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 05/26] xapcmd: new module for wrapping Xapian commands
Date: Thu, 23 May 2019 09:36:43 +0000	[thread overview]
Message-ID: <20190523093704.18367-6-e@80x24.org> (raw)
In-Reply-To: <20190523093704.18367-1-e@80x24.org>

Port public-inbox-compact(1) over to using it, and we will need
to wrap copydatabase(1) to ease glass migrations, too.
---
 MANIFEST                    |  1 +
 lib/PublicInbox/Xapcmd.pm   | 65 ++++++++++++++++++++++++++++++++++
 script/public-inbox-compact | 70 ++-----------------------------------
 3 files changed, 68 insertions(+), 68 deletions(-)
 create mode 100644 lib/PublicInbox/Xapcmd.pm

diff --git a/MANIFEST b/MANIFEST
index 2b101fa..dfc1f66 100644
--- a/MANIFEST
+++ b/MANIFEST
@@ -139,6 +139,7 @@ lib/PublicInbox/WwwHighlight.pm
 lib/PublicInbox/WwwListing.pm
 lib/PublicInbox/WwwStream.pm
 lib/PublicInbox/WwwText.pm
+lib/PublicInbox/Xapcmd.pm
 sa_config/Makefile
 sa_config/README
 sa_config/root/etc/spamassassin/public-inbox.pre
diff --git a/lib/PublicInbox/Xapcmd.pm b/lib/PublicInbox/Xapcmd.pm
new file mode 100644
index 0000000..586d7e6
--- /dev/null
+++ b/lib/PublicInbox/Xapcmd.pm
@@ -0,0 +1,65 @@
+# Copyright (C) 2018-2019 all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+package PublicInbox::Xapcmd;
+use strict;
+use warnings;
+use PublicInbox::Spawn qw(which spawn);
+use PublicInbox::Over;
+use File::Temp qw(tempdir);
+use File::Path qw(remove_tree);
+
+sub commit_changes ($$$) {
+	my ($im, $old, $new) = @_;
+	my @st = stat($old) or die "failed to stat($old): $!\n";
+
+	my $over = "$old/over.sqlite3";
+	if (-f $over) {
+		$over = PublicInbox::Over->new($over);
+		$over->connect->sqlite_backup_to_file("$new/over.sqlite3");
+	}
+	rename($old, "$new/old") or die "rename $old => $new/old: $!\n";
+	chmod($st[2] & 07777, $new) or die "chmod $old: $!\n";
+	rename($new, $old) or die "rename $new => $old: $!\n";
+	$im->lock_release;
+	remove_tree("$old/old") or die "failed to remove $old/old: $!\n";
+}
+
+sub run {
+	my ($ibx, $cmd) = @_;
+	my $dir = $ibx->{mainrepo} or die "no mainrepo in inbox\n";
+	which($cmd->[0]) or die "$cmd->[0] not found in PATH\n";
+	$ibx->umask_prepare;
+	my $old = $ibx->search->xdir(1);
+	-d $old or die "$old does not exist\n";
+	my $new = tempdir($cmd->[0].'-XXXXXXXX', CLEANUP => 1, DIR => $dir);
+	my $v = $ibx->{version} || 1;
+	my @cmds;
+	if ($v == 1) {
+		push @cmds, [@$cmd, $old, $new];
+	} else {
+		opendir my $dh, $old or die "Failed to opendir $old: $!\n";
+		while (defined(my $dn = readdir($dh))) {
+			if ($dn =~ /\A\d+\z/) {
+				push @cmds, [@$cmd, "$old/$dn", "$new/$dn"];
+			} elsif ($dn eq '.' || $dn eq '..') {
+			} elsif ($dn =~ /\Aover\.sqlite3/) {
+			} else {
+				warn "W: skipping unknown dir: $old/$dn\n"
+			}
+		}
+		die "No Xapian parts found in $old\n" unless @cmds;
+	}
+	my $im = $ibx->importer(0);
+	$ibx->with_umask(sub {
+		$im->lock_acquire;
