X-Git-Url: http://www.git.stargrave.org/?p=public-inbox.git;a=blobdiff_plain;f=lib%2FPublicInbox%2FGit.pm;h=f5c7a95c34d7aedad7860a1189f8e121167eb1fb;hp=4601f2599ac674ae96d6bcb7ce2d7681f3b587f2;hb=3c30532aed6256a984c535530c6667552c2e6a84;hpb=adf443322d8747bbc5b0b1d6e7bf819f70244456

diff --git a/lib/PublicInbox/Git.pm b/lib/PublicInbox/Git.pm
index 4601f259..f5c7a95c 100644
--- a/lib/PublicInbox/Git.pm
+++ b/lib/PublicInbox/Git.pm
@@ -13,7 +13,7 @@ use POSIX qw(dup2);
 require IO::Handle;
 use PublicInbox::Spawn qw(spawn popen_rd);
 use base qw(Exporter);
-our @EXPORT_OK = qw(git_unquote);
+our @EXPORT_OK = qw(git_unquote git_quote);
 
 my %GIT_ESC = (
 	a => "\a",
@@ -23,27 +23,54 @@ my %GIT_ESC = (
 	r => "\r",
 	t => "\t",
 	v => "\013",
+	'"' => '"',
+	'\\' => '\\',
 );
+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/);
 	$_[0] = $1;
-	$_[0] =~ s/\\([abfnrtv])/$GIT_ESC{$1}/g;
+	$_[0] =~ s/\\([\\"abfnrtv])/$GIT_ESC{$1}/g;
 	$_[0] =~ s/\\([0-7]{1,3})/chr(oct($1))/ge;
 	$_[0];
 }
 
+sub git_quote ($) {
+	if ($_[0] =~ s/([\\"\a\b\f\n\r\t\013]|[^[:print:]])/
+		      '\\'.($ESC_GIT{$1}||sprintf("%0o",ord($1)))/egs) {
+		return qq{"$_[0]"};
+	}
+	$_[0];
+}
+
 sub new {
 	my ($class, $git_dir) = @_;
 	my @st;
 	$st[7] = $st[10] = 0;
-	bless { git_dir => $git_dir, st => \@st }, $class
+	# may contain {-tmp} field for File::Temp::Dir
+	bless { git_dir => $git_dir, st => \@st, -git_path => {} }, $class
+}
+
+sub git_path ($$) {
+	my ($self, $path) = @_;
+	$self->{-git_path}->{$path} ||= do {
+		local $/ = "\n";
+		chomp(my $str = $self->qx(qw(rev-parse --git-path), $path));
+
+		# git prior to 2.5.0 did not understand --git-path
+		if ($str eq "--git-path\n$path") {
+			$str = "$self->{git_dir}/$path";
+		}
+		$str;
+	};
 }
 
 sub alternates_changed {
 	my ($self) = @_;
-	my $alt = "$self->{git_dir}/objects/info/alternates";
+	my $alt = git_path($self, 'objects/info/alternates');
 	my @st = stat($alt) or return 0;
 	my $old_st = $self->{st};
 	# 10 - ctime, 7 - size
@@ -51,9 +78,25 @@ sub alternates_changed {
 	$self->{st} = \@st;
 }
 
+sub last_check_err {
+	my ($self) = @_;
+	my $fh = $self->{err_c} or return;
+	sysseek($fh, 0, 0) or fail($self, "sysseek failed: $!");
+	defined(sysread($fh, my $buf, -s $fh)) or
+			fail($self, "sysread failed: $!");
+	$buf;
+}
+
 sub _bidi_pipe {
-	my ($self, $batch, $in, $out, $pid) = @_;
-	return if $self->{$pid};
+	my ($self, $batch, $in, $out, $pid, $err) = @_;
+	if ($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: $!");
+		}
+		return;
+	}
 	my ($in_r, $in_w, $out_r, $out_w);
 
 	pipe($in_r, $in_w) or fail($self, "pipe failed: $!");
@@ -63,8 +106,14 @@ sub _bidi_pipe {
 		fcntl($in_w, 1031, 4096) if $batch eq '--batch-check';
 	}
 
