Skip to content

C
cpython
Commit f342bfcb authored by Walter Dörwald's avatar Walter Dörwald
Browse files
Options

Change all functions that expect one unicode character to accept a pair of 

surrogates in narrow builds. Fixes issue #1706460. (Port of r63899).
parent 4daa61e8
Show whitespace changes
Inline Side-by-side
Showing with 82 additions and 73 deletions
Lib/test/test_unicodedata.py
View file @ f342bfcb
......@@ -103,6 +103,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
self.assertEqual(self.db.digit('9'), 9)
self.assertEqual(self.db.digit('\u215b', None), None)
self.assertEqual(self.db.digit('\u2468'), 9)
self.assertEqual(self.db.digit('\U00020000', None), None)
self.assertRaises(TypeError, self.db.digit)
self.assertRaises(TypeError, self.db.digit, 'xx')
......@@ -113,6 +114,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
self.assertEqual(self.db.numeric('9'), 9)
self.assertEqual(self.db.numeric('\u215b'), 0.125)
self.assertEqual(self.db.numeric('\u2468'), 9.0)
self.assertEqual(self.db.numeric('\U00020000', None), None)
self.assertRaises(TypeError, self.db.numeric)
self.assertRaises(TypeError, self.db.numeric, 'xx')
......@@ -123,6 +125,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
self.assertEqual(self.db.decimal('9'), 9)
self.assertEqual(self.db.decimal('\u215b', None), None)
self.assertEqual(self.db.decimal('\u2468', None), None)
self.assertEqual(self.db.decimal('\U00020000', None), None)
self.assertRaises(TypeError, self.db.decimal)
self.assertRaises(TypeError, self.db.decimal, 'xx')
......@@ -132,6 +135,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
self.assertEqual(self.db.category('\uFFFE'), 'Cn')
self.assertEqual(self.db.category('a'), 'Ll')
self.assertEqual(self.db.category('A'), 'Lu')
self.assertEqual(self.db.category('\U00020000'), 'Lo')
self.assertRaises(TypeError, self.db.category)
self.assertRaises(TypeError, self.db.category, 'xx')
......@@ -140,6 +144,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
self.assertEqual(self.db.bidirectional('\uFFFE'), '')
self.assertEqual(self.db.bidirectional(' '), 'WS')
self.assertEqual(self.db.bidirectional('A'), 'L')
self.assertEqual(self.db.bidirectional('\U00020000'), 'L')
self.assertRaises(TypeError, self.db.bidirectional)
self.assertRaises(TypeError, self.db.bidirectional, 'xx')
......@@ -155,6 +160,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
self.assertEqual(self.db.mirrored('\uFFFE'), 0)
self.assertEqual(self.db.mirrored('a'), 0)
self.assertEqual(self.db.mirrored('\u2201'), 1)
self.assertEqual(self.db.mirrored('\U00020000'), 0)
self.assertRaises(TypeError, self.db.mirrored)
self.assertRaises(TypeError, self.db.mirrored, 'xx')
......@@ -163,6 +169,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
self.assertEqual(self.db.combining('\uFFFE'), 0)
self.assertEqual(self.db.combining('a'), 0)
self.assertEqual(self.db.combining('\u20e1'), 230)
self.assertEqual(self.db.combining('\U00020000'), 0)
self.assertRaises(TypeError, self.db.combining)
self.assertRaises(TypeError, self.db.combining, 'xx')
......@@ -186,6 +193,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
self.assertEqual(eaw('\uFF66'), 'H')
self.assertEqual(eaw('\uFF1F'), 'F')
self.assertEqual(eaw('\u2010'), 'A')
self.assertEqual(eaw('\U00020000'), 'W')
class UnicodeMiscTest(UnicodeDatabaseTest):
......
