diff options
| author | Bénédikt Tran <10796600+picnixz@users.noreply.github.com> | 2025-01-14 13:25:33 (GMT) |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-01-14 13:25:33 (GMT) |
| commit | bbd3300ae82a71da483dbb0c345175ba090263c4 (patch) | |
| tree | ab4507f6a5f49876f21b89b4b43b798439db15f8 | |
| parent | 859db49029b1021e24b5c99d4a9a0f57327d1b57 (diff) | |
| download | cpython-bbd3300ae82a71da483dbb0c345175ba090263c4.zip cpython-bbd3300ae82a71da483dbb0c345175ba090263c4.tar.gz cpython-bbd3300ae82a71da483dbb0c345175ba090263c4.tar.bz2 | |
gh-118761: substitute `re` import in `base64.b16decode` for a more efficient alternative (#128736)
Co-authored-by: Adam Turner <9087854+AA-Turner@users.noreply.github.com>
Co-authored-by: Chris Markiewicz <effigies@gmail.com>
Co-authored-by: Hugo van Kemenade <1324225+hugovk@users.noreply.github.com>
| -rw-r--r-- | Doc/whatsnew/3.14.rst | 9 | ||||
| -rw-r--r-- | Lib/base64.py | 3 | ||||
| -rw-r--r-- | Misc/NEWS.d/next/Library/2025-01-10-13-06-54.gh-issue-118761.f8oADD.rst | 5 |
3 files changed, 15 insertions, 2 deletions
diff --git a/Doc/whatsnew/3.14.rst b/Doc/whatsnew/3.14.rst index 1152c7a..ac203b2 100644 --- a/Doc/whatsnew/3.14.rst +++ b/Doc/whatsnew/3.14.rst @@ -728,6 +728,15 @@ asyncio reduces memory usage. (Contributed by Kumar Aditya in :gh:`107803`.) + +base64 +------ + +* Improve the performance of :func:`base64.b16decode` by up to ten times, + and reduce the import time of :mod:`base64` by up to six times. + (Contributed by Bénédikt Tran, Chris Markiewicz, and Adam Turner in :gh:`118761`.) + + io --- * :mod:`io` which provides the built-in :func:`open` makes less system calls diff --git a/Lib/base64.py b/Lib/base64.py index 61be4fb..5d78cc0 100644 --- a/Lib/base64.py +++ b/Lib/base64.py @@ -4,7 +4,6 @@ # Modified 30-Dec-2003 by Barry Warsaw to add full RFC 3548 support # Modified 22-May-2007 by Guido van Rossum to use bytes everywhere -import re import struct import binascii @@ -284,7 +283,7 @@ def b16decode(s, casefold=False): s = _bytes_from_decode_data(s) if casefold: s = s.upper() - if re.search(b'[^0-9A-F]', s): + if s.translate(None, delete=b'0123456789ABCDEF'): raise binascii.Error('Non-base16 digit found') return binascii.unhexlify(s) diff --git a/Misc/NEWS.d/next/Library/2025-01-10-13-06-54.gh-issue-118761.f8oADD.rst b/Misc/NEWS.d/next/Library/2025-01-10-13-06-54.gh-issue-118761.f8oADD.rst new file mode 100644 index 0000000..37c25cb --- /dev/null +++ b/Misc/NEWS.d/next/Library/2025-01-10-13-06-54.gh-issue-118761.f8oADD.rst @@ -0,0 +1,5 @@ +Improve the performance of :func:`base64.b16decode` by up to ten times +by more efficiently checking the byte-string for hexadecimal digits. +Reduce the import time of :mod:`base64` by up to six times, +by no longer importing :mod:`re`. +Patch by Bénédikt Tran, Chris Markiewicz, and Adam Turner. |