# There are also API changes to simplify our usage and data set.
package PublicInbox::Git;
use strict;
-use warnings;
+use v5.10.1;
+use parent qw(Exporter);
use POSIX ();
use IO::Handle; # ->autoflush
+use Errno qw(EINTR);
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 base qw(Exporter);
+use Carp qw(croak);
+use Digest::SHA ();
our @EXPORT_OK = qw(git_unquote git_quote);
-use Errno qw(EINTR);
our $PIPE_BUFSIZ = 65536; # Linux default
+our $in_cleanup;
use constant MAX_INFLIGHT =>
- (($^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF()) * 2)
+ (($^O eq 'linux' ? 4096 : POSIX::_POSIX_PIPE_BUF()) * 3)
/
65; # SHA-256 hex size + "\n" in preparation for git using non-SHA1
fcntl($out_w, 1031, 4096);
fcntl($in_r, 1031, 4096) if $batch eq '--batch-check';
}
- $self->{$batch} = \(my $rbuf = '');
$self->{$out} = $out_w;
$self->{$in} = $in_r;
}
}
}
-sub _cat_async_step ($$) {
+sub cat_async_retry ($$$$$) {
+ my ($self, $inflight, $req, $cb, $arg) = @_;
+
+ # {inflight} may be non-existent, but if it isn't we delete it
+ # here to prevent cleanup() from waiting:
+ delete $self->{inflight};
+ cleanup($self);
+
+ $self->{inflight} = $inflight;
+ batch_prepare($self);
+ my $buf = "$req\n";
+ for (my $i = 0; $i < @$inflight; $i += 3) {
+ $buf .= "$inflight->[$i]\n";
+ }
+ print { $self->{out} } $buf or fail($self, "write error: $!");
+ unshift(@$inflight, \$req, $cb, $arg); # \$ref to indicate retried
+
+ cat_async_step($self, $inflight); # take one step
+}
+
+sub cat_async_step ($$) {
my ($self, $inflight) = @_;
- die 'BUG: inflight empty or odd' if scalar(@$inflight) < 2;
- my ($cb, $arg) = splice(@$inflight, 0, 2);
- my $head = my_readline($self->{in}, $self->{'--batch'});
- $head =~ / missing$/ and return
- eval { $cb->(undef, undef, undef, undef, $arg) };
-
- $head =~ /^([0-9a-f]{40}) (\S+) ([0-9]+)$/ or
- fail($self, "Unexpected result from async git cat-file: $head");
- my ($oid_hex, $type, $size) = ($1, $2, $3 + 0);
- my $ret = my_read($self->{in}, $self->{'--batch'}, $size + 1);
- fail($self, defined($ret) ? 'read EOF' : "read: $!") if !$ret;
- chop($$ret) eq "\n" or fail($self, 'newline missing after blob');
- eval { $cb->($ret, $oid_hex, $type, $size, $arg) };
- warn "E: $oid_hex $@\n" if $@;
+ die 'BUG: inflight empty or odd' if scalar(@$inflight) < 3;
+ my ($req, $cb, $arg) = splice(@$inflight, 0, 3);
+ my $rbuf = delete($self->{cat_rbuf}) // \(my $new = '');
+ my ($bref, $oid, $type, $size);
+ my $head = my_readline($self->{in}, $rbuf);
+ # ->fail may be called via Gcf2Client.pm
+ if ($head =~ /^([0-9a-f]{40,}) (\S+) ([0-9]+)$/) {
+ ($oid, $type, $size) = ($1, $2, $3 + 0);
+ $bref = my_read($self->{in}, $rbuf, $size + 1) or
+ $self->fail(defined($bref) ? 'read EOF' : "read: $!");
+ chop($$bref) eq "\n" or $self->fail('LF missing after blob');
+ } elsif ($head =~ s/ missing\n//s) {
+ $oid = $head;
+ # ref($req) indicates it's already been retried
+ # -gcf2 retries internally, so it never hits this path:
+ if (!ref($req) && !$in_cleanup && $self->alternates_changed) {
+ return cat_async_retry($self, $inflight,
+ $req, $cb, $arg);
+ }
+ $type = 'missing';
+ $oid = ref($req) ? $$req : $req if $oid eq '';
+ } else {
+ $self->fail("Unexpected result from async git cat-file: $head");
+ }
+ $self->{cat_rbuf} = $rbuf if $$rbuf ne '';
+ eval { $cb->($bref, $oid, $type, $size, $arg) };
+ warn "E: $oid: $@\n" if $@;
}
sub cat_async_wait ($) {
