path: root/danger/commit_messages/Dangerfile

# frozen_string_literal: true

require 'json'

URL_LIMIT_SUBJECT = "https://chris.beams.io/posts/git-commit/#limit-50"
URL_GIT_COMMIT = "https://chris.beams.io/posts/git-commit/"

# rubocop: disable Style/SignalException
# rubocop: disable Metrics/CyclomaticComplexity
# rubocop: disable Metrics/PerceivedComplexity

# Perform various checks against commits. We're not using
# https://github.com/jonallured/danger-commit_lint because its output is not
# very helpful, and it doesn't offer the means of ignoring merge commits.

class EmojiChecker
  DIGESTS = File.expand_path('../../fixtures/emojis/digests.json', __dir__)
  ALIASES = File.expand_path('../../fixtures/emojis/aliases.json', __dir__)

  # A regex that indicates a piece of text _might_ include an Emoji. The regex
  # alone is not enough, as we'd match `:foo:bar:baz`. Instead, we use this
  # regex to save us from having to check for all possible emoji names when we
  # know one definitely is not included.
  LIKELY_EMOJI = /:[\+a-z0-9_\-]+:/

  def initialize
    names = JSON.parse(File.read(DIGESTS)).keys +
      JSON.parse(File.read(ALIASES)).keys

    @emoji = names.map { |name| ":#{name}:" }
  end

  def includes_emoji?(text)
    return false unless text.match?(LIKELY_EMOJI)

    @emoji.any? { |emoji| text.include?(emoji) }
  end
end

def fail_commit(commit, message)
  fail("#{commit.sha}: #{message}")
end

def warn_commit(commit, message)
  warn("#{commit.sha}: #{message}")
end

def lines_changed_in_commit(commit)
  commit.diff_parent.stats[:total][:lines]
end

def subject_starts_with_capital?(subject)
  first_char = subject.chars.first

  first_char.upcase == first_char
end

def ce_upstream?
  gitlab.mr_labels.any? { |label| label == 'CE upstream' }
end

def too_many_changed_lines?(commit)
  commit.diff_parent.stats[:total][:files] > 3 &&
    lines_changed_in_commit(commit) >= 30
end

def emoji_checker
  @emoji_checker ||= EmojiChecker.new
end

def unicode_emoji_regex
  @unicode_emoji_regex ||= %r((
    [\u{1F300}-\u{1F5FF}] |
    [\u{1F1E6}-\u{1F1FF}] |
    [\u{2700}-\u{27BF}] |
    [\u{1F900}-\u{1F9FF}] |
    [\u{1F600}-\u{1F64F}] |
    [\u{1F680}-\u{1F6FF}] |
    [\u{2600}-\u{26FF}]
  ))x
end

def lint_commit(commit)
  # For now we'll ignore merge commits, as getting rid of those is a problem
  # separate from enforcing good commit messages.
  return false if commit.message.start_with?('Merge branch')

  # We ignore revert commits as they are well structured by Git already
  return false if commit.message.start_with?('Revert "')

  failures = false
  subject, separator, details = commit.message.split("\n", 3)

  if subject.split.length < 3
    fail_commit(
      commit,
      'The commit subject must contain at least three words'
    )

    failures = true
  end

  if subject.length > 72
    fail_commit(
      commit,
      'The commit subject may not be longer than 72 characters'
    )

    failures = true
  elsif subject.length > 50
    warn_commit(
      commit,
      "This commit's subject line is acceptable, but please try to [reduce it to 50 characters](#{URL_LIMIT_SUBJECT})."
    )
  end

  unless subject_starts_with_capital?(subject)
    fail_commit(commit, 'The commit subject must start with a capital letter')
    failures = true
  end

  if subject.end_with?('.')
    fail_commit(commit, 'The commit subject must not end with a period')
    failures = true
  end

  if separator && !separator.empty?
    fail_commit(
      commit,
      'The commit subject and body must be separated by a blank line'
    )

    failures = true
  end

  details&.each_line do |line|
    line = line.strip

    next if line.length <= 72

    url_size = line.scan(%r((https?://\S+))).sum { |(url)| url.length }

    # If the line includes a URL, we'll allow it to exceed 72 characters, but
    # only if the line _without_ the URL does not exceed this limit.
    next if line.length - url_size <= 72

    fail_commit(
      commit,
      'The commit body should not contain more than 72 characters per line'
    )

    failures = true
  end

  if !details && too_many_changed_lines?(commit)
    fail_commit(
      commit,
      'Commits that change 30 or more lines across at least three files ' \
        'must describe these changes in the commit body'
    )

    failures = true
  end

  if emoji_checker.includes_emoji?(commit.message)
    fail_commit(
      commit,
      'Avoid the use of Markdown Emoji such as `:+1:`. ' \
        'These add no value to the commit message, ' \
        'and are displayed as plain text outside of GitLab'
    )

    failures = true
  end

  if commit.message.match?(unicode_emoji_regex)
    fail_commit(
      commit,
      'Avoid the use of Unicode Emoji. ' \
        'These add no value to the commit message, ' \
        'and may not be displayed properly everywhere'
    )

    failures = true
  end

  if commit.message.match?(%r(([\w\-\/]+)?(#|!|&|%)\d+\b))
    fail_commit(
      commit,
      'Use full URLs instead of short references ' \
        '(`gitlab-org/gitlab-ce#123` or `!123`), as short references are ' \
        'displayed as plain text outside of GitLab'
    )

    failures = true
  end

  failures
end

def lint_commits(commits)
  failed = commits.select do |commit|
    lint_commit(commit)
  end

  if failed.any?
    markdown(<<~MARKDOWN)
      ## Commit message standards

      One or more commit messages do not meet our Git commit message standards.
      For more information on how to write a good commit message, take a look at
      [How to Write a Git Commit Message](#{URL_GIT_COMMIT}).

      Here is an example of a good commit message:

          Reject ruby interpolation in externalized strings

          When using ruby interpolation in externalized strings, they can't be
          detected. Which means they will never be presented to be translated.

          To mix variables into translations we need to use `sprintf`
          instead.

          Instead of:

              _("Hello \#{subject}")

          Use:

              _("Hello %{subject}") % { subject: 'world' }

      This is an example of a bad commit message:

          updated README.md

      This commit message is bad because although it tells us that README.md is
      updated, it doesn't tell us why or how it was updated.
    MARKDOWN
  end
end

if git.commits.length > 10 && !ce_upstream?
  warn(
    'This merge request includes more than 10 commits. ' \
      'Please rebase these commits into a smaller number of commits.'
  )
else
  lint_commits(git.commits)
end