X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWWW.pm;h=275e509f2f1136ad62d129e114b245f9c8b75cd4;hb=5513e163236d8a64411050ae2e1f87aa8d24f023;hp=13b66ee62be8413344435785809e861e82338930;hpb=6348b9adcf8a7d4a455298f45f62338e148d691a;p=public-inbox.git

diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 13b66ee6..275e509f 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2019 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 #
 # Main web interface for mailing list archives
@@ -19,9 +19,9 @@ use PublicInbox::Config;
 use PublicInbox::Hval;
 use URI::Escape qw(uri_unescape);
 use PublicInbox::MID qw(mid_escape);
-require PublicInbox::Git;
 use PublicInbox::GitHTTPBackend;
 use PublicInbox::UserContent;
+use PublicInbox::WwwStatic qw(r path_info_raw);
 
 # TODO: consider a routing tree now that we have more endpoints:
 our $INBOX_RE = qr!\A/([\w\-][\w\.\-]*)!;
@@ -42,19 +42,6 @@ sub run {
 	PublicInbox::WWW->new->call($req->env);
 }
 
-# PATH_INFO is decoded, and we want the undecoded original
-my %path_re_cache;
-sub path_info_raw ($) {
-	my ($env) = @_;
-	my $sn = $env->{SCRIPT_NAME};
-	my $re = $path_re_cache{$sn} ||= do {
-		$sn = '/'.$sn unless index($sn, '/') == 0;
-		$sn =~ s!/\z!!;
-		qr!\A(?:https?://[^/]+)?\Q$sn\E(/[^\?\#]+)!;
-	};
-	$env->{REQUEST_URI} =~ $re ? $1 : $env->{PATH_INFO};
-}
-
 sub call {
 	my ($self, $env) = @_;
 	my $ctx = { env => $env, www => $self };
@@ -78,12 +65,14 @@ sub call {
 			my ($epoch, $path) = ($2, $3);
 			return invalid_inbox($ctx, $1) ||
 				serve_git($ctx, $epoch, $path);
+		} elsif ($path_info =~ m!$INBOX_RE/(\w+)\.sql\.gz\z!o) {
+			return get_altid_dump($ctx, $1, $2);
 		} elsif ($path_info =~ m!$INBOX_RE/!o) {
 			return invalid_inbox($ctx, $1) || mbox_results($ctx);
 		}
 	}
-	elsif ($method !~ /\AGET|HEAD\z/) {
-		return r(405, 'Method Not Allowed');
+	elsif ($method !~ /\A(?:GET|HEAD)\z/) {
+		return r(405);
 	}
 
 	# top-level indices and feeds
@@ -97,6 +86,8 @@ sub call {
 		invalid_inbox($ctx, $1) || get_atom($ctx);
 	} elsif ($path_info =~ m!$INBOX_RE/new\.html\z!o) {
 		invalid_inbox($ctx, $1) || get_new($ctx);
+	} elsif ($path_info =~ m!$INBOX_RE/description\z!o) {
+		get_description($ctx, $1);
 	} elsif ($path_info =~ m!$INBOX_RE/(?:(?:git/)?([0-9]+)(?:\.git)?/)?
 				($PublicInbox::GitHTTPBackend::ANY)\z!ox) {
 		my ($epoch, $path) = ($2, $3);
@@ -134,6 +125,8 @@ sub call {
 		get_vcs_object($ctx, $1, $2, $3);
 	} elsif ($path_info =~ m!$INBOX_RE/($OID_RE)/s\z!o) {
 		r301($ctx, $1, $2, 's/');
+	} elsif ($path_info =~ m!$INBOX_RE/(\w+)\.sql\.gz\z!o) {
+		get_altid_dump($ctx, $1, $2);
 	# convenience redirects order matters
 	} elsif ($path_info =~ m!$INBOX_RE/([^/]{2,})\z!o) {
 		r301($ctx, $1, $2);
@@ -143,31 +136,48 @@ sub call {
 	}
 }
 
-# for CoW-friendliness, MOOOOO!
+# for CoW-friendliness, MOOOOO!  Even for single-process setups,
+# we want to get all immortal allocations done early to avoid heap
+# fragmentation since common allocators favor a large contiguous heap.
 sub preload {
 	my ($self) = @_;
+	require PublicInbox::ExtMsg;
 	require PublicInbox::Feed;
 	require PublicInbox::View;
 	require PublicInbox::SearchThread;
 	require PublicInbox::MIME;
-	require Digest::SHA;
-	require POSIX;
+	require PublicInbox::Mbox;
+	require PublicInbox::ViewVCS;
+	require PublicInbox::WwwText;
+	require PublicInbox::WwwAttach;
 	eval {
 		require PublicInbox::Search;
 		PublicInbox::Search::load_xapian();
 	};
-	foreach (qw(PublicInbox::SearchView
-			PublicInbox::Mbox IO::Compress::Gzip
-			PublicInbox::NewsWWW)) {
-		eval "require $_;";
+	for (qw(SearchView MboxGz WwwAltId)) {
+		eval "require PublicInbox::$_;";
 	}
 	if (ref($self)) {
+		my $pi_config = $self->{pi_config};
+		if (defined($pi_config->{'publicinbox.cgitrc'})) {
+			$pi_config->limiter('-cgit');
+		}
 		$self->cgit;
 		$self->stylesheets_prepare($_) for ('', '../', '../../');
 		$self->www_listing;
+		$self->news_www;
+		$pi_config->each_inbox(\&preload_inbox);
 	}
 }
 
+sub preload_inbox {
+	my $ibx = shift;
+	$ibx->altid_map;
+	$ibx->cloneurl;
+	$ibx->description;
+	$ibx->base_url;
+}
+
 # private functions below
 
 sub r404 {
@@ -176,12 +186,9 @@ sub r404 {
 		require PublicInbox::ExtMsg;
 		return PublicInbox::ExtMsg::ext_msg($ctx);
 	}
-	r(404, 'Not Found');
+	r(404);
 }
 
-# simple response for errors
-sub r { [ $_[0], ['Content-Type' => 'text/plain'], [ join(' ', @_, "\n") ] ] }
-
 sub news_cgit_fallback ($) {
 	my ($ctx) = @_;
 	my $www = $ctx->{www};
@@ -299,6 +306,14 @@ sub get_vcs_object ($$$;$) {
 	PublicInbox::ViewVCS::show($ctx, $oid, $filename);
 }
 
+sub get_altid_dump {
+	my ($ctx, $inbox, $altid_pfx) =@_;
+	my $r404 = invalid_inbox($ctx, $inbox);
+	return $r404 if $r404;
+	eval { require PublicInbox::WwwAltId } or return need($ctx, 'sqlite3');
+	PublicInbox::WwwAltId::sqldump($ctx, $altid_pfx);
+}
+
 sub need {
 	my ($ctx, $extra) = @_;
 	my $msg = <<EOF;
@@ -636,4 +651,13 @@ sub get_css ($$$) {
 	[ 200, $h, [ $css ] ];
 }
 
+sub get_description {
+	my ($ctx, $inbox) = @_;
+	invalid_inbox($ctx, $inbox) || do {
+		my $d = $ctx->{-inbox}->description . "\n";
+		[ 200, [ 'Content-Length', bytes::length($d),
+			'Content-Type', 'text/plain' ], [ $d ] ];
+	};
+}
+
 1;