It still makes HTTP(S) requests to retrieve the manifest or
scrape HTML, but doesn't make permanent changes to the FS
(aside from modifying {acm}time of ${TMPDIR-/tmp}).
repositories matching the given wildcard pattern. Supports the same
wildcards as L</--include>
repositories matching the given wildcard pattern. Supports the same
wildcards as L</--include>
+=item -n
+
+=item --dry-run
+
+Show what would be done, without making any changes.
+
my $f = "$mrr->{dst}/mirror.done";
if ($?) {
$lei->child_error($?);
my $f = "$mrr->{dst}/mirror.done";
if ($?) {
$lei->child_error($?);
- } elsif (!unlink($f)) {
+ } elsif (!$mrr->{dry_run} && !unlink($f)) {
warn("unlink($f): $!\n") unless $!{ENOENT};
} else {
warn("unlink($f): $!\n") unless $!{ENOENT};
} else {
- if ($lei->{cmd} ne 'public-inbox-clone') {
+ if (!$mrr->{dry_run} && $lei->{cmd} ne 'public-inbox-clone') {
# calls _finish_add_external
$lei->lazy_cb('add-external', '_finish_'
)->($lei, $mrr->{dst});
# calls _finish_add_external
$lei->lazy_cb('add-external', '_finish_'
)->($lei, $mrr->{dst});
my @st = stat($dst);
my $mode = @st ? ($st[2] & 07777) : ($open_mode & ~umask);
chmod($mode, $ft) or croak "E: chmod $fn: $!";
my @st = stat($dst);
my $mode = @st ? ($st[2] & 07777) : ($open_mode & ~umask);
chmod($mode, $ft) or croak "E: chmod $fn: $!";
- rename($fn, $dst) or croak "E: rename($fn => $ft): $!";
+ require File::Copy;
+ File::Copy::mv($fn, $dst) or croak "E: mv($fn => $ft): $!";
$ft->unlink_on_destroy(0);
}
$ft->unlink_on_destroy(0);
}
my $opt = { 0 => $lei->{0}, 1 => $lei->{1}, 2 => $lei->{2} };
my $cmd = $self->{curl}->for_uri($lei, $uri, qw(--compressed -R -o),
$ft->filename);
my $opt = { 0 => $lei->{0}, 1 => $lei->{1}, 2 => $lei->{2} };
my $cmd = $self->{curl}->for_uri($lei, $uri, qw(--compressed -R -o),
$ft->filename);
- $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ];
my $jobs = $lei->{opt}->{jobs} // 1;
reap_live() while keys(%LIVE) >= $jobs;
$lei->qerr("# @$cmd");
my $jobs = $lei->{opt}->{jobs} // 1;
reap_live() while keys(%LIVE) >= $jobs;
$lei->qerr("# @$cmd");
+ return if $self->{dry_run};
+ $self->{"-get_txt.$endpoint"} = [ $ft, $cmd, $uri ];
$LIVE{spawn($cmd, undef, $opt)} =
[ \&_get_txt_done, $self, $endpoint, $fini ];
}
$LIVE{spawn($cmd, undef, $opt)} =
[ \&_get_txt_done, $self, $endpoint, $fini ];
}
my $jobs = $self->{lei}->{opt}->{jobs} // 1;
reap_live() while keys(%LIVE) >= $jobs;
$self->{lei}->qerr("# @$cmd");
my $jobs = $self->{lei}->{opt}->{jobs} // 1;
reap_live() while keys(%LIVE) >= $jobs;
$self->{lei}->qerr("# @$cmd");
+ return if $self->{dry_run};
$LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ];
}
$LIVE{spawn($cmd, undef, $opt)} = [ \&reap_clone, $self, $cmd, $fini ];
}
sub v1_done { # called via OnDestroy
my ($self) = @_;
sub v1_done { # called via OnDestroy
my ($self) = @_;
+ return if $self->{dry_run};
_write_inbox_config($self);
my $dst = $self->{cur_dst} // $self->{dst};
if (defined(my $o = $self->{-ent} ? $self->{-ent}->{owner} : undef)) {
_write_inbox_config($self);
my $dst = $self->{cur_dst} // $self->{dst};
if (defined(my $o = $self->{-ent} ? $self->{-ent}->{owner} : undef)) {
sub v2_done { # called via OnDestroy
my ($self) = @_;
sub v2_done { # called via OnDestroy
my ($self) = @_;
+ return if $self->{dry_run};
_write_inbox_config($self);
require PublicInbox::MultiGit;
my $dst = $self->{cur_dst} // $self->{dst};
_write_inbox_config($self);
require PublicInbox::MultiGit;
my $dst = $self->{cur_dst} // $self->{dst};
# filter out the epochs we skipped
$self->{-culled_manifest} = 1 if delete(@$m{@skip});
# filter out the epochs we skipped
$self->{-culled_manifest} = 1 if delete(@$m{@skip});
- -d $dst || File::Path::mkpath($dst);
+ (!$self->{dry_run} && !-d $dst) and File::Path::mkpath($dst);
+
require PublicInbox::Lock;
my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task);
require PublicInbox::Lock;
my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
my $fini = PublicInbox::OnDestroy->new($$, \&v2_done, $task);
_get_txt_start($task, '_/text/config/raw', $fini);
