X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWWW.pm;h=534ee0285c8b6c5294b27b71ec605ed25fc5e828;hb=b836c9d3a2053fa97a98cc38e1657d3266173c7e;hp=6e69001c4c4d78fa2e52fc851525c30bfd8f7a59;hpb=6e6f7999361925e4c944f308df4bc32a1842cd69;p=public-inbox.git

diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 6e69001c..534ee028 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2018 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
@@ -11,24 +11,23 @@
 # - Must not rely on static content
 # - UTF-8 is only for user-content, 7-bit US-ASCII for us
 package PublicInbox::WWW;
-use 5.008;
+use 5.010_001;
 use strict;
 use warnings;
 use bytes (); # only for bytes::length
-use Plack::Util;
 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\.\-]*)!;
 our $MID_RE = qr!([^/]+)!;
 our $END_RE = qr!(T/|t/|t\.mbox(?:\.gz)?|t\.atom|raw|)!;
-our $ATTACH_RE = qr!(\d[\.\d]*)-([[:alnum:]][\w\.-]+[[:alnum:]])!i;
+our $ATTACH_RE = qr!([0-9][0-9\.]*)-($PublicInbox::Hval::FN)!;
 our $OID_RE = qr![a-f0-9]{7,40}!;
 
 sub new {
@@ -43,51 +42,40 @@ sub run {
 	PublicInbox::WWW->new->call($req->env);
 }
 
-my %path_re_cache;
-
-sub path_re ($) {
-	my $sn = $_[0]->{SCRIPT_NAME};
-	$path_re_cache{$sn} ||= do {
-		$sn = '/'.$sn unless index($sn, '/') == 0;
-		$sn =~ s!/\z!!;
-		qr!\A(?:https?://[^/]+)?\Q$sn\E(/[^\?\#]+)!;
-	};
-}
-
 sub call {
 	my ($self, $env) = @_;
 	my $ctx = { env => $env, www => $self };
 
 	# we don't care about multi-value
-	my %qp = map {
+	%{$ctx->{qp}} = map {
 		utf8::decode($_);
-		my ($k, $v) = split('=', uri_unescape($_), 2);
-		$v = '' unless defined $v;
-		$v =~ tr/+/ /;
-		($k, $v)
+		tr/+/ /;
+		my ($k, $v) = split('=', $_, 2);
+		$v = uri_unescape($v // '');
+		# none of the keys we care about will need escaping
+		$k => $v;
 	} split(/[&;]+/, $env->{QUERY_STRING});
-	$ctx->{qp} = \%qp;
 
-	# not using $env->{PATH_INFO} here since that's already decoded
-	my ($path_info) = ($env->{REQUEST_URI} =~ path_re($env));
+	my $path_info = path_info_raw($env);
 	my $method = $env->{REQUEST_METHOD};
 
