1 files changed, 39 insertions, 24 deletions

diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index 2c496eaada..643d10d274 100644
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -103,10 +103,6 @@ typedef wchar_t Py_UNICODE;
 # endif
 #endif
 
-#if defined(MS_WINDOWS)
-#  define HAVE_MBCS
-#endif
-
 #ifdef HAVE_WCHAR_H
 /* Work around a cosmetic bug in BSDI 4.x wchar.h; thanks to Thomas Wouters */
 # ifdef _HAVE_BSDI
@@ -117,21 +113,9 @@ typedef wchar_t Py_UNICODE;
 
 /* Py_UCS4 and Py_UCS2 are typedefs for the respective
    unicode representations. */
-#if SIZEOF_INT == 4
-typedef unsigned int Py_UCS4;
-#elif SIZEOF_LONG == 4
-typedef unsigned long Py_UCS4;
-#else
-#error "Could not find a proper typedef for Py_UCS4"
-#endif
-
-#if SIZEOF_SHORT == 2
-typedef unsigned short Py_UCS2;
-#else
-#error "Could not find a proper typedef for Py_UCS2"
-#endif
-
-typedef unsigned char Py_UCS1;
+typedef uint32_t Py_UCS4;
+typedef uint16_t Py_UCS2;
+typedef uint8_t Py_UCS1;
 
 /* --- Internal Unicode Operations ---------------------------------------- */
 
@@ -172,7 +156,7 @@ typedef unsigned char Py_UCS1;
     Py_UNICODE_ISNUMERIC(ch))
 
 #define Py_UNICODE_COPY(target, source, length) \
-    Py_MEMCPY((target), (source), (length)*sizeof(Py_UNICODE))
+    memcpy((target), (source), (length)*sizeof(Py_UNICODE))
 
 #define Py_UNICODE_FILL(target, value, length) \
     do {Py_ssize_t i_; Py_UNICODE *t_ = (target); Py_UNICODE v_ = (value);\
@@ -900,7 +884,7 @@ typedef struct {
     /* minimum character (default: 127, ASCII) */
     Py_UCS4 min_char;
 
-    /* If non-zero, overallocate the buffer by 25% (default: 0). */
+    /* If non-zero, overallocate the buffer (default: 0). */
     unsigned char overallocate;
 
     /* If readonly is 1, buffer is a shared string (cannot be modified)
@@ -934,6 +918,23 @@ PyAPI_FUNC(int)
 _PyUnicodeWriter_PrepareInternal(_PyUnicodeWriter *writer,
                                  Py_ssize_t length, Py_UCS4 maxchar);
 
+/* Prepare the buffer to have at least the kind KIND.
+   For example, kind=PyUnicode_2BYTE_KIND ensures that the writer will
+   support characters in range U+000-U+FFFF.
+
+   Return 0 on success, raise an exception and return -1 on error. */
+#define _PyUnicodeWriter_PrepareKind(WRITER, KIND)                    \
+    (assert((KIND) != PyUnicode_WCHAR_KIND),                          \
+     (KIND) <= (WRITER)->kind                                         \
+     ? 0                                                              \
+     : _PyUnicodeWriter_PrepareKindInternal((WRITER), (KIND)))
+
+/* Don't call this function directly, use the _PyUnicodeWriter_PrepareKind()
+   macro instead. */
+PyAPI_FUNC(int)
+_PyUnicodeWriter_PrepareKindInternal(_PyUnicodeWriter *writer,
+                                     enum PyUnicode_Kind kind);
+
 /* Append a Unicode character.
    Return 0 on success, raise an exception and return -1 on error. */
 PyAPI_FUNC(int)
@@ -1640,13 +1641,13 @@ PyAPI_FUNC(PyObject *) PyUnicode_TranslateCharmap(
     );
 #endif
 
-#ifdef HAVE_MBCS
+#ifdef MS_WINDOWS
 
 /* --- MBCS codecs for Windows -------------------------------------------- */
 
 PyAPI_FUNC(PyObject*) PyUnicode_DecodeMBCS(
     const char *string,         /* MBCS encoded string */
-    Py_ssize_t length,              /* size of string */
+    Py_ssize_t length,          /* size of string */
     const char *errors          /* error handling */
     );
 
@@ -1683,7 +1684,7 @@ PyAPI_FUNC(PyObject*) PyUnicode_EncodeCodePage(
     const char *errors          /* error handling */
     );
 
-#endif /* HAVE_MBCS */
+#endif /* MS_WINDOWS */
 
 /* --- Decimal Encoder ---------------------------------------------------- */
 
@@ -1938,6 +1939,14 @@ PyAPI_FUNC(PyObject*) PyUnicode_Join(
     PyObject *seq               /* Sequence object */
     );
 
+#ifndef Py_LIMITED_API
+PyAPI_FUNC(PyObject *) _PyUnicode_JoinArray(
+    PyObject *separator,
+    PyObject **items,
+    Py_ssize_t seqlen
+    );
+#endif /* Py_LIMITED_API */
+
 /* Return 1 if substr matches str[start:end] at the given tail end, 0
    otherwise. */
 
@@ -2248,11 +2257,17 @@ PyAPI_FUNC(int) _PyUnicode_CheckConsistency(
     int check_content);
 #endif
 
+#ifndef Py_LIMITED_API
 /* Return an interned Unicode object for an Identifier; may fail if there is no memory.*/
 PyAPI_FUNC(PyObject*) _PyUnicode_FromId(_Py_Identifier*);
 /* Clear all static strings. */
 PyAPI_FUNC(void) _PyUnicode_ClearStaticStrings(void);
 
+/* Fast equality check when the inputs are known to be exact unicode types
+   and where the hash values are equal (i.e. a very probable match) */
+PyAPI_FUNC(int) _PyUnicode_EQ(PyObject *, PyObject *);
+#endif /* !Py_LIMITED_API */
+
 #ifdef __cplusplus
 }
 #endif