From b83ee30fc1110d8e2d7ca0fb08b79506830a207a Mon Sep 17 00:00:00 2001 From: R David Murray Date: Wed, 26 Jun 2013 12:06:21 -0400 Subject: [PATCH] #11454: Reduce email module load time, improve surrogate check efficiency. The new _has_surrogates code was suggested by Serhiy Storchaka. See the issue for timings, but it is far faster than any other alternative, and also removes the load time that we previously incurred from compiling the complex regex this replaces. --- Lib/email/utils.py | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/Lib/email/utils.py b/Lib/email/utils.py index 93a625c8b44..b3b42bb3792 100644 --- a/Lib/email/utils.py +++ b/Lib/email/utils.py @@ -54,10 +54,16 @@ TICK = "'" specialsre = re.compile(r'[][\\()<>@,:;".]') escapesre = re.compile(r'[\\"]') -# How to figure out if we are processing strings that come from a byte -# source with undecodable characters. -_has_surrogates = re.compile( - '([^\ud800-\udbff]|\A)[\udc00-\udfff]([^\udc00-\udfff]|\Z)').search +def _has_surrogates(s): + """Return True if s contains surrogate-escaped binary data.""" + # This check is based on the fact that unless there are surrogates, utf8 + # (Python's default encoding) can encode any string. This is the fastest + # way to check for surrogates, see issue 11454 for timings. + try: + s.encode() + return False + except UnicodeEncodeError: + return True # How to deal with a string containing bytes before handing it to the # application through the 'normal' interface.