mirror of
https://github.com/python/cpython.git
synced 2025-07-08 03:45:36 +00:00
gh-113993: Allow interned strings to be mortal, and fix related issues (GH-120520)
* Add an InternalDocs file describing how interning should work and how to use it. * Add internal functions to *explicitly* request what kind of interning is done: - `_PyUnicode_InternMortal` - `_PyUnicode_InternImmortal` - `_PyUnicode_InternStatic` * Switch uses of `PyUnicode_InternInPlace` to those. * Disallow using `_Py_SetImmortal` on strings directly. You should use `_PyUnicode_InternImmortal` instead: - Strings should be interned before immortalization, otherwise you're possibly interning a immortalizing copy. - `_Py_SetImmortal` doesn't handle the `SSTATE_INTERNED_MORTAL` to `SSTATE_INTERNED_IMMORTAL` update, and those flags can't be changed in backports, as they are now part of public API and version-specific ABI. * Add private `_only_immortal` argument for `sys.getunicodeinternedsize`, used in refleak test machinery. * Make sure the statically allocated string singletons are unique. This means these sets are now disjoint: - `_Py_ID` - `_Py_STR` (including the empty string) - one-character latin-1 singletons Now, when you intern a singleton, that exact singleton will be interned. * Add a `_Py_LATIN1_CHR` macro, use it instead of `_Py_ID`/`_Py_STR` for one-character latin-1 singletons everywhere (including Clinic). * Intern `_Py_STR` singletons at startup. * For free-threaded builds, intern `_Py_LATIN1_CHR` singletons at startup. * Beef up the tests. Cover internal details (marked with `@cpython_only`). * Add lots of assertions Co-Authored-By: Eric Snow <ericsnowcurrently@gmail.com>
This commit is contained in:
parent
7595e6743a
commit
6f1d448bc1
42 changed files with 2464 additions and 1140 deletions
|
@ -10,9 +10,7 @@
|
|||
* See ast.unparse for a full unparser (written in Python)
|
||||
*/
|
||||
|
||||
_Py_DECLARE_STR(open_br, "{");
|
||||
_Py_DECLARE_STR(dbl_open_br, "{{");
|
||||
_Py_DECLARE_STR(close_br, "}");
|
||||
_Py_DECLARE_STR(dbl_close_br, "}}");
|
||||
|
||||
/* We would statically initialize this if doing so were simple enough. */
|
||||
|
@ -580,11 +578,13 @@ escape_braces(PyObject *orig)
|
|||
{
|
||||
PyObject *temp;
|
||||
PyObject *result;
|
||||
temp = PyUnicode_Replace(orig, &_Py_STR(open_br), &_Py_STR(dbl_open_br), -1);
|
||||
temp = PyUnicode_Replace(orig, _Py_LATIN1_CHR('{'),
|
||||
&_Py_STR(dbl_open_br), -1);
|
||||
if (!temp) {
|
||||
return NULL;
|
||||
}
|
||||
result = PyUnicode_Replace(temp, &_Py_STR(close_br), &_Py_STR(dbl_close_br), -1);
|
||||
result = PyUnicode_Replace(temp, _Py_LATIN1_CHR('}'),
|
||||
&_Py_STR(dbl_close_br), -1);
|
||||
Py_DECREF(temp);
|
||||
return result;
|
||||
}
|
||||
|
@ -678,7 +678,7 @@ append_formattedvalue(_PyUnicodeWriter *writer, expr_ty e)
|
|||
if (!temp_fv_str) {
|
||||
return -1;
|
||||
}
|
||||
if (PyUnicode_Find(temp_fv_str, &_Py_STR(open_br), 0, 1, 1) == 0) {
|
||||
if (PyUnicode_Find(temp_fv_str, _Py_LATIN1_CHR('{'), 0, 1, 1) == 0) {
|
||||
/* Expression starts with a brace, split it with a space from the outer
|
||||
one. */
|
||||
outer_brace = "{ ";
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue