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 30/95] lei_mirror: do not fetch descriptions if using manifest
Date: Mon, 28 Nov 2022 05:31:27 +0000	[thread overview]
Message-ID: <20221128053232.291618-31-e@80x24.org> (raw)
In-Reply-To: <20221128053232.291618-1-e@80x24.org>

If a manifest exists, we can expect the description to always be
present, thus there's no need to make a separate HTTP(S) request
since we can use it as-is from the manifest for v1||coderepos
and strip / \[epoch [0-9]+\]\z/ from v1.
---
 lib/PublicInbox/LeiMirror.pm | 56 ++++++++++++++++++++++++------------
 1 file changed, 37 insertions(+), 19 deletions(-)

diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index 1d6ed51c..2b20873e 100644
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -177,16 +177,17 @@ sub set_description ($) {
 	open my $fh, '+>>', $f or die "open($f): $!";
 	seek($fh, 0, SEEK_SET) or die "seek($f): $!";
 	my $d = do { local $/; <$fh> } // die "read($f): $!";
-	my $orig = $d;
+	chomp(my $orig = $d);
 	while (defined($d) && ($d =~ m!^\(\$INBOX_DIR/description missing\)! ||
 			$d =~ /^Unnamed repository/ || $d !~ /\S/)) {
 		$d = delete($self->{'txt.description'});
 	}
-	$d //= 'mirror of '.($self->{cur_src} // $self->{src})."\n";
+	$d //= 'mirror of '.($self->{cur_src} // $self->{src});
+	chomp $d;
 	return if $d eq $orig;
 	seek($fh, 0, SEEK_SET) or die "seek($f): $!";
 	truncate($fh, 0) or die "truncate($f): $!";
-	print $fh $d or die "print($f): $!";
+	print $fh $d, "\n" or die "print($f): $!";
 	close $fh or die "close($f): $!";
 }
 
@@ -261,8 +262,10 @@ sub clone_v1 {
 
 	$lei->{opt}->{'inbox-config'} =~ /\A(?:always|v1)\z/s and
 		_get_txt_start($self, '_/text/config/raw', $fini);
+
 	my $d = $self->{-ent} ? $self->{-ent}->{description} : undef;
-	defined($d) ? ($self->{'txt.description'} = $d) :
+	$self->{'txt.description'} = $d if defined $d;
+	(!defined($d) && !$nohang) and
 		_get_txt_start($self, 'description', $fini);
 
 	reap_live() until ($nohang || !keys(%$LIVE)); # for non-manifest clone
@@ -333,11 +336,14 @@ EOM
 EOM
 	}
 	close $fh or die "close($f): $!";
-	if (defined $ent->{head}) {
-		$f = "$edst/HEAD";
-		open $fh, '>', $f or die "open($f): $!";
-		print $fh $ent->{head}, "\n" or die "print($f): $!";
-		close $fh or die "close($f): $!";
+	my %map = (head => 'HEAD', description => undef);
+	while (my ($key, $fn) = each %map) {
+		my $val = $ent->{$key} // next;
+		$fn //= $key;
+		$fn = "$edst/$fn";
+		open $fh, '>', $fn or die "open($fn): $!";
+		print $fh $val, "\n" or die "print($fn): $!";
+		close $fh or die "close($fn): $!";
 	}
 }
 
@@ -385,10 +391,18 @@ sub v2_done { # called via OnDestroy
 	my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git');
 	$mg->fill_alternates;
 	for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) }
-	my $edst_owner = delete($self->{-owner}) // [];
-	while (@$edst_owner) {
-		my ($edst, $o) = splice(@$edst_owner);
-		run_die [qw(git config -f), "$edst/config", 'gitweb.owner', $o];
+	my $entries = delete($self->{-ent}) // [];
+	while (@$entries) {
+		my ($edst, $ent) = splice(@$entries);
+		if (defined(my $o = $ent->{owner})) {
+			run_die [qw(git config -f), "$edst/config",
+				'gitweb.owner', $o];
+		}
+		my $d = $ent->{description} // next;
+		my $fn = "$edst/description";
+		open my $fh, '>', $fn or die "open($fn): $!";
+		print $fh $d, "\n" or die "print($fn): $!";
+		close $fh or die "close($fn): $!";
 	}
 	for my $edst (@{delete($self->{-read_only}) // []}) {
 		my @st = stat($edst) or die "stat($edst): $!";
@@ -418,7 +432,7 @@ sub clone_v2 ($$;$) {
 	my $dst = $self->{cur_dst} // $self->{dst};
 	my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs);
 	my $task = $m ? bless { %$self }, __PACKAGE__ : $self;
-	my (@src_edst, @skip);
+	my (@src_edst, @skip, $desc);
 	for my $nr (sort { $a <=> $b } keys %$v2_epochs) {
 		my ($uri, $key) = @{$v2_epochs->{$nr}};
 		my $src = $uri->as_string;
@@ -428,13 +442,16 @@ failed to extract epoch number from $src
 
