bd334ef20fdccb74d310ca00b1134388645ba0a5,vendor/readability/encoding.py,,get_encoding,#Any#,4

Before Change

    if not text.strip() or len(text) < 10:
        return enc // can"t guess
    try:
        diff = text.decode(enc, "ignore").encode(enc)
        sizes = len(diff), len(text)
        if abs(len(text) - len(diff)) < max(sizes) * 0.01: // 99% of utf-8
            return enc
    except UnicodeDecodeError:
        pass
    res = chardet.detect(text)
    enc = res["encoding"]

After Change

    pragma_re = re.compile(r"<meta.*?content=["\"]*;?charset=(.+?)["\">]", flags=re.I)
    xml_re = re.compile(r"^<\?xml.*?encoding=["\"]*(.+?)["\">]")

    declared_encodings = (charset_re.findall(page) +
            pragma_re.findall(page) +
            xml_re.findall(page))

    // Try any declared encodings
    if len(declared_encodings) > 0:
        for declared_encoding in declared_encodings:
            try:
                page.decode(custom_decode(declared_encoding))

Instances