X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWWW.pm;h=508abf73856c3daf08614a9342b91670280cad5f;hb=f76f265a851944b5dedcc3be5f3b5224b6ebda89;hp=eeae3d326b0c5dd4a34dece0401f1e67f4ceca1e;hpb=71040e5ff8a68eb0cfaf20c273e227cdceb9dc23;p=public-inbox.git

diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index eeae3d32..508abf73 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014, Eric Wong <normalperson@yhbt.net> and all contributors
+# Copyright (C) 2014-2015 all contributors <meta@public-inbox.org>
 # License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
 #
 # We focus on the lowest common denominators here:
@@ -16,14 +16,14 @@ use URI::Escape qw(uri_escape_utf8 uri_unescape);
 use constant SSOMA_URL => 'http://ssoma.public-inbox.org/';
 use constant PI_URL => 'http://public-inbox.org/';
 our $LISTNAME_RE = qr!\A/([\w\.\-]+)!;
+our $MID_RE = qr!([^/]+)!;
+our $END_RE = qr!(f/|T/|t/|t\.mbox(?:\.gz)?|t\.atom|raw|)!;
 our $pi_config;
-BEGIN {
-	$pi_config = PublicInbox::Config->new;
-}
 
 sub run {
 	my ($cgi, $method) = @_;
-	my %ctx;
+	$pi_config ||= PublicInbox::Config->new;
+	my $ctx = { cgi => $cgi, pi_config => $pi_config };
 	if ($method !~ /\AGET|HEAD\z/) {
 		return r(405, 'Method Not Allowed');
 	}
@@ -33,43 +33,25 @@ sub run {
 	if ($path_info eq '/') {
 		r404();
 	} elsif ($path_info =~ m!$LISTNAME_RE\z!o) {
-		invalid_list(\%ctx, $1) || redirect_list_index(\%ctx, $cgi);
+		invalid_list($ctx, $1) || r301($ctx, $1);
 	} elsif ($path_info =~ m!$LISTNAME_RE(?:/|/index\.html)?\z!o) {
-		invalid_list(\%ctx, $1) || get_index(\%ctx, $cgi);
-	} elsif ($path_info =~ m!$LISTNAME_RE/atom\.xml\z!o) {
-		invalid_list(\%ctx, $1) || get_atom(\%ctx, $cgi);
-
-	# single-message pages
-	} elsif ($path_info =~ m!$LISTNAME_RE/m/(\S+)\.txt\z!o) {
-		invalid_list_mid(\%ctx, $1, $2) || get_mid_txt(\%ctx, $cgi);
-	} elsif ($path_info =~ m!$LISTNAME_RE/m/(\S+)\.html\z!o) {
-		invalid_list_mid(\%ctx, $1, $2) || get_mid_html(\%ctx, $cgi);
-
-	# full-message page
-	} elsif ($path_info =~ m!$LISTNAME_RE/f/(\S+)\.html\z!o) {
-		invalid_list_mid(\%ctx, $1, $2) || get_full_html(\%ctx, $cgi);
-
-	# thread display
-	} elsif ($path_info =~ m!$LISTNAME_RE/t/(\S+)\.html\z!o) {
-		invalid_list_mid(\%ctx, $1, $2) || get_thread(\%ctx, $cgi);
+		invalid_list($ctx, $1) || get_index($ctx);
+	} elsif ($path_info =~ m!$LISTNAME_RE/(?:atom\.xml|new\.atom)\z!o) {
+		invalid_list($ctx, $1) || get_atom($ctx);
 
-	} elsif ($path_info =~ m!$LISTNAME_RE/t/(\S+)\.mbox(\.gz)?\z!o) {
-		my $sfx = $3;
-		invalid_list_mid(\%ctx, $1, $2) ||
-			get_thread_mbox(\%ctx, $cgi, $sfx);
+	} elsif ($path_info =~ m!$LISTNAME_RE/$MID_RE/$END_RE\z!o) {
+		msg_page($ctx, $1, $2, $3);
 
-	} elsif ($path_info =~ m!$LISTNAME_RE/f/\S+\.txt\z!o) {
-		invalid_list_mid(\%ctx, $1, $2) ||
-			redirect_mid_txt(\%ctx, $cgi);
+	# in case people leave off the trailing slash:
+	} elsif ($path_info =~ m!$LISTNAME_RE/$MID_RE/(f|T|t)\z!o) {
+		r301($ctx, $1, $2, $3 eq 't' ? 't/#u' : $3);
 
-	# convenience redirects, order matters
-	} elsif ($path_info =~ m!$LISTNAME_RE/(m|f|t|s)/(\S+)\z!o) {
-		my $pfx = $2;
-		invalid_list_mid(\%ctx, $1, $3) ||
-			redirect_mid(\%ctx, $cgi, $2);
+	# convenience redirects order matters
+	} elsif ($path_info =~ m!$LISTNAME_RE/([^/]{2,})\z!o) {
+		r301($ctx, $1, $2);
 
