utils.py 文件源码

def guess_json_utf(data):
    # JSON always starts with two ASCII characters, so detection is as
    # easy as counting the nulls and from their location and count
    # determine the encoding. Also detect a BOM, if present.
    sample = data[:4]
    if sample in (codecs.BOM_UTF32_LE, codecs.BOM32_BE):
        return 'utf-32'     # BOM included
    if sample[:3] == codecs.BOM_UTF8:
        return 'utf-8-sig'  # BOM included, MS style (discouraged)
    if sample[:2] in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE):
        return 'utf-16'     # BOM included
    nullcount = sample.count(_null)
    if nullcount == 0:
        return 'utf-8'
    if nullcount == 2:
        if sample[::2] == _null2:   # 1st and 3rd are null
            return 'utf-16-be'
        if sample[1::2] == _null2:  # 2nd and 4th are null
            return 'utf-16-le'
        # Did not detect 2 valid UTF-16 ascii-range characters
    if nullcount == 3:
        if sample[:3] == _null3:
            return 'utf-32-be'
        if sample[1:] == _null3:
            return 'utf-32-le'
        # Did not detect a valid UTF-32 ascii-range character
    return None