[Python-checkins] gh-89653: PEP 670: Convert unicodeobject.h macros to functions (#91705)
vstinner
webhook-mailer at python.org
Wed Apr 20 20:51:26 EDT 2022
https://github.com/python/cpython/commit/4e52c66f6940a63ef7a62faf8ce32a980ac5aa2c
commit: 4e52c66f6940a63ef7a62faf8ce32a980ac5aa2c
branch: main
author: Victor Stinner <vstinner at python.org>
committer: vstinner <vstinner at python.org>
date: 2022-04-21T02:51:17+02:00
summary:
gh-89653: PEP 670: Convert unicodeobject.h macros to functions (#91705)
Convert unicodeobject.h macros to static inline functions:
* PyUnicode_CHECK_INTERNED()
* PyUnicode_DATA(), _PyUnicode_COMPACT_DATA(),
_PyUnicode_NONCOMPACT_DATA()
* PyUnicode_GET_LENGTH()
* PyUnicode_IS_ASCII()
* PyUnicode_IS_COMPACT()
* PyUnicode_IS_COMPACT_ASCII()
* PyUnicode_IS_READY()
Reorder functions to declare functions before their first usage.
Static inline functions are wrapped by macros which casts
arguments with _PyObject_CAST() to prevent introducing
new compiler warnings when passing "const PyObject*".
files:
M Include/cpython/unicodeobject.h
diff --git a/Include/cpython/unicodeobject.h b/Include/cpython/unicodeobject.h
index 69e4abfb5c442..9a993a1c7ff0c 100644
--- a/Include/cpython/unicodeobject.h
+++ b/Include/cpython/unicodeobject.h
@@ -287,37 +287,80 @@ PyAPI_FUNC(int) _PyUnicode_CheckConsistency(
#define SSTATE_INTERNED_IMMORTAL 2
/* Use only if you know it's a string */
-#define PyUnicode_CHECK_INTERNED(op) \
- (_PyASCIIObject_CAST(op)->state.interned)
+static inline unsigned int PyUnicode_CHECK_INTERNED(PyObject *op) {
+ return _PyASCIIObject_CAST(op)->state.interned;
+}
+#define PyUnicode_CHECK_INTERNED(op) PyUnicode_CHECK_INTERNED(_PyObject_CAST(op))
+
+/* Fast check to determine whether an object is ready. Equivalent to:
+ PyUnicode_IS_COMPACT(op) || _PyUnicodeObject_CAST(op)->data.any */
+static inline unsigned int PyUnicode_IS_READY(PyObject *op) {
+ return _PyASCIIObject_CAST(op)->state.ready;
+}
+#define PyUnicode_IS_READY(op) PyUnicode_IS_READY(_PyObject_CAST(op))
/* 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_IS_READY(op)), \
- _PyASCIIObject_CAST(op)->state.ascii)
+static inline unsigned int PyUnicode_IS_ASCII(PyObject *op) {
+ assert(PyUnicode_IS_READY(op));
+ return _PyASCIIObject_CAST(op)->state.ascii;
+}
+#define PyUnicode_IS_ASCII(op) PyUnicode_IS_ASCII(_PyObject_CAST(op))
/* 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_CAST(op)->state.compact)
+static inline unsigned int PyUnicode_IS_COMPACT(PyObject *op) {
+ return _PyASCIIObject_CAST(op)->state.compact;
+}
+#define PyUnicode_IS_COMPACT(op) PyUnicode_IS_COMPACT(_PyObject_CAST(op))
/* 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_CAST(op)->state.ascii && PyUnicode_IS_COMPACT(op))
+static inline int PyUnicode_IS_COMPACT_ASCII(PyObject *op) {
+ return (_PyASCIIObject_CAST(op)->state.ascii && PyUnicode_IS_COMPACT(op));
+}
+#define PyUnicode_IS_COMPACT_ASCII(op) PyUnicode_IS_COMPACT_ASCII(_PyObject_CAST(op))
enum PyUnicode_Kind {
