[Python-checkins] cpython: Speed up base64.urlsafe_{en,de}code().
guido.van.rossum
python-checkins at python.org
Sat Jun 23 00:18:50 CEST 2012
http://hg.python.org/cpython/rev/2cbbc015d8a2
changeset: 77592:2cbbc015d8a2
parent: 77571:de2a0cb6ba52
user: Guido van Rossum <guido at python.org>
date: Fri Jun 22 15:16:09 2012 -0700
summary:
Speed up base64.urlsafe_{en,de}code().
files:
Lib/base64.py | 24 +++++++++++-------------
Misc/NEWS | 2 ++
2 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/Lib/base64.py b/Lib/base64.py
--- a/Lib/base64.py
+++ b/Lib/base64.py
@@ -40,14 +40,6 @@
else:
raise TypeError("argument should be bytes or ASCII string, not %s" % s.__class__.__name__)
-def _translate(s, altchars):
- if not isinstance(s, bytes_types):
- raise TypeError("expected bytes, not %s" % s.__class__.__name__)
- translation = bytearray(range(256))
- for k, v in altchars.items():
- translation[ord(k)] = v[0]
- return s.translate(translation)
-
# Base64 encoding/decoding uses binascii
@@ -71,7 +63,7 @@
raise TypeError("expected bytes, not %s"
% altchars.__class__.__name__)
assert len(altchars) == 2, repr(altchars)
- return _translate(encoded, {'+': altchars[0:1], '/': altchars[1:2]})
+ return encoded.translate(bytes.maketrans(b'+/', altchars))
return encoded
@@ -93,7 +85,7 @@
if altchars is not None:
altchars = _bytes_from_decode_data(altchars)
assert len(altchars) == 2, repr(altchars)
- s = _translate(s, {chr(altchars[0]): b'+', chr(altchars[1]): b'/'})
+ s = s.translate(bytes.maketrans(altchars, b'+/'))
if validate and not re.match(b'^[A-Za-z0-9+/]*={0,2}$', s):
raise binascii.Error('Non-base64 digit found')
return binascii.a2b_base64(s)
@@ -116,6 +108,10 @@
"""
return b64decode(s)
+
+_urlsafe_encode_translation = bytes.maketrans(b'+/', b'-_')
+_urlsafe_decode_translation = bytes.maketrans(b'-_', b'+/')
+
def urlsafe_b64encode(s):
"""Encode a byte string using a url-safe Base64 alphabet.
@@ -123,7 +119,7 @@
returned. The alphabet uses '-' instead of '+' and '_' instead of
'/'.
"""
- return b64encode(s, b'-_')
+ return b64encode(s).translate(_urlsafe_encode_translation)
def urlsafe_b64decode(s):
"""Decode a byte string encoded with the standard Base64 alphabet.
@@ -135,7 +131,9 @@
The alphabet uses '-' instead of '+' and '_' instead of '/'.
"""
- return b64decode(s, b'-_')
+ s = _bytes_from_decode_data(s)
+ s = s.translate(_urlsafe_decode_translation)
+ return b64decode(s)
@@ -228,7 +226,7 @@
if map01 is not None:
map01 = _bytes_from_decode_data(map01)
assert len(map01) == 1, repr(map01)
- s = _translate(s, {b'0': b'O', b'1': map01})
+ s = s.translate(bytes.maketrans(b'01', b'O' + map01))
if casefold:
s = s.upper()
# Strip off pad characters from the right. We need to count the pad
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -40,6 +40,8 @@
Library
-------
+- Issue: #15138: base64.urlsafe_{en,de}code() are now 3-4x faster.
+
- Issue #9527: datetime.astimezone() method will now supply a class
timezone instance corresponding to the system local timezone when
called with no arguments.
--
Repository URL: http://hg.python.org/cpython
More information about the Python-checkins
mailing list