FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

gh-157710: Avoid resize in PyUnicodeWriter_Finish() for singleton by vstinner · Pull Request #157862 · python/cpython · GitHub

  1. python
  2. cpython

Repository navigation

gh-157710: Avoid resize in PyUnicodeWriter_Finish() for singleton #157862

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
vstinner merged 2 commits into from
Sep 20, 2026
Conversation 0 Commits 2 Checks 50 Files changed
Merged

gh-157710: Avoid resize in PyUnicodeWriter_Finish() for singleton #157862

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b8bd7cc
gh-157710: Avoid resize in PyUnicodeWriter_Finish() for singleton
vstinner Sep 20, 2026
f24dd57
Use final_size, not length
vstinner Sep 20, 2026
File filter

Filter by extension

Filter by extension .c  (2) .py  (1) All 2 file types selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
7 changes: 7 additions & 0 deletions Lib/test/test_capi/test_unicode.py
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -2050,12 +2050,19 @@ def test_singletons(self):
for size in (0, 123):
with self.subTest(size=size):
writer = self.create_writer(size)
writer.write_utf8(b'utf8', 0)
writer.write_ascii(b'ascii', 0)
writer.write_widechar(b'wstr', 0)
writer.write_ucs4(b'ucs4', 0)
writer.write_substring('text', 0, 0)
self.assertIs(writer.finish(), '')

for ch in range(256):
with self.subTest(ch=ch):
ch = chr(ch)
writer = self.create_writer(0)
# Use PyUnicodeWriter_WriteSubstring() to avoid the read-only
# buffer optimization
writer.write_substring(ch + 'xxx', 0, 1)
self.assertIs(writer.finish(), ch)

Expand Down
11 changes: 5 additions & 6 deletions Objects/bytesobject.c
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -3938,19 +3938,18 @@ PyBytesWriter_FinishWithSize(PyBytesWriter *writer, Py_ssize_t size)
}
}
else {
if (size != PyBytes_GET_SIZE(writer->obj)) {
if (_PyBytes_Resize(&writer->obj, size)) {
goto error;
}
}

if (size == 1) {
// Get the single byte singleton
unsigned char ch = PyBytes_AS_STRING(writer->obj)[0];
PyObject *op = (PyObject*)CHARACTER(ch);
assert(_Py_IsImmortal(op));
Py_SETREF(writer->obj, op);
}
else if (size != PyBytes_GET_SIZE(writer->obj)) {
if (_PyBytes_Resize(&writer->obj, size)) {
goto error;
}
}
}

result = writer->obj;
Expand Down
35 changes: 19 additions & 16 deletions Objects/unicode_writer.c
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -609,8 +609,6 @@ _PyUnicodeWriter_WriteLatin1String(_PyUnicodeWriter *writer,
PyObject *
_PyUnicodeWriter_Finish(_PyUnicodeWriter *writer)
{
PyObject *str;

#ifdef Py_DEBUG
// Check for buffer overflow
if (writer->buffer != NULL) {
Expand All @@ -625,23 +623,28 @@ _PyUnicodeWriter_Finish(_PyUnicodeWriter *writer)
}
#endif

if (writer->pos == 0) {
Py_CLEAR(writer->buffer);
return _PyUnicode_GetEmpty();
}

str = writer->buffer;
PyObject *str = writer->buffer;
writer->buffer = NULL;

if (writer->readonly) {
assert(PyUnicode_GET_LENGTH(str) == writer->pos);
assert(_PyUnicode_CheckConsistency(str, 1));
return str;
Py_ssize_t final_size = writer->pos;
if (final_size == 0) {
PyObject *empty = _PyUnicode_GetEmpty();
Py_XDECREF(str); // writer->buffer can be NULL if the position is 0
return empty;
}

if (PyUnicode_GET_LENGTH(str) != writer->pos) {
PyObject *str2;
str2 = _PyUnicode_ResizeCompact(str, writer->pos);
Py_ssize_t length = PyUnicode_GET_LENGTH(str);
if (final_size == 1 && PyUnicode_KIND(str) == PyUnicode_1BYTE_KIND) {
assert(length >= 1);
const Py_UCS1 *data = PyUnicode_1BYTE_DATA(str);
Py_UCS1 ch = data[0];
PyObject *latin1_char = _Py_LATIN1_CHR(ch);
Py_DECREF(str);
return latin1_char;
}

if (!writer->readonly && length != final_size) {
PyObject *str2 = _PyUnicode_ResizeCompact(str, final_size);
if (str2 == NULL) {
Py_DECREF(str);
return NULL;
Expand All @@ -650,7 +653,7 @@ _PyUnicodeWriter_Finish(_PyUnicodeWriter *writer)
}

assert(_PyUnicode_CheckConsistency(str, 1));
return _PyUnicode_Result(str);
return str;
}


Expand Down
Loading
Back | FazBrowse Home | New Git URL