diff options
author | Eric Wong <e@80x24.org> | 2020-11-29 05:09:35 +0000 |
---|---|---|
committer | Eric Wong <e@80x24.org> | 2020-11-29 06:42:00 +0000 |
commit | ea885bf0f76dc1795dc771667be721ec0fed5482 (patch) | |
tree | 5323da5926b6aa4c20619e2a05805f581722a389 /script | |
parent | 33f80a367325f3dac983633cb0a59946205776c2 (diff) | |
download | public-inbox-ea885bf0f76dc1795dc771667be721ec0fed5482.tar.gz |
Inboxes may be removed or newsgroups renamed over time. Introduce a switch to do garbage collection and eliminate stale search and xref3 results based on inboxes which remain in the config file. This may also fixup stale results leftover from any bugs which may leave stale data around. This is also useful in case a clumsy BOFH (me :P) is swapping between several PI_CONFIGs and accidentally indexed a bunch of inboxes they didn't intend to.
Diffstat (limited to 'script')
-rw-r--r-- | script/public-inbox-extindex | 19 |
1 files changed, 16 insertions, 3 deletions
diff --git a/script/public-inbox-extindex b/script/public-inbox-extindex index 20a0737c..17ad59fa 100644 --- a/script/public-inbox-extindex +++ b/script/public-inbox-extindex @@ -16,6 +16,7 @@ usage: public-inbox-extindex [options] EXTINDEX_DIR [INBOX_DIR] --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 + --gc perform garbage collection instead of indexing --verbose | -v increase verbosity (may be repeated) BYTES may use `k', `m', and `g' suffixes (e.g. `10m' for 10 megabytes) @@ -26,6 +27,7 @@ GetOptions($opt, qw(verbose|v+ reindex rethread compact|c+ jobs|j=i fsync|sync! indexlevel|index-level|L=s max_size|max-size=s batch_size|batch-size=s + gc all help|h)) or die $help; if ($opt->{help}) { print $help; exit 0 }; @@ -36,7 +38,13 @@ my $eidx_dir = shift(@ARGV) // die "E: $help"; local $SIG{USR1} = 'IGNORE'; # to be overridden in eidx_sync require PublicInbox::Admin; my $cfg = PublicInbox::Config->new; -my @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg); +my @ibxs; +if ($opt->{gc}) { + die "E: inbox paths must not be specified with --gc\n" if @ARGV; + die "E: --all not compatible --gc\n" if $opt->{all}; +} else { + @ibxs = PublicInbox::Admin::resolve_inboxes(\@ARGV, $opt, $cfg); +} PublicInbox::Admin::require_or_die(qw(-search)); PublicInbox::Config::json() or die "Cpanel::JSON::XS or similar missing\n"; PublicInbox::Admin::progress_prepare($opt); @@ -44,5 +52,10 @@ my $env = PublicInbox::Admin::index_prepare($opt, $cfg); local %ENV = (%ENV, %$env) if $env; require PublicInbox::ExtSearchIdx; my $eidx = PublicInbox::ExtSearchIdx->new($eidx_dir, $opt); -$eidx->attach_inbox($_) for @ibxs; -$eidx->eidx_sync($opt); +if ($opt->{gc}) { + $eidx->attach_config($cfg); + $eidx->eidx_gc($opt); +} else { + $eidx->attach_inbox($_) for @ibxs; + $eidx->eidx_sync($opt); +} |