Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
3 changes: 2 additions & 1 deletion Doc/library/string.rst
Original file line number Diff line number Diff line change
Expand Up @@ -971,7 +971,8 @@ attributes:

Alternatively, you can provide the entire regular expression pattern by
overriding the class attribute *pattern*. If you do this, the value must be a
regular expression object with four named capturing groups. The capturing
string containing the regular expression, or a compiled regular expression
object, with four named capturing groups. The capturing
groups correspond to the rules given above, along with the invalid placeholder
rule:

Expand Down
7 changes: 7 additions & 0 deletions Lib/string/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,14 @@ def __init_subclass__(cls):
def _compile_pattern(cls):
import re # deferred import, for performance

# `pattern` may be the `_TemplatePattern` sentinel (not yet compiled), an
# already-compiled regular expression object (as documented), or a string
# regular expression. An already-compiled object is returned as-is; the
# other two are compiled and cached back on the class.
pattern = cls.__dict__.get('pattern', _TemplatePattern)
if isinstance(pattern, re.Pattern):

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think I'd add a comment here just above this line, something to the effect of:

# `pattern` can be one of three objects: a `_TemplatePattern` indicating that the descriptor has not yet
# run, a compiled regular expression object as stated in the docs, or a string representing a regular
# expression pattern.  If it's an already compiled regular expression object, we can just return that
# immediately.  For the former two cases, we have to compile the pattern and cache it back on the
# attribute.

# re.compile() rejects flags on an already-compiled pattern.
return pattern
if pattern is _TemplatePattern:
delim = re.escape(cls.delimiter)
id = cls.idpattern
Expand Down
35 changes: 35 additions & 0 deletions Lib/test/test_free_threading/test_string_template_race.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,35 @@
import string
import unittest
from string import Template

from test.support import threading_helper


@threading_helper.requires_working_threading()
class TestTemplateCompileRace(unittest.TestCase):
def test_concurrent_first_use(self):
# Racing the lazy pattern compile must not raise a spurious ValueError
# from recompiling an already-compiled pattern. A throwaway subclass,
# re-armed to the sentinel each round, keeps string.Template unmutated
# (subclasses precompile eagerly in __init_subclass__).
uncompiled = string._TemplatePattern
errors = []

def use_template(cls):
try:
cls("$x and ${y}").substitute(x=1, y=2)
except Exception as e:
errors.append(e)

for _ in range(20):
class T(Template):
pass
T.pattern = uncompiled
T.flags = None
threading_helper.run_concurrently(use_template, nthreads=10, args=(T,))

self.assertEqual(errors, [], msg=f"unexpected errors: {errors}")


if __name__ == "__main__":
unittest.main()
14 changes: 14 additions & 0 deletions Lib/test/test_string/test_string.py
Original file line number Diff line number Diff line change
Expand Up @@ -299,6 +299,20 @@ def test_SafeTemplate(self):
eq(s.safe_substitute(dict(who='tim', what='ham', meal='dinner')),
'tim likes ham for dinner')

def test_precompiled_pattern(self):
# A subclass may supply an already-compiled pattern; it must be reused,
# not recompiled (re.compile() rejects flags on a compiled pattern).
import re

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It'll be nice when we can get rid of all these and just use lazy imports 😄

compiled = re.compile(
r'\$(?:(?P<escaped>\$)|(?P<named>[a-z]+)|'
r'\{(?P<braced>[a-z]+)\}|(?P<invalid>))')
class MyTemplate(Template):
pattern = compiled
self.assertIs(MyTemplate.pattern, compiled)
self.assertEqual(
MyTemplate('$who likes $what').substitute(who='tim', what='ham'),
'tim likes ham')

def test_invalid_placeholders(self):
raises = self.assertRaises
s = Template('$who likes $')
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
Fix :class:`string.Template` raising a spurious :exc:`ValueError` when the
*pattern* attribute is a compiled regular expression object, which the
documentation allows. On the free-threaded build this also occurred as a data
race on the first concurrent use.
Loading