diff options
Diffstat (limited to 'lib/PublicInbox/ManifestJsGz.pm')
-rw-r--r-- | lib/PublicInbox/ManifestJsGz.pm | 52 |
1 files changed, 32 insertions, 20 deletions
diff --git a/lib/PublicInbox/ManifestJsGz.pm b/lib/PublicInbox/ManifestJsGz.pm index 31cf15dc..be5d5f2a 100644 --- a/lib/PublicInbox/ManifestJsGz.pm +++ b/lib/PublicInbox/ManifestJsGz.pm @@ -1,24 +1,22 @@ -# Copyright (C) 2020-2021 all contributors <meta@public-inbox.org> +# Copyright (C) all contributors <meta@public-inbox.org> # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt> -# generates manifest.js.gz for grokmirror(1) +# generates manifest.js.gz for grokmirror(1) via PublicInbox::WWW +# This doesn't parse manifest.js.gz (that happens in LeiMirror) package PublicInbox::ManifestJsGz; -use strict; -use v5.10.1; +use v5.12; use parent qw(PublicInbox::WwwListing); -use bytes (); # length use PublicInbox::Config; use IO::Compress::Gzip qw(gzip); use HTTP::Date qw(time2str); my $json = PublicInbox::Config::json(); -# called by WwwListing -sub url_regexp { +sub url_filter { my ($ctx) = @_; # grokmirror uses relative paths, so it's domain-dependent - # SUPER calls PublicInbox::WwwListing::url_regexp - $ctx->SUPER::url_regexp('publicInbox.grokManifest', 'match=domain'); + # SUPER calls PublicInbox::WwwListing::url_filter + $ctx->SUPER::url_filter('publicInbox.grokManifest', 'match=domain'); } sub inject_entry ($$$;$) { @@ -29,7 +27,7 @@ sub inject_entry ($$$;$) { $ctx->{manifest}->{$url_path} = $ent; } -sub manifest_add ($$;$$) { +sub manifest_add ($$;$$) { # slow path w/o extindex "all" (or per-inbox) my ($ctx, $ibx, $epoch, $default_desc) = @_; my $url_path = "/$ibx->{name}"; my $git; @@ -55,6 +53,7 @@ sub slow_manifest_add ($$) { manifest_add($ctx, $ibx); } }; + warn "E: $@" if $@; } sub eidx_manifest_add ($$$) { @@ -67,23 +66,37 @@ sub eidx_manifest_add ($$$) { } } else { warn "E: `${\$ibx->eidx_key}' not indexed by $ALL->{topdir}\n"; + # do not use slow path for global manifest since + # it can become catastrophically slow. per-inbox manifest + # is not too bad with dozens of epochs, so never fail that: + slow_manifest_add($ctx, $ibx) if $ibx == $ctx->{ibx}; + } +} + +sub response { + my ($class, $ctx) = @_; + bless $ctx, $class; + my ($re, undef) = $ctx->url_filter; + $re // return psgi_triple($ctx); + my $iter = PublicInbox::ConfigIter->new($ctx->{www}->{pi_cfg}, + $ctx->can('list_match_i'), $re, $ctx); + sub { + $ctx->{-wcb} = $_[0]; # HTTP server callback + ($ctx->{www}->{pi_cfg}->ALL || + !$ctx->{env}->{'pi-httpd.async'}) ? + $iter->each_section : $iter->event_step; } } sub ibx_entry { my ($ctx, $ibx) = @_; my $ALL = $ctx->{www}->{pi_cfg}->ALL; - if ($ALL) { - eidx_manifest_add($ctx, $ALL, $ibx); - } else { + $ALL ? eidx_manifest_add($ctx, $ALL, $ibx) : slow_manifest_add($ctx, $ibx); - } - warn "E: $@" if $@; } -sub hide_key { 'manifest' } +sub hide_key { 'manifest' } # for WwwListing->list_match_i -# overrides WwwListing->psgi_triple sub psgi_triple { my ($ctx) = @_; my $abs2urlpath = delete($ctx->{-abs2urlpath}) // {}; @@ -96,13 +109,12 @@ sub psgi_triple { gzip(\$manifest => \(my $out)); [ 200, [ qw(Content-Type application/gzip), 'Last-Modified', time2str($ctx->{-mtime}), - 'Content-Length', bytes::length($out) ], [ $out ] ] + 'Content-Length', length($out) ], [ $out ] ] } sub per_inbox { my ($ctx) = @_; - # only one inbox, slow is probably OK - slow_manifest_add($ctx, $ctx->{ibx}); + ibx_entry($ctx, $ctx->{ibx}); psgi_triple($ctx); } |