 	} else {
-		r404();
+		legacy_redirects($ctx, $path_info);
 	}
 }
 
@@ -85,6 +67,7 @@ sub preload {
 
 	eval {
 		require PublicInbox::Search;
+		require PublicInbox::SearchView;
 		require PublicInbox::Mbox;
 		require IO::Compress::Gzip;
 	};
@@ -92,7 +75,15 @@ sub preload {
 
 # private functions below
 
-sub r404 { r(404, 'Not Found') }
+sub r404 {
+	my ($ctx) = @_;
+	if ($ctx && $ctx->{mid}) {
+		require PublicInbox::ExtMsg;
+		searcher($ctx);
+		return PublicInbox::ExtMsg::ext_msg($ctx);
+	}
+	r(404, 'Not Found');
+}
 
 # simple response for errors
 sub r { [ $_[0], ['Content-Type' => 'text/plain'], [ join(' ', @_, "\n") ] ] }
@@ -113,28 +104,40 @@ sub invalid_list {
 sub invalid_list_mid {
 	my ($ctx, $listname, $mid) = @_;
 	my $ret = invalid_list($ctx, $listname, $mid);
-	$ctx->{mid} = uri_unescape($mid) unless $ret;
-	$ret;
+	return $ret if $ret;
+
+	$ctx->{mid} = $mid = uri_unescape($mid);
+	if ($mid =~ /\A[a-f0-9]{40}\z/) {
+		if ($mid = mid2blob($ctx)) {
+			require Email::Simple;
+			use PublicInbox::MID qw/mid_clean/;
+			$mid = Email::Simple->new($mid);
+			$ctx->{mid} = mid_clean($mid->header('Message-ID'));
+		}
+	}
+	undef;
 }
 
-# /$LISTNAME/atom.xml                       -> Atom feed, includes replies
+# /$LISTNAME/new.atom                     -> Atom feed, includes replies
 sub get_atom {
-	my ($ctx, $cgi) = @_;
-	$ctx->{pi_config} = $pi_config;
-	$ctx->{cgi} = $cgi;
+	my ($ctx) = @_;
 	require PublicInbox::Feed;
 	PublicInbox::Feed::generate($ctx);
 }
 
 # /$LISTNAME/?r=$GIT_COMMIT                 -> HTML only
 sub get_index {
-	my ($ctx, $cgi) = @_;
+	my ($ctx) = @_;
 	require PublicInbox::Feed;
 	my $srch = searcher($ctx);
-	$ctx->{pi_config} = $pi_config;
-	$ctx->{cgi} = $cgi;
+	my $q = $ctx->{cgi}->param('q');
 	footer($ctx);
-	PublicInbox::Feed::generate_html_index($ctx);
+	if (defined $q) {
+		require PublicInbox::SearchView;
+		PublicInbox::SearchView::sres_top_html($ctx, $q);
+	} else {
+		PublicInbox::Feed::generate_html_index($ctx);
+	}
 }
 
 # just returns a string ref for the blob in the current ctx
@@ -144,7 +147,6 @@ sub mid2blob {
 	my $path = PublicInbox::MID::mid2path($ctx->{mid});
 	my @cmd = ('git', "--git-dir=$ctx->{git_dir}",
 			qw(cat-file blob), "HEAD:$path");
-	my $cmd = join(' ', @cmd);
 	my $pid = open my $fh, '-|';
 	defined $pid or die "fork failed: $!\n";
 	if ($pid == 0) {
@@ -157,35 +159,33 @@ sub mid2blob {
 	}
 }
 
-# /$LISTNAME/m/$MESSAGE_ID.txt                    -> raw mbox
+# /$LISTNAME/$MESSAGE_ID/raw                    -> raw mbox
 sub get_mid_txt {
-	my ($ctx, $cgi) = @_;
-	my $x = mid2blob($ctx) or return r404();
+	my ($ctx) = @_;
+	my $x = mid2blob($ctx) or return r404($ctx);
 	require PublicInbox::Mbox;
 	PublicInbox::Mbox::emit1($x);
 }
 
