Compares the files in two directories to find ones which are present in the source but not in the destination and vice versa. Useful for data migrations.

find-missing-files.bash

#!/bin/bash

# Based on
# https://github.com/capncodewash/Misc-shell-scripts/blob/master/find_missing_files.sh
# by Graeme West which is in turn based on the answer kindly supplied by
# 'Unknown' at StackOverflow:
# http://stackoverflow.com/questions/3006014/finding-missing-files-by-checksum
# with additions from aleksejrs.
#
# Compares the files in two directories to find ones which are present in the
# source but not in the destination and vice versa.  Useful for data migrations.

# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
# See the GNU General Public License for more details,
# which is available at www.gnu.org

set -o nounset

if [ $# -ne 2 ]; then
    echo "Usage: $(basename "$0") path/to/a/dir path/to/b/dir"
    exit 1
fi

src_dir="$1/"
dst_dir="$2/"

work_dir="$(mktemp -dt fmfXXXXXXX)"
function cleanup()
{
    rm -r "$work_dir"
}
trap cleanup EXIT

# Temporary files into which to write sorted checksums of all files, they are
# used to make the comparisons.
alist="$work_dir/cmp_source_files_sorted.txt"
blist="$work_dir/cmp_dest_files_sorted.txt"

# The files which will contain the final output.
# They will be cleared before output begins.
a_only="vifm-dircompare-a-only.lst"
b_only="vifm-dircompare-b-only.lst"

find "$src_dir" -type f -exec sha512sum {} \; | sort > "$alist"
find "$dst_dir" -type f -exec sha512sum {} \; | sort > "$blist"

function find_missing()
{
    function 1st()
    {
        cut -f1 -d' ' "$@"
    }
    function 2nd()
    {
        awk '{print $2}' "$@"
    }

    fgrep -f <(comm "-$1" <(1st "$alist") <(1st "$blist")) "$2" | 2nd | sort -u
}

find_missing 23 "$alist" > "$a_only"
find_missing 13 "$blist" > "$b_only"