user/dev discussion of public-inbox itself
 help / color / Atom feed
From: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 03/11] import: switch to "replace_oids" interface for purge
Date: Sun,  9 Jun 2019 02:51:39 +0000
Message-ID: <20190609025147.24966-4-e@80x24.org> (raw)
In-Reply-To: <20190609025147.24966-1-e@80x24.org>

Continuing the work by Eric Biederman in commit a118d58a402bd31b
("Import.pm: When purging replace a purged file with a zero length file"),
we can use a generic OID replacement mechanism to implement
purge.
---
 lib/PublicInbox/Import.pm     | 33 +++++++++++++++++++--------------
 lib/PublicInbox/V2Writable.pm |  6 +++---
 2 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/lib/PublicInbox/Import.pm b/lib/PublicInbox/Import.pm
index 6ee1935..2c8fe84 100644
--- a/lib/PublicInbox/Import.pm
+++ b/lib/PublicInbox/Import.pm
@@ -501,16 +501,16 @@ sub clean_purge_buffer {
 	}
 }
 
-sub purge_oids {
-	my ($self, $purge) = @_;
-	my $tmp = "refs/heads/purge-".((keys %$purge)[0]);
+sub replace_oids {
+	my ($self, $replace) = @_; # oid => raw string
+	my $tmp = "refs/heads/replace-".((keys %$replace)[0]);
 	my $old = $self->{'ref'};
 	my $git = $self->{git};
 	my @export = (qw(fast-export --no-data --use-done-feature), $old);
 	my $rd = $git->popen(@export);
 	my ($r, $w) = $self->gfi_start;
 	my @buf;
-	my $npurge = 0;
+	my $nreplace = 0;
 	my @oids;
 	my ($done, $mark);
 	my $tree = $self->{-tree};
@@ -533,10 +533,13 @@ sub purge_oids {
 		} elsif (/^M 100644 ([a-f0-9]+) (\w+)/) {
 			my ($oid, $path) = ($1, $2);
 			$tree->{$path} = 1;
-			if ($purge->{$oid}) {
+			my $sref = $replace->{$oid};
+			if (defined $sref) {
 				push @oids, $oid;
-				my $cmd = "M 100644 inline $path\ndata 0\n\n";
-				push @buf, $cmd;
+				my $n = length($$sref);
+				push @buf, "M 100644 inline $path\ndata $n\n";
+				push @buf, $$sref; # hope CoW works...
+				push @buf, "\n";
 			} else {
 				push @buf, $_;
 			}
@@ -549,7 +552,7 @@ sub purge_oids {
 				$out =~ s/^/# /sgm;
 				warn "purge rewriting\n", $out, "\n";
 				clean_purge_buffer(\@oids, \@buf);
-				$npurge++;
+				$nreplace++;
 			}
 			$w->print(@buf, "\n") or wfail;
 			@buf = ();
@@ -567,28 +570,30 @@ sub purge_oids {
 		$w->print(@buf) or wfail;
 	}
 	die 'done\n not seen from fast-export' unless $done;
-	chomp(my $cmt = $self->get_mark(":$mark")) if $npurge;
+	chomp(my $cmt = $self->get_mark(":$mark")) if $nreplace;
 	$self->{nchg} = 0; # prevent _update_git_info until update-ref:
 	$self->done;
 	my @git = ('git', "--git-dir=$git->{git_dir}");
 
-	run_die([@git, qw(update-ref), $old, $tmp]) if $npurge;
+	run_die([@git, qw(update-ref), $old, $tmp]) if $nreplace;
 
 	run_die([@git, qw(update-ref -d), $tmp]);
 
-	return if $npurge == 0;
+	return if $nreplace == 0;
 
 	run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all)]);
+
+	# check that old OIDs are gone
 	my $err = 0;
-	foreach my $oid (keys %$purge) {
+	foreach my $oid (keys %$replace) {
 		my @info = $git->check($oid);
 		if (@info) {
-			warn "$oid not purged\n";
+			warn "$oid not replaced\n";
 			$err++;
 		}
 	}
 	_update_git_info($self, 0);
-	die "Failed to purge $err object(s)\n" if $err;
+	die "Failed to replace $err object(s)\n" if $err;
 	$cmt;
 }
 
diff --git a/lib/PublicInbox/V2Writable.pm b/lib/PublicInbox/V2Writable.pm
index a435814..d6f72b0 100644
--- a/lib/PublicInbox/V2Writable.pm
+++ b/lib/PublicInbox/V2Writable.pm
@@ -298,7 +298,7 @@ sub idx_init {
 }
 
