X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FLeiMirror.pm;h=1ab5e0d898d26a5a842ffd515b2dd17fe9fd35b4;hb=718d054be8b2cc23635b42e8ce880424492d3a84;hp=fe1cefe20e4f1e1f6ff63beb5ff5753274c1f9b1;hpb=715f2505c0aab512ed99631697c0c3edf0062c26;p=public-inbox.git
diff --git a/lib/PublicInbox/LeiMirror.pm b/lib/PublicInbox/LeiMirror.pm
index fe1cefe2..1ab5e0d8 100644
--- a/lib/PublicInbox/LeiMirror.pm
+++ b/lib/PublicInbox/LeiMirror.pm
@@ -1,17 +1,19 @@
# Copyright (C) 2021 all contributors
# License: AGPL-3.0+
-# "lei add-external --mirror" support
+# "lei add-external --mirror" support (also "public-inbox-clone");
package PublicInbox::LeiMirror;
use strict;
use v5.10.1;
use parent qw(PublicInbox::IPC);
+use PublicInbox::Config;
use IO::Uncompress::Gunzip qw(gunzip $GunzipError);
-use PublicInbox::Spawn qw(popen_rd spawn);
+use IO::Compress::Gzip qw(gzip $GzipError);
+use PublicInbox::Spawn qw(popen_rd spawn run_die);
use File::Temp ();
-use Fcntl qw(SEEK_SET);
+use Fcntl qw(SEEK_SET O_CREAT O_EXCL O_WRONLY);
-sub do_finish_mirror { # dwaitpid callback
+sub _wq_done_wait { # dwaitpid callback (via wq_eof)
my ($arg, $pid) = @_;
my ($mrr, $lei) = @$arg;
my $f = "$mrr->{dst}/mirror.done";
@@ -28,12 +30,6 @@ sub do_finish_mirror { # dwaitpid callback
$lei->dclose;
}
-sub _lei_wq_eof { # EOF callback for main daemon
- my ($lei) = @_;
- my $mrr = delete $lei->{wq1} or return $lei->fail;
- $mrr->wq_wait_old(\&do_finish_mirror, $lei);
-}
-
# for old installations without manifest.js.gz
sub try_scrape {
my ($self) = @_;
@@ -48,15 +44,19 @@ sub try_scrape {
# we grep with URL below, we don't want Subject/From headers
# making us clone random URLs
- my @urls = ($html =~ m!\bgit clone --mirror ([a-z\+]+://\S+)!g);
+ my @html = split(/
/, $html);
+ my @urls = ($html[-1] =~ m!\bgit clone --mirror ([a-z\+]+://\S+)!g);
my $url = $uri->as_string;
chop($url) eq '/' or die "BUG: $uri not canonicalized";
# since this is for old instances w/o manifest.js.gz, try v1 first
return clone_v1($self) if grep(m!\A\Q$url\E/*\z!, @urls);
if (my @v2_urls = grep(m!\A\Q$url\E/[0-9]+\z!, @urls)) {
- my %v2_uris = map { $_ => URI->new($_) } @v2_urls; # uniq
- return clone_v2($self, [ values %v2_uris ]);
+ my %v2_epochs = map {
+ my ($n) = (m!/([0-9]+)\z!);
+ $n => URI->new($_)
+ } @v2_urls; # uniq
+ return clone_v2($self, \%v2_epochs);
}
# filter out common URLs served by WWW (e.g /$MSGID/T/)
@@ -176,7 +176,7 @@ sub index_cloned_inbox {
PublicInbox::Admin::progress_prepare($opt, $lei->{2});
PublicInbox::Admin::index_inbox($ibx, undef, $opt);
}
- open my $x, '>', "$self->{dst}/mirror.done"; # for do_finish_mirror
+ open my $x, '>', "$self->{dst}/mirror.done"; # for _wq_done_wait
}
sub run_reap {
@@ -187,7 +187,9 @@ sub run_reap {
my $reap = PublicInbox::OnDestroy->new($lei->can('sigint_reap'), $pid);
waitpid($pid, 0) == $pid or die "waitpid @$cmd: $!";
@$reap = (); # cancel reap
- $?