Modules/unicodedata.c
View file @ f342bfcb
......@@ -54,12 +54,6 @@ _getrecord_ex(Py_UCS4 code)
return &_PyUnicode_Database_Records[index];
}
static const _PyUnicode_DatabaseRecord*
_getrecord(PyUnicodeObject* v)
{
return _getrecord_ex(*PyUnicode_AS_UNICODE(v));
}
/* ------------- Previous-version API ------------------------------------- */
typedef struct previous_version {
PyObject_HEAD
......@@ -92,6 +86,24 @@ new_previous_version(const char*name, const change_record* (*getrecord)(Py_UCS4)
return (PyObject*)self;
}
static Py_UCS4 getuchar(PyUnicodeObject *obj)
{
Py_UNICODE *v = PyUnicode_AS_UNICODE(obj);
if (PyUnicode_GET_SIZE(obj) == 1)
return *v;
#ifndef Py_UNICODE_WIDE
else if ((PyUnicode_GET_SIZE(obj) == 2) &&
(0xD800 <= v[0] && v[0] <= 0xDBFF) &&
(0xDC00 <= v[1] && v[1] <= 0xDFFF))
return (((v[0] & 0x3FF)<<10) | (v[1] & 0x3FF)) + 0x10000;
#endif
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
return (Py_UCS4)-1;
}
/* --- Module API --------------------------------------------------------- */
PyDoc_STRVAR(unicodedata_decimal__doc__,
......@@ -108,17 +120,16 @@ unicodedata_decimal(PyObject *self, PyObject *args)
PyObject *defobj = NULL;
int have_old = 0;
long rc;
Py_UCS4 c;
if (!PyArg_ParseTuple(args, "O!|O:decimal", &PyUnicode_Type, &v, &defobj))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
c = getuchar(v);
if (c == (Py_UCS4)-1)
return NULL;
}
if (self) {
const change_record *old = get_old_record(self, *PyUnicode_AS_UNICODE(v));
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0) {
/* unassigned */
have_old = 1;
......@@ -131,7 +142,7 @@ unicodedata_decimal(PyObject *self, PyObject *args)
}
if (!have_old)
rc = Py_UNICODE_TODECIMAL(*PyUnicode_AS_UNICODE(v));
rc = Py_UNICODE_TODECIMAL(c);
if (rc < 0) {
if (defobj == NULL) {
PyErr_SetString(PyExc_ValueError,
......@@ -159,15 +170,14 @@ unicodedata_digit(PyObject *self, PyObject *args)
PyUnicodeObject *v;
PyObject *defobj = NULL;
long rc;
Py_UCS4 c;
if (!PyArg_ParseTuple(args, "O!|O:digit", &PyUnicode_Type, &v, &defobj))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
c = getuchar(v);
if (c == (Py_UCS4)-1)
return NULL;
}
rc = Py_UNICODE_TODIGIT(*PyUnicode_AS_UNICODE(v));
rc = Py_UNICODE_TODIGIT(c);
if (rc < 0) {
if (defobj == NULL) {
PyErr_SetString(PyExc_ValueError, "not a digit");
......@@ -195,17 +205,16 @@ unicodedata_numeric(PyObject *self, PyObject *args)
PyObject *defobj = NULL;
int have_old = 0;
double rc;
Py_UCS4 c;
if (!PyArg_ParseTuple(args, "O!|O:numeric", &PyUnicode_Type, &v, &defobj))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
c = getuchar(v);
if (c == (Py_UCS4)-1)
return NULL;
}
if (self) {
const change_record *old = get_old_record(self, *PyUnicode_AS_UNICODE(v));
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0) {
/* unassigned */
have_old = 1;
......@@ -218,7 +227,7 @@ unicodedata_numeric(PyObject *self, PyObject *args)
}
if (!have_old)
rc = Py_UNICODE_TONUMERIC(*PyUnicode_AS_UNICODE(v));
rc = Py_UNICODE_TONUMERIC(c);
if (rc == -1.0) {
if (defobj == NULL) {
PyErr_SetString(PyExc_ValueError, "not a numeric character");
......@@ -243,18 +252,17 @@ unicodedata_category(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
int index;
Py_UCS4 c;
if (!PyArg_ParseTuple(args, "O!:category",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
c = getuchar(v);
if (c == (Py_UCS4)-1)
return NULL;
}
index = (int) _getrecord(v)->category;
index = (int) _getrecord_ex(c)->category;
if (self) {
const change_record *old = get_old_record(self, *PyUnicode_AS_UNICODE(v));
const change_record *old = get_old_record(self, c);
if (old->category_changed != 0xFF)