-# /$LISTNAME/m/$MESSAGE_ID.html                   -> HTML content (short quotes)
+# /$LISTNAME/$MESSAGE_ID/                   -> HTML content (short quotes)
 sub get_mid_html {
-	my ($ctx, $cgi) = @_;
-	my $x = mid2blob($ctx);
-	return r404() unless $x;
+	my ($ctx) = @_;
+	my $x = mid2blob($ctx) or return r404($ctx);
 
 	require PublicInbox::View;
-	my $pfx = msg_pfx($ctx);
 	my $foot = footer($ctx);
 	require Email::MIME;
 	my $mime = Email::MIME->new($x);
 	searcher($ctx);
 	[ 200, [ 'Content-Type' => 'text/html; charset=UTF-8' ],
-	  [ PublicInbox::View::msg_html($ctx, $mime, $pfx, $foot) ] ];
+	  [ PublicInbox::View::msg_html($ctx, $mime, 'f/', $foot) ] ];
 }
 
-# /$LISTNAME/f/$MESSAGE_ID.html                   -> HTML content (fullquotes)
+# /$LISTNAME/$MESSAGE_ID/f/                   -> HTML content (fullquotes)
 sub get_full_html {
-	my ($ctx, $cgi) = @_;
-	my $x = mid2blob($ctx);
-	return r404() unless $x;
+	my ($ctx) = @_;
+	my $x = mid2blob($ctx) or return r404($ctx);
+
 	require PublicInbox::View;
 	my $foot = footer($ctx);
 	require Email::MIME;
@@ -195,12 +195,13 @@ sub get_full_html {
 	  [ PublicInbox::View::msg_html($ctx, $mime, undef, $foot)] ];
 }
 
-# /$LISTNAME/t/$MESSAGE_ID.html
+# /$LISTNAME/$MESSAGE_ID/t/
 sub get_thread {
-	my ($ctx, $cgi) = @_;
+	my ($ctx, $flat) = @_;
 	my $srch = searcher($ctx) or return need_search($ctx);
 	require PublicInbox::View;
 	my $foot = footer($ctx);
+	$ctx->{flat} = $flat;
 	PublicInbox::View::thread_html($ctx, $foot, $srch);
 }
 
@@ -209,42 +210,10 @@ sub self_url {
 	ref($cgi) eq 'CGI' ? $cgi->self_url : $cgi->uri->as_string;
 }
 
-sub redirect_list_index {
-	my ($ctx, $cgi) = @_;
-	do_redirect(self_url($cgi) . "/");
-}
-
-sub redirect_mid {
-	my ($ctx, $cgi, $pfx) = @_;
-	my $url = self_url($cgi);
-	my $anchor = '';
-	if (lc($pfx) eq 't') {
-		$anchor = '#u'; # <u id='#u'> is used to highlight in View.pm
-	}
-	do_redirect($url . ".html$anchor");
-}
-
-# only hit when somebody tries to guess URLs manually:
-sub redirect_mid_txt {
-	my ($ctx, $cgi, $pfx) = @_;
-	my $listname = $ctx->{listname};
-	my $url = self_url($cgi);
-	$url =~ s!/$listname/f/(\S+\.txt)\z!/$listname/m/$1!;
-	do_redirect($url);
-}
-
-sub do_redirect {
-	my ($url) = @_;
-	[ 301,
-	  [ Location => $url, 'Content-Type' => 'text/plain' ],
-	  [ "Redirecting to $url\n" ]
-	]
-}
-
 sub ctx_get {
 	my ($ctx, $key) = @_;
 	my $val = $ctx->{$key};
-	(defined $val && length $val) or die "BUG: bad ctx, $key unusable\n";
+	(defined $val && $val ne '') or die "BUG: bad ctx, $key unusable\n";
 	$val;
 }
 
@@ -327,22 +296,116 @@ EOF
 	[ 501, [ 'Content-Type' => 'text/html; charset=UTF-8' ], [ $msg ] ];
 }
 
-sub msg_pfx {
-	my ($ctx) = @_;
-	my $href = PublicInbox::Hval::ascii_html(uri_escape_utf8($ctx->{mid}));
-	"../f/$href.html";
-}
-
-# /$LISTNAME/t/$MESSAGE_ID.mbox           -> thread as mbox
-# /$LISTNAME/t/$MESSAGE_ID.mbox.gz        -> thread as gzipped mbox
+# /$LISTNAME/$MESSAGE_ID/t.mbox           -> thread as mbox
+# /$LISTNAME/$MESSAGE_ID/t.mbox.gz        -> thread as gzipped mbox
 # note: I'm not a big fan of other compression formats since they're
 # significantly more expensive on CPU than gzip and less-widely available,
 # especially on older systems.  Stick to zlib since that's what git uses.
 sub get_thread_mbox {
-	my ($ctx, $cgi, $sfx) = @_;
+	my ($ctx, $sfx) = @_;
 	my $srch = searcher($ctx) or return need_search($ctx);
 	require PublicInbox::Mbox;
 	PublicInbox::Mbox::thread_mbox($ctx, $srch, $sfx);
 }
 
