Skip to content

gh-135573: Make pickled lists, sets and dicts a tiny bit smaller #144162

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

Open
serhiy-storchaka wants to merge 1 commit into
base: main
Choose a base branch
from
+39 −40
Open

gh-135573: Make pickled lists, sets and dicts a tiny bit smaller #144162

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
79 changes: 39 additions & 40 deletions Modules/_pickle.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3034,11 +3034,6 @@ batch_list(PickleState *state, PicklerObject *self, PyObject *iter, PyObject *or

assert(iter != NULL);

/* XXX: I think this function could be made faster by avoiding the
iterator interface and fetching objects directly from list using
PyList_GET_ITEM.
*/

if (self->proto == 0) {
/* APPENDS isn't available; do one at a time. */
for (;; total++) {
Expand Down Expand Up @@ -3160,24 +3155,24 @@ batch_list_exact(PickleState *state, PicklerObject *self, PyObject *obj)
assert(obj != NULL);
assert(self->proto > 0);
assert(PyList_CheckExact(obj));

if (PyList_GET_SIZE(obj) == 1) {
item = PyList_GET_ITEM(obj, 0);
Py_INCREF(item);
int err = save(state, self, item, 0);
Py_DECREF(item);
if (err < 0) {
_PyErr_FormatNote("when serializing %T item 0", obj);
return -1;
}
if (_Pickler_Write(self, &append_op, 1) < 0)
return -1;
return 0;
}
assert(PyList_GET_SIZE(obj));

/* Write in batches of BATCHSIZE. */
total = 0;
do {
if (PyList_GET_SIZE(obj) - total == 1) {
item = PyList_GET_ITEM(obj, total);
Py_INCREF(item);
int err = save(state, self, item, 0);
Py_DECREF(item);
if (err < 0) {
_PyErr_FormatNote("when serializing %T item %zd", obj, total);
return -1;
}
if (_Pickler_Write(self, &append_op, 1) < 0)
return -1;
return 0;
}
this_batch = 0;
if (_Pickler_Write(self, &mark_op, 1) < 0)
return -1;
Expand Down Expand Up @@ -3438,28 +3433,29 @@ batch_dict_exact(PickleState *state, PicklerObject *self, PyObject *obj)
assert(self->proto > 0);

dict_size = PyDict_GET_SIZE(obj);

/* Special-case len(d) == 1 to save space. */
if (dict_size == 1) {
PyDict_Next(obj, &ppos, &key, &value);
Py_INCREF(key);
Py_INCREF(value);
if (save(state, self, key, 0) < 0) {
goto error;
}
if (save(state, self, value, 0) < 0) {
_PyErr_FormatNote("when serializing %T item %R", obj, key);
goto error;
}
Py_CLEAR(key);
Py_CLEAR(value);
if (_Pickler_Write(self, &setitem_op, 1) < 0)
return -1;
return 0;
}
assert(dict_size);

/* Write in batches of BATCHSIZE. */
Py_ssize_t total = 0;
do {
if (dict_size - total == 1) {
PyDict_Next(obj, &ppos, &key, &value);
Py_INCREF(key);
Py_INCREF(value);
if (save(state, self, key, 0) < 0) {
goto error;
}
if (save(state, self, value, 0) < 0) {
_PyErr_FormatNote("when serializing %T item %R", obj, key);
goto error;
}
Py_CLEAR(key);
Py_CLEAR(value);
if (_Pickler_Write(self, &setitem_op, 1) < 0)
return -1;
return 0;
}

i = 0;
if (_Pickler_Write(self, &mark_op, 1) < 0)
return -1;
Expand All @@ -3475,6 +3471,7 @@ batch_dict_exact(PickleState *state, PicklerObject *self, PyObject *obj)
}
Py_CLEAR(key);
Py_CLEAR(value);
total++;
if (++i == BATCHSIZE)
break;
}
Expand All @@ -3487,7 +3484,7 @@ batch_dict_exact(PickleState *state, PicklerObject *self, PyObject *obj)
return -1;
}

} while (i == BATCHSIZE);
} while (total < dict_size);
return 0;
error:
Py_XDECREF(key);
Expand Down Expand Up @@ -3605,6 +3602,7 @@ save_set(PickleState *state, PicklerObject *self, PyObject *obj)
return 0; /* nothing to do */

/* Write in batches of BATCHSIZE. */
Py_ssize_t total = 0;
do {
i = 0;
if (_Pickler_Write(self, &mark_op, 1) < 0)
Expand All @@ -3619,6 +3617,7 @@ save_set(PickleState *state, PicklerObject *self, PyObject *obj)
_PyErr_FormatNote("when serializing %T element", obj);
break;
}
total++;
if (++i == BATCHSIZE)
break;
}
Expand All @@ -3634,7 +3633,7 @@ save_set(PickleState *state, PicklerObject *self, PyObject *obj)
"set changed size during iteration");
return -1;
}
} while (i == BATCHSIZE);
} while (total < set_size);

return 0;
}
Expand Down
Loading