josh-sync/lib/onboard.sh

#!/usr/bin/env bash
# lib/onboard.sh — Onboard orchestration and PR migration
#
# Provides:
#   onboard_flow()      — Interactive: import → wait for merge → reset to new repo
#   migrate_one_pr()    — Migrate a single PR from archived repo to new repo
#
# Onboard state is stored on the josh-sync-state branch at <target>/onboard.json.
# Steps: start → importing → waiting-for-merge → resetting → complete
#
# Requires: lib/core.sh, lib/config.sh, lib/auth.sh, lib/state.sh, lib/sync.sh sourced
# Expects: JOSH_SYNC_TARGET_NAME, BOT_NAME, BOT_EMAIL, SUBREPO_API, SUBREPO_TOKEN, etc.

# ─── Onboard State Helpers ────────────────────────────────────────
# Follow the same pattern as read_state()/write_state() in lib/state.sh.

read_onboard_state() {
  local target_name="${1:-$JOSH_SYNC_TARGET_NAME}"
  git fetch origin "$STATE_BRANCH" 2>/dev/null || true
  git show "origin/${STATE_BRANCH}:${target_name}/onboard.json" 2>/dev/null || echo '{}'
}

write_onboard_state() {
  local target_name="${1:-$JOSH_SYNC_TARGET_NAME}"
  local state_json="$2"
  local key="${target_name}/onboard"
  local tmp_dir
  tmp_dir=$(mktemp -d)

  if git rev-parse "origin/${STATE_BRANCH}" >/dev/null 2>&1; then
    git worktree add "$tmp_dir" "origin/${STATE_BRANCH}" 2>/dev/null
  else
    git worktree add --detach "$tmp_dir" 2>/dev/null
    (cd "$tmp_dir" && git checkout --orphan "$STATE_BRANCH" && { git rm -rf . 2>/dev/null || true; })
  fi

  mkdir -p "$(dirname "${tmp_dir}/${key}.json")"
  echo "$state_json" | jq '.' > "${tmp_dir}/${key}.json"

  (
    cd "$tmp_dir" || exit
    git add -A
    if ! git diff --cached --quiet 2>/dev/null; then
      git -c user.name="$BOT_NAME" -c user.email="$BOT_EMAIL" \
        commit -m "onboard: update ${target_name}"
      git push origin "HEAD:${STATE_BRANCH}" || log "WARN" "Failed to push onboard state"
    fi
  )

  git worktree remove "$tmp_dir" 2>/dev/null || rm -rf "$tmp_dir"
}

# ─── Derive Archived API URL ─────────────────────────────────────
# Given a URL like "git@host:org/repo-archived.git" or
# "https://host/org/repo-archived.git", derive the Gitea API URL.

_archived_api_from_url() {
  local url="$1"
  # Strip .git suffix first — avoids non-greedy regex issues in POSIX ERE
  url="${url%.git}"
  local host repo_path

  if echo "$url" | grep -qE '^(ssh://|git@)'; then
    # SSH URL
    if echo "$url" | grep -q '^ssh://'; then
      host=$(echo "$url" | sed -E 's|ssh://[^@]*@([^/]+)/.*|\1|')
      repo_path=$(echo "$url" | sed -E 's|ssh://[^@]*@[^/]+/(.+)$|\1|')
    else
      host=$(echo "$url" | sed -E 's|git@([^:/]+)[:/].*|\1|')
      repo_path=$(echo "$url" | sed -E 's|git@[^:/]+[:/](.+)$|\1|')
    fi
  else
    # HTTPS URL
    host=$(echo "$url" | sed -E 's|https?://([^/]+)/.*|\1|')
    repo_path=$(echo "$url" | sed -E 's|https?://[^/]+/(.+)$|\1|')
  fi

  echo "https://${host}/api/v1/repos/${repo_path}"
}

# ─── Onboard Flow ────────────────────────────────────────────────
# Interactive orchestrator with checkpoint/resume.
# Usage: onboard_flow <target_json> <restart>

onboard_flow() {
  local target_json="$1"
  local restart="${2:-false}"
  local target_name="$JOSH_SYNC_TARGET_NAME"

  # Load existing onboard state (or empty)
  local onboard_state
  onboard_state=$(read_onboard_state "$target_name")
  local current_step
  current_step=$(echo "$onboard_state" | jq -r '.step // "start"')

  if [ "$restart" = true ]; then
    log "INFO" "Restarting onboard from scratch"
    current_step="start"
    onboard_state='{}'
  fi

  log "INFO" "Onboard step: ${current_step}"