 	if ($method eq 'POST') {
-		if ($path_info =~ m!$INBOX_RE/(?:(\d+)/)?(git-upload-pack)\z!) {
-			my ($part, $path) = ($2, $3);
+		if ($path_info =~ m!$INBOX_RE/(?:(?:git/)?([0-9]+)(?:\.git)?/)?
+					(git-upload-pack)\z!x) {
+			my ($epoch, $path) = ($2, $3);
 			return invalid_inbox($ctx, $1) ||
-				serve_git($ctx, $part, $path);
+				serve_git($ctx, $epoch, $path);
 		} elsif ($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
-	if ($path_info eq '/') {
-		r404();
+	if ($path_info eq '/' || $path_info eq '/manifest.js.gz') {
+		www_listing($self)->call($env);
 	} elsif ($path_info =~ m!$INBOX_RE\z!o) {
 		invalid_inbox($ctx, $1) || r301($ctx, $1);
 	} elsif ($path_info =~ m!$INBOX_RE(?:/|/index\.html)?\z!o) {
@@ -96,11 +84,13 @@ sub call {
 		invalid_inbox($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/(?:(\d+)/)?
+	} 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 ($part, $path) = ($2, $3);
-		invalid_inbox($ctx, $1) || serve_git($ctx, $part, $path);
-	} elsif ($path_info =~ m!$INBOX_RE/([\w-]+).mbox\.gz\z!o) {
+		my ($epoch, $path) = ($2, $3);
+		invalid_inbox($ctx, $1) || serve_git($ctx, $epoch, $path);
+	} elsif ($path_info =~ m!$INBOX_RE/([a-zA-Z0-9_\-]+).mbox\.gz\z!o) {
 		serve_mbox_range($ctx, $1, $2);
 	} elsif ($path_info =~ m!$INBOX_RE/$MID_RE/$END_RE\z!o) {
 		msg_page($ctx, $1, $2, $3);
@@ -122,11 +112,14 @@ sub call {
 		r301($ctx, $1, $2);
 	} elsif ($path_info =~ m!$INBOX_RE/_/text(?:/(.*))?\z!o) {
 		get_text($ctx, $1, $2);
-	} elsif ($path_info =~ m!$INBOX_RE/([\w\-\.]+)\.css\z!o) {
+	} elsif ($path_info =~ m!$INBOX_RE/([a-zA-Z0-9_\-\.]+)\.css\z!o) {
 		get_css($ctx, $1, $2);
+	} elsif ($path_info =~ m!$INBOX_RE/manifest\.js\.gz\z!o) {
+		get_inbox_manifest($ctx, $1, $2);
 	} elsif ($path_info =~ m!$INBOX_RE/($OID_RE)/s/\z!o) {
 		get_vcs_object($ctx, $1, $2);
-	} elsif ($path_info =~ m!$INBOX_RE/($OID_RE)/s/([\w\.\-]+)\z!o) {
+	} elsif ($path_info =~ m!$INBOX_RE/($OID_RE)/s/
+				($PublicInbox::Hval::FN)\z!ox) {
 		get_vcs_object($ctx, $1, $2, $3);
 	} elsif ($path_info =~ m!$INBOX_RE/($OID_RE)/s\z!o) {
 		r301($ctx, $1, $2, 's/');
@@ -142,21 +135,28 @@ sub call {
 # for CoW-friendliness, MOOOOO!
 sub preload {
 	my ($self) = @_;
+	require PublicInbox::ExtMsg;
 	require PublicInbox::Feed;
 	require PublicInbox::View;
 	require PublicInbox::SearchThread;
 	require PublicInbox::MIME;
-	require Digest::SHA;
-	require POSIX;
-
-	foreach (qw(PublicInbox::Search PublicInbox::SearchView
-			PublicInbox::Mbox IO::Compress::Gzip
+	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::MboxGz
 			PublicInbox::NewsWWW)) {
 		eval "require $_;";
 	}
 	if (ref($self)) {
 		$self->cgit;
 		$self->stylesheets_prepare($_) for ('', '../', '../../');
+		$self->www_listing;
 	}
 }
 
@@ -166,15 +166,11 @@ sub r404 {
 	my ($ctx) = @_;
 	if ($ctx && $ctx->{mid}) {
 		require PublicInbox::ExtMsg;
-		searcher($ctx);
 		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 = $ctx->{www};
@@ -237,7 +233,6 @@ sub get_new {
 sub get_index {
 	my ($ctx) = @_;
 	require PublicInbox::Feed;
-	searcher($ctx);
 	if ($ctx->{env}->{QUERY_STRING} =~ /(?:\A|[&;])q=/) {
 		require PublicInbox::SearchView;
 		PublicInbox::SearchView::sres_top_html($ctx);
@@ -257,14 +252,13 @@ sub get_mid_txt {
 sub get_mid_html {
 	my ($ctx) = @_;
 	require PublicInbox::View;
-	searcher($ctx);
 	PublicInbox::View::msg_page($ctx) || r404($ctx);
 }
 
 # /$INBOX/$MESSAGE_ID/t/
 sub get_thread {
 	my ($ctx, $flat) = @_;
-	searcher($ctx) or return need_search($ctx);
+	$ctx->{-inbox}->over or return need($ctx, 'Overview');
 	$ctx->{flat} = $flat;
 	require PublicInbox::View;
 	PublicInbox::View::thread_html($ctx);
@@ -294,28 +288,11 @@ sub get_vcs_object ($$$;$) {
 	PublicInbox::ViewVCS::show($ctx, $oid, $filename);
 }
 
