# HG changeset patch
# Parent  a497e7faa09b9a836983635b96adbf216a39e4f5
Decode hostnames as ASCII/surrogateescape (except
socket.gethostname() on Windows).

diff --git a/Doc/library/os.rst b/Doc/library/os.rst
--- a/Doc/library/os.rst
+++ b/Doc/library/os.rst
@@ -587,12 +587,21 @@ process and user.
    :func:`socket.gethostname`  or even
    ``socket.gethostbyaddr(socket.gethostname())``.
 
+   The strings are converted using the file system encoding and
+   the ``'surrogateescape'`` error handler, except for
+   :attr:`nodename`, which is converted as ASCII with the
+   ``'surrogateescape'`` error handler (see the :mod:`socket`
+   module documentation for details).
+
    Availability: recent flavors of Unix.
 
    .. versionchanged:: 3.3
       Return type changed from a tuple to a tuple-like object
       with named attributes.
 
+   .. versionchanged:: XXX
+      The :attr:`nodename` attribute is now converted as
+      ASCII/``surrogateescape``.
 
 .. function:: unsetenv(key)
 
diff --git a/Doc/library/socket.rst b/Doc/library/socket.rst
--- a/Doc/library/socket.rst
+++ b/Doc/library/socket.rst
@@ -124,6 +124,14 @@ differently into an actual IPv4/v6 addre
 resolution and/or the host configuration.  For deterministic behavior use a
 numeric address in *host* portion.
 
+When a hostname is returned by a system interface (except
+:func:`gethostname` on Windows), it is decoded into a string
+using the ``'ascii'`` codec and the ``'surrogateescape'`` error
+handler; this leaves ASCII bytes as ASCII, including IDNA
+ASCII-compatible encodings (see :mod:`encodings.idna`), but
+converts any non-ASCII bytes to the Unicode lone surrogate codes
+U+DC80...U+DCFF.
+
 All errors raise exceptions.  The normal exceptions for invalid argument types
 and out-of-memory conditions can be raised; starting from Python 3.3, errors
 related to socket or address semantics raise :exc:`OSError` or one of its
diff --git a/Modules/posixmodule.c b/Modules/posixmodule.c
--- a/Modules/posixmodule.c
+++ b/Modules/posixmodule.c
@@ -4464,6 +4464,7 @@ os_uname_impl(PyModuleDef *module)
     struct utsname u;
     int res;
     PyObject *value;
+    PyObject *o;
 
     Py_BEGIN_ALLOW_THREADS
     res = uname(&u);
@@ -4486,7 +4487,13 @@ os_uname_impl(PyModuleDef *module)
     } \
 
     SET(0, u.sysname);
-    SET(1, u.nodename);
+    o = PyUnicode_DecodeASCII(u.nodename, strlen(u.nodename),
+                              "surrogateescape");
+    if (!o) {
+        Py_DECREF(value);
+        return NULL;
+    }
+    PyStructSequence_SET_ITEM(value, 1, o);
     SET(2, u.release);
     SET(3, u.version);
     SET(4, u.machine);
diff --git a/Modules/socketmodule.c b/Modules/socketmodule.c
--- a/Modules/socketmodule.c
+++ b/Modules/socketmodule.c
@@ -895,6 +895,15 @@ static PyThread_type_lock netdb_lock;
 #endif
 
 
+/* Return the string representation for the given hostname. */
+
+static PyObject *
+decode_hostname(const char *name)
+{
+    return PyUnicode_DecodeASCII(name, strlen(name), "surrogateescape");
+}
+
+
 /* Convert a string specifying a host name or one of a few symbolic
    names to a numeric IP address.  This usually calls gethostbyname()
    to do the work; the names "" and "<broadcast>" are special.
@@ -4440,7 +4449,7 @@ socket_gethostname(PyObject *self, PyObj
     if (res < 0)
         return set_error();
     buf[sizeof buf - 1] = '\0';
-    return PyUnicode_DecodeFSDefault(buf);
+    return decode_hostname(buf);
 #endif
 }
 
@@ -4562,7 +4571,7 @@ gethost_common(struct hostent *h, struct
     if (h->h_aliases) {
         for (pch = h->h_aliases; *pch != NULL; pch++) {
             int status;
-            tmp = PyUnicode_FromString(*pch);
+            tmp = decode_hostname(*pch);
             if (tmp == NULL)
                 goto err;
 
@@ -4630,7 +4639,8 @@ gethost_common(struct hostent *h, struct
             goto err;
     }
 
-    rtn_tuple = Py_BuildValue("sOO", h->h_name, name_list, addr_list);
+    rtn_tuple = Py_BuildValue("NOO", decode_hostname(h->h_name),
+                              name_list, addr_list);
 
  err:
     Py_XDECREF(name_list);
@@ -5573,9 +5583,9 @@ socket_getaddrinfo(PyObject *self, PyObj
             makesockaddr(-1, res->ai_addr, res->ai_addrlen, protocol);
         if (addr == NULL)
             goto err;
-        single = Py_BuildValue("iiisO", res->ai_family,
+        single = Py_BuildValue("iiiNO", res->ai_family,
             res->ai_socktype, res->ai_protocol,
-            res->ai_canonname ? res->ai_canonname : "",
+            decode_hostname(res->ai_canonname ? res->ai_canonname : ""),
             addr);
         Py_DECREF(addr);
         if (single == NULL)
@@ -5681,7 +5691,7 @@ socket_getnameinfo(PyObject *self, PyObj
         set_gaierror(error);
         goto fail;
     }
-    ret = Py_BuildValue("ss", hbuf, pbuf);
+    ret = Py_BuildValue("Ns", decode_hostname(hbuf), pbuf);
 
 fail:
     if (res)