Merge pull request #5343 from pitrou/cache_dtype_hash

Fix #5339: cache dtype.__hash__.

8 files changed, 50 insertions, 18 deletions

diff --git a/doc/release/1.10.0-notes.rst b/doc/release/1.10.0-notes.rst
index d5cd99203..a7c0e2852 100644
--- a/doc/release/1.10.0-notes.rst
+++ b/doc/release/1.10.0-notes.rst
@@ -61,6 +61,9 @@ C API
 The changes to *swapaxes* also apply to the *PyArray_SwapAxes* C function,
 which now returns a view in all cases.
 
+The dtype structure (PyArray_Descr) has a new member at the end to cache
+its hash value.  This shouldn't affect any well-written applications.
+
 recarray field return types
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Previously the returned types for recarray fields accessed by attribute and by
diff --git a/numpy/core/include/numpy/ndarraytypes.h b/numpy/core/include/numpy/ndarraytypes.h
index 78f79d5fe..edae27c72 100644
--- a/numpy/core/include/numpy/ndarraytypes.h
+++ b/numpy/core/include/numpy/ndarraytypes.h
@@ -619,6 +619,10 @@ typedef struct _PyArray_Descr {
          * for NumPy 1.7.0.
          */
         NpyAuxData *c_metadata;
+        /* Cached hash value (-1 if not yet computed).
+         * This was added for NumPy 2.0.0.
+         */
+        npy_hash_t hash;
 } PyArray_Descr;
 
 typedef struct _arr_descr {
diff --git a/numpy/core/include/numpy/npy_3kcompat.h b/numpy/core/include/numpy/npy_3kcompat.h
index 8a9109c5c..ef5b5694c 100644
--- a/numpy/core/include/numpy/npy_3kcompat.h
+++ b/numpy/core/include/numpy/npy_3kcompat.h
@@ -486,19 +486,6 @@ NpyCapsule_Check(PyObject *ptr)
 
 #endif
 
-/*
- * Hash value compatibility.
- * As of Python 3.2 hash values are of type Py_hash_t.
- * Previous versions use C long.
- */
-#if PY_VERSION_HEX < 0x03020000
-typedef long npy_hash_t;
-#define NPY_SIZEOF_HASH_T NPY_SIZEOF_LONG
-#else
-typedef Py_hash_t npy_hash_t;
-#define NPY_SIZEOF_HASH_T NPY_SIZEOF_INTP
-#endif
-
 #ifdef __cplusplus
 }
 #endif
diff --git a/numpy/core/include/numpy/npy_common.h b/numpy/core/include/numpy/npy_common.h
index 92b03d20c..eff5dd339 100644
--- a/numpy/core/include/numpy/npy_common.h
+++ b/numpy/core/include/numpy/npy_common.h
@@ -317,6 +317,19 @@ typedef float npy_float;
 typedef double npy_double;
 
 /*
+ * Hash value compatibility.
+ * As of Python 3.2 hash values are of type Py_hash_t.
+ * Previous versions use C long.
+ */
+#if PY_VERSION_HEX < 0x03020000
+typedef long npy_hash_t;
+#define NPY_SIZEOF_HASH_T NPY_SIZEOF_LONG
+#else
+typedef Py_hash_t npy_hash_t;
+#define NPY_SIZEOF_HASH_T NPY_SIZEOF_INTP
+#endif
+
+/*
  * Disabling C99 complex usage: a lot of C code in numpy/scipy rely on being
  * able to do .real/.imag. Will have to convert code first.
  */
diff --git a/numpy/core/src/multiarray/arraytypes.c.src b/numpy/core/src/multiarray/arraytypes.c.src
index 05b843fc4..8287c2268 100644
--- a/numpy/core/src/multiarray/arraytypes.c.src
+++ b/numpy/core/src/multiarray/arraytypes.c.src
@@ -4031,6 +4031,8 @@ static PyArray_Descr @from@_Descr = {
     NULL,
     /* c_metadata */
     NULL,
+    /* hash */
+    -1,
 };
 
