X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FGit.pm;h=ff3ac40f59511aab560b114d4ad73eecc3f067b2;hb=24f55535e78be0f1fa394bcd1aebc8c027e937c7;hp=78b47096f63087c8ff49da51c9eff67a09929777;hpb=a93c7e471ca70bdb476c2285cf894e319b38f160;p=public-inbox.git

diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index 78b47096..ff3ac40f 100644
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -16,20 +16,22 @@ use Errno qw(EINTR EAGAIN ENOENT);
 use File::Glob qw(bsd_glob GLOB_NOSORT);
 use File::Spec ();
 use Time::HiRes qw(stat);
-use PublicInbox::Spawn qw(popen_rd spawn);
+use PublicInbox::Spawn qw(popen_rd which);
 use PublicInbox::Tmpfile;
 use IO::Poll qw(POLLIN);
 use Carp qw(croak carp);
 use Digest::SHA ();
-use PublicInbox::DS qw(dwaitpid);
+use PublicInbox::DS qw(awaitpid);
 our @EXPORT_OK = qw(git_unquote git_quote);
 our $PIPE_BUFSIZ = 65536; # Linux default
 our $in_cleanup;
 our $RDTIMEO = 60_000; # milliseconds
 our $async_warn; # true in read-only daemons
 
-use constant MAX_INFLIGHT => (POSIX::PIPE_BUF * 3) /
-	65; # SHA-256 hex size + "\n" in preparation for git using non-SHA1
+# 512: POSIX PIPE_BUF minimum (see pipe(7))
+# 3: @$inflight is flattened [ $OID, $cb, $arg ]
+# 65: SHA-256 hex size + "\n" in preparation for git using non-SHA1
+use constant MAX_INFLIGHT => 512 * 3 / 65;
 
 my %GIT_ESC = (
 	a => "\a",
@@ -44,7 +46,6 @@ my %GIT_ESC = (
 );
 my %ESC_GIT = map { $GIT_ESC{$_} => $_ } keys %GIT_ESC;
 
-
 # unquote pathnames used by git, see quote.c::unquote_c_style.c in git.git
 sub git_unquote ($) {
 	return $_[0] unless ($_[0] =~ /\A"(.*)"\z/);
@@ -120,6 +121,26 @@ sub _bidi_pipe {
 		}
 		return;
 	}
+
+	state $EXE_ST = ''; # pack('dd', st_ctime, st_size);
+	my $exe = which('git') // die "git not found in $ENV{PATH}";
+	my @st = stat($exe) or die "stat: $!";
+	my $st = pack('dd', $st[10], $st[7]);
+	state $VER;
+	if ($st ne $EXE_ST) {
+		my $rd = popen_rd([ $exe, '--version' ]);
+		my $v = readline($rd);
+		$v =~ /\b([0-9]+(?:\.[0-9]+){2})/ or die
+			"$exe --version output: $v # unparseable";
+		my @v = split(/\./, $1, 3);
+		$VER = ($v[0] << 24) | ($v[1] << 16) | $v[2];
+		$EXE_ST = $st;
+	}
+
+	# git 2.31.0+ supports -c core.abbrev=no, don't bother with
+	# core.abbrev=64 since not many releases had SHA-256 prior to 2.31
+	my $abbr = $VER < (2 << 24 | 31 << 16) ? 40 : 'no';
+
 	pipe(my ($out_r, $out_w)) or $self->fail("pipe failed: $!");
 	my $rdr = { 0 => $out_r, pgid => 0 };
 	my $gd = $self->{git_dir};
@@ -127,8 +148,8 @@ sub _bidi_pipe {
 		$rdr->{-C} = $gd;
 		$gd = $1;
 	}
-	my @cmd = (qw(git), "--git-dir=$gd",
-			qw(-c core.abbrev=40 cat-file), $batch);
+	my @cmd = ($exe, "--git-dir=$gd", '-c', "core.abbrev=$abbr",
+			'cat-file', $batch);
 	if ($err) {
 		my $id = "git.$self->{git_dir}$batch.err";
 		my $fh = tmpfile($id) or $self->fail("tmpfile($id): $!");
@@ -136,13 +157,14 @@ sub _bidi_pipe {
 		$rdr->{2} = $fh;
 	}
 	my ($in_r, $p) = popen_rd(\@cmd, undef, $rdr);
-	$self->{$pid} = $p;
+	awaitpid($self->{$pid} = $p, undef);
 	$self->{"$pid.owner"} = $$;
 	$out_w->autoflush(1);
 	if ($^O eq 'linux') { # 1031: F_SETPIPE_SZ
 		fcntl($out_w, 1031, 4096);
 		fcntl($in_r, 1031, 4096) if $batch eq '--batch-check';
 	}
+	$out_w->blocking(0);
 	$self->{$out} = $out_w;
 	$self->{$in} = $in_r;
 }
@@ -201,7 +223,9 @@ sub cat_async_retry ($$) {
 	for (my $i = 0; $i < @$inflight; $i += 3) {
 		$buf .= "$inflight->[$i]\n";
 	}
+	$self->{out}->blocking(1); # brand new pipe, should never block
 	print { $self->{out} } $buf or $self->fail("write error: $!");
+	$self->{out}->blocking(0);
 	my $req = shift @$inflight;
 	unshift(@$inflight, \$req); # \$ref to indicate retried
 
