From 0361908320f307a6c79786890a87f8af9d0d6966 Mon Sep 17 00:00:00 2001
From: Thomas Spurden <thomas@spurden.name>
Date: Sat, 17 Aug 2019 12:10:21 +0100
Subject: [PATCH] Add script to remove deleted photos from database

---
 README.md |  8 ++++----
 clean-db  | 25 +++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 4 deletions(-)
 create mode 100755 clean-db

diff --git a/README.md b/README.md
index d278541..ca29553 100644
--- a/README.md
+++ b/README.md
@@ -29,6 +29,10 @@ Example usage:
 That should be all you need to find duplicates. But read on if you want more
 info.
 
+`clean-db` will delete entries from the database which no longer exist on disk.
+
+	./clean-db photos/db photos/
+
 # Details
 
 `fingerprint-files.py` reads a list of (newline-separated) filenames from stdin
@@ -53,7 +57,3 @@ Note that whilst the method is the same this implementation uses OpenCV rather
 than ImageMagick, so fingerprints will not be comparable.
 
 [1]: http://www.jhnc.org/findimagedupes/
-
-# TODO
-
- - Some automated way to remove files from the db which don't exist on disc?
diff --git a/clean-db b/clean-db
new file mode 100755
index 0000000..7db6573
--- /dev/null
+++ b/clean-db
@@ -0,0 +1,25 @@
+#!/bin/bash
+
+placeholder=xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
+
+if test $# -lt 2; then
+	echo "Usage: $0 <db> paths..."
+	exit 1
+fi
+
+db=$1
+tmpdb=$db.tmp
+shift
+
+script_dir=$(dirname $0)
+
+if test -e $tmpdb; then
+	echo "Looks like you have a temp db left at $tmpdb"
+	echo "If you are sure you do not want it then delete it"
+	exit 1
+fi
+
+{ cat "$db" 2>/dev/null; find $@ -type f -printf "$placeholder %p\n"; } | \
+	sort -k2 | uniq -D -s65 | grep -v "^$placeholder " > "$tmpdb"
+
+mv -- "$tmpdb" "$db"
-- 
2.45.2