 		$1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr";
 		$edst .= "/git/$nr.git";
-		$m->{$key} // die "BUG: `$key' not in manifest.js.gz";
+		my $ent = $m->{$key} // die "BUG: `$key' not in manifest.js.gz";
+		if (defined(my $d = $ent->{description})) {
+			$d =~ s/ \[epoch [0-9]+\]\z//s;
+			$desc = $d;
+		}
 		if (!$want || $want->{$nr}) {
 			push @src_edst, $src, $edst;
-			my $o = $m->{$key}->{owner};
-			push(@{$task->{-owner}}, $edst, $o) if defined($o);
+			push @{$task->{-ent}}, $edst, $ent;
 		} else { # create a placeholder so users only need to chmod +w
-			init_placeholder($src, $edst, $m->{$key});
+			init_placeholder($src, $edst, $ent);
 			push @{$task->{-read_only}}, $edst;
 			push @skip, $key;
 		}
@@ -450,7 +467,8 @@ failed to extract epoch number from $src
 	$lei->{opt}->{'inbox-config'} =~ /\A(?:always|v2)\z/s and
 		_get_txt_start($task, '_/text/config/raw', $fini);
 
-	_get_txt_start($task, 'description', $fini);
+	defined($desc) ? ($task->{'txt.description'} = $desc) :
+		_get_txt_start($task, 'description', $fini);
 
 	my @cmd = clone_cmd($lei, my $opt = {});
 	while (@src_edst && !$lei->{child_error}) {

