bpo-47164: Add _PyASCIIObject_CAST() macro (GH-32191)

Add macros to cast objects to PyASCIIObject*, PyCompactUnicodeObject*
and PyUnicodeObject*: _PyASCIIObject_CAST(),
_PyCompactUnicodeObject_CAST() and _PyUnicodeObject_CAST(). Using
these new macros make the code more readable and check their argument
with: assert(PyUnicode_Check(op)).

Remove redundant assert(PyUnicode_Check(op)) in macros using directly
or indirectly these new CAST macros.

Replacing existing casts with these macros.

8 files changed, 76 insertions, 78 deletions

diff --git a/Include/cpython/unicodeobject.h b/Include/cpython/unicodeobject.h
index 77a171b..69e4abf 100644
--- a/Include/cpython/unicodeobject.h
+++ b/Include/cpython/unicodeobject.h
@@ -234,6 +234,15 @@ PyAPI_FUNC(int) _PyUnicode_CheckConsistency(
     PyObject *op,
     int check_content);
 
+
+#define _PyASCIIObject_CAST(op) \
+    (assert(PyUnicode_Check(op)), (PyASCIIObject*)(op))
+#define _PyCompactUnicodeObject_CAST(op) \
+    (assert(PyUnicode_Check(op)), (PyCompactUnicodeObject*)(op))
+#define _PyUnicodeObject_CAST(op) \
+    (assert(PyUnicode_Check(op)), (PyUnicodeObject*)(op))
+
+
 /* Fast access macros */
 
 /* Returns the deprecated Py_UNICODE representation's size in code units
@@ -243,11 +252,10 @@ PyAPI_FUNC(int) _PyUnicode_CheckConsistency(
 
 /* Py_DEPRECATED(3.3) */
 #define PyUnicode_GET_SIZE(op)                       \
-    (assert(PyUnicode_Check(op)),                    \
-     (((PyASCIIObject *)(op))->wstr) ?               \
+    (_PyASCIIObject_CAST(op)->wstr ?                 \
       PyUnicode_WSTR_LENGTH(op) :                    \
       ((void)PyUnicode_AsUnicode(_PyObject_CAST(op)),\
-       assert(((PyASCIIObject *)(op))->wstr),        \
+       assert(_PyASCIIObject_CAST(op)->wstr),        \
        PyUnicode_WSTR_LENGTH(op)))
 
 /* Py_DEPRECATED(3.3) */
@@ -261,9 +269,8 @@ PyAPI_FUNC(int) _PyUnicode_CheckConsistency(
 
 /* Py_DEPRECATED(3.3) */
 #define PyUnicode_AS_UNICODE(op) \
-    (assert(PyUnicode_Check(op)), \
-     (((PyASCIIObject *)(op))->wstr) ? (((PyASCIIObject *)(op))->wstr) : \
-      PyUnicode_AsUnicode(_PyObject_CAST(op)))
+    (_PyASCIIObject_CAST(op)->wstr ? _PyASCIIObject_CAST(op)->wstr : \
+     PyUnicode_AsUnicode(_PyObject_CAST(op)))
 
 /* Py_DEPRECATED(3.3) */
 #define PyUnicode_AS_DATA(op) \
@@ -281,25 +288,24 @@ PyAPI_FUNC(int) _PyUnicode_CheckConsistency(
 
 /* Use only if you know it's a string */
 #define PyUnicode_CHECK_INTERNED(op) \
-    (((PyASCIIObject *)(op))->state.interned)
+    (_PyASCIIObject_CAST(op)->state.interned)
 
 /* Return true if the string contains only ASCII characters, or 0 if not. The
    string may be compact (PyUnicode_IS_COMPACT_ASCII) or not, but must be
    ready. */
 #define PyUnicode_IS_ASCII(op)                   \
-    (assert(PyUnicode_Check(op)),                \
-     assert(PyUnicode_IS_READY(op)),             \
-     ((PyASCIIObject*)op)->state.ascii)
+    (assert(PyUnicode_IS_READY(op)),             \
+     _PyASCIIObject_CAST(op)->state.ascii)
 
