FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

gh-124502: Add PyUnicode_Equal() function by vstinner · Pull Request #124504 · python/cpython · GitHub

/ cpython Public
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension .c  (3) .dat  (1) .h  (1) .py  (2) .rst  (3) .toml  (1) All 6 file types selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
25 changes: 25 additions & 0 deletions Doc/c-api/unicode.rst
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -1438,6 +1438,31 @@ They all return ``NULL`` or ``-1`` if an exception occurs.
This function returns ``-1`` upon failure, so one should call
:c:func:`PyErr_Occurred` to check for errors.

.. seealso::

The :c:func:`PyUnicode_Equal` function.


.. c:function:: int PyUnicode_Equal(PyObject *a, PyObject *b)

Test if two strings are equal:

* Return ``1`` if *a* is equal to *b*.
* Return ``0`` if *a* is not equal to *b*.
* Set a :exc:`TypeError` exception and return ``-1`` if *a* or *b* is not a
:class:`str` object.

The function always succeeds if *a* and *b* are :class:`str` objects.

The function works for :class:`str` subclasses, but does not honor custom
``__eq__()`` method.

.. seealso::

The :c:func:`PyUnicode_Compare` function.

.. versionadded:: 3.14


.. c:function:: int PyUnicode_EqualToUTF8AndSize(PyObject *unicode, const char *string, Py_ssize_t size)

Expand Down
1 change: 1 addition & 0 deletions Doc/data/stable_abi.dat

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

4 changes: 4 additions & 0 deletions Doc/whatsnew/3.14.rst
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -687,6 +687,10 @@ New Features
<https://peps.python.org/pep-0630/#type-checking>`__ mentioned in :pep:`630`
(:gh:`124153`).

* Add :c:func:`PyUnicode_Equal` function to the limited C API:
test if two strings are equal.
(Contributed by Victor Stinner in :gh:`124502`.)


Porting to Python 3.14
----------------------
Expand Down
4 changes: 4 additions & 0 deletions Include/unicodeobject.h
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -966,6 +966,10 @@ PyAPI_FUNC(int) PyUnicode_EqualToUTF8(PyObject *, const char *);
PyAPI_FUNC(int) PyUnicode_EqualToUTF8AndSize(PyObject *, const char *, Py_ssize_t);
#endif

#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x030e0000
PyAPI_FUNC(int) PyUnicode_Equal(PyObject *str1, PyObject *str2);
#endif

/* Rich compare two strings and return one of the following:

- NULL in case an exception was raised
Expand Down
33 changes: 33 additions & 0 deletions Lib/test/test_capi/test_unicode.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -1903,6 +1903,39 @@ def test_recover_error(self):

self.assertEqual(writer.finish(), 'Hello World.')

def test_unicode_equal(self):
unicode_equal = _testlimitedcapi.unicode_equal

def copy(text):
return text.encode().decode()

self.assertTrue(unicode_equal("", ""))
Comment thread
vstinner marked this conversation as resolved.
self.assertTrue(unicode_equal("abc", "abc"))
self.assertTrue(unicode_equal("abc", copy("abc")))
self.assertTrue(unicode_equal("\u20ac", copy("\u20ac")))
self.assertTrue(unicode_equal("\U0010ffff", copy("\U0010ffff")))

self.assertFalse(unicode_equal("abc", "abcd"))
self.assertFalse(unicode_equal("\u20ac", "\u20ad"))
self.assertFalse(unicode_equal("\U0010ffff", "\U0010fffe"))

# str subclass
self.assertTrue(unicode_equal("abc", Str("abc")))
self.assertTrue(unicode_equal(Str("abc"), "abc"))
self.assertFalse(unicode_equal("abc", Str("abcd")))
self.assertFalse(unicode_equal(Str("abc"), "abcd"))

# invalid type
for invalid_type in (b'bytes', 123, ("tuple",)):
with self.subTest(invalid_type=invalid_type):
with self.assertRaises(TypeError):
Comment thread
vstinner marked this conversation as resolved.
unicode_equal("abc", invalid_type)
with self.assertRaises(TypeError):
unicode_equal(invalid_type, "abc")

# CRASHES unicode_equal("abc", NULL)
# CRASHES unicode_equal(NULL, "abc")


if __name__ == "__main__":
unittest.main()
1 change: 1 addition & 0 deletions Lib/test/test_stable_abi_ctypes.py

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

This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Add :c:func:`PyUnicode_Equal` function to the limited C API: test if two
strings are equal. Patch by Victor Stinner.
2 changes: 2 additions & 0 deletions Misc/stable_abi.toml
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -2536,3 +2536,5 @@
added = '3.14'
[const.Py_TP_USE_SPEC]
added = '3.14'
[function.PyUnicode_Equal]
added = '3.14'
22 changes: 20 additions & 2 deletions Modules/_testlimitedcapi/unicode.c
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
#include "pyconfig.h" // Py_GIL_DISABLED
#ifndef Py_GIL_DISABLED
// Need limited C API 3.13 to test PyUnicode_EqualToUTF8()
# define Py_LIMITED_API 0x030d0000
// Need limited C API 3.14 to test PyUnicode_Equal()
# define Py_LIMITED_API 0x030e0000
#endif

#include "parts.h"
Expand Down Expand Up @@ -1837,6 +1837,23 @@ test_string_from_format(PyObject *self, PyObject *Py_UNUSED(ignored))
#undef CHECK_FORMAT_0
}


/* Test PyUnicode_Equal() */
static PyObject *
unicode_equal(PyObject *module, PyObject *args)
{
PyObject *str1, *str2;
if (!PyArg_ParseTuple(args, "OO", &str1, &str2)) {
return NULL;
}

NULLABLE(str1);
NULLABLE(str2);
RETURN_INT(PyUnicode_Equal(str1, str2));
}



static PyMethodDef TestMethods[] = {
{"codec_incrementalencoder", codec_incrementalencoder, METH_VARARGS},
{"codec_incrementaldecoder", codec_incrementaldecoder, METH_VARARGS},
Expand Down Expand Up @@ -1924,6 +1941,7 @@ static PyMethodDef TestMethods[] = {
{"unicode_format", unicode_format, METH_VARARGS},
{"unicode_contains", unicode_contains, METH_VARARGS},
{"unicode_isidentifier", unicode_isidentifier, METH_O},
{"unicode_equal", unicode_equal, METH_VARARGS},
{NULL},
};

Expand Down
18 changes: 18 additions & 0 deletions Objects/unicodeobject.c
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Original file line number Diff line number Diff line change
Expand Up @@ -11001,6 +11001,24 @@ _PyUnicode_Equal(PyObject *str1, PyObject *str2)
}


int
PyUnicode_Equal(PyObject *str1, PyObject *str2)
{
if (!PyUnicode_Check(str1)) {
PyErr_Format(PyExc_TypeError,
"first argument must be str, not %T", str1);
Comment thread
vstinner marked this conversation as resolved.
return -1;
}
if (!PyUnicode_Check(str2)) {
PyErr_Format(PyExc_TypeError,
"second argument must be str, not %T", str2);
return -1;
}

return _PyUnicode_Equal(str1, str2);
}


int
PyUnicode_Compare(PyObject *left, PyObject *right)
{
Expand Down
1 change: 1 addition & 0 deletions PC/python3dll.c

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


Back | FazBrowse Home | New Git URL