X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWWW.pm;h=289d0ce48e255a9bf4e315164ed380da284f2fe4;hb=46742d95647c7a80cb2f60d5c134717dd91e22e2;hp=251979d5db6ee88af2defb614f2eed43ea5edb6e;hpb=db748229054d52cdcc95843db5d827b49defeaff;p=public-inbox.git diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm index 251979d5..289d0ce4 100644 --- a/lib/PublicInbox/WWW.pm +++ b/lib/PublicInbox/WWW.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2014-2019 all contributors +# Copyright (C) 2014-2020 all contributors # License: AGPL-3.0+ # # Main web interface for mailing list archives @@ -19,9 +19,10 @@ use PublicInbox::Config; 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 path_info_raw); +use PublicInbox::Eml; # TODO: consider a routing tree now that we have more endpoints: our $INBOX_RE = qr!\A/([\w\-][\w\.\-]*)!; @@ -42,17 +43,6 @@ sub run { PublicInbox::WWW->new->call($req->env); } -my %path_re_cache; - -sub path_re ($) { - my $sn = $_[0]->{SCRIPT_NAME}; - $path_re_cache{$sn} ||= do { - $sn = '/'.$sn unless index($sn, '/') == 0; - $sn =~ s!/\z!!; - qr!\A(?:https?://[^/]+)?\Q$sn\E(/[^\?\#]+)!; - }; -} - sub call { my ($self, $env) = @_; my $ctx = { env => $env, www => $self }; @@ -67,9 +57,7 @@ sub call { $k => $v; } split(/[&;]+/, $env->{QUERY_STRING}); - # 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 $path_info = path_info_raw($env); my $method = $env->{REQUEST_METHOD}; if ($method eq 'POST') { @@ -78,12 +66,14 @@ sub call { 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 ($method !~ /\AGET|HEAD\z/) { - return r(405, 'Method Not Allowed'); + elsif ($method !~ /\A(?:GET|HEAD)\z/) { + return r(405); } # top-level indices and feeds @@ -97,6 +87,8 @@ 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/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, $3); @@ -134,6 +126,8 @@ sub call { get_vcs_object($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, $2); @@ -143,31 +137,54 @@ sub call { } } -# for CoW-friendliness, MOOOOO! +# for CoW-friendliness, MOOOOO! Even for single-process setups, +# we want to get all immortal allocations done early to avoid heap +# fragmentation since common allocators favor a large contiguous heap. sub preload { my ($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; + $ibx->base_url; +} + # private functions below sub r404 { @@ -176,12 +193,9 @@ sub r404 { require PublicInbox::ExtMsg; return PublicInbox::ExtMsg::ext_msg($ctx); } - r(404, 'Not Found'); + r(404); } -# simple response for errors -sub r { [ $_[0], ['Content-Type' => 'text/plain'], [ join(' ', @_, "\n") ] ] } - sub news_cgit_fallback ($) { my ($ctx) = @_; my $www = $ctx->{www}; @@ -218,9 +232,8 @@ sub invalid_inbox_mid { my ($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; @@ -299,6 +312,14 @@ sub get_vcs_object ($$$;$) { PublicInbox::ViewVCS::show($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 $msg = <{-inbox}->description . "\n"; + [ 200, [ 'Content-Length', bytes::length($d), + 'Content-Type', 'text/plain' ], [ $d ] ]; + }; +} + 1;