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/libgettext.tex

@@ -51,6 +51,14 @@ for \var{domain} is returned.\footnote{
         the start of your application.}
 \end{funcdesc}
 
+\begin{funcdesc}{bind_textdomain_codeset}{domain\optional{, codeset}}
+Bind the \var{domain} to \var{codeset}, changing the encoding of
+strings returned by the \function{gettext()} family of functions.
+If \var{codeset} is omitted, then the current binding is returned.
+
+\versionadded{2.4}
+\end{funcdesc}
+
 \begin{funcdesc}{textdomain}{\optional{domain}}
 Change or query the current global domain.  If \var{domain} is
 \code{None}, then the current global domain is returned, otherwise the
@@ -64,11 +72,27 @@ is usually aliased as \function{_} in the local namespace (see
 examples below).
 \end{funcdesc}
 
+\begin{funcdesc}{lgettext}{message}
+Equivalent to \function{gettext()}, but the translation is returned
+in the preferred system encoding, if no other encoding was explicitly
+set with \function{bind_textdomain_codeset()}.
+
+\versionadded{2.4}
+\end{funcdesc}
+
 \begin{funcdesc}{dgettext}{domain, message}
 Like \function{gettext()}, but look the message up in the specified
 \var{domain}.
 \end{funcdesc}
 
+\begin{funcdesc}{ldgettext}{domain, message}
+Equivalent to \function{dgettext()}, but the translation is returned
+in the preferred system encoding, if no other encoding was explicitly
+set with \function{bind_textdomain_codeset()}.
+
+\versionadded{2.4}
+\end{funcdesc}
+
 \begin{funcdesc}{ngettext}{singular, plural, n}
 
 Like \function{gettext()}, but consider plural forms. If a translation
@@ -87,6 +111,14 @@ formulas for a variety of languages.
 
 \end{funcdesc}
 
+\begin{funcdesc}{lngettext}{singular, plural, n}
+Equivalent to \function{ngettext()}, but the translation is returned
+in the preferred system encoding, if no other encoding was explicitly
+set with \function{bind_textdomain_codeset()}.
+
+\versionadded{2.4}
+\end{funcdesc}
+
 \begin{funcdesc}{dngettext}{domain, singular, plural, n}
 Like \function{ngettext()}, but look the message up in the specified
 \var{domain}.
@@ -94,6 +126,15 @@ Like \function{ngettext()}, but look the message up in the specified
 \versionadded{2.3}
 \end{funcdesc}
 
+\begin{funcdesc}{ldngettext}{domain, singular, plural, n}
+Equivalent to \function{dngettext()}, but the translation is returned
+in the preferred system encoding, if no other encoding was explicitly
+set with \function{bind_textdomain_codeset()}.
+
+\versionadded{2.4}
+\end{funcdesc}
+
+
 
 Note that GNU \program{gettext} also defines a \function{dcgettext()}
 method, but this was deemed not useful and so it is currently
@@ -152,8 +193,8 @@ they appear in the languages list or the environment variables.
 \end{funcdesc}
 
 \begin{funcdesc}{translation}{domain\optional{, localedir\optional{,
-                              languages\optional{, 
+                              languages\optional{, class_\optional{,
-                              class_,\optional{fallback}}}}}
+			      fallback\optional{, codeset}}}}}}
 Return a \class{Translations} instance based on the \var{domain},
 \var{localedir}, and \var{languages}, which are first passed to
 \function{find()} to get a list of the
@@ -161,7 +202,8 @@ associated \file{.mo} file paths.  Instances with
 identical \file{.mo} file names are cached.  The actual class instantiated
 is either \var{class_} if provided, otherwise
 \class{GNUTranslations}.  The class's constructor must take a single
-file object argument.  
+file object argument. If provided, \var{codeset} will change the
+charset used to encode translated strings.
 
