Merge branch 'fix/make-github-import-retryable' into 'master'

Modify GitHub importer to be retryable

Closes #23533

See merge request !7003

8 files changed, 112 insertions, 23 deletions

diff --git a/lib/gitlab/github_import/base_formatter.rb b/lib/gitlab/github_import/base_formatter.rb
index 8cacf4f4925..6dbae64a9fe 100644
--- a/lib/gitlab/github_import/base_formatter.rb
+++ b/lib/gitlab/github_import/base_formatter.rb
@@ -10,7 +10,9 @@ module Gitlab
       end
 
       def create!
-        self.klass.create!(self.attributes)
+        project.public_send(project_association).find_or_create_by!(find_condition) do |record|
+          record.attributes = attributes
+        end
       end
 
       private
diff --git a/lib/gitlab/github_import/client.rb b/lib/gitlab/github_import/client.rb
index 348005d5659..85df6547a67 100644
--- a/lib/gitlab/github_import/client.rb
+++ b/lib/gitlab/github_import/client.rb
@@ -110,7 +110,7 @@ module Gitlab
         if block_given?
           yield data
           # api.last_response could change while we're yielding (e.g. fetching labels for each PR)
-          # so we cache our own last request
+          # so we cache our own last response
           each_response_page(last_response, &block)
         else
           each_response_page(last_response) { |page| data.concat(page) }
diff --git a/lib/gitlab/github_import/importer.rb b/lib/gitlab/github_import/importer.rb
index 27946dff608..ecc28799737 100644
--- a/lib/gitlab/github_import/importer.rb
+++ b/lib/gitlab/github_import/importer.rb
@@ -24,7 +24,8 @@ module Gitlab
         import_milestones
         import_issues
         import_pull_requests
-        import_comments
+        import_comments(:issues)
+        import_comments(:pull_requests)
         import_wiki
         import_releases
         handle_errors
@@ -48,7 +49,7 @@ module Gitlab
       end
 
       def import_labels
-        client.labels(repo, per_page: 100) do |labels|
+        fetch_resources(:labels, repo, per_page: 100) do |labels|
           labels.each do |raw|
             begin
               label = LabelFormatter.new(project, raw).create!
@@ -61,7 +62,7 @@ module Gitlab
       end
 
       def import_milestones
-        client.milestones(repo, state: :all, per_page: 100) do |milestones|
+        fetch_resources(:milestones, repo, state: :all, per_page: 100) do |milestones|
           milestones.each do |raw|
             begin
               MilestoneFormatter.new(project, raw).create!
@@ -73,7 +74,7 @@ module Gitlab
       end
 
       def import_issues
-        client.issues(repo, state: :all, sort: :created, direction: :asc, per_page: 100) do |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)
 
@@ -90,7 +91,7 @@ module Gitlab
       end
 
       def import_pull_requests
-        client.pull_requests(repo, state: :all, sort: :created, direction: :asc, per_page: 100) do |pull_requests|
+        fetch_resources(:pull_requests, repo, state: :all, sort: :created, direction: :asc, per_page: 100) do |pull_requests|
           pull_requests.each do |raw|
             pull_request = PullRequestFormatter.new(project, raw)
             next unless pull_request.valid?
@@ -148,12 +149,23 @@ module Gitlab
         end
       end
 
-      def import_comments
-        client.issues_comments(repo, per_page: 100) do |comments|
-          create_comments(comments)
-        end
+      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
 
-        client.pull_requests_comments(repo, per_page: 100) do |comments|
           create_comments(comments)
         end
       end
@@ -177,6 +189,24 @@ module Gitlab
         end
       end
 
+      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
         unless project.wiki.repository_exists?
           wiki = WikiFormatter.new(project)
@@ -192,7 +222,7 @@ module Gitlab
       end
 
       def import_releases
-        client.releases(repo, per_page: 100) do |releases|
+        fetch_resources(:releases, repo, per_page: 100) do |releases|
           releases.each do |raw|
             begin
               gh_release = ReleaseFormatter.new(project, raw)
@@ -203,6 +233,47 @@ module Gitlab
           end
         end
       end
+
+      def fetch_resources(resource_type, *opts)
+        return if imported?(resource_type)
+
+        opts.last.merge!(page: current_page(resource_type))
+
+        client.public_send(resource_type, *opts) do |resources|
+          yield resources
+          increment_page(resource_type)
+        end
+
+        imported!(resource_type)
+      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
diff --git a/lib/gitlab/github_import/issue_formatter.rb b/lib/gitlab/github_import/issue_formatter.rb
index 77621de9f4c..8c32ac59fc5 100644
--- a/lib/gitlab/github_import/issue_formatter.rb
+++ b/lib/gitlab/github_import/issue_formatter.rb
@@ -20,8 +20,12 @@ module Gitlab
         raw_data.comments > 0
       end
 
-      def klass
-        Issue
+      def project_association
+        :issues
+      end
+
+      def find_condition
+        { iid: number }
       end
 
       def number
diff --git a/lib/gitlab/github_import/label_formatter.rb b/lib/gitlab/github_import/label_formatter.rb
index 942dfb3312b..002494739e9 100644
--- a/lib/gitlab/github_import/label_formatter.rb
+++ b/lib/gitlab/github_import/label_formatter.rb
@@ -9,8 +9,8 @@ module Gitlab
         }
       end
 
-      def klass
-        Label
+      def project_association
+        :labels
       end
 
       def create!
diff --git a/lib/gitlab/github_import/milestone_formatter.rb b/lib/gitlab/github_import/milestone_formatter.rb
index b2fa524cf5b..401dd962521 100644
--- a/lib/gitlab/github_import/milestone_formatter.rb
+++ b/lib/gitlab/github_import/milestone_formatter.rb
@@ -14,8 +14,12 @@ module Gitlab
         }
       end
 
-      def klass
-        Milestone
+      def project_association
+        :milestones
+      end
+
+      def find_condition
+        { iid: raw_data.number }
       end
 
       private
diff --git a/lib/gitlab/github_import/pull_request_formatter.rb b/lib/gitlab/github_import/pull_request_formatter.rb
index 1408683100f..b9a227fb11a 100644
--- a/lib/gitlab/github_import/pull_request_formatter.rb
+++ b/lib/gitlab/github_import/pull_request_formatter.rb
@@ -24,8 +24,12 @@ module Gitlab
         }
       end
 
-      def klass
-        MergeRequest
+      def project_association
+        :merge_requests
+      end
+
+      def find_condition
+        { iid: number }
       end
 
       def number
diff --git a/lib/gitlab/github_import/release_formatter.rb b/lib/gitlab/github_import/release_formatter.rb
index 73d643b00ad..1ad702a6058 100644
--- a/lib/gitlab/github_import/release_formatter.rb
+++ b/lib/gitlab/github_import/release_formatter.rb
@@ -11,8 +11,12 @@ module Gitlab
         }
       end
 
-      def klass
-        Release
+      def project_association
+        :releases
+      end
+
+      def find_condition
+        { tag: raw_data.tag_name }
       end
 
       def valid?