* [PATCH 16/52] inboxwritable: eidx_key for external index
2020-10-27 7:54 7% [PATCH 00/52] detached external index: mostly Eric Wong
@ 2020-10-27 7:54 5% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-10-27 7:54 UTC (permalink / raw)
To: meta
This is preferable to open-coding "newsgroup // inboxdir" everywhere.
---
lib/PublicInbox/InboxWritable.pm | 2 ++
lib/PublicInbox/SearchIdx.pm | 12 ++++++------
lib/PublicInbox/SearchIdxShard.pm | 32 ++++++++++++++++++++-----------
3 files changed, 29 insertions(+), 17 deletions(-)
diff --git a/lib/PublicInbox/InboxWritable.pm b/lib/PublicInbox/InboxWritable.pm
index e97c7e2d..d3c255c7 100644
--- a/lib/PublicInbox/InboxWritable.pm
+++ b/lib/PublicInbox/InboxWritable.pm
@@ -319,4 +319,6 @@ sub git_dir_latest {
$latest;
}
+sub eidx_key { $_[0]->{newsgroup} // $_[0]->{inboxdir} }
+
1;
diff --git a/lib/PublicInbox/SearchIdx.pm b/lib/PublicInbox/SearchIdx.pm
index 283bdd6c..061a8153 100644
--- a/lib/PublicInbox/SearchIdx.pm
+++ b/lib/PublicInbox/SearchIdx.pm
@@ -368,9 +368,9 @@ sub add_xapian ($$$$) {
$tg->set_document($doc);
index_headers($self, $smsg);
- if (my $ng_or_dir = $self->{ng_or_dir}) { # external index
+ if (defined(my $eidx_key = $smsg->{eidx_key})) {
$doc->add_boolean_term('P'.
- "$ng_or_dir:$smsg->{num}:$smsg->{blob}");
+ "$eidx_key:$smsg->{num}:$smsg->{blob}");
}
msg_iter($eml, \&index_xapian, [ $self, $doc ]);
index_ids($self, $doc, $eml, $mids);
@@ -456,21 +456,21 @@ sub _get_doc ($$$) {
}
sub add_xref3 {
- my ($self, $docid, $xnum, $oid, $ng_or_dir, $eml) = @_;
+ my ($self, $docid, $xnum, $oid, $eidx_key, $eml) = @_;
begin_txn_lazy($self);
my $doc = _get_doc($self, $docid, $oid) or return;
term_generator($self)->set_document($doc);
- $doc->add_boolean_term('P'."$ng_or_dir:$xnum:$oid");
+ $doc->add_boolean_term('P'."$eidx_key:$xnum:$oid");
index_list_id($self, $doc, $eml);
$self->{xdb}->replace_document($docid, $doc);
}
sub remove_xref3 {
- my ($self, $docid, $oid, $ng_or_dir, $eml) = @_;
+ my ($self, $docid, $oid, $eidx_key, $eml) = @_;
begin_txn_lazy($self);
my $doc = _get_doc($self, $docid, $oid) or return;
my $xref3 = PublicInbox::Smsg::xref3(undef, $doc);
- for (grep(/\A\Q$ng_or_dir\E:[0-9]+:\Q$oid\E\z/, @$xref3)) {
+ for (grep(/\A\Q$eidx_key\E:[0-9]+:\Q$oid\E\z/, @$xref3)) {
$doc->remove_term('P' . $_);
}
for my $l ($eml->header_raw('List-Id')) {
diff --git a/lib/PublicInbox/SearchIdxShard.pm b/lib/PublicInbox/SearchIdxShard.pm
index 8ff9ab8b..fa77a9f9 100644
--- a/lib/PublicInbox/SearchIdxShard.pm
+++ b/lib/PublicInbox/SearchIdxShard.pm
@@ -74,17 +74,21 @@ sub shard_worker_loop ($$$$$) {
} elsif ($line =~ /\AD ([a-f0-9]{40,}) ([0-9]+)\n\z/s) {
$self->remove_by_oid($1, $2 + 0);
} elsif ($line =~ s/\A\+X //) {
- my ($len, $docid, $xnum, $oid, $ng_or_dir) =
+ my ($len, $docid, $xnum, $oid, $eidx_key) =
split(/ /, $line, 5);
- $self->add_xref3($docid, $xnum, $oid, $ng_or_dir,
+ $self->add_xref3($docid, $xnum, $oid, $eidx_key,
eml($r, $len));
} elsif ($line =~ s/\A-X //) {
- my ($len, $docid, $xnum, $oid, $ng_or_dir) =
+ my ($len, $docid, $xnum, $oid, $eidx_key) =
split(/ /, $line, 5);
$self->remove_xref3($docid, $xnum, $oid,
- $ng_or_dir, eml($r, $len));
+ $eidx_key, eml($r, $len));
} else {
chomp $line;
+ my $eidx_key;
+ if ($line =~ s/\AX(.+)\0//) {
+ $eidx_key = $1;
