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 02/95] clone: support --include and --exclude with multi-clone
Date: Mon, 28 Nov 2022 05:30:59 +0000	[thread overview]
Message-ID: <20221128053232.291618-3-e@80x24.org> (raw)
In-Reply-To: <20221128053232.291618-1-e@80x24.org>

These will be handy when someone is interested in a subset of
inboxes on a large hosting site.
---
 Documentation/public-inbox-clone.pod | 14 +++++++++++++
 lib/PublicInbox/LeiMirror.pm         | 31 +++++++++++++++++++++++++---
 script/public-inbox-clone            |  2 +-
 t/www_listing.t                      | 22 ++++++++++++++++++++
 4 files changed, 65 insertions(+), 4 deletions(-)

diff --git a/Documentation/public-inbox-clone.pod b/Documentation/public-inbox-clone.pod
index c80c3c5f..7e95146e 100644
--- a/Documentation/public-inbox-clone.pod
+++ b/Documentation/public-inbox-clone.pod
@@ -51,6 +51,20 @@ C<--epoch=~2..> clones the three latest epochs.
 Default: C<0..~0> or C<0..> or C<..~0>
 (all epochs, all three examples are equivalent)
 
+=item -I PATTERN
+
+=item --include=PATTERN
+
+When cloning a top-level with multiple inboxes, only clone inboxes and
+repositories matching a given wildcard pattern (using C<*?> and C<[]> is
+supported).
+
+=item --exclude=PATTERN
+
+When cloning a top-level with multiple inboxes, ignore inboxes and
+repositories matching the given wildcard pattern.  Supports the same
+wildcards as L</--include>
+
 =item -q
 
 =item --quiet
diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index e356b5c5..d5017642 100644
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -347,6 +347,8 @@ sub decode_manifest ($$$) {
 
 sub multi_inbox ($$$) {
 	my ($self, $path, $m) = @_;
+	my $incl = $self->{lei}->{opt}->{include};
+	my $excl = $self->{lei}->{opt}->{exclude};
 
 	# assuming everything not v2 is v1, for now
 	my @v1 = sort grep(!m!.+/git/[0-9]+\.git\z!, keys %$m);
@@ -354,13 +356,35 @@ sub multi_inbox ($$$) {
 	my $v2 = {};
 
 	for (@v2_epochs) {
-		m!\A/(.+)/git/[0-9]+\.git\z! or die "BUG: $_";
+		m!\A(/.+)/git/[0-9]+\.git\z! or die "BUG: $_";
 		push @{$v2->{$1}}, $_;
 	}
 	my $n = scalar(keys %$v2) + scalar(@v1);
-	my $ret; # { v1 => [ ... ], v2 => { $inbox_name => [ epochs ] }}
+	my @orig = defined($incl // $excl) ? (keys %$v2, @v1) : ();
+	if (defined $incl) {
+		my $re = '(?:'.join('|', map {
+				$self->{lei}->glob2re($_) // qr/\A\Q$_\E\z/
+			} @$incl).')';
+		my @gone = delete @$v2{grep(!/$re/, keys %$v2)};
+		delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1;
+		delete @$m{grep(!/$re/, @v1)} and $self->{-culled_manifest} = 1;
+		@v1 = grep(/$re/, @v1);
+	}
+	if (defined $excl) {
+		my $re = '(?:'.join('|', map {
+				$self->{lei}->glob2re($_) // qr/\A\Q$_\E\z/
+			} @$excl).')';
+		my @gone = delete @$v2{grep(/$re/, keys %$v2)};
+		delete @$m{map { @$_ } @gone} and $self->{-culled_manifest} = 1;
+		delete @$m{grep(/$re/, @v1)} and $self->{-culled_manifest} = 1;
+		@v1 = grep(!/$re/, @v1);
+	}
+	my $ret; # { v1 => [ ... ], v2 => { "/$inbox_name" => [ epochs ] }}
 	$ret->{v1} = \@v1 if @v1;
 	$ret->{v2} = $v2 if keys %$v2;
+	$ret //= @orig ? "Nothing to clone, available repositories:\n\t".
+				join("\n\t", sort @orig)
+			: "Nothing available to clone\n";
 	my $path_pfx = '';
 