 /* Return true if the string is compact or 0 if not.
    No type checks or Ready calls are performed. */
 #define PyUnicode_IS_COMPACT(op) \
-    (((PyASCIIObject*)(op))->state.compact)
+    (_PyASCIIObject_CAST(op)->state.compact)
 
 /* Return true if the string is a compact ASCII string (use PyASCIIObject
    structure), or 0 if not.  No type checks or Ready calls are performed. */
 #define PyUnicode_IS_COMPACT_ASCII(op)                 \
-    (((PyASCIIObject*)op)->state.ascii && PyUnicode_IS_COMPACT(op))
+    (_PyASCIIObject_CAST(op)->state.ascii && PyUnicode_IS_COMPACT(op))
 
 enum PyUnicode_Kind {
 /* String contains only wstr byte characters.  This is only possible
@@ -323,23 +329,21 @@ enum PyUnicode_Kind {
 
 /* Return one of the PyUnicode_*_KIND values defined above. */
 #define PyUnicode_KIND(op) \
-    (assert(PyUnicode_Check(op)), \
-     assert(PyUnicode_IS_READY(op)),            \
-     ((PyASCIIObject *)(op))->state.kind)
+    (assert(PyUnicode_IS_READY(op)),            \
+     _PyASCIIObject_CAST(op)->state.kind)
 
 /* Return a void pointer to the raw unicode buffer. */
 #define _PyUnicode_COMPACT_DATA(op)                     \
-    (PyUnicode_IS_ASCII(op) ?                   \
-     ((void*)((PyASCIIObject*)(op) + 1)) :              \
-     ((void*)((PyCompactUnicodeObject*)(op) + 1)))
+    (PyUnicode_IS_ASCII(op) ?                           \
+     ((void*)(_PyASCIIObject_CAST(op) + 1)) :           \
+     ((void*)(_PyCompactUnicodeObject_CAST(op) + 1)))
 
 #define _PyUnicode_NONCOMPACT_DATA(op)                  \
-    (assert(((PyUnicodeObject*)(op))->data.any),        \
-     ((((PyUnicodeObject *)(op))->data.any)))
+    (assert(_PyUnicodeObject_CAST(op)->data.any),       \
+     (_PyUnicodeObject_CAST(op)->data.any))
 
 #define PyUnicode_DATA(op) \
-    (assert(PyUnicode_Check(op)), \
-     PyUnicode_IS_COMPACT(op) ? _PyUnicode_COMPACT_DATA(op) :   \
+    (PyUnicode_IS_COMPACT(op) ? _PyUnicode_COMPACT_DATA(op) :   \
      _PyUnicode_NONCOMPACT_DATA(op))
 
 /* In the access macros below, "kind" may be evaluated more than once.
@@ -386,8 +390,7 @@ enum PyUnicode_Kind {
    PyUnicode_READ_CHAR, for multiple consecutive reads callers should
    cache kind and use PyUnicode_READ instead. */
 #define PyUnicode_READ_CHAR(unicode, index) \
-    (assert(PyUnicode_Check(unicode)),          \
-     assert(PyUnicode_IS_READY(unicode)),       \
+    (assert(PyUnicode_IS_READY(unicode)),       \
      (Py_UCS4)                                  \
         (PyUnicode_KIND((unicode)) == PyUnicode_1BYTE_KIND ? \
             ((const Py_UCS1 *)(PyUnicode_DATA((unicode))))[(index)] : \
@@ -401,23 +404,21 @@ enum PyUnicode_Kind {
    the string has it's canonical representation set before calling
    this macro.  Call PyUnicode_(FAST_)Ready to ensure that. */
 #define PyUnicode_GET_LENGTH(op)                \
-    (assert(PyUnicode_Check(op)),               \
-     assert(PyUnicode_IS_READY(op)),            \
-     ((PyASCIIObject *)(op))->length)
+    (assert(PyUnicode_IS_READY(op)),            \
+     _PyASCIIObject_CAST(op)->length)
 
 
 /* Fast check to determine whether an object is ready. Equivalent to
-   PyUnicode_IS_COMPACT(op) || ((PyUnicodeObject*)(op))->data.any */
+   PyUnicode_IS_COMPACT(op) || _PyUnicodeObject_CAST(op)->data.any */
 
