-# Copyright (C) 2014-2021 all contributors <meta@public-inbox.org>
+# Copyright (C) all contributors <meta@public-inbox.org>
# License: GPLv2 or later <https://www.gnu.org/licenses/gpl-2.0.txt>
#
# Used to read files from a git repository without excessive forking.
use parent qw(Exporter);
use POSIX ();
use IO::Handle; # ->autoflush
-use Errno qw(EINTR EAGAIN ENOENT);
+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 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::SHA ();
+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 + length('contents ')),
+ BATCH_CMD_VER => (2 << 24 | 36 << 16), # git 2.36+
+};
my %GIT_ESC = (
a => "\a",
);
my %ESC_GIT = map { $GIT_ESC{$_} => $_ } keys %GIT_ESC;
+my $EXE_ST = ''; # pack('dd', st_ctime, st_size);
+my ($GIT_EXE, $GIT_VER);
+
+sub version {
+ check_git_exe();
+ $GIT_VER;
+}
+
+sub check_git_exe () {
+ $GIT_EXE = which('git') // die "git not found in $ENV{PATH}";
+ my @st = stat($GIT_EXE) or die "stat: $!";
+ my $st = pack('dd', $st[10], $st[7]);
+ if ($st ne $EXE_ST) {
+ my $rd = popen_rd([ $GIT_EXE, '--version' ]);
+ my $v = readline($rd);
+ $v =~ /\b([0-9]+(?:\.[0-9]+){2})/ or die
+ "$GIT_EXE --version output: $v # unparseable";
+ my @v = split(/\./, $1, 3);
+ $GIT_VER = ($v[0] << 24) | ($v[1] << 16) | $v[2];
+ $EXE_ST = $st;
+ }
+}
# unquote pathnames used by git, see quote.c::unquote_c_style.c in git.git
sub git_unquote ($) {
$git_dir =~ tr!/!/!s;
$git_dir =~ s!/*\z!!s;
# may contain {-tmp} field for File::Temp::Dir
- bless { git_dir => $git_dir, alt_st => '', -git_path => {} }, $class
+ bless { git_dir => $git_dir }, $class
}
sub git_path ($$) {
my ($self, $path) = @_;
- $self->{-git_path}->{$path} ||= do {
+ $self->{-git_path}->{$path} //= do {
local $/ = "\n";
chomp(my $str = $self->qx(qw(rev-parse --git-path), $path));
# can't rely on 'q' on some 32-bit builds, but `d' works
my $st = pack('dd', $st[10], $st[7]); # 10: ctime, 7: size
- return 0 if $self->{alt_st} eq $st;
+ return 0 if ($self->{alt_st} // '') eq $st;
$self->{alt_st} = $st; # always a true value
}
+sub object_format {
+ $_[0]->{object_format} //= do {
+ my $fmt = $_[0]->qx(qw(config extensions.objectformat));
+ $fmt eq "sha256\n" ? \'sha256' : \undef;
+ }
+}
+
sub last_check_err {
my ($self) = @_;
my $fh = $self->{err_c} or return;
}
return;
}
+
pipe(my ($out_r, $out_w)) or $self->fail("pipe failed: $!");
- my $rdr = { 0 => $out_r };
+ my $rdr = { 0 => $out_r, pgid => 0 };
my $gd = $self->{git_dir};
if ($gd =~ s!/([^/]+/[^/]+)\z!/!) {
$rdr->{-C} = $gd;
$gd = $1;
}
- my @cmd = (qw(git), "--git-dir=$gd",
