git-send-email: add charset header if we add encoded 'From'

We sometimes pick out the original rfc822 'From' header and
include it in the body of the message. If the original
author's name needs encoding, then we should specify that in
the content-type header.

If we already had a content-type header in the mail, then we
may need to re-encode. The logic is there to detect
this case, but it doesn't actually do the re-encoding.

Signed-off-by: Jeff King <peff@peff.net>
Acked-by: Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/git-send-email.perl b/git-send-email.perl
index 8760cf88a5fe52723297eda1b4db54d6e97d50bb..2b1f1b598c62ddaed693635adef12e490f49838f 100755 (executable)
--- a/git-send-email.perl
+++ b/git-send-email.perl
@@ -468,11 +468,13 @@ $time = time - scalar $#files;
 
 sub unquote_rfc2047 {
        local ($_) = @_;
-       if (s/=\?utf-8\?q\?(.*)\?=/$1/g) {
+       my $encoding;
+       if (s/=\?([^?]+)\?q\?(.*)\?=/$2/g) {
+               $encoding = $1;
                s/_/ /g;
                s/=([0-9A-F]{2})/chr(hex($1))/eg;
        }
-       return "$_";
+       return wantarray ? ($_, $encoding) : $_;
 }
 
 # use the simplest quoting being able to handle the recipient
@@ -599,6 +601,9 @@ foreach my $t (@files) {
        open(F,"<",$t) or die "can't open file $t";
 
        my $author = undef;
+       my $author_encoding;
+       my $has_content_type;
+       my $body_encoding;
        @cc = @initial_cc;
        @xh = ();
        my $input_format = undef;
@@ -624,12 +629,20 @@ foreach my $t (@files) {
                                                next if ($suppress_from);
                                        }
                                        elsif ($1 eq 'From') {
-                                               $author = unquote_rfc2047($2);
+                                               ($author, $author_encoding)
+                                                 = unquote_rfc2047($2);
                                        }
                                        printf("(mbox) Adding cc: %s from line '%s'\n",
                                                $2, $_) unless $quiet;
                                        push @cc, $2;
                                }
+                               elsif (/^Content-type:/i) {
+                                       $has_content_type = 1;
+                                       if (/charset="?[^ "]+/) {
+                                               $body_encoding = $1;
+                                       }
+                                       push @xh, $_;
+                               }
                                elsif (!/^Date:\s/ && /^[-A-Za-z]+:\s+\S/) {
                                        push @xh, $_;
                                }
@@ -686,6 +699,21 @@ foreach my $t (@files) {
 
        if (defined $author) {
                $message = "From: $author\n\n$message";
+               if (defined $author_encoding) {
+                       if ($has_content_type) {
+                               if ($body_encoding eq $author_encoding) {
+                                       # ok, we already have the right encoding
+                               }
+                               else {
+                                       # uh oh, we should re-encode
+                               }
+                       }
+                       else {
+                               push @xh,
+                                 'MIME-Version: 1.0',
+                                 "Content-Type: text/plain; charset=$author_encoding";
+                       }
+               }
        }
 
        send_message();