debian-mirror-gitlab/lib/gitlab/legacy_github_import/importer.rb

340 lines
12 KiB
Ruby
Raw Normal View History

2019-02-15 15:39:39 +05:30
# frozen_string_literal: true
2015-04-26 12:48:37 +05:30
module Gitlab
2018-03-17 18:26:18 +05:30
module LegacyGithubImport
2015-04-26 12:48:37 +05:30
class Importer
2018-03-17 18:26:18 +05:30
def self.refmap
Gitlab::GithubImport.refmap
end
2017-08-17 22:00:37 +05:30
attr_reader :errors, :project, :repo, :repo_url
2015-04-26 12:48:37 +05:30
def initialize(project)
2016-06-02 11:05:42 +05:30
@project = project
@repo = project.import_source
@repo_url = project.import_url
2016-09-13 17:45:13 +05:30
@errors = []
2016-11-03 12:29:30 +05:30
@labels = {}
2017-08-17 22:00:37 +05:30
end
def client
return @client if defined?(@client)
2018-03-17 18:26:18 +05:30
2017-08-17 22:00:37 +05:30
unless credentials
raise Projects::ImportService::Error,
"Unable to find project import data credentials for project ID: #{@project.id}"
end
2016-06-02 11:05:42 +05:30
2017-08-17 22:00:37 +05:30
opts = {}
# Gitea plan to be GitHub compliant
if project.gitea_import?
uri = URI.parse(project.import_url)
host = "#{uri.scheme}://#{uri.host}:#{uri.port}#{uri.path}".sub(%r{/?[\w-]+/[\w-]+\.git\z}, '')
opts = {
host: host,
api_version: 'v1'
}
2016-06-02 11:05:42 +05:30
end
2017-08-17 22:00:37 +05:30
2021-01-29 00:20:46 +05:30
@client = Client.new(credentials[:user], **opts)
2015-04-26 12:48:37 +05:30
end
def execute
2017-08-17 22:00:37 +05:30
# The ordering of importing is important here due to the way GitHub structures their data
# 1. Labels are required by other items while not having a dependency on anything else
# so need to be first
# 2. Pull requests must come before issues. Every pull request is also an issue but not
# all issues are pull requests. Only the issue entity has labels defined in GitHub. GitLab
# doesn't structure data like this so we need to make sure that we've created the MRs
# before we attempt to add the labels defined in the GitHub issue for the related, already
# imported, pull request
2016-09-13 17:45:13 +05:30
import_labels
import_milestones
import_pull_requests
2017-08-17 22:00:37 +05:30
import_issues
2016-11-03 12:29:30 +05:30
import_comments(:issues)
2019-09-04 21:01:54 +05:30
# Gitea doesn't have an API endpoint for pull requests comments
unless project.gitea_import?
import_comments(:pull_requests)
end
2016-09-13 17:45:13 +05:30
import_wiki
2017-08-17 22:00:37 +05:30
# Gitea doesn't have a Release API yet
# See https://github.com/go-gitea/gitea/issues/330
unless project.gitea_import?
import_releases
end
2016-09-13 17:45:13 +05:30
handle_errors
true
end
private
2016-06-02 11:05:42 +05:30
def credentials
2017-08-17 22:00:37 +05:30
return @credentials if defined?(@credentials)
@credentials = project.import_data ? project.import_data.credentials : nil
2016-06-02 11:05:42 +05:30
end
2016-09-13 17:45:13 +05:30
def handle_errors
return unless errors.any?
2019-02-15 15:39:39 +05:30
project.import_state.update_column(:last_error, {
2016-09-13 17:45:13 +05:30
message: 'The remote data could not be fully imported.',
errors: errors
}.to_json)
end
2016-06-02 11:05:42 +05:30
def import_labels
2016-11-03 12:29:30 +05:30
fetch_resources(:labels, repo, per_page: 100) do |labels|
labels.each do |raw|
2019-07-07 11:18:12 +05:30
gh_label = LabelFormatter.new(project, raw)
gh_label.create!
