| 1 | # frozen_string_literal: true |
| 2 | |
| 3 | # The "Import from GitHub" experience: connect GitHub and pick repos, or paste a |
| 4 | # public git URL. Imports run off the request thread in RepositoryImportJob; this |
| 5 | # controller only validates, enforces limits, records RepositoryImport rows, and |
| 6 | # enqueues the work. |
| 7 | class ImportsController < ApplicationController |
| 8 | before_action :require_sign_in! |
| 9 | before_action :noindex! |
| 10 | |
| 11 | # Guardrails against abuse / one user saturating the workers. |
| 12 | MAX_ACTIVE_IMPORTS = Integer(ENV.fetch("IMPORT_MAX_ACTIVE_PER_USER", 10)) |
| 13 | MAX_USER_VOLUME_KB = Integer(ENV.fetch("IMPORT_MAX_USER_VOLUME_KB", 10_000_000)) # ~10 GB in flight |
| 14 | MAX_REPO_SIZE_KB = RepositoryImportService::DEFAULT_MAX_SIZE_KB |
| 15 | |
| 16 | # GET /import |
| 17 | def new |
| 18 | @connection = current_user.github_connection |
| 19 | @recent_imports = current_user.repository_imports.recent.limit(20) |
| 20 | @github_repos = load_github_repos(@connection) if @connection |
| 21 | end |
| 22 | |
| 23 | # GET /import (list-only, e.g. progress polling of all imports) |
| 24 | def index |
| 25 | @imports = current_user.repository_imports.recent.limit(50) |
| 26 | end |
| 27 | |
| 28 | # GET /import/:id — progress for a single import |
| 29 | def show |
| 30 | @import = current_user.repository_imports.find(params[:id]) |
| 31 | rescue ActiveRecord::RecordNotFound |
| 32 | redirect_to new_import_path, alert: "Import not found." |
| 33 | end |
| 34 | |
| 35 | # POST /import |
| 36 | # Either: |
| 37 | # source=github, repos[]=owner/name..., mode=migrate|mirror |
| 38 | # source=url, url=..., name=..., mode=..., visibility=public|private |
| 39 | def create |
| 40 | mode = params[:mode].to_s == "mirror" ? "mirror" : "migrate" |
| 41 | |
| 42 | specs = |
| 43 | if params[:source].to_s == "url" |
| 44 | build_url_spec(mode) |
| 45 | else |
| 46 | build_github_specs(mode) |
| 47 | end |
| 48 | |
| 49 | return if performed? # a builder already redirected with an error |
| 50 | if specs.blank? |
| 51 | return redirect_to new_import_path, alert: "Select at least one repository to import." |
| 52 | end |
| 53 | |
| 54 | enqueue_imports(specs) |
| 55 | end |
| 56 | |
| 57 | # POST /import/:id/retry |
| 58 | def retry |
| 59 | import = current_user.repository_imports.find(params[:id]) |
| 60 | unless import.retryable? |
| 61 | return redirect_to import_path(import), alert: "This import can't be retried." |
| 62 | end |
| 63 | |
| 64 | import.update!(status: "queued", error_message: nil, started_at: nil, finished_at: nil) |
| 65 | RepositoryImportJob.perform_later(import.id) |
| 66 | redirect_to import_path(import), notice: "Retrying import." |
| 67 | rescue ActiveRecord::RecordNotFound |
| 68 | redirect_to new_import_path, alert: "Import not found." |
| 69 | end |
| 70 | |
| 71 | private |
| 72 | |
| 73 | # Builds a single import spec from the by-URL form. Validates the URL (SSRF |
| 74 | # guard) and the target name. Redirects with an error on invalid input. |
| 75 | def build_url_spec(mode) |
| 76 | url = ImportUrlValidator.validate!(params[:url]) |
| 77 | host = URI.parse(url).host |
| 78 | name = params[:name].presence || derive_name_from_url(url) |
| 79 | |
| 80 | [ { source_url: url, source_host: host, mode: mode, |
| 81 | target_name: name, target_private: false, size_kb: nil, |
| 82 | description: nil, default_branch: nil } ] |
| 83 | rescue ImportUrlValidator::InvalidUrl => e |
| 84 | redirect_to new_import_path, alert: e.message |
| 85 | nil |
| 86 | end |
| 87 | |
| 88 | # Builds import specs from selected GitHub repos. Reads fresh metadata from |
| 89 | # GitHub so we capture the real visibility/size/default branch (never trusting |
| 90 | # client-supplied values for security-relevant fields like private). |
| 91 | def build_github_specs(mode) |
| 92 | selected = Array(params[:repos]).reject(&:blank?).uniq |
| 93 | return [] if selected.empty? |
| 94 | |
| 95 | connection = current_user.github_connection |
| 96 | return redirect_to(new_import_path, alert: "Connect GitHub first.") && nil if connection.nil? |
| 97 | |
| 98 | client = connection.api_client |
| 99 | selected.filter_map do |full_name| |
| 100 | meta = client.repository(full_name) |
| 101 | next if meta.nil? |
| 102 | |
| 103 | { |
