numpy · rgommers · Oct 4, 2023 · Oct 4, 2023 · Oct 4, 2023
diff --git a/doc/release/upcoming_changes/24854.python_removal.rst b/doc/release/upcoming_changes/24854.python_removal.rst
@@ -0,0 +1,2 @@
+``np.dtype("a")`` alias for ``np.dtype(np.bytes_)`` was removed.
+Use ``np.dtype("S")`` alias instead.
diff --git a/doc/source/reference/arrays.dtypes.rst b/doc/source/reference/arrays.dtypes.rst
@@ -252,7 +252,7 @@ Array-protocol type strings (see :ref:`arrays.interface`)
       >>> dt = np.dtype('i4')   # 32-bit signed integer
       >>> dt = np.dtype('f8')   # 64-bit floating-point number
       >>> dt = np.dtype('c16')  # 128-bit complex floating-point number
-      >>> dt = np.dtype('a25')  # 25-length zero-terminated bytes
+      >>> dt = np.dtype('S25')  # 25-length zero-terminated bytes
       >>> dt = np.dtype('U25')  # 25-character string
 
    .. _string-dtype-note:
@@ -293,7 +293,7 @@ String with comma-separated fields
       - field named ``f2`` containing a 3 x 4 sub-array
         containing 10-character strings
 
-      >>> dt = np.dtype("a3, 3u8, (3,4)a10")
+      >>> dt = np.dtype("S3, 3u8, (3,4)S10")
 
 Type strings
    Any string name of a NumPy dtype, e.g.:

diff --git a/doc/source/user/basics.rec.rst b/doc/source/user/basics.rec.rst
@@ -671,7 +671,7 @@ A record array representation of a structured array can be obtained using the
 appropriate `view <numpy-ndarray-view>`_::
 
  >>> arr = np.array([(1, 2., 'Hello'), (2, 3., "World")],
- ...                dtype=[('foo', 'i4'),('bar', 'f4'), ('baz', 'a10')])
+ ...                dtype=[('foo', 'i4'),('bar', 'f4'), ('baz', 'S10')])
  >>> recordarr = arr.view(dtype=np.dtype((np.record, arr.dtype)),
  ...                      type=np.recarray)
 

diff --git a/numpy/core/_type_aliases.py b/numpy/core/_type_aliases.py
@@ -222,7 +222,7 @@ def _set_array_types():
 
 # Add additional strings to the sctypeDict
 _toadd = ['int', ('float', 'double'), ('complex', 'cdouble'), 
-          'bool', 'object', 'str', 'bytes', ('a', 'bytes_')]
+          'bool', 'object', 'str', 'bytes']
 
 for name in _toadd:
     if isinstance(name, tuple):

diff --git a/numpy/core/include/numpy/ndarraytypes.h b/numpy/core/include/numpy/ndarraytypes.h
@@ -112,7 +112,6 @@ enum NPY_TYPECHAR {
         NPY_CLONGDOUBLELTR = 'G',
         NPY_OBJECTLTR = 'O',
         NPY_STRINGLTR = 'S',
-        NPY_STRINGLTR2 = 'a',
         NPY_UNICODELTR = 'U',
         NPY_VOIDLTR = 'V',
         NPY_DATETIMELTR = 'M',

diff --git a/numpy/core/src/multiarray/arraytypes.c.src b/numpy/core/src/multiarray/arraytypes.c.src
@@ -4724,8 +4724,6 @@ set_typeinfo(PyObject *dict)
 
