Skip to content

bpo-46881: Statically allocate and initialize the latin1 characters. #31616

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
miss-islington merged 8 commits into from
Mar 9, 2022
Merged

bpo-46881: Statically allocate and initialize the latin1 characters. #31616

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
574e0b6
static latin1
kumaraditya303 Mar 3, 2022
62720ff
📜🤖 Added by blurb_it.
blurb-it[bot] Mar 3, 2022
7bf2ac5
fmt macro
kumaraditya303 Mar 3, 2022
366810f
Update Objects/unicodeobject.c
kumaraditya303 Mar 4, 2022
fd3676b
add assertions for _PyUnicode_CheckConsistency for latin1 characters
kumaraditya303 Mar 4, 2022
be04d68
refactor macro
kumaraditya303 Mar 4, 2022
7f88519
code review
kumaraditya303 Mar 5, 2022
f9d1a87
rename macro
kumaraditya303 Mar 5, 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
8 changes: 8 additions & 0 deletions Include/internal/pycore_global_strings.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -348,6 +348,14 @@ struct _Py_global_strings {
STRUCT_FOR_ID(write)
STRUCT_FOR_ID(zipimporter)
} identifiers;
struct {
PyASCIIObject _ascii;
uint8_t _data[2];
} ascii[128];
struct {
PyCompactUnicodeObject _latin1;
uint8_t _data[2];
} latin1[128];
};
/* End auto-generated code */

Expand Down
278 changes: 277 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 @@ -112,7 +112,23 @@ extern "C" {
._ ## NAME = _PyASCIIObject_INIT(LITERAL)
#define INIT_ID(NAME) \
._ ## NAME = _PyASCIIObject_INIT(#NAME)

#define _PyCompactUnicodeObject_INIT(LITERAL) \
{ \
._latin1 = { \
._base = { \
.ob_base = _PyObject_IMMORTAL_INIT(&PyUnicode_Type), \
.length = sizeof(LITERAL) - 1, \
.hash = -1, \
.state = { \
.kind = 1, \
.compact = 1, \
.ascii = 0, \
.ready = 1, \
}, \
}, \
}, \
._data = LITERAL, \
}

