From 0fa156e24038d4228a77d18545c85db171742ae5 Mon Sep 17 00:00:00 2001
From: Matthias Urlichs <matthias@urlichs.de>
Date: Thu, 31 Oct 2024 14:45:19 +0100
Subject: [PATCH] Write to a file without rewriting constant parts

This little tool writes its standard input to a file.

It only writes to parts that actually change. This is very useful for keeping incremental backups small when the file in question is mostly-constant.
Example: Backing up database tables that are append-only or change seldom or never.
---
 contrib/tools/write_to.py | 47 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)
 create mode 100644 contrib/tools/write_to.py

diff --git a/contrib/tools/write_to.py b/contrib/tools/write_to.py
new file mode 100644
index 0000000..9b4a837
--- /dev/null
+++ b/contrib/tools/write_to.py
@@ -0,0 +1,47 @@
+#!/usr/bin/python3
+
+"""
+This simple tool reads data from stdin and writes them to a file,
+carefully *not* overwriting blocks that already have the desired content.
+
+Usage example:
+
+    cd /mnt/backup/mysql
+    mysql -Ne "show databases;" | grep -v '_schema$' | while read db ; do
+      mysql -Ne "show tables;" "$db" | while read t ; do
+        f="$db/$t.db"
+        if ! test -f "$f" ; then
+            mkdir -p $db
+            touch "$f"
+        fi
+        echo "mysqldump '$db' '$t' | write_to '$f'"
+      done
+    done | parallel
+
+The effect is that when your tables don't change/ are only appended to,
+your files are not overwritten and thus your incremental backups stay
+nice and small.
+"""
+
+import sys
+
+if len(sys.argv) != 2:
+	raise RuntimeError(f"Usage: {sys.argv[0]} destfile")
+
+fpos=0
+bs=4096
+
+fi = sys.stdin.buffer
+with open(sys.argv[1], "rb+") as fo:
+    fo.seek(0)
+    while True:
+        od=fi.read(bs)
+        if not od:
+            fo.truncate(fpos)
+            break
+        nd=fo.read(bs)
+        if nd != od:
+            fo.seek(fpos)
+            fo.write(od)
+        fpos += len(od)
+