-sub ctx_get {
-	my ($ctx, $key) = @_;
-	my $val = $ctx->{$key};
-	(defined $val && $val ne '') or die "BUG: bad ctx, $key unusable";
-	$val;
-}
-
-# search support is optional, returns undef if Xapian is not installed
-# or not configured for the given GIT_DIR
-sub searcher {
-	my ($ctx) = @_;
-	eval {
-		require PublicInbox::Search;
-		$ctx->{srch} = $ctx->{-inbox}->search;
-	};
-}
-
-sub need_search {
-	my ($ctx) = @_;
+sub need {
+	my ($ctx, $extra) = @_;
 	my $msg = <<EOF;
-<html><head><title>Search not available for this
-public-inbox</title><body><pre>Search is not available for this public-inbox
+<html><head><title>$extra not available for this
+public-inbox</title><body><pre>$extra is not available for this public-inbox
 <a href="../">Return to index</a></pre></body></html>
 EOF
 	[ 501, [ 'Content-Type' => 'text/html; charset=UTF-8' ], [ $msg ] ];
@@ -328,16 +305,16 @@ EOF
 # especially on older systems.  Stick to zlib since that's what git uses.
 sub get_thread_mbox {
 	my ($ctx, $sfx) = @_;
-	my $srch = searcher($ctx) or return need_search($ctx);
+	my $over = $ctx->{-inbox}->over or return need($ctx, 'Overview');
 	require PublicInbox::Mbox;
-	PublicInbox::Mbox::thread_mbox($ctx, $srch, $sfx);
+	PublicInbox::Mbox::thread_mbox($ctx, $over, $sfx);
 }
 
 
 # /$INBOX/$MESSAGE_ID/t.atom		  -> thread as Atom feed
 sub get_thread_atom {
 	my ($ctx) = @_;
-	searcher($ctx) or return need_search($ctx);
+	$ctx->{-inbox}->over or return need($ctx, 'Overview');
 	require PublicInbox::Feed;
 	PublicInbox::Feed::generate_thread_atom($ctx);
 }
@@ -441,17 +418,17 @@ sub msg_page {
 }
 
 sub serve_git {
-	my ($ctx, $part, $path) = @_;
+	my ($ctx, $epoch, $path) = @_;
 	my $env = $ctx->{env};
 	my $ibx = $ctx->{-inbox};
-	my $git = defined $part ? $ibx->git_part($part) : $ibx->git;
+	my $git = defined $epoch ? $ibx->git_epoch($epoch) : $ibx->git;
 	$git ? PublicInbox::GitHTTPBackend::serve($env, $git, $path) : r404();
 }
 
 sub mbox_results {
 	my ($ctx) = @_;
 	if ($ctx->{env}->{QUERY_STRING} =~ /(?:\A|[&;])q=/) {
-		searcher($ctx) or return need_search($ctx);
+		$ctx->{-inbox}->search or return need($ctx, 'search');
 		require PublicInbox::SearchView;
 		return PublicInbox::SearchView::mbox_results($ctx);
 	}
@@ -462,7 +439,6 @@ sub serve_mbox_range {
 	my ($ctx, $inbox, $range) = @_;
 	invalid_inbox($ctx, $inbox) || eval {
 		require PublicInbox::Mbox;
-		searcher($ctx);
 		PublicInbox::Mbox::emit_range($ctx, $range);
 	}
 }
@@ -484,11 +460,29 @@ sub cgit {
 			require PublicInbox::Cgit;
 			PublicInbox::Cgit->new($pi_config);
 		} else {
+			require Plack::Util;
 			Plack::Util::inline_object(call => sub { r404() });
 		}
 	}
 }
 
+sub www_listing {
+	my ($self) = @_;
+	$self->{www_listing} ||= do {
+		require PublicInbox::WwwListing;
+		PublicInbox::WwwListing->new($self);
+	}
+}
+
+# GET $INBOX/manifest.js.gz
+sub get_inbox_manifest ($$$) {
+	my ($ctx, $inbox, $key) = @_;
+	my $r404 = invalid_inbox($ctx, $inbox);
+	return $r404 if $r404;
+	require PublicInbox::WwwListing;
+	PublicInbox::WwwListing::js($ctx->{env}, [$ctx->{-inbox}]);
+}
+
 sub get_attach {
 	my ($ctx, $idx, $fn) = @_;
 	require PublicInbox::WwwAttach;
@@ -535,11 +529,15 @@ sub stylesheets_prepare ($$) {
 			$inline_ok = 0;
 		} else {
 			my $fn = $_;
+			my ($key) = (m!([^/]+?)(?:\.css)?\z!i);
+			if ($key !~ /\A[a-zA-Z0-9_\-\.]+\z/) {
+				warn "ignoring $fn, non-ASCII word character\n";
+				next;
+			}
 			open(my $fh, '<', $fn) or do {
 				warn "failed to open $fn: $!\n";
 				next;
 			};
-			my ($key) = (m!([^/]+?)(?:\.css)?\z!i);
 			my $ctime = 0;
 			my $local = do { local $/; <$fh> };
 			if ($local =~ /\S/) {
@@ -627,4 +625,13 @@ 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;