A file to fix spurios encoding errors in a gedcom.

gedconvert.py

import smc.bibencodings
import sys


infile = open(sys.argv[1], 'rb')
outfile = open(sys.argv[2], 'wb')

while True:
    text = infile.read(2**16)
    if not text:
         break
    text = text.replace('\xcf', '')
    try:
        out = text.decode('ansel').encode('latin-1')
    except UnicodeEncodeError as e:
        print(e)
        out = text.decode('ansel').encode('latin-1', 'replace')
        
    outfile.write(out)