X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=script%2Fpublic-inbox-index;h=5dad6ecb5dfb5bb1d47552736aa143e3875a1471;hb=16870b42ac68a8704467989cb20c2c571e4749ab;hp=be518134ceb29d8a2dbad565f1e7f1e983325641;hpb=06a2418fd053c9a5b80217e74d1b47b8e1ca85e1;p=public-inbox.git diff --git a/script/public-inbox-index b/script/public-inbox-index index be518134..5dad6ecb 100755 --- a/script/public-inbox-index +++ b/script/public-inbox-index @@ -1,4 +1,4 @@ -#!/usr/bin/perl -w +#!perl -w # Copyright (C) 2015-2020 all contributors # License: AGPL-3.0+ # Basic tool to create a Xapian search index for a public-inbox. @@ -6,81 +6,91 @@ # 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 $help = < -1, compact => 0, maxsize => undef, sync => 1 }; -GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i prune sync! - indexlevel|L=s maxsize|max-size=s batchsize|batch-size=s - sequentialshard|seq-shard|sequential-shard)) - or die "bad command-line args\n$usage"; -die "--jobs must be >= 0\n" if defined $opt->{jobs} && $opt->{jobs} < 0; + Create and update search indices -if ($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; - } -} +options: -my $cfg = PublicInbox::Config->new; -my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, undef, $cfg); -PublicInbox::Admin::require_or_die('-index'); -unless (@ibxs) { print STDERR "Usage: $usage\n"; exit 1 } + --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) -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"; +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"; } -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; -} +# require lazily to speed up --help +require PublicInbox::Admin; +PublicInbox::Admin::require_or_die('-index'); -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; -} +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'); +unless (@ibxs) { print STDERR $help; exit 1 } my $mods = {}; 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} //= $opt->{indexlevel} // - PublicInbox::Admin::detect_indexlevel($ibx); - $ibx->{index_max_size} = $max_size; + $ibx->{indexlevel} //= $opt->{indexlevel} // ($opt->{xapian_only} ? + 'full' : $detected); PublicInbox::Admin::scan_ibx_modules($mods, $ibx); } +# "Search::Xapian" includes SWIG "Xapian", too: +$opt->{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}); } - $ibx->{-no_sync} = 1 if !$opt->{sync}; + $ibx->{-no_fsync} = 1 if !$opt->{fsync}; + $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, $ibx_opt); - PublicInbox::Xapcmd::run($ibx, 'compact', $compact_opt) if $compact_opt; + if (my $copt = $opt->{compact_opt}) { + local $copt->{jobs} = 0 if $ibx_opt->{sequential_shard}; + PublicInbox::Xapcmd::run($ibx, 'compact', $copt); + } }