Function decode_header

Lib/email/header.py:59–156

Decode a message header value without converting charset. For historical reasons, this function may return either: 1. A list of length 1 containing a pair (str, None). 2. A list of (bytes, charset) pairs containing each of the decoded parts of the header. Charset is None for no

(header)

def decode_header(header):
    """Decode a message header value without converting charset.

    For historical reasons, this function may return either:

    1. A list of length 1 containing a pair (str, None).
    2. A list of (bytes, charset) pairs containing each of the decoded
       parts of the header.  Charset is None for non-encoded parts of the header,
       otherwise a lower-case string containing the name of the character set
       specified in the encoded string.

    header may be a string that may or may not contain RFC2047 encoded words,
    or it may be a Header object.

    An email.errors.HeaderParseError may be raised when certain decoding error
    occurs (e.g. a base64 decoding exception).

    This function exists for backwards compatibility only. For new code, we
    recommend using email.headerregistry.HeaderRegistry instead.
    """
    # If it is a Header object, we can just return the encoded chunks.
    if hasattr(header, '_chunks'):
        return [(_charset._encode(string, str(charset)), str(charset))
                    for string, charset in header._chunks]
    # If no encoding, just return the header with no charset.
    if not ecre.search(header):
        return [(header, None)]
    # First step is to parse all the encoded parts into triplets of the form
    # (encoded_string, encoding, charset).  For unencoded strings, the last
    # two parts will be None.
    words = []
    for line in header.splitlines():
        parts = ecre.split(line)
        first = True
        while parts:
            unencoded = parts.pop(0)
            if first:
                unencoded = unencoded.lstrip()
                first = False
            if unencoded:
                words.append((unencoded, None, None))
            if parts:
                charset = parts.pop(0).lower()
                encoding = parts.pop(0).lower()
                encoded = parts.pop(0)
                words.append((encoded, encoding, charset))
    # Now loop over words and remove words that consist of whitespace
    # between two encoded strings.
    droplist = []
    for n, w in enumerate(words):
        if n>1 and w[1] and words[n-2][1] and words[n-1][0].isspace():
            droplist.append(n-1)
    for d in reversed(droplist):
        del words[d]

    # The next step is to decode each encoded word by applying the reverse
    # base64 or quopri transformation.  decoded_words is now a list of the
    # form (decoded_word, charset).