gdkbox 0.1.12 → 0.1.13

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b71b4f7e72836332b32feca0a6e3e0c485f8255fcfb0f1dc93c7792c3f6fc5ab
-  data.tar.gz: 66e0331f211fd1df2b67694e42e65d8971502615b42c61093f86a3a465e06425
+  metadata.gz: 8df6faa5d2c2a7a0fe888195af92305774354b997ef5e0e2d1a7ee61469b60bf
+  data.tar.gz: 4c859a064721f68cdadc7a7140dc73b0d3a179a57fe3b538c63699c021115109
 SHA512:
-  metadata.gz: b70d9d914b6ce31f0a644cae9260a98adb3540b0d76555a1ed4e72fc423b9602deb84b338b1b91cf29bf455546b248e875dbfa2e7fdc5dafc9b37322cb2d58be
-  data.tar.gz: 73ebbfbfb11732b3d5fb9f40ea0d795a846c61ccb24d513c51684542424d2d78a7eef919e03d5d2007f64df3c3f0704cb75f07dbc3e7b494f90f9ae892daec43
+  metadata.gz: 9ebd61583a5e01145206ba5407e2fbaad1cf456bbfbb040ecc58e66d0d471c3a5566fca4d194467f9dcc988f5540f57f54c73edf96ac5805248a3c34996f4095
+  data.tar.gz: fd01809df5f90d1eff5229918f424c311577f15a756ea32328157ebdcaf237e5d1c998a1db87d004a07dbc77be413c4260cc17baaa9db58248f5087cd3488467

data/lib/gdkbox/box.rb

@@ -1,5 +1,6 @@
 # frozen_string_literal: true
 
+require "shellwords"
 require "time"
 
 module GDKBox
@@ -209,22 +210,58 @@ module GDKBox
       url
     end
 
+    # The hydrate fetch, run inside the box. The filter is passed to `git
+    # fetch` directly and only persisted to config after the fetch succeeds
+    # (and, for a full hydrate, the previous filter is put back on failure),
+    # so an interrupted hydrate cannot leave the config claiming objects the
+    # store does not have (issue #8).
+    HYDRATE_SCRIPT = <<~'BASH'
+      set -e
+      if [ -n "$GDKBOX_HYDRATE_FILTER" ]; then
+        git fetch --refetch --progress --filter="$GDKBOX_HYDRATE_FILTER" origin
+        git config remote.origin.partialclonefilter "$GDKBOX_HYDRATE_FILTER"
+      else
+        prev=$(git config --get remote.origin.partialclonefilter || true)
+        git config --unset-all remote.origin.partialclonefilter || true
+        if ! git fetch --refetch --progress origin; then
+          if [ -n "$prev" ]; then git config remote.origin.partialclonefilter "$prev"; fi
+          echo "hydrate: fetch failed; previous filter config restored" >&2
+          exit 1
+        fi
+        git config --unset remote.origin.promisor || true
+      fi
+    BASH
+
     # Backfill the box's treeless GitLab clone so deep-history operations
     # (old rebases, blame, bisect) work. trees: true fetches only the missing
-    # trees (much smaller; file contents stay lazy). Prepares the SSH client
-    # first when origin is an SSH remote — a refetch without multiplexing
-    # would hit the same throttling the lazy fetches do. Streams git's
-    # progress lines to the block.
+    # trees (much smaller; file contents stay lazy).
+    #
+    # The fetch runs over SSH (`ssh -F <generated config> <alias>`), not
+    # `docker exec`: the remote is typically git@gitlab.com, and only an SSH
+    # session carries the user's forwarded agent — docker exec has no
+    # SSH_AUTH_SOCK, so it cannot authenticate at all (issue #8). The SSH
+    # client stanza (host key + multiplexing) is seeded first for SSH
+    # origins. Streams git's progress lines to the block; raises
+    # CommandError when the fetch fails.
     def hydrate!(trees: false, &progress)
-      provisioner = Provisioner.new(docker: @docker, config: @config)
       origin = @docker.exec(
         container_name, "git remote get-url origin",
         user: @config.ssh_user, workdir: @config.gitlab_checkout_path
       ).stdout.strip
       if (host = self.class.remote_ssh_host(origin))
-        provisioner.setup_git_ssh(container_name, host)
+        Provisioner.new(docker: @docker, config: @config)
+          .setup_git_ssh(container_name, host)
       end
-      provisioner.hydrate(container_name, trees: trees, &progress)
+
+      filter = trees ? "blob:none" : ""
+      remote_cmd = "cd #{Shellwords.escape(@config.gitlab_checkout_path)} && " \
+        "GDKBOX_HYDRATE_FILTER=#{Shellwords.escape(filter)} " \
+        "bash -c #{Shellwords.escape(HYDRATE_SCRIPT)}"
+      argv = ["ssh", "-F", @config.ssh_config_path, ssh_host_alias, remote_cmd]
+      result = @shell.stream_tty(*argv, &progress)
+      raise CommandError.new(argv, result.status, "") unless result.success?
+
+      result
     end
 