+		my %pids = map {; spawn($_) => join(' ', @$_) } @cmds;
+		while (scalar keys %pids) {
+			my $pid = waitpid(-1, 0);
+			my $desc = delete $pids{$pid};
+			die "$desc failed: $?\n" if $?;
+		}
+		commit_changes($im, $old, $new);
+	});
+}
+
+1;
diff --git a/script/public-inbox-compact b/script/public-inbox-compact
index 395eec3..4aa6273 100755
--- a/script/public-inbox-compact
+++ b/script/public-inbox-compact
@@ -8,9 +8,7 @@ use PublicInbox::Search;
 use PublicInbox::Config;
 use PublicInbox::InboxWritable;
 use Cwd 'abs_path';
-use File::Temp qw(tempdir);
-use File::Path qw(remove_tree);
-use PublicInbox::Spawn qw(spawn);
+use PublicInbox::Xapcmd;
 my $usage = "Usage: public-inbox-compact REPO_DIR\n";
 my $dir = shift or die $usage;
 my $config = eval { PublicInbox::Config->new };
@@ -31,71 +29,7 @@ unless ($ibx) {
 	};
 	$ibx = PublicInbox::Inbox->new($ibx);
 }
-my $v = ($ibx->{version} || 1);
 $ibx = PublicInbox::InboxWritable->new($ibx);
-$ibx->umask_prepare;
-
-sub commit_changes ($$$) {
-	my ($im, $old, $new) = @_;
-	my @st = stat($old) or die "failed to stat($old): $!\n";
-
-	my $over = "$old/over.sqlite3";
-	if (-f $over) {
-		require PublicInbox::Over;
-		$over = PublicInbox::Over->new($over);
-		$over->connect->sqlite_backup_to_file("$new/over.sqlite3");
-	}
-	rename($old, "$new/old") or die "rename $old => $new/old: $!\n";
-	chmod($st[2] & 07777, $new) or die "chmod $old: $!\n";
-	rename($new, $old) or die "rename $new => $old: $!\n";
-	$im->lock_release;
-	remove_tree("$old/old") or die "failed to remove $old/old: $!\n";
-}
 
 # we rely on --no-renumber to keep docids synched to NNTP
-my @compact = qw(xapian-compact --no-renumber);
-if ($v == 2) {
-	require PublicInbox::V2Writable;
-	my $v2w = PublicInbox::V2Writable->new($ibx);
-	my $xap_v = 'xap'.PublicInbox::Search::SCHEMA_VERSION;
-	my $old = "$dir/$xap_v";
-	opendir my $dh, $old or die "Failed to opendir $old: $!\n";
-	my $new = tempdir('compact-XXXXXXXX', CLEANUP => 1, DIR => $dir);
-	$ibx->with_umask(sub {
-		$v2w->lock_acquire;
-		my %pids;
-		while (defined(my $dn = readdir($dh))) {
-			if ($dn =~ /\A\d+\z/) {
-				my $cmd = [ @compact, "$old/$dn", "$new/$dn" ];
-				$pids{spawn($cmd)} = join(' ', @$cmd);
-			} elsif ($dn eq '.' || $dn eq '..') {
-			} elsif ($dn =~ /\Aover\.sqlite3/) {
-			} else {
-				warn "W: skipping unknown Xapian DB: $old/$dn\n"
-			}
-		}
-		close $dh;
-		die "No Xapian parts found in $old\n" unless keys %pids;
-		while (scalar keys %pids) {
-			my $pid = waitpid(-1, 0);
-			my $desc = delete $pids{$pid};
-			die "$desc failed: $?\n" if $?;
-		}
-		commit_changes($v2w, $old, $new);
-	});
-} elsif ($v == 1) {
-	require PublicInbox::Import;
-	my $im = PublicInbox::Import->new($ibx->git, undef, undef, $ibx);
-	my $xap_v = 'xapian'.PublicInbox::Search::SCHEMA_VERSION;
-	my $v1_root = "$dir/public-inbox";
-	my $old = "$v1_root/$xap_v";
-	-d $old or die "$old does not exist\n";
-	my $new = tempdir('compact-XXXXXXXX', CLEANUP => 1, DIR => $v1_root);
