From 341a805fca9a06ce12e9f4bbbe15b3dded9eb6a4 Mon Sep 17 00:00:00 2001 From: Scott Moser Date: Thu, 16 Apr 2015 17:00:19 -0400 Subject: fix cloud-config-archive handling handling of cloud-config-archive input would fail in fully_decoded_payload. part.get_charset() would return a Charset object, but get_charset.input_codec is a string suitable for passing to decode. This handles that correctly, and is more careful about binary data inside input. The test added verifies that cloud-config inside a cloud-config-archive is handled correctly and also that binary data there is ignored without exceptions raised. LP: #1445143 --- cloudinit/handlers/__init__.py | 5 ++++- cloudinit/user_data.py | 9 +++++++-- cloudinit/util.py | 8 ++++++-- 3 files changed, 17 insertions(+), 5 deletions(-) (limited to 'cloudinit') diff --git a/cloudinit/handlers/__init__.py b/cloudinit/handlers/__init__.py index 52defe66..53d5604a 100644 --- a/cloudinit/handlers/__init__.py +++ b/cloudinit/handlers/__init__.py @@ -263,7 +263,10 @@ def fixup_handler(mod, def_freq=PER_INSTANCE): def type_from_starts_with(payload, default=None): - payload_lc = payload.lower() + try: + payload_lc = util.decode_binary(payload).lower() + except UnicodeDecodeError: + return default payload_lc = payload_lc.lstrip() for text in INCLUSION_SRCH: if payload_lc.startswith(text): diff --git a/cloudinit/user_data.py b/cloudinit/user_data.py index eb3c7336..f7c5787c 100644 --- a/cloudinit/user_data.py +++ b/cloudinit/user_data.py @@ -49,6 +49,7 @@ INCLUDE_TYPES = ['text/x-include-url', 'text/x-include-once-url'] ARCHIVE_TYPES = ["text/cloud-config-archive"] UNDEF_TYPE = "text/plain" ARCHIVE_UNDEF_TYPE = "text/cloud-config" +ARCHIVE_UNDEF_BINARY_TYPE = "application/octet-stream" # This seems to hit most of the gzip possible content types. DECOMP_TYPES = [ @@ -265,11 +266,15 @@ class UserDataProcessor(object): content = ent.get('content', '') mtype = ent.get('type') if not mtype: - mtype = handlers.type_from_starts_with(content, - ARCHIVE_UNDEF_TYPE) + default = ARCHIVE_UNDEF_TYPE + if isinstance(content, six.binary_type): + default = ARCHIVE_UNDEF_BINARY_TYPE + mtype = handlers.type_from_starts_with(content, default) maintype, subtype = mtype.split('/', 1) if maintype == "text": + if isinstance(content, six.binary_type): + content = content.decode() msg = MIMEText(content, _subtype=subtype) else: msg = MIMEBase(maintype, subtype) diff --git a/cloudinit/util.py b/cloudinit/util.py index 971c1c2d..cae57770 100644 --- a/cloudinit/util.py +++ b/cloudinit/util.py @@ -121,8 +121,12 @@ def fully_decoded_payload(part): if (six.PY3 and part.get_content_maintype() == 'text' and isinstance(cte_payload, bytes)): - charset = part.get_charset() or 'utf-8' - return cte_payload.decode(charset, errors='surrogateescape') + charset = part.get_charset() + if charset and charset.input_codec: + encoding = charset.input_codec + else: + encoding = 'utf-8' + return cte_payload.decode(encoding, errors='surrogateescape') return cte_payload -- cgit v1.2.3