gitea-ci-library/git-pages/files/retention-lib.sh

#!/usr/bin/env bash
# Shared functions for retention-cleanup.sh
# Can be sourced by tests for unit testing

age_days() {
  local published="$1" epoch_pub now
  epoch_pub=$(date -d "$published" +%s 2>/dev/null || date -j -f "%Y-%m-%dT%H:%M:%SZ" "$published" +%s 2>/dev/null || echo 0)
  [ "$epoch_pub" -eq 0 ] && echo 99999 && return
  now=$(date -u +%s)
  echo $(( (now - epoch_pub) / 86400 ))
}

parse_path() {
  local rel="$1"
  OWNER="${rel%%/*}"
  rest="${rel#*/}"
  REPO="${rest%%/*}"
}

read_rule() {
  local config="$1" branch="$2" key="$3" default="$4"
  v=$(jq -r --arg b "$branch" --arg k "$key" '.branches[$b][$k] // empty' "$config")
  [ -n "$v" ] && echo "$v" || echo "$default"
}

# ---------------------------------------------------------------------------
# Gitea branch/repo checking via git ls-remote
# Uses global: GITEA_API_URL, GITEA_TOKEN
# Sets global: REPO_BRANCHES_CACHE, REPO_STATUS
# ---------------------------------------------------------------------------

# Fetch all branches for a repo (one git ls-remote call per repo).
# Sets REPO_STATUS[owner/repo].
# Echos branch list on success.
# Returns: 0=ok, 1=deleted, 2=cert_error, 3=error (fail-safe keep)
repo_branches() {
  local owner="$1" repo="$2" key="${owner}/${repo}"
  local attempt output

  [ -z "$GITEA_API_URL" ] && return 0
  [ -z "$GITEA_TOKEN" ] && return 0

  # Check cached status first (avoids re-running git on every report)
  case "${REPO_STATUS[$key]:-}" in
    deleted)    return 1 ;;
    cert_error) return 2 ;;
    error)      echo "${REPO_BRANCHES_CACHE[$key]:-}"; return 3 ;;
  esac

  # Cache hit (success with branch list)
  [ -n "${REPO_BRANCHES_CACHE[$key]:-}" ] && { echo "${REPO_BRANCHES_CACHE[$key]}"; return 0; }

  local git_host
  git_host=$(echo "$GITEA_API_URL" | sed -E 's|^https?://||' | sed 's|/.*$||')
  local git_url="https://token:${GITEA_TOKEN}@${git_host}/${owner}/${repo}.git"

  for attempt in 1 2 3; do
    output=$(git ls-remote --heads "$git_url" 2>&1) && {
      local branches
      branches=$(echo "$output" | sed -n 's|.*refs/heads/||p')
      REPO_BRANCHES_CACHE[$key]="$branches"
      REPO_STATUS[$key]="ok"
      echo "$branches"
      return 0
    }

    # Repo deleted → no retry
    if echo "$output" | grep -qiE "fatal:.*(not found|repository.*not|could not read)"; then
      REPO_BRANCHES_CACHE[$key]="__REPO_DELETED__"
      REPO_STATUS[$key]="deleted"
      echo "  REPO DELETED: ${owner}/${repo}" >&2
      return 1
    fi

    [ "$attempt" -lt 3 ] && sleep 10
  done

  # Certificate verification failure → configuration error, stop
  if echo "$output" | grep -qi "server certificate verification failed"; then
    REPO_STATUS[$key]="cert_error"
    echo "[ERROR] git-pages.retention: certificate verification failed for ${owner}/${repo}" >&2
    echo "[ERROR] git-pages.retention:   check CA certificates or set GIT_SSL_NO_VERIFY=1" >&2
    echo "[ERROR] git-pages.retention:   git output:" >&2
    echo "$output" >&2
    return 2
  fi