/* The following is auto-generated by Tools/scripts/generate_global_objects.py. */
#define _Py_global_objects_INIT { \
Expand Down Expand Up @@ -963,6 +979,266 @@ extern "C" {
INIT_ID(write), \
INIT_ID(zipimporter), \
}, \
.ascii = { \
_PyASCIIObject_INIT("\x00"), \
_PyASCIIObject_INIT("\x01"), \
_PyASCIIObject_INIT("\x02"), \
_PyASCIIObject_INIT("\x03"), \
_PyASCIIObject_INIT("\x04"), \
_PyASCIIObject_INIT("\x05"), \
_PyASCIIObject_INIT("\x06"), \
_PyASCIIObject_INIT("\x07"), \
_PyASCIIObject_INIT("\x08"), \
_PyASCIIObject_INIT("\x09"), \
_PyASCIIObject_INIT("\x0a"), \
_PyASCIIObject_INIT("\x0b"), \
_PyASCIIObject_INIT("\x0c"), \
_PyASCIIObject_INIT("\x0d"), \
_PyASCIIObject_INIT("\x0e"), \
_PyASCIIObject_INIT("\x0f"), \
_PyASCIIObject_INIT("\x10"), \
_PyASCIIObject_INIT("\x11"), \
_PyASCIIObject_INIT("\x12"), \
_PyASCIIObject_INIT("\x13"), \
_PyASCIIObject_INIT("\x14"), \
_PyASCIIObject_INIT("\x15"), \
_PyASCIIObject_INIT("\x16"), \
_PyASCIIObject_INIT("\x17"), \
_PyASCIIObject_INIT("\x18"), \
_PyASCIIObject_INIT("\x19"), \
_PyASCIIObject_INIT("\x1a"), \
_PyASCIIObject_INIT("\x1b"), \
_PyASCIIObject_INIT("\x1c"), \
_PyASCIIObject_INIT("\x1d"), \
_PyASCIIObject_INIT("\x1e"), \
_PyASCIIObject_INIT("\x1f"), \
_PyASCIIObject_INIT("\x20"), \
_PyASCIIObject_INIT("\x21"), \
_PyASCIIObject_INIT("\x22"), \
_PyASCIIObject_INIT("\x23"), \
_PyASCIIObject_INIT("\x24"), \
_PyASCIIObject_INIT("\x25"), \
_PyASCIIObject_INIT("\x26"), \
_PyASCIIObject_INIT("\x27"), \
_PyASCIIObject_INIT("\x28"), \
_PyASCIIObject_INIT("\x29"), \
_PyASCIIObject_INIT("\x2a"), \
_PyASCIIObject_INIT("\x2b"), \
_PyASCIIObject_INIT("\x2c"), \
_PyASCIIObject_INIT("\x2d"), \
_PyASCIIObject_INIT("\x2e"), \
_PyASCIIObject_INIT("\x2f"), \
_PyASCIIObject_INIT("\x30"), \
_PyASCIIObject_INIT("\x31"), \
_PyASCIIObject_INIT("\x32"), \
_PyASCIIObject_INIT("\x33"), \
_PyASCIIObject_INIT("\x34"), \
_PyASCIIObject_INIT("\x35"), \
_PyASCIIObject_INIT("\x36"), \
_PyASCIIObject_INIT("\x37"), \
_PyASCIIObject_INIT("\x38"), \
_PyASCIIObject_INIT("\x39"), \
_PyASCIIObject_INIT("\x3a"), \
_PyASCIIObject_INIT("\x3b"), \
_PyASCIIObject_INIT("\x3c"), \
_PyASCIIObject_INIT("\x3d"), \
_PyASCIIObject_INIT("\x3e"), \
_PyASCIIObject_INIT("\x3f"), \
_PyASCIIObject_INIT("\x40"), \
_PyASCIIObject_INIT("\x41"), \
_PyASCIIObject_INIT("\x42"), \
_PyASCIIObject_INIT("\x43"), \
_PyASCIIObject_INIT("\x44"), \
_PyASCIIObject_INIT("\x45"), \
_PyASCIIObject_INIT("\x46"), \
_PyASCIIObject_INIT("\x47"), \
_PyASCIIObject_INIT("\x48"), \
_PyASCIIObject_INIT("\x49"), \
_PyASCIIObject_INIT("\x4a"), \
_PyASCIIObject_INIT("\x4b"), \
_PyASCIIObject_INIT("\x4c"), \
_PyASCIIObject_INIT("\x4d"), \
_PyASCIIObject_INIT("\x4e"), \
_PyASCIIObject_INIT("\x4f"), \
_PyASCIIObject_INIT("\x50"), \
_PyASCIIObject_INIT("\x51"), \
_PyASCIIObject_INIT("\x52"), \
_PyASCIIObject_INIT("\x53"), \
_PyASCIIObject_INIT("\x54"), \
_PyASCIIObject_INIT("\x55"), \
_PyASCIIObject_INIT("\x56"), \
_PyASCIIObject_INIT("\x57"), \
_PyASCIIObject_INIT("\x58"), \
_PyASCIIObject_INIT("\x59"), \
_PyASCIIObject_INIT("\x5a"), \
_PyASCIIObject_INIT("\x5b"), \
_PyASCIIObject_INIT("\x5c"), \
_PyASCIIObject_INIT("\x5d"), \
_PyASCIIObject_INIT("\x5e"), \
_PyASCIIObject_INIT("\x5f"), \
_PyASCIIObject_INIT("\x60"), \
_PyASCIIObject_INIT("\x61"), \
_PyASCIIObject_INIT("\x62"), \
_PyASCIIObject_INIT("\x63"), \