my ($self) = @_;
- my $inflight = delete $self->{inflight} or return;
+ my $inflight = $self->{inflight} or return;
while (scalar(@$inflight)) {
- _cat_async_step($self, $inflight);
+ cat_async_step($self, $inflight);
}
}
_bidi_pipe($_[0], qw(--batch in out pid));
}
+sub _cat_file_cb {
+ my ($bref, undef, undef, $size, $result) = @_;
+ @$result = ($bref, $size);
+}
+
sub cat_file {
- my ($self, $obj, $sizeref) = @_;
- my ($retried, $head);
+ my ($self, $oid, $sizeref) = @_;
+ my $result = [];
+ cat_async($self, $oid, \&_cat_file_cb, $result);
cat_async_wait($self);
-again:
- batch_prepare($self);
- print { $self->{out} } $obj, "\n" or fail($self, "write error: $!");
- $head = my_readline($self->{in}, $self->{'--batch'});
- if ($head =~ / missing$/) {
- if (!$retried && alternates_changed($self)) {
- $retried = 1;
- cleanup($self);
- goto again;
- }
- return;
+ $$sizeref = $result->[1] if $sizeref;
+ $result->[0];
+}
+
+sub check_async_step ($$) {
+ my ($self, $inflight_c) = @_;
+ die 'BUG: inflight empty or odd' if scalar(@$inflight_c) < 3;
+ my ($req, $cb, $arg) = splice(@$inflight_c, 0, 3);
+ my $rbuf = delete($self->{chk_rbuf}) // \(my $new = '');
+ chomp(my $line = my_readline($self->{in_c}, $rbuf));
+ my ($hex, $type, $size) = split(/ /, $line);
+
+ # Future versions of git.git may have type=ambiguous, but for now,
+ # we must handle 'dangling' below (and maybe some other oddball
+ # stuff):
+ # https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/
+ if ($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;
}
- $head =~ /^[0-9a-f]{40} \S+ ([0-9]+)$/ or
- fail($self, "Unexpected result from git cat-file: $head");
+ $self->{chk_rbuf} = $rbuf if $$rbuf ne '';
+ eval { $cb->($hex, $type, $size, $arg, $self) };
+ warn "E: check($req) $@\n" if $@;
+}
- my $size = $1 + 0;
- $$sizeref = $size if $sizeref;
- my $ret = my_read($self->{in}, $self->{'--batch'}, $size + 1);
- fail($self, defined($ret) ? 'read EOF' : "read: $!") if !$ret;
- chop($$ret) eq "\n" or fail($self, 'newline missing after blob');
- $ret;
+sub check_async_wait ($) {
+ my ($self) = @_;
+ my $inflight_c = $self->{inflight_c} or return;
+ while (scalar(@$inflight_c)) {
+ check_async_step($self, $inflight_c);
+ }
}
-sub check {
- my ($self, $obj) = @_;
+sub check_async_begin ($) {
+ my ($self) = @_;
+ cleanup($self) if alternates_changed($self);
_bidi_pipe($self, qw(--batch-check in_c out_c pid_c err_c));
- print { $self->{out_c} } $obj, "\n" or fail($self, "write error: $!");
- chomp(my $line = my_readline($self->{in_c}, $self->{'--batch-check'}));
- my ($hex, $type, $size) = split(' ', $line);
+ die 'BUG: already in async check' if $self->{inflight_c};
+ $self->{inflight_c} = [];
+}
+
+sub check_async ($$$$) {
+ 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 fail($self, "write error: $!");
+ push(@$inflight_c, $oid, $cb, $arg);
+}
+
+sub _check_cb { # check_async callback
+ my ($hex, $type, $size, $result) = @_;
+ @$result = ($hex, $type, $size);
+}
+
+sub check {
+ my ($self, $oid) = @_;
+ my $result = [];
+ check_async($self, $oid, \&_check_cb, $result);
+ check_async_wait($self);
+ my ($hex, $type, $size) = @$result;
# 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') {
- my $ret = my_read($self->{in_c}, $self->{'--batch-check'},
- $type + 1);
- fail($self, defined($ret) ? 'read EOF' : "read: $!") if !$ret;
- return;
- }
-
