new public-inbox-{clone,fetch} commands

Setting up and maintaining git-only mirrors of v2 inboxes is
complex since multiple commands are required to clone and fetch
into epochs.

Unlike grokmirror, these commands do not require any
configuration.  Instead, they rely on existing git config files
and work like "git clone --mirror" and "git fetch",
respectively.

Like grokmirror, they use manifest.js.gz, but only on a
per-inbox basis so users won't have to clone every inbox of a
large instance nor edit config files to include/exclude inboxes
they're interested in.

2 files changed, 93 insertions, 0 deletions

diff --git a/script/public-inbox-clone b/script/public-inbox-clone
new file mode 100755
index 00000000..2b18969f
--- /dev/null
+++ b/script/public-inbox-clone
@@ -0,0 +1,58 @@
+#!perl -w
+# Copyright (C) all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+# Wrapper to git clone remote public-inboxes
+use strict;
+use v5.10.1;
+use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
+my $opt = {};
+my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
+usage: public-inbox-clone INBOX_URL [DESTINATION]
+
+  clone remote public-inboxes
+
+options:
+
+  --torsocks VAL      whether or not to wrap git and curl commands with
+                      torsocks (default: `auto')
+                      Must be one of: `auto', `no' or `yes'
+  --verbose | -v      increase verbosity (may be repeated)
+    --quiet | -q      increase verbosity (may be repeated)
+    -C DIR            chdir to specified directory
+EOF
+GetOptions($opt, qw(help|h quiet|q verbose|v+ C=s@ c=s@
+                no-torsocks torsocks=s)) or die $help;
+if ($opt->{help}) { print $help; exit };
+require PublicInbox::Admin; # loads Config
+PublicInbox::Admin::do_chdir(delete $opt->{C});
+PublicInbox::Admin::setup_signals();
+$SIG{PIPE} = 'IGNORE';
+
+my ($url, $dst, $extra) = @ARGV;
+die $help if !defined($url) || defined($extra);
+defined($dst) or ($dst) = ($url =~ m!/([^/]+)/?\z!);
+index($dst, "\n") >= 0 and die "`\\n' not allowed in `$dst'";
+
+# n.b. this is still a truckload of code...
+require URI;
+require PublicInbox::LEI;
+require PublicInbox::LeiExternal;
+require PublicInbox::LeiMirror;
+require PublicInbox::LeiCurl;
+require PublicInbox::Lock;
+
+$url = PublicInbox::LeiExternal::ext_canonicalize($url);
+my $lei = bless {
+        env => \%ENV, opt => $opt, cmd => 'public-inbox-clone',
+        0 => *STDIN{GLOB}, 2 => *STDERR{GLOB},
+}, 'PublicInbox::LEI';
+open $lei->{1}, '+<&=', 1 or die "dup: $!";
+open $lei->{3}, '.' or die "open . $!";
+my $mrr = bless {
+        lei => $lei,
+        src => $url,
+        dst => $dst,
+}, 'PublicInbox::LeiMirror';
+$mrr->do_mirror;
+$mrr->can('do_finish_mirror')->([$mrr, $lei], $$);
+exit(($lei->{child_error} // 0) >> 8);
diff --git a/script/public-inbox-fetch b/script/public-inbox-fetch
new file mode 100755
index 00000000..5d303574
--- /dev/null
+++ b/script/public-inbox-fetch
@@ -0,0 +1,35 @@
+#!perl -w
+# Copyright (C) all contributors <meta@public-inbox.org>
+# License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
+# Wrapper to git fetch remote public-inboxes
+use strict;
+use v5.10.1;
+use Getopt::Long qw(:config gnu_getopt no_ignore_case auto_abbrev);
+my $opt = {};
+my $help = <<EOF; # the following should fit w/o scrolling in 80x24 term:
+usage: public-inbox-fetch -C DESTINATION
+
+  fetch remote public-inboxes
+
+options:
+
+  --torsocks VAL      whether or not to wrap git and curl commands with
+                      torsocks (default: `auto')
+                      Must be one of: `auto', `no' or `yes'
+  --verbose | -v      increase verbosity (may be repeated)
+    --quiet | -q      increase verbosity (may be repeated)
+    -C DIR            chdir to specified directory
+EOF
+GetOptions($opt, qw(help|h quiet|q verbose|v+ C=s@ c=s@
+        no-torsocks torsocks=s)) or die $help;
+if ($opt->{help}) { print $help; exit };
+require PublicInbox::Fetch; # loads Admin
+PublicInbox::Admin::do_chdir(delete $opt->{C});
+PublicInbox::Admin::setup_signals();
+$SIG{PIPE} = 'IGNORE';
+
+my $lei = bless {
+        env => \%ENV, opt => $opt, cmd => 'public-inbox-fetch',
+        0 => *STDIN{GLOB}, 1 => *STDOUT{GLOB}, 2 => *STDERR{GLOB},
+}, 'PublicInbox::LEI';
+PublicInbox::Fetch->do_fetch($lei, '.');