-	my @cmd = ('git', "--git-dir=$self->{git_dir}", qw(cat-file), $batch);
+	my @cmd = (qw(git), "--git-dir=$self->{git_dir}",
+			qw(-c core.abbrev=40 cat-file), $batch);
 	my $redir = { 0 => fileno($out_r), 1 => fileno($in_w) };
+	if ($err) {
+		open(my $fh, '+>', undef) or fail($self, "open.err failed: $!");
+		$self->{$err} = $fh;
+		$redir->{2} = fileno($fh);
+	}
 	my $p = spawn(\@cmd, undef, $redir);
 	defined $p or fail($self, "spawn failed: $!");
 	$self->{$pid} = $p;
@@ -92,45 +141,28 @@ again:
 		}
 		return;
 	}
-	$head =~ /^[0-9a-f]{40} \S+ (\d+)$/ or
+	$head =~ /^[0-9a-f]{40} \S+ ([0-9]+)$/ or
 		fail($self, "Unexpected result from git cat-file: $head");
 
 	my $size = $1;
-	my $ref_type = $ref ? ref($ref) : '';
-
 	my $rv;
 	my $left = $size;
-	$$ref = $size if ($ref_type eq 'SCALAR');
-	my $cb_err;
-
-	if ($ref_type eq 'CODE') {
-		$rv = eval { $ref->($in, \$left) };
-		$cb_err = $@;
-		# drain the rest
-		my $max = 8192;
-		while ($left > 0) {
-			my $r = read($in, my $x, $left > $max ? $max : $left);
-			defined($r) or fail($self, "read failed: $!");
-			$r == 0 and fail($self, 'exited unexpectedly');
-			$left -= $r;
-		}
-	} else {
-		my $offset = 0;
-		my $buf = '';
-		while ($left > 0) {
-			my $r = read($in, $buf, $left, $offset);
-			defined($r) or fail($self, "read failed: $!");
-			$r == 0 and fail($self, 'exited unexpectedly');
-			$left -= $r;
-			$offset += $r;
-		}
-		$rv = \$buf;
+	$$ref = $size if $ref;
+
+	my $offset = 0;
+	my $buf = '';
+	while ($left > 0) {
+		my $r = read($in, $buf, $left, $offset);
+		defined($r) or fail($self, "read failed: $!");
+		$r == 0 and fail($self, 'exited unexpectedly');
+		$left -= $r;
+		$offset += $r;
 	}
+	$rv = \$buf;
 
-	my $r = read($in, my $buf, 1);
+	my $r = read($in, my $lf, 1);
 	defined($r) or fail($self, "read failed: $!");
-	fail($self, 'newline missing after blob') if ($r != 1 || $buf ne "\n");
-	die $cb_err if $cb_err;
+	fail($self, 'newline missing after blob') if ($r != 1 || $lf ne "\n");
 
 	$rv;
 }
@@ -139,21 +171,33 @@ sub batch_prepare ($) { _bidi_pipe($_[0], qw(--batch in out pid)) }
 
 sub check {
 	my ($self, $obj) = @_;
-	$self->_bidi_pipe(qw(--batch-check in_c out_c pid_c));
+	_bidi_pipe($self, qw(--batch-check in_c out_c pid_c err_c));
 	$self->{out_c}->print($obj, "\n") or fail($self, "write error: $!");
 	local $/ = "\n";
 	chomp(my $line = $self->{in_c}->getline);
 	my ($hex, $type, $size) = split(' ', $line);
-	return if $type eq 'missing';
+
+	# Future versions of git.git may show 'ambiguous', but for now,
+	# we must handle 'dangling' below (and maybe some other oddball
+	# stuff):
+	# https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/
+	return if $type eq 'missing' || $type eq 'ambiguous';
+
+	if ($hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop') {
+		$size = $type + length("\n");
+		my $r = read($self->{in_c}, my $buf, $size);
+		defined($r) or fail($self, "read failed: $!");
+		return;
+	}
+
 	($hex, $type, $size);
 }
 
 sub _destroy {
-	my ($self, $in, $out, $pid) = @_;
+	my ($self, $in, $out, $pid, $err) = @_;
 	my $p = delete $self->{$pid} or return;
-	foreach my $f ($in, $out) {
-		delete $self->{$f};
-	}
+	delete @$self{($in, $out)};
+	delete $self->{$err} if $err; # `err_c'
 	waitpid $p, 0;
 }
 
