[Python-checkins] cpython: _PyUnicode_Ready() cannot be used on ready strings anymore

Thu Sep 29 19:46:13 CEST 2011

http://hg.python.org/cpython/rev/2fc483009f6d
changeset: 72529:2fc483009f6d
user: Victor Stinner <victor.stinner at haypocalc.com>
date: Thu Sep 29 19:43:17 2011 +0200
summary:
 _PyUnicode_Ready() cannot be used on ready strings anymore
 * Change its prototype: PyObject* instead of PyUnicodeoObject*.
 * Remove an old assertion, the result of PyUnicode_READY (_PyUnicode_Ready)
 must be checked instead
files:
 Include/unicodeobject.h | 16 ++++++-----
 Objects/unicodeobject.c | 40 +++++++++++-----------------
 2 files changed, 25 insertions(+), 31 deletions(-)

diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -456,7 +456,7 @@
 #define PyUnicode_READY(op) \
 (assert(PyUnicode_Check(op)), \
 (PyUnicode_IS_READY(op) ? \
- 0 : _PyUnicode_Ready((PyUnicodeObject *)(op))))
+ 0 : _PyUnicode_Ready((PyObject *)(op))))
 
 /* Return a maximum character value which is suitable for creating another
 string based on op. This is always an approximation but more efficient
@@ -497,14 +497,16 @@
 );
 #endif
 
-/* Initializes the canonical string representation from a the deprected
- wstr/Py_UNICODE representation. This function is used to convert
- unicode objects which were created using the old API to the new flexible
- format introduced with PEP 393. The PyUnicode_READY() macro can be
- more efficient if the string is already ready. */
+/* Initializes the canonical string representation from a the deprecated
+ wstr/Py_UNICODE representation. This function is used to convert Unicode
+ objects which were created using the old API to the new flexible format
+ introduced with PEP 393.
+
+ Don't call this function directly, use the public PyUnicode_READY() macro
+ instead. */
 #ifndef Py_LIMITED_API
 PyAPI_FUNC(int) _PyUnicode_Ready(
- PyUnicodeObject *unicode /* Unicode object */
+ PyObject *unicode /* Unicode object */
 );
 #endif
 
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -781,8 +781,9 @@
 #endif
 
 int
-_PyUnicode_Ready(PyUnicodeObject *unicode)
-{
+_PyUnicode_Ready(PyObject *obj)
+{
+ PyUnicodeObject *unicode = (PyUnicodeObject *)obj;
 wchar_t *end;
 Py_UCS4 maxchar = 0;
 Py_ssize_t num_surrogates;
@@ -790,25 +791,19 @@
 Py_ssize_t length_wo_surrogates;
 #endif
 
- assert(PyUnicode_Check(unicode));
-
- if (unicode->data.any != NULL) {
- assert(PyUnicode_KIND(unicode) != PyUnicode_WCHAR_KIND);
- return 0;
- }
-
 /* _PyUnicode_Ready() is only intented for old-style API usage where
- * strings were created using _PyObject_New() and where no canonical
- * representation (the str field) has been set yet aka strings
- * which are not yet ready.
- */
+ strings were created using _PyObject_New() and where no canonical
+ representation (the str field) has been set yet aka strings
+ which are not yet ready. */
+ assert(PyUnicode_Check(obj));
+ assert(!PyUnicode_IS_READY(obj));
+ assert(!PyUnicode_IS_COMPACT(obj));
+ assert(_PyUnicode_KIND(obj) == PyUnicode_WCHAR_KIND);
 assert(_PyUnicode_WSTR(unicode) != NULL);
- assert(_PyUnicode_KIND(unicode) == PyUnicode_WCHAR_KIND);
- assert(!PyUnicode_IS_COMPACT(unicode));
- assert(!PyUnicode_IS_READY(unicode));
+ assert(unicode->data.any == NULL);
+ assert(unicode->_base.utf8 == NULL);
 /* Actually, it should neither be interned nor be anything else: */
- assert(_PyUnicode_STATE(unicode).interned == 0);
- assert(unicode->_base.utf8 == NULL);
+ assert(_PyUnicode_STATE(unicode).interned == SSTATE_NOT_INTERNED);
 
 #ifdef Py_DEBUG
 ++unicode_ready_calls;
@@ -816,11 +811,8 @@
 
 end = _PyUnicode_WSTR(unicode) + _PyUnicode_WSTR_LENGTH(unicode);
 if (find_maxchar_surrogates(_PyUnicode_WSTR(unicode), end,
- &maxchar,
- &num_surrogates) == -1) {
- assert(0 && "PyUnicode_FindMaxCharAndNumSurrogatePairs failed");
+ &maxchar, &num_surrogates) == -1)
 return -1;
- }
 
 if (maxchar < 256) {
 unicode->data.any = PyObject_MALLOC(_PyUnicode_WSTR_LENGTH(unicode) + 1);
@@ -1046,8 +1038,8 @@
 
 /* If not empty and not single character, copy the Unicode data
 into the new object */
- if (find_maxchar_surrogates(u, u + size, &maxchar,
- &num_surrogates) == -1)
+ if (find_maxchar_surrogates(u, u + size,
+ &maxchar, &num_surrogates) == -1)
 return NULL;
 
 unicode = (PyUnicodeObject *) PyUnicode_New(size - num_surrogates,
-- 
Repository URL: http://hg.python.org/cpython