index = old->category_changed;
}
......@@ -273,18 +281,17 @@ unicodedata_bidirectional(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
int index;
Py_UCS4 c;
if (!PyArg_ParseTuple(args, "O!:bidirectional",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
c = getuchar(v);
if (c == (Py_UCS4)-1)
return NULL;
}
index = (int) _getrecord(v)->bidirectional;
index = (int) _getrecord_ex(c)->bidirectional;
if (self) {
const change_record *old = get_old_record(self, *PyUnicode_AS_UNICODE(v));
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0)
index = 0; /* unassigned */
else if (old->bidir_changed != 0xFF)
......@@ -305,18 +312,17 @@ unicodedata_combining(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
int index;
Py_UCS4 c;
if (!PyArg_ParseTuple(args, "O!:combining",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
c = getuchar(v);
if (c == (Py_UCS4)-1)
return NULL;
}
index = (int) _getrecord(v)->combining;
index = (int) _getrecord_ex(c)->combining;
if (self) {
const change_record *old = get_old_record(self, *PyUnicode_AS_UNICODE(v));
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0)
index = 0; /* unassigned */
}
......@@ -335,18 +341,17 @@ unicodedata_mirrored(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
int index;
Py_UCS4 c;
if (!PyArg_ParseTuple(args, "O!:mirrored",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
c = getuchar(v);
if (c == (Py_UCS4)-1)
return NULL;
}
index = (int) _getrecord(v)->mirrored;
index = (int) _getrecord_ex(c)->mirrored;
if (self) {
const change_record *old = get_old_record(self, *PyUnicode_AS_UNICODE(v));
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0)
index = 0; /* unassigned */
}
......@@ -364,18 +369,17 @@ unicodedata_east_asian_width(PyObject *self, PyObject *args)
{
PyUnicodeObject *v;
int index;
Py_UCS4 c;
if (!PyArg_ParseTuple(args, "O!:east_asian_width",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
c = getuchar(v);
if (c == (Py_UCS4)-1)
return NULL;
}
index = (int) _getrecord(v)->east_asian_width;
index = (int) _getrecord_ex(c)->east_asian_width;
if (self) {
const change_record *old = get_old_record(self, *PyUnicode_AS_UNICODE(v));
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0)
index = 0; /* unassigned */
}
......@@ -396,20 +400,19 @@ unicodedata_decomposition(PyObject *self, PyObject *args)
char decomp[256];
int code, index, count, i;
unsigned int prefix_index;
Py_UCS4 c;
if (!PyArg_ParseTuple(args, "O!:decomposition",
&PyUnicode_Type, &v))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
c = getuchar(v);
if (c == (Py_UCS4)-1)
return NULL;
}
code = (int) *PyUnicode_AS_UNICODE(v);
code = (int)c;
if (self) {
const change_record *old = get_old_record(self, *PyUnicode_AS_UNICODE(v));
const change_record *old = get_old_record(self, c);
if (old->category_changed == 0)
return PyUnicode_FromString(""); /* unassigned */
}
......@@ -1039,20 +1042,18 @@ static PyObject *
unicodedata_name(PyObject* self, PyObject* args)
{
char name[NAME_MAXLEN];
Py_UCS4 c;
PyUnicodeObject* v;
PyObject* defobj = NULL;
if (!PyArg_ParseTuple(args, "O!|O:name", &PyUnicode_Type, &v, &defobj))
return NULL;
if (PyUnicode_GET_SIZE(v) != 1) {
PyErr_SetString(PyExc_TypeError,
"need a single Unicode character as parameter");
c = getuchar(v);
if (c == (Py_UCS4)-1)
return NULL;
}
if (!_getucname(self, (Py_UCS4) *PyUnicode_AS_UNICODE(v),
name, sizeof(name))) {
if (!_getucname(self, c, name, sizeof(name))) {
if (defobj == NULL) {
PyErr_SetString(PyExc_ValueError, "no such name");
return NULL;
......
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
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7