unofficial mirror of meta@public-inbox.org
 help / color / mirror / Atom feed
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 15/52] v2: some changes for ExtSearchIdx compatibility
Date: Tue, 27 Oct 2020 07:54:16 +0000	[thread overview]
Message-ID: <20201027075453.19163-16-e@80x24.org> (raw)
In-Reply-To: <20201027075453.19163-1-e@80x24.org>

We'll be using per-sync-state {ibx} refs instead, so make parts
of the v2 indexing code less-dependent on $self->{ibx} where
$self is a V2Writable object.
---
 lib/PublicInbox/InboxWritable.pm | 21 ++++++++++++++
 lib/PublicInbox/V2Writable.pm    | 49 +++++++++++---------------------
 lib/PublicInbox/Xapcmd.pm        |  2 +-
 3 files changed, 38 insertions(+), 34 deletions(-)

diff --git a/lib/PublicInbox/InboxWritable.pm b/lib/PublicInbox/InboxWritable.pm
index 752f1997..e97c7e2d 100644
--- a/lib/PublicInbox/InboxWritable.pm
+++ b/lib/PublicInbox/InboxWritable.pm
@@ -298,4 +298,25 @@ sub warn_ignore_cb {
 	}
 }
 
+# v2+ only
+sub git_dir_n { "$_[0]->{inboxdir}/git/$_[1].git" }
+
+# v2+ only
+sub git_dir_latest {
+	my ($self, $max) = @_;
+	$$max = -1;
+	my $pfx = "$self->{inboxdir}/git";
+	return unless -d $pfx;
+	my $latest;
+	opendir my $dh, $pfx or die "opendir $pfx: $!\n";
+	while (defined(my $git_dir = readdir($dh))) {
+		$git_dir =~ m!\A([0-9]+)\.git\z! or next;
+		if ($1 > $$max) {
+			$$max = $1;
+			$latest = "$pfx/$git_dir";
+		}
+	}
+	$latest;
+}
+
 1;
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index 667a11f8..6af50f5d 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -120,7 +120,7 @@ sub init_inbox {
 	$self->idx_init;
 	$self->{mm}->skip_artnum($skip_artnum) if defined $skip_artnum;
 	my $epoch_max = -1;
-	git_dir_latest($self, \$epoch_max);
+	$self->{ibx}->git_dir_latest(\$epoch_max);
 	if (defined $skip_epoch && $epoch_max == -1) {
 		$epoch_max = $skip_epoch;
 	}
@@ -320,12 +320,13 @@ sub idx_init {
 sub _replace_oids ($$$) {
 	my ($self, $mime, $replace_map) = @_;
 	$self->done;
-	my $pfx = "$self->{ibx}->{inboxdir}/git";
+	my $ibx = $self->{ibx};
+	my $pfx = "$ibx->{inboxdir}/git";
 	my $rewrites = []; # epoch => commit
 	my $max = $self->{epoch_max};
 
 	unless (defined($max)) {
-		defined(my $latest = git_dir_latest($self, \$max)) or return;
+		defined(my $latest = $ibx->git_dir_latest(\$max)) or return;
 		$self->{epoch_max} = $max;
 	}
 
@@ -748,23 +749,6 @@ sub git_init {
 	$git_dir
 }
 
-sub git_dir_latest {
-	my ($self, $max) = @_;
-	$$max = -1;
-	my $pfx = "$self->{ibx}->{inboxdir}/git";
-	return unless -d $pfx;
-	my $latest;
-	opendir my $dh, $pfx or die "opendir $pfx: $!\n";
-	while (defined(my $git_dir = readdir($dh))) {
-		$git_dir =~ m!\A([0-9]+)\.git\z! or next;
-		if ($1 > $$max) {
-			$$max = $1;
-			$latest = "$pfx/$git_dir";
-		}
-	}
-	$latest;
-}
-
 sub importer {
 	my ($self) = @_;
 	my $im = $self->{im};
@@ -783,7 +767,7 @@ sub importer {
 	}
 	my $epoch = 0;
 	my $max;
-	my $latest = git_dir_latest($self, \$max);
+	my $latest = $self->{ibx}->git_dir_latest(\$max);
 	if (defined $latest) {
 		my $git = PublicInbox::Git->new($latest);
 		my $packed_bytes = $git->packed_bytes;
@@ -977,8 +961,6 @@ sub update_last_commit {
 	last_epoch_commit($self, $i, $cmt);
 }
 
-sub git_dir_n ($$) { "$_[0]->{ibx}->{inboxdir}/git/$_[1].git" }
-
 sub last_commits ($$) {
 	my ($self, $epoch_max) = @_;
 	my $heads = [];
@@ -989,8 +971,8 @@ sub last_commits ($$) {
 }
 