+ return if $hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop';
($hex, $type, $size);
}
sub _destroy {
- my ($self, $batch, $in, $out, $pid, $err) = @_;
- my $p = delete $self->{$pid} or return;
- delete @$self{($batch, $in, $out)};
+ my ($self, $rbuf, $in, $out, $pid, $err) = @_;
+ 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;
+
# PublicInbox::DS may not be loaded
eval { PublicInbox::DS::dwaitpid($p, undef, undef) };
waitpid($p, 0) if $@; # wait synchronously if not in event loop
sub cat_async_abort ($) {
my ($self) = @_;
- my $inflight = delete $self->{inflight} or die 'BUG: not in async';
+ if (my $inflight = $self->{inflight}) {
+ while (@$inflight) {
+ my ($req, $cb, $arg) = splice(@$inflight, 0, 3);
+ $req =~ s/ .*//; # drop git_dir for Gcf2Client
+ eval { $cb->(undef, $req, undef, undef, $arg) };
+ warn "E: $req: $@ (in abort)\n" if $@;
+ }
+ delete $self->{cat_rbuf};
+ delete $self->{inflight};
+ }
cleanup($self);
}
sub fail {
my ($self, $msg) = @_;
- $self->{inflight} ? cat_async_abort($self) : cleanup($self);
- die $msg;
+ cat_async_abort($self);
+ croak(ref($self) . ' ' . ($self->{git_dir} // '') . ": $msg");
}
sub popen {
<$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) = @_;
- _destroy($self, qw(--batch in out pid));
- _destroy($self, qw(--batch-check in_c out_c pid_c err_c));
+ local $in_cleanup = 1;
+ delete $self->{async_cat};
+ async_wait_all($self);
+ delete $self->{inflight};
+ delete $self->{inflight_c};
+ _destroy($self, qw(cat_rbuf in out pid));
+ _destroy($self, qw(chk_rbuf in_c out_c pid_c err_c));
!!($self->{pid} || $self->{pid_c});
}
+
# assuming a well-maintained repo, this should be a somewhat
# accurate estimation of its size
# TODO: show this in the WWW UI as a hint to potential cloners
sub cat_async_begin {
my ($self) = @_;
- cleanup($self) if alternates_changed($self);
- batch_prepare($self);
+ cleanup($self) if $self->alternates_changed;
+ $self->batch_prepare;
die 'BUG: already in async' if $self->{inflight};
$self->{inflight} = [];
}
sub cat_async ($$$;$) {
my ($self, $oid, $cb, $arg) = @_;
- my $inflight = $self->{inflight} or die 'BUG: not in async';
- if (scalar(@$inflight) >= MAX_INFLIGHT) {
- _cat_async_step($self, $inflight);
+ my $inflight = $self->{inflight} // cat_async_begin($self);
+ while (scalar(@$inflight) >= MAX_INFLIGHT) {
+ cat_async_step($self, $inflight);
}
-
print { $self->{out} } $oid, "\n" or fail($self, "write error: $!");
- push(@$inflight, $cb, $arg);
+ push(@$inflight, $oid, $cb, $arg);
+}
+
+sub async_prefetch {
+ my ($self, $oid, $cb, $arg) = @_;
+ if (my $inflight = $self->{inflight}) {
+ # we could use MAX_INFLIGHT here w/o the halving,
+ # but lets not allow one client to monopolize a git process
+ if (scalar(@$inflight) < int(MAX_INFLIGHT/2)) {
+ print { $self->{out} } $oid, "\n" or
+ fail($self, "write error: $!");
+ return push(@$inflight, $oid, $cb, $arg);
+ }
+ }
+ undef;
}
sub extract_cmt_time {
my ($self) = @_;
my $modified = 0;
my $fh = popen($self, qw(rev-parse --branches));
- cat_async_begin($self);
local $/ = "\n";
while (my $oid = <$fh>) {
chomp $oid;
$modified || time;
}
+# for grokmirror, which doesn't read gitweb.description
+# templates/hooks--update.sample and git-multimail in git.git
+# only match "Unnamed repository", not the full contents of
+# templates/this--description in git.git
+sub manifest_entry {
+ my ($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