Tool to recover RIFF formats (e.g. .wav files) from raw binary dd files. Requires gdd on mac from brew coreutils.

recoverriff.py

#!/usr/bin/env python3

import sys
import os
import mmap

filename = sys.argv[1]

tag = b"RIFF"

def doit(f, s):
    #sz = os.stat(f.fileno()).st_size
    c = 0
    p = 0
    while True:
        p = f.find(s)
        yield p
        f.seek(p+len(s))

sd = open(filename, 'rb')
sz = os.stat(sd.fileno()).st_size
sd.seek(0)
mm = mmap.mmap(sd.fileno(), 0, access=mmap.ACCESS_READ)
mm.seek(sd.tell())

print("#!/usr/bin/env bash")
print("""
if command -v gdd &> /dev/null
then
  DD=gdd
fi

set -e
set -m
trap 'killall ${DD-dd}' EXIT
set -v
""")
for i,p in enumerate(doit(mm, tag)):
    with open(sd.fileno(), 'rb', closefd=False) as line:
        try:
            line.seek(p)
            #print(line.peek(200).replace(b'\x00', b''))
            assert(line.read(4) == b"RIFF")
            field = line.read(4)
            sz = 0
            adj = 1
            for n in field:
                sz += adj*n
                adj *= 0x100
            sz += 8
            print("${{DD-dd}} bs=1M iflag=skip_bytes,count_bytes skip={0} count={1} if={filename} of=recovery/{2}.wav &".format(p, sz, i, filename=filename))
        except OSError as e:
            #print(e)
            break
print("wait && trap - EXIT")