 # returns a revision range for git-log(1)
-sub log_range ($$$$$) {
-	my ($self, $sync, $git, $i, $tip) = @_;
+sub log_range ($$$$) {
+	my ($sync, $git, $i, $tip) = @_;
 	my $opt = $sync->{-opt};
 	my $pr = $opt->{-progress} if (($opt->{verbose} || 0) > 1);
 	my $cur = $sync->{ranges}->[$i] or do {
@@ -1043,14 +1025,14 @@ sub sync_prepare ($$$) {
 	my ($self, $sync, $epoch_max) = @_;
 	my $pr = $sync->{-opt}->{-progress};
 	my $regen_max = 0;
-	my $head = $self->{ibx}->{ref_head} || 'HEAD';
+	my $head = $sync->{ibx}->{ref_head} || 'HEAD';
 
 	# reindex stops at the current heads and we later rerun index_sync
 	# without {reindex}
 	my $reindex_heads = $self->last_commits($epoch_max) if $sync->{reindex};
 
 	for (my $i = $epoch_max; $i >= 0; $i--) {
-		my $git_dir = git_dir_n($self, $i);
+		my $git_dir = $sync->{ibx}->git_dir_n($i);
 		-d $git_dir or next; # missing epochs are fine
 		my $git = PublicInbox::Git->new($git_dir);
 		if ($reindex_heads) {
@@ -1059,7 +1041,7 @@ sub sync_prepare ($$$) {
 		chomp(my $tip = $git->qx(qw(rev-parse -q --verify), $head));
 
 		next if $?; # new repo
-		my $range = log_range($self, $sync, $git, $i, $tip) or next;
+		my $range = log_range($sync, $git, $i, $tip) or next;
 		# can't use 'rev-list --count' if we use --diff-filter
 		$pr->("$i.git counting $range ... ") if $pr;
 		# Don't bump num_highwater on --reindex by using {D}.
@@ -1067,7 +1049,7 @@ sub sync_prepare ($$$) {
 		# because we want NNTP article number gaps from unindexed
 		# messages to show up in mirrors, too.
 		$sync->{D} //= $sync->{reindex} ? {} : undef; # OID_BIN => NR
-		my $stk = log2stack($sync, $git, $range, $self->{ibx});
+		my $stk = log2stack($sync, $git, $range, $sync->{ibx});
 		my $nr = $stk ? $stk->num_records : 0;
 		$pr->("$nr\n") if $pr;
 		$sync->{stacks}->[$i] = $stk if $stk;
@@ -1143,7 +1125,7 @@ sub git { $_[0]->{ibx}->git }
 
 # this is rare, it only happens when we get discontiguous history in
 # a mirror because the source used -purge or -edit
-sub unindex ($$$$) {
+sub unindex_epoch ($$$$) {
 	my ($self, $sync, $git, $unindex_range) = @_;
 	my $unindexed = $sync->{unindexed} //= {}; # $mid0 => $num
 	my $before = scalar keys %$unindexed;
@@ -1216,11 +1198,11 @@ sub index_xap_step ($$$;$) {
 sub index_epoch ($$$) {
 	my ($self, $sync, $i) = @_;
 
-	my $git_dir = git_dir_n($self, $i);
+	my $git_dir = $sync->{ibx}->git_dir_n($i);
 	-d $git_dir or return; # missing epochs are fine
 	my $git = PublicInbox::Git->new($git_dir);
 	if (my $unindex_range = delete $sync->{unindex_range}->{$i}) { # rare
-		unindex($self, $sync, $git, $unindex_range);
+		unindex_epoch($self, $sync, $git, $unindex_range);
 	}
 	defined(my $stk = $sync->{stacks}->[$i]) or return;
 	$sync->{stacks}->[$i] = undef;
@@ -1284,7 +1266,7 @@ sub index_sync {
 
 	my $pr = $opt->{-progress};
 	my $epoch_max;
-	my $latest = git_dir_latest($self, \$epoch_max);
+	my $latest = $self->{ibx}->git_dir_latest(\$epoch_max);
 	return unless defined $latest;
 
 	my $seq = $opt->{sequential_shard};
@@ -1301,6 +1283,7 @@ sub index_sync {
 		reindex => $opt->{reindex},
 		-opt => $opt,
 		v2w => $self,
+		ibx => $self->{ibx},
 	};
 	$sync->{ranges} = sync_ranges($self, $sync, $epoch_max);
 	if (sync_prepare($self, $sync, $epoch_max)) {
diff --git a/lib/PublicInbox/Xapcmd.pm b/lib/PublicInbox/Xapcmd.pm
index 6a74daf9..4332943c 100644
--- a/lib/PublicInbox/Xapcmd.pm
+++ b/lib/PublicInbox/Xapcmd.pm
@@ -110,7 +110,7 @@ sub prepare_reindex ($$$) {
 		}
 	} else { # v2
 		my $max;
-		$im->git_dir_latest(\$max) or return;
+		$ibx->git_dir_latest(\$max) or return;
 		my $from = $opt->{reindex}->{from};
 		my $mm = $ibx->mm;
 		my $v = PublicInbox::Search::SCHEMA_VERSION();

  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 ` Eric Wong [this message]
2020-10-27  7:54 ` [PATCH 16/52] inboxwritable: eidx_key " 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 ` [PATCH 30/52] extsearchidx: more compatibility with V2Writable callers Eric Wong
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=20201027075453.19163-16-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.
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).