X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FWWW.pm;h=37f55347ac45d8d5e9ff57b0deb22771db7be789;hb=7a92c24157953dc6d9fad911b955c8691cdfcad9;hp=efe7c8ca0064427e3425bb99190e41c373837a94;hpb=078f637c80cc33c7d29973b95fdc16205ad7bb32;p=public-inbox.git diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm index efe7c8ca..37f55347 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 @@ -19,17 +19,17 @@ 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\.\-]*)!; 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, $pi_config) = @_; @@ -66,17 +66,23 @@ sub call { my ($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 ($method !~ /\AGET|HEAD\z/) { + elsif ($method !~ /\A(?:GET|HEAD)\z/) { return r(405); } # 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!$INBOX_RE(?:/|/index\.html)?\z!o) { @@ -85,6 +91,8 @@ sub call { invalid_inbox($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, $3); @@ -122,6 +130,8 @@ sub call { get_vcs_object($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, $2); @@ -131,31 +141,53 @@ sub call { } } -# for CoW-friendliness, MOOOOO! +# for CoW-friendliness, MOOOOO! Even for single-process setups, +# we want to get all immortal allocations done early to avoid heap +# fragmentation since common allocators favor a large contiguous heap. sub preload { my ($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; + $ibx->base_url; +} + # private functions below sub r404 { @@ -203,9 +235,8 @@ sub invalid_inbox_mid { my ($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; @@ -273,9 +304,8 @@ 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 ($$$;$) { my ($ctx, $inbox, $oid, $filename) = @_; my $r404 = invalid_inbox($ctx, $inbox); @@ -284,14 +314,21 @@ sub get_vcs_object ($$$;$) { PublicInbox::ViewVCS::show($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 $msg = <$extra not available for this -public-inbox
$extra is not available for this public-inbox
-Return to index
+ require PublicInbox::WwwStream; + PublicInbox::WwwStream::html_oneshot($ctx, 501, \<$extra is not available for this public-inbox +Return to index EOF - [ 501, [ 'Content-Type' => 'text/html; charset=UTF-8' ], [ $msg ] ]; } # /$INBOX/$MESSAGE_ID/t.mbox -> thread as mbox @@ -462,21 +499,13 @@ sub cgit { } } -sub www_listing { - my ($self) = @_; - $self->{www_listing} ||= do { - require PublicInbox::WwwListing; - PublicInbox::WwwListing->new($self); - } -} - # GET $INBOX/manifest.js.gz sub get_inbox_manifest ($$$) { my ($ctx, $inbox, $key) = @_; my $r404 = invalid_inbox($ctx, $inbox); return $r404 if $r404; - require PublicInbox::WwwListing; - PublicInbox::WwwListing::js($ctx->{env}, [$ctx->{-inbox}]); + require PublicInbox::ManifestJsGz; + PublicInbox::ManifestJsGz::per_inbox($ctx); } sub get_attach { @@ -621,4 +650,13 @@ sub get_css ($$$) { [ 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;