2021-06-08 01:23:25 +05:30
rescue StandardError => e
2019-07-07 11:18:12 +05:30
errors << { type: :label, url: Gitlab::UrlSanitizer.sanitize(gh_label.url), errors: e.message }
2016-09-13 17:45:13 +05:30
end
end
2017-08-17 22:00:37 +05:30
cache_labels!
2016-06-02 11:05:42 +05:30
end
def import_milestones
2016-11-03 12:29:30 +05:30
fetch_resources(:milestones, repo, state: :all, per_page: 100) do |milestones|
milestones.each do |raw|
2019-07-07 11:18:12 +05:30
gh_milestone = MilestoneFormatter.new(project, raw)
gh_milestone.create!
2021-06-08 01:23:25 +05:30
rescue StandardError => e
2019-07-07 11:18:12 +05:30
errors << { type: :milestone, url: Gitlab::UrlSanitizer.sanitize(gh_milestone.url), errors: e.message }
2016-09-13 17:45:13 +05:30
end
end
2016-06-02 11:05:42 +05:30
end
2018-12-05 23:21:45 +05:30
# rubocop: disable CodeReuse/ActiveRecord
def import_issues
2016-11-03 12:29:30 +05:30
fetch_resources(:issues, repo, state: :all, sort: :created, direction: :asc, per_page: 100) do |issues|
issues.each do |raw|
2017-08-17 22:00:37 +05:30
gh_issue = IssueFormatter.new(project, raw, client)
begin
issuable =
if gh_issue.pull_request?
MergeRequest.find_by(target_project_id: project.id, iid: gh_issue.number)
else
gh_issue.create!
end
apply_labels(issuable, raw)
2021-06-08 01:23:25 +05:30
rescue StandardError => e
2017-08-17 22:00:37 +05:30
errors << { type: :issue, url: Gitlab::UrlSanitizer.sanitize(gh_issue.url), errors: e.message }
2016-09-13 17:45:13 +05:30
end
end
end
end
2018-12-05 23:21:45 +05:30
# rubocop: enable CodeReuse/ActiveRecord
def import_pull_requests
2016-11-03 12:29:30 +05:30
fetch_resources(:pull_requests, repo, state: :all, sort: :created, direction: :asc, per_page: 100) do |pull_requests|
pull_requests.each do |raw|
2017-08-17 22:00:37 +05:30
gh_pull_request = PullRequestFormatter.new(project, raw, client)
next unless gh_pull_request.valid?
2016-11-03 12:29:30 +05:30
begin
2017-08-17 22:00:37 +05:30
restore_source_branch(gh_pull_request) unless gh_pull_request.source_branch_exists?
restore_target_branch(gh_pull_request) unless gh_pull_request.target_branch_exists?
merge_request = gh_pull_request.create!
2016-11-03 12:29:30 +05:30
2017-08-17 22:00:37 +05:30
# Gitea doesn't return PR in the Issue API endpoint, so labels must be assigned at this stage
if project.gitea_import?
apply_labels(merge_request, raw)
end
2021-06-08 01:23:25 +05:30
rescue StandardError => e
2017-08-17 22:00:37 +05:30
errors << { type: :pull_request, url: Gitlab::UrlSanitizer.sanitize(gh_pull_request.url), errors: e.message }
2016-11-03 12:29:30 +05:30
ensure
2017-08-17 22:00:37 +05:30
clean_up_restored_branches(gh_pull_request)
2016-11-03 12:29:30 +05:30
end
2016-09-13 17:45:13 +05:30
end
2015-04-26 12:48:37 +05:30
end
2016-11-03 12:29:30 +05:30
project.repository.after_remove_branch
end
2016-09-13 17:45:13 +05:30
def restore_source_branch(pull_request)
2017-08-17 22:00:37 +05:30
project.repository.create_branch(pull_request.source_branch_name, pull_request.source_branch_sha)
end
2016-09-13 17:45:13 +05:30
def restore_target_branch(pull_request)
project.repository.create_branch(pull_request.target_branch_name, pull_request.target_branch_sha)
2016-06-22 15:30:34 +05:30
end
2016-09-13 17:45:13 +05:30
def remove_branch(name)
project.repository.delete_branch(name)
2018-03-17 18:26:18 +05:30
rescue Gitlab::Git::Repository::DeleteBranchFailed
2016-09-13 17:45:13 +05:30
errors << { type: :remove_branch, name: name }
2015-04-26 12:48:37 +05:30
end
2016-09-13 17:45:13 +05:30
def clean_up_restored_branches(pull_request)
2017-08-17 22:00:37 +05:30
return if pull_request.opened?
