[pypy-commit] pypy default: Implement PyUnicode_EncodeUTF8

[amauryfa]

Author: Amaury Forgeot d'Arc <amauryfa at gmail.com>
Branch: 
Changeset: r48849:6cd69184b2f4
Date: 2011-11-06 20:20 +0100
http://bitbucket.org/pypy/pypy/changeset/6cd69184b2f4/

Log:	Implement PyUnicode_EncodeUTF8

diff --git a/pypy/module/cpyext/stubs.py b/pypy/module/cpyext/stubs.py
--- a/pypy/module/cpyext/stubs.py
+++ b/pypy/module/cpyext/stubs.py
@@ -2281,15 +2281,6 @@
     changes in your code for properly supporting 64-bit systems."""
     raise NotImplementedError
 
- at cpython_api([rffi.CWCHARP, Py_ssize_t, rffi.CCHARP], PyObject)
-def PyUnicode_EncodeUTF8(space, s, size, errors):
-    """Encode the Py_UNICODE buffer of the given size using UTF-8 and return a
-    Python string object.  Return NULL if an exception was raised by the codec.
-
-    This function used an int type for size. This might require
-    changes in your code for properly supporting 64-bit systems."""
-    raise NotImplementedError
-
 @cpython_api([rffi.CCHARP, Py_ssize_t, rffi.CCHARP, rffi.INTP], PyObject)
 def PyUnicode_DecodeUTF32(space, s, size, errors, byteorder):
     """Decode length bytes from a UTF-32 encoded buffer string and return the
diff --git a/pypy/module/cpyext/test/test_unicodeobject.py b/pypy/module/cpyext/test/test_unicodeobject.py
--- a/pypy/module/cpyext/test/test_unicodeobject.py
+++ b/pypy/module/cpyext/test/test_unicodeobject.py
@@ -188,6 +188,12 @@
         assert space.unwrap(w_u) == 'sp'
         rffi.free_charp(u)
 
+    def test_encode_utf8(self, space, api):
+        u = rffi.unicode2wcharp(u'sp&#65533;m')
+        w_s = api.PyUnicode_EncodeUTF8(u, 4, None)
+        assert space.unwrap(w_s) == u'sp&#65533;m'.encode('utf-8')
+        rffi.free_wcharp(u)
+
     def test_IS(self, space, api):
         for char in [0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x1c, 0x1d, 0x1e, 0x1f,
                      0x20, 0x85, 0xa0, 0x1680, 0x2000, 0x2001, 0x2002,
diff --git a/pypy/module/cpyext/unicodeobject.py b/pypy/module/cpyext/unicodeobject.py
--- a/pypy/module/cpyext/unicodeobject.py
+++ b/pypy/module/cpyext/unicodeobject.py
@@ -438,6 +438,16 @@
         w_errors = space.w_None
     return space.call_method(w_str, 'decode', space.wrap("utf-8"), w_errors)
 
+ at cpython_api([CONST_WSTRING, Py_ssize_t, CONST_STRING], PyObject)
+def PyUnicode_EncodeUTF8(space, s, size, errors):
+    """Encode the Py_UNICODE buffer of the given size using UTF-8 and return a
+    Python string object.  Return NULL if an exception was raised by the codec.
+
+    This function used an int type for size. This might require
+    changes in your code for properly supporting 64-bit systems."""
+    w_s = space.wrap(rffi.wcharpsize2unicode(s, size))
+    return space.call_method(w_s, 'encode', space.wrap('utf-8'))
+
 @cpython_api([rffi.CCHARP, Py_ssize_t, rffi.CCHARP, rffi.INTP], PyObject)
 def PyUnicode_DecodeUTF16(space, s, size, llerrors, pbyteorder):
     """Decode length bytes from a UTF-16 encoded buffer string and return the