X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWWW.pm;h=570e690ec8136ca7cf6c98b4ea0138da42c57032;hb=5c8909925072804901e9c3b45bbf25446d379e7b;hp=3a428218f783c85849085a1fec549fcaf260adfc;hpb=dc7dc9ef49e3d396d2b47fa2befd1718aff45f0d;p=public-inbox.git

diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 3a428218..570e690e 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2014-2020 all contributors <meta@public-inbox.org>
+# Copyright (C) 2014-2021 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
@@ -11,10 +11,8 @@
 # - Must not rely on static content
 # - UTF-8 is only for user-content, 7-bit US-ASCII for us
 package PublicInbox::WWW;
-use 5.010_001;
 use strict;
-use warnings;
-use bytes (); # only for bytes::length
+use v5.10.1;
 use PublicInbox::Config;
 use PublicInbox::Hval;
 use URI::Escape qw(uri_unescape);
@@ -22,18 +20,18 @@ use PublicInbox::MID qw(mid_escape);
 use PublicInbox::GitHTTPBackend;
 use PublicInbox::UserContent;
 use PublicInbox::WwwStatic qw(r path_info_raw);
+use PublicInbox::Eml;
 
 # 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 $ATTACH_RE = qr!([0-9][0-9\.]*)-($PublicInbox::Hval::FN)!;
-our $OID_RE = qr![a-f0-9]{7,40}!;
+our $OID_RE = qr![a-f0-9]{7,}!;
 
 sub new {
-	my ($class, $pi_config) = @_;
-	$pi_config ||= PublicInbox::Config->new;
-	bless { pi_config => $pi_config }, $class;
+	my ($class, $pi_cfg) = @_;
+	bless { pi_cfg => $pi_cfg // PublicInbox::Config->new }, $class;
 }
 
 # backwards compatibility, do not use
@@ -50,10 +48,9 @@ sub call {
 	%{$ctx->{qp}} = map {
 		utf8::decode($_);
 		tr/+/ /;
-		my ($k, $v) = split('=', $_, 2);
-		$v = uri_unescape($v // '');
+		my ($k, $v) = split(/=/, $_, 2);
 		# none of the keys we care about will need escaping
-		$k => $v;
+		($k // '', uri_unescape($v // ''))
 	} split(/[&;]+/, $env->{QUERY_STRING});
 
 	my $path_info = path_info_raw($env);
@@ -76,8 +73,12 @@ sub call {
 	}
 
 	# top-level indices and feeds
-	if ($path_info eq '/' || $path_info eq '/manifest.js.gz') {
-		www_listing($self)->call($env);
+	if ($path_info eq '/') {
+		require PublicInbox::WwwListing;
+		PublicInbox::WwwListing->response($ctx);
+	} elsif ($path_info eq '/manifest.js.gz') {
+		require PublicInbox::ManifestJsGz;
+		PublicInbox::ManifestJsGz->response($ctx);
 	} elsif ($path_info =~ m!$INBOX_RE\z!o) {
 		invalid_inbox($ctx, $1) || r301($ctx, $1);
 	} elsif ($path_info =~ m!$INBOX_RE(?:/|/index\.html)?\z!o) {
@@ -130,7 +131,8 @@ sub call {
 	# convenience redirects order matters
 	} elsif ($path_info =~ m!$INBOX_RE/([^/]{2,})\z!o) {
 		r301($ctx, $1, $2);
-
+	} elsif ($path_info =~ m!\A/\+/([a-zA-Z0-9_\-\.]+)\.css\z!) {
+		get_css($ctx, undef, $1); # for WwwListing
 	} else {
 		legacy_redirects($ctx, $path_info);
 	}
@@ -151,7 +153,7 @@ sub preload {
 	require PublicInbox::Feed;
 	require PublicInbox::View;
 	require PublicInbox::SearchThread;
-	require PublicInbox::MIME;
+	require PublicInbox::Eml;
 	require PublicInbox::Mbox;
 	require PublicInbox::ViewVCS;
 	require PublicInbox::WwwText;
@@ -164,15 +166,14 @@ sub preload {
 		eval "require PublicInbox::$_;";
 	}
 	if (ref($self)) {
-		my $pi_config = $self->{pi_config};
-		if (defined($pi_config->{'publicinbox.cgitrc'})) {
-			$pi_config->limiter('-cgit');
+		my $pi_cfg = $self->{pi_cfg};
+		if (defined($pi_cfg->{'publicinbox.cgitrc'})) {
+			$pi_cfg->limiter('-cgit');
 		}
 		$self->cgit;
 		$self->stylesheets_prepare($_) for ('', '../', '../../');
-		$self->www_listing;
 		$self->news_www;
-		$pi_config->each_inbox(\&preload_inbox);
+		$pi_cfg->each_inbox(\&preload_inbox);
 	}
 }
 
