wb_read_file.py 文件源码

def encodingFromContents( contents ):
    if( len(contents) > len(codecs.BOM_UTF8)
    and contents[0:len(codecs.BOM_UTF8)] == codecs.BOM_UTF8 ):
        encoding = 'utf-8'

    elif( len(contents) > len(codecs.BOM_UTF16_LE)
    and contents[0:len(codecs.BOM_UTF16_LE)] in [codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE]):
        encoding = 'utf-16'

    elif( len(contents) > len(codecs.BOM_UTF32_LE)
    and contents[0:len(codecs.BOM_UTF32_LE)] in [codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE]):
        encoding = 'utf-32'

    else:
        encoding = locale.getdefaultlocale()[1]

        # Mac says mac-roman when utf-8 is what is required
        if encoding == 'mac-roman':
            encoding = 'utf-8'

    if encoding is None:
        encoding = 'iso8859-1'

    return encoding