2016-09-13 17:45:13 +05:30
remove_branch(pull_request.source_branch_name) unless pull_request.source_branch_exists?
remove_branch(pull_request.target_branch_name) unless pull_request.target_branch_exists?
2016-06-02 11:05:42 +05:30
end
2017-08-17 22:00:37 +05:30
def apply_labels(issuable, raw)
return unless raw.labels.count > 0
2016-11-03 12:29:30 +05:30
2017-08-17 22:00:37 +05:30
label_ids = raw.labels
.map { |attrs| @labels[attrs.name] }
.compact
2016-06-02 11:05:42 +05:30
2017-08-17 22:00:37 +05:30
issuable.update_attribute(:label_ids, label_ids)
2016-06-02 11:05:42 +05:30
end
2018-12-05 23:21:45 +05:30
# rubocop: disable CodeReuse/ActiveRecord
2016-11-03 12:29:30 +05:30
def import_comments(issuable_type)
resource_type = "#{issuable_type}_comments".to_sym
# Two notes here:
# 1. We don't have a distinctive attribute for comments (unlike issues iid), so we fetch the last inserted note,
# compare it against every comment in the current imported page until we find match, and that's where start importing
# 2. GH returns comments for _both_ issues and PRs through issues_comments API, while pull_requests_comments returns
# only comments on diffs, so select last note not based on noteable_type but on line_code
line_code_is = issuable_type == :pull_requests ? 'NOT NULL' : 'NULL'
last_note = project.notes.where("line_code IS #{line_code_is}").last
fetch_resources(resource_type, repo, per_page: 100) do |comments|
if last_note
discard_inserted_comments(comments, last_note)
last_note = nil
end
2015-04-26 12:48:37 +05:30
2016-11-03 12:29:30 +05:30
create_comments(comments)
end
end
2018-12-05 23:21:45 +05:30
# rubocop: enable CodeReuse/ActiveRecord
2018-12-05 23:21:45 +05:30
# rubocop: disable CodeReuse/ActiveRecord
2016-11-03 12:29:30 +05:30
def create_comments(comments)
2016-09-29 09:46:39 +05:30
ActiveRecord::Base.no_touching do
comments.each do |raw|
2019-07-07 11:18:12 +05:30
comment = CommentFormatter.new(project, raw, client)