-#define PyUnicode_IS_READY(op) (((PyASCIIObject*)op)->state.ready)
+#define PyUnicode_IS_READY(op) (_PyASCIIObject_CAST(op)->state.ready)
 
 /* PyUnicode_READY() does less work than _PyUnicode_Ready() in the best
    case.  If the canonical representation is not yet set, it will still call
    _PyUnicode_Ready().
    Returns 0 on success and -1 on errors. */
 #define PyUnicode_READY(op)                        \
-    (assert(PyUnicode_Check(op)),                       \
-     (PyUnicode_IS_READY(op) ?                          \
+    ((PyUnicode_IS_READY(op) ?                     \
       0 : _PyUnicode_Ready(_PyObject_CAST(op))))
 
 /* Return a maximum character value which is suitable for creating another
@@ -436,8 +437,8 @@ enum PyUnicode_Kind {
 Py_DEPRECATED(3.3)
 static inline Py_ssize_t PyUnicode_WSTR_LENGTH(PyObject *op) {
     return PyUnicode_IS_COMPACT_ASCII(op) ?
-            ((PyASCIIObject*)op)->length :
-            ((PyCompactUnicodeObject*)op)->wstr_length;
+            _PyASCIIObject_CAST(op)->length :
+            _PyCompactUnicodeObject_CAST(op)->wstr_length;
 }
 #define PyUnicode_WSTR_LENGTH(op) PyUnicode_WSTR_LENGTH(_PyObject_CAST(op))
 
diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index 6426c5d..1d2f546 100644
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -112,7 +112,7 @@ PyAPI_DATA(PyTypeObject) PyUnicode_Type;
 PyAPI_DATA(PyTypeObject) PyUnicodeIter_Type;
 
 #define PyUnicode_Check(op) \
-                 PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_UNICODE_SUBCLASS)
+    PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_UNICODE_SUBCLASS)
 #define PyUnicode_CheckExact(op) Py_IS_TYPE(op, &PyUnicode_Type)
 
 /* --- Constants ---------------------------------------------------------- */
diff --git a/Modules/_collectionsmodule.c b/Modules/_collectionsmodule.c
index e7bd8bc..b47f977 100644
--- a/Modules/_collectionsmodule.c
+++ b/Modules/_collectionsmodule.c
@@ -2352,7 +2352,7 @@ _collections__count_elements_impl(PyObject *module, PyObject *mapping,
                 break;
 
             if (!PyUnicode_CheckExact(key) ||
-                (hash = ((PyASCIIObject *) key)->hash) == -1)
+                (hash = _PyASCIIObject_CAST(key)->hash) == -1)
             {
                 hash = PyObject_Hash(key);
                 if (hash == -1)
diff --git a/Objects/dictobject.c b/Objects/dictobject.c
index 635a738..88addfd 100644
--- a/Objects/dictobject.c
+++ b/Objects/dictobject.c
@@ -286,7 +286,7 @@ static inline Py_hash_t
 unicode_get_hash(PyObject *o)
 {
     assert(PyUnicode_CheckExact(o));
-    return ((PyASCIIObject*)o)->hash;
+    return _PyASCIIObject_CAST(o)->hash;
 }
 
 /* Print summary info about the state of the optimized allocator */
diff --git a/Objects/setobject.c b/Objects/setobject.c
index c65b7d5..022ae8e 100644
--- a/Objects/setobject.c
+++ b/Objects/setobject.c
@@ -346,7 +346,7 @@ set_add_key(PySetObject *so, PyObject *key)
     Py_hash_t hash;
 
     if (!PyUnicode_CheckExact(key) ||
-        (hash = ((PyASCIIObject *) key)->hash) == -1) {
+        (hash = _PyASCIIObject_CAST(key)->hash) == -1) {
         hash = PyObject_Hash(key);
         if (hash == -1)
             return -1;
@@ -360,7 +360,7 @@ set_contains_key(PySetObject *so, PyObject *key)
     Py_hash_t hash;
 
