X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FManifestJsGz.pm;h=d5048a96de45da8589cc659fff787588a941c64a;hb=23af251dd607c4e75ab1e68063f2c885c48cc035;hp=ab1478afcc38507245a8b41b9ac0ddfcb747d5c9;hpb=f1bdfad51c98825e7e2569aa34db7d3879fa9ef4;p=public-inbox.git diff --git a/lib/PublicInbox/ManifestJsGz.pm b/lib/PublicInbox/ManifestJsGz.pm index ab1478af..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) @@ -6,96 +6,42 @@ package PublicInbox::ManifestJsGz; use strict; use v5.10.1; use parent qw(PublicInbox::WwwListing); -use Digest::SHA (); -use File::Spec (); -use bytes (); # length -use PublicInbox::Inbox; use PublicInbox::Config; -use PublicInbox::Git; use IO::Compress::Gzip qw(gzip); use HTTP::Date qw(time2str); -*try_cat = \&PublicInbox::Inbox::try_cat; -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 + $ctx->SUPER::url_filter('publicInbox.grokManifest', 'match=domain'); } -sub fingerprint ($) { - my ($git) = @_; - # TODO: convert to qspawn for fairness when there's - # thousands of repos - my ($fh, $pid) = $git->popen('show-ref'); - my $dig = Digest::SHA->new(1); - while (read($fh, my $buf, 65536)) { - $dig->add($buf); - } - close $fh; - waitpid($pid, 0); - return if $?; # empty, uninitialized git repo - $dig->hexdigest; +sub inject_entry ($$$;$) { + my ($ctx, $url_path, $ent, $git_dir) = @_; + $ctx->{-abs2urlpath}->{$git_dir // delete $ent->{git_dir}} = $url_path; + my $modified = $ent->{modified}; + $ctx->{-mtime} = $modified if $modified > ($ctx->{-mtime} // 0); + $ctx->{manifest}->{$url_path} = $ent; } -sub manifest_add ($$;$$) { +sub manifest_add ($$;$$) { # slow path w/o extindex "all" (or per-inbox) my ($ctx, $ibx, $epoch, $default_desc) = @_; my $url_path = "/$ibx->{name}"; - my $git_dir = $ibx->{inboxdir}; + my $git; if (defined $epoch) { - $git_dir .= "/git/$epoch.git"; $url_path .= "/git/$epoch.git"; + $git = $ibx->git_epoch($epoch) or return; + } else { + $git = $ibx->git; } - return unless -d $git_dir; - my $git = PublicInbox::Git->new($git_dir); - my $fingerprint = fingerprint($git) or return; # no empty repos - - chomp(my $owner = $git->qx('config', 'gitweb.owner')); - chomp(my $desc = try_cat("$git_dir/description")); - utf8::decode($owner); - utf8::decode($desc); - $owner = undef if $owner eq ''; - $desc = 'Unnamed repository' if $desc eq ''; - - # templates/hooks--update.sample and git-multimail in git.git - # only match "Unnamed repository", not the full contents of - # templates/this--description in git.git - if ($desc =~ /\AUnnamed repository/) { - $desc = "$default_desc [epoch $epoch]" if defined($epoch); - } - - my $reference; - chomp(my $alt = try_cat("$git_dir/objects/info/alternates")); - if ($alt) { - # n.b.: GitPython doesn't seem to handle comments or C-quoted - # strings like native git does; and we don't for now, either. - my @alt = split(/\n+/, $alt); - - # grokmirror only supports 1 alternate for "reference", - if (scalar(@alt) == 1) { - my $objdir = "$git_dir/objects"; - $reference = File::Spec->rel2abs($alt[0], $objdir); - $reference =~ s!/[^/]+/?\z!!; # basename - } - } - $ctx->{-abs2urlpath}->{$git_dir} = $url_path; - my $modified = $git->modified; - if ($modified > ($ctx->{-mtime} // 0)) { - $ctx->{-mtime} = $modified; - } - $ctx->{manifest}->{$url_path} = { - owner => $owner, - reference => $reference, - description => $desc, - modified => $modified, - fingerprint => $fingerprint, - }; + my $ent = $git->manifest_entry($epoch, $default_desc) or return; + inject_entry($ctx, $url_path, $ent, $git->{git_dir}); } -sub ibx_entry { +sub slow_manifest_add ($$) { my ($ctx, $ibx) = @_; eval { if (defined(my $max = $ibx->max_git_epoch)) { @@ -110,9 +56,46 @@ sub ibx_entry { warn "E: $@" if $@; } -sub hide_key { 'manifest' } +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; + $ALL ? eidx_manifest_add($ctx, $ALL, $ibx) : + slow_manifest_add($ctx, $ibx); +} + +sub hide_key { 'manifest' } # for WwwListing->list_match_i -# overrides WwwListing->psgi_triple sub psgi_triple { my ($ctx) = @_; my $abs2urlpath = delete($ctx->{-abs2urlpath}) // {}; @@ -125,7 +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;