X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWWW.pm;h=4b7177c1b157b2e4c2b5a7f8841123f287c928a1;hb=7df78fd98370832e5dcb22863dfa4f044fa21f20;hp=cbaf88450ca8548c513abb9bdd85e8da16b2cd65;hpb=17b71a0c6265677275718771b35adb08ed480db8;p=public-inbox.git diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm index cbaf8845..4b7177c1 100644 --- a/lib/PublicInbox/WWW.pm +++ b/lib/PublicInbox/WWW.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2014-2018 all contributors +# Copyright (C) 2014-2019 all contributors # License: AGPL-3.0+ # # Main web interface for mailing list archives @@ -11,10 +11,11 @@ # - 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); @@ -27,7 +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 { @@ -58,24 +59,26 @@ 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; - # not using $env->{PATH_INFO} here since that's already decoded + # avoiding $env->{PATH_INFO} here since that's already decoded my ($path_info) = ($env->{REQUEST_URI} =~ path_re($env)); + $path_info //= $env->{PATH_INFO}; 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); } @@ -85,8 +88,8 @@ sub call { } # 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!$INBOX_RE(?:/|/index\.html)?\z!o) { @@ -95,11 +98,11 @@ sub call { invalid_inbox($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!$INBOX_RE/([\w-]+).mbox\.gz\z!o) { + my ($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, $3); @@ -121,11 +124,14 @@ sub call { r301($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/'); @@ -147,14 +153,19 @@ 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 $_;"; } if (ref($self)) { + $self->cgit; $self->stylesheets_prepare($_) for ('', '../', '../../'); + $self->www_listing; } } @@ -164,7 +175,6 @@ sub r404 { my ($ctx) = @_; if ($ctx && $ctx->{mid}) { require PublicInbox::ExtMsg; - searcher($ctx); return PublicInbox::ExtMsg::ext_msg($ctx); } r(404, 'Not Found'); @@ -173,14 +183,20 @@ sub r404 { # simple response for errors sub r { [ $_[0], ['Content-Type' => 'text/plain'], [ join(' ', @_, "\n") ] ] } +sub news_cgit_fallback ($) { + my ($ctx) = @_; + my $www = $ctx->{www}; + my $env = $ctx->{env}; + my $res = $www->news_www->call($env); + $res->[0] == 404 ? $www->cgit->call($env) : $res; +} + # returns undef if valid, array ref response if invalid sub invalid_inbox ($$) { my ($ctx, $inbox) = @_; - my $www = $ctx->{www}; - my $obj = $www->{pi_config}->lookup_name($inbox); - if (defined $obj) { - $ctx->{git} = $obj->git; - $ctx->{-inbox} = $obj; + my $ibx = $ctx->{www}->{pi_config}->lookup_name($inbox); + if (defined $ibx) { + $ctx->{-inbox} = $ibx; return; } @@ -188,7 +204,7 @@ sub invalid_inbox ($$) { # generation and link things intended for nntp:// to https?://, # so try to infer links and redirect them to the appropriate # list URL. - $www->news_www->call($ctx->{env}); + news_cgit_fallback($ctx); } # returns undef if valid, array ref response if invalid @@ -229,7 +245,6 @@ sub get_new { sub get_index { my ($ctx) = @_; require PublicInbox::Feed; - searcher($ctx); if ($ctx->{env}->{QUERY_STRING} =~ /(?:\A|[&;])q=/) { require PublicInbox::SearchView; PublicInbox::SearchView::sres_top_html($ctx); @@ -249,14 +264,13 @@ sub get_mid_txt { sub get_mid_html { my ($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); @@ -286,28 +300,11 @@ 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 = <Search not available for this -public-inbox
Search is not available for this public-inbox
+$extra not available for this
+public-inbox
$extra is not available for this public-inbox
 Return to index
EOF [ 501, [ 'Content-Type' => 'text/html; charset=UTF-8' ], [ $msg ] ]; @@ -320,16 +317,16 @@ 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); } @@ -388,19 +385,19 @@ sub legacy_redirects { } elsif ($path_info =~ m!$INBOX_RE/(\S+/\S+)/f\z!o) { r301($ctx, $1, $2); } else { - $ctx->{www}->news_www->call($ctx->{env}); + news_cgit_fallback($ctx); } } sub r301 { my ($ctx, $inbox, $mid_ue, $suffix) = @_; - my $obj = $ctx->{-inbox}; - unless ($obj) { + my $ibx = $ctx->{-inbox}; + unless ($ibx) { my $r404 = invalid_inbox($ctx, $inbox); return $r404 if $r404; - $obj = $ctx->{-inbox}; + $ibx = $ctx->{-inbox}; } - my $url = $obj->base_url($ctx->{env}); + my $url = $ibx->base_url($ctx->{env}); my $qs = $ctx->{env}->{QUERY_STRING}; if (defined $mid_ue) { # common, and much nicer as '@' than '%40': @@ -433,17 +430,17 @@ 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); } @@ -454,7 +451,6 @@ sub serve_mbox_range { my ($ctx, $inbox, $range) = @_; invalid_inbox($ctx, $inbox) || eval { require PublicInbox::Mbox; - searcher($ctx); PublicInbox::Mbox::emit_range($ctx, $range); } } @@ -467,6 +463,37 @@ sub news_www { } } +sub cgit { + my ($self) = @_; + $self->{cgit} ||= do { + my $pi_config = $self->{pi_config}; + + if (defined($pi_config->{'publicinbox.cgitrc'})) { + require PublicInbox::Cgit; + PublicInbox::Cgit->new($pi_config); + } else { + 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; @@ -512,17 +539,29 @@ sub stylesheets_prepare ($$) { if (defined $attr->{href}) { $inline_ok = 0; } else { - open(my $fh, '<', $_) or do { - warn "failed to open $_: $!\n"; + 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/) { $ctime = sprintf('%x',(stat($fh))[10]); $local = $mini->($local); } + + # do not let BOFHs override userContent.css: + if ($local =~ /!\s*important\b/i) { + warn "ignoring $fn since it uses `!important'\n"; + next; + } + $css_map->{$key} = $local; $attr->{href} = "$upfx$key.css?$ctime"; if (defined($attr->{title})) {