Re: [PATCH 2/2] send-email: rfc2047-quote subject lines with non-ascii characters

[Junio C Hamano <gitster@pobox.com>]

Last night I was going through old mail-logs and found this and another
one that this is a follow-up to, which I think are still needed.  Does
anybody see anything wrong with them?

Jeff King <peff@peff.net> writes:

> We always use 'utf-8' as the encoding, since we currently
> have no way of getting the information from the user.
>
> This also refactors the quoting of recipient names, since
> both processes can share the rfc2047 quoting code.
>
> Signed-off-by: Jeff King <peff@peff.net>
> ---
>  git-send-email.perl   |   19 +++++++++++++++++--
>  t/t9001-send-email.sh |   15 +++++++++++++++
>  2 files changed, 32 insertions(+), 2 deletions(-)
>
> diff --git a/git-send-email.perl b/git-send-email.perl
> index 7c4f06c..d0f9d4a 100755
> --- a/git-send-email.perl
> +++ b/git-send-email.perl
> @@ -536,6 +536,14 @@ EOT
>  		if (!$in_body && /^MIME-Version:/i) {
>  			$need_8bit_cte = 0;
>  		}
> +		if (!$in_body && /^Subject: ?(.*)/i) {
> +			my $subject = $1;
> +			$_ = "Subject: " .
> +				($subject =~ /[^[:ascii:]]/ ?
> +				 quote_rfc2047($subject) :
> +				 $subject) .
> +				"\n";
> +		}
>  		print C2 $_;
>  	}
>  	close(C);
> @@ -626,6 +634,14 @@ sub unquote_rfc2047 {
>  	return wantarray ? ($_, $encoding) : $_;
>  }
>  
> +sub quote_rfc2047 {
> +	local $_ = shift;
> +	my $encoding = shift || 'utf-8';
> +	s/([^-a-zA-Z0-9!*+\/])/sprintf("=%02X", ord($1))/eg;
> +	s/(.*)/=\?$encoding\?q\?$1\?=/;
> +	return $_;
> +}
> +
>  # use the simplest quoting being able to handle the recipient
>  sub sanitize_address
>  {
> @@ -643,8 +659,7 @@ sub sanitize_address
>  
>  	# rfc2047 is needed if a non-ascii char is included
>  	if ($recipient_name =~ /[^[:ascii:]]/) {
> -		$recipient_name =~ s/([^-a-zA-Z0-9!*+\/])/sprintf("=%02X", ord($1))/eg;
> -		$recipient_name =~ s/(.*)/=\?utf-8\?q\?$1\?=/;
> +		$recipient_name = quote_rfc2047($recipient_name);
>  	}
>  
>  	# double quotes are needed if specials or CTLs are included
> diff --git a/t/t9001-send-email.sh b/t/t9001-send-email.sh
> index e222c49..a4bcd28 100755
> --- a/t/t9001-send-email.sh
> +++ b/t/t9001-send-email.sh
> @@ -210,4 +210,19 @@ test_expect_success '--compose respects user mime type' '
>  	! grep "^Content-Type: text/plain; charset=utf-8" msgtxt1
>  '
>  
> +test_expect_success '--compose adds MIME for utf8 subject' '
> +	clean_fake_sendmail &&
> +	echo y | \
> +	  GIT_EDITOR=$(pwd)/fake-editor \
> +	  GIT_SEND_EMAIL_NOTTY=1 \
> +	  git send-email \
> +	  --compose --subject utf8-sübjëct \
> +	  --from="Example <nobody@example.com>" \
> +	  --to=nobody@example.com \
> +	  --smtp-server="$(pwd)/fake.sendmail" \
> +	  $patches &&
> +	grep "^fake edit" msgtxt1 &&
> +	grep "^Subject: =?utf-8?q?utf8-s=C3=BCbj=C3=ABct?=" msgtxt1
> +'
> +
>  test_done
> -- 
> 1.5.5.rc1.141.g50ecd.dirty