X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FExtMsg.pm;h=51e7799de8640929be9538713d3f2ee7e1b1081d;hb=a46893a2b5dabfdbcf7b593ac19967daecfb1772;hp=98da45cc588d5251c260c98ca4814a3ad0b25674;hpb=0bcf715b7ef1e51bf05eeb46b066be8a762e13aa;p=public-inbox.git

diff --git a/lib/PublicInbox/ExtMsg.pm b/lib/PublicInbox/ExtMsg.pm
index 98da45cc..51e7799d 100644
--- a/lib/PublicInbox/ExtMsg.pm
+++ b/lib/PublicInbox/ExtMsg.pm
@@ -1,5 +1,5 @@
-# Copyright (C) 2015 all contributors <meta@public-inbox.org>
-# License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
+# Copyright (C) 2015-2018 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <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
@@ -8,152 +8,192 @@
 package PublicInbox::ExtMsg;
 use strict;
 use warnings;
-use URI::Escape qw(uri_escape_utf8);
 use PublicInbox::Hval;
 use PublicInbox::MID qw/mid2path/;
+use PublicInbox::WwwStream;
 
 # TODO: user-configurable
 our @EXT_URL = (
-	'http://mid.gmane.org/%s',
+	# leading "//" denotes protocol-relative (http:// or https://)
+	'//marc.info/?i=%s',
+	'//www.mail-archive.com/search?l=mid&q=%s',
+	'nntp://news.gmane.org/%s',
 	'https://lists.debian.org/msgid-search/%s',
-	'http://mid.mail-archive.com/%s',
-	'http://marc.info/?i=%s',
+	'//docs.FreeBSD.org/cgi/mid.cgi?db=mid&id=%s',
+	'https://www.w3.org/mid/%s',
+	'http://www.postgresql.org/message-id/%s',
+	'https://lists.debconf.org/cgi-lurker/keyword.cgi?'.
+		'doc-url=/lurker&format=en.html&query=id:%s'
 );
 
-sub ext_msg {
-	my ($ctx) = @_;
-	my $pi_config = $ctx->{pi_config};
-	my $listname = $ctx->{listname};
-	my $mid = $ctx->{mid};
-
-	eval { require PublicInbox::Search };
-	my $have_xap = $@ ? 0 : 1;
-	my (@nox, @pfx);
-
-	foreach my $k (keys %$pi_config) {
-		$k =~ /\Apublicinbox\.([A-Z0-9a-z-]+)\.url\z/ or next;
-		my $list = $1;
-		next if $list eq $listname;
-
-		my $git_dir = $pi_config->{"publicinbox.$list.mainrepo"};
-		defined $git_dir or next;
-
-		my $url = $pi_config->{"publicinbox.$list.url"};
-		defined $url or next;
-
-		$url =~ s!/+\z!!;
-
-		# try to find the URL with Xapian to avoid forking
-		if ($have_xap) {
-			my $s;
-			my $doc_id = eval {
-				$s = PublicInbox::Search->new($git_dir);
-				$s->find_unique_doc_id('mid', $mid);
-			};
-			if ($@) {
-				# xapian not configured for this repo
-			} else {
-				# maybe we found it!
-				return r302($url, $mid) if (defined $doc_id);
-
-				# 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;
-			}
+sub PARTIAL_MAX () { 100 }
+
+sub search_partial ($$) {
+	my ($srch, $mid) = @_;
+	my $opt = { limit => PARTIAL_MAX, mset => 2 };
+	my @try = ("m:$mid*");
+	my $chop = $mid;
+	if ($chop =~ s/(\W+)(\w*)\z//) {
+		my ($delim, $word) = ($1, $2);
+		if (length($word)) {
+			push @try, "m:$chop$delim";
+			push @try, "m:$chop$delim*";
 		}
-
-		# queue up for forking after we've tried Xapian on all of them
-		push @nox, { git_dir => $git_dir, url => $url };
+		push @try, "m:$chop";
+		push @try, "m:$chop*";
 	}
 
-	# Xapian not installed or configured for some repos
-	my $path = "HEAD:" . mid2path($mid);
+	# break out long words individually to search for, because
+	# too many messages begin with "Pine.LNX." (or "alpine" or "nycvar")
+	if ($mid =~ /\w{9,}/) {
+		my @long = ($mid =~ m!(\w{3,})!g);
+		push(@try, join(' ', map { "m:$_" } @long));
+
+		# is the last element long enough to not trigger excessive
+		# wildcard matches?
+		if (length($long[-1]) > 8) {
+			$long[-1] .= '*';
+			push(@try, join(' ', map { "m:$_" } @long));
+		}
+	}
 
-	foreach my $n (@nox) {
-		# 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');
+	foreach my $m (@try) {
+		my $mset = eval { $srch->query($m, $opt) };
+		if (ref($@) eq 'Search::Xapian::QueryParserError') {
+			# If Xapian can't handle the wildcard since it
+			# has too many results.
+			next;
+		}
+		my @mids = map {
+			my $doc = $_->get_document;
+			PublicInbox::SearchMsg->load_doc($doc)->mid;
+		} $mset->items;
+		return \@mids if scalar(@mids);
 	}
+}
 
