X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FManifestJsGz.pm;h=d5048a96de45da8589cc659fff787588a941c64a;hb=23af251dd607c4e75ab1e68063f2c885c48cc035;hp=fb7a45e733d084d6e47eeec056ffca6068c43f03;hpb=0d38f65c490466837ae091afa7a7b6f59d04ce7c;p=public-inbox.git diff --git a/lib/PublicInbox/ManifestJsGz.pm b/lib/PublicInbox/ManifestJsGz.pm index fb7a45e7..d5048a96 100644 --- a/lib/PublicInbox/ManifestJsGz.pm +++ b/lib/PublicInbox/ManifestJsGz.pm @@ -1,4 +1,4 @@ -# Copyright (C) 2020 all contributors +# Copyright (C) 2020-2021 all contributors # License: AGPL-3.0+ # generates manifest.js.gz for grokmirror(1) @@ -6,19 +6,17 @@ package PublicInbox::ManifestJsGz; use strict; use v5.10.1; use parent qw(PublicInbox::WwwListing); -use bytes (); # length use PublicInbox::Config; use IO::Compress::Gzip qw(gzip); use HTTP::Date qw(time2str); -our $json = PublicInbox::Config::json(); +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; @@ -55,34 +53,49 @@ sub slow_manifest_add ($$) { manifest_add($ctx, $ibx); } }; + warn "E: $@" if $@; } sub eidx_manifest_add ($$$) { my ($ctx, $ALL, $ibx) = @_; if (my $data = $ALL->misc->inbox_data($ibx)) { $data = $json->decode($data); + delete $data->{''}; # private while (my ($url_path, $ent) = each %$data) { inject_entry($ctx, $url_path, $ent); } } else { warn "E: `${\$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->{env}->{'pi-httpd.async'} ? + $iter->event_step : $iter->each_section; } } sub ibx_entry { my ($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}) // {}; @@ -95,7 +108,13 @@ 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) = @_; + ibx_entry($ctx, $ctx->{ibx}); + psgi_triple($ctx); } 1;