Merge remote-tracking branch 'origin/manifest' into next

[public-inbox.git] / lib / PublicInbox / NNTP.pm

diff --git a/lib/PublicInbox/NNTP.pm b/lib/PublicInbox/NNTP.pm
index 8cb6c56de82ba765a1fa2474408fb3002de16fb8..8a31b910be76a317df6838879a5918a32d0c46b2 100644 (file)
--- a/lib/PublicInbox/NNTP.pm
+++ b/lib/PublicInbox/NNTP.pm
@@ -121,7 +121,7 @@ sub args_ok ($$) {
 # returns 1 if we can continue, 0 if not due to buffered writes or disconnect
 sub process_line ($$) {
        my ($self, $l) = @_;
-       my ($req, @args) = split(/\s+/, $l);
+       my ($req, @args) = split(/[ \t]/, $l);
        return 1 unless defined($req); # skip blank line
        $req = lc($req);
        $req = eval {
@@ -434,10 +434,30 @@ sub xref ($$$$) {
 sub set_nntp_headers ($$$$$) {
        my ($self, $hdr, $ng, $n, $mid) = @_;
 
+       # why? leafnode requires a Path: header for some inexplicable
+       # reason.  We'll fake the shortest one possible.
+       $hdr->header_set('Path', 'y');
+
+       # leafnode (and maybe other NNTP clients) have trouble dealing
+       # with v2 messages which have multiple Message-IDs (either due
+       # to our own content-based dedupe or buggy git-send-email versions).
+       my @mids = $hdr->header('Message-ID');
+       if (scalar(@mids) > 1) {
+               my $mid0 = "<$mid>";
+               $hdr->header_set('Message-ID', $mid0);
+               my @alt = $hdr->header('X-Alt-Message-ID');
+               my %seen = map { $_ => 1 } (@alt, $mid0);
+               foreach my $m (@mids) {
+                       next if $seen{$m}++;
+                       push @alt, $m;
+               }
+               $hdr->header_set('X-Alt-Message-ID', @alt);
+       }
+
        # clobber some
        my $xref = xref($self, $ng, $n, $mid);
        $hdr->header_set('Xref', $xref);
-       $xref =~ s/:\d+//g;
+       $xref =~ s/:[0-9]+//g;
        $hdr->header_set('Newsgroups', (split(/ /, $xref, 2))[1]);
        header_append($hdr, 'List-Post', "<mailto:$ng->{-primary_address}>");
        if (my $url = $ng->base_url) {
@@ -453,7 +473,7 @@ sub art_lookup ($$$) {
        my ($n, $mid);
        my $err;
        if (defined $art) {
-               if ($art =~ /\A\d+\z/o) {
+               if ($art =~ /\A[0-9]+\z/) {
                        $err = '423 no such article number in this group';
                        $n = int($art);
                        goto find_mid;
@@ -508,13 +528,20 @@ sub simple_body_write ($$) {
 
 sub set_art {
        my ($self, $art) = @_;
-       $self->{article} = $art if defined $art && $art =~ /\A\d+\z/;
+       $self->{article} = $art if defined $art && $art =~ /\A[0-9]+\z/;
 }
 
 sub _header ($) {
        my $hdr = $_[0]->header_obj->as_string;
        utf8::encode($hdr);
        $hdr =~ s/(?<!\r)\n/\r\n/sg;
+
+       # for leafnode compatibility, we need to ensure Message-ID headers
+       # are only a single line.  We can't subclass Email::Simple::Header
+       # and override _default_fold_at in here, either; since that won't
+       # affect messages already in the archive.
+       $hdr =~ s/^(Message-ID:)[ \t]*\r\n[ \t]+([^\r]+)\r\n/$1 $2\r\n/igsm;
+
        $hdr
 }
 
@@ -576,11 +603,11 @@ sub get_range ($$) {
        defined $range or return '420 No article(s) selected';
        my ($beg, $end);
        my ($min, $max) = $ng->mm->minmax;
-       if ($range =~ /\A(\d+)\z/) {
+       if ($range =~ /\A([0-9]+)\z/) {
                $beg = $end = $1;
-       } elsif ($range =~ /\A(\d+)-\z/) {
+       } elsif ($range =~ /\A([0-9]+)-\z/) {
                ($beg, $end) = ($1, $max);
-       } elsif ($range =~ /\A(\d+)-(\d+)\z/) {
+       } elsif ($range =~ /\A([0-9]+)-([0-9]+)\z/) {
                ($beg, $end) = ($1, $2);
        } else {
                return r501;
@@ -959,7 +986,7 @@ sub event_read {
                $self->{rbuf} .= $$buf;
        }
        my $r = 1;
-       while ($r > 0 && $self->{rbuf} =~ s/\A\s*([^\r\n]*)\r?\n//) {
+       while ($r > 0 && $self->{rbuf} =~ s/\A[ \t\r\n]*([^\r\n]*)\r?\n//) {
                my $line = $1;
                return $self->close if $line =~ /[[:cntrl:]]/s;
                my $t0 = now();