 /**end repeat**/
@@ -4172,6 +4174,8 @@ NPY_NO_EXPORT PyArray_Descr @from@_Descr = {
     NULL,
     /* c_metadata */
     NULL,
+    /* hash */
+    -1,
 };
 
 /**end repeat**/
diff --git a/numpy/core/src/multiarray/descriptor.c b/numpy/core/src/multiarray/descriptor.c
index 0993190b7..bbcd5da36 100644
--- a/numpy/core/src/multiarray/descriptor.c
+++ b/numpy/core/src/multiarray/descriptor.c
@@ -1591,6 +1591,7 @@ PyArray_DescrNew(PyArray_Descr *base)
     }
     Py_XINCREF(newdescr->typeobj);
     Py_XINCREF(newdescr->metadata);
+    newdescr->hash = -1;
 
     return newdescr;
 }
@@ -1994,6 +1995,8 @@ arraydescr_names_set(PyArray_Descr *self, PyObject *val)
             return -1;
         }
     }
+    /* Invalidate cached hash value */
+    self->hash = -1;
     /* Update dictionary keys in fields */
     new_names = PySequence_Tuple(val);
     new_fields = PyDict_New();
@@ -2443,6 +2446,8 @@ arraydescr_setstate(PyArray_Descr *self, PyObject *args)
                      version);
         return NULL;
     }
+    /* Invalidate cached hash value */
+    self->hash = -1;
 
     if (version == 1 || version == 0) {
         if (fields != Py_None) {
diff --git a/numpy/core/src/multiarray/hashdescr.c b/numpy/core/src/multiarray/hashdescr.c
index 29d69fddb..fa5fb95cd 100644
--- a/numpy/core/src/multiarray/hashdescr.c
+++ b/numpy/core/src/multiarray/hashdescr.c
@@ -301,7 +301,6 @@ PyArray_DescrHash(PyObject* odescr)
 {
     PyArray_Descr *descr;
     int st;
-    npy_hash_t hash;
 
     if (!PyArray_DescrCheck(odescr)) {
         PyErr_SetString(PyExc_ValueError,
@@ -310,10 +309,12 @@ PyArray_DescrHash(PyObject* odescr)
     }
     descr = (PyArray_Descr*)odescr;
 
-    st = _PyArray_DescrHashImp(descr, &hash);
-    if (st) {
-        return -1;
+    if (descr->hash == -1) {
+        st = _PyArray_DescrHashImp(descr, &descr->hash);
+        if (st) {
+            return -1;
+        }
     }
 
-    return hash;
+    return descr->hash;
 }
diff --git a/numpy/core/tests/test_dtype.py b/numpy/core/tests/test_dtype.py
index 3a255b038..852660432 100644
--- a/numpy/core/tests/test_dtype.py
+++ b/numpy/core/tests/test_dtype.py
@@ -125,6 +125,21 @@ class TestRecord(TestCase):
                       'titles': ['RRed pixel', 'Blue pixel']})
         assert_dtype_not_equal(a, b)
 
+    def test_mutate(self):
+        # Mutating a dtype should reset the cached hash value
+        a = np.dtype([('yo', np.int)])
+        b = np.dtype([('yo', np.int)])
+        c = np.dtype([('ye', np.int)])
+        assert_dtype_equal(a, b)
+        assert_dtype_not_equal(a, c)
+        a.names = ['ye']
+        assert_dtype_equal(a, c)
+        assert_dtype_not_equal(a, b)
+        state = b.__reduce__()[2]
+        a.__setstate__(state)
+        assert_dtype_equal(a, b)
+        assert_dtype_not_equal(a, c)
+
     def test_not_lists(self):
         """Test if an appropriate exception is raised when passing bad values to
         the dtype constructor.