@@ -206,9 +207,10 @@ sub news_cgit_fallback ($) {
 # returns undef if valid, array ref response if invalid
 sub invalid_inbox ($$) {
 	my ($ctx, $inbox) = @_;
-	my $ibx = $ctx->{www}->{pi_config}->lookup_name($inbox);
+	my $ibx = $ctx->{www}->{pi_cfg}->lookup_name($inbox) //
+			$ctx->{www}->{pi_cfg}->lookup_ei($inbox);
 	if (defined $ibx) {
-		$ctx->{-inbox} = $ibx;
+		$ctx->{ibx} = $ibx;
 		return;
 	}
 
@@ -226,14 +228,13 @@ sub invalid_inbox_mid {
 	return $ret if $ret;
 
 	my $mid = $ctx->{mid} = uri_unescape($mid_ue);
-	my $ibx = $ctx->{-inbox};
+	my $ibx = $ctx->{ibx};
 	if ($mid =~ m!\A([a-f0-9]{2})([a-f0-9]{38})\z!) {
 		my ($x2, $x38) = ($1, $2);
 		# this is horrifically wasteful for legacy URLs:
-		my $str = $ctx->{-inbox}->msg_by_path("$x2/$x38") or return;
-		require Email::Simple;
-		my $s = Email::Simple->new($str);
-		$mid = PublicInbox::MID::mid_clean($s->header('Message-ID'));
+		my $str = $ctx->{ibx}->msg_by_path("$x2/$x38") or return;
+		my $s = PublicInbox::Eml->new($str);
+		$mid = PublicInbox::MID::mid_clean($s->header_raw('Message-ID'));
 		return r301($ctx, $inbox, mid_escape($mid));
 	}
 	undef;
@@ -269,7 +270,7 @@ sub get_index {
 sub get_mid_txt {
 	my ($ctx) = @_;
 	require PublicInbox::Mbox;
-	PublicInbox::Mbox::emit_raw($ctx) || r404($ctx);
+	PublicInbox::Mbox::emit_raw($ctx) || r(404);
 }
 
 # /$INBOX/$MESSAGE_ID/                   -> HTML content (short quotes)
@@ -282,7 +283,7 @@ sub get_mid_html {
 # /$INBOX/$MESSAGE_ID/t/
 sub get_thread {
 	my ($ctx, $flat) = @_;
-	$ctx->{-inbox}->over or return need($ctx, 'Overview');
+	$ctx->{ibx}->over or return need($ctx, 'Overview');
 	$ctx->{flat} = $flat;
 	require PublicInbox::View;
 	PublicInbox::View::thread_html($ctx);
@@ -301,13 +302,12 @@ sub get_text {
 }
 