 If multiple files are found, later files are used as fallbacks for
 earlier ones. To allow setting the fallback, \function{copy.copy}
@@ -172,13 +214,17 @@ If no \file{.mo} file is found, this function raises
 \exception{IOError} if \var{fallback} is false (which is the default),
 and returns a \class{NullTranslations} instance if \var{fallback} is
 true.
+
+\versionchanged[Added the \var{codeset} parameter]{2.4}
 \end{funcdesc}
 
-\begin{funcdesc}{install}{domain\optional{, localedir\optional{, unicode}}}
+\begin{funcdesc}{install}{domain\optional{, localedir\optional{, unicode
+			  \optional{, codeset}}}}
 This installs the function \function{_} in Python's builtin namespace,
-based on \var{domain}, and \var{localedir} which are passed to the
+based on \var{domain}, \var{localedir}, and \var{codeset} which are
-function \function{translation()}.  The \var{unicode} flag is passed to
+passed to the function \function{translation()}.  The \var{unicode}
-the resulting translation object's \method{install} method.
+flag is passed to the resulting translation object's \method{install}
+method.
 
 As seen below, you usually mark the strings in your application that are
 candidates for translation, by wrapping them in a call to the
@@ -191,6 +237,8 @@ print _('This string will be translated.')
 For convenience, you want the \function{_()} function to be installed in
 Python's builtin namespace, so it is easily accessible in all modules
 of your application.  
+
+\versionchanged[Added the \var{codeset} parameter]{2.4}
 \end{funcdesc}
 
 \subsubsection{The \class{NullTranslations} class}
@@ -223,25 +271,39 @@ provide a translation for a given message.
 \end{methoddesc}
 
 \begin{methoddesc}[NullTranslations]{gettext}{message}
-If a fallback has been set, forward \method{gettext} to the fallback.
+If a fallback has been set, forward \method{gettext()} to the fallback.
 Otherwise, return the translated message.  Overridden in derived classes.
 \end{methoddesc}
 
+\begin{methoddesc}[NullTranslations]{lgettext}{message}
+If a fallback has been set, forward \method{lgettext()} to the fallback.
+Otherwise, return the translated message.  Overridden in derived classes.
+
+\versionadded{2.4}
+\end{methoddesc}
+
 \begin{methoddesc}[NullTranslations]{ugettext}{message}
-If a fallback has been set, forward \method{ugettext} to the fallback.
+If a fallback has been set, forward \method{ugettext()} to the fallback.
 Otherwise, return the translated message as a Unicode string.
 Overridden in derived classes.
 \end{methoddesc}
 
 \begin{methoddesc}[NullTranslations]{ngettext}{singular, plural, n}
-If a fallback has been set, forward \method{ngettext} to the fallback.
+If a fallback has been set, forward \method{ngettext()} to the fallback.
 Otherwise, return the translated message.  Overridden in derived classes.
 
 \versionadded{2.3}
 \end{methoddesc}
 
+\begin{methoddesc}[NullTranslations]{lngettext}{singular, plural, n}
+If a fallback has been set, forward \method{ngettext()} to the fallback.
+Otherwise, return the translated message.  Overridden in derived classes.
+
+\versionadded{2.4}
+\end{methoddesc}
+
 \begin{methoddesc}[NullTranslations]{ungettext}{singular, plural, n}
-If a fallback has been set, forward \method{ungettext} to the fallback.
+If a fallback has been set, forward \method{ungettext()} to the fallback.
 Otherwise, return the translated message as a Unicode string.
 Overridden in derived classes.
 
