Add interning of unicode strings by copying the functionality from

stringobject.c.

Intern "True" and "False" in bool_repr() again as it was in the
8bit string era.

1 files changed, 15 insertions, 0 deletions

diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index 131278d..2a27dbc 100644
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -390,6 +390,9 @@ typedef struct {
     Py_ssize_t length;		/* Length of raw Unicode data in buffer */
     Py_UNICODE *str;		/* Raw Unicode buffer */
     long hash;			/* Hash value; -1 if not set */
+    int state;			/* != 0 if interned. In this case the two
+    				 * references from the dictionary to this object
+    				 * are *not* counted in ob_refcnt. */
     PyObject *defenc;		/* (Default) Encoded version as Python
 				   string, or NULL; this is used for
 				   implementing the buffer protocol */
@@ -397,6 +400,10 @@ typedef struct {
 
 PyAPI_DATA(PyTypeObject) PyUnicode_Type;
 
+#define SSTATE_NOT_INTERNED 0
+#define SSTATE_INTERNED_MORTAL 1
+#define SSTATE_INTERNED_IMMORTAL 2
+
 #define PyUnicode_Check(op) \
                  PyType_FastSubclass((op)->ob_type, Py_TPFLAGS_UNICODE_SUBCLASS)
 #define PyUnicode_CheckExact(op) ((op)->ob_type == &PyUnicode_Type)
@@ -529,6 +536,14 @@ PyAPI_FUNC(PyObject*) PyUnicode_FromObject(
 PyAPI_FUNC(PyObject *) PyUnicode_FromFormatV(const char*, va_list);
 PyAPI_FUNC(PyObject *) PyUnicode_FromFormat(const char*, ...);
 
+PyAPI_FUNC(void) PyUnicode_InternInPlace(PyObject **);
+PyAPI_FUNC(void) PyUnicode_InternImmortal(PyObject **);
+PyAPI_FUNC(PyObject *) PyUnicode_InternFromString(const char *);
+PyAPI_FUNC(void) _Py_ReleaseInternedUnicodeStrings(void);
+
+/* Use only if you know it's a string */
+#define PyUnicode_CHECK_INTERNED(op) (((PyUnicodeObject *)(op))->state)
+
 /* --- wchar_t support for platforms which support it --------------------- */
 
 #ifdef HAVE_WCHAR_H