_PyASCIIObject_INIT("\x64"), \
_PyASCIIObject_INIT("\x65"), \
_PyASCIIObject_INIT("\x66"), \
_PyASCIIObject_INIT("\x67"), \
_PyASCIIObject_INIT("\x68"), \
_PyASCIIObject_INIT("\x69"), \
_PyASCIIObject_INIT("\x6a"), \
_PyASCIIObject_INIT("\x6b"), \
_PyASCIIObject_INIT("\x6c"), \
_PyASCIIObject_INIT("\x6d"), \
_PyASCIIObject_INIT("\x6e"), \
_PyASCIIObject_INIT("\x6f"), \
_PyASCIIObject_INIT("\x70"), \
_PyASCIIObject_INIT("\x71"), \
_PyASCIIObject_INIT("\x72"), \
_PyASCIIObject_INIT("\x73"), \
_PyASCIIObject_INIT("\x74"), \
_PyASCIIObject_INIT("\x75"), \
_PyASCIIObject_INIT("\x76"), \
_PyASCIIObject_INIT("\x77"), \
_PyASCIIObject_INIT("\x78"), \
_PyASCIIObject_INIT("\x79"), \
_PyASCIIObject_INIT("\x7a"), \
_PyASCIIObject_INIT("\x7b"), \
_PyASCIIObject_INIT("\x7c"), \
_PyASCIIObject_INIT("\x7d"), \
_PyASCIIObject_INIT("\x7e"), \
_PyASCIIObject_INIT("\x7f"), \
}, \
.latin1 = { \
_PyCompactUnicodeObject_INIT("\x80"), \
_PyCompactUnicodeObject_INIT("\x81"), \
_PyCompactUnicodeObject_INIT("\x82"), \
_PyCompactUnicodeObject_INIT("\x83"), \
_PyCompactUnicodeObject_INIT("\x84"), \
_PyCompactUnicodeObject_INIT("\x85"), \
_PyCompactUnicodeObject_INIT("\x86"), \
_PyCompactUnicodeObject_INIT("\x87"), \
_PyCompactUnicodeObject_INIT("\x88"), \
_PyCompactUnicodeObject_INIT("\x89"), \
_PyCompactUnicodeObject_INIT("\x8a"), \
_PyCompactUnicodeObject_INIT("\x8b"), \
_PyCompactUnicodeObject_INIT("\x8c"), \
_PyCompactUnicodeObject_INIT("\x8d"), \
_PyCompactUnicodeObject_INIT("\x8e"), \
_PyCompactUnicodeObject_INIT("\x8f"), \
_PyCompactUnicodeObject_INIT("\x90"), \
_PyCompactUnicodeObject_INIT("\x91"), \
_PyCompactUnicodeObject_INIT("\x92"), \
_PyCompactUnicodeObject_INIT("\x93"), \
_PyCompactUnicodeObject_INIT("\x94"), \
_PyCompactUnicodeObject_INIT("\x95"), \
_PyCompactUnicodeObject_INIT("\x96"), \
_PyCompactUnicodeObject_INIT("\x97"), \
_PyCompactUnicodeObject_INIT("\x98"), \
_PyCompactUnicodeObject_INIT("\x99"), \
_PyCompactUnicodeObject_INIT("\x9a"), \
_PyCompactUnicodeObject_INIT("\x9b"), \
_PyCompactUnicodeObject_INIT("\x9c"), \
_PyCompactUnicodeObject_INIT("\x9d"), \
_PyCompactUnicodeObject_INIT("\x9e"), \
_PyCompactUnicodeObject_INIT("\x9f"), \
_PyCompactUnicodeObject_INIT("\xa0"), \
_PyCompactUnicodeObject_INIT("\xa1"), \
_PyCompactUnicodeObject_INIT("\xa2"), \
_PyCompactUnicodeObject_INIT("\xa3"), \
_PyCompactUnicodeObject_INIT("\xa4"), \
_PyCompactUnicodeObject_INIT("\xa5"), \
_PyCompactUnicodeObject_INIT("\xa6"), \
_PyCompactUnicodeObject_INIT("\xa7"), \
_PyCompactUnicodeObject_INIT("\xa8"), \
_PyCompactUnicodeObject_INIT("\xa9"), \
_PyCompactUnicodeObject_INIT("\xaa"), \
_PyCompactUnicodeObject_INIT("\xab"), \
_PyCompactUnicodeObject_INIT("\xac"), \
_PyCompactUnicodeObject_INIT("\xad"), \
_PyCompactUnicodeObject_INIT("\xae"), \
_PyCompactUnicodeObject_INIT("\xaf"), \
_PyCompactUnicodeObject_INIT("\xb0"), \
_PyCompactUnicodeObject_INIT("\xb1"), \
_PyCompactUnicodeObject_INIT("\xb2"), \
_PyCompactUnicodeObject_INIT("\xb3"), \
_PyCompactUnicodeObject_INIT("\xb4"), \
_PyCompactUnicodeObject_INIT("\xb5"), \
_PyCompactUnicodeObject_INIT("\xb6"), \
_PyCompactUnicodeObject_INIT("\xb7"), \
_PyCompactUnicodeObject_INIT("\xb8"), \
_PyCompactUnicodeObject_INIT("\xb9"), \
_PyCompactUnicodeObject_INIT("\xba"), \
_PyCompactUnicodeObject_INIT("\xbb"), \
_PyCompactUnicodeObject_INIT("\xbc"), \
_PyCompactUnicodeObject_INIT("\xbd"), \
