[pypy-commit] pypy unicode-utf8: test, fix for compatibility - cpython accepts invalid unicode

[mattip]

Author: Matti Picus <matti.picus at gmail.com>
Branch: unicode-utf8
Changeset: r95567:26a182fd648c
Date: 2019-01-02 11:34 +0200
http://bitbucket.org/pypy/pypy/changeset/26a182fd648c/

Log:	test, fix for compatibility - cpython accepts invalid unicode

diff --git a/pypy/module/array/interp_array.py b/pypy/module/array/interp_array.py
--- a/pypy/module/array/interp_array.py
+++ b/pypy/module/array/interp_array.py
@@ -390,7 +390,8 @@
         if len(s) % self.itemsize != 0:
             raise oefmt(self.space.w_ValueError,
                         "string length not a multiple of item size")
-        self.check_valid_unicode(space, s) # empty for non-u arrays
+        # CPython accepts invalid unicode
+        # self.check_valid_unicode(space, s) # empty for non-u arrays
         oldlen = self.len
         new = len(s) / self.itemsize
         if not new:
diff --git a/pypy/module/array/test/test_array.py b/pypy/module/array/test/test_array.py
--- a/pypy/module/array/test/test_array.py
+++ b/pypy/module/array/test/test_array.py
@@ -589,6 +589,12 @@
             assert a[1] == 2
             assert a[2] == 3
 
+    def test_deepcopy(self):
+        a = self.array('u', u'\x01\u263a\x00\ufeff')
+        from copy import deepcopy
+        b = deepcopy(a)
+        assert a == b
+
     def test_addmul(self):
         a = self.array('i', [1, 2, 3])
         assert repr(a + a) == "array('i', [1, 2, 3, 1, 2, 3])"
@@ -846,12 +852,6 @@
         b.byteswap()
         assert a != b
 
-    def test_unicode_ord_positive(self):
-        import sys
-        if sys.maxunicode == 0xffff:
-            skip("test for 32-bit unicodes")
-        raises(ValueError, self.array, 'u', b'\xff\xff\xff\xff')
-
     def test_weakref(self):
         import weakref
         a = self.array('c', 'Hi!')