+
+# /$LISTNAME/$MESSAGE_ID/t.atom		  -> thread as Atom feed
+sub get_thread_atom {
+	my ($ctx) = @_;
+	searcher($ctx) or return need_search($ctx);
+	$ctx->{self_url} = self_url($ctx->{cgi});
+	require PublicInbox::Feed;
+	PublicInbox::Feed::generate_thread_atom($ctx);
+}
+
+sub legacy_redirects {
+	my ($ctx, $path_info) = @_;
+
+	# single-message pages
+	if ($path_info =~ m!$LISTNAME_RE/m/(\S+)/\z!o) {
+		r301($ctx, $1, $2);
+	} elsif ($path_info =~ m!$LISTNAME_RE/m/(\S+)/raw\z!o) {
+		r301($ctx, $1, $2, 'raw');
+
+	} elsif ($path_info =~ m!$LISTNAME_RE/f/(\S+)/\z!o) {
+		r301($ctx, $1, $2, 'f/');
+
+	# thread display
+	} elsif ($path_info =~ m!$LISTNAME_RE/t/(\S+)/\z!o) {
+		r301($ctx, $1, $2, 't/#u');
+
+	} elsif ($path_info =~ m!$LISTNAME_RE/t/(\S+)/mbox(\.gz)?\z!o) {
+		r301($ctx, $1, $2, "t.mbox$3");
+
+	# even older legacy redirects
+	} elsif ($path_info =~ m!$LISTNAME_RE/m/(\S+)\.html\z!o) {
+		r301($ctx, $1, $2);
+
+	} elsif ($path_info =~ m!$LISTNAME_RE/t/(\S+)\.html\z!o) {
+		r301($ctx, $1, $2, 't/#u');
+
+	} elsif ($path_info =~ m!$LISTNAME_RE/f/(\S+)\.html\z!o) {
+		r301($ctx, $1, $2, 'f/');
+
+	} elsif ($path_info =~ m!$LISTNAME_RE/(?:m|f)/(\S+)\.txt\z!o) {
+		r301($ctx, $1, $2, 'raw');
+
+	} elsif ($path_info =~ m!$LISTNAME_RE/t/(\S+)(\.mbox(?:\.gz)?)\z!o) {
+		r301($ctx, $1, $2, "t$3");
+
+	# legacy convenience redirects, order still matters
+	} elsif ($path_info =~ m!$LISTNAME_RE/m/(\S+)\z!o) {
+		r301($ctx, $1, $2);
+	} elsif ($path_info =~ m!$LISTNAME_RE/t/(\S+)\z!o) {
+		r301($ctx, $1, $2, 't/#u');
+	} elsif ($path_info =~ m!$LISTNAME_RE/f/(\S+)\z!o) {
+		r301($ctx, $1, $2, 'f/');
+
+	# some Message-IDs have slashes in them and the HTTP server
+	# may try to be clever and unescape them :<
+	} elsif ($path_info =~ m!$LISTNAME_RE/(\S+/\S+)/$END_RE\z!o) {
+		msg_page($ctx, $1, $2, $3);
+
+	# in case people leave off the trailing slash:
+	} elsif ($path_info =~ m!$LISTNAME_RE/(\S+/\S+)/(f|T|t)\z!o) {
+		r301($ctx, $1, $2, $3 eq 't' ? 't/#u' : $3);
+	} else {
+		r404();
+	}
+}
+
+sub r301 {
+	my ($ctx, $listname, $mid, $suffix) = @_;
+	my $cgi = $ctx->{cgi};
+	my $url;
+	if (ref($cgi) eq 'CGI') {
+		$url = $cgi->url(-base) . '/';
+	} else {
+		$url = $cgi->base->as_string;
+	}
+
+	$url .= $listname . '/';
+	$url .= (uri_escape_utf8($mid) . '/') if (defined $mid);
+	$url .= $suffix if (defined $suffix);
+
+	[ 301,
+	  [ Location => $url, 'Content-Type' => 'text/plain' ],
+	  [ "Redirecting to $url\n" ] ]
+}
+
+sub msg_page {
+	my ($ctx, $list, $mid, $e) = @_;
+	unless (invalid_list_mid($ctx, $list, $mid)) {
+		'' eq $e and return get_mid_html($ctx);
+		't/' eq $e and return get_thread($ctx);
+		't.atom' eq $e and return get_thread_atom($ctx);
+		't.mbox' eq $e and return get_thread_mbox($ctx);
+		't.mbox.gz' eq $e and return get_thread_mbox($ctx, '.gz');
+		'T/' eq $e and return get_thread($ctx, 1);
+		'raw' eq $e and return get_mid_txt($ctx);
+		'f/' eq $e and return get_full_html($ctx);
+	}
+	r404($ctx);
+}
+
 1;