From 31a8aab92656279b141a9c29e484c4895bde15d3 Mon Sep 17 00:00:00 2001 From: Oleg Strikov Date: Wed, 11 Mar 2015 20:22:54 +0300 Subject: userdata-handlers: python3-related fixes on do-not-process-this-part path Cloud-init crashed when received multipart userdata object with 'application/octet-stream' part or some other 'application/*' part except archived ones (x-gzip and friends). These parts are not processed by cloud-init and result only in a message in the log. We used some non-python3-friendly techniques while generating this log message which was a reason for the crash. --- cloudinit/handlers/__init__.py | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) (limited to 'cloudinit') diff --git a/cloudinit/handlers/__init__.py b/cloudinit/handlers/__init__.py index 6b7abbcd..d62fcd19 100644 --- a/cloudinit/handlers/__init__.py +++ b/cloudinit/handlers/__init__.py @@ -163,12 +163,19 @@ def walker_handle_handler(pdata, _ctype, _filename, payload): def _extract_first_or_bytes(blob, size): - # Extract the first line upto X bytes or X bytes from more than the - # first line if the first line does not contain enough bytes - first_line = blob.split("\n", 1)[0] - if len(first_line) >= size: - start = first_line[:size] - else: + # Extract the first line or upto X symbols for text objects + # Extract first X bytes for binary objects + try: + if isinstance(blob, six.string_types): + start = blob.split("\n", 1)[0] + else: + # We want to avoid decoding the whole blob (it might be huge) + # By taking 4*size bytes we have a guarantee to decode size utf8 chars + start = blob[:4*size].decode(errors='ignore').split("\n", 1)[0] + if len(start) >= size: + start = start[:size] + except UnicodeDecodeError: + # Bytes array doesn't contain a text object -- return chunk of raw bytes start = blob[0:size] return start @@ -183,6 +190,11 @@ def _escape_string(text): except TypeError: # Give up... pass + except AttributeError: + # We're in Python3 and received blob as text + # No escaping is needed because bytes are printed + # as 'b\xAA\xBB' automatically in Python3 + pass return text -- cgit v1.2.3