From 8c41b8aac3efb78178fe1eaf52d8d1bbc44941a8 Mon Sep 17 00:00:00 2001
From: Werner Koch <wk@gnupg.org>
Date: Fri, 5 Mar 2021 15:33:40 +0100
Subject: [PATCH] w32: Always use Unicode for console input and output.

* common/init.c (_init_common_subsystems) [W32]: Set the codepage to
UTF-8 for input and putput.  Switch gettext to UTF-8.
* tools/gpgconf.c (main): Display the input and output codepage if
they differ.
* g10/gpg.c (utf8_strings) [W32]: Make sure this is always set.
--

With this patch the former patch to use ReadConsoleW and WriteConsoleW
in ttyio.c are kind of superfluous because the ANSI version of these
functions are also able to read/write UTF-8 directly given the console
code page has been set correctly.  However, this seems to work only
with recent versions of Windows-10.

GnuPG-bug-id: 4365
---
 common/init.c   | 11 +++++++++++
 doc/gpg.texi    | 19 +++++++++++++------
 g10/gpg.c       | 14 ++++++++++++--
 tools/gpgconf.c |  6 +++++-
 4 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/common/init.c b/common/init.c
index ba20cd8d0..7b6b4aea0 100644
--- a/common/init.c
+++ b/common/init.c
@@ -202,6 +202,17 @@ _init_common_subsystems (gpg_err_source_t errsource, int *argcp, char ***argvp)
   parse_std_file_handles (argcp, argvp);
 #endif
 
+#ifdef HAVE_W32_SYSTEM
+  /* We want gettext to always output UTF-8 and we put the console in
+   * utf-8 mode.  */
+  gettext_use_utf8 (1);
+  if (!SetConsoleCP (CP_UTF8) || !SetConsoleOutputCP (CP_UTF8))
+    {
+      log_info ("SetConsoleCP failed: %s\n", w32_strerror (-1));
+      log_info ("Warning: Garbled console data possible\n");
+    }
+#endif
+
   /* Access the standard estreams as early as possible.  If we don't
      do this the original stdio streams may have been closed when
      _es_get_std_stream is first use and in turn it would connect to
diff --git a/doc/gpg.texi b/doc/gpg.texi
index 6b912d674..b93b52cd7 100644
--- a/doc/gpg.texi
+++ b/doc/gpg.texi
@@ -1529,13 +1529,14 @@ not used).
 
 @item --display-charset @var{name}
 @opindex display-charset
-Set the name of the native character set. This is used to convert
-some informational strings like user IDs to the proper UTF-8 encoding.
+Set the name of the native character set. This is used to convert some
+informational strings like user IDs to the proper UTF-8 encoding.
 Note that this has nothing to do with the character set of data to be
-encrypted or signed; GnuPG does not recode user-supplied data. If
-this option is not used, the default character set is determined from
-the current locale. A verbosity level of 3 shows the chosen set.
-Valid values for @var{name} are:
+encrypted or signed; GnuPG does not recode user-supplied data. If this
+option is not used, the default character set is determined from the
+current locale. A verbosity level of 3 shows the chosen set.  This
+option should not be used on Windows.  Valid values for @var{name}
+are:
 
 @table @asis
 
@@ -1571,6 +1572,12 @@ encoded in the character set as specified by
 @option{--display-charset}. These options affect all following
 arguments. Both options may be used multiple times.
 
+This option has no effect on Windows.  There the internal used UTF-8
+encoding is translated for console input and output.  The command line
+arguments are expected as Unicode and translated to UTF-8.  Thus when
+calling this program from another, make sure to use the Unicode
+version of CreateProcess.
+
 @anchor{gpg-option --options}
 @item --options @var{file}
 @opindex options
diff --git a/g10/gpg.c b/g10/gpg.c
index 8e19a89f3..c61f17188 100644
--- a/g10/gpg.c
+++ b/g10/gpg.c
@@ -1007,7 +1007,13 @@ static struct debug_flags_s debug_flags [] =
 
 int g10_errors_seen = 0;
 
-static int utf8_strings = 0;
+static int utf8_strings =
+#ifdef HAVE_W32_SYSTEM
+  1
+#else
+  0
+#endif
+  ;
 static int maybe_setuid = 1;
 static unsigned int opt_set_iobuf_size;
 static unsigned int opt_set_iobuf_size_used;
@@ -3406,7 +3412,11 @@ main (int argc, char **argv)
 	    opt.verify_options&=~VERIFY_SHOW_NOTATIONS;
 	    break;
 	  case oUtf8Strings: utf8_strings = 1; break;
-	  case oNoUtf8Strings: utf8_strings = 0; break;
+	  case oNoUtf8Strings:
+#ifdef HAVE_W32_SYSTEM
+            utf8_strings = 0;
+#endif
+            break;
 	  case oDisableCipherAlgo:
             {
               int algo = string_to_cipher_algo (pargs.r.ret_str);
diff --git a/tools/gpgconf.c b/tools/gpgconf.c
index 13170e452..63c305483 100644
--- a/tools/gpgconf.c
+++ b/tools/gpgconf.c
@@ -945,7 +945,11 @@ main (int argc, char **argv)
 #ifdef HAVE_W32_SYSTEM
       {
         get_outfp (&outfp);
-        es_fprintf (outfp, "Console: CP%u\n", GetConsoleOutputCP ());
+        if (GetConsoleCP () != GetConsoleOutputCP ())
+          es_fprintf (outfp, "Console: CP%u/CP%u\n",
+                      GetConsoleCP (), GetConsoleOutputCP ());
+        else
+          es_fprintf (outfp, "Console: CP%u\n", GetConsoleCP ());
         es_fprintf (outfp, "ANSI: CP%u\n", GetACP ());
         es_fprintf (outfp, "OEM: CP%u\n", GetOEMCP ());
       }