This change implements the following gettext features, as

discussed recently in python-dev:

In _locale module:

- bind_textdomain_codeset() binding

In gettext module:

- bind_textdomain_codeset() function
- lgettext(), lngettext(), ldgettext(), ldngettext(),
  which return translated strings encoded in
  preferred system encoding, if
  bind_textdomain_codeset() was not used.
- Added equivalent functionality in translate()
  function and catalog classes.

Every change was also documented.

Doc/lib/liblocale.tex

@@ -469,15 +469,16 @@ that the \module{_locale} module is not accessible as a shared library.
 The locale module exposes the C library's gettext interface on systems
 that provide this interface.  It consists of the functions
 \function{gettext()}, \function{dgettext()}, \function{dcgettext()},
-\function{textdomain()}, and \function{bindtextdomain()}.  These are
-similar to the same functions in the \refmodule{gettext} module, but use
-the C library's binary format for message catalogs, and the C
-library's search algorithms for locating message catalogs. 
+\function{textdomain()}, \function{bindtextdomain()}, and
+\function{bind_textdomain_codeset()}.  These are similar to the same
+functions in the \refmodule{gettext} module, but use the C library's
+binary format for message catalogs, and the C library's search
+algorithms for locating message catalogs. 
 
 Python applications should normally find no need to invoke these
 functions, and should use \refmodule{gettext} instead.  A known
 exception to this rule are applications that link use additional C
 libraries which internally invoke \cfunction{gettext()} or
-\function{cdgettext()}.  For these applications, it may be necessary to
+\function{dcgettext()}.  For these applications, it may be necessary to
 bind the text domain, so that the libraries can properly locate their
 message catalogs.

Lib/gettext.py

@@ -46,7 +46,7 @@ internationalized, to the local language and cultural habits.
 #   find this format documented anywhere.
 
 
-import copy, os, re, struct, sys
+import locale, copy, os, re, struct, sys
 from errno import ENOENT
 
 
@@ -171,6 +171,7 @@ class NullTranslations:
     def __init__(self, fp=None):
         self._info = {}
         self._charset = None
+        self._output_charset = None
         self._fallback = None
         if fp is not None:
             self._parse(fp)
@@ -189,6 +190,11 @@ class NullTranslations:
             return self._fallback.gettext(message)
         return message
 
+    def lgettext(self, message):
+        if self._fallback:
+            return self._fallback.lgettext(message)
+        return message
+
     def ngettext(self, msgid1, msgid2, n):
         if self._fallback:
             return self._fallback.ngettext(msgid1, msgid2, n)
@@ -197,6 +203,14 @@ class NullTranslations:
         else:
             return msgid2
 
+    def lngettext(self, msgid1, msgid2, n):
+        if self._fallback:
+            return self._fallback.lngettext(msgid1, msgid2, n)
+        if n == 1:
+            return msgid1
+        else:
+            return msgid2
+
     def ugettext(self, message):
         if self._fallback:
             return self._fallback.ugettext(message)
@@ -216,6 +230,12 @@ class NullTranslations:
     def charset(self):
         return self._charset
 
+    def output_charset(self):
+        return self._output_charset
+
+    def set_output_charset(self, charset):
+        self._output_charset = charset
+
     def install(self, unicode=False):
         import __builtin__
         __builtin__.__dict__['_'] = unicode and self.ugettext or self.gettext
@@ -315,14 +335,29 @@ class GNUTranslations(NullTranslations):
                 return self._fallback.gettext(message)
             return message
         # Encode the Unicode tmsg back to an 8-bit string, if possible
-        if self._charset:
+        if self._output_charset:
+            return tmsg.encode(self._output_charset)
+        elif self._charset:
             return tmsg.encode(self._charset)
         return tmsg
 