  parent reply	other threads:[~2022-11-28  5:32 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-11-28  5:30 [PATCH 00/95] clone: multi-inbox/repo support Eric Wong
2022-11-28  5:30 ` [PATCH 01/95] clone: support multi-inbox clone Eric Wong
2022-11-28  5:30 ` [PATCH 02/95] clone: support --include and --exclude with multi-clone Eric Wong
2022-11-28  5:31 ` [PATCH 03/95] clone: parallelize v2 epoch clones Eric Wong
2022-11-28  5:31 ` [PATCH 04/95] lei_mirror: async config retrieval for v2 w/ manifest Eric Wong
2022-11-28  5:31 ` [PATCH 05/95] lei_mirror: rely on DESTROY to index v2 inbox Eric Wong
2022-11-28  5:31 ` [PATCH 06/95] lei_mirror: rely on global process reaper Eric Wong
2022-11-28  5:31 ` [PATCH 07/95] clone: support parallel v1 clones Eric Wong
2022-11-28  5:31 ` [PATCH 08/95] lei_mirror: default to single job by default Eric Wong
2022-11-28  5:31 ` [PATCH 09/95] lei_mirror: move directory creation to v2-only path Eric Wong
2022-11-28  5:31 ` [PATCH 10/95] lei_mirror: retrieve description text asynchronously, too Eric Wong
2022-11-28  5:31 ` [PATCH 11/95] switch inotify/kevent stuff to v5.12 Eric Wong
2022-11-28  5:31 ` [PATCH 12/95] manifest: update module blurb + v5.12 Eric Wong
2022-11-28  5:31 ` [PATCH 13/95] lei_mirror: simplify _get_txt_start callers Eric Wong
2022-11-28  5:31 ` [PATCH 14/95] lei_mirror: elide description retrieval for v1|coderepo Eric Wong
2022-11-28  5:31 ` [PATCH 15/95] lei_mirror: add a hint for skipped epoch permissions Eric Wong
2022-11-28  5:31 ` [PATCH 16/95] lei_mirror: consolidate clone process management Eric Wong
2022-11-28  5:31 ` [PATCH 17/95] lei_mirror: load File::Path unconditionally Eric Wong
2022-11-28  5:31 ` [PATCH 18/95] lei_mirror: load most modules up-front Eric Wong
2022-11-28  5:31 ` [PATCH 19/95] lei_mirror: set gitweb.owner from manifest Eric Wong
2022-11-28  5:31 ` [PATCH 20/95] clone: support --dry-run / -n flag Eric Wong
2022-11-28  5:31 ` [PATCH 21/95] lei_mirror: initialize placeholders with "head" from manifest Eric Wong
2022-11-28  5:31 ` [PATCH 22/95] lei_mirror: support {reference} for v1 manifest clones Eric Wong
2022-11-28  5:31 ` [PATCH 23/95] lei_mirror: reduce noise on interrupted clones Eric Wong
2022-11-28  5:31 ` [PATCH 24/95] clone: support --inbox-config option Eric Wong
2022-11-28  5:31 ` [PATCH 25/95] lei_mirror: retrieve v2 description properly Eric Wong
2022-11-28  5:31 ` [PATCH 26/95] lei_mirror: reduce scope of v2 lock Eric Wong
2022-11-28  5:31 ` [PATCH 27/95] lei_mirror: allow --epoch on mixed v1/v2 clones Eric Wong
2022-11-28  5:31 ` [PATCH 28/95] lei_mirror: fix infinite loop in dependency resolution Eric Wong
2022-11-28  5:31 ` [PATCH 29/95] lei_mirror: defend against infinite loops Eric Wong
2022-11-28  5:31 ` Eric Wong [this message]
2022-11-28  5:31 ` [PATCH 31/95] lei_mirror: require PublicInbox::Lock at use Eric Wong
2022-11-28  5:31 ` [PATCH 32/95] lei_mirror: fix glob semantics to match end-of-path Eric Wong
2022-11-28  5:31 ` [PATCH 33/95] lei_mirror: differentiate -entv vs -ent Eric Wong
2022-11-28  5:31 ` [PATCH 34/95] lei_mirror: support manifest {references} for v2 epochs Eric Wong
2022-11-28  5:31 ` [PATCH 35/95] lei_mirror: simplify v2 code paths Eric Wong
2022-11-28  5:31 ` [PATCH 36/95] clone: support --inbox-version Eric Wong
2022-11-28  5:31 ` [PATCH 37/95] lei_mirror: require Perl v5.12+ Eric Wong
2022-11-28  5:31 ` [PATCH 38/95] lei_mirror: ensure curl exits 22 on HTTP 404 responses Eric Wong
2022-11-28  5:31 ` [PATCH 39/95] lei_mirror: cleanup File::Temp OO usage Eric Wong
2022-11-28  5:31 ` [PATCH 40/95] lei_mirror: add `index' target to generated Makefile Eric Wong
2022-11-28  5:31 ` [PATCH 41/95] lei_mirror: do not write Makefile for --inbox-config=never Eric Wong
2022-11-28  5:31 ` [PATCH 42/95] lei_mirror: hoist out dump_manifest sub Eric Wong
2022-11-28  5:31 ` [PATCH 43/95] lei_mirror: avoid convoluted lazy_cb usage Eric Wong
2022-11-28  5:31 ` [PATCH 44/95] lei_mirror: simplify clone_v2_prep Eric Wong
2022-11-28  5:31 ` [PATCH 45/95] lei_mirror: support --objstore and forkgroups Eric Wong
2022-11-28  5:31 ` [PATCH 46/95] lei_mirror: cleanup process reaping logic Eric Wong
2022-11-28  5:31 ` [PATCH 47/95] lei_mirror: ensure git <1.8.5 fallback can use torsocks Eric Wong
2022-11-28  5:31 ` [PATCH 48/95] clone: flesh out --objstore behavior and document Eric Wong