-	# fall back to partial MID matching
-	my $n_partial = 0;
-	my @partial;
+sub ext_msg {
+	my ($ctx) = @_;
+	my $cur = $ctx->{-inbox};
+	my $mid = $ctx->{mid};
 
 	eval { require PublicInbox::Msgmap };
 	my $have_mm = $@ ? 0 : 1;
-	if ($have_mm) {
-		my $tmp_mid = $mid;
-again:
-		my $cgi = $ctx->{cgi};
-		my $url = ref($cgi) eq 'CGI' ? $cgi->url(-base) . '/'
-				: $cgi->base->as_string; # Plack::Request
-		$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;
-			}
+	my (@ibx, @found);
+
+	$ctx->{www}->{pi_config}->each_inbox(sub {
+		my ($other) = @_;
+		return if $other->{name} eq $cur->{name} || !$other->base_url;
+
+		my $mm = $other->mm or return;
+
+		# try to find the URL with Msgmap to avoid forking
+		my $num = $mm->num_for($mid);
+		if (defined $num) {
+			push @found, $other;
+		} else {
+			# no point in trying the fork fallback if we
+			# know Xapian is up-to-date but missing the
+			# message in the current repo
+			push @ibx, $other;
 		}
-		# fixup common errors:
-		if (!$n_partial && $tmp_mid =~ s,/[tTf],,) {
-			goto again;
+	});
+
+	return exact($ctx, \@found, $mid) if @found;
+
+	# fall back to partial MID matching
+	my @partial;
+	my $n_partial = 0;
+	my $srch = $cur->search;
+	my $mids = search_partial($srch, $mid) if $srch;
+	if ($mids) {
+		$n_partial = scalar(@$mids);
+		push @partial, [ $cur, $mids ];
+	}
+
+	# can't find a partial match in current inbox, try the others:
+	if (!$n_partial && length($mid) >= 16) {
+		foreach my $ibx (@ibx) {
+			$srch = $ibx->search or next;
+			$mids = search_partial($srch, $mid) or next;
+			$n_partial += scalar(@$mids);
+			push @partial, [ $ibx, $mids];
+			last if $n_partial >= PARTIAL_MAX;
 		}
 	}
 
 	my $code = 404;
-	my $h = PublicInbox::Hval->new_msgid($mid, 1);
-	my $href = $h->as_href;
+	my $h = PublicInbox::Hval->new_msgid($mid);
+	my $href = $h->{href};
 	my $html = $h->as_html;
-	my $title = "Message-ID &lt;$html&gt; not found";
-	my $s = "<html><head><title>$title</title>" .
-		"</head><body><pre><b>$title</b>\n";
-
+	my $title = "&lt;$html&gt; not found";
+	my $s = "<pre>Message-ID &lt;$html&gt;\nnot found\n";
 	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}}) {
+		$n_partial .= '+' if ($n_partial == PARTIAL_MAX);
+		$s .= "\n$n_partial partial match$es found:\n\n";
+		my $cur_name = $cur->{name};
+		foreach my $pair (@partial) {
+			my ($ibx, $res) = @$pair;
+			my $env = $ctx->{env} if $ibx->{name} eq $cur_name;
+			my $u = $ibx->base_url($env) or next;
+			foreach my $m (@$res) {
 				my $p = PublicInbox::Hval->new_msgid($m);
-				my $r = $p->as_href;
+				my $r = $p->{href};
 				my $t = $p->as_html;
-				$s .= qq{<a\nhref="$u/$r/">$u/$t/</a>\n};
+				$s .= qq{<a\nhref="$u$r/">$u$t/</a>\n};
 			}
 		}
 	}
+	my $ext = ext_urls($ctx, $mid, $href, $html);
+	if ($ext ne '') {
+		$s .= $ext;
+		$code = 300;
+	}
+	$ctx->{-html_tip} = $s .= '</pre>';
+	$ctx->{-title_html} = $title;
+	$ctx->{-upfx} = '../';
+	PublicInbox::WwwStream->response($ctx, $code);
+}
+
+sub ext_urls {
+	my ($ctx, $mid, $href, $html) = @_;
 
 	# Fall back to external repos if configured
 	if (@EXT_URL && index($mid, '@') >= 0) {
-		$code = 300;
-		$s .= "\nPerhaps try an external site:\n\n";
-		foreach my $u (@EXT_URL) {
+		my $env = $ctx->{env};
+		my $e = "\nPerhaps try an external site:\n\n";
+		foreach my $url (@EXT_URL) {
+			my $u = PublicInbox::Hval::prurl($env, $url);
 			my $r = sprintf($u, $href);
 			my $t = sprintf($u, $html);
-			$s .= qq{<a\nhref="$r">$t</a>\n};
+			$e .= qq{<a\nhref="$r">$t</a>\n};
 		}
+		return $e;
 	}
-	$s .= '</pre></body></html>';
-
-	[300, ['Content-Type'=>'text/html; charset=UTF-8'], [$s]];
+	''
 }
 
-# Redirect to another public-inbox which is mapped by $pi_config
-sub r302 {
-	my ($url, $mid) = @_;
-	$url .= '/' . uri_escape_utf8($mid) . '/';
-	[ 302,
-	  [ 'Location' => $url, 'Content-Type' => 'text/plain' ],
-	  [ "Redirecting to\n$url\n" ] ]
+sub exact {
+	my ($ctx, $found, $mid) = @_;
+	my $h = PublicInbox::Hval->new_msgid($mid);
+	my $href = $h->{href};
+	my $html = $h->as_html;
+	my $title = "&lt;$html&gt; found in ";
+	my $end = @$found == 1 ? 'another inbox' : 'other inboxes';
+	$ctx->{-title_html} = $title . $end;
+	$ctx->{-upfx} = '../';
+	my $ext_urls = ext_urls($ctx, $mid, $href, $html);
+	my $code = (@$found == 1 && $ext_urls eq '') ? 200 : 300;
+	$ctx->{-html_tip} = join('',
+			"<pre>Message-ID: &lt;$html&gt;\nfound in $end:\n\n",
+				(map {
+					my $u = $_->base_url;
+					qq(<a\nhref="$u$href/">$u$html/</a>\n)
+				} @$found),
+			$ext_urls, '</pre>');
+	PublicInbox::WwwStream->response($ctx, $code);
 }
 
 1;