string encoding detect

encoding_detect.py

import chardet

BOM_UTF8 = '\xef\xbb\xbf'

def detect(raw):
    if raw.startswith(BOM_UTF8):
        return 'utf-8-sig'
    else:
        result = chardet.detect(raw)
        return result['encoding']

def detectFile(fileName):
    with open(fileName, "rb") as f:
        raw = f.read(32)
        return detect(raw)