2022-11-28  5:31 ` [PATCH 49/95] lei_mirror: always pack refs for coderepos Eric Wong
2022-11-28  5:31 ` [PATCH 50/95] lei_mirror: set description for non-inboxes, too Eric Wong
2022-11-28  5:31 ` [PATCH 51/95] lei_mirror: force --no-tags when fetching forkgroups Eric Wong
2022-11-28  5:31 ` [PATCH 52/95] lei_mirror: preserve permissions of existing alternates file Eric Wong
2022-11-28  5:31 ` [PATCH 53/95] lei_mirror: do not show ref updates w/o --verbose Eric Wong
2022-11-28  5:31 ` [PATCH 54/95] lei_mirror: drop git <1.8.5 support Eric Wong
2022-11-28  5:31 ` [PATCH 55/95] lei_mirror: make basename more descriptive Eric Wong
2022-11-28  5:31 ` [PATCH 56/95] lei_mirror: fix --dry-run for forkgroups Eric Wong
2022-11-28  5:31 ` [PATCH 57/95] lei_mirror: forkgroups use `git fetch --multiple' Eric Wong
2022-11-28  5:31 ` [PATCH 58/95] clone: move --dry-run handling to lei_mirror Eric Wong
2022-11-28  5:31 ` [PATCH 59/95] clone: drop unnecessary requires Eric Wong
2022-11-28  5:31 ` [PATCH 60/95] clone: use v5.12 Eric Wong
2022-11-28  5:31 ` [PATCH 61/95] clone: require `--objstore=' for default location Eric Wong
2022-11-28  5:31 ` [PATCH 62/95] lei_mirror: shorten remote names Eric Wong
2022-11-28  5:32 ` [PATCH 63/95] fetch: use v5.12 Eric Wong
2022-11-28  5:32 ` [PATCH 64/95] fetch: eliminate File::Temp->filename var Eric Wong
2022-11-28  5:32 ` [PATCH 65/95] lei_mirror: properly pack-refs in non-forkgroup repos Eric Wong
2022-11-28  5:32 ` [PATCH 66/95] lei_mirror: show child error error code Eric Wong
2022-11-28  5:32 ` [PATCH 67/95] on_destroy: support ->cancel callback Eric Wong
2022-11-28  5:32 ` [PATCH 68/95] lei_mirror: support resuming multi-repo clones Eric Wong
2022-11-28  5:32 ` [PATCH 69/95] lei_mirror: check fingerprints before fetching Eric Wong
2022-11-28  5:32 ` [PATCH 70/95] clone: support loading manifest.js.gz from destination Eric Wong
2022-11-28  5:32 ` [PATCH 71/95] lei_mirror: delay configuring forkgroups Eric Wong
2022-11-28  5:32 ` [PATCH 72/95] clone: canonicalize destination path from CLI Eric Wong
2022-11-28  5:32 ` [PATCH 73/95] clone|fetch: support passing --prune(-tags) to `git fetch' Eric Wong
2022-11-28  5:32 ` [PATCH 74/95] lei_mirror: avoid needless FD passing Eric Wong
2022-11-28  5:32 ` [PATCH 75/95] clone: support --keep-going/-k like make(1) Eric Wong
2022-11-28  5:32 ` [PATCH 76/95] lei_mirror: don't warn on missing manifest on initial clone Eric Wong
2022-11-28  5:32 ` [PATCH 77/95] lei_mirror: respect `./' and `../' prefixes for CLI args Eric Wong
2022-11-28  5:32 ` [PATCH 78/95] lei_mirror: --manifest= affects destination, too Eric Wong
2022-11-28  5:32 ` [PATCH 79/95] lei_mirror: update fingerprints when writing local manifest.js.gz Eric Wong
2022-11-28  5:32 ` [PATCH 80/95] lei_mirror: remove janky mirror.done stamp file Eric Wong
2022-11-28  5:32 ` [PATCH 81/95] lei_mirror: simplify most process spawning Eric Wong
2022-11-28  5:32 ` [PATCH 82/95] lei_mirror: run v1_done earlier on forkgroup done Eric Wong
2022-11-28  5:32 ` [PATCH 83/95] lei_mirror: simplify forkgroup-related subs Eric Wong
2022-11-28  5:32 ` [PATCH 84/95] lei_mirror: shorten scope mirror objects Eric Wong
2022-11-28  5:32 ` [PATCH 85/95] lei_mirror: set {head} from manifest Eric Wong
2022-11-28  5:32 ` [PATCH 86/95] lei_mirror: support {symlinks} " Eric Wong
2022-11-28  5:32 ` [PATCH 87/95] lei_mirror: eliminate circular references Eric Wong
2022-11-28  5:32 ` [PATCH 88/95] lei_mirror: use curl -z/--timecond if manifest exists Eric Wong
2022-11-28  5:32 ` [PATCH 89/95] lei_mirror: avoid redundant curl `-f' use Eric Wong
2022-11-28  5:32 ` [PATCH 90/95] lei_mirror: omit trailing slash for git remote.*.url Eric Wong
2022-11-28  5:32 ` [PATCH 91/95] lei_mirror: set info/web/last-modified from manifest Eric Wong
2022-11-28  5:32 ` [PATCH 92/95] lei_mirror: don't clobber inbox.config.example if it exists Eric Wong
2022-11-28  5:32 ` [PATCH 93/95] lei_mirror: break out of fgrp fetch iteration early Eric Wong
2022-11-28  5:32 ` [PATCH 94/95] clone: support --project-list= for cgit Eric Wong
2022-11-28  5:32 ` [PATCH 95/95] lei_mirror: handle forkgroup changes 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=20221128053232.291618-31-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).