X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FExtMsg.pm;h=cf9b6d58ba8d3b9836300a28cf96cf2000c1fa8f;hb=8968889e3ebfa09dd2c80fe8b917b83ac13ff356;hp=3e0e6e4e636b068dd36e7dd7897efed466e6b1b0;hpb=793da75fbcb5a2c546b3d582f39761fff3d8292d;p=public-inbox.git diff --git a/lib/PublicInbox/ExtMsg.pm b/lib/PublicInbox/ExtMsg.pm index 3e0e6e4e..cf9b6d58 100644 --- a/lib/PublicInbox/ExtMsg.pm +++ b/lib/PublicInbox/ExtMsg.pm @@ -1,18 +1,24 @@ # Copyright (C) 2015 all contributors # License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt) +# +# Used by the web interface to link to messages outside of the our +# public-inboxes. Mail threads may cross projects/threads; so +# we should ensure users can find more easily find them on other +# sites. package PublicInbox::ExtMsg; use strict; use warnings; use URI::Escape qw(uri_escape_utf8); use PublicInbox::Hval; -use PublicInbox::MID qw/mid_compress mid2path/; +use PublicInbox::MID qw/mid2path/; # TODO: user-configurable our @EXT_URL = ( 'http://mid.gmane.org/%s', 'https://lists.debian.org/msgid-search/%s', - 'http://mid.mail-archive.com/%s', - 'http://marc.info/?i=%s', + # leading "//" denotes protocol-relative (http:// or https://) + '//mid.mail-archive.com/%s', + '//marc.info/?i=%s', ); sub ext_msg { @@ -23,7 +29,7 @@ sub ext_msg { eval { require PublicInbox::Search }; my $have_xap = $@ ? 0 : 1; - my @nox; + my (@nox, @pfx); foreach my $k (keys %$pi_config) { $k =~ /\Apublicinbox\.([A-Z0-9a-z-]+)\.url\z/ or next; @@ -40,8 +46,9 @@ sub ext_msg { # try to find the URL with Xapian to avoid forking if ($have_xap) { + my $s; my $doc_id = eval { - my $s = PublicInbox::Search->new($git_dir); + $s = PublicInbox::Search->new($git_dir); $s->find_unique_doc_id('mid', $mid); }; if ($@) { @@ -53,6 +60,7 @@ sub ext_msg { # no point in trying the fork fallback if we # know Xapian is up-to-date but missing the # message in the current repo + push @pfx, { git_dir => $git_dir, url => $url }; next; } } @@ -65,21 +73,41 @@ sub ext_msg { my $path = "HEAD:" . mid2path($mid); foreach my $n (@nox) { - my @cmd = ('git', "--git-dir=$n->{git_dir}", 'cat-file', - '-t', $path); - my $pid = open my $fh, '-|'; - defined $pid or die "fork failed: $!\n"; - - if ($pid == 0) { - open STDERR, '>', '/dev/null'; # ignore errors - exec @cmd or die "exec failed: $!\n"; - } else { - my $type = eval { local $/; <$fh> }; - close $fh; - if ($? == 0 && $type eq "blob\n") { - return r302($n->{url}, $mid); + # TODO: reuse existing PublicInbox::Git objects to save forks + my $git = PublicInbox::Git->new($n->{git_dir}); + my (undef, $type, undef) = $git->check($path); + return r302($n->{url}, $mid) if ($type && $type eq 'blob'); + } + + # fall back to partial MID matching + my $n_partial = 0; + my @partial; + + eval { require PublicInbox::Msgmap }; + my $have_mm = $@ ? 0 : 1; + my $cgi = $ctx->{cgi}; + my $base_url = $cgi->base->as_string; + if ($have_mm) { + my $tmp_mid = $mid; + my $url; +again: + $url = $base_url . $listname; + unshift @pfx, { git_dir => $ctx->{git_dir}, url => $url }; + foreach my $pfx (@pfx) { + my $git_dir = delete $pfx->{git_dir} or next; + my $mm = eval { PublicInbox::Msgmap->new($git_dir) }; + + $mm or next; + if (my $res = $mm->mid_prefixes($tmp_mid)) { + $n_partial += scalar(@$res); + $pfx->{res} = $res; + push @partial, $pfx; } } + # fixup common errors: + if (!$n_partial && $tmp_mid =~ s,/[tTf],,) { + goto again; + } } my $code = 404; @@ -87,20 +115,37 @@ sub ext_msg { my $href = $h->as_href; my $html = $h->as_html; my $title = "Message-ID <$html> not found"; - - # Fall back to external repos if configured my $s = "$title" . - "
$title";
+		"
$title\n";
 
-	if (@EXT_URL) {
+	if ($n_partial) {
+		$code = 300;
+		my $es = $n_partial == 1 ? '' : 'es';
+		$s.= "\n$n_partial partial match$es found:\n\n";
+		foreach my $pfx (@partial) {
+			my $u = $pfx->{url};
+			foreach my $m (@{$pfx->{res}}) {
+				my $p = PublicInbox::Hval->new_msgid($m);
+				my $r = $p->as_href;
+				my $t = $p->as_html;
+				$s .= qq{$u/$t/\n};
+			}
+		}
+	}
+
+	# Fall back to external repos if configured
+	if (@EXT_URL && index($mid, '@') >= 0) {
 		$code = 300;
-		$s .= "\n\nPerhaps try an external site:\n\n";
+		$s .= "\nPerhaps try an external site:\n\n";
+		my $scheme = $cgi->scheme;
 		foreach my $u (@EXT_URL) {
+			$u = "$scheme:$u" if $u =~ m!\A//!;
 			my $r = sprintf($u, $href);
 			my $t = sprintf($u, $html);
 			$s .= qq{$t\n};
 		}
 	}
+	$s .= '
';
 
 	[300, ['Content-Type'=>'text/html; charset=UTF-8'], [$s]];
 }