     if (!PyUnicode_CheckExact(key) ||
-        (hash = ((PyASCIIObject *) key)->hash) == -1) {
+        (hash = _PyASCIIObject_CAST(key)->hash) == -1) {
         hash = PyObject_Hash(key);
         if (hash == -1)
             return -1;
@@ -374,7 +374,7 @@ set_discard_key(PySetObject *so, PyObject *key)
     Py_hash_t hash;
 
     if (!PyUnicode_CheckExact(key) ||
-        (hash = ((PyASCIIObject *) key)->hash) == -1) {
+        (hash = _PyASCIIObject_CAST(key)->hash) == -1) {
         hash = PyObject_Hash(key);
         if (hash == -1)
             return -1;
diff --git a/Objects/typeobject.c b/Objects/typeobject.c
index 4bed3ef..5de8c3d 100644
--- a/Objects/typeobject.c
+++ b/Objects/typeobject.c
@@ -3759,7 +3759,7 @@ find_name_in_mro(PyTypeObject *type, PyObject *name, int *error)
 {
     Py_hash_t hash;
     if (!PyUnicode_CheckExact(name) ||
-        (hash = ((PyASCIIObject *) name)->hash) == -1)
+        (hash = _PyASCIIObject_CAST(name)->hash) == -1)
     {
         hash = PyObject_Hash(name);
         if (hash == -1) {
@@ -3853,7 +3853,7 @@ _PyType_Lookup(PyTypeObject *type, PyObject *name)
         struct type_cache_entry *entry = &cache->hashtable[h];
         entry->version = type->tp_version_tag;
         entry->value = res;  /* borrowed */
-        assert(((PyASCIIObject *)(name))->hash != -1);
+        assert(_PyASCIIObject_CAST(name)->hash != -1);
 #if MCACHE_STATS
         if (entry->name != Py_None && entry->name != name) {
             cache->collisions++;
@@ -8951,7 +8951,7 @@ super_init_without_args(_PyInterpreterFrame *cframe, PyCodeObject *co,
         if (cframe->f_lasti >= 0) {
             // MAKE_CELL and COPY_FREE_VARS have no quickened forms, so no need
             // to use _PyOpcode_Deopt here:
-            assert(_Py_OPCODE(_PyCode_CODE(co)[0]) == MAKE_CELL || 
+            assert(_Py_OPCODE(_PyCode_CODE(co)[0]) == MAKE_CELL ||
                    _Py_OPCODE(_PyCode_CODE(co)[0]) == COPY_FREE_VARS);
             assert(PyCell_Check(firstarg));
             firstarg = PyCell_GET(firstarg);
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 72f9245..5a1d2c0 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -113,46 +113,46 @@ extern "C" {
 #endif
 
 #define _PyUnicode_UTF8(op)                             \
-    (((PyCompactUnicodeObject*)(op))->utf8)
+    (_PyCompactUnicodeObject_CAST(op)->utf8)
 #define PyUnicode_UTF8(op)                              \
     (assert(_PyUnicode_CHECK(op)),                      \
      assert(PyUnicode_IS_READY(op)),                    \
      PyUnicode_IS_COMPACT_ASCII(op) ?                   \
-         ((char*)((PyASCIIObject*)(op) + 1)) :          \
+         ((char*)(_PyASCIIObject_CAST(op) + 1)) :       \
          _PyUnicode_UTF8(op))
 #define _PyUnicode_UTF8_LENGTH(op)                      \
-    (((PyCompactUnicodeObject*)(op))->utf8_length)
+    (_PyCompactUnicodeObject_CAST(op)->utf8_length)
 #define PyUnicode_UTF8_LENGTH(op)                       \
     (assert(_PyUnicode_CHECK(op)),                      \
      assert(PyUnicode_IS_READY(op)),                    \
      PyUnicode_IS_COMPACT_ASCII(op) ?                   \
-         ((PyASCIIObject*)(op))->length :               \
+         _PyASCIIObject_CAST(op)->length :              \
          _PyUnicode_UTF8_LENGTH(op))
 #define _PyUnicode_WSTR(op)                             \
-    (((PyASCIIObject*)(op))->wstr)
+    (_PyASCIIObject_CAST(op)->wstr)
 
