Skip to content

GH-96458: Statically initialize utf8 representation of static strings #96481

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 2 commits into from
Sep 3, 2022
Merged

GH-96458: Statically initialize utf8 representation of static strings #96481

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
1ee2f54
static initialize utf8 representation
kumaraditya303 Aug 31, 2022
c15d97d
fix global objects
kumaraditya303 Sep 1, 2022
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
4 changes: 3 additions & 1 deletion Include/internal/pycore_runtime_init.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,10 +113,12 @@ extern "C" {
._ ## NAME = _PyASCIIObject_INIT(LITERAL)
#define INIT_ID(NAME) \
._ ## NAME = _PyASCIIObject_INIT(#NAME)
#define _PyUnicode_LATIN1_INIT(LITERAL) \
#define _PyUnicode_LATIN1_INIT(LITERAL, UTF8) \
{ \
._latin1 = { \
._base = _PyUnicode_ASCII_BASE_INIT((LITERAL), 0), \
.utf8 = (UTF8), \
.utf8_length = sizeof(UTF8) - 1, \
}, \
._data = (LITERAL), \
}
Expand Down
256 changes: 128 additions & 128 deletions Include/internal/pycore_runtime_init_generated.h
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 0 additions & 1 deletion Include/internal/pycore_unicodeobject.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,6 @@ extern PyStatus _PyUnicode_InitGlobalObjects(PyInterpreterState *);
extern PyStatus _PyUnicode_InitTypes(PyInterpreterState *);
extern void _PyUnicode_Fini(PyInterpreterState *);
extern void _PyUnicode_FiniTypes(PyInterpreterState *);
extern void _PyStaticUnicode_Dealloc(PyObject *);

extern PyTypeObject _PyUnicodeASCIIIter_Type;

Expand Down
33 changes: 0 additions & 33 deletions Objects/unicodeobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15184,23 +15184,6 @@ _PyUnicode_FiniTypes(PyInterpreterState *interp)
}


static void unicode_static_dealloc(PyObject *op)
{
PyASCIIObject *ascii = _PyASCIIObject_CAST(op);

assert(ascii->state.compact);

if (!ascii->state.ascii) {
PyCompactUnicodeObject* compact = (PyCompactUnicodeObject*)op;
if (compact->utf8) {
PyObject_Free(compact->utf8);
compact->utf8 = NULL;
compact->utf8_length = 0;
}
}
}


void
_PyUnicode_Fini(PyInterpreterState *interp)
{
Expand All @@ -15217,24 +15200,8 @@ _PyUnicode_Fini(PyInterpreterState *interp)
_PyUnicode_FiniEncodings(&state->fs_codec);

unicode_clear_identifiers(state);

// Clear the single character singletons
for (int i = 0; i < 128; i++) {
unicode_static_dealloc((PyObject*)&_Py_SINGLETON(strings).ascii[i]);
}
for (int i = 0; i < 128; i++) {
unicode_static_dealloc((PyObject*)&_Py_SINGLETON(strings).latin1[i]);
}
}


void
_PyStaticUnicode_Dealloc(PyObject *op)
{
unicode_static_dealloc(op);
}


/* A _string module, to export formatter_parser and formatter_field_name_split
to the string.Formatter class implemented in Python. */

Expand Down
4 changes: 3 additions & 1 deletion Tools/scripts/deepfreeze.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -195,7 +195,6 @@ def generate_unicode(self, name: str, s: str) -> str:
else:
self.write("PyCompactUnicodeObject _compact;")
self.write(f"{datatype} _data[{len(s)+1}];")
self.deallocs.append(f"_PyStaticUnicode_Dealloc((PyObject *)&{name});")
with self.block(f"{name} =", ";"):
if ascii:
with self.block("._ascii =", ","):
Expand All @@ -218,6 +217,9 @@ def generate_unicode(self, name: str, s: str) -> str:
self.write(f".kind = {kind},")
self.write(".compact = 1,")
self.write(".ascii = 0,")
utf8 = s.encode('utf-8')
self.write(f'.utf8 = {make_string_literal(utf8)},')
self.write(f'.utf8_length = {len(utf8)},')
with self.block(f"._data =", ","):
for i in range(0, len(s), 16):
data = s[i:i+16]
Expand Down
6 changes: 5 additions & 1 deletion Tools/scripts/generate_global_objects.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -287,7 +287,11 @@ def generate_runtime_init(identifiers, strings):
immortal_objects.append(f'(PyObject *)&_Py_SINGLETON(strings).ascii[{i}]')
with printer.block('.latin1 =', ','):
for i in range(128, 256):
printer.write(f'_PyUnicode_LATIN1_INIT("\\x{i:02x}"),')
utf8 = ['"']
for c in chr(i).encode('utf-8'):
utf8.append(f"\\x{c:02x}")
utf8.append('"')
printer.write(f'_PyUnicode_LATIN1_INIT("\\x{i:02x}", {"".join(utf8)}),')
immortal_objects.append(f'(PyObject *)&_Py_SINGLETON(strings).latin1[{i} - 128]')
printer.write('')
with printer.block('.tuple_empty =', ','):
Expand Down