Skip to content

C
cpython
Kaydet (Commit) 62bb3947 authored tarafından Victor Stinner's avatar Victor Stinner
Dosyalara gözat
Seçenekler

Close #13072: Restore code before the PEP 393 for the array module 

'u' format of the array module uses again Py_UNICODE type for backward
compatibility with Python 3.2.

The only change from Python 3.2 is that PyUnicode_AsUnicode() result is now
checked for NULL value.
üst 3af26174
Hide whitespace changes
Inline Side-by-side
Showing with 56 additions and 41 deletions
Doc/library/array.rst
Dosyayı görüntüle @ 62bb3947
......@@ -21,7 +21,7 @@ defined:
+-----------+--------------------+-------------------+-----------------------+-------+
| ``'B'`` | unsigned char | int | 1 | |
+-----------+--------------------+-------------------+-----------------------+-------+
| ``'u'`` | Py_UCS4 | Unicode character | 4 | |
| ``'u'`` | Py_UNICODE | Unicode character | 2 | \(1) |
+-----------+--------------------+-------------------+-----------------------+-------+
| ``'h'`` | signed short | int | 2 | |
+-----------+--------------------+-------------------+-----------------------+-------+
......@@ -35,9 +35,9 @@ defined:
+-----------+--------------------+-------------------+-----------------------+-------+
| ``'L'`` | unsigned long | int | 4 | |
+-----------+--------------------+-------------------+-----------------------+-------+
| ``'q'`` | signed long long | int | 8 | \(1) |
| ``'q'`` | signed long long | int | 8 | \(2) |
+-----------+--------------------+-------------------+-----------------------+-------+
| ``'Q'`` | unsigned long long | int | 8 | \(1) |
| ``'Q'`` | unsigned long long | int | 8 | \(2) |
+-----------+--------------------+-------------------+-----------------------+-------+
| ``'f'`` | float | float | 4 | |
+-----------+--------------------+-------------------+-----------------------+-------+
......@@ -47,6 +47,11 @@ defined:
Notes:
(1)
The ``'u'`` type code corresponds to Python's unicode character
(:c:type:`Py_UNICODE` which is :c:type:`wchar_t`). Depending on the
platform, it can be 16 bits or 32 bits.
(2)
The ``'q'`` and ``'Q'`` type codes are available only if
the platform C compiler used to build Python supports C :c:type:`long long`,
or, on Windows, :c:type:`__int64`.
......
Modules/arraymodule.c
Dosyayı görüntüle @ 62bb3947
......@@ -174,25 +174,24 @@ BB_setitem(arrayobject *ap, Py_ssize_t i, PyObject *v)
static PyObject *
u_getitem(arrayobject *ap, Py_ssize_t i)
{
return PyUnicode_FromOrdinal(((Py_UCS4 *) ap->ob_item)[i]);
return PyUnicode_FromUnicode(&((Py_UNICODE *) ap->ob_item)[i], 1);
}
static int
u_setitem(arrayobject *ap, Py_ssize_t i, PyObject *v)
{
PyObject *p;
Py_UNICODE *p;
Py_ssize_t len;
if (!PyArg_Parse(v, "U;array item must be unicode character", &p))
return -1;
if (PyUnicode_READY(p))
if (!PyArg_Parse(v, "u#;array item must be unicode character", &p, &len))
return -1;
if (PyUnicode_GET_LENGTH(p) != 1) {
if (len != 1) {
PyErr_SetString(PyExc_TypeError,
"array item must be unicode character");
return -1;
}
if (i >= 0)
((Py_UCS4 *)ap->ob_item)[i] = PyUnicode_READ_CHAR(p, 0);
((Py_UNICODE *)ap->ob_item)[i] = p[0];
return 0;
}
......@@ -444,13 +443,6 @@ d_setitem(arrayobject *ap, Py_ssize_t i, PyObject *v)
return 0;
}
#if SIZEOF_INT == 4
# define STRUCT_LONG_FORMAT "I"
#elif SIZEOF_LONG == 4
# define STRUCT_LONG_FORMAT "L"
#else
# error "Unable to get struct format for Py_UCS4"
#endif
/* Description of types.
*
......@@ -460,7 +452,7 @@ d_setitem(arrayobject *ap, Py_ssize_t i, PyObject *v)
static struct arraydescr descriptors[] = {
{'b', 1, b_getitem, b_setitem, "b", 1, 1},
{'B', 1, BB_getitem, BB_setitem, "B", 1, 0},
{'u', sizeof(Py_UCS4), u_getitem, u_setitem, STRUCT_LONG_FORMAT, 0, 0},
{'u', sizeof(Py_UNICODE), u_getitem, u_setitem, "u", 0, 0},
{'h', sizeof(short), h_getitem, h_setitem, "h", 1, 1},
{'H', sizeof(short), HH_getitem, HH_setitem, "H", 1, 0},
{'i', sizeof(int), i_getitem, i_setitem, "i", 1, 1},