_PyCompactUnicodeObject_INIT("\xbe"), \
_PyCompactUnicodeObject_INIT("\xbf"), \
_PyCompactUnicodeObject_INIT("\xc0"), \
_PyCompactUnicodeObject_INIT("\xc1"), \
_PyCompactUnicodeObject_INIT("\xc2"), \
_PyCompactUnicodeObject_INIT("\xc3"), \
_PyCompactUnicodeObject_INIT("\xc4"), \
_PyCompactUnicodeObject_INIT("\xc5"), \
_PyCompactUnicodeObject_INIT("\xc6"), \
_PyCompactUnicodeObject_INIT("\xc7"), \
_PyCompactUnicodeObject_INIT("\xc8"), \
_PyCompactUnicodeObject_INIT("\xc9"), \
_PyCompactUnicodeObject_INIT("\xca"), \
_PyCompactUnicodeObject_INIT("\xcb"), \
_PyCompactUnicodeObject_INIT("\xcc"), \
_PyCompactUnicodeObject_INIT("\xcd"), \
_PyCompactUnicodeObject_INIT("\xce"), \
_PyCompactUnicodeObject_INIT("\xcf"), \
_PyCompactUnicodeObject_INIT("\xd0"), \
_PyCompactUnicodeObject_INIT("\xd1"), \
_PyCompactUnicodeObject_INIT("\xd2"), \
_PyCompactUnicodeObject_INIT("\xd3"), \
_PyCompactUnicodeObject_INIT("\xd4"), \
_PyCompactUnicodeObject_INIT("\xd5"), \
_PyCompactUnicodeObject_INIT("\xd6"), \
_PyCompactUnicodeObject_INIT("\xd7"), \
_PyCompactUnicodeObject_INIT("\xd8"), \
_PyCompactUnicodeObject_INIT("\xd9"), \
_PyCompactUnicodeObject_INIT("\xda"), \
_PyCompactUnicodeObject_INIT("\xdb"), \
_PyCompactUnicodeObject_INIT("\xdc"), \
_PyCompactUnicodeObject_INIT("\xdd"), \
_PyCompactUnicodeObject_INIT("\xde"), \
_PyCompactUnicodeObject_INIT("\xdf"), \
_PyCompactUnicodeObject_INIT("\xe0"), \
_PyCompactUnicodeObject_INIT("\xe1"), \
_PyCompactUnicodeObject_INIT("\xe2"), \
_PyCompactUnicodeObject_INIT("\xe3"), \
_PyCompactUnicodeObject_INIT("\xe4"), \
_PyCompactUnicodeObject_INIT("\xe5"), \
_PyCompactUnicodeObject_INIT("\xe6"), \
_PyCompactUnicodeObject_INIT("\xe7"), \
_PyCompactUnicodeObject_INIT("\xe8"), \
_PyCompactUnicodeObject_INIT("\xe9"), \
_PyCompactUnicodeObject_INIT("\xea"), \
_PyCompactUnicodeObject_INIT("\xeb"), \
_PyCompactUnicodeObject_INIT("\xec"), \
_PyCompactUnicodeObject_INIT("\xed"), \
_PyCompactUnicodeObject_INIT("\xee"), \
_PyCompactUnicodeObject_INIT("\xef"), \
_PyCompactUnicodeObject_INIT("\xf0"), \
_PyCompactUnicodeObject_INIT("\xf1"), \
_PyCompactUnicodeObject_INIT("\xf2"), \
_PyCompactUnicodeObject_INIT("\xf3"), \
_PyCompactUnicodeObject_INIT("\xf4"), \
_PyCompactUnicodeObject_INIT("\xf5"), \
_PyCompactUnicodeObject_INIT("\xf6"), \
_PyCompactUnicodeObject_INIT("\xf7"), \
_PyCompactUnicodeObject_INIT("\xf8"), \
_PyCompactUnicodeObject_INIT("\xf9"), \
_PyCompactUnicodeObject_INIT("\xfa"), \
_PyCompactUnicodeObject_INIT("\xfb"), \
_PyCompactUnicodeObject_INIT("\xfc"), \
_PyCompactUnicodeObject_INIT("\xfd"), \
_PyCompactUnicodeObject_INIT("\xfe"), \
_PyCompactUnicodeObject_INIT("\xff"), \
}, \
}, \
\
.tuple_empty = { \
Expand Down
3 changes: 0 additions & 3 deletions Include/internal/pycore_unicodeobject.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,9 +44,6 @@ struct _Py_unicode_ids {
};

struct _Py_unicode_state {
/* Single character Unicode strings in the Latin-1 range are being
shared as well. */
PyObject *latin1[256];
struct _Py_unicode_fs_codec fs_codec;

// Unicode identifiers (_Py_Identifier): see _PyUnicode_FromId()
Expand Down
1 change: 1 addition & 0 deletions Misc/NEWS.d/next/Core and Builtins/2022-03-03-09-08-17.bpo-46881.ckD4tT.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Statically allocate and initialize the latin1 characters.
Loading