- SF #962502: Add two more methods for unicode type; width() and

iswide() for east asian width manipulation. (Inspired by David
Goodger, Reviewed by Martin v. Loewis)
- Move _PyUnicode_TypeRecord.flags to the end of the struct so that
no padding is added for UCS-4 builds. (Suggested by Martin v. Loewis)

1 files changed, 18 insertions, 0 deletions

diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index 1690f8a..345dacf 100644
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -180,6 +180,7 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
 # define PyUnicode_GetDefaultEncoding PyUnicodeUCS2_GetDefaultEncoding
 # define PyUnicode_GetMax PyUnicodeUCS2_GetMax
 # define PyUnicode_GetSize PyUnicodeUCS2_GetSize
+# define PyUnicode_GetWidth PyUnicodeUCS2_GetWidth
 # define PyUnicode_Join PyUnicodeUCS2_Join
 # define PyUnicode_Replace PyUnicodeUCS2_Replace
 # define PyUnicode_Resize PyUnicodeUCS2_Resize
@@ -199,6 +200,7 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
 # define _PyUnicode_IsLinebreak _PyUnicodeUCS2_IsLinebreak
 # define _PyUnicode_IsLowercase _PyUnicodeUCS2_IsLowercase
 # define _PyUnicode_IsNumeric _PyUnicodeUCS2_IsNumeric
+# define _PyUnicode_IsWide _PyUnicodeUCS2_IsWide
 # define _PyUnicode_IsTitlecase _PyUnicodeUCS2_IsTitlecase
 # define _PyUnicode_IsUppercase _PyUnicodeUCS2_IsUppercase
 # define _PyUnicode_IsWhitespace _PyUnicodeUCS2_IsWhitespace
@@ -252,6 +254,7 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
 # define PyUnicode_GetDefaultEncoding PyUnicodeUCS4_GetDefaultEncoding
 # define PyUnicode_GetMax PyUnicodeUCS4_GetMax
 # define PyUnicode_GetSize PyUnicodeUCS4_GetSize
+# define PyUnicode_GetWidth PyUnicodeUCS4_GetWidth
 # define PyUnicode_Join PyUnicodeUCS4_Join
 # define PyUnicode_Replace PyUnicodeUCS4_Replace
 # define PyUnicode_Resize PyUnicodeUCS4_Resize
@@ -270,6 +273,7 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
 # define _PyUnicode_IsLinebreak _PyUnicodeUCS4_IsLinebreak
 # define _PyUnicode_IsLowercase _PyUnicodeUCS4_IsLowercase
 # define _PyUnicode_IsNumeric _PyUnicodeUCS4_IsNumeric
+# define _PyUnicode_IsWide _PyUnicodeUCS4_IsWide
 # define _PyUnicode_IsTitlecase _PyUnicodeUCS4_IsTitlecase
 # define _PyUnicode_IsUppercase _PyUnicodeUCS4_IsUppercase
 # define _PyUnicode_IsWhitespace _PyUnicodeUCS4_IsWhitespace
@@ -315,6 +319,8 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
 
 #define Py_UNICODE_ISALPHA(ch) iswalpha(ch)
 
+#define Py_UNICODE_ISWIDE(ch) _PyUnicode_IsWide(ch)
+
 #else
 
 #define Py_UNICODE_ISSPACE(ch) _PyUnicode_IsWhitespace(ch)
@@ -338,6 +344,8 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
 
 #define Py_UNICODE_ISALPHA(ch) _PyUnicode_IsAlpha(ch)
 
+#define Py_UNICODE_ISWIDE(ch) _PyUnicode_IsWide(ch)
+
 #endif
 
 #define Py_UNICODE_ISALNUM(ch) \
@@ -430,6 +438,12 @@ PyAPI_FUNC(int) PyUnicode_GetSize(
     PyObject *unicode	 	/* Unicode object */
     );
 
+/* Get the fixed-width representation length of the Unicode object */
+
+PyAPI_FUNC(int) PyUnicode_GetWidth(
+    PyObject *unicode	 	/* Unicode object */
+    );
+
 /* Get the maximum ordinal for a Unicode character. */
 PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void);
 
@@ -1151,6 +1165,10 @@ PyAPI_FUNC(int) _PyUnicode_IsAlpha(
     Py_UNICODE ch 	/* Unicode character */
     );
 
+PyAPI_FUNC(int) _PyUnicode_IsWide(
+    Py_UNICODE ch 	/* Unicode character */
+    );
+
 #ifdef __cplusplus
 }
 #endif