#!/bin/sh
# Unattended wrapper around gdl-sync.py. One argument: the run mode.
#
#   stories   daily      ~6 requests; the only surface that cannot be backfilled
#   full      monthly    every surface, --abort 50 (stops at already-held content)
#   sweep     quarterly  every surface, no abort -- the only run that notices
#                        carousels edited after we archived them
#
# Exits non-zero if the sync does, so cron mails you. Everything is logged.
set -eu

MODE="${1:?usage: gdl-cron.sh stories|full|sweep}"

GDL_HOME="${GDL_HOME:-$HOME/gdl}"
INDEX="${GDL_INDEX:-https://instaarchive.ergosteur.com}"
PUBLISH="${GDL_PUBLISH:-agentapi@10.20.28.200:/volume1/rslsync/sync/Instagram-archive/archives/}"
STAGING="$GDL_HOME/staging-$MODE"
LOG="$GDL_HOME/logs/$MODE-$(date +%Y%m%d-%H%M%S).log"

PATH="$HOME/.local/bin:$PATH"; export PATH

case "$MODE" in
  stories) ARGS="--only stories" ;;
  full)    ARGS="--only posts,reels,stories,highlights --abort 50" ;;
  sweep)   ARGS="--only posts,reels,stories,highlights" ;;
  *) echo "unknown mode: $MODE" >&2; exit 2 ;;
esac

mkdir -p "$GDL_HOME/logs"

# Staging is wiped every run ON PURPOSE. What we already hold is decided by the
# skip-archive (--download-archive), never by which files happen to be sitting
# in staging, so starting empty is correct -- and it keeps the publish rsync
# to just the new files instead of re-walking gigabytes each time.
rm -rf "$STAGING"

{
  echo "=== $MODE run $(date -Is) ==="
  # shellcheck disable=SC2086
  "$GDL_HOME/gdl-sync.py" \
      --index "$INDEX" \
      --staging "$STAGING" \
      --publish "$PUBLISH" \
      --archive-db "$GDL_HOME/artms.db" \
      --urls-file "$GDL_HOME/artms_account_links.txt" \
      $ARGS --execute
  status=$?
  echo "=== exit $status at $(date -Is) ==="
  exit $status
} 2>&1 | tee -a "$LOG"

# Keep the log directory from growing without bound.
ls -1t "$GDL_HOME/logs" | tail -n +30 | while read -r old; do
  rm -f "$GDL_HOME/logs/$old"
done