Author: Amaury Forgeot d'Arc <amaur...@gmail.com>
Branch: cpyext-ext
Changeset: r83057:931af853eaab
Date: 2016-03-14 22:20 +0100
http://bitbucket.org/pypy/pypy/changeset/931af853eaab/
Log: Fix PyString_AsString() to accept a Unicode object, it is encoded
using the default encoding.
Also fix _PyUnicode_AsDefaultEncodedString() to return a referrence
borrowed on the unicode.
diff --git a/pypy/module/cpyext/bytesobject.py
b/pypy/module/cpyext/bytesobject.py
--- a/pypy/module/cpyext/bytesobject.py
+++ b/pypy/module/cpyext/bytesobject.py
@@ -1,4 +1,4 @@
-from pypy.interpreter.error import OperationError
+from pypy.interpreter.error import OperationError, oefmt
from rpython.rtyper.lltypesystem import rffi, lltype
from pypy.module.cpyext.api import (
cpython_api, cpython_struct, bootstrap_function, build_type_checkers,
@@ -171,8 +171,14 @@
if from_ref(space, rffi.cast(PyObject, ref.c_ob_type)) is space.w_str:
pass # typecheck returned "ok" without forcing 'ref' at all
elif not PyString_Check(space, ref): # otherwise, use the alternate way
- raise OperationError(space.w_TypeError, space.wrap(
- "PyString_AsString only support strings"))
+ from pypy.module.cpyext.unicodeobject import (
+ PyUnicode_Check, _PyUnicode_AsDefaultEncodedString)
+ if PyUnicode_Check(space, ref):
+ ref = _PyUnicode_AsDefaultEncodedString(space, ref, None)
+ else:
+ raise oefmt(space.w_TypeError,
+ "expected string or Unicode object, %T found",
+ from_ref(space, ref))
ref_str = rffi.cast(PyStringObject, ref)
if not ref_str.c_buffer:
# copy string buffer
@@ -184,8 +190,14 @@
@cpython_api([PyObject, rffi.CCHARPP, rffi.CArrayPtr(Py_ssize_t)],
rffi.INT_real, error=-1)
def PyString_AsStringAndSize(space, ref, buffer, length):
if not PyString_Check(space, ref):
- raise OperationError(space.w_TypeError, space.wrap(
- "PyString_AsStringAndSize only support strings"))
+ from pypy.module.cpyext.unicodeobject import (
+ PyUnicode_Check, _PyUnicode_AsDefaultEncodedString)
+ if PyUnicode_Check(space, ref):
+ ref = _PyUnicode_AsDefaultEncodedString(space, ref, None)
+ else:
+ raise oefmt(space.w_TypeError,
+ "expected string or Unicode object, %T found",
+ from_ref(space, ref))
ref_str = rffi.cast(PyStringObject, ref)
if not ref_str.c_buffer:
# copy string buffer
diff --git a/pypy/module/cpyext/test/test_bytesobject.py
b/pypy/module/cpyext/test/test_bytesobject.py
--- a/pypy/module/cpyext/test/test_bytesobject.py
+++ b/pypy/module/cpyext/test/test_bytesobject.py
@@ -172,6 +172,44 @@
])
module.getstring()
+ def test_py_string_as_string_Unicode(self):
+ module = self.import_extension('foo', [
+ ("getstring_unicode", "METH_NOARGS",
+ """
+ Py_UNICODE chars[] = {'t', 'e', 's', 't'};
+ PyObject* u1 = PyUnicode_FromUnicode(chars, 4);
+ char *buf;
+ buf = PyString_AsString(u1);
+ if (buf == NULL)
+ return NULL;
+ if (buf[3] != 't') {
+ PyErr_SetString(PyExc_AssertionError, "Bad conversion");
+ return NULL;
+ }
+ Py_DECREF(u1);
+ Py_INCREF(Py_None);
+ return Py_None;
+ """),
+ ("getstringandsize_unicode", "METH_NOARGS",
+ """
+ Py_UNICODE chars[] = {'t', 'e', 's', 't'};
+ PyObject* u1 = PyUnicode_FromUnicode(chars, 4);
+ char *buf;
+ Py_ssize_t len;
+ if (PyString_AsStringAndSize(u1, &buf, &len) < 0)
+ return NULL;
+ if (len != 4) {
+ PyErr_SetString(PyExc_AssertionError, "Bad Length");
+ return NULL;
+ }
+ Py_DECREF(u1);
+ Py_INCREF(Py_None);
+ return Py_None;
+ """),
+ ])
+ module.getstring_unicode()
+ module.getstringandsize_unicode()
+
def test_format_v(self):
module = self.import_extension('foo', [
("test_string_format_v", "METH_VARARGS",
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
@@ -89,6 +89,22 @@
res = module.test_hash(u"xyz")
assert res == hash(u'xyz')
+ def test_default_encoded_string(self):
+ module = self.import_extension('foo', [
+ ("test_default_encoded_string", "METH_O",
+ '''
+ PyObject* result = _PyUnicode_AsDefaultEncodedString(args,
"replace");
+ Py_INCREF(result);
+ return result;
+ '''
+ ),
+ ])
+ res = module.test_default_encoded_string(u"xyz")
+ assert isinstance(res, str)
+ assert res == 'xyz'
+ res = module.test_default_encoded_string(u"caf\xe9")
+ assert isinstance(res, str)
+ assert res == 'caf?'
class TestUnicode(BaseApiTest):
def test_unicodeobject(self, space, api):
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
@@ -375,8 +375,15 @@
return PyUnicode_FromUnicode(space, wchar_p, length)
@cpython_api([PyObject, CONST_STRING], PyObject)
-def _PyUnicode_AsDefaultEncodedString(space, w_unicode, errors):
- return PyUnicode_AsEncodedString(space, w_unicode,
lltype.nullptr(rffi.CCHARP.TO), errors)
+def _PyUnicode_AsDefaultEncodedString(space, ref, errors):
+ # Returns a borrowed reference.
+ py_uni = rffi.cast(PyUnicodeObject, ref)
+ if not py_uni.c_defenc:
+ py_uni.c_defenc = make_ref(
+ space, PyUnicode_AsEncodedString(
+ space, ref,
+ lltype.nullptr(rffi.CCHARP.TO), errors))
+ return py_uni.c_defenc
@cpython_api([CONST_STRING, Py_ssize_t, CONST_STRING, CONST_STRING], PyObject)
def PyUnicode_Decode(space, s, size, encoding, errors):
_______________________________________________
pypy-commit mailing list
pypy-commit@python.org
https://mail.python.org/mailman/listinfo/pypy-commit
