bpo-41746: Add type information to asdl_seq objects (GH-22223)

* Add new capability to the PEG parser to type variable assignments. For instance:
```
       | a[asdl_stmt_seq*]=';'.small_stmt+ [';'] NEWLINE { a }
```

* Add new sequence types from the asdl definition (automatically generated)
* Make `asdl_seq` type a generic aliasing pointer type.
* Create a new `asdl_generic_seq` for the generic case using `void*`.
* The old `asdl_seq_GET`/`ast_seq_SET` macros now are typed.
* New `asdl_seq_GET_UNTYPED`/`ast_seq_SET_UNTYPED` macros for dealing with generic sequences.
* Changes all possible `asdl_seq` types to use specific versions everywhere.

1 files changed, 63 insertions, 8 deletions

diff --git a/Include/asdl.h b/Include/asdl.h
index e962560..8b61e16 100644
--- a/Include/asdl.h
+++ b/Include/asdl.h
@@ -13,22 +13,65 @@ typedef PyObject * constant;
    interned Python strings.
 */
 
-/* XXX A sequence should be typed so that its use can be typechecked. */
+#define _ASDL_SEQ_HEAD \
+    Py_ssize_t size;   \
+    void **elements;
 
 typedef struct {
-    Py_ssize_t size;
-    void *elements[1];
+    _ASDL_SEQ_HEAD
 } asdl_seq;
 
 typedef struct {
-    Py_ssize_t size;
-    int elements[1];
+    _ASDL_SEQ_HEAD
+    void *typed_elements[1];
+} asdl_generic_seq;
+
+typedef struct {
+    _ASDL_SEQ_HEAD
+    PyObject *typed_elements[1];
+} asdl_identifier_seq;
+
+typedef struct {
+    _ASDL_SEQ_HEAD
+    int typed_elements[1];
 } asdl_int_seq;
 
-asdl_seq *_Py_asdl_seq_new(Py_ssize_t size, PyArena *arena);
+asdl_generic_seq *_Py_asdl_generic_seq_new(Py_ssize_t size, PyArena *arena);
+asdl_identifier_seq *_Py_asdl_identifier_seq_new(Py_ssize_t size, PyArena *arena);
 asdl_int_seq *_Py_asdl_int_seq_new(Py_ssize_t size, PyArena *arena);
 
-#define asdl_seq_GET(S, I) (S)->elements[(I)]
+
+#define GENERATE_ASDL_SEQ_CONSTRUCTOR(NAME, TYPE) \
+asdl_ ## NAME ## _seq *_Py_asdl_ ## NAME ## _seq_new(Py_ssize_t size, PyArena *arena) \
+{ \
+    asdl_ ## NAME ## _seq *seq = NULL; \
+    size_t n; \
+    /* check size is sane */ \
+    if (size < 0 || \
+        (size && (((size_t)size - 1) > (SIZE_MAX / sizeof(void *))))) { \
+        PyErr_NoMemory(); \
+        return NULL; \
+    } \
+    n = (size ? (sizeof(TYPE *) * (size - 1)) : 0); \
+    /* check if size can be added safely */ \
+    if (n > SIZE_MAX - sizeof(asdl_ ## NAME ## _seq)) { \
+        PyErr_NoMemory(); \
+        return NULL; \
+    } \
+    n += sizeof(asdl_ ## NAME ## _seq); \
+    seq = (asdl_ ## NAME ## _seq *)PyArena_Malloc(arena, n); \
+    if (!seq) { \
+        PyErr_NoMemory(); \
+        return NULL; \
+    } \
+    memset(seq, 0, n); \
+    seq->size = size; \
+    seq->elements = (void**)seq->typed_elements; \
+    return seq; \
+}
+
+#define asdl_seq_GET_UNTYPED(S, I) (S)->elements[(I)]
+#define asdl_seq_GET(S, I) (S)->typed_elements[(I)]
 #define asdl_seq_LEN(S) ((S) == NULL ? 0 : (S)->size)
 #ifdef Py_DEBUG
 #define asdl_seq_SET(S, I, V) \
@@ -36,10 +79,22 @@ asdl_int_seq *_Py_asdl_int_seq_new(Py_ssize_t size, PyArena *arena);
         Py_ssize_t _asdl_i = (I); \
         assert((S) != NULL); \
         assert(0 <= _asdl_i && _asdl_i < (S)->size); \
+        (S)->typed_elements[_asdl_i] = (V); \
+    } while (0)
+#else
+#define asdl_seq_SET(S, I, V) (S)->typed_elements[I] = (V)
+#endif
+
+#ifdef Py_DEBUG
+#define asdl_seq_SET_UNTYPED(S, I, V) \
+    do { \
+        Py_ssize_t _asdl_i = (I); \
+        assert((S) != NULL); \
+        assert(0 <= _asdl_i && _asdl_i < (S)->size); \
         (S)->elements[_asdl_i] = (V); \
     } while (0)
 #else
-#define asdl_seq_SET(S, I, V) (S)->elements[I] = (V)
+#define asdl_seq_SET_UNTYPED(S, I, V) (S)->elements[I] = (V)
 #endif
 
 #endif /* !Py_ASDL_H */