Skip to content

bpo-1635741 unicodedata #21375

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

Closed
koubaa wants to merge 4 commits into from
Closed

bpo-1635741 unicodedata #21375

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
954fd68
port unicodedata to multi-phase init
koubaa Jul 7, 2020
0b3b0c0
fix type check
koubaa Jul 7, 2020
751081e
fix issue and blurb
koubaa Jul 7, 2020
1cba0bc
update code
koubaa Jul 8, 2020
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
Next Next commit
port unicodedata to multi-phase init
  • Loading branch information
@koubaa
koubaa committed Jul 7, 2020
commit 954fd688137ec09d88ab1437d44c442a00816a08
157 changes: 78 additions & 79 deletions Modules/unicodedata.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,6 +26,18 @@ _Py_IDENTIFIER(NFD);
_Py_IDENTIFIER(NFKC);
_Py_IDENTIFIER(NFKD);

typedef struct {
PyTypeObject *ucd_type;
} UnicodeDataState;

static inline UnicodeDataState*
unicodedata_get_state(PyObject *module)
{
void *state = PyModule_GetState(module);
assert(state != NULL);
return (UnicodeDataState *)state;
}

/*[clinic input]
module unicodedata
class unicodedata.UCD 'PreviousDBVersion *' '&UCD_Type'
Expand Down Expand Up @@ -90,22 +102,28 @@ static PyMemberDef DB_members[] = {
{NULL}
};

/* forward declaration */
static PyTypeObject UCD_Type;
#define UCD_Check(o) Py_IS_TYPE(o, &UCD_Type)
inline int UCD_Check(PyObject *o)
{
UnicodeDataState *state;
state = PyType_GetModuleState(Py_TYPE(o));
return Py_IS_TYPE(o, state->ucd_type);
}

static PyObject*
new_previous_version(const char*name, const change_record* (*getrecord)(Py_UCS4),
new_previous_version(PyObject *module, const char*name, const change_record* (*getrecord)(Py_UCS4),
Py_UCS4 (*normalization)(Py_UCS4))
{
PreviousDBVersion *self;
self = PyObject_New(PreviousDBVersion, &UCD_Type);
if (self == NULL)
return NULL;
self->name = name;
self->getrecord = getrecord;
self->normalization = normalization;
return (PyObject*)self;
UnicodeDataState* st;
PreviousDBVersion *self;

st = unicodedata_get_state(module);
self = PyObject_New(PreviousDBVersion, st->ucd_type);
if (self == NULL)
return NULL;
self->name = name;
self->getrecord = getrecord;
self->normalization = normalization;
return (PyObject*)self;
}


Expand Down Expand Up @@ -1384,50 +1402,19 @@ static PyMethodDef unicodedata_functions[] = {
{NULL, NULL} /* sentinel */
};

static PyTypeObject UCD_Type = {
/* The ob_type field must be initialized in the module init function
* to be portable to Windows without using C++. */
PyVarObject_HEAD_INIT(NULL, 0)
"unicodedata.UCD", /*tp_name*/
sizeof(PreviousDBVersion), /*tp_basicsize*/
0, /*tp_itemsize*/
/* methods */
(destructor)PyObject_Del, /*tp_dealloc*/
0, /*tp_vectorcall_offset*/
0, /*tp_getattr*/
0, /*tp_setattr*/
0, /*tp_as_async*/
0, /*tp_repr*/
0, /*tp_as_number*/
0, /*tp_as_sequence*/
0, /*tp_as_mapping*/
0, /*tp_hash*/
0, /*tp_call*/
0, /*tp_str*/
PyObject_GenericGetAttr,/*tp_getattro*/
0, /*tp_setattro*/
0, /*tp_as_buffer*/
Py_TPFLAGS_DEFAULT, /*tp_flags*/
0, /*tp_doc*/
0, /*tp_traverse*/
0, /*tp_clear*/
0, /*tp_richcompare*/
0, /*tp_weaklistoffset*/
0, /*tp_iter*/
0, /*tp_iternext*/
unicodedata_functions, /*tp_methods*/
DB_members, /*tp_members*/
0, /*tp_getset*/
0, /*tp_base*/
0, /*tp_dict*/
0, /*tp_descr_get*/
0, /*tp_descr_set*/
0, /*tp_dictoffset*/
0, /*tp_init*/
0, /*tp_alloc*/
0, /*tp_new*/
0, /*tp_free*/
0, /*tp_is_gc*/
static PyType_Slot unicodedata_ucd_type_slots[] = {
{Py_tp_dealloc, PyObject_Del},
{Py_tp_getattro, PyObject_GenericGetAttr},
{Py_tp_methods, unicodedata_functions},
{Py_tp_members, DB_members},
{0,0}
};