@@ -179,10 +223,12 @@ sub qx {
 	<$fh>
 }
 
+# returns true if there are pending "git cat-file" processes
 sub cleanup {
 	my ($self) = @_;
 	_destroy($self, qw(in out pid));
-	_destroy($self, qw(in_c out_c pid_c));
+	_destroy($self, qw(in_c out_c pid_c err_c));
+	!!($self->{pid} || $self->{pid_c});
 }
 
 # assuming a well-maintained repo, this should be a somewhat
@@ -191,7 +237,8 @@ sub cleanup {
 sub packed_bytes {
 	my ($self) = @_;
 	my $n = 0;
-	foreach my $p (glob("$self->{git_dir}/objects/pack/*.pack")) {
+	my $pack_dir = git_path($self, 'objects/pack');
+	foreach my $p (glob("$pack_dir/*.pack")) {
 		$n += -s $p;
 	}
 	$n
@@ -199,6 +246,69 @@ sub packed_bytes {
 
 sub DESTROY { cleanup(@_) }
 
+sub local_nick ($) {
+	my ($self) = @_;
+	my $ret = '???';
+	# don't show full FS path, basename should be OK:
+	if ($self->{git_dir} =~ m!/([^/]+)(?:/\.git)?\z!) {
+		$ret = "/path/to/$1";
+	}
+	wantarray ? ($ret) : $ret;
+}
+
+# show the blob URL for cgit/gitweb/whatever
+sub src_blob_url {
+	my ($self, $oid) = @_;
+	# blob_url_format = "https://example.com/foo.git/blob/%s"
+	if (my $bfu = $self->{blob_url_format}) {
+		return map { sprintf($_, $oid) } @$bfu if wantarray;
+		return sprintf($bfu->[0], $oid);
+	}
+	local_nick($self);
+}
+
+sub host_prefix_url ($$) {
+	my ($env, $url) = @_;
+	return $url if index($url, '//') >= 0;
+	my $scheme = $env->{'psgi.url_scheme'};
+	my $host_port = $env->{HTTP_HOST} ||
+		"$env->{SERVER_NAME}:$env->{SERVER_PORT}";
+	"$scheme://$host_port". ($env->{SCRIPT_NAME} || '/') . $url;
+}
+
+sub pub_urls {
+	my ($self, $env) = @_;
+	if (my $urls = $self->{cgit_url}) {
+		return map { host_prefix_url($env, $_) } @$urls;
+	}
+	local_nick($self);
+}
+
+sub commit_title ($$) {
+	my ($self, $oid) = @_; # PublicInbox::Git, $sha1hex
+	my $buf = cat_file($self, $oid) or return;
+	utf8::decode($$buf);
+	($$buf =~ /\r?\n\r?\n([^\r\n]+)\r?\n?/)[0]
+}
+
+# returns the modified time of a git repo, same as the "modified" field
+# of a grokmirror manifest
+sub modified ($) {
+	my ($self) = @_;
+	my $modified = 0;
+	my $fh = popen($self, qw(rev-parse --branches));
+	defined $fh or return $modified;
+	local $/ = "\n";
+	foreach my $oid (<$fh>) {
+		chomp $oid;
+		my $buf = cat_file($self, $oid) or next;
+		$$buf =~ /^committer .*?> ([0-9]+) [\+\-]?[0-9]+/sm or next;
+		my $cmt_time = $1 + 0;
+		$modified = $cmt_time if $cmt_time > $modified;
+	}
+	$modified || time;
+}
+
 1;
 __END__
 =pod