- qw(-c core.abbrev=40 cat-file), $batch);
+
+ # git 2.31.0+ supports -c core.abbrev=no, don't bother with
+ # core.abbrev=64 since not many releases had SHA-256 prior to 2.31
+ my $abbr = $GIT_VER < (2 << 24 | 31 << 16) ? 40 : 'no';
+ my @cmd = ($GIT_EXE, "--git-dir=$gd", '-c', "core.abbrev=$abbr",
+ 'cat-file', "--$batch");
if ($err) {
- my $id = "git.$self->{git_dir}$batch.err";
+ my $id = "git.$self->{git_dir}.$batch.err";
my $fh = tmpfile($id) or $self->fail("tmpfile($id): $!");
$self->{$err} = $fh;
$rdr->{2} = $fh;
}
+ # see lib/PublicInbox/ProcessPipe.pm for why we don't use that here
my ($in_r, $p) = popen_rd(\@cmd, undef, $rdr);
- $self->{$pid} = $p;
+ awaitpid($self->{$pid} = $p, undef);
$self->{"$pid.owner"} = $$;
$out_w->autoflush(1);
if ($^O eq 'linux') { # 1031: F_SETPIPE_SZ
fcntl($out_w, 1031, 4096);
- fcntl($in_r, 1031, 4096) if $batch eq '--batch-check';
+ fcntl($in_r, 1031, 4096) if $batch eq 'batch-check';
}
+ $out_w->blocking(0);
$self->{$out} = $out_w;
$self->{$in} = $in_r;
}
return; # unrecoverable error
}
}
- \substr($$rbuf, 0, $len, '');
+ my $no_pad = substr($$rbuf, 0, $len, '');
+ \$no_pad;
}
sub my_readline ($$) {
for (my $i = 0; $i < @$inflight; $i += 3) {
$buf .= "$inflight->[$i]\n";
}
+ $self->{out}->blocking(1); # brand new pipe, should never block
print { $self->{out} } $buf or $self->fail("write error: $!");
+ $self->{out}->blocking(0);
my $req = shift @$inflight;
unshift(@$inflight, \$req); # \$ref to indicate retried
cat_async_step($self, $inflight); # take one step
}
+# returns true if prefetch is successful
+sub async_prefetch {
+ my ($self, $oid, $cb, $arg) = @_;
+ my $inflight = $self->{inflight} or return;
+ return if @$inflight;
+ substr($oid, 0, 0) = 'contents ' if $self->{-bc};
+ write_all($self, $self->{out}, "$oid\n", \&cat_async_step, $inflight);
+ push(@$inflight, $oid, $cb, $arg);
+}
+
sub cat_async_step ($$) {
my ($self, $inflight) = @_;
die 'BUG: inflight empty or odd' if scalar(@$inflight) < 3;
my $rbuf = delete($self->{rbuf}) // \(my $new = '');
my ($bref, $oid, $type, $size);
my $head = my_readline($self->{in}, $rbuf);
+ my $cmd = ref($req) ? $$req : $req;
# ->fail may be called via Gcf2Client.pm
+ my $bc = $self->{-bc};
if ($head =~ /^([0-9a-f]{40,}) (\S+) ([0-9]+)$/) {
($oid, $type, $size) = ($1, $2, $3 + 0);
- $bref = my_read($self->{in}, $rbuf, $size + 1) or
- $self->fail(defined($bref) ? 'read EOF' : "read: $!");
- chop($$bref) eq "\n" or $self->fail('LF missing after blob');
+ unless ($bc && $cmd =~ /\Ainfo /) { # --batch-command
+ $bref = my_read($self->{in}, $rbuf, $size + 1) or
+ $self->fail(defined($bref) ?
