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

#!/usr/bin/env bash
set -eo pipefail

PAGES_URL="${PAGES_URL:-http://localhost:3000}"
PAGES_HOST="${PAGES_HOST:?PAGES_HOST is required}"
CONFIG="${RETENTION_CONFIG:-/etc/retention/retention.json}"
GITEA_API_URL="${GITEA_API_URL:-}"
GITEA_TOKEN="${GITEA_TOKEN:-}"

curl_with_host() {
  curl -sS -H "Host: ${PAGES_HOST}" "$@"
}

[ -f "$CONFIG" ] || { echo "ERROR: config missing: $CONFIG" >&2; exit 1; }

declare -A BRANCH_CACHE
branch_exists() {
  local owner="$1" repo="$2" branch="$3" key="${owner}/${repo}/${branch}"
  local status attempt
  
  [ -z "$GITEA_API_URL" ] && return 0
  [ -z "$GITEA_TOKEN" ] && return 0
  
  if [ "${BRANCH_CACHE[$key]:-}" = "1" ]; then
    return 0
  fi
  
  # Retry up to 2 times on API errors (hardcoded)
  for attempt in 1 2 3; do
    status=$(curl -sS -o /dev/null -w "%{http_code}" \
      -H "Authorization: token ${GITEA_TOKEN}" \
      "${GITEA_API_URL}/api/v1/repos/${owner}/${repo}/branches/${branch}" 2>/dev/null || echo "000")
    
    if [ "$status" = "200" ]; then
      BRANCH_CACHE[$key]=1
      return 0
    fi
    
    if [ "$status" = "404" ]; then
      return 1
    fi
    
    # API error - retry if not last attempt
    if [ "$attempt" -lt 3 ]; then
      sleep 10
      continue
    fi
  done
  
  # All retries failed - keep report (fail-safe)
  echo "  WARN: Gitea API error for ${owner}/${repo}/${branch} (status ${status}) after 3 attempts - KEEPING report"
  BRANCH_CACHE[$key]=1
  return 0
}

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

rule_max_age() {
  local branch="$1" v
  v=$(jq -r --arg b "$branch" '.branches[$b].maxAgeDays // empty' "$CONFIG")
  [ -n "$v" ] && echo "$v" || echo "$default_max_age"
}

rule_keep_min() {
  local branch="$1" v
  v=$(jq -r --arg b "$branch" '.branches[$b].keepMin // empty' "$CONFIG")
  [ -n "$v" ] && echo "$v" || echo "$default_keep_min"
}

age_days() {
  local published="$1" epoch_pub now
  epoch_pub=$(date -u -d "$published" +%s 2>/dev/null || echo 0)
  [ "$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%%/*}"
}

echo "Fetching manifest from ${PAGES_URL}/.git-pages/manifest.json"
MANIFEST=$(curl_with_host "${PAGES_URL}/.git-pages/manifest.json")
echo "Manifest loaded"

META_PATHS=$(echo "$MANIFEST" | jq -r '.contents | to_entries[] | select(.key | test("/reports/")) | select(.key | endswith("/.meta")) | .key' 2>/dev/null || true)

if [ -z "$META_PATHS" ]; then
  echo "No .meta files found under /reports/ — nothing to clean"
  exit 0
fi

echo ""
echo "=== Phase 1: collect reports ==="
declare -A SEEN_REPORTS
declare -a REPORTS
while IFS= read -r meta_path; do
  report_dir=$(dirname "$meta_path")
  
  # Skip duplicates - same report dir already processed
  [ -z "${SEEN_REPORTS[$report_dir]:-}" ] || continue
  SEEN_REPORTS[$report_dir]=1
  
  parse_path "$report_dir"
  meta_content=$(curl_with_host "${PAGES_URL}/${meta_path}" 2>/dev/null || true)
  [ -n "$meta_content" ] || { echo "  WARN: could not fetch $meta_path"; continue; }

  branch=$(echo "$meta_content" | jq -r '.branch // empty' 2>/dev/null || true)
  published=$(echo "$meta_content" | jq -r '.published_at // empty' 2>/dev/null || true)

  [ -n "$branch" ] || { echo "  WARN: no branch in $meta_path"; continue; }
  [ -n "$published" ] || { echo "  WARN: no published_at in $meta_path"; continue; }

  days=$(age_days "$published")
  REPORTS+=("${report_dir}|${OWNER}|${REPO}|${branch}|${days}")
  echo "  ${OWNER}/${REPO} branch=${branch} age=${days}d"
done <<< "$META_PATHS"