-	$ibx->with_umask(sub {
-		$im->lock_acquire;
-		PublicInbox::Import::run_die([@compact, $old, $new]);
-		commit_changes($im, $old, $new);
-	});
-} else {
-	die "Unsupported inbox version: $v\n";
-}
+PublicInbox::Xapcmd::run($ibx, [qw(xapian-compact --no-renumber)]);
-- 
EW


  parent reply	other threads:[~2019-05-23  9:37 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-23  9:36 [PATCH 00/26] xcpdb: ease Xapian DB format migrations Eric Wong
2019-05-23  9:36 ` [PATCH 01/26] t/convert-compact: skip on missing xapian-compact(1) Eric Wong
2019-05-23  9:36 ` [PATCH 02/26] v1writable: retire in favor of InboxWritable Eric Wong
2019-05-23  9:36 ` [PATCH 03/26] doc: document the reason for --no-renumber Eric Wong
2019-05-23  9:36 ` [PATCH 04/26] search: reenable phrase search on non-chert Xapian Eric Wong
2019-05-23  9:36 ` Eric Wong [this message]
2019-05-23  9:36 ` [PATCH 06/26] admin: hoist out resolve_inboxes for -compact and -index Eric Wong
2019-05-23  9:36 ` [PATCH 07/26] xapcmd: support spawn options Eric Wong
2019-05-23  9:36 ` [PATCH 08/26] xcpdb: new tool which wraps Xapian's copydatabase(1) Eric Wong
2019-05-23  9:36 ` [PATCH 09/26] xapcmd: do not cleanup on errors Eric Wong
2019-05-23  9:36 ` [PATCH 10/26] admin: move index_inbox over Eric Wong
2019-05-23  9:36 ` [PATCH 11/26] xcpdb: implement using Perl bindings Eric Wong
2019-05-23  9:36 ` [PATCH 12/26] xapcmd: xcpdb supports compaction Eric Wong
2019-05-23  9:36 ` [PATCH 13/26] v2writable: hoist out log_range sub for readability Eric Wong
2019-05-23  9:36 ` [PATCH 14/26] xcpdb: use fine-grained locking Eric Wong
2019-05-23  9:36 ` [PATCH 15/26] xcpdb: implement progress reporting Eric Wong
2019-05-23  9:36 ` [PATCH 16/26] xcpdb: cleanup error handling and diagnosis Eric Wong
2019-05-23  9:36 ` [PATCH 17/26] xapcmd: avoid EXDEV when finalizing changes Eric Wong
2019-05-23  9:36 ` [PATCH 18/26] doc: xcpdb: update to reflect the current state Eric Wong
2019-05-23  9:36 ` [PATCH 19/26] xapcmd: use "print STDERR" for progress reporting Eric Wong
2019-05-23  9:36 ` [PATCH 20/26] xcpdb: show re-indexing progress Eric Wong
2019-05-23  9:36 ` [PATCH 21/26] xcpdb: remove temporary directories on aborts Eric Wong
2019-05-23  9:37 ` [PATCH 22/26] compact: reuse infrastructure from xcpdb Eric Wong
2019-05-23  9:37 ` [PATCH 23/26] xcpdb|compact: support some xapian-compact switches Eric Wong
2019-05-23  9:37 ` [PATCH 24/26] xapcmd: cleanup on interrupted xcpdb "--compact" Eric Wong
2019-05-23  9:37 ` [PATCH 25/26] xcpdb|compact: support --jobs/-j flag like gmake(1) Eric Wong
2019-05-23  9:37 ` [PATCH 26/26] xapcmd: do not reset %SIG until last Xtmpdir is done Eric Wong
2019-05-23 10:37 ` [PATCH 27/26] doc: various updates to reflect current state 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: http://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=20190523093704.18367-6-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).