| 104 | source_url: meta[:clone_url], |
| 105 | source_host: "github.com", |
| 106 | mode: mode, |
| 107 | target_name: meta[:name], |
| 108 | target_private: !!meta[:private], |
| 109 | size_kb: meta[:size_kb], |
| 110 | description: meta[:description], |
| 111 | default_branch: meta[:default_branch] |
| 112 | } |
| 113 | end |
| 114 | rescue GithubApiClient::RateLimited |
| 115 | redirect_to new_import_path, alert: "GitHub rate limit reached. Please try again shortly." |
| 116 | nil |
| 117 | rescue GithubApiClient::Error |
| 118 | redirect_to new_import_path, alert: "Couldn't read repositories from GitHub. Please try again." |
| 119 | nil |
| 120 | end |
| 121 | |
| 122 | # Applies caps, resolves name collisions, creates the RepositoryImport rows, |
| 123 | # and enqueues one job per import. Redirects with a summary. |
| 124 | def enqueue_imports(specs) |
| 125 | active = current_user.repository_imports.active.count |
| 126 | volume = current_user.active_import_size_kb |
| 127 | |
| 128 | created = [] |
| 129 | rejected = [] |
| 130 | |
| 131 | specs.each do |spec| |
| 132 | if spec[:size_kb] && spec[:size_kb] > MAX_REPO_SIZE_KB |
| 133 | rejected << "#{spec[:target_name]} (too large: #{(spec[:size_kb] / 1024.0).round} MB)" |
| 134 | next |
| 135 | end |
| 136 | if active + created.length >= MAX_ACTIVE_IMPORTS |
| 137 | rejected << "#{spec[:target_name]} (import queue full — try again later)" |
| 138 | next |
| 139 | end |
| 140 | if volume + (spec[:size_kb] || 0) > MAX_USER_VOLUME_KB |
| 141 | rejected << "#{spec[:target_name]} (would exceed your in-flight import limit)" |
| 142 | next |
| 143 | end |
| 144 | |
| 145 | import = current_user.repository_imports.create!( |
| 146 | source_url: spec[:source_url], |
| 147 | source_host: spec[:source_host], |
| 148 | mode: spec[:mode], |
| 149 | target_name: unique_repo_name(spec[:target_name]), |
| 150 | target_private: spec[:target_private], |
| 151 | description: spec[:description], |
| 152 | default_branch: spec[:default_branch], |
| 153 | source_size_kb: spec[:size_kb], |
| 154 | status: "queued" |
| 155 | ) |
| 156 | RepositoryImportJob.perform_later(import.id) |
| 157 | created << import |
| 158 | volume += (spec[:size_kb] || 0) |
| 159 | end |
| 160 | |
| 161 | notice = created.any? ? "Queued #{created.length} import#{'s' if created.length != 1}." : nil |
| 162 | alert = rejected.any? ? "Skipped: #{rejected.join('; ')}." : nil |
| 163 | |
| 164 | if created.length == 1 && rejected.empty? |
| 165 | redirect_to import_path(created.first), notice: notice |
| 166 | else |
| 167 | redirect_to new_import_path, notice: notice, alert: alert |
| 168 | end |
| 169 | end |
| 170 | |
| 171 | # Ensures the target name doesn't collide with an existing repo (or another |
| 172 | # queued import) by appending -1, -2, … This makes bulk imports and retries |
| 173 | # idempotent rather than failing on the unique (user, name) index. |
| 174 | def unique_repo_name(base) |
| 175 | base = base.to_s.gsub(/[^a-zA-Z0-9._-]/, "-").gsub(/-{2,}/, "-").gsub(/\A[-.]+|[-.]+\z/, "") |
| 176 | base = "imported-repo" if base.blank? |
| 177 | |
| 178 | taken = current_user.repositories.pluck(:name).map(&:downcase).to_set |
| 179 | taken.merge(current_user.repository_imports.active.pluck(:target_name).map(&:downcase)) |
| 180 | |
| 181 | return base unless taken.include?(base.downcase) |
| 182 | |
| 183 | (1..1000).each do |n| |
| 184 | candidate = "#{base}-#{n}" |
| 185 | return candidate unless taken.include?(candidate.downcase) |
| 186 | end |
| 187 | "#{base}-#{SecureRandom.hex(3)}" |
| 188 | end |
| 189 | |
| 190 | def derive_name_from_url(url) |
| 191 | File.basename(URI.parse(url).path.to_s).sub(/\.git\z/, "").presence || "imported-repo" |
| 192 | end |
| 193 | |
| 194 | # Lists the user's GitHub repos for the picker. Cached briefly so re-rendering |
| 195 | # the page (and Turbo revisits) don't re-hit GitHub. Never blocks the page on a |
| 196 | # rate-limit/outage — returns nil and the view shows a fallback. |
| 197 | def load_github_repos(connection) |
| 198 | Rails.cache.fetch("github_repos/#{connection.id}/#{connection.updated_at.to_i}", expires_in: 5.minutes) do |
| 199 | connection.api_client.list_repositories |
| 200 | end |
| 201 | rescue GithubApiClient::RateLimited, GithubApiClient::Error, GithubApiClient::Unauthorized |
| 202 | nil |
| 203 | end |
| 204 | end |