  # ── Step 1: Prerequisites + archived repo info ──
  if [ "$current_step" = "start" ]; then
    echo "" >&2
    echo "=== Onboarding ${target_name} ===" >&2
    echo "" >&2
    echo "Before proceeding, you should have:" >&2
    echo "  1. Renamed the existing subrepo (e.g., storefront → storefront-archived)" >&2
    echo "  2. Created a new EMPTY repo at the original URL" >&2
    echo "" >&2

    # Verify the new (empty) subrepo is reachable (no HEAD ref — works on empty repos)
    if git ls-remote "$(subrepo_auth_url)" >/dev/null 2>&1; then
      # shellcheck disable=SC2001  # sed is clearer for URL pattern replacement
      log "INFO" "New subrepo is reachable at $(echo "$SUBREPO_URL" | sed 's|://[^@]*@|://***@|')"
    else
      log "WARN" "New subrepo is not reachable — make sure you created the new empty repo"
    fi

    echo "Enter the archived repo URL (e.g., git@host:org/repo-archived.git):" >&2
    local archived_url
    read -r archived_url
    [ -n "$archived_url" ] || die "Archived URL is required"

    # Determine auth type for archived repo (same as current subrepo)
    local archived_auth="${SUBREPO_AUTH:-https}"

    # Derive API URL
    local archived_api
    archived_api=$(_archived_api_from_url "$archived_url")

    # Verify archived repo is reachable via API
    if curl -sf -H "Authorization: token ${SUBREPO_TOKEN}" \
      "${archived_api}" >/dev/null 2>&1; then
      log "INFO" "Archived repo reachable: ${archived_api}"
    else
      log "WARN" "Cannot reach archived repo API — check URL and token"
      echo "Continue anyway? (y/N):" >&2
      local confirm
      read -r confirm
      [ "$confirm" = "y" ] || [ "$confirm" = "Y" ] || die "Aborted"
    fi

    # Save state
    onboard_state=$(jq -n \
      --arg step "importing" \
      --arg archived_api "$archived_api" \
      --arg archived_url "$archived_url" \
      --arg archived_auth "$archived_auth" \
      --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
      '{step:$step, archived_api:$archived_api, archived_url:$archived_url,
        archived_auth:$archived_auth, import_prs:{}, reset_branches:[],
        migrated_prs:[], timestamp:$ts}')
    write_onboard_state "$target_name" "$onboard_state"
    current_step="importing"
  fi

  # ── Step 2: Import (reuses initial_import()) ──
  if [ "$current_step" = "importing" ]; then
    echo "" >&2
    log "INFO" "Step 2: Importing subrepo content into monorepo..."

    local branches
    branches=$(echo "$target_json" | jq -r '.branches | keys[]')

    # Load existing import_prs from state (resume support)
    local import_prs
    import_prs=$(echo "$onboard_state" | jq -r '.import_prs // {}')

    for branch in $branches; do
      local mapped
      mapped=$(echo "$target_json" | jq -r --arg b "$branch" '.branches[$b] // empty')
      [ -z "$mapped" ] && continue

      # Skip branches that already have an import PR recorded
      if echo "$import_prs" | jq -e --arg b "$branch" 'has($b)' >/dev/null 2>&1; then
        log "INFO" "Import PR already recorded for ${branch} — skipping"
        continue
      fi

      export SYNC_BRANCH_MONO="$branch"
      export SYNC_BRANCH_SUBREPO="$mapped"

      log "INFO" "Importing branch: ${branch} (subrepo: ${mapped})"
      local result
      result=$(initial_import)
      log "INFO" "Import result for ${branch}: ${result}"

      if [ "$result" = "pr-created" ]; then
        # Find the import PR number via API
        local prs pr_number
        prs=$(list_open_prs "$MONOREPO_API" "$GITEA_TOKEN")
        pr_number=$(echo "$prs" | jq -r --arg t "$target_name" --arg b "$branch" \
          '[.[] | select(.title | test("\\[Import\\] " + $t + ":")) | select(.base.ref == $b)] | .[0].number // empty')

        if [ -n "$pr_number" ]; then
          import_prs=$(echo "$import_prs" | jq --arg b "$branch" --arg n "$pr_number" '. + {($b): ($n | tonumber)}')
          log "INFO" "Import PR for ${branch}: #${pr_number}"
        else
          log "WARN" "Could not find import PR number for ${branch} — check monorepo PRs"
        fi
      fi

