experimental UCS-4 support: added USE_UCS4_STORAGE define to

unicodeobject.h, which forces sizeof(Py_UNICODE) == sizeof(Py_UCS4).
(this may be good enough for platforms that doesn't have a 16-bit
type.  the UTF-16 codecs don't work, though)

diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index f91a5a0c8c7f35e0b7fbd8bb3b83e437bd89084e..e330fd1bbe5d0274178ef3d0c307159c129d66a4 100644 (file)
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -58,6 +58,19 @@ Copyright (c) Corporation for National Research Initiatives.
 
 /* --- Internal Unicode Format -------------------------------------------- */
 
+/* experimental UCS-4 support.  enable at your own risk! */
+#undef USE_UCS4_STORAGE
+
+/*
+ * Use this typedef when you need to represent a UTF-16 surrogate pair
+ * as single unsigned integer.
+ */
+#if SIZEOF_INT >= 4 
+typedef unsigned int Py_UCS4; 
+#elif SIZEOF_LONG >= 4
+typedef unsigned long Py_UCS4; 
+#endif 
+
 /* Set these flags if the platform has "wchar.h", "wctype.h" and the
    wchar_t type is a 16-bit unsigned type */
 /* #define HAVE_WCHAR_H */
@@ -66,8 +79,8 @@ Copyright (c) Corporation for National Research Initiatives.
 /* Defaults for various platforms */
 #ifndef HAVE_USABLE_WCHAR_T
 
-/* Windows has a usable wchar_t type */
-# if defined(MS_WIN32)
+/* Windows has a usable wchar_t type (unless we're using UCS-4) */
+# if defined(MS_WIN32) && !defined(USE_UCS4_STORAGE)
 #  define HAVE_USABLE_WCHAR_T
 # endif
 
@@ -105,19 +118,13 @@ typedef wchar_t Py_UNICODE;
    If a short is not 16 bits on your platform, you have to fix the
    typedef below, or the module initialization code will complain. */
 
+#ifdef USE_UCS4_STORAGE
+typedef Py_UCS4 Py_UNICODE;
+#else
 typedef unsigned short Py_UNICODE;
-
 #endif
 
-/*
- * Use this typedef when you need to represent a UTF-16 surrogate pair
- * as single unsigned integer.
- */
-#if SIZEOF_INT >= 4 
-typedef unsigned int Py_UCS4; 
-#elif SIZEOF_LONG >= 4
-typedef unsigned long Py_UCS4; 
-#endif 
+#endif
 
 
 /* --- Internal Unicode Operations ---------------------------------------- */

diff --git a/Modules/sre.h b/Modules/sre.h
index bf58eb5434501b95f9ac235a61b82c06319e060a..61a020896ab0b19119412c165953654abfbf1dca 100644 (file)
--- a/Modules/sre.h
+++ b/Modules/sre.h
@@ -14,7 +14,11 @@
 #include "sre_constants.h"
 
 /* size of a code word (must be unsigned short or larger) */
+#ifdef USE_UCS4_STORAGE
+#define SRE_CODE unsigned long
+#else
 #define SRE_CODE unsigned short
+#endif
 
 typedef struct {
     PyObject_VAR_HEAD

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index c62f65bcd0e27a6585cd6caad7dd626f4458e708..742c770f34379692f18db72fb3a88c1d2b18e499 100644 (file)
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -5282,9 +5282,11 @@ void _PyUnicode_Init(void)
     int i;
 
     /* Doublecheck the configuration... */
+#ifndef USE_UCS4_STORAGE
     if (sizeof(Py_UNICODE) != 2)
         Py_FatalError("Unicode configuration error: "
                      "sizeof(Py_UNICODE) != 2 bytes");
+#endif
 
     /* Init the implementation */
     unicode_freelist = NULL;