Unicode character detection across a directory.

utftester.py

import chardet  # https://pypi.python.org/pypi/chardet
import os
import sys
import fnmatch

def detect(arg, dir, names):
    for name in names:
        if fnmatch.fnmatch(name, arg):
            fpath = os.path.join(dir, name)
            r = chardet.detect(fpath)
            print "%s is %s with confidence %s" % (fpath, r['encoding'], r['confidence'])

os.path.walk(".", detect, sys.argv[1])

# Example usage:
#  cd to top of directory to test.
#  utftester.py *.txt