......@@ -1519,26 +1511,25 @@ This method is deprecated. Use tobytes instead.");
static PyObject *
array_fromunicode(arrayobject *self, PyObject *args)
{
PyObject *ustr;
Py_UNICODE *ustr;
Py_ssize_t n;
char typecode;
if (!PyArg_ParseTuple(args, "U:fromunicode", &ustr))
if (!PyArg_ParseTuple(args, "u#:fromunicode", &ustr, &n))
return NULL;
if (self->ob_descr->typecode != 'u') {
typecode = self->ob_descr->typecode;
if ((typecode != 'u')) {
PyErr_SetString(PyExc_ValueError,
"fromunicode() may only be called on "
"unicode type arrays");
return NULL;
}
if (PyUnicode_READY(ustr))
return NULL;
n = PyUnicode_GET_LENGTH(ustr);
if (n > 0) {
Py_ssize_t old_size = Py_SIZE(self);
if (array_resize(self, old_size + n) == -1)
return NULL;
if (!PyUnicode_AsUCS4(ustr, (Py_UCS4 *)self->ob_item + old_size, n, 0))
return NULL;
memcpy(self->ob_item + old_size * sizeof(Py_UNICODE),
ustr, n * sizeof(Py_UNICODE));
}
Py_INCREF(Py_None);
......@@ -1557,14 +1548,14 @@ append Unicode data to an array of some other type.");
static PyObject *
array_tounicode(arrayobject *self, PyObject *unused)
{
if (self->ob_descr->typecode != 'u') {
char typecode;
typecode = self->ob_descr->typecode;
if ((typecode != 'u')) {
PyErr_SetString(PyExc_ValueError,
"tounicode() may only be called on unicode type arrays");
return NULL;
}
return PyUnicode_FromKindAndData(PyUnicode_4BYTE_KIND,
(Py_UCS4 *) self->ob_item,
Py_SIZE(self));
return PyUnicode_FromUnicode((Py_UNICODE *) self->ob_item, Py_SIZE(self));
}
PyDoc_STRVAR(tounicode_doc,
......@@ -1671,7 +1662,13 @@ typecode_to_mformat_code(char typecode)
return UNSIGNED_INT8;
case 'u':
return UTF32_LE + is_big_endian;
if (sizeof(Py_UNICODE) == 2) {
return UTF16_LE + is_big_endian;
}
if (sizeof(Py_UNICODE) == 4) {
return UTF32_LE + is_big_endian;
}
return UNKNOWN_FORMAT;
case 'f':
if (sizeof(float) == 4) {
......@@ -2419,8 +2416,14 @@ array_buffer_getbuf(arrayobject *self, Py_buffer *view, int flags)
view->strides = &(view->itemsize);
view->format = NULL;
view->internal = NULL;
if ((flags & PyBUF_FORMAT) == PyBUF_FORMAT)
if ((flags & PyBUF_FORMAT) == PyBUF_FORMAT) {
view->format = self->ob_descr->formats;
#ifdef Py_UNICODE_WIDE
if (self->ob_descr->typecode == 'u') {
view->format = "w";
}
#endif
}
finish:
self->ob_exports++;
......@@ -2534,25 +2537,29 @@ array_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
Py_DECREF(v);
}
else if (initial != NULL && PyUnicode_Check(initial)) {
Py_UNICODE *ustr;
Py_ssize_t n;
if (PyUnicode_READY(initial)) {
ustr = PyUnicode_AsUnicode(initial);
if (ustr == NULL) {
PyErr_NoMemory();
Py_DECREF(a);
return NULL;
}
n = PyUnicode_GET_LENGTH(initial);
n = PyUnicode_GET_DATA_SIZE(initial);
if (n > 0) {
arrayobject *self = (arrayobject *)a;
Py_UCS4 *item = (Py_UCS4 *)self->ob_item;
item = (Py_UCS4 *)PyMem_Realloc(item, n * sizeof(Py_UCS4));
char *item = self->ob_item;
item = (char *)PyMem_Realloc(item, n);
if (item == NULL) {
PyErr_NoMemory();
Py_DECREF(a);
return NULL;
}
self->ob_item = (char*)item;
Py_SIZE(self) = n;
if (!PyUnicode_AsUCS4(initial, item, n, 0))
return NULL;
self->ob_item = item;
Py_SIZE(self) = n / sizeof(Py_UNICODE);
memcpy(item, ustr, n);
self->allocated = Py_SIZE(self);
}
}
......@@ -2593,7 +2600,7 @@ is a single character. The following type codes are defined:\n\
Type code C Type Minimum size in bytes \n\
'b' signed integer 1 \n\
'B' unsigned integer 1 \n\
'u' Unicode character 4 \n\
'u' Unicode character 2 (see note) \n\
'h' signed integer 2 \n\
'H' unsigned integer 2 \n\
'i' signed integer 2 \n\
......@@ -2605,6 +2612,9 @@ is a single character. The following type codes are defined:\n\
'f' floating point 4 \n\
'd' floating point 8 \n\
\n\
NOTE: The 'u' typecode corresponds to Python's unicode character. On \n\
narrow builds this is 2-bytes on wide builds this is 4-bytes.\n\
\n\
NOTE: The 'q' and 'Q' type codes are only available if the platform \n\
C compiler used to build Python supports 'long long', or, on Windows, \n\
'__int64'.\n\
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment