user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 30/52] extsearchidx: more compatibility with V2Writable callers
Date: Tue, 27 Oct 2020 07:54:31 +0000	[thread overview]
Message-ID: <20201027075453.19163-31-e@80x24.org> (raw)
In-Reply-To: <20201027075453.19163-1-e@80x24.org>

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;

  parent reply	other threads:[~2020-10-27  7:54 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-27  7:54 [PATCH 00/52] detached external index: mostly Eric Wong
2020-10-27  7:54 ` [PATCH 01/52] doc/standards: add RFCs for URL schemes Eric Wong
2020-11-05  7:54   ` [PATCH v2] " Eric Wong
2020-10-27  7:54 ` [PATCH 02/52] search: hoist out _xdb_sharded for v2 inboxes Eric Wong
2020-10-27  7:54 ` [PATCH 03/52] extsearch: start mocking out Eric Wong
2020-10-27  7:54 ` [PATCH 04/52] searchidx: expose INDEXLEVELS as `our' Eric Wong
2020-10-27  7:54 ` [PATCH 05/52] v2writable: add git method Eric Wong
2020-10-27  7:54 ` [PATCH 06/52] v2writable: make OO calls to last_commit-related methods Eric Wong
2020-10-27  7:54 ` [PATCH 07/52] search: xdb_sharded: make this a public method for ExtSearch Eric Wong
2020-10-27  7:54 ` [PATCH 08/52] searchidx: introduce "xref3" concept Eric Wong
2020-10-27  7:54 ` [PATCH 09/52] v2writable: prepare initialization for external indices Eric Wong
2020-10-27  7:54 ` [PATCH 10/52] v2writable: hoist out write_alternates Eric Wong
2020-10-27  7:54 ` [PATCH 11/52] searchidxshard: allow msgref to be undef Eric Wong
2020-10-27  7:54 ` [PATCH 12/52] v2writable: idx_shard: simplify callers Eric Wong
2020-10-27  7:54 ` [PATCH 13/52] v2writable: count_shards: allow working without {ibx} Eric Wong
2020-10-27  7:54 ` [PATCH 14/52] overidx: introduce changes for external index Eric Wong
2020-10-27  7:54 ` [PATCH 15/52] v2: some changes for ExtSearchIdx compatibility Eric Wong
2020-10-27  7:54 ` [PATCH 16/52] inboxwritable: eidx_key for external index Eric Wong
2020-10-27  7:54 ` [PATCH 17/52] v2writable: rename remaining "remote" terminology Eric Wong
2020-10-27  7:54 ` [PATCH 18/52] v2writable: checkpoint: account for lack of {mm} Eric Wong
2020-10-27  7:54 ` [PATCH 19/52] extsearchidx: initial implementation Eric Wong
2020-10-27  7:54 ` [PATCH 20/52] searchidx: index eidx_key as a boolean term Eric Wong
2020-10-27  7:54 ` [PATCH 21/52] searchidx: xref3 delete support Eric Wong
2020-10-27  7:54 ` [PATCH 22/52] searchidxshard: special init for eidx Eric Wong
2020-10-27  7:54 ` [PATCH 23/52] searchidx: put {ibx} into $sync state Eric Wong
2020-10-27  7:54 ` [PATCH 24/52] searchidx: log2stack: simplify callers Eric Wong
2020-10-27  7:54 ` [PATCH 25/52] v2writable: more generic sync setup code Eric Wong
2020-10-27  7:54 ` [PATCH 26/52] v2writable: allow OO method references Eric Wong
2020-10-27  7:54 ` [PATCH 27/52] v2writable: rename {v2w} field to {self} Eric Wong
2020-10-27  7:54 ` [PATCH 28/52] v2writable: make *last_commits and sync_prepare OO methods Eric Wong
2020-10-27  7:54 ` [PATCH 29/52] v2writable: move size check init to sync_prepare Eric Wong
2020-10-27  7:54 ` Eric Wong [this message]
2020-10-27  7:54 ` [PATCH 31/52] v2writable: reduce scope of epoch-aware code Eric Wong
2020-10-27  7:54 ` [PATCH 32/52] extsearchidx: remove {unindex_range} field Eric Wong
2020-10-27  7:54 ` [PATCH 33/52] v2writable: pass oid to uindex_oid Eric Wong
2020-10-27  7:54 ` [PATCH 34/52] extsearchidx: sync unit updates Eric Wong
2020-10-27  7:54 ` [PATCH 35/52] searchidx: export prepare_stack Eric Wong
2020-10-27  7:54 ` [PATCH 36/52] extsearchidx: sync updates Eric Wong
2020-10-27  7:54 ` [PATCH 37/52] searchidx: reduce inbox-dependency, wrap ->with_umask Eric Wong
2020-10-27  7:54 ` [PATCH 38/52] searchidx: favor $sync->{ibx} (over $self->{ibx}) Eric Wong
2020-10-27  7:54 ` [PATCH 39/52] Makefile.PL: do not build manpage if POD is missing Eric Wong
2020-10-27  7:54 ` [PATCH 40/52] script: add preliminary eindex implementation Eric Wong
2020-10-27  7:54 ` [PATCH 41/52] index: eindex wiring Eric Wong
2020-10-27  7:54 ` [PATCH 42/52] over: store xref3 data in over.sqlite3 Eric Wong
2020-10-27  7:54 ` [PATCH 43/52] searchidx: remove xref3 support for Xapian Eric Wong
2020-10-27  7:54 ` [PATCH 44/52] t/extsearch.t: verify results and xref3 ordering Eric Wong
2020-10-27  7:54 ` [PATCH 45/52] t/v2writable: remove pointless ->barrier call Eric Wong
2020-10-27  7:54 ` [PATCH 46/52] extsearch: wire up smsg_eml Eric Wong
2020-10-27  7:54 ` [PATCH 47/52] extsearchidx: handle edits Eric Wong
2020-10-27  7:54 ` [PATCH 48/52] extsearch: wire up remaining Inbox-like methods for WWW Eric Wong
2020-10-27  7:54 ` [PATCH 49/52] searchidx: ignore exceptions from ->remove_term Eric Wong
2020-10-27  7:54 ` [PATCH 50/52] extsearchidx: set current_info in warning callbacks Eric Wong
2020-10-27  7:54 ` [PATCH 51/52] extsearchidx: support --batch-size checkpoints Eric Wong
2020-11-03  9:08   ` Eric Wong
2020-10-27  7:54 ` [PATCH 52/52] searchidxshard: make warnings with eidx_key less confusing Eric Wong
2020-10-27 12:08 ` [PATCH 00/52] detached external index: mostly Konstantin Ryabitsev
2020-11-10 18:53 ` detached external index: performance note Eric Wong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://public-inbox.org/README

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201027075453.19163-31-e@80x24.org \
    --to=e@80x24.org \
    --cc=meta@public-inbox.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).