Merge remote-tracking branch 'origin/manifest' into next

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

diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 0f963dcbd907af3097ed5d0a8462c20acee3a0d9..e468263699bbcdd13af2e8efeb020f743b06907b 100644 (file)
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -28,7 +28,7 @@ use PublicInbox::UserContent;
 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 {
@@ -59,14 +59,14 @@ sub call {
        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;
 
        # avoiding $env->{PATH_INFO} here since that's already decoded
        my ($path_info) = ($env->{REQUEST_URI} =~ path_re($env));
@@ -74,7 +74,8 @@ sub call {
        my $method = $env->{REQUEST_METHOD};
 
        if ($method eq 'POST') {
-               if ($path_info =~ m!$INBOX_RE/(?:(\d+)/)?(git-upload-pack)\z!) {
+               if ($path_info =~ m!$INBOX_RE/(?:(?:git/)?([0-9]+)(?:\.git)?/)?
+                                       (git-upload-pack)\z!x) {
                        my ($part, $path) = ($2, $3);
                        return invalid_inbox($ctx, $1) ||
                                serve_git($ctx, $part, $path);
@@ -87,7 +88,7 @@ sub call {
        }
 
        # top-level indices and feeds
-       if ($path_info eq '/') {
+       if ($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, $1);
@@ -97,11 +98,11 @@ sub call {
                invalid_inbox($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/(?:(?: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!$INBOX_RE/([\w-]+).mbox\.gz\z!o) {
+       } elsif ($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, $3);
@@ -123,11 +124,14 @@ sub call {
                r301($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/');
@@ -149,8 +153,11 @@ sub preload {
        require PublicInbox::MIME;
        require Digest::SHA;
        require POSIX;
-
-       foreach (qw(PublicInbox::Search PublicInbox::SearchView
+       eval {
+               require PublicInbox::Search;
+               PublicInbox::Search::load_xapian();
+       };
+       foreach (qw(PublicInbox::SearchView
                        PublicInbox::Mbox IO::Compress::Gzip
                        PublicInbox::NewsWWW)) {
                eval "require $_;";
@@ -485,6 +492,15 @@ sub www_listing {
        }
 }
 
+# GET $INBOX/manifest.js.gz
+sub get_inbox_manifest ($$$) {
+       my ($ctx, $inbox, $key) = @_;
+       my $r404 = invalid_inbox($ctx, $inbox);
+       return $r404 if $r404;
+       require PublicInbox::WwwListing;
+       PublicInbox::WwwListing::js($ctx->{env}, [$ctx->{-inbox}]);
+}
+
 sub get_attach {
        my ($ctx, $idx, $fn) = @_;
        require PublicInbox::WwwAttach;
@@ -531,11 +547,15 @@ sub stylesheets_prepare ($$) {
                        $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/) {