[pypy-commit] pypy py3k: hg merge default

[antocuni]

Author: Antonio Cuni <anto.cuni at gmail.com>
Branch: py3k
Changeset: r57051:83a304c73c9a
Date: 2012-08-31 11:20 +0200
http://bitbucket.org/pypy/pypy/changeset/83a304c73c9a/

Log:	hg merge default

diff --git a/pypy/rpython/lltypesystem/rstr.py b/pypy/rpython/lltypesystem/rstr.py
--- a/pypy/rpython/lltypesystem/rstr.py
+++ b/pypy/rpython/lltypesystem/rstr.py
@@ -147,6 +147,7 @@
         from pypy.rpython.annlowlevel import hlstr, llunicode
         from pypy.rlib.runicode import str_decode_utf_8
         value = hlstr(llvalue)
+        assert value is not None
         univalue, _ = str_decode_utf_8(value, len(value), 'strict')
         return llunicode(univalue)
 
@@ -199,6 +200,7 @@
         from pypy.rpython.annlowlevel import hlunicode, llstr
         from pypy.rlib.runicode import unicode_encode_utf_8
         s = hlunicode(ll_s)
+        assert s is not None
         bytes = unicode_encode_utf_8(s, len(s), 'strict')
         return llstr(bytes)
 
diff --git a/pypy/rpython/ootypesystem/rstr.py b/pypy/rpython/ootypesystem/rstr.py
--- a/pypy/rpython/ootypesystem/rstr.py
+++ b/pypy/rpython/ootypesystem/rstr.py
@@ -64,6 +64,7 @@
         from pypy.rpython.annlowlevel import hlstr, oounicode
         from pypy.rlib.runicode import str_decode_utf_8
         value = hlstr(llvalue)
+        assert value is not None
         univalue, _ = str_decode_utf_8(value, len(value), 'strict')
         return oounicode(univalue)
 
@@ -109,6 +110,7 @@
         from pypy.rpython.annlowlevel import hlunicode, oostr
         from pypy.rlib.runicode import unicode_encode_utf_8
         s = hlunicode(ll_s)
+        assert s is not None
         bytes = unicode_encode_utf_8(s, len(s), 'strict')
         return oostr(bytes)
 
diff --git a/pypy/rpython/test/test_runicode.py b/pypy/rpython/test/test_runicode.py
--- a/pypy/rpython/test/test_runicode.py
+++ b/pypy/rpython/test/test_runicode.py
@@ -106,6 +106,20 @@
 
         assert self.ll_to_string(self.interpret(f, [38])) == f(38)
 
+    def test_utf_8_encoding_annotation(self):
+        from pypy.rlib.runicode import unicode_encode_utf_8
+        def f(n):
+            x = u'&#224;&#232;&#236;' + unichr(n)
+            if x:
+                y = u'&#236;&#242;&#233;'
+            else:
+                y = u'&#242;&#236;&#224;&#224;'
+            # the annotation of y is SomeUnicodeString(can_be_None=False)
+            y = unicode_encode_utf_8(y, len(y), 'strict')
+            return x.encode('utf-8') + y
+
+        assert self.ll_to_string(self.interpret(f, [38])) == f(38)
+
     def test_unicode_encode_error(self):
         def f(x, which):
             if which:
@@ -139,6 +153,17 @@
 
         assert self.ll_to_string(self.interpret(f, [0])) == f(0)
 
+    def test_utf_8_decoding_annotation(self):
+        from pypy.rlib.runicode import str_decode_utf_8
+        strings = [u'&#224;&#232;&#236;'.encode('utf-8'), u'&#236;&#242;&#233;&#224;'.encode('utf-8')]
+        def f(n):
+            x = strings[n]
+            # the annotation of y is SomeUnicodeString(can_be_None=False)
+            y, _ = str_decode_utf_8(x, len(x), 'strict')
+            return x.decode('utf-8') + y
+
+        assert self.ll_to_string(self.interpret(f, [1])) == f(1)
+
     def test_unicode_decode_error(self):
         def f(x):
             y = 'xxx'