_get_txt_start($self, 'description', $fini);
_get_txt_start($task, '_/text/config/raw', $fini);
_get_txt_start($self, 'description', $fini);
- $task->{-locked} = $lk->lock_for_scope($$);
+ $task->{-locked} = $lk->lock_for_scope($$) if !$self->{dry_run};
my @cmd = clone_cmd($lei, my $opt = {});
while (@src_edst && !$lei->{child_error}) {
my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ];
my @cmd = clone_cmd($lei, my $opt = {});
while (@src_edst && !$lei->{child_error}) {
my $cmd = [ @$pfx, @cmd, splice(@src_edst, 0, 2) ];
my $path = $uri->path;
chop($path) eq '/' or die "BUG: $uri not canonicalized";
$uri->path($path . '/manifest.js.gz');
my $path = $uri->path;
chop($path) eq '/' or die "BUG: $uri not canonicalized";
$uri->path($path . '/manifest.js.gz');
- my $pdir = $lei->rel2abs($self->{dst});
- $pdir =~ s!/[^/]+/?\z!!;
- -d $pdir || File::Path::mkpath($pdir);
- my $ft = File::Temp->new(TEMPLATE => 'm-XXXX',
- UNLINK => 1, DIR => $pdir, SUFFIX => '.tmp');
+ my $ft = File::Temp->new(TEMPLATE => '.manifest-XXXX',
+ UNLINK => 1, TMPDIR => 1, SUFFIX => '.tmp');
- my ($bn) = ($fn =~ m!/([^/]+)\z!);
- my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $bn);
- my $opt = { -C => $pdir };
- $opt->{$_} = $lei->{$_} for (0..2);
- my $cerr = run_reap($lei, $cmd, $opt);
+ my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $fn);
+ my %opt = map { $_ => $lei->{$_} } (0..2);
+ my $cerr = run_reap($lei, $cmd, \%opt);
local %LIVE;
if ($cerr) {
return try_scrape($self) if ($cerr >> 8) == 22; # 404 missing
local %LIVE;
if ($cerr) {
return try_scrape($self) if ($cerr >> 8) == 22; # 404 missing
}
}
reap_live() while keys(%LIVE);
}
}
reap_live() while keys(%LIVE);
- return if $self->{lei}->{child_error};
+ return if $self->{lei}->{child_error} || $self->{dry_run};
if (delete $self->{-culled_manifest}) { # set by clone_v2/-I/--exclude
# write the smaller manifest if epochs were skipped so
if (delete $self->{-culled_manifest}) { # set by clone_v2/-I/--exclude
# write the smaller manifest if epochs were skipped so
--torsocks VAL whether or not to wrap git and curl commands with
torsocks (default: `auto')
Must be one of: `auto', `no' or `yes'
--torsocks VAL whether or not to wrap git and curl commands with
torsocks (default: `auto')
Must be one of: `auto', `no' or `yes'
+ --dry-run | -n show what would be cloned without cloning
--verbose | -v increase verbosity (may be repeated)
--quiet | -q increase verbosity (may be repeated)
-C DIR chdir to specified directory
EOF
GetOptions($opt, qw(help|h quiet|q verbose|v+ C=s@ c=s@ include|I=s@ exclude=s@
--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@ include|I=s@ exclude=s@
- jobs|j=i no-torsocks torsocks=s epoch=s)) or die $help;
+ dry-run|n jobs|j=i no-torsocks torsocks=s epoch=s)) or die $help;
if ($opt->{help}) { print $help; exit };
require PublicInbox::Admin; # loads Config
PublicInbox::Admin::do_chdir(delete $opt->{C});
if ($opt->{help}) { print $help; exit };
require PublicInbox::Admin; # loads Config
PublicInbox::Admin::do_chdir(delete $opt->{C});
src => $url,
dst => $dst,
}, 'PublicInbox::LeiMirror';
src => $url,
dst => $dst,
}, 'PublicInbox::LeiMirror';
+
+$? = 0;
+$mrr->{dry_run} = 1 if $lei->{opt}->{'dry-run'};
$mrr->do_mirror;
$mrr->can('_wq_done_wait')->([$mrr, $lei], $$);
exit(($lei->{child_error} // 0) >> 8);
$mrr->do_mirror;
$mrr->can('_wq_done_wait')->([$mrr, $lei], $$);
exit(($lei->{child_error} // 0) >> 8);
is(xqx([qw(git config -f), "$tmpdir/incl/alt/config", 'gitweb.owner']),
"lorelei \xc4\x80\n", 'gitweb.owner set by -clone');
is(xqx([qw(git config -f), "$tmpdir/incl/alt/config", 'gitweb.owner']),
"lorelei \xc4\x80\n", 'gitweb.owner set by -clone');
+ $clone_err = '';
+ ok(run_script(['-clone', '--dry-run',
+ "http://$host:$port/pfx", "$tmpdir/dry-run" ],
+ undef, $opt), 'clone --dry-run') or diag "clone_err=$clone_err";
+ ok(!-d "$tmpdir/dry-run", 'nothing cloned with --dry-run');
+
undef $td;
open $mh, '<', "$tmpdir/incl/manifest.js.gz" or xbail "open: $!";
undef $td;
open $mh, '<', "$tmpdir/incl/manifest.js.gz" or xbail "open: $!";