+ }
# n.b. $mid may contain spaces(!)
my ($len, $bytes, $num, $oid, $ds, $ts, $tid, $mid)
= split(/ /, $line, 8);
@@ -98,6 +102,7 @@ sub shard_worker_loop ($$$$$) {
ds => $ds,
ts => $ts,
}, 'PublicInbox::Smsg';
+ $smsg->{eidx_key} = $eidx_key if defined($eidx_key);
$self->add_message(eml($r, $len), $smsg);
}
}
@@ -105,8 +110,12 @@ sub shard_worker_loop ($$$$$) {
}
sub index_raw {
- my ($self, $msgref, $eml, $smsg) = @_;
+ my ($self, $msgref, $eml, $smsg, $ibx) = @_;
if (my $w = $self->{w}) {
+ if ($ibx) {
+ print $w 'X', $ibx->eidx_key, "\0" or die
+ "failed to write shard: $!\n";
+ }
$msgref //= \($eml->as_string);
$smsg->{raw_bytes} //= length($$msgref);
# mid must be last, it can contain spaces (but not LF)
@@ -120,33 +129,34 @@ sub index_raw {
$eml = PublicInbox::Eml->new($msgref);
}
$self->begin_txn_lazy;
+ $smsg->{eidx_key} = $ibx->eidx_key if $ibx;
$self->add_message($eml, $smsg);
}
}
sub shard_add_xref3 {
my ($self, $docid, $xnum, $oid, $xibx, $eml) = @_;
- my $ng_or_dir = $xibx->{newsgroup} // $xibx->{inboxdir};
+ my $eidx_key = $xibx->eidx_key;
if (my $w = $self->{w}) {
my $hdr = $eml->header_obj->as_string;
my $len = length($hdr);
- print $w "+X $len $docid $xnum $oid $ng_or_dir\n", $hdr or
+ print $w "+X $len $docid $xnum $oid $eidx_key\n", $hdr or
die "failed to write shard: $!";
} else {
- $self->add_xref3($docid, $xnum, $oid, $ng_or_dir, $eml);
+ $self->add_xref3($docid, $xnum, $oid, $eidx_key, $eml);
}
}
sub shard_remove_xref3 {
my ($self, $docid, $oid, $xibx, $eml) = @_;
- my $ng_or_dir = $xibx->{newsgroup} // $xibx->{inboxdir};
+ my $eidx_key = $xibx->eidx_key;
if (my $w = $self->{w}) {
my $hdr = $eml->header_obj->as_string;
my $len = length($hdr);
- print $w "-X $len $docid $oid $ng_or_dir\n", $hdr or
+ print $w "-X $len $docid $oid $eidx_key\n", $hdr or
die "failed to write shard: $!";
} else {
- $self->remove_xref3($docid, $oid, $ng_or_dir, $eml);
+ $self->remove_xref3($docid, $oid, $eidx_key, $eml);
}
}
^ permalink raw reply related [relevance 5%]
* [PATCH 00/52] detached external index: mostly
@ 2020-10-27 7:54 7% Eric Wong
2020-10-27 7:54 5% ` [PATCH 16/52] inboxwritable: eidx_key for external index Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-10-27 7:54 UTC (permalink / raw)
To: meta
...and mostly wired up for WWW, but requires manual config
editing atm. Needs docs and tests, and IMAP support.
This will also form the basis of a mairix workalike client.
Not sure about the usability aspects, but I think this can
replace the need for per-inbox Xapian DBs and save a truckload
of disk space (and more importantly: cache space). Per-inbox
over.sqlite3 remains required for compatibility with NNTP/IMAP
and existing WWW code.
I don't know if the command-line tool is going to be called
public-inbox-eindex or public-inbox-extindex, but probably the
latter...
