[pypy-commit] pypy py3.5: Use CPython implemntations for PyUnicode_GetSize, PyUnicode_GetLength

[rlamy]

Author: Ronan Lamy <ronan.l...@gmail.com>
Branch: py3.5
Changeset: r90040:8360e512f159
Date: 2017-02-10 19:41 +0000
http://bitbucket.org/pypy/pypy/changeset/8360e512f159/

Log:    Use CPython implemntations for PyUnicode_GetSize,
        PyUnicode_GetLength

diff --git a/pypy/module/cpyext/api.py b/pypy/module/cpyext/api.py
--- a/pypy/module/cpyext/api.py
+++ b/pypy/module/cpyext/api.py
@@ -563,6 +563,7 @@
     'PyArg_ParseTuple', 'PyArg_UnpackTuple', 'PyArg_ParseTupleAndKeywords',
     'PyArg_VaParse', 'PyArg_VaParseTupleAndKeywords', '_PyArg_NoKeywords',
     'PyUnicode_FromFormat', 'PyUnicode_FromFormatV', 
'PyUnicode_AsWideCharString',
+    'PyUnicode_GetSize', 'PyUnicode_GetLength',
     'PyModule_AddObject', 'PyModule_AddIntConstant', 
'PyModule_AddStringConstant',
     'Py_BuildValue', 'Py_VaBuildValue', 'PyTuple_Pack',
     '_PyArg_Parse_SizeT', '_PyArg_ParseTuple_SizeT',
diff --git a/pypy/module/cpyext/include/unicodeobject.h 
b/pypy/module/cpyext/include/unicodeobject.h
--- a/pypy/module/cpyext/include/unicodeobject.h
+++ b/pypy/module/cpyext/include/unicodeobject.h
@@ -217,6 +217,19 @@
 
 /* === Public API ========================================================= */
 
+/* Get the length of the Unicode object. */
+
+PyAPI_FUNC(Py_ssize_t) PyUnicode_GetLength(
+    PyObject *unicode
+);
+
+/* Get the number of Py_UNICODE units in the
+   string representation. */
+
+PyAPI_FUNC(Py_ssize_t) PyUnicode_GetSize(
+    PyObject *unicode           /* Unicode object */
+    );
+
 PyAPI_FUNC(PyObject *) PyUnicode_FromFormatV(
     const char *format,   /* ASCII-encoded string  */
     va_list vargs
diff --git a/pypy/module/cpyext/src/unicodeobject.c 
b/pypy/module/cpyext/src/unicodeobject.c
--- a/pypy/module/cpyext/src/unicodeobject.c
+++ b/pypy/module/cpyext/src/unicodeobject.c
@@ -551,3 +551,27 @@
     return buffer;
 }
 
+Py_ssize_t
+PyUnicode_GetSize(PyObject *unicode)
+{
+    if (!PyUnicode_Check(unicode)) {
+        PyErr_BadArgument();
+        goto onError;
+    }
+    return PyUnicode_GET_SIZE(unicode);
+
+  onError:
+    return -1;
+}
+
+Py_ssize_t
+PyUnicode_GetLength(PyObject *unicode)
+{
+    if (!PyUnicode_Check(unicode)) {
+        PyErr_BadArgument();
+        return -1;
+    }
+    if (PyUnicode_READY(unicode) == -1)
+        return -1;
+    return PyUnicode_GET_LENGTH(unicode);
+}
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
@@ -68,6 +68,16 @@
         assert module.test_is_unicode(u"")
         assert not module.test_is_unicode(())
 
+    def test_strlen(self):
+        module = self.import_extension('foo', [
+            ('strlen', "METH_O",
+             """
+                PyObject* s = PyObject_Str(args);
+                return PyLong_FromLong(PyUnicode_GetLength(s));
+             """)])
+        print(module.strlen(True))
+        assert module.strlen(True) == 4
+
     def test_unicode_buffer_init(self):
         module = self.import_extension('foo', [
             ("getunicode", "METH_NOARGS",
@@ -213,9 +223,6 @@
 
 class TestUnicode(BaseApiTest):
     def test_unicodeobject(self, space):
-        assert PyUnicode_GetSize(space, space.wrap(u'sp&#228;m')) == 4
-        unichar = rffi.sizeof(Py_UNICODE)
-
         encoding = rffi.charp2str(PyUnicode_GetDefaultEncoding(space, ))
         w_default_encoding = space.call_function(
             space.sys.get('getdefaultencoding')
@@ -627,7 +634,7 @@
 
         assert space.eq_w(w_y, space.wrap(u"abcd"))
 
-        size = PyUnicode_GetSize(space, w_x)
+        size = get_wsize(as_pyobj(space, w_x))
         Py_UNICODE_COPY(space, target_chunk, x_chunk, size)
         w_y = space.wrap(rffi.wcharpsize2unicode(target_chunk, size))
 
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
@@ -273,6 +273,7 @@
             w_obj._value, len(w_obj._value), errors='strict'))
         set_data(py_obj, cts.cast('void*', ucs1_data))
         set_kind(py_obj, _1BYTE_KIND)
+        set_len(py_obj, get_wsize(py_obj))
         if maxchar < 128:
             set_ascii(py_obj, 1)
             set_utf8(py_obj, cts.cast('char*', get_data(py_obj)))
@@ -328,28 +329,6 @@
         set_utf8(ref, rffi.str2charp(s))
     return get_utf8(ref)
 
-@cpython_api([PyObject], Py_ssize_t, error=-1)
-def PyUnicode_GetSize(space, ref):
-    """Return the size of the deprecated Py_UNICODE representation, in code
-    units (this includes surrogate pairs as 2 units).
-
-    Please migrate to using PyUnicode_GetLength().
-    """
-    if from_ref(space, rffi.cast(PyObject, ref.c_ob_type)) is space.w_unicode:
-        return get_wsize(ref)
-    else:
-        w_obj = from_ref(space, ref)
-        return space.len_w(w_obj)
-
-@cpython_api([PyObject], Py_ssize_t, error=-1)
-def PyUnicode_GetLength(space, unicode):
-    """Return the length of the Unicode object, in code points."""
-    # XXX: this is a stub
-    if not PyUnicode_Check(space, unicode):
-        PyErr_BadArgument(space)
-    #PyUnicode_READY(w_unicode)
-    return get_len(unicode)
-
 @cpython_api([PyObject, rffi.CWCHARP, Py_ssize_t], Py_ssize_t, error=-1)
 def PyUnicode_AsWideChar(space, ref, buf, size):
     """Copy the Unicode object contents into the wchar_t buffer w.  At most
_______________________________________________
pypy-commit mailing list
pypy-commit@python.org
https://mail.python.org/mailman/listinfo/pypy-commit