 	# PSGI mount prefixes and manifest.js.gz prefixes don't always align...
@@ -407,6 +431,7 @@ sub try_manifest {
 		return try_scrape($self);
 	}
 	my ($path_pfx, $n, $multi) = multi_inbox($self, \$path, $m);
+	return $lei->child_error(1, $multi) if !ref($multi);
 	if (my $v2 = delete $multi->{v2}) {
 		for my $name (sort keys %$v2) {
 			my $epochs = delete $v2->{$name};
@@ -449,7 +474,7 @@ EOM
 			clone_v1($self, 1);
 		}
 	}
-	if (delete $self->{-culled_manifest}) { # set by clone_v2
+	if (delete $self->{-culled_manifest}) { # set by clone_v2/-I/--exclude
 		# write the smaller manifest if epochs were skipped so
 		# users won't have to delete manifest if they +w an
 		# epoch they no longer want to skip
diff --git a/script/public-inbox-clone b/script/public-inbox-clone
index 54059d03..4244e0c8 100755
--- a/script/public-inbox-clone
+++ b/script/public-inbox-clone
@@ -21,7 +21,7 @@ options:
     --quiet | -q      increase verbosity (may be repeated)
     -C DIR            chdir to specified directory
 EOF
-GetOptions($opt, qw(help|h quiet|q verbose|v+ C=s@ c=s@
+GetOptions($opt, qw(help|h quiet|q verbose|v+ C=s@ c=s@ include|I=s@ exclude=s@
 		no-torsocks torsocks=s epoch=s)) or die $help;
 if ($opt->{help}) { print $help; exit };
 require PublicInbox::Admin; # loads Config
diff --git a/t/www_listing.t b/t/www_listing.t
index e88bfbc5..e6bb1bda 100644
--- a/t/www_listing.t
+++ b/t/www_listing.t
@@ -135,8 +135,29 @@ EOM
 	my $opt = { 2 => \(my $clone_err = '') };
 	ok(run_script(['-clone', "http://$host:$port/pfx", "$tmpdir/pfx" ],
 		undef, $opt), 'pfx clone w/pfx') or diag "clone_err=$clone_err";
+
+	open my $mh, '<', "$tmpdir/pfx/manifest.js.gz" or xbail "open: $!";
+	gunzip(\(do { local $/; <$mh> }) => \(my $mjs = ''));
+	my $mf = $json->decode($mjs);
+	is_deeply([sort keys %$mf], [ qw(/alt /bare /v2/git/0.git
+					/v2/git/1.git /v2/git/2.git) ],
+		'manifest saved');
+	for (keys %$mf) { ok(-d "$tmpdir/pfx$_", "pfx/$_ cloned") }
+
+	$clone_err = '';
+	ok(run_script(['-clone', '--include=*/alt',
+			"http://$host:$port/pfx", "$tmpdir/incl" ],
+		undef, $opt), 'clone w/include') or diag "clone_err=$clone_err";
+	ok(-d "$tmpdir/incl/alt", 'alt cloned');
+	ok(!-d "$tmpdir/incl/v2" && !-d "$tmpdir/incl/bare", 'only alt cloned');
+
 	undef $td;
 
+	open $mh, '<', "$tmpdir/incl/manifest.js.gz" or xbail "open: $!";
+	gunzip(\(do { local $/; <$mh> }) => \($mjs = ''));
+	$mf = $json->decode($mjs);
+	is_deeply([keys %$mf], [ '/alt' ], 'excluded keys skipped in manifest');
+
 	$td = start_script($cmd, $env, { 3 => $sock });
 
 	# default publicinboxGrokManifest match=domain default
@@ -146,6 +167,7 @@ EOM
 	$clone_err = '';
 	ok(run_script(['-clone', "http://$host:$port/", "$tmpdir/full" ],
 		undef, $opt), 'full clone') or diag "clone_err=$clone_err";
+	ok(-d "$tmpdir/full/$_", "$_ cloned") for qw(alt v2 bare);
 
 	undef $td;
 

  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 ` Eric Wong [this message]
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 ` [PATCH 30/95] lei_mirror: do not fetch descriptions if using manifest Eric Wong
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=20221128053232.291618-3-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).