[pypy-commit] pypy py3.5: Correctly initialize data in 4BYTE case of _PyUnicode_Ready(), and fix test to behave the same whether translated or not

[rlamy]

Author: Ronan Lamy <ronan.l...@gmail.com>
Branch: py3.5
Changeset: r92416:ffe904e9ac64
Date: 2017-09-18 19:08 +0100
http://bitbucket.org/pypy/pypy/changeset/ffe904e9ac64/

Log:    Correctly initialize data in 4BYTE case of _PyUnicode_Ready(), and
        fix test to behave the same whether translated or not

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
@@ -199,16 +199,21 @@
              if (!PyArg_ParseTuple(args, "On", &text, &start))
                 return NULL;
              if (PyUnicode_READY(text) == -1) return NULL;
+             if (!PyUnicode_1BYTE_DATA(text)) {
+                // Don't segfault, just fail the test.
+                Py_RETURN_NONE;
+             }
              length = PyUnicode_GET_LENGTH(text);
              if (start > length) return PyLong_FromSsize_t(start);
              return PyUnicode_FromKindAndData(PyUnicode_KIND(text),
                  PyUnicode_1BYTE_DATA(text) + start*PyUnicode_KIND(text),
                  length-start);
              ''')])
-        s = 'a&#1040;b&#1041;c&#1057;d&#1044;'
+        s = u'a&#1040;b&#1041;c&#1057;d&#1044;'
         assert module.slice_start(s, 2) == 'b&#1041;c&#1057;d&#1044;'
-        s = 'xx\N{PILE OF POO}'
-        assert module.slice_start(s, 2) == '\N{PILE OF POO}'
+        # s = u'xx\N{PILE OF POO}'
+        s = u'xx\U0001F4A9'
+        assert module.slice_start(s, 2) == u'\U0001F4A9'
 
     def test_aswidecharstring(self):
         module = self.import_extension('foo', [
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
@@ -300,6 +300,11 @@
         set_utf8_len(py_obj, 0)
     else:
         # XXX: assumes that sizeof(wchar_t) == 4
+        if not get_wbuffer(py_obj):
+            # Copy unicode buffer
+            u = w_obj._value
+            set_wbuffer(py_obj, rffi.unicode2wcharp(u))
+            set_wsize(py_obj, len(u))
         ucs4_data = get_wbuffer(py_obj)
         set_data(py_obj, cts.cast('void*', ucs4_data))
         set_len(py_obj, get_wsize(py_obj))
_______________________________________________
pypy-commit mailing list
pypy-commit@python.org
https://mail.python.org/mailman/listinfo/pypy-commit