support unicode in user-data input of unknown types

Fix the case where a unknown type is seen and it has contents which are in
unicode.  That caused python to blow-up when this happens since
'string-escape' doesn't work on unicode (at least in 2.6).

LP: #1075756

2 files changed, 15 insertions, 1 deletions

diff --git a/ChangeLog b/ChangeLog
index 1243ce7f..ac84c75f 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -8,6 +8,7 @@
    mime or cloud-archive config (LP: #1065116).
  - tools/Z99-cloud-locale-test.sh: avoid warning when user's shell is
    zsh (LP: #1073077)
+ - fix stack trace when unknown user-data input had unicode (LP: #1075756)
 0.7.0:
  - add a 'exception_cb' argument to 'wait_for_url'.  If provided, this
    method will be called back with the exception received and the message.
diff --git a/cloudinit/handlers/__init__.py b/cloudinit/handlers/__init__.py
index 99caed1f..8d6dcd4d 100644
--- a/cloudinit/handlers/__init__.py
+++ b/cloudinit/handlers/__init__.py
@@ -160,6 +160,19 @@ def _extract_first_or_bytes(blob, size):
     return start
 
 
+def _escape_string(text):
+    try:
+        return text.encode("string-escape")
+    except TypeError:
+        try:
+            # Unicode doesn't support string-escape...
+            return text.encode('unicode-escape')
+        except TypeError:
+            # Give up...
+            pass
+    return text
+
+
 def walker_callback(pdata, ctype, filename, payload):
     if ctype in PART_CONTENT_TYPES:
         walker_handle_handler(pdata, ctype, filename, payload)
@@ -171,7 +184,7 @@ def walker_callback(pdata, ctype, filename, payload):
     elif payload:
         # Extract the first line or 24 bytes for displaying in the log
         start = _extract_first_or_bytes(payload, 24)
-        details = "'%s...'" % (start.encode("string-escape"))
+        details = "'%s...'" % (_escape_string(start))
         if ctype == NOT_MULTIPART_TYPE:
             LOG.warning("Unhandled non-multipart (%s) userdata: %s",
                         ctype, details)