+ my $ret = $?;
+ $? = 0; # don't let it influence normal exit
+ $ret;
}
sub clone_v1 {
@@ -195,42 +197,127 @@ sub clone_v1 {
my $lei = $self->{lei};
my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return;
my $uri = URI->new($self->{src});
+ defined($lei->{opt}->{epoch}) and
+ die "$uri is a v1 inbox, --epoch is not supported\n";
my $pfx = $curl->torsocks($lei, $uri) or return;
my $cmd = [ @$pfx, clone_cmd($lei, my $opt = {}),
$uri->as_string, $self->{dst} ];
my $cerr = run_reap($lei, $cmd, $opt);
return $lei->child_error($cerr, "@$cmd failed") if $cerr;
_try_config($self);
+ write_makefile($self->{dst}, 1);
index_cloned_inbox($self, 1);
}
-sub clone_v2 {
- my ($self, $v2_uris) = @_;
+sub parse_epochs ($$) {
+ my ($opt_epochs, $v2_epochs) = @_; # $epcohs "LOW..HIGH"
+ $opt_epochs // return; # undef => all epochs
+ my ($lo, $dotdot, $hi, @extra) = split(/(\.\.)/, $opt_epochs);
+ undef($lo) if ($lo // '') eq '';
+ my $re = qr/\A~?[0-9]+\z/;
+ if (@extra || (($lo // '0') !~ $re) ||
+ (($hi // '0') !~ $re) ||
+ !(grep(defined, $lo, $hi))) {
+ die < $b } keys %$v2_epochs;
+ for (grep(defined, $lo, $hi)) {
+ if (/\A[0-9]+\z/) {
+ $_ > $n[-1] and die
+"`$_' exceeds maximum available epoch ($n[-1])\n";
+ $_ < $n[0] and die
+"`$_' is lower than minimum available epoch ($n[0])\n";
+ } elsif (/\A~([0-9]+)/) {
+ my $off = -$1 - 1;
+ $n[$off] // die "`$_' is out of range\n";
+ $_ = $n[$off];
+ } else { die "`$_' not understood\n" }
+ }
+ defined($lo) && defined($hi) && $lo > $hi and die
+"low value (`$lo') exceeds high (`$hi')\n";
+ $lo //= $n[0] if $dotdot;
+ $hi //= $n[-1] if $dotdot;
+ $hi //= $lo;
+ my $want = {};
+ for ($lo..$hi) {
+ if (defined $v2_epochs->{$_}) {
+ $want->{$_} = 1;
+ } else {
+ warn
+"# epoch $_ is not available (non-fatal, $lo..$hi)\n";
+ }
+ }
+ $want
+}
+
+sub init_placeholder ($$) {
+ my ($src, $edst) = @_;
+ PublicInbox::Import::init_bare($edst);
+ my $f = "$edst/config";
+ open my $fh, '>>', $f or die "open($f): $!";
+ print $fh < manifest.js.gz hashref
my $lei = $self->{lei};
my $curl = $self->{curl} //= PublicInbox::LeiCurl->new($lei) or return;
- my $pfx //= $curl->torsocks($lei, $v2_uris->[0]) or return;
- my @epochs;
+ my $pfx = $curl->torsocks($lei, (values %$v2_epochs)[0]) or return;
my $dst = $self->{dst};
- my @src_edst;
- for my $uri (@$v2_uris) {
+ my $want = parse_epochs($lei->{opt}->{epoch}, $v2_epochs);
+ my (@src_edst, @read_only, @skip_nr);
+ for my $nr (sort { $a <=> $b } keys %$v2_epochs) {
+ my $uri = $v2_epochs->{$nr};
my $src = $uri->as_string;
my $edst = $dst;
$src =~ m!/([0-9]+)(?:\.git)?\z! or die <<"";
failed to extract epoch number from $src
- my $nr = $1 + 0;
+ $1 + 0 == $nr or die "BUG: <$uri> miskeyed $1 != $nr";
$edst .= "/git/$nr.git";
- push @src_edst, [ $src, $edst ];
+ if (!$want || $want->{$nr}) {
+ push @src_edst, $src, $edst;
+ } else { # create a placeholder so users only need to chmod +w
+ init_placeholder($src, $edst);
+ push @read_only, $edst;
+ push @skip_nr, $nr;
+ }
+ }
+ if (@skip_nr) { # filter out the epochs we skipped
+ my $re = join('|', @skip_nr);
+ my @del = grep(m!/git/$re\.git\z!, keys %$m);
+ delete @$m{@del};
+ $self->{-culled_manifest} = 1;
}
my $lk = bless { lock_path => "$dst/inbox.lock" }, 'PublicInbox::Lock';
_try_config($self);
my $on_destroy = $lk->lock_for_scope($$);
my @cmd = clone_cmd($lei, my $opt = {});
- while (my $pair = shift(@src_edst)) {
- my $cmd = [ @$pfx, @cmd, @$pair ];
+ while (my ($src, $edst) = splice(@src_edst, 0, 2)) {
+ my $cmd = [ @$pfx, @cmd, $src, $edst ];
my $cerr = run_reap($lei, $cmd, $opt);
return $lei->child_error($cerr, "@$cmd failed") if $cerr;
}
+ require PublicInbox::MultiGit;
+ my $mg = PublicInbox::MultiGit->new($dst, 'all.git', 'git');
+ $mg->fill_alternates;
+ for my $i ($mg->git_epochs) { $mg->epoch_cfg_set($i) }
+ for my $edst (@read_only) {
+ my @st = stat($edst) or die "stat($edst): $!";
+ chmod($st[2] & 0555, $edst) or die "chmod(a-w, $edst): $!";
+ }
+ write_makefile($self->{dst}, 2);
undef $on_destroy; # unlock
index_cloned_inbox($self, 2);
