X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGit.pm;h=084069259110d26e8b043822c0c22ecc4a8a81d7;hb=0d38f65c490466837ae091afa7a7b6f59d04ce7c;hp=e3a2bcb8df8f43d5c3e421852ded73dde2c9a9e2;hpb=28704f95181f193e20856b7b52454e8cf0e57a57;p=public-inbox.git

diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index e3a2bcb8..08406925 100644
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -12,15 +12,19 @@ use v5.10.1;
 use parent qw(Exporter);
 use POSIX ();
 use IO::Handle; # ->autoflush
-use Errno qw(EINTR);
+use Errno qw(EINTR EAGAIN);
 use File::Glob qw(bsd_glob GLOB_NOSORT);
+use File::Spec ();
 use Time::HiRes qw(stat);
 use PublicInbox::Spawn qw(popen_rd);
 use PublicInbox::Tmpfile;
+use IO::Poll qw(POLLIN);
 use Carp qw(croak);
+use Digest::SHA ();
 our @EXPORT_OK = qw(git_unquote git_quote);
 our $PIPE_BUFSIZ = 65536; # Linux default
 our $in_cleanup;
+our $RDTIMEO = 60_000; # milliseconds
 
 use constant MAX_INFLIGHT =>
 	(($^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF()) * 3)
@@ -92,9 +96,9 @@ sub alternates_changed {
 sub last_check_err {
 	my ($self) = @_;
 	my $fh = $self->{err_c} or return;
-	sysseek($fh, 0, 0) or fail($self, "sysseek failed: $!");
+	sysseek($fh, 0, 0) or $self->fail("sysseek failed: $!");
 	defined(sysread($fh, my $buf, -s $fh)) or
-			fail($self, "sysread failed: $!");
+			$self->fail("sysread failed: $!");
 	$buf;
 }
 
@@ -103,19 +107,19 @@ sub _bidi_pipe {
 	if ($self->{$pid}) {
 		if (defined $err) { # "err_c"
 			my $fh = $self->{$err};
-			sysseek($fh, 0, 0) or fail($self, "sysseek failed: $!");
-			truncate($fh, 0) or fail($self, "truncate failed: $!");
+			sysseek($fh, 0, 0) or $self->fail("sysseek failed: $!");
+			truncate($fh, 0) or $self->fail("truncate failed: $!");
 		}
 		return;
 	}
 	my ($out_r, $out_w);
-	pipe($out_r, $out_w) or fail($self, "pipe failed: $!");
+	pipe($out_r, $out_w) or $self->fail("pipe failed: $!");
 	my @cmd = (qw(git), "--git-dir=$self->{git_dir}",
 			qw(-c core.abbrev=40 cat-file), $batch);
 	my $redir = { 0 => $out_r };
 	if ($err) {
 		my $id = "git.$self->{git_dir}$batch.err";
-		my $fh = tmpfile($id) or fail($self, "tmpfile($id): $!");
+		my $fh = tmpfile($id) or $self->fail("tmpfile($id): $!");
 		$self->{$err} = $fh;
 		$redir->{2} = $fh;
 	}
@@ -130,6 +134,8 @@ sub _bidi_pipe {
 	$self->{$in} = $in_r;
 }
 
+sub poll_in ($) { IO::Poll::_poll($RDTIMEO, fileno($_[0]), my $ev = POLLIN) }
+
 sub my_read ($$$) {
 	my ($fh, $rbuf, $len) = @_;
 	my $left = $len - length($$rbuf);
@@ -138,9 +144,12 @@ sub my_read ($$$) {
 		$r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf));
 		if ($r) {
 			$left -= $r;
+		} elsif (defined($r)) { # EOF
+			return 0;
 		} else {
-			next if (!defined($r) && $! == EINTR);
-			return $r;
+			next if ($! == EAGAIN and poll_in($fh));
+			next if $! == EINTR; # may be set by sysread or poll_in
+			return; # unrecoverable error
 		}
 	}
 	\substr($$rbuf, 0, $len, '');
@@ -152,9 +161,15 @@ sub my_readline ($$) {
 		if ((my $n = index($$rbuf, "\n")) >= 0) {
 			return substr($$rbuf, 0, $n + 1, '');
 		}
-		my $r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf));
-		next if $r || (!defined($r) && $! == EINTR);
-		return defined($r) ? '' : undef; # EOF or error
+		my $r = sysread($fh, $$rbuf, $PIPE_BUFSIZ, length($$rbuf))
+								and next;
+
+		# return whatever's left on EOF
+		return substr($$rbuf, 0, length($$rbuf)+1, '') if defined($r);
+
+		next if ($! == EAGAIN and poll_in($fh));
+		next if $! == EINTR; # may be set by sysread or poll_in
+		return; # unrecoverable error
 	}
 }
 