     /**end repeat**/
 
-    _letter_to_num[NPY_STRINGLTR2] = NPY_STRING;
-
     /**begin repeat
       * #name = BOOL,
       *         BYTE, UBYTE, SHORT, USHORT, INT, UINT,

diff --git a/numpy/core/src/multiarray/conversion_utils.c b/numpy/core/src/multiarray/conversion_utils.c
@@ -1297,7 +1297,6 @@ PyArray_TypestrConvert(int itemsize, int gentype)
             break;
 
         case NPY_STRINGLTR:
-        case NPY_STRINGLTR2:
             newtype = NPY_STRING;
             break;
 

diff --git a/numpy/core/src/multiarray/descriptor.c b/numpy/core/src/multiarray/descriptor.c
@@ -1792,7 +1792,6 @@ _convert_from_str(PyObject *obj, int align)
             kind = type[0];
             switch (kind) {
                 case NPY_STRINGLTR:
-                case NPY_STRINGLTR2:
                     check_num = NPY_STRING;
                     break;
 

diff --git a/numpy/core/tests/test_dtype.py b/numpy/core/tests/test_dtype.py
@@ -146,7 +146,7 @@ def test_expired_dtypes_with_bad_bytesize(self):
     @pytest.mark.parametrize(
         'value',
         ['m8', 'M8', 'datetime64', 'timedelta64',
-         'i4, (2,3)f8, f4', 'a3, 3u8, (3,4)a10',
+         'i4, (2,3)f8, f4', 'S3, 3u8, (3,4)S10',
          '>f', '<f', '=f', '|f',
         ])
     def test_dtype_bytes_str_equivalence(self, value):

diff --git a/numpy/core/tests/test_records.py b/numpy/core/tests/test_records.py
@@ -51,17 +51,29 @@ def test_fromrecords_2d(self):
         assert_equal(r1, r2)
 
     def test_method_array(self):
-        r = np.rec.array(b'abcdefg' * 100, formats='i2,a3,i4', shape=3, byteorder='big')
+        r = np.rec.array(
+            b'abcdefg' * 100, formats='i2,S3,i4', shape=3, byteorder='big'
+        )
         assert_equal(r[1].item(), (25444, b'efg', 1633837924))
 
     def test_method_array2(self):
-        r = np.rec.array([(1, 11, 'a'), (2, 22, 'b'), (3, 33, 'c'), (4, 44, 'd'), (5, 55, 'ex'),
-                     (6, 66, 'f'), (7, 77, 'g')], formats='u1,f4,a1')
+        r = np.rec.array(
+            [
+                (1, 11, 'a'), (2, 22, 'b'), (3, 33, 'c'), (4, 44, 'd'),
+                (5, 55, 'ex'), (6, 66, 'f'), (7, 77, 'g')
+            ],
+            formats='u1,f4,S1'
+        )
         assert_equal(r[1].item(), (2, 22.0, b'b'))
 
     def test_recarray_slices(self):
-        r = np.rec.array([(1, 11, 'a'), (2, 22, 'b'), (3, 33, 'c'), (4, 44, 'd'), (5, 55, 'ex'),
-                     (6, 66, 'f'), (7, 77, 'g')], formats='u1,f4,a1')
+        r = np.rec.array(
+            [
+                (1, 11, 'a'), (2, 22, 'b'), (3, 33, 'c'), (4, 44, 'd'),
+                (5, 55, 'ex'), (6, 66, 'f'), (7, 77, 'g')
+            ],
+            formats='u1,f4,S1'
+        )
         assert_equal(r[1::2][1].item(), (4, 44.0, b'd'))
 
     def test_recarray_fromarrays(self):
@@ -78,14 +90,16 @@ def test_recarray_fromfile(self):
         filename = path.join(data_dir, 'recarray_from_file.fits')
         fd = open(filename, 'rb')
         fd.seek(2880 * 2)
-        r1 = np.rec.fromfile(fd, formats='f8,i4,a5', shape=3, byteorder='big')
+        r1 = np.rec.fromfile(fd, formats='f8,i4,S5', shape=3, byteorder='big')
         fd.seek(2880 * 2)
-        r2 = np.rec.array(fd, formats='f8,i4,a5', shape=3, byteorder='big')
+        r2 = np.rec.array(fd, formats='f8,i4,S5', shape=3, byteorder='big')
         fd.seek(2880 * 2)
         bytes_array = BytesIO()
         bytes_array.write(fd.read())
         bytes_array.seek(0)
-        r3 = np.rec.fromfile(bytes_array, formats='f8,i4,a5', shape=3, byteorder='big')
+        r3 = np.rec.fromfile(
+            bytes_array, formats='f8,i4,S5', shape=3, byteorder='big'
+        )
         fd.close()
         assert_equal(r1, r2)
         assert_equal(r2, r3)
@@ -330,12 +344,12 @@ def test_tofile_fromfile(self):
         with temppath(suffix='.bin') as path:
             path = Path(path)
             np.random.seed(123)
-            a = np.random.rand(10).astype('f8,i4,a5')
+            a = np.random.rand(10).astype('f8,i4,S5')
             a[5] = (0.5,10,'abcde')
             with path.open("wb") as fd:
                 a.tofile(fd)
             x = np.core.records.fromfile(path,
-                                         formats='f8,i4,a5',
+                                         formats='f8,i4,S5',
                                          shape=10)
             assert_array_equal(x, a)
 

