From 0b6f6c82b51b7071d88f48abb3192bf3dc2a2d24 Mon Sep 17 00:00:00 2001 From: R David Murray Date: Fri, 25 May 2012 18:42:14 -0400 Subject: #12586: add provisional email policy with new header parsing and folding. When the new policies are used (and only when the new policies are explicitly used) headers turn into objects that have attributes based on their parsed values, and can be set using objects that encapsulate the values, as well as set directly from unicode strings. The folding algorithm then takes care of encoding unicode where needed, and folding according to the highest level syntactic objects. With this patch only date and time headers are parsed as anything other than unstructured, but that is all the helper methods in the existing API handle. I do plan to add more parsers, and complete the set specified in the RFC before the package becomes stable. --- Lib/email/utils.py | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'Lib/email/utils.py') diff --git a/Lib/email/utils.py b/Lib/email/utils.py index b82d5c578b..b7e1bb99f4 100644 --- a/Lib/email/utils.py +++ b/Lib/email/utils.py @@ -62,6 +62,13 @@ escapesre = re.compile(r'[\\"]') _has_surrogates = re.compile( '([^\ud800-\udbff]|\A)[\udc00-\udfff]([^\udc00-\udfff]|\Z)').search +# How to deal with a string containing bytes before handing it to the +# application through the 'normal' interface. +def _sanitize(string): + # Turn any escaped bytes into unicode 'unknown' char. + original_bytes = string.encode('ascii', 'surrogateescape') + return original_bytes.decode('ascii', 'replace') + # Helpers -- cgit v1.2.1