+    def lgettext(self, message):
+        missing = object()
+        tmsg = self._catalog.get(message, missing)
+        if tmsg is missing:
+            if self._fallback:
+                return self._fallback.lgettext(message)
+            return message
+        if self._output_charset:
+            return tmsg.encode(self._output_charset)
+        return tmsg.encode(locale.getpreferredencoding())
+
     def ngettext(self, msgid1, msgid2, n):
         try:
             tmsg = self._catalog[(msgid1, self.plural(n))]
-            if self._charset:
+            if self._output_charset:
+                return tmsg.encode(self._output_charset)
+            elif self._charset:
                 return tmsg.encode(self._charset)
             return tmsg
         except KeyError:
@@ -333,6 +368,20 @@ class GNUTranslations(NullTranslations):
             else:
                 return msgid2
 
+    def lngettext(self, msgid1, msgid2, n):
+        try:
+            tmsg = self._catalog[(msgid1, self.plural(n))]
+            if self._output_charset:
+                return tmsg.encode(self._output_charset)
+            return tmsg.encode(locale.getpreferredencoding())
+        except KeyError:
+            if self._fallback:
+                return self._fallback.lngettext(msgid1, msgid2, n)
+            if n == 1:
+                return msgid1
+            else:
+                return msgid2
+
     def ugettext(self, message):
         missing = object()
         tmsg = self._catalog.get(message, missing)
@@ -397,7 +446,7 @@ def find(domain, localedir=None, languages=None, all=0):
 _translations = {}
 
 def translation(domain, localedir=None, languages=None,
-                class_=None, fallback=False):
+                class_=None, fallback=False, codeset=None):
     if class_ is None:
         class_ = GNUTranslations
     mofiles = find(domain, localedir, languages, all=1)
@@ -414,9 +463,12 @@ def translation(domain, localedir=None, languages=None,
         t = _translations.get(key)
         if t is None:
             t = _translations.setdefault(key, class_(open(mofile, 'rb')))
-        # Copy the translation object to allow setting fallbacks.
-        # All other instance data is shared with the cached object.
+        # Copy the translation object to allow setting fallbacks and
+        # output charset. All other instance data is shared with the
+        # cached object.
         t = copy.copy(t)
+        if codeset:
+            t.set_output_charset(codeset)
         if result is None:
             result = t
         else:
@@ -424,13 +476,16 @@ def translation(domain, localedir=None, languages=None,
     return result
 
 
-def install(domain, localedir=None, unicode=False):
-    translation(domain, localedir, fallback=True).install(unicode)
+def install(domain, localedir=None, unicode=False, codeset=None):
+    t = translation(domain, localedir, fallback=True, codeset=codeset)
+    t.install(unicode)
 
 
 
 # a mapping b/w domains and locale directories
 _localedirs = {}
+# a mapping b/w domains and codesets
+_localecodesets = {}
 # current global domain, `messages' used for compatibility w/ GNU gettext
 _current_domain = 'messages'
 
@@ -449,17 +504,33 @@ def bindtextdomain(domain, localedir=None):
     return _localedirs.get(domain, _default_localedir)
 
 
+def bind_textdomain_codeset(domain, codeset=None):
+    global _localecodesets
+    if codeset is not None:
+        _localecodesets[domain] = codeset
+    return _localecodesets.get(domain)
+
+
 def dgettext(domain, message):
     try:
-        t = translation(domain, _localedirs.get(domain, None))
+        t = translation(domain, _localedirs.get(domain, None),
+                        codeset=_localecodesets.get(domain))
     except IOError:
         return message
     return t.gettext(message)
 
+def ldgettext(domain, message):
+    try:
+        t = translation(domain, _localedirs.get(domain, None),
+                        codeset=_localecodesets.get(domain))
+    except IOError:
+        return message
+    return t.lgettext(message)
 
 def dngettext(domain, msgid1, msgid2, n):
     try:
-        t = translation(domain, _localedirs.get(domain, None))
+        t = translation(domain, _localedirs.get(domain, None),
+                        codeset=_localecodesets.get(domain))
     except IOError:
         if n == 1:
             return msgid1
@@ -467,14 +538,28 @@ def dngettext(domain, msgid1, msgid2, n):
             return msgid2
     return t.ngettext(msgid1, msgid2, n)
 