[ "${#REPORTS[@]}" -eq 0 ] && { echo "No actionable reports"; exit 0; }

echo ""
echo "=== Phase 2: check branches in Gitea ==="
declare -a TO_DELETE
declare -a KEEP
for entry in "${REPORTS[@]}"; do
  IFS='|' read -r dir owner repo branch days <<< "$entry"

  if [ -n "$GITEA_API_URL" ] && [ -n "$GITEA_TOKEN" ]; then
    if branch_exists "$owner" "$repo" "$branch"; then
      echo "  BRANCH EXISTS: ${owner}/${repo}/${branch}"
      KEEP+=("${dir}|${owner}|${repo}|${branch}|${days}")
    else
      echo "  BRANCH DELETED: ${owner}/${repo}/${branch} -> DELETE"
      TO_DELETE+=("$dir")
    fi
  else
    KEEP+=("${dir}|${owner}|${repo}|${branch}|${days}")
  fi
done

echo ""
echo "=== Phase 3: apply retention rules to remaining reports ==="
declare -A BRANCH_COUNTS
if [ "${#KEEP[@]}" -gt 0 ]; then
  IFS=$'\n'
  for entry in $(printf '%s\n' "${KEEP[@]}" | sort -t'|' -k4,4 -k5,5rn); do
    IFS='|' read -r dir owner repo branch days <<< "$entry"
    max_age=$(rule_max_age "$branch")
    keep_min=$(rule_keep_min "$branch")

    if [ "$days" -gt "$max_age" ]; then
      echo "  DELETE: ${dir} (age ${days}d > maxAge ${max_age}d, branch ${branch})"
      TO_DELETE+=("$dir")
      continue
    fi

    key="${branch}"
    count="${BRANCH_COUNTS[$key]:-0}"
    count=$((count + 1))
    BRANCH_COUNTS["$key"]=$count
    if [ "$count" -gt "$keep_min" ]; then
      echo "  DELETE: ${dir} (kept ${keep_min}/${count}, exceeds keepMin, branch ${branch})"
      TO_DELETE+=("$dir")
    fi
  done
  unset IFS
fi

if [ "${#TO_DELETE[@]}" -eq 0 ]; then
  echo "Nothing to delete"
  exit 0
fi

echo ""
echo "=== Phase 4: full site rebuild ==="
echo "Rebuilding site (${#TO_DELETE[@]} report(s) to delete)..."

ARCHIVE_FILE=$(mktemp)
SITE_DIR=$(mktemp -d)
NEW_TAR=$(mktemp)
cleanup_phase4() {
  rm -f "$ARCHIVE_FILE" "$NEW_TAR"
  rm -rf "$SITE_DIR"
}
trap cleanup_phase4 EXIT

# Try archive.tar first
echo "Downloading archive.tar..."
HTTP_CODE=$(curl_with_host -o "$ARCHIVE_FILE" -w "%{http_code}" -sS "${PAGES_URL}/.git-pages/archive.tar")

if [ "$HTTP_CODE" = "200" ] && tar -tf "$ARCHIVE_FILE" >/dev/null 2>&1; then
  echo "Extracting archive..."
  tar -xf "$ARCHIVE_FILE" -C "$SITE_DIR"

  for dir in "${TO_DELETE[@]}"; do
    if [ -d "$SITE_DIR/$dir" ]; then
      echo "  Removing: $dir"
      rm -rf "$SITE_DIR/$dir"
    fi
  done
else
  echo "archive.tar failed (HTTP ${HTTP_CODE}) - falling back to manifest-based rebuild"

  ALL_PATHS=$(echo "$MANIFEST" | jq -r '.contents | keys[]' 2>/dev/null || true)

  if [ -z "$ALL_PATHS" ]; then
    echo "ERROR: no files in manifest - cannot rebuild" >&2
    exit 1
  fi

  EXCLUDE_GREP=""
  for dir in "${TO_DELETE[@]}"; do
    EXCLUDE_GREP="${EXCLUDE_GREP}${EXCLUDE_GREP:+|}^${dir}/"
  done

  if [ -n "$EXCLUDE_GREP" ]; then
    KEEP_PATHS=$(echo "$ALL_PATHS" | grep -v -E "$EXCLUDE_GREP" || true)
  else
    KEEP_PATHS="$ALL_PATHS"
  fi

  if [ -z "$KEEP_PATHS" ]; then
    echo "No files to keep - site will be empty"
    mkdir -p "$SITE_DIR/__placeholder__"
    echo "placeholder" > "$SITE_DIR/__placeholder__/index.html"
  else
    FILE_COUNT=$(echo "$KEEP_PATHS" | wc -l | tr -d ' ')
    echo "Downloading ${FILE_COUNT} file(s)..."
    while IFS= read -r path; do
      [ -z "$path" ] && continue
      dir=$(dirname "$SITE_DIR/$path")
      mkdir -p "$dir"
      curl_with_host -o "$SITE_DIR/$path" -sS "${PAGES_URL}/${path}" || {
        echo "  WARN: failed to download ${path}"
      }
    done <<< "$KEEP_PATHS"
  fi
fi

if [ -z "$(ls -A "$SITE_DIR" 2>/dev/null)" ]; then
  echo "Site is empty - creating placeholder"
  mkdir -p "$SITE_DIR/__placeholder__"
  echo "placeholder" > "$SITE_DIR/__placeholder__/index.html"
fi

tar -cf "$NEW_TAR" -C "$SITE_DIR" .

echo "PUT: replacing site contents..."
HTTP_CODE=$(curl_with_host -X PUT "${PAGES_URL}/" \
  -H "Content-Type: application/x-tar" \
  --data-binary @"${NEW_TAR}" \
  -w "%{http_code}" \
  -o /dev/null)

echo "HTTP ${HTTP_CODE}"
if [ "$HTTP_CODE" = "200" ] || [ "$HTTP_CODE" = "201" ] || [ "$HTTP_CODE" = "204" ]; then
  echo "Site rebuild completed."
else
  echo "ERROR: PUT HTTP ${HTTP_CODE}" >&2
  exit 1
fi