 sub purge_oids ($$) {
-	my ($self, $purge) = @_; # $purge = { $object_id => 1, ... }
+	my ($self, $purge) = @_; # $purge = { $object_id => \'', ... }
 	$self->done;
 	my $pfx = "$self->{-inbox}->{mainrepo}/git";
 	my $purges = [];
@@ -313,7 +313,7 @@ sub purge_oids ($$) {
 		-d $git_dir or next;
 		my $git = PublicInbox::Git->new($git_dir);
 		my $im = $self->import_init($git, 0, 1);
-		$purges->[$i] = $im->purge_oids($purge);
+		$purges->[$i] = $im->replace_oids($purge);
 		$im->done;
 	}
 	$purges;
@@ -386,7 +386,7 @@ sub remove_internal ($$$$) {
 			$removed = $smsg;
 			my $oid = $smsg->{blob};
 			if ($purge) {
-				$purge->{$oid} = 1;
+				$purge->{$oid} = \'';
 			} else {
 				($mark, undef) = $im->remove($orig, $cmt_msg);
 			}
-- 
EW


  parent reply index

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-09  2:51 [PATCH 00/11] v2: implement message editing Eric Wong (Contractor, The Linux Foundation)
2019-06-09  2:51 ` [PATCH 01/11] v2writable: consolidate overview and indexing call Eric Wong (Contractor, The Linux Foundation)
2019-06-09  2:51 ` [PATCH 02/11] import: extract_author_info becomes extract_commit_info Eric Wong (Contractor, The Linux Foundation)
2019-06-09  2:51 ` Eric Wong (Contractor, The Linux Foundation) [this message]
2019-06-09  2:51 ` [PATCH 04/11] v2writable: implement ->replace call Eric Wong (Contractor, The Linux Foundation)
2019-06-09  2:51 ` [PATCH 05/11] admin: remove warning arg for unconfigured inboxes Eric Wong (Contractor, The Linux Foundation)
2019-06-09  2:51 ` [PATCH 06/11] purge: start moving common options to AdminEdit module Eric Wong (Contractor, The Linux Foundation)
2019-06-09  2:51 ` [PATCH 07/11] admin: beef up resolve_inboxes to handle purge options Eric Wong (Contractor, The Linux Foundation)
2019-06-09  2:51 ` [PATCH 08/11] AdminEdit: move editability checks from -purge Eric Wong (Contractor, The Linux Foundation)
2019-06-09  2:51 ` [PATCH 09/11] admin: expose ->config Eric Wong (Contractor, The Linux Foundation)
2019-06-09  2:51 ` [PATCH 10/11] doc: document the --prune option for -index Eric Wong (Contractor, The Linux Foundation)
2019-06-09  2:51 ` [PATCH 11/11] edit: new tool to perform edits Eric Wong (Contractor, The Linux Foundation)
2019-06-10 16:06   ` Konstantin Ryabitsev
2019-06-10 18:02     ` Eric Wong
2019-06-13  8:07     ` Eric Wong
2019-06-10 15:06 ` [PATCH 00/11] v2: implement message editing Konstantin Ryabitsev
2019-06-10 15:40   ` Eric Wong
2019-06-10 17:56     ` [PATCH 12/11] edit|purge: improve output on rewrites Eric Wong
2019-06-10 18:57     ` [PATCH 00/11] v2: implement message editing Konstantin Ryabitsev
2019-06-10 19:29       ` Eric Wong
2019-06-10 19:40         ` Konstantin Ryabitsev
2019-06-10 22:03           ` [WIP] v2writable: support INBOX_DEBUG=replace Eric Wong
2019-06-10 22:13             ` Konstantin Ryabitsev
2019-06-10 23:12               ` [WIP] add more debug tracing around idx_init Eric Wong
2019-06-11 15:33                 ` Konstantin Ryabitsev
2019-06-11 18:43             ` [WIP] v2writable: support INBOX_DEBUG=replace Eric Wong
2019-06-11 21:06       ` [PATCH 00/11] v2: implement message editing Konstantin Ryabitsev
2019-06-12  0:18         ` [PATCH] searchidx: improve error message when Xapian fails Eric Wong
2019-06-10 18:17 ` [PATCH 13/11] edit: drop unwanted headers before noop check Eric Wong (Contractor, The Linux Foundation)
2019-06-10 21:58 ` [PATCH 14/11] v2writable: replace: kill git processes before reindexing Eric Wong (Contractor, The Linux Foundation)
2019-06-12  0:25 ` [PATCH 15/11] edit: unlink temporary file when done Eric Wong (Contractor, The Linux Foundation)

Reply instructions:

You may reply publically 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=20190609025147.24966-4-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

user/dev discussion of public-inbox itself

Archives are clonable:
	git clone --mirror http://public-inbox.org/meta
	git clone --mirror http://czquwvybam4bgbro.onion/meta
	git clone --mirror http://hjrcffqmbrq6wope.onion/meta
	git clone --mirror http://ou63pmih66umazou.onion/meta

Example config snippet for mirrors

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.mail.public-inbox.meta
	nntp://ou63pmih66umazou.onion/inbox.comp.mail.public-inbox.meta
	nntp://czquwvybam4bgbro.onion/inbox.comp.mail.public-inbox.meta
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.mail.public-inbox.meta
	nntp://news.gmane.org/gmane.mail.public-inbox.general

 note: .onion URLs require Tor: https://www.torproject.org/

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git