diff --git a/numpy/core/tests/test_regression.py b/numpy/core/tests/test_regression.py
@@ -573,7 +573,7 @@ def test_rec_fromarray(self):
         x1 = np.array([[1, 2], [3, 4], [5, 6]])
         x2 = np.array(['a', 'dd', 'xyz'])
         x3 = np.array([1.1, 2, 3])
-        np.rec.fromarrays([x1, x2, x3], formats="(2,)i4,a3,f8")
+        np.rec.fromarrays([x1, x2, x3], formats="(2,)i4,S3,f8")
 
     def test_object_array_assign(self):
         x = np.empty((2, 2), object)

diff --git a/numpy/f2py/tests/test_return_complex.py b/numpy/f2py/tests/test_return_complex.py
@@ -33,7 +33,7 @@ def check_function(self, t, tname):
         assert abs(t(array([234 + 3j], "F")) - (234 + 3j)) <= err
         assert abs(t(array([234], "D")) - 234.0) <= err
 
-        # pytest.raises(TypeError, t, array([234], 'a1'))
+        # pytest.raises(TypeError, t, array([234], 'S1'))
         pytest.raises(TypeError, t, "abc")
 
         pytest.raises(IndexError, t, [])

diff --git a/numpy/lib/tests/test_function_base.py b/numpy/lib/tests/test_function_base.py
@@ -580,7 +580,7 @@ def test_index_array_copied(self):
 
     def test_structured_array(self):
         a = np.array([(1, 'a'), (2, 'b'), (3, 'c')],
-                     dtype=[('foo', 'i'), ('bar', 'a1')])
+                     dtype=[('foo', 'i'), ('bar', 'S1')])
         val = (4, 'd')
         b = np.insert(a, 0, val)
         assert_array_equal(b[0], np.array(val, dtype=b.dtype))

diff --git a/tools/replace_old_macros.sed b/tools/replace_old_macros.sed
@@ -94,7 +94,6 @@ s/\bPyArray_CDOUBLELTR\b/NPY_CDOUBLELTR/g
 s/\bPyArray_CLONGDOUBLELTR\b/NPY_CLONGDOUBLELTR/g
 s/\bPyArray_OBJECTLTR\b/NPY_OBJECTLTR/g
 s/\bPyArray_STRINGLTR\b/NPY_STRINGLTR/g
-s/\bPyArray_STRINGLTR2\b/NPY_STRINGLTR2/g
 s/\bPyArray_UNICODELTR\b/NPY_UNICODELTR/g
 s/\bPyArray_VOIDLTR\b/NPY_VOIDLTR/g
 s/\bPyArray_DATETIMELTR\b/NPY_DATETIMELTR/g
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		``np.dtype("a")`` alias for ``np.dtype(np.bytes_)`` was removed.
		Use ``np.dtype("S")`` alias instead.
-Original file line number
+Diff line change
@@ Expand Up / @@ -1297,7 +1297,6 @@ PyArray_TypestrConvert(int itemsize, int gentype) @@
                 break;
             case NPY_STRINGLTR:
-            case NPY_STRINGLTR2:
                 newtype = NPY_STRING;
                 break;
@@ Expand Down @@