Source code encoding detection modifications for intltool

--=-RC5GE1dAImJ8AxHStwxP
Content-Type: multipart/mixed; boundary="=-s8gFV8N70Sv0P62/EXDY"


--=-s8gFV8N70Sv0P62/EXDY
Content-Type: text/plain; charset=ISO-8859-15
Content-Transfer-Encoding: quoted-printable

Hi, here you have a patch that tries to detect the file encoding used
and then, calls xgettext with that encoding option.

Please, test it and review it I have no idea about perl so my change
it's mainly a cut & paste fix

I will also prepare a gettext >=3D 0.12 check so new intltool releases
will require it to be able to deal with UTF-8 source files.

Some comments. I get the file encoding with the "file" command and thus,
I'm not able to know  the XML and yacc files encoding, so I'm assuming
that XML files are UTF-8 and any other file that it's not UTF-8, ISO* or
XML is ASCII

Comments, ideas?

I will apply this patch to my intltool installation so the status pages
will start to use it.

Cheers.

P.S.: This patch is an evolution from this
http://deaddog.org/~maddog/intltool-update.patch
--=20
Carlos Perell=F3 Mar=EDn
Debian GNU/Linux Sid (PowerPC)
Linux Registered User #121232
mailto:[email protected] || mailto:[email protected]
http://carlos.pemas.net
Valencia - Spain

--=-s8gFV8N70Sv0P62/EXDY
Content-Disposition: attachment; filename=intltool.patch
Content-Transfer-Encoding: quoted-printable
Content-Type: text/plain; name=intltool.patch; charset=ISO-8859-15

? .intltool-update.in.in.swp
Index: intltool-update.in.in
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
RCS file: /cvs/gnome/intltool/intltool-update.in.in,v
retrieving revision 1.85
diff -u -w -r1.85 intltool-update.in.in
--- intltool-update.in.in	25 May 2003 23:06:05 -0000	1.85
+++ intltool-update.in.in	14 Jul 2003 18:26:45 -0000
@@ -55,6 +55,7 @@
 my $conf_file; # remove later
 my %varhash =3D ();
 my %po_files_by_lang =3D ();
+my $encoding =3D "ASCII";
=20
 # Regular expressions to categorize file types.
 # FIXME: Please check if the following is correct
@@ -251,6 +252,38 @@
    return "gettext\/$gettext_type";
 }
=20
+sub determine_code ($)=20
+{
+   my $comments =3D $_;
+   my $code =3D $_;
+   my $filename;
+   my $type;
+   my $gettext_code=3D"ASCII"; # All files are ASCII by default
+
+   if ($comments =3D~ /^[^#]/)
+   {
+       $code =3D~ s/^\[[^\[].*]\s*//;
+       $filename =3D "../$code";
+       $type=3D`file $filename | cut -d ' ' -f 2`;
+       if ($? eq "0")
+       {
+           if (!($type =3D~ /^[^ISO]/) or !($type =3D~ /^[^UTF]/))
+           {
+               $gettext_code=3D$type;
+	       chomp $gettext_code;
+	   }
+	   elsif (!($type =3D~ /^[^XML]/))
+	   {
+	       $gettext_code=3D"UTF-8"; # We asume that .glade and other .xml fil=
es are UTF-8
+	   }
+       }
+
+   }
+  =20
+   return $gettext_code;
+}
+
+
 sub find_leftout_files
 {
     my (@buf_i18n_plain,
@@ -517,14 +550,31 @@
     while (<INFILE>)=20
     {
         chomp;
+
+	my $gettext_code;
+=09
         if (/\.($xml_extension|$ini_extension)$/ || /^\[/)=20
 	{
             s/^\[.*]\s*//;
 	    print OUTFILE "$_.h\n";
+	    $gettext_code =3D &determine_code ("$_.h");
         }=20
         else=20
         {
             print OUTFILE "$_\n";
+	    $gettext_code =3D &determine_code ("$_");
+        }
+
+	if ($gettext_code ne "" and $encoding ne $gettext_code)
+	{
+	    if ($encoding eq "ASCII")
+	    {
+	        $encoding=3D$gettext_code;
+	    }
+	    elsif ($gettext_code ne "ASCII")
+	    {
+	        print "Warning: You should use the same file encoding for all you=
r project files, but you have $encoding and $gettext_code files ($_).\n";
+	    }
         }
     }
    =20
@@ -534,6 +584,7 @@
     system ("xgettext", "--default-domain\=3D$MODULE",=20
 			"--directory\=3D\.\.",
 	   		"--add-comments",=20
+			"--from-code\=3D$encoding",=20
 			"--keyword\=3D\_",=20
 			"--keyword\=3DN\_",=20
 			"--keyword\=3DU\_",
@@ -675,7 +726,7 @@
 	}
     }
    =20
-    if ($str =3D~ /^(.*)\${?([A-Z]+)}?(.*)$/)
+    if ($str =3D~ /^(.*)\${?([A-Z_]+)}?(.*)$/)
     {
 	my $rest =3D $3;
 	my $untouched =3D $1;

--=-s8gFV8N70Sv0P62/EXDY--

--=-RC5GE1dAImJ8AxHStwxP
Content-Type: application/pgp-signature; name=signature.asc
Content-Description: Esta parte del mensaje =?ISO-8859-1?Q?est=E1?= firmada
	digitalmente

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.2 (GNU/Linux)

iD8DBQA/EvepEuPMamD5V9cRAvshAJ9c8FtO1F7upT55vLfP3obr8vXFJwCfbap8
CSIpAp5Nx1kIxfCR8hfX8nM=
=6kju
-----END PGP SIGNATURE-----

--=-RC5GE1dAImJ8AxHStwxP--