From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <e@80x24.org>
X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net
X-Spam-Level: 
X-Spam-ASN:  
X-Spam-Status: No, score=-3.9 required=3.0 tests=ALL_TRUSTED,AWL,BAYES_00,
	DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF shortcircuit=no
	autolearn=ham autolearn_force=no version=3.4.2
Received: from localhost (dcvr.yhbt.net [127.0.0.1])
	by dcvr.yhbt.net (Postfix) with ESMTP id DB48B203D5
	for <meta@public-inbox.org>; Mon, 28 Nov 2022 05:32:52 +0000 (UTC)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=80x24.org;
	s=selector1; t=1669613572;
	bh=5nInRM5uuFJ7a7jmzZrxqJ4smJersv0x/RK6wKdaQEI=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=ZFa1q3wl8LKCdUBH/0x4bqqUu5HSq9onaVYK0b+JbBj0I2RXGcnTCKgMcLNWO7dNt
	 1ZcH0JYtOtzZikqlJF1C/xv7J7ATLBTf2rVyFbeH7StbWH2O1a4cSyQGsjQmxgqHOv
	 ign2bvvxPvpzC2owgR9Po3CmPmBXTB9vDzWPEjAk=
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 94/95] clone: support --project-list= for cgit
Date: Mon, 28 Nov 2022 05:32:31 +0000
Message-Id: <20221128053232.291618-95-e@80x24.org>
In-Reply-To: <20221128053232.291618-1-e@80x24.org>
References: <20221128053232.291618-1-e@80x24.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
List-Id: <meta.public-inbox.org>

grokmirror supports it, and we also support cgit, so this should
make running mirrors easier.  This will be useful for scripting
purposes, too.
---
 lib/PublicInbox/LeiMirror.pm | 39 +++++++++++++++++++++++++++++++++---
 script/public-inbox-clone    |  4 ++++
 2 files changed, 40 insertions(+), 3 deletions(-)

diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index 0508c9a8..d4b14699 100644
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -991,6 +991,34 @@ sub dump_manifest ($$) {
 	utime($mtime, $mtime, "$ft") or die "utime(..., $ft): $!";
 }
 
+sub dump_project_list ($$) {
+	my ($self, $m) = @_;
+	my $f = $self->{'-project-list'} // return;
+	my $old = PublicInbox::Git::try_cat($f);
+	my %new;
+
+	open my $dh, '<', '.' or die "open(.): $!";
+	chdir($self->{dst}) or die "chdir($self->{dst}): $!";
+	my @local = grep { -e $_ ? ($new{$_} = undef) : 1 } split(/\n/s, $old);
+	chdir($dh) or die "chdir(restore): $!";
+
+	$new{substr($_, 1)} = 1 for keys %$m; # drop leading '/'
+	my @list = sort keys %new;
+	my @remote = grep { !defined($new{$_}) } @list;
+
+	warn <<EOM if @remote;
+The following local repositories are ignored/gone from $self->{src}:
+EOM
+	warn "\t", $_, "\n" for @remote;
+	warn <<EOM if @local;
+The following repos in $f no longer exist on the filesystem:
+EOM
+	warn "\t", $_, "\n" for @local;
+
+	my (undef, $dn, $bn) = File::Spec->splitpath($f);
+	atomic_write($dn, $bn, join("\n", @list, ''));
+}
+
 # FIXME: this gets confused by single inbox instance w/ global manifest.js.gz
 sub try_manifest {
 	my ($self) = @_;
@@ -1104,6 +1132,7 @@ EOM
 	warn(<<EOM, map { ("\t", $_, "\n") } @$bad) if $bad;
 W: The following exist and have not been converted to symlinks
 EOM
+	dump_project_list($self, $m);
 	ft_rename($ft, $manifest, 0666);
 }
 
@@ -1124,14 +1153,18 @@ sub do_mirror { # via wq_io_do or public-inbox-clone
 		$ic =~ /\A(?:v1|v2|always|never)\z/s or die <<"";
 --inbox-config must be one of `always', `v2', `v1', or `never'
 
-		# we support --objstore= and --manifest= with '' (empty string)
-		for my $default (qw(objstore manifest.js.gz)) {
-			my ($k) = (split(/\./, $default))[0];
+		# we support these switches with '' (empty string).
+		# defaults match example conf distributed with grokmirror
+		my @pairs = qw(objstore objstore manifest manifest.js.gz
+				project-list projects.list);
+		while (@pairs) {
+			my ($k, $default) = splice(@pairs, 0, 2);
 			my $v = $lei->{opt}->{$k} // next;
 			$v = $default if $v eq '';
 			$v = "$self->{dst}/$v" if $v !~ m!\A\.{0,2}/!;
 			$self->{"-$k"} = $v;
 		}
+
 		local $LIVE = {};
 		local $TODO = {};
 		local $FGRP_TODO = {};
diff --git a/script/public-inbox-clone b/script/public-inbox-clone
index efe0cff6..677c56c8 100755
--- a/script/public-inbox-clone
+++ b/script/public-inbox-clone
@@ -22,8 +22,12 @@ options:
     --quiet | -q      increase verbosity (may be repeated)
     -C DIR            chdir to specified directory
 EOF
+
+# cgit calls it `project-list', grokmirror calls it `projectslist',
+# support both :/
 GetOptions($opt, qw(help|h quiet|q verbose|v+ C=s@ c=s@ include|I=s@ exclude=s@
 	inbox-config=s inbox-version=i objstore=s manifest=s
+	project-list|projectslist=s
 	prune|p keep-going|k
 	dry-run|n jobs|j=i no-torsocks torsocks=s epoch=s)) or die $help;
 if ($opt->{help}) { print $help; exit };