      # Save progress after each branch (resume support)
      onboard_state=$(echo "$onboard_state" | jq --argjson prs "$import_prs" '.import_prs = $prs')
      write_onboard_state "$target_name" "$onboard_state"
    done

    # Update state
    onboard_state=$(echo "$onboard_state" | jq \
      --arg step "waiting-for-merge" \
      --argjson prs "$import_prs" \
      '.step = $step | .import_prs = $prs')
    write_onboard_state "$target_name" "$onboard_state"
    current_step="waiting-for-merge"
  fi

  # ── Step 3: Wait for merge ──
  if [ "$current_step" = "waiting-for-merge" ]; then
    echo "" >&2
    log "INFO" "Step 3: Waiting for import PR(s) to be merged..."

    local import_prs
    import_prs=$(echo "$onboard_state" | jq -r '.import_prs')
    local pr_count
    pr_count=$(echo "$import_prs" | jq 'length')

    if [ "$pr_count" -eq 0 ]; then
      log "WARN" "No import PRs recorded — skipping merge check"
    else
      echo "" >&2
      echo "Import PRs to merge:" >&2
      echo "$import_prs" | jq -r 'to_entries[] | "  \(.key): PR #\(.value)"' >&2
      echo "" >&2
      echo "Merge the import PR(s) on the monorepo, then press Enter..." >&2
      read -r

      # Verify each PR is merged
      local all_merged=true
      for branch in $(echo "$import_prs" | jq -r 'keys[]'); do
        local pr_number
        pr_number=$(echo "$import_prs" | jq -r --arg b "$branch" '.[$b]')
        local pr_json merged
        pr_json=$(get_pr "$MONOREPO_API" "$GITEA_TOKEN" "$pr_number")
        merged=$(echo "$pr_json" | jq -r '.merged // false')

        if [ "$merged" = "true" ]; then
          log "INFO" "PR #${pr_number} (${branch}): merged"
        else
          log "ERROR" "PR #${pr_number} (${branch}): NOT merged — merge it first"
          all_merged=false
        fi
      done

      if [ "$all_merged" = false ]; then
        die "Not all import PRs are merged. Re-run 'josh-sync onboard ${target_name}' after merging."
      fi
    fi

    # Update state
    onboard_state=$(echo "$onboard_state" | jq '.step = "resetting"')
    write_onboard_state "$target_name" "$onboard_state"
    current_step="resetting"
  fi

  # ── Step 4: Reset (pushes josh-filtered history to new repo) ──
  if [ "$current_step" = "resetting" ]; then
    echo "" >&2
    log "INFO" "Step 4: Pushing josh-filtered history to new subrepo..."

    local branches
    branches=$(echo "$target_json" | jq -r '.branches | keys[]')
    local already_reset
    already_reset=$(echo "$onboard_state" | jq -r '.reset_branches // []')

    for branch in $branches; do
      # Skip branches already reset (resume support)
      if echo "$already_reset" | jq -e --arg b "$branch" 'index($b) != null' >/dev/null 2>&1; then
        log "INFO" "Branch ${branch} already reset — skipping"
        continue
      fi

      local mapped
      mapped=$(echo "$target_json" | jq -r --arg b "$branch" '.branches[$b] // empty')
      [ -z "$mapped" ] && continue

      export SYNC_BRANCH_MONO="$branch"
      export SYNC_BRANCH_SUBREPO="$mapped"

      local result
      result=$(subrepo_reset)
      log "INFO" "Reset result for ${branch}: ${result}"

      # Track progress
      onboard_state=$(echo "$onboard_state" | jq --arg b "$branch" \
        '.reset_branches += [$b]')
      write_onboard_state "$target_name" "$onboard_state"
    done

    # Update state
    onboard_state=$(echo "$onboard_state" | jq \
      --arg step "complete" \
      --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \
      '.step = $step | .timestamp = $ts')
    write_onboard_state "$target_name" "$onboard_state"
    current_step="complete"
  fi

  # ── Step 5: Done ──
  if [ "$current_step" = "complete" ]; then
    echo "" >&2
    echo "=== Onboarding complete! ===" >&2
    echo "" >&2
    echo "The new subrepo now has josh-filtered history." >&2
    echo "Developers should re-clone or reset their local copies:" >&2
    echo "  git fetch origin && git reset --hard origin/main" >&2
    echo "" >&2
    echo "To migrate open PRs from the archived repo:" >&2
    echo "  josh-sync migrate-pr ${target_name}        # interactive picker" >&2
    echo "  josh-sync migrate-pr ${target_name} --all   # migrate all" >&2
    echo "  josh-sync migrate-pr ${target_name} 5 8 12  # specific PRs" >&2
  fi
}

