Create file deletion script from two 'openssl sha1' outputs. Deletions are done in files referenced in source hash file.

create_deleter.py

#!/usr/bin/python3

from sys import argv, exit
import re

hashline_re = re.compile('^SHA1\((.*?)\)= (.*)$')

dsthashes = dict()

if len(argv) < 4:
    print("Usage: " + argv[0] + " <srchashes> <dsthashes> <output-script> [<prefix>]")
    exit(1)
try:
    prefix = argv[4]
except IndexError:
    prefix = ""

try:
    hsrc = open(argv[1], "r")
    hdst = open(argv[2], "r")
    outscript = open(argv[3], "w")
except IOError as e:
    print(e)
    exit(2)

lcnt = 0
mcnt = 0
dcnt = 0
ncnt = 0
for l in hdst.readlines():
    lcnt += 1
    match = hashline_re.search(l)
    if match:
        mcnt += 1
        fname = match.group(1)
        fhash = match.group(2)
        if fhash in dsthashes:
            print("Duplicate file in destination. File {} equals {}, hash={}".format(fname, dsthashes[fhash], fhash))
            dcnt += 1
        else:
            dsthashes[fhash] = fname
    else:
        ncnt += 1
        print("Line '{}' not recognized")
hdst.close()
print("Read {} lines, {} matched, {} not. Found {} duplicates in destination".format(lcnt, mcnt, ncnt, dcnt))

print("#!/bin/sh", file=outscript)
lcnt = 0
mcnt = 0
dcnt = 0
ncnt = 0
for l in hsrc.readlines():
    lcnt += 1
    match = hashline_re.search(l)
    if match:
        mcnt += 1
        fname = match.group(1)
        fhash = match.group(2)
        if fhash in dsthashes:
            dcnt += 1
            print("# duplicate: src={} (deleted), dst={}, hash={}".format(fname, dsthashes[fhash], fhash), file=outscript)
            print("rm {}{}".format(prefix, fname), file=outscript)
        else:
            print("File '{}' (hash: {}) has no duplicate in destination".format(fname, fhash))
    else:
        ncnt += 1
        print("Line '{}' not recognized")
hsrc.close()
outscript.close()
print("Read {} lines, {} matched, {} not. Found {} duplicates in destination".format(lcnt, mcnt, ncnt, dcnt))