  # Other network errors → fail-safe keep, continue
  REPO_BRANCHES_CACHE[$key]="__REPO_ERROR__"
  REPO_STATUS[$key]="error"
  echo "[WARN] git-pages.retention: cannot reach Gitea for ${owner}/${repo} — keeping all reports" >&2
  echo "[WARN] git-pages.retention:   git output:" >&2
  echo "$output" >&2
  return 3
}

# Check if a specific branch exists in a repo.
# Returns 0 (exists), 1 (not found/deleted).
# Returns 2 (cert error), 3 (network error).
branch_exists() {
  local owner="$1" repo="$2" branch="$3"
  local branches rc

  [ -z "$GITEA_API_URL" ] && return 0
  [ -z "$GITEA_TOKEN" ] && return 0

  branches=$(repo_branches "$owner" "$repo")
  rc=$?

  # Return codes from repo_branches propagate through $() subshell:
  # 0=ok, 1=deleted, 2=cert_error, 3=error
  case $rc in
    2) echo "[FATAL] git-pages.retention: cannot reach Gitea (${owner}/${repo}) — check configuration" >&2
       exit 1 ;;
    3) return 0 ;;  # network error → fail-safe keep
    1) return 1 ;;  # repo/branch gone
  esac

  echo "$branches" | grep -qxF "$branch"
}

# Phase 3: apply retention rules to KEEP array, populate TO_DELETE
# Reads from global KEEP array
# Populates global TO_DELETE array
# Usage: apply_retention <config_path>
apply_retention() {
  local config="$1"
  local default_max_age default_keep_min
  local max_age keep_min key count seen_key commit_dir
  local entry dir owner repo branch days

  default_max_age=$(jq -r '.branches.default.maxAgeDays // 90' "$config")
  default_keep_min=$(jq -r '.branches.default.keepMin // 5' "$config")

  declare -A BRANCH_COUNTS
  declare -A SEEN_COMMITS
  declare -A DELETED_COMMITS

  if [ "${#KEEP[@]}" -eq 0 ]; then
    return
  fi

  IFS=$'\n'
  for entry in $(printf '%s\n' "${KEEP[@]}" | sort -t'|' -k4,4 -k5,5n); do
    IFS='|' read -r dir owner repo branch days <<< "$entry"

    max_age=$(read_rule "$config" "$branch" "maxAgeDays" "$default_max_age")
    keep_min=$(read_rule "$config" "$branch" "keepMin" "$default_keep_min")

    # Age check — per-report-type deletion
    if [ "$days" -gt "$max_age" ]; then
      echo "  DELETE: ${dir} (age ${days}d > maxAge ${max_age}d, branch ${branch})"
      TO_DELETE+=("$dir")
      REASON_MAP["$dir"]="maxAgeDays exceed"
      MAXAGE_DELETED=$((MAXAGE_DELETED + 1))
      continue
    fi

    # keepMin — per-commit counting
    commit_dir=$(dirname "$dir")
    key="$branch"
    seen_key="${key}|${commit_dir}"

    if [ -z "${SEEN_COMMITS[$seen_key]:-}" ]; then
      SEEN_COMMITS["$seen_key"]=1
      count="${BRANCH_COUNTS[$key]:-0}"
      count=$((count + 1))
      BRANCH_COUNTS["$key"]=$count
    else
      count="${BRANCH_COUNTS[$key]:-0}"
    fi

    if [ "$count" -gt "$keep_min" ]; then
      if [ -z "${DELETED_COMMITS[$commit_dir]:-}" ]; then
        DELETED_COMMITS[$commit_dir]=1
        echo "  DELETE: ${commit_dir} (kept ${keep_min}/${count} commits, exceeds keepMin, branch ${branch})"
        TO_DELETE+=("$commit_dir")
        REASON_MAP["$commit_dir"]="keepMin exceed"
        KEEPMIN_DELETED=$((KEEPMIN_DELETED + 1))
      fi
    fi
  done
  unset IFS
}