 /* Don't use deprecated macro of unicodeobject.h */
 #undef PyUnicode_WSTR_LENGTH
 #define PyUnicode_WSTR_LENGTH(op) \
-    (PyUnicode_IS_COMPACT_ASCII(op) ?                  \
-     ((PyASCIIObject*)op)->length :                    \
-     ((PyCompactUnicodeObject*)op)->wstr_length)
+    (PyUnicode_IS_COMPACT_ASCII(op) ?                   \
+     _PyASCIIObject_CAST(op)->length :                  \
+     _PyCompactUnicodeObject_CAST(op)->wstr_length)
 #define _PyUnicode_WSTR_LENGTH(op)                      \
-    (((PyCompactUnicodeObject*)(op))->wstr_length)
+    (_PyCompactUnicodeObject_CAST(op)->wstr_length)
 #define _PyUnicode_LENGTH(op)                           \
-    (((PyASCIIObject *)(op))->length)
+    (_PyASCIIObject_CAST(op)->length)
 #define _PyUnicode_STATE(op)                            \
-    (((PyASCIIObject *)(op))->state)
+    (_PyASCIIObject_CAST(op)->state)
 #define _PyUnicode_HASH(op)                             \
-    (((PyASCIIObject *)(op))->hash)
+    (_PyASCIIObject_CAST(op)->hash)
 #define _PyUnicode_KIND(op)                             \
     (assert(_PyUnicode_CHECK(op)),                      \
-     ((PyASCIIObject *)(op))->state.kind)
+     _PyASCIIObject_CAST(op)->state.kind)
 #define _PyUnicode_GET_LENGTH(op)                       \
     (assert(_PyUnicode_CHECK(op)),                      \
-     ((PyASCIIObject *)(op))->length)
+     _PyASCIIObject_CAST(op)->length)
 #define _PyUnicode_DATA_ANY(op)                         \
-    (((PyUnicodeObject*)(op))->data.any)
+    (_PyUnicodeObject_CAST(op)->data.any)
 
 #undef PyUnicode_READY
 #define PyUnicode_READY(op)                             \
@@ -190,7 +190,7 @@ extern "C" {
    buffer where the result characters are written to. */
 #define _PyUnicode_CONVERT_BYTES(from_type, to_type, begin, end, to) \
     do {                                                \
-        to_type *_to = (to_type *)(to);                \
+        to_type *_to = (to_type *)(to);                 \
         const from_type *_iter = (const from_type *)(begin);\
         const from_type *_end = (const from_type *)(end);\
         Py_ssize_t n = (_end) - (_iter);                \
@@ -509,21 +509,18 @@ _PyUnicode_CheckConsistency(PyObject *op, int check_content)
 #define CHECK(expr) \
     do { if (!(expr)) { _PyObject_ASSERT_FAILED_MSG(op, Py_STRINGIFY(expr)); } } while (0)
 
-    PyASCIIObject *ascii;
-    unsigned int kind;
-
     assert(op != NULL);
     CHECK(PyUnicode_Check(op));
 
-    ascii = (PyASCIIObject *)op;
-    kind = ascii->state.kind;
+    PyASCIIObject *ascii = _PyASCIIObject_CAST(op);
+    unsigned int kind = ascii->state.kind;
 
     if (ascii->state.ascii == 1 && ascii->state.compact == 1) {
         CHECK(kind == PyUnicode_1BYTE_KIND);
         CHECK(ascii->state.ready == 1);
     }
     else {
-        PyCompactUnicodeObject *compact = (PyCompactUnicodeObject *)op;
+        PyCompactUnicodeObject *compact = _PyCompactUnicodeObject_CAST(op);
         void *data;
 
         if (ascii->state.compact == 1) {
@@ -536,7 +533,7 @@ _PyUnicode_CheckConsistency(PyObject *op, int check_content)
             CHECK(compact->utf8 != data);
         }
         else {
-            PyUnicodeObject *unicode = (PyUnicodeObject *)op;
+            PyUnicodeObject *unicode = _PyUnicodeObject_CAST(op);
 
