Skip to content

gh-125196: Use PyUnicodeWriter for repr(list) #125202

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 5 commits into from
Oct 9, 2024
Merged

gh-125196: Use PyUnicodeWriter for repr(list) #125202

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
8c33f91
gh-125196: Use PyUnicodeWriter for repr(list)
vstinner Oct 9, 2024
5fa3466
Fix error handling
vstinner Oct 9, 2024
0273017
Avoid PyUnicodeWriter_WriteUTF8()
vstinner Oct 9, 2024
8b33b0e
PyUnicodeWriter_Discard(NULL) does nothing
vstinner Oct 9, 2024
9c910b5
Revert "PyUnicodeWriter_Discard(NULL) does nothing"
vstinner Oct 9, 2024
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
43 changes: 21 additions & 22 deletions Objects/listobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -522,49 +522,48 @@ list_dealloc(PyObject *self)
static PyObject *
list_repr_impl(PyListObject *v)
{
PyObject *s;
_PyUnicodeWriter writer;
Py_ssize_t i = Py_ReprEnter((PyObject*)v);
if (i != 0) {
return i > 0 ? PyUnicode_FromString("[...]") : NULL;
int res = Py_ReprEnter((PyObject*)v);
if (res != 0) {
return (res > 0 ? PyUnicode_FromString("[...]") : NULL);
}

_PyUnicodeWriter_Init(&writer);
writer.overallocate = 1;
/* "[" + "1" + ", 2" * (len - 1) + "]" */
writer.min_length = 1 + 1 + (2 + 1) * (Py_SIZE(v) - 1) + 1;
Py_ssize_t prealloc = 1 + 1 + (2 + 1) * (Py_SIZE(v) - 1) + 1;
PyUnicodeWriter *writer = PyUnicodeWriter_Create(prealloc);
if (writer == NULL) {
goto error;
}

if (_PyUnicodeWriter_WriteChar(&writer, '[') < 0)
if (PyUnicodeWriter_WriteChar(writer, '[') < 0) {
goto error;
}

/* Do repr() on each element. Note that this may mutate the list,
so must refetch the list size on each iteration. */
for (i = 0; i < Py_SIZE(v); ++i) {
for (Py_ssize_t i = 0; i < Py_SIZE(v); ++i) {
if (i > 0) {
if (_PyUnicodeWriter_WriteASCIIString(&writer, ", ", 2) < 0)
if (PyUnicodeWriter_WriteChar(writer, ',') < 0) {
goto error;
}
if (PyUnicodeWriter_WriteChar(writer, ' ') < 0) {
goto error;
}
}

s = PyObject_Repr(v->ob_item[i]);
if (s == NULL)
goto error;

if (_PyUnicodeWriter_WriteStr(&writer, s) < 0) {
Py_DECREF(s);
if (PyUnicodeWriter_WriteRepr(writer, v->ob_item[i]) < 0) {
goto error;
}
Py_DECREF(s);
}

writer.overallocate = 0;
if (_PyUnicodeWriter_WriteChar(&writer, ']') < 0)
if (PyUnicodeWriter_WriteChar(writer, ']') < 0) {
goto error;
}

Py_ReprLeave((PyObject *)v);
return _PyUnicodeWriter_Finish(&writer);
return PyUnicodeWriter_Finish(writer);

error:
_PyUnicodeWriter_Dealloc(&writer);
PyUnicodeWriter_Discard(writer);
Py_ReprLeave((PyObject *)v);
return NULL;
}
Expand Down
3 changes: 3 additions & 0 deletions Objects/unicodeobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13428,6 +13428,9 @@ PyUnicodeWriter_Create(Py_ssize_t length)

void PyUnicodeWriter_Discard(PyUnicodeWriter *writer)
{
if (writer == NULL) {
Copy link
Member

Choose a reason for hiding this comment

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

This should be documented. Please do this in a separate PR.

Also, I think it is worth to try to optimize PyUnicodeWriter_WriteUTF8() for short ASCII strings.

Copy link
Member Author

Choose a reason for hiding this comment

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

This should be documented. Please do this in a separate PR.

Oh ok. I reverted the change.

return;
}
_PyUnicodeWriter_Dealloc((_PyUnicodeWriter*)writer);
PyMem_Free(writer);
}
Expand Down
Loading