[pypy-commit] pypy unicode-utf8: (fijal, arigo)

[arigo]

Author: Armin Rigo <arigo at tunes.org>
Branch: unicode-utf8
Changeset: r92249:c9a84142d1e3
Date: 2017-08-24 14:50 +0200
http://bitbucket.org/pypy/pypy/changeset/c9a84142d1e3/

Log:	(fijal, arigo)

	Fix the gateway logic: we can now pass 'utf8' to get just a
	utf-8-encoded string

diff --git a/pypy/interpreter/gateway.py b/pypy/interpreter/gateway.py
--- a/pypy/interpreter/gateway.py
+++ b/pypy/interpreter/gateway.py
@@ -160,6 +160,9 @@
     def visit_text0(self, el, app_sig):
         self.checked_space_method(el, app_sig)
 
+    def visit_utf8(self, el, app_sig):
+        self.checked_space_method(el, app_sig)
+
     def visit_fsencode(self, el, app_sig):
         self.checked_space_method(el, app_sig)
 
@@ -244,7 +247,6 @@
     def __init__(self):
         UnwrapSpecEmit.__init__(self)
         self.run_args = []
-        self.extracode = []
 
     def scopenext(self):
         return "scope_w[%d]" % self.succ()
@@ -305,6 +307,9 @@
     def visit_text0(self, typ):
         self.run_args.append("space.text0_w(%s)" % (self.scopenext(),))
 
+    def visit_utf8(self, typ):
+        self.run_args.append("space.utf8_w(%s)" % (self.scopenext(),))
+
     def visit_fsencode(self, typ):
         self.run_args.append("space.fsencode_w(%s)" % (self.scopenext(),))
 
@@ -359,9 +364,8 @@
             d = {}
             source = """if 1:
                 def _run(self, space, scope_w):
-                    %s
                     return self.behavior(%s)
-                \n""" % ("\n".join(self.extracode), ', '.join(self.run_args))
+                \n""" % (', '.join(self.run_args),)
             exec compile2(source) in self.miniglobals, d
 
             activation_cls = type("BuiltinActivation_UwS_%s" % label,
@@ -402,7 +406,6 @@
         UnwrapSpecEmit.__init__(self)
         self.args = []
         self.unwrap = []
-        self.extracode = []
         self.finger = 0
 
     def dispatch(self, el, *args):
@@ -472,6 +475,9 @@
     def visit_text0(self, typ):
         self.unwrap.append("space.text0_w(%s)" % (self.nextarg(),))
 
+    def visit_utf8(self, typ):
+        self.unwrap.append("space.utf8_w(%s)" % (self.nextarg(),))
+
     def visit_fsencode(self, typ):
         self.unwrap.append("space.fsencode_w(%s)" % (self.nextarg(),))
 
@@ -526,10 +532,9 @@
             unwrap_info.miniglobals['func'] = func
             source = """if 1:
                 def fastfunc_%s_%d(%s):
-                    %s
                     return func(%s)
                 \n""" % (func.__name__.replace('-', '_'), narg,
-                         ', '.join(args), '\n'.join(unwrap_info.extracode),
+                         ', '.join(args),
                          ', '.join(unwrap_info.unwrap))
             exec compile2(source) in unwrap_info.miniglobals, d
             fastfunc = d['fastfunc_%s_%d' % (func.__name__.replace('-', '_'), narg)]
diff --git a/pypy/interpreter/test/test_gateway.py b/pypy/interpreter/test/test_gateway.py
--- a/pypy/interpreter/test/test_gateway.py
+++ b/pypy/interpreter/test/test_gateway.py
@@ -538,8 +538,8 @@
     def test_interp2app_unwrap_spec_utf8(self):
         space = self.space
         w = space.wrap
-        def g3_u(space, utf8, utf8len):
-            return space.newtuple([space.wrap(len(utf8)), space.wrap(utf8len)])
+        def g3_u(space, utf8):
+            return space.wrap(utf8)
         app_g3_u = gateway.interp2app_temp(g3_u,
                                          unwrap_spec=[gateway.ObjSpace,
                                                       'utf8'])
@@ -547,14 +547,20 @@
         encoded = u"gęść".encode('utf8')
         assert self.space.eq_w(
             space.call_function(w_app_g3_u, w(u"gęść")),
-            space.newtuple([w(len(encoded)), w(4)]))
+            w(encoded))
         assert self.space.eq_w(
             space.call_function(w_app_g3_u, w("foo")),
-            space.newtuple([w(3), w(3)]))
+            w("foo"))
         raises(gateway.OperationError, space.call_function, w_app_g3_u,
                w(None))
         raises(gateway.OperationError, space.call_function, w_app_g3_u,
                w(42))
+        w_ascii = space.appexec([], """():
+            import sys
+            return sys.getdefaultencoding() == 'ascii'""")
+        if space.is_true(w_ascii):
+            raises(gateway.OperationError, space.call_function, w_app_g3_u,
+                   w("\x80"))
 
     def test_interp2app_unwrap_spec_unwrapper(self):
         space = self.space
diff --git a/pypy/module/_codecs/interp_codecs.py b/pypy/module/_codecs/interp_codecs.py
--- a/pypy/module/_codecs/interp_codecs.py
+++ b/pypy/module/_codecs/interp_codecs.py
@@ -374,10 +374,10 @@
 
 def make_encoder_wrapper(name):
     rname = "utf8_encode_%s" % (name.replace("_encode", ""), )
-    XXX
     @unwrap_spec(utf8='utf8', errors='text_or_none')
     def wrap_encoder(space, utf8, utf8len, errors="strict"):
         from pypy.interpreter import unicodehelper
+        XXX
 
         if errors is None:
             errors = 'strict'
diff --git a/pypy/objspace/std/unicodeobject.py b/pypy/objspace/std/unicodeobject.py
--- a/pypy/objspace/std/unicodeobject.py
+++ b/pypy/objspace/std/unicodeobject.py
@@ -831,7 +831,8 @@
             s = space.charbuf_w(w_obj)
             try:
                 rutf8.check_ascii(s)
-            except rutf8.AsciiCheckError as e:
+            except rutf8.CheckError:
+                XXX
                 unicodehelper.decode_error_handler(space)(None,
                     'ascii', "ordinal not in range(128)", s, e.pos, e.pos+1)
                 assert False
@@ -842,7 +843,8 @@
             try:
                 _, lgt = rutf8.str_check_utf8(s, len(s), final=True,
                                               allow_surrogates=True)
-            except rutf8.Utf8CheckError as e:
+            except rutf8.CheckError:
+                XXX
                 eh(None, 'utf8', e.msg, s, e.startpos, e.endpos)
                 assert False, "has to raise"
             return space.newutf8(s, lgt)