Initial commit: backup + mirror automation for self-hosted Gitea

Includes: - gitea-backups/bin/backup.sh (per-push bundle + DB snapshot to local + S3) - gitea-backups/bin/install-hooks.sh (idempotent post-receive shim installer) - gitea-backups/bin/retention.sh (count-based retention: keep newest 7 dates) - gitea-mirror/bin/auto-mirror.sh (Gitea -> GitHub push mirror automation, hardened against Gitea outages) - crontab.txt (reference for the 3 cron entries) - README.md (architecture, layout, bootstrap)
2026-05-09 06:02:09 +00:00
commit a181625c89
7 changed files with 496 additions and 0 deletions
@@ -0,0 +1,79 @@
+#!/usr/bin/env bash
+# Daily retention sweep — keeps the newest KEEP_DAYS distinct calendar
+# dates of backups, on BOTH local disk and S3, regardless of how old
+# those dates are. So a long quiet period leaves backups intact instead
+# of letting them age out.
+#
+# Idempotent. Safe to run on a cron.
+
+set -uo pipefail
+
+CONFIG_DIR="/home/ubuntu/gitea-backups"
+LOG="${CONFIG_DIR}/logs/retention.log"
+KEEP_DAYS=7
+
+S3_REMOTE="s3"
+S3_BUCKET="toqqer-gitea-backup"
+RCLONE_CONF="/home/ubuntu/.config/rclone/rclone.conf"
+
+QUIET=0
+[[ "${1:-}" == "--quiet" ]] && QUIET=1
+log() { printf '%s %s\n' "$(date -u +%FT%TZ)" "$*" >> "$LOG"; }
+say() { [[ $QUIET -eq 0 ]] && echo "$*"; log "$*"; }
+
+# ---- S3: keep newest KEEP_DAYS top-level YYYY-MM-DD folders ----
+mapfile -t s3_dates < <(
+    rclone --config "$RCLONE_CONF" lsd "${S3_REMOTE}:${S3_BUCKET}/" 2>/dev/null \
+        | awk '{print $NF}' \
+        | grep -E '^[0-9]{4}-[0-9]{2}-[0-9]{2}$' \
+        | sort
+)
+n=${#s3_dates[@]}
+if (( n <= KEEP_DAYS )); then
+    say "S3: ${n} date-folder(s) present — all kept (limit ${KEEP_DAYS})"
+else
+    to_delete=$(( n - KEEP_DAYS ))
+    deleted=0
+    for ((i=0; i<to_delete; i++)); do
+        d="${s3_dates[i]}"
+        if rclone --config "$RCLONE_CONF" purge "${S3_REMOTE}:${S3_BUCKET}/${d}" 2>>"$LOG"; then
+            say "S3: deleted ${d}/"
+            deleted=$((deleted+1))
+        else
+            say "S3: FAIL deleting ${d}/ (see log)"
+        fi
+    done
+    say "S3: kept newest ${KEEP_DAYS} date-folder(s), deleted ${deleted} older"
+fi
+
+# ---- LOCAL: same semantics on /home/ubuntu/gitea-backups/{repos,db}/ ----
+# All filenames are date-prefixed (YYYY-MM-DDTHH-MM-SSZ...), so we group by
+# the leading date and keep files only from the newest KEEP_DAYS dates seen.
+mapfile -t local_dates < <(
+    {
+        find "${CONFIG_DIR}/repos" -type f -name '*.bundle' 2>/dev/null
+        find "${CONFIG_DIR}/db"    -type f -name '*.db.gz'  2>/dev/null
+    } | grep -oE '[0-9]{4}-[0-9]{2}-[0-9]{2}' | sort -u
+)
+ln=${#local_dates[@]}
+if (( ln <= KEEP_DAYS )); then
+    say "LOCAL: ${ln} date(s) present — all kept (limit ${KEEP_DAYS})"
+else
+    keep_from=$(( ln - KEEP_DAYS ))
+    keep_set="$(printf '%s\n' "${local_dates[@]:$keep_from}")"
+    deleted_files=0
+    while IFS= read -r f; do
+        [[ -z "$f" ]] && continue
+        fd=$(grep -oE '[0-9]{4}-[0-9]{2}-[0-9]{2}' <<< "$(basename "$f")" | head -1)
+        if ! grep -qx "$fd" <<< "$keep_set"; then
+            rm -f "$f" && deleted_files=$((deleted_files+1))
+        fi
+    done < <(
+        find "${CONFIG_DIR}/repos" -type f -name '*.bundle' 2>/dev/null
+        find "${CONFIG_DIR}/db"    -type f -name '*.db.gz'  2>/dev/null
+    )
+    find "${CONFIG_DIR}/repos" -mindepth 2 -type d -empty -delete 2>>"$LOG" || true
+    say "LOCAL: kept newest ${KEEP_DAYS} date(s), deleted ${deleted_files} file(s)"
+fi
+
+exit 0