Skip to content

gh-118761: Reduce import time of gettext.py by delaying re import #128898

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 20, 2025
Merged

gh-118761: Reduce import time of gettext.py by delaying re import #128898

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 18 additions & 15 deletions Lib/gettext.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,6 @@

import operator
import os
import re
import sys


Expand All @@ -70,22 +69,26 @@
# https://www.gnu.org/software/gettext/manual/gettext.html#Plural-forms
# http://git.savannah.gnu.org/cgit/gettext.git/tree/gettext-runtime/intl/plural.y

_token_pattern = re.compile(r"""
(?P<WHITESPACES>[ \t]+) | # spaces and horizontal tabs
(?P<NUMBER>[0-9]+\b) | # decimal integer
(?P<NAME>n\b) | # only n is allowed
(?P<PARENTHESIS>[()]) |
(?P<OPERATOR>[-*/%+?:]|[><!]=?|==|&&|\|\|) | # !, *, /, %, +, -, <, >,
# <=, >=, ==, !=, &&, ||,
# ? :
# unary and bitwise ops
# not allowed
(?P<INVALID>\w+|.) # invalid token
""", re.VERBOSE|re.DOTALL)

_token_pattern = None

def _tokenize(plural):
for mo in re.finditer(_token_pattern, plural):
global _token_pattern
if _token_pattern is None:
import re
_token_pattern = re.compile(r"""
(?P<WHITESPACES>[ \t]+) | # spaces and horizontal tabs
(?P<NUMBER>[0-9]+\b) | # decimal integer
(?P<NAME>n\b) | # only n is allowed
(?P<PARENTHESIS>[()]) |
(?P<OPERATOR>[-*/%+?:]|[><!]=?|==|&&|\|\|) | # !, *, /, %, +, -, <, >,
# <=, >=, ==, !=, &&, ||,
# ? :
# unary and bitwise ops
# not allowed
(?P<INVALID>\w+|.) # invalid token
""", re.VERBOSE|re.DOTALL)

for mo in _token_pattern.finditer(plural):
kind = mo.lastgroup
if kind == 'WHITESPACES':
continue
Expand Down
3 changes: 3 additions & 0 deletions Misc/NEWS.d/next/Library/2025-01-15-19-16-50.gh-issue-118761.cbW2ZL.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
Reduce import time of :mod:`gettext` by up to ten times, by importing
:mod:`re` on demand. In particular, ``re`` is no longer implicitly
exposed as ``gettext.re``. Patch by Eli Schwartz.
Loading