+def ldngettext(domain, msgid1, msgid2, n):
+    try:
+        t = translation(domain, _localedirs.get(domain, None),
+                        codeset=_localecodesets.get(domain))
+    except IOError:
+        if n == 1:
+            return msgid1
+        else:
+            return msgid2
+    return t.lngettext(msgid1, msgid2, n)
 
 def gettext(message):
     return dgettext(_current_domain, message)
 
+def lgettext(message):
+    return ldgettext(_current_domain, message)
 
 def ngettext(msgid1, msgid2, n):
     return dngettext(_current_domain, msgid1, msgid2, n)
 
+def lngettext(msgid1, msgid2, n):
+    return ldngettext(_current_domain, msgid1, msgid2, n)
 
 # dcgettext() has been deemed unnecessary and is not implemented.
 

Misc/NEWS

@@ -33,6 +33,8 @@ Core and builtins
   will cause a TypeError to be raised.  This matches the behavior of
   Jython.
 
+- Implemented bind_textdomain_codeset() in locale module.
+
 Extension modules
 -----------------
 
@@ -112,6 +114,12 @@ Library
 - Bug #990307: when keep_empty_values is True, cgi.parse_qsl()
   no longer returns spurious empty fields.
 
+- Implemented bind_textdomain_codeset() in gettext module.
+
+- Introduced in gettext module the l*gettext() family of functions,
+  which return translation strings encoded in the preferred encoding,
+  as informed by locale module's getpreferredencoding().
+
 
 Tools/Demos
 -----------

Modules/_localemodule.c

@@ -649,6 +649,24 @@ PyIntl_bindtextdomain(PyObject* self,PyObject*args)
 	return PyString_FromString(dirname);
 }
 
+#ifdef HAVE_BIND_TEXTDOMAIN_CODESET
+PyDoc_STRVAR(bind_textdomain_codeset__doc__,
+"bind_textdomain_codeset(domain, codeset) -> string\n"
+"Bind the C library's domain to codeset.");
+
+static PyObject*
+PyIntl_bind_textdomain_codeset(PyObject* self,PyObject*args)
+{
+	char *domain,*codeset;
+	if (!PyArg_ParseTuple(args, "sz", &domain, &codeset))
+		return NULL;
+	codeset = bind_textdomain_codeset(domain, codeset);
+	if (codeset)
+		return PyString_FromString(codeset);
+	Py_RETURN_NONE;
+}
+#endif
+
 #endif
 
 static struct PyMethodDef PyLocale_Methods[] = {
@@ -678,6 +696,10 @@ static struct PyMethodDef PyLocale_Methods[] = {
    textdomain__doc__},
   {"bindtextdomain",(PyCFunction)PyIntl_bindtextdomain,METH_VARARGS,
    bindtextdomain__doc__},
+#ifdef HAVE_BIND_TEXTDOMAIN_CODESET
+  {"bind_textdomain_codeset",(PyCFunction)PyIntl_bind_textdomain_codeset,
+   METH_VARARGS, bind_textdomain_codeset__doc__},
+#endif
 #endif  
   {NULL, NULL}
 };

configure.in

@@ -2044,8 +2044,8 @@ fi
 AC_MSG_RESULT(MACHDEP_OBJS)
 
 # checks for library functions
-AC_CHECK_FUNCS(alarm chown clock confstr ctermid execv \
- fork fpathconf ftime ftruncate \
+AC_CHECK_FUNCS(alarm bind_textdomain_codeset chown clock confstr ctermid \
+ execv fork fpathconf ftime ftruncate \
  gai_strerror getgroups getlogin getloadavg getpeername getpgid getpid \
  getpriority getpwent getsid getwd \
  kill killpg lchown lstat mkfifo mknod mktime \

pyconfig.h.in

@@ -37,6 +37,9 @@
 /* Define this if your time.h defines altzone. */
 #undef HAVE_ALTZONE
 
+/* Define to 1 if you have the `bind_textdomain_codeset' function. */
+#undef HAVE_BIND_TEXTDOMAIN_CODESET
+
 /* Define to 1 if you have the <bluetooth/bluetooth.h> header file. */
 #undef HAVE_BLUETOOTH_BLUETOOTH_H