summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorVictor Stinner <victor.stinner@haypocalc.com>2010-09-29 10:25:54 +0000
committerVictor Stinner <victor.stinner@haypocalc.com>2010-09-29 10:25:54 +0000
commit137c34c0274954b2cdd1fd5b490c654528ff30f7 (patch)
treeec540a9b6bba9617af8afcb099fd4908a5bac230
parent41a64a53a30f2d81de7b4a05e5e8e9b4089f7ca7 (diff)
downloadcpython-git-137c34c0274954b2cdd1fd5b490c654528ff30f7.tar.gz
Issue #9979: Create function PyUnicode_AsWideCharString().
-rw-r--r--Doc/c-api/unicode.rst13
-rw-r--r--Include/unicodeobject.h19
-rw-r--r--Misc/NEWS2
-rw-r--r--Objects/unicodeobject.c62
4 files changed, 80 insertions, 16 deletions
diff --git a/Doc/c-api/unicode.rst b/Doc/c-api/unicode.rst
index 2e274ad636..50a1254192 100644
--- a/Doc/c-api/unicode.rst
+++ b/Doc/c-api/unicode.rst
@@ -462,6 +462,19 @@ wchar_t support for platforms which support it:
required by the application.
+.. cfunction:: wchar_t* PyUnicode_AsWideCharString(PyUnicodeObject *unicode, Py_ssize_t *size)
+
+ Convert the Unicode object to a wide character string. The output string
+ always ends with a nul character. If *size* is not *NULL*, write the number
+ of wide characters (including the nul character) into *\*size*.
+
+ Returns a buffer allocated by :cfunc:`PyMem_Alloc` (use :cfunc:`PyMem_Free`
+ to free it) on success. On error, returns *NULL*, *\*size* is undefined and
+ raises a :exc:`MemoryError`.
+
+ .. versionadded:: 3.2
+
+
.. _builtincodecs:
Built-in Codecs
diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index 111d7e230e..f206895a10 100644
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -99,8 +99,8 @@ Copyright (c) Corporation for National Research Initiatives.
#endif
/* If the compiler provides a wchar_t type we try to support it
- through the interface functions PyUnicode_FromWideChar() and
- PyUnicode_AsWideChar(). */
+ through the interface functions PyUnicode_FromWideChar(),
+ PyUnicode_AsWideChar() and PyUnicode_AsWideCharString(). */
#ifdef HAVE_USABLE_WCHAR_T
# ifndef HAVE_WCHAR_H
@@ -156,6 +156,7 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
# define PyUnicode_AsUnicode PyUnicodeUCS2_AsUnicode
# define PyUnicode_AsUnicodeEscapeString PyUnicodeUCS2_AsUnicodeEscapeString
# define PyUnicode_AsWideChar PyUnicodeUCS2_AsWideChar
+# define PyUnicode_AsWideCharString PyUnicodeUCS2_AsWideCharString
# define PyUnicode_ClearFreeList PyUnicodeUCS2_ClearFreelist
# define PyUnicode_Compare PyUnicodeUCS2_Compare
# define PyUnicode_CompareWithASCII PyUnicodeUCS2_CompareASCII
@@ -239,6 +240,7 @@ typedef PY_UNICODE_TYPE Py_UNICODE;
# define PyUnicode_AsUnicode PyUnicodeUCS4_AsUnicode
# define PyUnicode_AsUnicodeEscapeString PyUnicodeUCS4_AsUnicodeEscapeString
# define PyUnicode_AsWideChar PyUnicodeUCS4_AsWideChar
+# define PyUnicode_AsWideCharString PyUnicodeUCS4_AsWideCharString
# define PyUnicode_ClearFreeList PyUnicodeUCS4_ClearFreelist
# define PyUnicode_Compare PyUnicodeUCS4_Compare
# define PyUnicode_CompareWithASCII PyUnicodeUCS4_CompareWithASCII
@@ -570,6 +572,19 @@ PyAPI_FUNC(Py_ssize_t) PyUnicode_AsWideChar(
Py_ssize_t size /* size of buffer */
);
+/* Convert the Unicode object to a wide character string. The output string
+ always ends with a nul character. If size is not NULL, write the number of
+ wide characters (including the nul character) into *size.
