* [PATCH 30/52] extsearchidx: more compatibility with V2Writable callers
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
We'll use `index_oid' and `unindex_oid' as our method names
so V2Writable methods may use `$self->can' to access them.
---
lib/PublicInbox/ExtSearchIdx.pm | 64 +++++++++++++++++----------------
1 file changed, 34 insertions(+), 30 deletions(-)
diff --git a/lib/PublicInbox/ExtSearchIdx.pm b/lib/PublicInbox/ExtSearchIdx.pm
index edf17974..609151e4 100644
--- a/lib/PublicInbox/ExtSearchIdx.pm
+++ b/lib/PublicInbox/ExtSearchIdx.pm
@@ -105,11 +105,11 @@ sub is_bad_blob ($$$$) {
sub do_xpost ($$) {
my ($req, $smsg) = @_;
- my $self = $req->{eidx};
+ my $self = $req->{self};
my $docid = $smsg->{num};
my $idx = $self->idx_shard($docid);
my $oid = $req->{oid};
- my $xibx = $self->{sync}->{ibx};
+ my $xibx = $req->{ibx};
my $eml = $req->{eml};
if (my $new_smsg = $req->{new_smsg}) { # 'm' on cross-posted message
my $xnum = $req->{xnum};
@@ -119,17 +119,20 @@ sub do_xpost ($$) {
}
}
+# called by V2Writable::sync_prepare
+sub artnum_max { $_[0]->{oidx}->get_counter('eidx_docid') }
+
sub index_unseen ($) {
my ($req) = @_;
my $new_smsg = $req->{new_smsg} or die 'BUG: {new_smsg} unset';
- $new_smsg->populate($req->{eml}, $req);
- my $self = $req->{eidx};
+ my $eml = delete $req->{eml};
+ $new_smsg->populate($eml, $req);
+ my $self = $req->{self};
my $docid = $self->{oidx}->adj_counter('eidx_docid', '+');
$new_smsg->{num} = $docid;
my $idx = $self->idx_shard($docid);
- my $eml = delete $req->{eml};
$self->{oidx}->add_overview($eml, $new_smsg);
- $idx->index_raw(undef, $eml, $new_smsg, delete $new_smsg->{ibx});
+ $idx->index_raw(undef, $eml, $new_smsg, $req->{ibx});
}
sub do_finalize ($) {
@@ -145,7 +148,7 @@ sub do_finalize ($) {
sub do_step ($) { # main iterator for adding messages to the index
my ($req) = @_;
- my $self = $req->{eidx};
+ my $self = $req->{self};
while (1) {
if (my $next_arg = $req->{next_arg}) {
if (my $smsg = $self->{oidx}->next_by_mid(@$next_arg)) {
@@ -181,7 +184,7 @@ sub ck_existing { # git->cat_async callback
# return the number if so
sub cur_ibx_xnum ($$) {
my ($req, $bref) = @_;
- my $ibx = $req->{sync}->{ibx} or die 'BUG: current {ibx} missing';
+ my $ibx = $req->{ibx} or die 'BUG: current {ibx} missing';
# XXX overkill?
git_blob_digest($bref)->hexdigest eq $req->{oid} or die
@@ -200,31 +203,34 @@ sub cur_ibx_xnum ($$) {
undef;
}
-sub m_start { # git->cat_async callback for 'm'
+sub index_oid { # git->cat_async callback for 'm'
my ($bref, $oid, $type, $size, $req) = @_;
return if is_bad_blob($oid, $type, $size, $req->{oid});
my $new_smsg = $req->{new_smsg} = bless {
blob => $oid,
- raw_bytes => $size,
}, 'PublicInbox::Smsg';
- $new_smsg->{bytes} = $new_smsg->{raw_bytes} + crlf_adjust($$bref);
+ $new_smsg->{bytes} = $size + crlf_adjust($$bref);
defined($req->{xnum} = cur_ibx_xnum($req, $bref)) or return;
- $new_smsg->{ibx} = $req->{sync}->{ibx};
do_step($req);
}
-sub d_start { # git->cat_async callback for 'd'
+sub unindex_oid { # git->cat_async callback for 'd'
my ($bref, $oid, $type, $size, $req) = @_;
return if is_bad_blob($oid, $type, $size, $req->{oid});
return if defined(cur_ibx_xnum($req, $bref)); # was re-added
do_step($req);
}
-sub eidx_last_epoch_commit ($$$) {
- my ($self, $sync, $epoch) = @_;
- my $key = $sync->{ibx}->eidx_key;
- my $uidvalidity = $sync->{ibx}->uidvalidity;
- $self->{oidx}->eidx_meta("lc-v2:$key//$uidvalidity;$epoch");
+# overrides V2Writable::last_commits, called by sync_ranges via sync_prepare
+sub last_commits {
+ my ($self, $sync) = @_;
+ my $heads = [];
+ my $ekey = $sync->{ibx}->eidx_key;
+ my $uv = $sync->{ibx}->uidvalidity;
+ for my $i (0..$sync->{epoch_max}) {
+ $heads->[$i] = $self->{oidx}->eidx_meta("lc-v2:$ekey//$uv;$i");
+ }
+ $heads;
}
sub _sync_inbox ($$$) {
@@ -234,27 +240,23 @@ sub _sync_inbox ($$$) {
unindex_range => {}, # EPOCH => oid_old..oid_new
reindex => $opt->{reindex},
-opt => $opt,
- eidx => $self,
+ self => $self,
ibx => $ibx,
};
- my $key = $ibx->eidx_key;
- my $u = $ibx->uidvalidity;
- my $oidx = $self->{oidx};
my $v = $ibx->version;
+ my $ekey = $ibx->eidx_key;
if ($v == 2) {
my $epoch_max;
defined($ibx->git_dir_latest(\$epoch_max)) or return;
- my $heads = $sync->{ranges} = [];
- for my $i (0..$epoch_max) {
- $heads->[$i] = $oidx->eidx_meta("lc-v2:$key//$u;$i");
- }
-
-
+ $sync->{epoch_max} = $epoch_max;
+ sync_prepare($self, $sync) or return;
+ index_epoch($self, $sync, $_) for (0..$epoch_max);
} elsif ($v == 1) {
- my $lc = $oidx->eidx_meta("lc-v1:$key//$u");
+ my $uv = $ibx->uidvalidity;
+ my $lc = $self->{oidx}->eidx_meta("lc-v1:$ekey//$uv");
prepare_stack($sync, $lc ? "$lc..HEAD" : 'HEAD');
} else {
- warn "E: $key unsupported inbox version (v$v)\n";
+ warn "E: $ekey unsupported inbox version (v$v)\n";
return;
}
}
@@ -307,5 +309,7 @@ no warnings 'once';
*with_umask = \&PublicInbox::InboxWritable::with_umask;
*parallel_init = \&PublicInbox::V2Writable::parallel_init;
*nproc_shards = \&PublicInbox::V2Writable::nproc_shards;
+*sync_prepare = \&PublicInbox::V2Writable::sync_prepare;
+*index_epoch = \&PublicInbox::V2Writable::index_epoch;
1;
^ 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 30/52] extsearchidx: more compatibility with V2Writable callers 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 30/52] extsearchidx: more compatibility with V2Writable callers 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).