@@ -172,7 +187,7 @@ sub cat_async_retry ($$$$$) {
 	for (my $i = 0; $i < @$inflight; $i += 3) {
 		$buf .= "$inflight->[$i]\n";
 	}
-	print { $self->{out} } $buf or fail($self, "write error: $!");
+	print { $self->{out} } $buf or $self->fail("write error: $!");
 	unshift(@$inflight, \$req, $cb, $arg); # \$ref to indicate retried
 
 	cat_async_step($self, $inflight); # take one step
@@ -202,7 +217,8 @@ sub cat_async_step ($$) {
 		$type = 'missing';
 		$oid = ref($req) ? $$req : $req if $oid eq '';
 	} else {
-		$self->fail("Unexpected result from async git cat-file: $head");
+		my $err = $! ? " ($!)" : '';
+		$self->fail("bad result from async cat-file: $head$err");
 	}
 	$self->{cat_rbuf} = $rbuf if $$rbuf ne '';
 	eval { $cb->($bref, $oid, $type, $size, $arg) };
@@ -249,7 +265,7 @@ sub check_async_step ($$) {
 	# https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/
 	if ($hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop') {
 		my $ret = my_read($self->{in_c}, $rbuf, $type + 1);
-		fail($self, defined($ret) ? 'read EOF' : "read: $!") if !$ret;
+		$self->fail(defined($ret) ? 'read EOF' : "read: $!") if !$ret;
 	}
 	$self->{chk_rbuf} = $rbuf if $$rbuf ne '';
 	eval { $cb->($hex, $type, $size, $arg, $self) };
@@ -278,7 +294,7 @@ sub check_async ($$$$) {
 	while (scalar(@$inflight_c) >= MAX_INFLIGHT) {
 		check_async_step($self, $inflight_c);
 	}
-	print { $self->{out_c} } $oid, "\n" or fail($self, "write error: $!");
+	print { $self->{out_c} } $oid, "\n" or $self->fail("write error: $!");
 	push(@$inflight_c, $oid, $cb, $arg);
 }
 
@@ -331,7 +347,7 @@ sub cat_async_abort ($) {
 	cleanup($self);
 }
 
-sub fail {
+sub fail { # may be augmented in subclasses
 	my ($self, $msg) = @_;
 	cat_async_abort($self);
 	croak(ref($self) . ' ' . ($self->{git_dir} // '') . ": $msg");
@@ -352,13 +368,23 @@ sub qx {
 	<$fh>
 }
 
+# check_async and cat_async may trigger the other, so ensure they're
+# both completely done by using this:
+sub async_wait_all ($) {
+	my ($self) = @_;
+	while (scalar(@{$self->{inflight_c} // []}) ||
+			scalar(@{$self->{inflight} // []})) {
+		$self->check_async_wait;
+		$self->cat_async_wait;
+	}
+}
+
 # returns true if there are pending "git cat-file" processes
 sub cleanup {
 	my ($self) = @_;
 	local $in_cleanup = 1;
 	delete $self->{async_cat};
-	check_async_wait($self);
-	cat_async_wait($self);
+	async_wait_all($self);
 	delete $self->{inflight};
 	delete $self->{inflight_c};
 	_destroy($self, qw(cat_rbuf in out pid));
@@ -423,7 +449,7 @@ sub cat_async ($$$;$) {
 	while (scalar(@$inflight) >= MAX_INFLIGHT) {
 		cat_async_step($self, $inflight);
 	}
-	print { $self->{out} } $oid, "\n" or fail($self, "write error: $!");
+	print { $self->{out} } $oid, "\n" or $self->fail("write error: $!");
 	push(@$inflight, $oid, $cb, $arg);
 }
 
@@ -434,7 +460,7 @@ sub async_prefetch {
 		# but lets not allow one client to monopolize a git process
 		if (scalar(@$inflight) < int(MAX_INFLIGHT/2)) {
 			print { $self->{out} } $oid, "\n" or
-						fail($self, "write error: $!");
+						$self->fail("write error: $!");
 			return push(@$inflight, $oid, $cb, $arg);
 		}
 	}
@@ -465,6 +491,57 @@ sub modified ($) {
 	$modified || time;
 }
 
+# for grokmirror, which doesn't read gitweb.description
+# templates/hooks--update.sample and git-multimail in git.git
+# only match "Unnamed repository", not the full contents of
+# templates/this--description in git.git
+sub manifest_entry {
+	my ($self, $epoch, $default_desc) = @_;
+	my ($fh, $pid) = $self->popen('show-ref');
+	my $dig = Digest::SHA->new(1);
+	while (read($fh, my $buf, 65536)) {
+		$dig->add($buf);
+	}
+	close $fh;
+	waitpid($pid, 0);
+	return if $?; # empty, uninitialized git repo
+	my $git_dir = $self->{git_dir};
+	my $ent = {
+		fingerprint => $dig->hexdigest,
+		reference => undef,
+		modified => modified($self),
+	};
+	chomp(my $owner = $self->qx('config', 'gitweb.owner'));
+	utf8::decode($owner);
+	$ent->{owner} = $owner eq '' ? undef : $owner;
+	my $desc = '';
+	if (open($fh, '<', "$git_dir/description")) {
+		local $/ = "\n";
+		chomp($desc = <$fh>);
+		utf8::decode($desc);
+	}
+	$desc = 'Unnamed repository' if $desc eq '';
+	if (defined $epoch && $desc =~ /\AUnnamed repository/) {
+		$desc = "$default_desc [epoch $epoch]";
+	}
+	$ent->{description} = $desc;
+	if (open($fh, '<', "$git_dir/objects/info/alternates")) {
+		# n.b.: GitPython doesn't seem to handle comments or C-quoted
+		# strings like native git does; and we don't for now, either.
+		local $/ = "\n";
+		chomp(my @alt = <$fh>);
+
+		# grokmirror only supports 1 alternate for "reference",
+		if (scalar(@alt) == 1) {
+			my $objdir = "$git_dir/objects";
+			my $ref = File::Spec->rel2abs($alt[0], $objdir);
+			$ref =~ s!/[^/]+/?\z!!; # basename
+			$ent->{reference} = $ref;
+		}
+	}
+	$ent;
+}
+
 1;
 __END__
 =pod