1a9f3c6105ecaf68c174fc3fbcddd71a0e9ada6236ae03093a0dcfd812d59
+  diff-lcs (1.6.2) sha256=9ae0d2cba7d4df3075fe8cd8602a8604993efc0dfa934cff568969efb1909962
+  json (2.19.8) sha256=6354310fd76ef69b87d5bd1f38b40d730613baf90b6803d2d0a48f618d32dfaa
+  language_server-protocol (3.17.0.5) sha256=fd1e39a51a28bf3eec959379985a72e296e9f9acfce46f6a79d31ca8760803cc
+  lint_roller (1.1.0) sha256=2c0c845b632a7d172cb849cc90c1bce937a28c5c8ccccb50dfd46a485003cc87
+  memory_profiler (1.1.0) sha256=79a17df7980a140c83c469785905409d3027ca614c42c086089d128b805aa8f8
+  nokogiri (1.19.3-x86_64-linux-gnu) sha256=2f5078620fe12e83669b5b17311b32532a8153d02eee7ad06948b926d6080976
+  nokolexbor (0.7.0-x86_64-linux) sha256=6348178e41233e67e0f533f84b0b1974b187fe137616541f1453bb7c0c16baf6
+  parallel (2.1.0) sha256=b35258865c2e31134c5ecb708beaaf6772adf9d5efae28e93e99260877b09356
+  parser (3.3.11.1) sha256=d17ace7aabe3e72c3cc94043714be27cc6f852f104d81aa284c2281aecc65d54
+  prism (1.9.0) sha256=7b530c6a9f92c24300014919c9dcbc055bf4cdf51ec30aed099b06cd6674ef85
+  racc (1.8.1) sha256=4a7f6929691dbec8b5209a0b373bc2614882b55fc5d2e447a21aaa691303d62f
+  rainbow (3.1.1) sha256=039491aa3a89f42efa1d6dec2fc4e62ede96eb6acd95e52f1ad581182b79bc6a
+  regexp_parser (2.12.0) sha256=35a916a1d63190ab5c9009457136ae5f3c0c7512d60291d0d1378ba18ce08ebb
+  rspec (3.13.2) sha256=206284a08ad798e61f86d7ca3e376718d52c0bc944626b2349266f239f820587
+  rspec-core (3.13.6) sha256=a8823c6411667b60a8bca135364351dda34cd55e44ff94c4be4633b37d828b2d
+  rspec-expectations (3.13.5) sha256=33a4d3a1d95060aea4c94e9f237030a8f9eae5615e9bd85718fe3a09e4b58836
+  rspec-mocks (3.13.8) sha256=086ad3d3d17533f4237643de0b5c42f04b66348c28bf6b9c2d3f4a3b01af1d47
+  rspec-support (3.13.7) sha256=0640e5570872aafefd79867901deeeeb40b0c9875a36b983d85f54fb7381c47c
+  rubocop (1.87.0) sha256=b9d9ddf55116a513f8ef2c7ae660662d8b49301f118d3f0df61865b33a5c188d
+  rubocop-ast (1.49.1) sha256=4412f3ee70f6fe4546cc489548e0f6fcf76cafcfa80fa03af67098ffed755035
+  ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33
+  unicode-display_width (3.2.0) sha256=0cdd96b5681a5949cdbc2c55e7b420facae74c4aaf9a9815eee1087cb1853c42
+  unicode-emoji (4.2.0) sha256=519e69150f75652e40bf736106cfbc8f0f73aa3fb6a65afe62fefa7f80b0f80f
+
+BUNDLED WITH
+  4.0.10

benchmark/memory_profile.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+require 'memory_profiler'
+require 'carousel_parser'
+require_relative 'parsers'
+require_relative 'tee'
+
+fixture = ARGV[0] || 'van-gogh-paintings.html'
+backend = (ARGV[1] || 'nokolexbor').to_sym
+parser = Parsers::ALL.fetch(backend)
+
+html = File.read(File.expand_path("../spec/fixtures/#{fixture}", __dir__))
+
+report_name = "memory_profile-#{File.basename(fixture, '.html')}-#{backend}.txt"
+$stdout = Tee.new(File.expand_path("reports/#{report_name}", __dir__))
+
+carousel = CarouselParser.new(parser: parser)
+carousel.parse(html)
+
+report = MemoryProfiler.report { carousel.parse(html) }
+
+puts "Memory profile: #{fixture} via #{backend} (#{html.bytesize / 1024} KB input)\n\n"
+report.pretty_print(scale_bytes: true)
+
+$stdout.close

benchmark/parse_benchmark.rb

@@ -0,0 +1,28 @@
+# frozen_string_literal: true
+
+require 'benchmark/ips'
+require 'carousel_parser'
+require_relative 'parsers'
+require_relative 'tee'
+
+$stdout = Tee.new(File.expand_path('reports/parse_benchmark.txt', __dir__))
+
+FIXTURES_DIR = File.expand_path('../spec/fixtures', __dir__)
+
+fixtures = Dir[File.join(FIXTURES_DIR, '*.html')].sort.to_h do |path|
+  [File.basename(path), File.read(path)]
+end
+
+puts "End-to-end parse across all fixtures, by html parser backend\n\n"
+
+Benchmark.ips do |x|
+  x.config(time: 5, warmup: 2)
+
+  Parsers::ALL.each do |name, parser|
+    x.report(name) { fixtures.each_value { |html| CarouselParser.parse(html, parser: parser) } }
+  end
+
+  x.compare!
+end
+
+$stdout.close

benchmark/parsers.rb

@@ -0,0 +1,13 @@
+# frozen_string_literal: true
+
+require 'nokolexbor'
+require 'nokogiri'
+
+# Catalog of html parser backends to compare in benchmarks.
+module Parsers
+  ALL = {
+    nokolexbor: ->(html) { Nokolexbor::HTML(html) },
+    nokogiri: ->(html) { Nokogiri::HTML(html) },
+    nokogiri5: ->(html) { Nokogiri::HTML5(html) }
+  }.freeze
+end