 # show git objects (blobs and commits)
-# /$INBOX/_/$OBJECT_ID/show
-# /$INBOX/_/${OBJECT_ID}_${FILENAME}
-# KEY may contain slashes
+# /$INBOX/$GIT_OBJECT_ID/s/
+# /$INBOX/$GIT_OBJECT_ID/s/$FILENAME
 sub get_vcs_object ($$$;$) {
 	my ($ctx, $inbox, $oid, $filename) = @_;
 	my $r404 = invalid_inbox($ctx, $inbox);
-	return $r404 if $r404;
+	return $r404 if $r404 || !$ctx->{www}->{pi_cfg}->repo_objs($ctx->{ibx});
 	require PublicInbox::ViewVCS;
 	PublicInbox::ViewVCS::show($ctx, $oid, $filename);
 }
@@ -322,12 +322,11 @@ sub get_altid_dump {
 
 sub need {
 	my ($ctx, $extra) = @_;
-	my $msg = <<EOF;
-<html><head><title>$extra not available for this
-public-inbox</title><body><pre>$extra is not available for this public-inbox
-<a href="../">Return to index</a></pre></body></html>
+	require PublicInbox::WwwStream;
+	PublicInbox::WwwStream::html_oneshot($ctx, 501, \<<EOF);
+<pre>$extra is not available for this public-inbox
+<a\nhref="../">Return to index</a></pre>
 EOF
-	[ 501, [ 'Content-Type' => 'text/html; charset=UTF-8' ], [ $msg ] ];
 }
 
 # /$INBOX/$MESSAGE_ID/t.mbox           -> thread as mbox
@@ -337,7 +336,7 @@ EOF
 # especially on older systems.  Stick to zlib since that's what git uses.
 sub get_thread_mbox {
 	my ($ctx, $sfx) = @_;
-	my $over = $ctx->{-inbox}->over or return need($ctx, 'Overview');
+	my $over = $ctx->{ibx}->over or return need($ctx, 'Overview');
 	require PublicInbox::Mbox;
 	PublicInbox::Mbox::thread_mbox($ctx, $over, $sfx);
 }
@@ -346,7 +345,7 @@ sub get_thread_mbox {
 # /$INBOX/$MESSAGE_ID/t.atom		  -> thread as Atom feed
 sub get_thread_atom {
 	my ($ctx) = @_;
-	$ctx->{-inbox}->over or return need($ctx, 'Overview');
+	$ctx->{ibx}->over or return need($ctx, 'Overview');
 	require PublicInbox::Feed;
 	PublicInbox::Feed::generate_thread_atom($ctx);
 }
@@ -411,11 +410,11 @@ sub legacy_redirects {
 
 sub r301 {
 	my ($ctx, $inbox, $mid_ue, $suffix) = @_;
-	my $ibx = $ctx->{-inbox};
+	my $ibx = $ctx->{ibx};
 	unless ($ibx) {
 		my $r404 = invalid_inbox($ctx, $inbox);
 		return $r404 if $r404;
-		$ibx = $ctx->{-inbox};
+		$ibx = $ctx->{ibx};
 	}
 	my $url = $ibx->base_url($ctx->{env});
 	my $qs = $ctx->{env}->{QUERY_STRING};
@@ -452,7 +451,7 @@ sub msg_page {
 sub serve_git {
 	my ($ctx, $epoch, $path) = @_;
 	my $env = $ctx->{env};
-	my $ibx = $ctx->{-inbox};
+	my $ibx = $ctx->{ibx};
 	my $git = defined $epoch ? $ibx->git_epoch($epoch) : $ibx->git;
 	$git ? PublicInbox::GitHTTPBackend::serve($env, $git, $path) : r404();
 }
@@ -460,7 +459,7 @@ sub serve_git {
 sub mbox_results {
 	my ($ctx) = @_;
 	if ($ctx->{env}->{QUERY_STRING} =~ /(?:\A|[&;])q=/) {
-		$ctx->{-inbox}->search or return need($ctx, 'search');
+		$ctx->{ibx}->isrch or return need($ctx, 'search');
 		require PublicInbox::SearchView;
 		return PublicInbox::SearchView::mbox_results($ctx);
 	}
@@ -479,18 +478,18 @@ sub news_www {
 	my ($self) = @_;
 	$self->{news_www} ||= do {
 		require PublicInbox::NewsWWW;
-		PublicInbox::NewsWWW->new($self->{pi_config});
+		PublicInbox::NewsWWW->new($self->{pi_cfg});
 	}
 }
 
 sub cgit {
 	my ($self) = @_;
 	$self->{cgit} ||= do {
-		my $pi_config = $self->{pi_config};
+		my $pi_cfg = $self->{pi_cfg};
 
