-# Copyright (C) 2014-2019 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
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);
+use PublicInbox::WwwStatic qw(r path_info_raw);
+use PublicInbox::Eml;
# TODO: consider a routing tree now that we have more endpoints:
our $INBOX_RE = qr!\A/([\w\-][\w\.\-]*)!;
PublicInbox::WWW->new->call($req->env);
}
-# PATH_INFO is decoded, and we want the undecoded original
-my %path_re_cache;
-sub path_info_raw ($) {
- my ($env) = @_;
- my $sn = $env->{SCRIPT_NAME};
- my $re = $path_re_cache{$sn} ||= do {
- $sn = '/'.$sn unless index($sn, '/') == 0;
- $sn =~ s!/\z!!;
- qr!\A(?:https?://[^/]+)?\Q$sn\E(/[^\?\#]+)!;
- };
- $env->{REQUEST_URI} =~ $re ? $1 : $env->{PATH_INFO};
-}
-
sub call {
my ($self, $env) = @_;
my $ctx = { env => $env, www => $self };
my ($epoch, $path) = ($2, $3);
return invalid_inbox($ctx, $1) ||
serve_git($ctx, $epoch, $path);
+ } elsif ($path_info =~ m!$INBOX_RE/(\w+)\.sql\.gz\z!o) {
+ return get_altid_dump($ctx, $1, $2);
} elsif ($path_info =~ m!$INBOX_RE/!o) {
return invalid_inbox($ctx, $1) || mbox_results($ctx);
}
}
- elsif ($method !~ /\AGET|HEAD\z/) {
+ elsif ($method !~ /\A(?:GET|HEAD)\z/) {
return r(405);
}
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/description\z!o) {
+ get_description($ctx, $1);
} elsif ($path_info =~ m!$INBOX_RE/(?:(?:git/)?([0-9]+)(?:\.git)?/)?
($PublicInbox::GitHTTPBackend::ANY)\z!ox) {
my ($epoch, $path) = ($2, $3);
get_vcs_object($ctx, $1, $2, $3);
} elsif ($path_info =~ m!$INBOX_RE/($OID_RE)/s\z!o) {
r301($ctx, $1, $2, 's/');
+ } elsif ($path_info =~ m!$INBOX_RE/(\w+)\.sql\.gz\z!o) {
+ get_altid_dump($ctx, $1, $2);
# convenience redirects order matters
} elsif ($path_info =~ m!$INBOX_RE/([^/]{2,})\z!o) {
r301($ctx, $1, $2);
}
}
-# for CoW-friendliness, MOOOOO!
+# for CoW-friendliness, MOOOOO! Even for single-process setups,
+# we want to get all immortal allocations done early to avoid heap
+# fragmentation since common allocators favor a large contiguous heap.
sub preload {
my ($self) = @_;
+
+ # populate caches used by Encode internally, since emails
+ # may show up with any encoding.
+ require Encode;
+ Encode::find_encoding($_) for Encode->encodings(':all');
+
+ require PublicInbox::ExtMsg;
require PublicInbox::Feed;
require PublicInbox::View;
require PublicInbox::SearchThread;
- require PublicInbox::MIME;
- require Digest::SHA;
- require POSIX;
+ require PublicInbox::Eml;
+ 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::Mbox IO::Compress::Gzip
- PublicInbox::NewsWWW)) {
- eval "require $_;";
+ for (qw(SearchView MboxGz WwwAltId)) {
+ eval "require PublicInbox::$_;";
}
if (ref($self)) {
+ my $pi_config = $self->{pi_config};
+ if (defined($pi_config->{'publicinbox.cgitrc'})) {
+ $pi_config->limiter('-cgit');
+ }
$self->cgit;
$self->stylesheets_prepare($_) for ('', '../', '../../');
$self->www_listing;
+ $self->news_www;
+ $pi_config->each_inbox(\&preload_inbox);
}
}
+sub preload_inbox {
+ my $ibx = shift;
+ $ibx->altid_map;
+ $ibx->cloneurl;
+ $ibx->description;
+ $ibx->base_url;
+}
+
# private functions below
sub r404 {
my ($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 $s = PublicInbox::Eml->new($str);
+ $mid = PublicInbox::MID::mid_clean($s->header_raw('Message-ID'));
return r301($ctx, $inbox, mid_escape($mid));
}
undef;
}
# 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, $inbox);
PublicInbox::ViewVCS::show($ctx, $oid, $filename);
}
+sub get_altid_dump {
+ my ($ctx, $inbox, $altid_pfx) =@_;
+ my $r404 = invalid_inbox($ctx, $inbox);
+ return $r404 if $r404;
+ eval { require PublicInbox::WwwAltId } or return need($ctx, 'sqlite3');
+ PublicInbox::WwwAltId::sqldump($ctx, $altid_pfx);
+}
+
sub need {
my ($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/$MESSAGE_ID/t.mbox -> thread as mbox
my ($ctx, $inbox, $key) = @_;
my $r404 = invalid_inbox($ctx, $inbox);
return $r404 if $r404;
- require PublicInbox::WwwListing;
- PublicInbox::WwwListing::js($ctx->{env}, [$ctx->{-inbox}]);
+ require PublicInbox::ManifestJsGz;
+ PublicInbox::ManifestJsGz::response($ctx->{env}, [$ctx->{-inbox}]);
}
sub get_attach {
[ 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;