2017-08-17 22:00:37 +05:30
2019-07-07 11:18:12 +05:30
# GH does not return info about comment's parent, so we guess it by checking its URL!
*_, parent, iid = URI(raw.html_url).path.split('/')
2017-08-17 22:00:37 +05:30
2019-07-07 11:18:12 +05:30
issuable = if parent == 'issues'
Issue.find_by(project_id: project.id, iid: iid)
else
MergeRequest.find_by(target_project_id: project.id, iid: iid)
end
2017-08-17 22:00:37 +05:30
2019-07-07 11:18:12 +05:30
next unless issuable
2016-11-03 12:29:30 +05:30
2019-07-07 11:18:12 +05:30
issuable.notes.create!(comment.attributes)
2021-06-08 01:23:25 +05:30
rescue StandardError => e
2019-07-07 11:18:12 +05:30
errors << { type: :comment, url: Gitlab::UrlSanitizer.sanitize(raw.url), errors: e.message }
2016-09-13 17:45:13 +05:30
end
end
2015-04-26 12:48:37 +05:30
end
2018-12-05 23:21:45 +05:30
# rubocop: enable CodeReuse/ActiveRecord
2016-11-03 12:29:30 +05:30
def discard_inserted_comments(comments, last_note)
last_note_attrs = nil
cut_off_index = comments.find_index do |raw|
comment = CommentFormatter.new(project, raw)
comment_attrs = comment.attributes
last_note_attrs ||= last_note.slice(*comment_attrs.keys)
comment_attrs.with_indifferent_access == last_note_attrs
end
# No matching resource in the collection, which means we got halted right on the end of the last page, so all good
return unless cut_off_index
# Otherwise, remove the resources we've already inserted
comments.shift(cut_off_index + 1)
end
def import_wiki
2020-04-08 14:13:33 +05:30
return if project.wiki.repository_exists?
wiki = WikiFormatter.new(project)
project.wiki.repository.import_repository(wiki.import_url)
rescue ::Gitlab::Git::CommandError => e
2016-04-02 18:10:28 +05:30
# GitHub error message when the wiki repo has not been created,
# this means that repo has wiki enabled, but have no pages. So,
# we can skip the import.
if e.message !~ /repository not exported/
2016-09-13 17:45:13 +05:30
errors << { type: :wiki, errors: e.message }
2016-01-29 22:53:50 +05:30
end
end
2016-09-29 09:46:39 +05:30
def import_releases
2016-11-03 12:29:30 +05:30
fetch_resources(:releases, repo, per_page: 100) do |releases|
releases.each do |raw|
2019-07-07 11:18:12 +05:30
gh_release = ReleaseFormatter.new(project, raw)
gh_release.create! if gh_release.valid?
2021-06-08 01:23:25 +05:30
rescue StandardError => e
2019-07-07 11:18:12 +05:30
errors << { type: :release, url: Gitlab::UrlSanitizer.sanitize(gh_release.url), errors: e.message }
2016-09-29 09:46:39 +05:30
end
end
end
2016-11-03 12:29:30 +05:30
2017-08-17 22:00:37 +05:30
def cache_labels!
project.labels.select(:id, :title).find_each do |label|
@labels[label.title] = label.id
end
end
2016-11-03 12:29:30 +05:30
def fetch_resources(resource_type, *opts)
return if imported?(resource_type)
2017-08-17 22:00:37 +05:30
opts.last[:page] = current_page(resource_type)
2016-11-03 12:29:30 +05:30
2018-03-17 18:26:18 +05:30
client.public_send(resource_type, *opts) do |resources| # rubocop:disable GitlabSecurity/PublicSend
2016-11-03 12:29:30 +05:30
yield resources
increment_page(resource_type)
end
imported!(resource_type)
2021-01-29 00:20:46 +05:30
rescue ::Octokit::NotFound => e
errors << { type: resource_type, errors: e.message }
2016-11-03 12:29:30 +05:30
end
def imported?(resource_type)
Rails.cache.read("#{cache_key_prefix}:#{resource_type}:imported")
end
def imported!(resource_type)
Rails.cache.write("#{cache_key_prefix}:#{resource_type}:imported", true, ex: 1.day)
end
def increment_page(resource_type)
key = "#{cache_key_prefix}:#{resource_type}:current-page"
# Rails.cache.increment calls INCRBY directly on the value stored under the key, which is
# a serialized ActiveSupport::Cache::Entry, so it will return an error by Redis, hence this ugly work-around
page = Rails.cache.read(key)
page += 1
Rails.cache.write(key, page)
page
end
def current_page(resource_type)
Rails.cache.fetch("#{cache_key_prefix}:#{resource_type}:current-page", ex: 1.day) { 1 }
end
def cache_key_prefix
@cache_key_prefix ||= "github-import:#{project.id}"
end
2015-04-26 12:48:37 +05:30
end
end
end