def _update_mime_text_info(self, msg, payload, part, text):
charset = part.get_charset()
text_count = self.get_local(msg, "mime_body_text_count")
self.set_local(msg, "mime_body_text_count", text_count + 1)
if part.get_content_subtype() == "plain":
plain_characters_count = self.get_local(msg,
"plain_characters_count")
self.set_local(msg, "plain_characters_count",
plain_characters_count + len(text))
ascii_count = self.get_local(msg, "ascii_count")
ascii_count += len(text)
self.set_local(msg, "ascii_count", ascii_count)
unicode_chars = Regex(r"(&\#x[0-9A-F]{4};)", re.X).search(text)
unicode_count = 0
if unicode_chars:
unicode_count = self.get_local(msg, "unicode_count")
unicode_count += len(unicode_chars.groups())
self.set_local(msg, "unicode_count", unicode_count)
# XXX This does not work properly anymore
if not charset or charset == r"us-ascii":
try:
payload.encode("ascii")
except (UnicodeEncodeError, UnicodeDecodeError):
self.set_local(msg, "mime_ascii_text_illegal", True)
if len(re.split("--", msg.raw_msg)) <= 4:
self.set_local(msg, "mime_missing_boundary", True)
def _update_quopri_stats(self, msg, part):
max_line_len = 79
qp_count = self.get_local(msg, "mime_qp_count")
qp_bytes = self.get_local(msg, "qp_bytes")
qp_chars = self.get_local(msg, "qp_chars")
quoted_printables = Regex(r"=(?:09|3[0-9ABCEF]|[2456][0-9A-F]|7["
r"0-9A-E])").search(part.get_payload())
qp_bytes += len(part.get_payload())
self.set_local(msg, "qp_bytes", qp_bytes)
if quoted_printables:
qp_chars += len(quoted_printables.groups())
self.set_local(msg, "qp_chars", qp_chars)
self.set_local(msg, "mime_qp_count", qp_count + 1)
raw = msg.translate_line_breaks(part.as_string())
has_long_line = self.get_local(msg, "mime_qp_long_line")
if not has_long_line:
has_long_line = any(
len("".join(line.split(":")[1:])) > max_line_len
and not line.startswith("SPAM") for line in raw.splitlines())
self.set_local(msg, "mime_qp_long_line", has_long_line)