@@ -303,13 +327,26 @@ sub check_async_begin ($) {
 	$self->{inflight_c} = [];
 }
 
+sub write_all {
+	my ($self, $out, $buf, $read_step, $inflight) = @_;
+	$read_step->($self, $inflight) while @$inflight >= MAX_INFLIGHT;
+	do {
+		my $w = syswrite($out, $buf);
+		if (defined $w) {
+			return if $w == length($buf);
+			substr($buf, 0, $w, ''); # sv_chop
+		} elsif ($! != EAGAIN) {
+			$self->fail("write: $!");
+		}
+		$read_step->($self, $inflight);
+	} while (1);
+}
+
 sub check_async ($$$$) {
 	my ($self, $oid, $cb, $arg) = @_;
 	my $inflight_c = $self->{inflight_c} // check_async_begin($self);
-	while (scalar(@$inflight_c) >= MAX_INFLIGHT) {
-		check_async_step($self, $inflight_c);
-	}
-	print { $self->{out_c} } $oid, "\n" or $self->fail("write error: $!");
+	write_all($self, $self->{out_c}, $oid."\n",
+		\&check_async_step, $inflight_c);
 	push(@$inflight_c, $oid, $cb, $arg);
 }
 
@@ -339,9 +376,9 @@ sub _destroy {
 	delete @$self{($rbuf, $in, $out)};
 	delete $self->{$err} if $err; # `err_c'
 
-	# GitAsyncCat::event_step may delete {pid}
-	my $p = delete $self->{$pid} or return;
-	dwaitpid($p) if $$ == $self->{"$pid.owner"};
+	# GitAsyncCat::event_step may delete {$pid}
+	my $p = delete($self->{$pid}) // return;
+	awaitpid($p) if $$ == $self->{"$pid.owner"};
 }
 
 sub async_abort ($) {
@@ -426,6 +463,7 @@ sub cleanup {
 				scalar(@{$self->{inflight} // []}));
 	local $in_cleanup = 1;
 	delete $self->{async_cat};
+	delete $self->{async_chk};
 	async_wait_all($self);
 	delete $self->{inflight};
 	delete $self->{inflight_c};
@@ -451,24 +489,37 @@ sub DESTROY { cleanup(@_) }
 
 sub local_nick ($) {
 	# don't show full FS path, basename should be OK:
-	$_[0]->{git_dir} =~ m!/([^/]+?)(?:/*\.git/*)?\z! ? "$1.git" : '???';
+	$_[0]->{nick} // ($_[0]->{git_dir} =~ m!/([^/]+?)(?:/*\.git/*)?\z! ?
+			"$1.git" : undef);
 }
 
 sub host_prefix_url ($$) {
 	my ($env, $url) = @_;
 	return $url if index($url, '//') >= 0;
-	my $scheme = $env->{'psgi.url_scheme'};
 	my $host_port = $env->{HTTP_HOST} //
 		"$env->{SERVER_NAME}:$env->{SERVER_PORT}";
-	"$scheme://$host_port". ($env->{SCRIPT_NAME} || '/') . $url;
+	my $sn = $env->{SCRIPT_NAME} // '';
+	"$env->{'psgi.url_scheme'}://$host_port$sn/$url";
 }
 
+sub base_url { # for coderepos, PSGI-only
+	my ($self, $env) = @_; # env - PSGI env
+	my $nick = $self->{nick} // return undef;
+	my $url = host_prefix_url($env, '');
+	# for mount in Plack::Builder
+	$url .= '/' if substr($url, -1, 1) ne '/';
+	$url . $nick . '/';
+}
+
+sub isrch {} # TODO
+
 sub pub_urls {
 	my ($self, $env) = @_;
 	if (my $urls = $self->{cgit_url}) {
-		return map { host_prefix_url($env, $_) } @$urls;
+		map { host_prefix_url($env, $_) } @$urls;
+	} else {
+		(base_url($self, $env) // '???');
 	}
-	(local_nick($self));
 }
 
 sub cat_async_begin {
@@ -482,10 +533,7 @@ sub cat_async_begin {
 sub cat_async ($$$;$) {
 	my ($self, $oid, $cb, $arg) = @_;
 	my $inflight = $self->{inflight} // cat_async_begin($self);
-	while (scalar(@$inflight) >= MAX_INFLIGHT) {
-		cat_async_step($self, $inflight);
-	}
-	print { $self->{out} } $oid, "\n" or $self->fail("write error: $!");
+	write_all($self, $self->{out}, $oid."\n", \&cat_async_step, $inflight);
 	push(@$inflight, $oid, $cb, $arg);
 }
 
@@ -498,13 +546,31 @@ sub modified ($) {
 	(split(/ /, <$fh> // time))[0] + 0; # integerize for JSON
 }
 
+sub try_cat {
+	my ($path) = @_;
+	open(my $fh, '<', $path) or return '';
+	local $/;
+	<$fh> // '';
+}
+
+sub cat_desc ($) {
+	my $desc = try_cat($_[0]);
+	chomp $desc;
+	utf8::decode($desc);
+	$desc =~ s/\s+/ /smg;
+	$desc eq '' ? undef : $desc;
+}
+
 sub description {
-	my $desc = '';
-	if (open(my $fh, '<:utf8', "$_[0]->{git_dir}/description")) {
-		local $/ = "\n";
-		chomp($desc = <$fh> // '');
-	}
-	$desc eq '' ? 'Unnamed repository' : $desc;
+	cat_desc("$_[0]->{git_dir}/description") // 'Unnamed repository';
+}
+
+sub cloneurl {
+	my ($self, $env) = @_;
+	$self->{cloneurl} // do {
+		my @urls = split(/\s+/s, try_cat("$self->{git_dir}/cloneurl"));
+		scalar(@urls) ? ($self->{cloneurl} = \@urls) : undef;
+	} // [ substr(base_url($self, $env), 0, -1) ];
 }
 
 # for grokmirror, which doesn't read gitweb.description