}
@@ -238,15 +325,15 @@ failed to extract epoch number from $src
# PSGI mount prefixes and manifest.js.gz prefixes don't always align...
sub deduce_epochs ($$) {
my ($m, $path) = @_;
- my ($v1_bare, @v2_epochs);
+ my ($v1_ent, @v2_epochs);
my $path_pfx = '';
$path =~ s!/+\z!!;
do {
- $v1_bare = $m->{$path};
+ $v1_ent = $m->{$path};
@v2_epochs = grep(m!\A\Q$path\E/git/[0-9]+\.git\z!, keys %$m);
- } while (!defined($v1_bare) && !@v2_epochs &&
+ } while (!defined($v1_ent) && !@v2_epochs &&
$path =~ s!\A(/[^/]+)/!/! and $path_pfx .= $1);
- ($path_pfx, $v1_bare, @v2_epochs);
+ ($path_pfx, $v1_ent ? $path : undef, @v2_epochs);
}
sub decode_manifest ($$$) {
@@ -271,39 +358,53 @@ sub try_manifest {
$uri->path($path . '/manifest.js.gz');
my $pdir = $lei->rel2abs($self->{dst});
$pdir =~ s!/[^/]+/?\z!!;
- my $ft = File::Temp->new(TEMPLATE => 'manifest-XXXX',
- UNLINK => 1, DIR => $pdir);
+ my $ft = File::Temp->new(TEMPLATE => 'm-XXXX',
+ UNLINK => 1, DIR => $pdir, SUFFIX => '.tmp');
my $fn = $ft->filename;
- my $cmd = $curl->for_uri($lei, $uri, '-R', '-o', $fn);
- my $opt = { 0 => $lei->{0}, 1 => $lei->{1}, 2 => $lei->{2} };
+ my ($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, $opt);
if ($cerr) {
return try_scrape($self) if ($cerr >> 8) == 22; # 404 missing
return $lei->child_error($cerr, "@$cmd failed");
}
- my $m = decode_manifest($ft, $fn, $uri);
- my ($path_pfx, $v1_bare, @v2_epochs) = deduce_epochs($m, $path);
+ my $m = eval { decode_manifest($ft, $fn, $uri) };
+ if ($@) {
+ warn $@;
+ return try_scrape($self);
+ }
+ my ($path_pfx, $v1_path, @v2_epochs) = deduce_epochs($m, $path);
if (@v2_epochs) {
# It may be possible to have v1 + v2 in parallel someday:
- $lei->err(<err(<path($path_pfx.$_);
- $uri->clone
+ my ($n) = ("$uri" =~ m!/([0-9]+)\.git\z!);
+ $n => $uri->clone
} @v2_epochs;
- clone_v2($self, \@v2_epochs);
- my $fin = "$self->{dst}/manifest.js.gz";
- rename($fn, $fin) or die "E: rename($fn, $fin): $!";
- $ft->unlink_on_destroy(0);
- } elsif (defined $v1_bare) {
+ clone_v2($self, \%v2_epochs, $m);
+ } elsif (defined $v1_path) {
clone_v1($self);
} else {
die "E: confused by <$uri>, possible matches:\n\t",
join(', ', sort keys %$m), "\n";
}
+ if (delete $self->{-culled_manifest}) { # set by clone_v2
+ # 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
+ my $json = PublicInbox::Config->json->encode($m);
+ gzip(\$json => $fn) or die "gzip: $GzipError";
+ }
+ my $fin = "$self->{dst}/manifest.js.gz";
+ rename($fn, $fin) or die "E: rename($fn, $fin): $!";
+ $ft->unlink_on_destroy(0);
}
sub start_clone_url {
@@ -353,4 +454,61 @@ sub ipc_atfork_child {
$self->SUPER::ipc_atfork_child;
}
+sub write_makefile {
+ my ($dir, $ibx_ver) = @_;
+ my $f = "$dir/Makefile";
+ if (sysopen my $fh, $f, O_CREAT|O_EXCL|O_WRONLY) {
+ print $fh <