Mercurial > cpython-lru_cache-weakref

diff Include/unicodeobject.h @ 42013:cd125fe83051

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Make identifiers str (not str8) objects throughout. This affects the parser, various object implementations, and all places that put identifiers into C string literals. In testing, a number of crashes occurred as code would fail when the recursion limit was reached (such as the Unicode interning dictionary having key/value pairs where key is not value). To solve these, I added an overflowed flag, which allows for 50 more recursions after the limit was reached and the exception was raised, and a recursion_critical flag, which indicates that recursion absolutely must be allowed, i.e. that a certain call must not cause a stack overflow exception. There are still some places where both str and str8 are accepted as identifiers; these should eventually be removed.
author Martin v. Löwis <martin@v.loewis.de>
date Sun, 10 Jun 2007 09:51:05 +0000
parents dcb43f40390b
children e70cdce0e8b2
line wrap: on
line diff
--- a/Include/unicodeobject.h	Sat Jun 09 16:13:23 2007 +0000
+++ b/Include/unicodeobject.h	Sun Jun 10 09:51:05 2007 +0000
@@ -410,13 +410,13 @@
 
 /* Fast access macros */
 #define PyUnicode_GET_SIZE(op) \
-        (((PyUnicodeObject *)(op))->length)
+        (assert(PyUnicode_Check(op)),(((PyUnicodeObject *)(op))->length))
 #define PyUnicode_GET_DATA_SIZE(op) \
-        (((PyUnicodeObject *)(op))->length * sizeof(Py_UNICODE))
+        (assert(PyUnicode_Check(op)),(((PyUnicodeObject *)(op))->length * sizeof(Py_UNICODE)))
 #define PyUnicode_AS_UNICODE(op) \
-        (((PyUnicodeObject *)(op))->str)
+        (assert(PyUnicode_Check(op)),(((PyUnicodeObject *)(op))->str))
 #define PyUnicode_AS_DATA(op) \
-        ((const char *)((PyUnicodeObject *)(op))->str)
+        (assert(PyUnicode_Check(op)),((const char *)((PyUnicodeObject *)(op))->str))
 
 /* --- Constants ---------------------------------------------------------- */
 
@@ -627,6 +627,13 @@
 PyAPI_FUNC(PyObject *) _PyUnicode_AsDefaultEncodedString(
     PyObject *, const char *);
 
+/* Return a char* holding the default encoded value of the
+   Unicode object. 
+*/
+
+PyAPI_FUNC(char *) PyUnicode_AsString(PyObject*);
+
+
 /* Returns the currently active default encoding.
 
    The default encoding is currently implemented as run-time settable
@@ -1193,6 +1200,11 @@
     PyObject *right		/* Right string */
     );
 
+PyAPI_FUNC(int) PyUnicode_CompareWithASCIIString(
+    PyObject *left,
+    const char *right
+    );
+
 /* Rich compare two strings and return one of the following:
 
    - NULL in case an exception was raised
@@ -1310,6 +1322,22 @@
     Py_UNICODE ch 	/* Unicode character */
     );
 
+PyAPI_FUNC(size_t) Py_UNICODE_strlen(const Py_UNICODE *u);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strcpy(
+    Py_UNICODE *s1, const Py_UNICODE *s2);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strncpy(
+    Py_UNICODE *s1, const Py_UNICODE *s2, size_t n);
+
+PyAPI_FUNC(int) Py_UNICODE_strcmp(
+    const Py_UNICODE *s1, const Py_UNICODE *s2);
+
+PyAPI_FUNC(Py_UNICODE*) Py_UNICODE_strchr(
+    const Py_UNICODE *s, Py_UNICODE c
+    );
+
+
 #ifdef __cplusplus
 }
 #endif