1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
|
# frozen_string_literal: true
module Gitlab
module LegacyGithubImport
class Importer
def self.refmap
Gitlab::GithubImport.refmap
end
attr_reader :errors, :project, :repo, :repo_url
def initialize(project)
@project = project
@repo = project.import_source
@repo_url = project.import_url
@errors = []
@labels = {}
end
def client
return @client if defined?(@client)
unless credentials
raise Projects::ImportService::Error,
"Unable to find project import data credentials for project ID: #{@project.id}"
end
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'
}
end
@client = Client.new(credentials[:user], **opts)
end
def execute
# 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
import_labels
import_milestones
import_pull_requests
import_issues
import_comments(:issues)
# Gitea doesn't have an API endpoint for pull requests comments
unless project.gitea_import?
import_comments(:pull_requests)
end
import_wiki
# Gitea doesn't have a Release API yet
# See https://github.com/go-gitea/gitea/issues/330
# On re-enabling care should be taken to include releases `author_id` field and enable corresponding tests.
# See:
# 1) https://gitlab.com/gitlab-org/gitlab/-/issues/343448#note_985979730
# 2) https://gitlab.com/gitlab-org/gitlab/-/merge_requests/89694/diffs#dfc4a8141aa296465ea3c50b095a30292fb6ebc4_180_182
unless project.gitea_import?
import_releases
end
handle_errors
true
end
private
def credentials
return @credentials if defined?(@credentials)
@credentials = project.import_data ? project.import_data.credentials : nil
end
def handle_errors
return unless errors.any?
project.import_state.update_column(:last_error, {
message: 'The remote data could not be fully imported.',
errors: errors
}.to_json)
end
def import_labels
fetch_resources(:labels, repo, per_page: 100) do |labels|
labels.each do |raw|
gh_label = LabelFormatter.new(project, raw)
gh_label.create!
rescue StandardError => e
errors << { type: :label, url: Gitlab::UrlSanitizer.sanitize(gh_label.url), errors: e.message }
end
end
cache_labels!
end
def import_milestones
fetch_resources(:milestones, repo, state: :all, per_page: 100) do |milestones|
milestones.each do |raw|
gh_milestone = MilestoneFormatter.new(project, raw)
gh_milestone.create!
rescue StandardError => e
errors << { type: :milestone, url: Gitlab::UrlSanitizer.sanitize(gh_milestone.url), errors: e.message }
end
end
end
# rubocop: disable CodeReuse/ActiveRecord
def import_issues
fetch_resources(:issues, repo, state: :all, sort: :created, direction: :asc, per_page: 100) do |issues|
issues.each do |raw|
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)
rescue StandardError => e
errors << { type: :issue, url: Gitlab::UrlSanitizer.sanitize(gh_issue.url), errors: e.message }
end
end
end
end
# rubocop: enable CodeReuse/ActiveRecord
def import_pull_requests
fetch_resources(:pull_requests, repo, state: :all, sort: :created, direction: :asc, per_page: 100) do |pull_requests|
pull_requests.each do |raw|
gh_pull_request = PullRequestFormatter.new(project, raw, client)
next unless gh_pull_request.valid?
begin
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!
# 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
rescue StandardError => e
errors << { type: :pull_request, url: Gitlab::UrlSanitizer.sanitize(gh_pull_request.url), errors: e.message }
ensure
clean_up_restored_branches(gh_pull_request)
end
end
end
project.repository.after_remove_branch
end
def restore_source_branch(pull_request)
project.repository.create_branch(pull_request.source_branch_name, pull_request.source_branch_sha)
end
def restore_target_branch(pull_request)
project.repository.create_branch(pull_request.target_branch_name, pull_request.target_branch_sha)
end
def remove_branch(name)
project.repository.delete_branch(name)
rescue Gitlab::Git::Repository::DeleteBranchFailed
errors << { type: :remove_branch, name: name }
end
def clean_up_restored_branches(pull_request)
return if pull_request.opened?
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?
end
def apply_labels(issuable, raw)
return unless raw.labels.count > 0
label_ids = raw.labels
.map { |attrs| @labels[attrs.name] }
.compact
issuable.update_attribute(:label_ids, label_ids)
end
# rubocop: disable CodeReuse/ActiveRecord
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
create_comments(comments)
end
end
# rubocop: enable CodeReuse/ActiveRecord
# rubocop: disable CodeReuse/ActiveRecord
def create_comments(comments)
ActiveRecord::Base.no_touching do
comments.each do |raw|
comment = CommentFormatter.new(project, raw, client)
# 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('/')
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
next unless issuable
issuable.notes.create!(comment.attributes)
rescue StandardError => e
errors << { type: :comment, url: Gitlab::UrlSanitizer.sanitize(raw.url), errors: e.message }
end
end
end
# rubocop: enable CodeReuse/ActiveRecord
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
return if project.wiki.repository_exists?
wiki = WikiFormatter.new(project)
project.wiki.repository.import_repository(wiki.import_url)
rescue ::Gitlab::Git::CommandError => e
# 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/
errors << { type: :wiki, errors: e.message }
end
end
def import_releases
fetch_resources(:releases, repo, per_page: 100) do |releases|
releases.each do |raw|
gh_release = ReleaseFormatter.new(project, raw)
gh_release.create! if gh_release.valid?
rescue StandardError => e
errors << { type: :release, url: Gitlab::UrlSanitizer.sanitize(gh_release.url), errors: e.message }
end
end
end
def cache_labels!
project.labels.select(:id, :title).find_each do |label|
@labels[label.title] = label.id
end
end
def fetch_resources(resource_type, *opts)
return if imported?(resource_type)
opts.last[:page] = current_page(resource_type)
client.public_send(resource_type, *opts) do |resources| # rubocop:disable GitlabSecurity/PublicSend
yield resources
increment_page(resource_type)
end
imported!(resource_type)
rescue ::Octokit::NotFound => e
errors << { type: resource_type, errors: e.message }
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
end
end
end
|