/* String contains only wstr byte characters. This is only possible
when the string was created with a legacy API and _PyUnicode_Ready()
has not been called yet. */
PyUnicode_WCHAR_KIND = 0,
-/* Return values of the PyUnicode_KIND() macro: */
+/* Return values of the PyUnicode_KIND() function: */
PyUnicode_1BYTE_KIND = 1,
PyUnicode_2BYTE_KIND = 2,
PyUnicode_4BYTE_KIND = 4
};
+/* 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)
+
+/* Return a void pointer to the raw unicode buffer. */
+static inline void* _PyUnicode_COMPACT_DATA(PyObject *op) {
+ if (PyUnicode_IS_ASCII(op)) {
+ return (void*)(_PyASCIIObject_CAST(op) + 1);
+ }
+ return (void*)(_PyCompactUnicodeObject_CAST(op) + 1);
+}
+
+static inline void* _PyUnicode_NONCOMPACT_DATA(PyObject *op) {
+ void *data = _PyUnicodeObject_CAST(op)->data.any;
+ assert(data != NULL);
+ return data;
+}
+
+static inline void* PyUnicode_DATA(PyObject *op) {
+ if (PyUnicode_IS_COMPACT(op)) {
+ return _PyUnicode_COMPACT_DATA(op);
+ }
+ return _PyUnicode_NONCOMPACT_DATA(op);
+}
+#define PyUnicode_DATA(op) PyUnicode_DATA(_PyObject_CAST(op))
+
/* Return pointers to the canonical representation cast to unsigned char,
Py_UCS2, or Py_UCS4 for direct character access.
No checks are performed, use PyUnicode_KIND() before to ensure
@@ -327,24 +370,14 @@ enum PyUnicode_Kind {
#define PyUnicode_2BYTE_DATA(op) ((Py_UCS2*)PyUnicode_DATA(op))
#define PyUnicode_4BYTE_DATA(op) ((Py_UCS4*)PyUnicode_DATA(op))
-/* Return one of the PyUnicode_*_KIND values defined above. */
-#define PyUnicode_KIND(op) \
- (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_CAST(op) + 1)) : \
- ((void*)(_PyCompactUnicodeObject_CAST(op) + 1)))
-
-#define _PyUnicode_NONCOMPACT_DATA(op) \
- (assert(_PyUnicodeObject_CAST(op)->data.any), \
- (_PyUnicodeObject_CAST(op)->data.any))
-
-#define PyUnicode_DATA(op) \
- (PyUnicode_IS_COMPACT(op) ? _PyUnicode_COMPACT_DATA(op) : \
- _PyUnicode_NONCOMPACT_DATA(op))
+/* Returns the length of the unicode string. The caller has to make sure that
+ the string has it's canonical representation set before calling
+ this function. Call PyUnicode_(FAST_)Ready to ensure that. */
+static inline Py_ssize_t PyUnicode_GET_LENGTH(PyObject *op) {
+ assert(PyUnicode_IS_READY(op));
+ return _PyASCIIObject_CAST(op)->length;
+}
+#define PyUnicode_GET_LENGTH(op) PyUnicode_GET_LENGTH(_PyObject_CAST(op))
/* In the access macros below, "kind" may be evaluated more than once.
All other macro parameters are evaluated exactly once, so it is safe
@@ -400,19 +433,6 @@ enum PyUnicode_Kind {
) \
))
-/* Returns the length of the unicode string. The caller has to make sure that
- 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_IS_READY(op)), \
- _PyASCIIObject_CAST(op)->length)
-
-
-/* Fast check to determine whether an object is ready. Equivalent to
- PyUnicode_IS_COMPACT(op) || _PyUnicodeObject_CAST(op)->data.any */
-
-#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().
More information about the Python-checkins
mailing list