-		if (defined($pi_config->{'publicinbox.cgitrc'})) {
+		if (defined($pi_cfg->{'publicinbox.cgitrc'})) {
 			require PublicInbox::Cgit;
-			PublicInbox::Cgit->new($pi_config);
+			PublicInbox::Cgit->new($pi_cfg);
 		} else {
 			require Plack::Util;
 			Plack::Util::inline_object(call => sub { r404() });
@@ -498,21 +497,13 @@ sub cgit {
 	}
 }
 
-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}, [$ctx->{-inbox}]);
+	require PublicInbox::ManifestJsGz;
+	PublicInbox::ManifestJsGz::per_inbox($ctx);
 }
 
 sub get_attach {
@@ -544,7 +535,7 @@ sub stylesheets_prepare ($$) {
 	} || sub { $_[0] };
 
 	my $css_map = {};
-	my $stylesheets = $self->{pi_config}->{css} || [];
+	my $stylesheets = $self->{pi_cfg}->{css} || [];
 	my $links = [];
 	my $inline_ok = 1;
 
@@ -635,24 +626,25 @@ sub style {
 	};
 }
 
-# /$INBOX/$KEY.css endpoint
+# /$INBOX/$KEY.css and /+/$KEY.css endpoints
 # CSS is configured globally for all inboxes, but we access them on
 # a per-inbox basis.  This allows administrators to setup per-inbox
 # static routes to intercept the request before it hits PSGI
+# inbox == undef => top-level WwwListing
 sub get_css ($$$) {
 	my ($ctx, $inbox, $key) = @_;
-	my $r404 = invalid_inbox($ctx, $inbox);
+	my $r404 = defined($inbox) ? invalid_inbox($ctx, $inbox) : undef;
 	return $r404 if $r404;
 	my $self = $ctx->{www};
-	my $css_map = $self->{-css_map} || stylesheets_prepare($self, '');
+	my $css_map = $self->{-css_map} ||
+		stylesheets_prepare($self, defined($inbox) ? '' : '+/');
 	my $css = $css_map->{$key};
-	if (!defined($css) && $key eq 'userContent') {
+	if (!defined($css) && defined($inbox) && $key eq 'userContent') {
 		my $env = $ctx->{env};
-		$css = PublicInbox::UserContent::sample($ctx->{-inbox}, $env);
+		$css = PublicInbox::UserContent::sample($ctx->{ibx}, $env);
 	}
 	defined $css or return r404();
-	my $h = [ 'Content-Length', bytes::length($css),
-		'Content-Type', 'text/css' ];
+	my $h = [ 'Content-Length', length($css), 'Content-Type', 'text/css' ];
 	PublicInbox::GitHTTPBackend::cache_one_year($h);
 	[ 200, $h, [ $css ] ];
 }
@@ -660,8 +652,9 @@ sub get_css ($$$) {
 sub get_description {
 	my ($ctx, $inbox) = @_;
 	invalid_inbox($ctx, $inbox) || do {
-		my $d = $ctx->{-inbox}->description . "\n";
-		[ 200, [ 'Content-Length', bytes::length($d),
+		my $d = $ctx->{ibx}->description . "\n";
+		utf8::encode($d);
+		[ 200, [ 'Content-Length', length($d),
 			'Content-Type', 'text/plain' ], [ $d ] ];
 	};
 }