     # Seed a git identity into the box so `git commit` works there. Falls back

data/lib/gdkbox/docker.rb

@@ -223,21 +223,6 @@ module GDKBox
       check ? @shell.run!(*cmd, input: input) : @shell.run(*cmd, input: input)
     end
 
-    # Like #exec, but for long-running scripts whose output should be seen
-    # live (e.g. a multi-GB git fetch): runs under a PTY and yields each
-    # output line as it appears. Raises CommandError on a non-zero exit.
-    def exec_stream(name, script, user: nil, workdir: nil, env: {}, &block)
-      cmd = ["docker", "exec"]
-      cmd.push("-u", user) if user
-      cmd.push("-w", workdir) if workdir
-      env.each { |key, value| cmd.push("-e", "#{key}=#{value}") }
-      cmd.push(name, "bash", "-lc", script)
-      result = @shell.stream_tty(*cmd, &block)
-      raise CommandError.new(cmd, result.status, "") unless result.success?
-
-      result
-    end
-
     # Copy a host path into a container at dest (a full destination path).
     def cp_into(name, src, dest)
       @shell.run!("docker", "cp", src, "#{name}:#{dest}")

data/lib/gdkbox/provisioner.rb

@@ -183,27 +183,6 @@ module GDKBox
       git fetch --quiet origin
     BASH
 
-    # Backfills the treeless GitLab clone (the image clones with
-    # --filter=tree:0, so operations spanning a large history gap storm the
-    # network with lazy fetches and fail; see #7). Two levels:
-    #
-    # - GDKBOX_HYDRATE_FILTER=blob:none — fetch all missing trees, keep file
-    #   contents lazy. A fraction of the download; enough for deep rebases,
-    #   which mostly storm tree fetches.
-    # - no filter (full) — fetch everything and drop the promisor config;
-    #   the repository behaves like a normal full clone afterwards.
-    HYDRATE = <<~'BASH'
-      set -e
-      if [ -n "$GDKBOX_HYDRATE_FILTER" ]; then
-        git config remote.origin.partialclonefilter "$GDKBOX_HYDRATE_FILTER"
-        git fetch --refetch --progress origin
-      else
-        git config --unset-all remote.origin.partialclonefilter || true
-        git fetch --refetch --progress origin
-        git config --unset remote.origin.promisor || true
-      fi
-    BASH
-
     def initialize(docker:, config:)
       @docker = docker
       @config = config
@@ -252,18 +231,6 @@ module GDKBox
       )
     end
 
-    # Hydrate the GitLab checkout, streaming git's progress lines to the
-    # block. trees: true fetches trees only (blobs stay lazy).
-    def hydrate(container_name, trees: false, &block)
-      @docker.exec_stream(
-        container_name, HYDRATE,
-        user: @config.ssh_user,
-        workdir: @config.gitlab_checkout_path,
-        env: { "GDKBOX_HYDRATE_FILTER" => (trees ? "blob:none" : "") },
-        &block
-      )
-    end
-
     def setup_git_ssh(container_name, host)
       @docker.exec(
         container_name, GIT_SSH_SETUP,

data/lib/gdkbox/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module GDKBox
-  VERSION = "0.1.12"
+  VERSION = "0.1.13"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: gdkbox
 version: !ruby/object:Gem::Version
-  version: 0.1.12
+  version: 0.1.13
 platform: ruby
 authors:
 - jotolo