imap+nntp: share COMPRESS implementation

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

diff --git a/lib/PublicInbox/NewsWWW.pm b/lib/PublicInbox/NewsWWW.pm
index 8626cf96eaba44acee92a10a2aa3d84fcb7ab788..d13731ae3f96b77b1996086647e1868b7615211c 100644 (file)
--- a/lib/PublicInbox/NewsWWW.pm
+++ b/lib/PublicInbox/NewsWWW.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2016-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2016-2021 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Plack app redirector for mapping /$NEWSGROUP requests to
@@ -10,11 +10,11 @@ use strict;
 use warnings;
 use PublicInbox::Config;
 use PublicInbox::MID qw(mid_escape);
+use PublicInbox::Hval qw(prurl);
 
 sub new {
-       my ($class, $pi_config) = @_;
-       $pi_config ||= PublicInbox::Config->new;
-       bless { pi_config => $pi_config }, $class;
+       my ($class, $pi_cfg) = @_;
+       bless { pi_cfg => $pi_cfg // PublicInbox::Config->new }, $class;
 }
 
 sub redirect ($$) {
@@ -24,16 +24,19 @@ sub redirect ($$) {
          [ "Redirecting to $url\n" ] ]
 }
 
-sub try_inbox ($$) {
-       my ($ibx, $mid) = @_;
+sub try_inbox {
+       my ($ibx, $arg) = @_;
+       return if scalar(@$arg) > 1;
+
        # do not pass $env since HTTP_HOST may differ
        my $url = $ibx->base_url or return;
 
+       my ($mid) = @$arg;
        eval { $ibx->mm->num_for($mid) } or return;
 
        # 302 since the same message may show up on
        # multiple inboxes and inboxes can be added/reordered
-       redirect(302, $url .= mid_escape($mid) . '/');
+       $arg->[1] = redirect(302, $url .= mid_escape($mid) . '/');
 }
 
 sub call {
@@ -42,12 +45,14 @@ sub call {
        # some links may have the article number in them:
        # /inbox.foo.bar/123456
        my (undef, @parts) = split(m!/!, $env->{PATH_INFO});
+       @parts or return
+               [ 404, [qw(Content-Type text/plain)], ["404 Not Found\n"] ];
        my ($ng, $article) = @parts;
-       my $pi_config = $self->{pi_config};
-       if (my $ibx = $pi_config->lookup_newsgroup($ng)) {
-               my $url = PublicInbox::Hval::prurl($env, $ibx->{url});
+       my $pi_cfg = $self->{pi_cfg};
+       if (my $ibx = $pi_cfg->lookup_newsgroup($ng)) {
+               my $url = prurl($env, $ibx->{url});
                my $code = 301;
-               if (defined $article && $article =~ /\A\d+\z/) {
+               if (defined $article && $article =~ /\A[0-9]+\z/) {
                        my $mid = eval { $ibx->mm->mid_for($article) };
                        if (defined $mid) {
                                # article IDs are not stable across clones,
@@ -59,7 +64,6 @@ sub call {
                return redirect($code, $url);
        }
 
-       my $res;
        my @try = (join('/', @parts));
 
        # trailing slash is in the rest of our WWW, so maybe some users
@@ -68,14 +72,31 @@ sub call {
                pop @parts;
                push @try, join('/', @parts);
        }
-
-       foreach my $mid (@try) {
-               $pi_config->each_inbox(sub {
-                       $res ||= try_inbox($_[0], $mid);
-               });
-               last if defined $res;
+       my $ALL = $pi_cfg->ALL;
+       if (my $over = $ALL ? $ALL->over : undef) {
+               my $by_eidx_key = $pi_cfg->{-by_eidx_key};
+               for my $mid (@try) {
+                       my ($id, $prev);
+                       while (my $x = $over->next_by_mid($mid, \$id, \$prev)) {
+                               my $xr3 = $over->get_xref3($x->{num});
+                               for (@$xr3) {
+                                       s/:[0-9]+:$x->{blob}\z// or next;
+                                       my $ibx = $by_eidx_key->{$_} // next;
+                                       my $url = $ALL->base_url($env) //
+                                                       $ibx->base_url // next;
+                                       $url .= mid_escape($mid) . '/';
+                                       return redirect(302, $url);
+                               }
+                       }
+               }
+       } else { # slow path, scan every inbox
+               for my $mid (@try) {
+                       my $arg = [ $mid ]; # [1] => result
+                       $pi_cfg->each_inbox(\&try_inbox, $arg);
+                       return $arg->[1] if $arg->[1];
+               }
        }
-       $res || [ 404, [qw(Content-Type text/plain)], ["404 Not Found\n"] ];
+       [ 404, [qw(Content-Type text/plain)], ["404 Not Found\n"] ];
 }
 
 1;