"xindex" could be confusing, and "eindex" rhymes with "reindex"
which could also be confusing. But I'm even more easily
confused than usual these days :x
Performance isn't great, it took 30+ hours to index my mirror of
lore on a SATA SSD, but the entire index is <200GB due to
deduplication between cross posts. -compact isn't working with
these indices, yet, but will sometime...
More changes on the way, still trying fix my brain and get
through this year...
Eric Wong (52):
doc/standards: add RFCs for URL schemes
search: hoist out _xdb_sharded for v2 inboxes
extsearch: start mocking out
searchidx: expose INDEXLEVELS as `our'
v2writable: add git method
v2writable: make OO calls to last_commit-related methods
search: xdb_sharded: make this a public method for ExtSearch
searchidx: introduce "xref3" concept
v2writable: prepare initialization for external indices
v2writable: hoist out write_alternates
searchidxshard: allow msgref to be undef
v2writable: idx_shard: simplify callers
v2writable: count_shards: allow working without {ibx}
overidx: introduce changes for external index
v2: some changes for ExtSearchIdx compatibility
inboxwritable: eidx_key for external index
v2writable: rename remaining "remote" terminology
v2writable: checkpoint: account for lack of {mm}
extsearchidx: initial implementation
searchidx: index eidx_key as a boolean term
searchidx: xref3 delete support
searchidxshard: special init for eidx
searchidx: put {ibx} into $sync state
searchidx: log2stack: simplify callers
v2writable: more generic sync setup code
v2writable: allow OO method references
v2writable: rename {v2w} field to {self}
v2writable: make *last_commits and sync_prepare OO methods
v2writable: move size check init to sync_prepare
extsearchidx: more compatibility with V2Writable callers
v2writable: reduce scope of epoch-aware code
extsearchidx: remove {unindex_range} field
v2writable: pass oid to uindex_oid
extsearchidx: sync unit updates
searchidx: export prepare_stack
extsearchidx: sync updates
searchidx: reduce inbox-dependency, wrap ->with_umask
searchidx: favor $sync->{ibx} (over $self->{ibx})
Makefile.PL: do not build manpage if POD is missing
script: add preliminary eindex implementation
index: eindex wiring
over: store xref3 data in over.sqlite3
searchidx: remove xref3 support for Xapian
t/extsearch.t: verify results and xref3 ordering
t/v2writable: remove pointless ->barrier call
extsearch: wire up smsg_eml
extsearchidx: handle edits
extsearch: wire up remaining Inbox-like methods for WWW
searchidx: ignore exceptions from ->remove_term
extsearchidx: set current_info in warning callbacks
extsearchidx: support --batch-size checkpoints
searchidxshard: make warnings with eidx_key less confusing
Documentation/standards.perl | 3 +
MANIFEST | 4 +
Makefile.PL | 16 +-
lib/PublicInbox/Config.pm | 12 +
lib/PublicInbox/ExtSearch.pm | 69 +++++
lib/PublicInbox/ExtSearchIdx.pm | 404 ++++++++++++++++++++++++++++++
lib/PublicInbox/Inbox.pm | 53 ++--
lib/PublicInbox/InboxWritable.pm | 23 ++
lib/PublicInbox/Over.pm | 19 ++
lib/PublicInbox/OverIdx.pm | 122 ++++++++-
lib/PublicInbox/Search.pm | 62 ++---
lib/PublicInbox/SearchIdx.pm | 135 +++++++---
lib/PublicInbox/SearchIdxShard.pm | 77 +++++-
lib/PublicInbox/V2Writable.pm | 310 ++++++++++++-----------
lib/PublicInbox/WWW.pm | 3 +-
lib/PublicInbox/Xapcmd.pm | 2 +-
script/public-inbox-eindex | 43 ++++
script/public-inbox-index | 3 +-
t/extsearch.t | 75 ++++++
t/over.t | 24 ++
t/search.t | 2 -
t/v2writable.t | 3 +-
22 files changed, 1204 insertions(+), 260 deletions(-)
create mode 100644 lib/PublicInbox/ExtSearch.pm
create mode 100644 lib/PublicInbox/ExtSearchIdx.pm
create mode 100644 script/public-inbox-eindex
create mode 100644 t/extsearch.t
^ permalink raw reply [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2020-10-27 7:54 7% [PATCH 00/52] detached external index: mostly Eric Wong
2020-10-27 7:54 5% ` [PATCH 16/52] inboxwritable: eidx_key for external index Eric Wong
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).