X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=a04be9fcb4f18456777f3eb0e0295c9cd283ce96;hp=56df5bfec6faed0a9338c88cecf5230607dcf3a9;hb=refs%2Fheads%2Fmaster;hpb=8a66a8d396c6cff82e6041d107d7fb842db6d602 diff --git a/script/public-inbox-index b/script/public-inbox-index index 56df5bfe..a04be9fc 100755 --- a/script/public-inbox-index +++ b/script/public-inbox-index @@ -1,90 +1,156 @@ -#!/usr/bin/perl -w -# Copyright (C) 2015-2020 all contributors +#!perl -w +# Copyright (C) 2015-2021 all contributors # License: AGPL-3.0+ # Basic tool to create a Xapian search index for a public-inbox. # Usage with libeatmydata # 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 INBOX_DIR"; -use PublicInbox::Admin; -PublicInbox::Admin::require_or_die('-index'); -use PublicInbox::Xapcmd; +my $help = < -1, compact => 0, maxsize => undef, fsync => 1 }; + --no-fsync speed up indexing, risk corruption on power outage + -L LEVEL `basic', `medium', or `full' (default: full) + -E EXTINDEX update extindex (default: `all') + --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) + --since=DATE limit --reindex to changes after DATE + --until=DATE limit --reindex to changes before DATE + --rethread regenerate thread IDs (if upgrading, use sparingly) + --prune prune git storage on discontiguous history + --verbose | -v increase verbosity (may be repeated) + +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 $opt = { + quiet => -1, compact => 0, max_size => undef, fsync => 1, + 'update-extindex' => [], # ":s@" optional arg sets '' if no arg given +}; GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune - fsync|sync! xapianonly|xapian-only - indexlevel|L=s maxsize|max-size=s batchsize|batch-size=s - sequentialshard|seq-shard|sequential-shard)) - or die "bad command-line args\n$usage"; + fsync|sync! xapian_only|xapian-only dangerous + indexlevel|index-level|L=s max_size|max-size=s + batch_size|batch-size=s + since|after=s until|before=s + sequential-shard|seq-shard + no-update-extindex update-extindex|E=s@ + fast-noop|F skip-docdata all C=s@ 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->{compact}) { - require PublicInbox::Xapcmd; - PublicInbox::Xapcmd::check_compact(); - $compact_opt = { -coarse_lock => 1, compact => 1 }; - if (defined(my $jobs = $opt->{jobs})) { - $compact_opt->{jobs} = $jobs; - } +if ($opt->{xapian_only} && !$opt->{reindex}) { + die "--xapian-only requires --reindex\n"; +} +if ($opt->{reindex} && delete($opt->{'fast-noop'})) { + warn "--fast-noop ignored with --reindex\n"; } -my $cfg = PublicInbox::Config->new; -my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, undef, $cfg); +# require lazily to speed up --help +require PublicInbox::Admin; PublicInbox::Admin::require_or_die('-index'); -unless (@ibxs) { print STDERR "Usage: $usage\n"; exit 1 } +PublicInbox::Admin::do_chdir(delete $opt->{C}); -my $max_size = $opt->{maxsize} // $cfg->{lc('publicInbox.indexMaxSize')}; -if (defined $max_size) { - PublicInbox::Admin::parse_unsigned(\$max_size) or - die "`publicInbox.indexMaxSize=$max_size' not parsed\n"; -} +my $cfg = PublicInbox::Config->new; # Config is loaded by Admin +$opt->{-use_cwd} = 1; +my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg); +PublicInbox::Admin::require_or_die('-index'); +unless (@ibxs) { print STDERR $help; exit 1 } -if (my $bs = $opt->{batchsize} // $cfg->{lc('publicInbox.indexBatchSize')}) { - PublicInbox::Admin::parse_unsigned(\$bs) or - die "`publicInbox.indexBatchSize=$bs' not parsed\n"; - $PublicInbox::SearchIdx::BATCH_BYTES = $bs; +my (@eidx, %eidx_seen); +my $update_extindex = $opt->{'update-extindex'}; +if (!scalar(@$update_extindex) && (my $ALL = $cfg->ALL)) { + # extindex and normal inboxes may have different owners + push(@$update_extindex, 'all') if -w $ALL->{topdir}; } - -my $s = $opt->{sequentialshard} // - $cfg->{lc('publicInbox.indexSequentialShard')}; -if (defined $s) { - my $v = $cfg->git_bool($s); - defined($v) or - die "`publicInbox.indexSequentialShard=$s' not boolean\n"; - $opt->{sequentialshard} = $v; +@$update_extindex = () if $opt->{'no-update-extindex'}; +if (scalar @$update_extindex) { + PublicInbox::Admin::require_or_die('-search'); + require PublicInbox::ExtSearchIdx; +} +for my $ei_name (@$update_extindex) { + my $es = $cfg->lookup_ei($ei_name); + my $topdir; + if (!$es && -d $ei_name) { # allow dirname or config section name + $topdir = $ei_name; + } elsif ($es) { + $topdir = $es->{topdir}; + } else { + die "extindex `$ei_name' not configured or found\n"; + } + my $o = { %$opt }; + delete $o->{indexlevel} if ($o->{indexlevel}//'') eq 'basic'; + $eidx_seen{$topdir} //= + push(@eidx, PublicInbox::ExtSearchIdx->new($topdir, $o)); } - my $mods = {}; +my @eidx_unconfigured; foreach my $ibx (@ibxs) { + # 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->{xapianonly} ? - 'full' : PublicInbox::Admin::detect_indexlevel($ibx)); - $ibx->{index_max_size} = $max_size; + $ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapian_only} ? + 'full' : $detected); PublicInbox::Admin::scan_ibx_modules($mods, $ibx); + if (@eidx && $ibx->{-unconfigured}) { + push @eidx_unconfigured, " $ibx->{inboxdir}\n"; + } } +warn <{compact} = 0 if !$mods->{'Search::Xapian'}; 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', $compact_opt); + PublicInbox::Xapcmd::run($ibx, 'compact', $opt->{compact_opt}); } $ibx->{-no_fsync} = 1 if !$opt->{fsync}; + $ibx->{-dangerous} = 1 if $opt->{dangerous}; + $ibx->{-skip_docdata} //= $opt->{'skip-docdata'}; my $ibx_opt = $opt; - if (defined(my $s = $ibx->{indexsequentialshard})) { + if (defined(my $s = $ibx->{lc('indexSequentialShard')})) { defined(my $v = $cfg->git_bool($s)) or die <{name}.indexSequentialShard not boolean EOL - $ibx_opt = { %$opt, sequentialshard => $v }; + $ibx_opt = { %$opt, 'sequential-shard' => $v }; } - PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt); - if ($compact_opt) { - local $compact_opt->{jobs} = 0 if $ibx_opt->{sequentialshard}; - PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt); + my $nidx = PublicInbox::Admin::index_inbox($ibx, undef, $ibx_opt); + last if $ibx_opt->{quit}; + if (my $copt = $opt->{compact_opt}) { + local $copt->{jobs} = 0 if $ibx_opt->{'sequential-shard'}; + PublicInbox::Xapcmd::run($ibx, 'compact', $copt); } + last if $ibx_opt->{quit}; + next if $ibx->{-unconfigured} || !$nidx; + for my $eidx (@eidx) { + $eidx->attach_inbox($ibx); + } +} +my $pr = $opt->{-progress}; +for my $eidx (@eidx) { + $pr->("indexing $eidx->{topdir} ...\n") if $pr; + $eidx->eidx_sync($opt); + last if $opt->{quit}; }