+
+ Returns a buffer allocated by PyMem_Alloc() (use PyMem_Free() to free it)
+ on success. On error, returns NULL, *size is undefined and raises a
+ MemoryError. */
+
+PyAPI_FUNC(wchar_t*) PyUnicode_AsWideCharString(
+ PyUnicodeObject *unicode, /* Unicode object */
+ Py_ssize_t *size /* number of characters of the result */
+ );
+
#endif
/* --- Unicode ordinals --------------------------------------------------- */
diff --git a/Misc/NEWS b/Misc/NEWS
index 03ca4a5c60..f774926069 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -10,6 +10,8 @@ What's New in Python 3.2 Alpha 3?
Core and Builtins
-----------------
+- Issue #9979: Create function PyUnicode_AsWideCharString().
+
- Issue #7397: Mention that importlib.import_module() is probably what someone
really wants to be using in __import__'s docstring.
diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 489c98cd83..527e219896 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -1153,9 +1153,26 @@ PyUnicode_FromFormat(const char *format, ...)
return ret;
}
-Py_ssize_t PyUnicode_AsWideChar(PyUnicodeObject *unicode,
- wchar_t *w,
- Py_ssize_t size)
+static void
+unicode_aswidechar(PyUnicodeObject *unicode,
+ wchar_t *w,
+ Py_ssize_t size)
+{
+#if Py_UNICODE_SIZE == SIZEOF_WCHAR_T
+ memcpy(w, unicode->str, size * sizeof(wchar_t));
+#else
+ register Py_UNICODE *u;
+ register Py_ssize_t i;
+ u = PyUnicode_AS_UNICODE(unicode);
+ for (i = size; i > 0; i--)
+ *w++ = *u++;
+#endif
+}
+
+Py_ssize_t
+PyUnicode_AsWideChar(PyUnicodeObject *unicode,
+ wchar_t *w,
+ Py_ssize_t size)
{
if (unicode == NULL) {
PyErr_BadInternalCall();
@@ -1166,17 +1183,7 @@ Py_ssize_t PyUnicode_AsWideChar(PyUnicodeObject *unicode,
if (size > PyUnicode_GET_SIZE(unicode))
size = PyUnicode_GET_SIZE(unicode) + 1;
-#if Py_UNICODE_SIZE == SIZEOF_WCHAR_T
- memcpy(w, unicode->str, size * sizeof(wchar_t));
-#else
- {
- register Py_UNICODE *u;
- register Py_ssize_t i;
- u = PyUnicode_AS_UNICODE(unicode);
- for (i = size; i > 0; i--)
- *w++ = *u++;
- }
-#endif
+ unicode_aswidechar(unicode, w, size);
if (size > PyUnicode_GET_SIZE(unicode))
return PyUnicode_GET_SIZE(unicode);
@@ -1184,6 +1191,33 @@ Py_ssize_t PyUnicode_AsWideChar(PyUnicodeObject *unicode,
return size;
}
+wchar_t*
+PyUnicode_AsWideCharString(PyUnicodeObject *unicode,
+ Py_ssize_t *size)
+{
+ wchar_t* buffer;
+ Py_ssize_t buflen;
+
+ if (unicode == NULL) {
+ PyErr_BadInternalCall();
+ return NULL;
+ }
+
+ if ((PY_SSIZE_T_MAX / sizeof(wchar_t) - 1) < PyUnicode_GET_SIZE(unicode)) {
+ PyErr_NoMemory();
+ return NULL;
+ }
+
+ buflen = PyUnicode_GET_SIZE(unicode) + 1; /* copy L'\0' */
+ buffer = PyMem_MALLOC(buflen * sizeof(wchar_t));
+ if (buffer == NULL) {
+ PyErr_NoMemory();
+ return NULL;
+ }
+ unicode_aswidechar(unicode, buffer, buflen);
+ return buffer;
+}
+
#endif
PyObject *PyUnicode_FromOrdinal(int ordinal)