             data = unicode->data.any;
             if (kind == PyUnicode_WCHAR_KIND) {
@@ -1330,8 +1327,8 @@ const void *_PyUnicode_data(void *unicode_raw) {
     printf("obj %p\n", (void*)unicode);
     printf("compact %d\n", PyUnicode_IS_COMPACT(unicode));
     printf("compact ascii %d\n", PyUnicode_IS_COMPACT_ASCII(unicode));
-    printf("ascii op %p\n", ((void*)((PyASCIIObject*)(unicode) + 1)));
-    printf("compact op %p\n", ((void*)((PyCompactUnicodeObject*)(unicode) + 1)));
+    printf("ascii op %p\n", (void*)(_PyASCIIObject_CAST(unicode) + 1));
+    printf("compact op %p\n", (void*)(_PyCompactUnicodeObject_CAST(unicode) + 1));
     printf("compact data %p\n", _PyUnicode_COMPACT_DATA(unicode));
     return PyUnicode_DATA(unicode);
 }
@@ -1339,9 +1336,9 @@ const void *_PyUnicode_data(void *unicode_raw) {
 void
 _PyUnicode_Dump(PyObject *op)
 {
-    PyASCIIObject *ascii = (PyASCIIObject *)op;
-    PyCompactUnicodeObject *compact = (PyCompactUnicodeObject *)op;
-    PyUnicodeObject *unicode = (PyUnicodeObject *)op;
+    PyASCIIObject *ascii = _PyASCIIObject_CAST(op);
+    PyCompactUnicodeObject *compact = _PyCompactUnicodeObject_CAST(op);
+    PyUnicodeObject *unicode = _PyUnicodeObject_CAST(op);
     const void *data;
 
     if (ascii->state.compact)
@@ -1976,7 +1973,7 @@ unicode_is_singleton(PyObject *unicode)
         return 1;
     }
 
-    PyASCIIObject *ascii = (PyASCIIObject *)unicode;
+    PyASCIIObject *ascii = _PyASCIIObject_CAST(unicode);
     if (ascii->state.kind != PyUnicode_WCHAR_KIND && ascii->length == 1) {
         Py_UCS4 ch = PyUnicode_READ_CHAR(unicode, 0);
         if (ch < 256 && LATIN1(ch) == unicode) {
@@ -16053,7 +16050,7 @@ _PyUnicode_FiniTypes(PyInterpreterState *interp)
 
 static void unicode_static_dealloc(PyObject *op)
 {
-    PyASCIIObject* ascii = (PyASCIIObject*)op;
+    PyASCIIObject *ascii = _PyASCIIObject_CAST(op);
 
     assert(ascii->state.compact);
 
diff --git a/Python/traceback.c b/Python/traceback.c
index 6a721cf..f5c1849 100644
--- a/Python/traceback.c
+++ b/Python/traceback.c
@@ -1073,7 +1073,7 @@ _Py_DumpHexadecimal(int fd, uintptr_t value, Py_ssize_t width)
 void
 _Py_DumpASCII(int fd, PyObject *text)
 {
-    PyASCIIObject *ascii = (PyASCIIObject *)text;
+    PyASCIIObject *ascii = _PyASCIIObject_CAST(text);
     Py_ssize_t i, size;
     int truncated;
     int kind;
@@ -1087,19 +1087,19 @@ _Py_DumpASCII(int fd, PyObject *text)
     size = ascii->length;
     kind = ascii->state.kind;
     if (kind == PyUnicode_WCHAR_KIND) {
-        wstr = ((PyASCIIObject *)text)->wstr;
+        wstr = ascii->wstr;
         if (wstr == NULL)
             return;
-        size = ((PyCompactUnicodeObject *)text)->wstr_length;
+        size = _PyCompactUnicodeObject_CAST(text)->wstr_length;
     }
     else if (ascii->state.compact) {
         if (ascii->state.ascii)
-            data = ((PyASCIIObject*)text) + 1;
+            data = ascii + 1;
         else
-            data = ((PyCompactUnicodeObject*)text) + 1;
+            data = _PyCompactUnicodeObject_CAST(text) + 1;
     }
     else {
-        data = ((PyUnicodeObject *)text)->data.any;
+        data = _PyUnicodeObject_CAST(text)->data.any;
         if (data == NULL)
             return;
     }