static PyType_Spec unicodedata_ucd_type_spec = {
.name = "unicodedata.UCD",
.basicsize = sizeof(PreviousDBVersion),
.flags = Py_TPFLAGS_DEFAULT,
.slots = unicodedata_ucd_type_slots
};

PyDoc_STRVAR(unicodedata_docstring,
Expand All @@ -1439,43 +1426,55 @@ this database is based on the UnicodeData.txt file version\n\
The module uses the same names and symbols as defined by the\n\
UnicodeData File Format " UNIDATA_VERSION ".");

static struct PyModuleDef unicodedatamodule = {
PyModuleDef_HEAD_INIT,
"unicodedata",
unicodedata_docstring,
-1,
unicodedata_functions,
NULL,
NULL,
NULL,
NULL
};

PyMODINIT_FUNC
PyInit_unicodedata(void)
static int unicodedata_exec(PyObject *m)
{
PyObject *m, *v;
PyObject *v;
UnicodeDataState* st;

Py_SET_TYPE(&UCD_Type, &PyType_Type);
st = unicodedata_get_state(m);
Comment thread
koubaa marked this conversation as resolved.
Outdated

m = PyModule_Create(&unicodedatamodule);
if (!m)
return NULL;
st->ucd_type = (PyTypeObject *)PyType_FromModuleAndSpec(m, &unicodedata_ucd_type_spec, NULL);
if (st->ucd_type == NULL) {
return -1;
}

PyModule_AddStringConstant(m, "unidata_version", UNIDATA_VERSION);
Py_INCREF(&UCD_Type);
PyModule_AddObject(m, "UCD", (PyObject*)&UCD_Type);

Py_INCREF(st->ucd_type);
if (PyModule_AddObject(m, "UCD", (PyObject*)st->ucd_type) < 0) {
Py_DECREF(st->ucd_type);
return -1;
}

/* Previous versions */
v = new_previous_version("3.2.0", get_change_3_2_0, normalization_3_2_0);
v = new_previous_version(m, "3.2.0", get_change_3_2_0, normalization_3_2_0);
if (v != NULL)
PyModule_AddObject(m, "ucd_3_2_0", v);

@vstinner vstinner Jul 7, 2020

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Please add error checking. For this call and other calls. Be careful, PyModule_AddObject() only requires DECREF on error!


/* Export C API */
v = PyCapsule_New((void *)&hashAPI, PyUnicodeData_CAPSULE_NAME, NULL);
if (v != NULL)
Comment thread
koubaa marked this conversation as resolved.
Outdated
PyModule_AddObject(m, "ucnhash_CAPI", v);
return m;
return 0;
}

static PyModuleDef_Slot unicodedata_slots[] = {
{Py_mod_exec, unicodedata_exec},
{0, NULL}
};

static struct PyModuleDef unicodedata_module = {
PyModuleDef_HEAD_INIT,
.m_name = "unicodedata",
Comment thread
koubaa marked this conversation as resolved.
.m_size = sizeof(UnicodeDataState),
.m_methods = unicodedata_functions,
.m_slots = unicodedata_slots,
};

PyMODINIT_FUNC
PyInit_unicodedata(void)
{
return PyModuleDef_Init(&unicodedata_module);
}

/*
Expand Down