# ─── Migrate One PR ──────────────────────────────────────────────
# Applies a PR's diff from the archived repo to the new subrepo.
# Usage: migrate_one_pr <pr_number>
#
# Expects: JOSH_SYNC_TARGET_NAME, SUBREPO_API, SUBREPO_TOKEN, BOT_NAME, BOT_EMAIL loaded

migrate_one_pr() {
  local pr_number="$1"
  local target_name="$JOSH_SYNC_TARGET_NAME"

  # Read archived repo info from onboard state
  local onboard_state archived_api
  onboard_state=$(read_onboard_state "$target_name")
  archived_api=$(echo "$onboard_state" | jq -r '.archived_api')
  if [ -z "$archived_api" ] || [ "$archived_api" = "null" ]; then
    die "No archived repo info found. Run 'josh-sync onboard ${target_name}' first."
  fi

  # Check if this PR was already migrated
  local already_migrated
  already_migrated=$(echo "$onboard_state" | jq -r \
    --argjson num "$pr_number" '.migrated_prs // [] | map(select(.old_number == $num)) | length')
  if [ "$already_migrated" -gt 0 ]; then
    log "INFO" "PR #${pr_number} already migrated — skipping"
    return 0
  fi

  # Same credentials — the repo was just renamed
  local archived_token="$SUBREPO_TOKEN"

  # 1. Get PR metadata from archived repo
  local pr_json title base head body
  pr_json=$(get_pr "$archived_api" "$archived_token" "$pr_number") \
    || die "Failed to fetch PR #${pr_number} from archived repo"
  title=$(echo "$pr_json" | jq -r '.title')
  base=$(echo "$pr_json" | jq -r '.base.ref')
  head=$(echo "$pr_json" | jq -r '.head.ref')
  body=$(echo "$pr_json" | jq -r '.body // ""')

  log "INFO" "Migrating PR #${pr_number}: \"${title}\" (${base} <- ${head})"

  # 2. Get diff from archived repo
  local diff
  diff=$(get_pr_diff "$archived_api" "$archived_token" "$pr_number")
  if [ -z "$diff" ]; then
    log "WARN" "Empty diff for PR #${pr_number} — skipping"
    return 1
  fi

  # 3. Clone new subrepo, apply patch
  # Save cwd so we can restore it (function runs in caller's shell, not subshell)
  local original_dir
  original_dir=$(pwd)

  local work_dir
  work_dir=$(mktemp -d)
  # shellcheck disable=SC2064  # Intentional early expansion
  trap "cd '$original_dir' 2>/dev/null; rm -rf '$work_dir'" RETURN

  git clone "$(subrepo_auth_url)" --branch "$base" --single-branch \
    "${work_dir}/subrepo" 2>&1 || die "Failed to clone new subrepo (branch: ${base})"

  cd "${work_dir}/subrepo" || exit
  git config user.name "$BOT_NAME"
  git config user.email "$BOT_EMAIL"

  git checkout -B "$head" >&2

  if echo "$diff" | git apply --check 2>/dev/null; then
    echo "$diff" | git apply
    git add -A
    git commit -m "${title}

Migrated from archived repo PR #${pr_number}" >&2

    git push "$(subrepo_auth_url)" "$head" >&2 \
      || die "Failed to push branch ${head}"

    # 4. Create PR on new repo
    local new_number
    new_number=$(create_pr_number "$SUBREPO_API" "$SUBREPO_TOKEN" \
      "$base" "$head" "$title" "$body")
    log "INFO" "Migrated PR #${pr_number} -> #${new_number}: \"${title}\""

    # 5. Record in onboard state
    cd "$original_dir" || true
    onboard_state=$(read_onboard_state "$target_name")
    onboard_state=$(echo "$onboard_state" | jq \
      --argjson old "$pr_number" \
      --argjson new_num "${new_number}" \
      --arg title "$title" \
      '.migrated_prs += [{"old_number":$old, "new_number":$new_num, "title":$title}]')
    write_onboard_state "$target_name" "$onboard_state"
  else
    log "ERROR" "Patch doesn't apply cleanly for PR #${pr_number} — skipping"
    log "ERROR" "Manual migration needed: get diff from archived repo and resolve conflicts"
    return 1
  fi
}