X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=5dad6ecb5dfb5bb1d47552736aa143e3875a1471;hb=16870b42ac68a8704467989cb20c2c571e4749ab;hp=9399c272a1b25f2a66b06c4abfc535d52fe81238;hpb=d537fa4148134fe45595305a7398895682f43c96;p=public-inbox.git diff --git a/script/public-inbox-index b/script/public-inbox-index index 9399c272..5dad6ecb 100755 --- a/script/public-inbox-index +++ b/script/public-inbox-index @@ -1,77 +1,96 @@ -#!/usr/bin/perl -w -# Copyright (C) 2015-2019 all contributors +#!perl -w +# Copyright (C) 2015-2020 all contributors # License: AGPL-3.0+ -# Basic tool to create a Xapian search index for a git repository -# configured for public-inbox. +# Basic tool to create a Xapian search index for a public-inbox. # Usage with libeatmydata -# highly recommended: eatmydata public-inbox-index REPO_DIR +# highly recommended: eatmydata public-inbox-index INBOX_DIR use strict; -use warnings; +use v5.10.1; use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev); -my $usage = "public-inbox-index REPO_DIR"; -use PublicInbox::Admin; -PublicInbox::Admin::require_or_die('-index'); +my $help = < \$reindex, - '--jobs|j=i' => \$jobs, - '--prune' => \$prune, - 'L|indexlevel=s' => \$indexlevel, -); -GetOptions(%opts) or die "bad command-line args\n$usage"; -die "--jobs must be positive\n" if defined $jobs && $jobs < 0; + --no-fsync speed up indexing, risk corruption on power outage + -L LEVEL `basic', `medium', or `full' (default: full) + --all index all configured inboxes + --compact | -c run public-inbox-compact(1) after indexing + --sequential-shard index Xapian shards sequentially for slow storage + --jobs=NUM set or disable parallelization (NUM=0) + --batch-size=BYTES flush changes to OS after a given number of bytes + --max-size=BYTES do not index messages larger than the given size + --reindex index previously indexed data (if upgrading) + --rethread regenerate thread IDs (if upgrading, use sparingly) + --prune prune git storage on discontiguous history + --verbose | -v increase verbosity (may be repeated) -sub usage { print STDERR "Usage: $usage\n"; exit 1 } +BYTES may use `k', `m', and `g' suffixes (e.g. `10m' for 10 megabytes) +See public-inbox-index(1) man page for full documentation. +EOF +my $opt = { quiet => -1, compact => 0, max_size => undef, fsync => 1 }; +GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune + fsync|sync! xapian_only|xapian-only + indexlevel|index-level|L=s max_size|max-size=s + batch_size|batch-size=s + sequential_shard|seq-shard|sequential-shard + skip-docdata all help|h)) + or die $help; +if ($opt->{help}) { print $help; exit 0 }; +die "--jobs must be >= 0\n" if defined $opt->{jobs} && $opt->{jobs} < 0; +if ($opt->{xapian_only} && !$opt->{reindex}) { + die "--xapian-only requires --reindex\n"; +} + +# require lazily to speed up --help +require PublicInbox::Admin; +PublicInbox::Admin::require_or_die('-index'); -# do we really care about this message? It's annoying... -my $warn = 'public-inbox unconfigured for serving, indexing anyways...'; -my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $warn); +my $cfg = PublicInbox::Config->new; # Config is loaded by Admin +my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg); PublicInbox::Admin::require_or_die('-index'); -usage() unless @ibxs; +unless (@ibxs) { print STDERR $help; exit 1 } + my $mods = {}; foreach my $ibx (@ibxs) { - if (defined $indexlevel && !defined($ibx->{indexlevel})) { - # XXX: users can shoot themselves in the foot, with this... - $ibx->{indexlevel} = $indexlevel; - } + # detect_indexlevel may also set $ibx->{-skip_docdata} + my $detected = PublicInbox::Admin::detect_indexlevel($ibx); + # XXX: users can shoot themselves in the foot, with opt->{indexlevel} + $ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapian_only} ? + 'full' : $detected); PublicInbox::Admin::scan_ibx_modules($mods, $ibx); } -PublicInbox::Admin::require_or_die(keys %$mods); +# "Search::Xapian" includes SWIG "Xapian", too: +$opt->{compact} = 0 if !$mods->{'Search::Xapian'}; -require PublicInbox::SearchIdx; -index_inbox($_) for @ibxs; +PublicInbox::Admin::require_or_die(keys %$mods); +my $env = PublicInbox::Admin::index_prepare($opt, $cfg); +local %ENV = (%ENV, %$env) if $env; +require PublicInbox::InboxWritable; +PublicInbox::Xapcmd::check_compact() if $opt->{compact}; +PublicInbox::Admin::progress_prepare($opt); +for my $ibx (@ibxs) { + $ibx = PublicInbox::InboxWritable->new($ibx); + if ($opt->{compact} >= 2) { + PublicInbox::Xapcmd::run($ibx, 'compact', $opt->{compact_opt}); + } + $ibx->{-no_fsync} = 1 if !$opt->{fsync}; + $ibx->{-skip_docdata} //= $opt->{'skip-docdata'}; -sub index_inbox { - my ($repo) = @_; - if (ref($repo) && ($repo->{version} || 1) == 2) { - eval { require PublicInbox::V2Writable }; - die "v2 requirements not met: $@\n" if $@; - my $v2w = eval { - PublicInbox::V2Writable->new($repo, {nproc=>$jobs}); - }; - if (defined $jobs) { - if ($jobs == 0) { - $v2w->{parallel} = 0; - } else { - my $n = $v2w->{partitions}; - if ($jobs != ($n + 1)) { - warn -"Unable to respect --jobs=$jobs, inbox was created with $n partitions\n"; - } - } - } - local $SIG{__WARN__} = sub { - print STDERR $v2w->{current_info}, ': ', @_; - }; - $v2w->index_sync({ reindex => $reindex, prune => $prune }); - } else { - my $s = PublicInbox::SearchIdx->new($repo, 1); - $s->index_sync({ reindex => $reindex }); + my $ibx_opt = $opt; + if (defined(my $s = $ibx->{lc('indexSequentialShard')})) { + defined(my $v = $cfg->git_bool($s)) or die <{name}.indexSequentialShard not boolean +EOL + $ibx_opt = { %$opt, sequential_shard => $v }; + } + PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt); + if (my $copt = $opt->{compact_opt}) { + local $copt->{jobs} = 0 if $ibx_opt->{sequential_shard}; + PublicInbox::Xapcmd::run($ibx, 'compact', $copt); } }