@@ -256,6 +318,20 @@ Return the ``protected'' \member{_info} variable.
 Return the ``protected'' \member{_charset} variable.
 \end{methoddesc}
 
+\begin{methoddesc}[NullTranslations]{output_charset}{}
+Return the ``protected'' \member{_output_charset} variable, which
+defines the encoding used to return translated messages.
+
+\versionadded{2.4}
+\end{methoddesc}
+
+\begin{methoddesc}[NullTranslations]{set_output_charset}{charset}
+Change the ``protected'' \member{_output_charset} variable, which
+defines the encoding used to return translated messages.
+
+\versionadded{2.4}
+\end{methoddesc}
+
 \begin{methoddesc}[NullTranslations]{install}{\optional{unicode}}
 If the \var{unicode} flag is false, this method installs
 \method{self.gettext()} into the built-in namespace, binding it to
@@ -323,6 +399,14 @@ look up is forwarded to the fallback's \method{gettext()} method.
 Otherwise, the \var{message} id is returned.
 \end{methoddesc}
 
+\begin{methoddesc}[GNUTranslations]{lgettext}{message}
+Equivalent to \method{gettext()}, but the translation is returned
+in the preferred system encoding, if no other encoding was explicitly
+set with \method{set_output_charset()}.
+
+\versionadded{2.4}
+\end{methoddesc}
+
 \begin{methoddesc}[GNUTranslations]{ugettext}{message}
 Look up the \var{message} id in the catalog and return the
 corresponding message string, as a Unicode string.  If there is no
@@ -346,6 +430,14 @@ returned, and \var{plural} is returned in all other cases.
 \versionadded{2.3}
 \end{methoddesc}
 
+\begin{methoddesc}[GNUTranslations]{lngettext}{singular, plural, n}
+Equivalent to \method{gettext()}, but the translation is returned
+in the preferred system encoding, if no other encoding was explicitly
+set with \method{set_output_charset()}.
+
+\versionadded{2.4}
+\end{methoddesc}
+
 \begin{methoddesc}[GNUTranslations]{ungettext}{singular, plural, n}
 Do a plural-forms lookup of a message id.  \var{singular} is used as
 the message id for purposes of lookup in the catalog, while \var{n} is
@@ -495,7 +587,7 @@ you would put at the top of your module:
 \begin{verbatim}
 import gettext
 t = gettext.translation('spam', '/usr/share/locale')
-_ = t.gettext
+_ = t.lgettext
 \end{verbatim}
 
 If your translators were providing you with Unicode strings in their
@@ -633,6 +725,21 @@ program to look for translatable strings marked with \function{N_()}.
 \program{pygettext} and \program{xpot} both support this through the
 use of command line switches.
 
+\subsubsection{\function{gettext()} vs. \function{lgettext()}}
+In Python 2.4 the \function{lgettext()} family of functions were
+introduced. The intention of these functions is to provide an
+alternative which is more compliant with the current
+implementation of GNU gettext. Unlike \function{gettext()}, which
+returns strings encoded with the same codeset used in the
+translation file, \function{lgettext()} will return strings
+encoded with the preferred system encoding, as returned by
+\function{locale.getpreferredencoding()}. Also notice that
+Python 2.4 introduces new functions to explicitly choose
+the codeset used in translated strings. If a codeset is explicitly
+set, even \function{lgettext()} will return translated strings in
+the requested codeset, as would be expected in the GNU gettext
+implementation.
+
 \subsection{Acknowledgements}
 
 The following people contributed code, feedback, design suggestions,
@@ -647,4 +754,5 @@ this module:
     \item Martin von L\"owis
     \item Fran\c cois Pinard
     \item Barry Warsaw
+    \item Gustavo Niemeyer
 \end{itemize}

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
+\function{textdomain()}, \function{bindtextdomain()}, and
-similar to the same functions in the \refmodule{gettext} module, but use
+\function{bind_textdomain_codeset()}.  These are similar to the same
-the C library's binary format for message catalogs, and the C
+functions in the \refmodule{gettext} module, but use the C library's
-library's search algorithms for locating message catalogs. 
+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.
+        # Copy the translation object to allow setting fallbacks and
-        # All other instance data is shared with the cached object.
+        # 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):
+def install(domain, localedir=None, unicode=False, codeset=None):
-    translation(domain, localedir, fallback=True).install(unicode)
+    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 \
+AC_CHECK_FUNCS(alarm bind_textdomain_codeset chown clock confstr ctermid \
- fork fpathconf ftime ftruncate \
+ 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