+ 'read EOF' : "read: $!");
+ chop($$bref) eq "\n" or
+ $self->fail('LF missing after blob');
+ }
+ } elsif ($bc && $cmd =~ /\Ainfo / &&
+ $head =~ / (missing|ambiguous)\n/) {
+ $type = $1;
+ $oid = substr($cmd, 5);
} elsif ($head =~ s/ missing\n//s) {
$oid = $head;
# ref($req) indicates it's already been retried
return cat_async_retry($self, $inflight);
}
$type = 'missing';
- $oid = ref($req) ? $$req : $req if $oid eq '';
+ if ($oid eq '') {
+ $oid = $cmd;
+ $oid =~ s/\A(?:contents|info) // if $bc;
+ }
} else {
my $err = $! ? " ($!)" : '';
$self->fail("bad result from async cat-file: $head$err");
}
$self->{rbuf} = $rbuf if $$rbuf ne '';
splice(@$inflight, 0, 3); # don't retry $cb on ->fail
- eval { $cb->($bref, $oid, $type, $size, $arg) };
- async_err($self, $req, $oid, $@, 'cat') if $@;
+ if ($bc && $cmd =~ /\Ainfo /) {
+ eval { $cb->($oid, $type, $size, $arg, $self) };
+ async_err($self, $req, $oid, $@, 'check') if $@;
+ } else {
+ eval { $cb->($bref, $oid, $type, $size, $arg) };
+ async_err($self, $req, $oid, $@, 'cat') if $@;
+ }
}
sub cat_async_wait ($) {
}
sub batch_prepare ($) {
- _bidi_pipe($_[0], qw(--batch in out pid));
+ my ($self) = @_;
+ check_git_exe();
+ if ($GIT_VER >= BATCH_CMD_VER) {
+ _bidi_pipe($self, qw(batch-command in out pid err_c));
+ $self->{-bc} = 1;
+ } else {
+ _bidi_pipe($self, qw(batch in out pid));
+ }
+ $self->{inflight} = [];
}
sub _cat_file_cb {
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):
+ # git <2.21 would show `dangling' (2.21+ shows `ambiguous')
# https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/
- if ($hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop') {
+ if ($hex eq 'dangling') {
my $ret = my_read($self->{in_c}, $rbuf, $type + 1);
$self->fail(defined($ret) ? 'read EOF' : "read: $!") if !$ret;
}
sub check_async_wait ($) {
my ($self) = @_;
+ return cat_async_wait($self) if $self->{-bc};
my $inflight_c = $self->{inflight_c} or return;
- while (scalar(@$inflight_c)) {
- check_async_step($self, $inflight_c);
- }
+ check_async_step($self, $inflight_c) while (scalar(@$inflight_c));
}
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));
die 'BUG: already in async check' if $self->{inflight_c};
- $self->{inflight_c} = [];
+ cleanup($self) if alternates_changed($self);
+ check_git_exe();
+ if ($GIT_VER >= BATCH_CMD_VER) {
+ _bidi_pipe($self, qw(batch-command in out pid err_c));
+ $self->{-bc} = 1;
+ $self->{inflight} = [];
+ } else {
+ _bidi_pipe($self, qw(batch-check in_c out_c pid_c err_c));
+ $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 ($$$$) {
my ($self, $oid, $cb, $arg) = @_;
- my $inflight_c = $self->{inflight_c} // check_async_begin($self);
- while (scalar(@$inflight_c) >= MAX_INFLIGHT) {
- check_async_step($self, $inflight_c);
+ my $inflight = $self->{-bc} ?
+ ($self->{inflight} // cat_async_begin($self)) :
+ ($self->{inflight_c} // check_async_begin($self));
+ if ($self->{-bc}) {
+ substr($oid, 0, 0) = 'info ';
+ write_all($self, $self->{out}, "$oid\n",
+ \&cat_async_step, $inflight);
+ } else {
+ write_all($self, $self->{out_c}, "$oid\n",
+ \&check_async_step, $inflight);
}
- print { $self->{out_c} } $oid, "\n" or $self->fail("write error: $!");
- push(@$inflight_c, $oid, $cb, $arg);
+ push(@$inflight, $oid, $cb, $arg);
}
sub _check_cb { # check_async callback
check_async_wait($self);
my ($hex, $type, $size) = @$result;
- # Future versions of git.git may show 'ambiguous', but for now,
- # we must handle 'dangling' below (and maybe some other oddball
- # stuff):
+ # git <2.21 would show `dangling' (2.21+ shows `ambiguous')
# https://public-inbox.org/git/20190118033845.s2vlrb3wd3m2jfzu@dcvr/T/
- return if $type eq 'missing' || $type eq 'ambiguous';
- return if $hex eq 'dangling' || $hex eq 'notdir' || $hex eq 'loop';
+ return if $type =~ /\A(?:missing|ambiguous)\z/ || $hex eq 'dangling';
($hex, $type, $size);
}
sub _destroy {
- my ($self, $rbuf, $in, $out, $pid, $err) = @_;
- delete @$self{($rbuf, $in, $out)};
- delete $self->{$err} if $err; # `err_c'
+ my ($self, $pid, @rest) = @_; # rest = rbuf, in, out, err
+ my ($p) = delete @$self{($pid, @rest)};
- # GitAsyncCat::event_step may delete {pid}
- my $p = delete $self->{$pid} or return;
- dwaitpid($p) if $$ == $self->{"$pid.owner"};
+ # GitAsyncCat::event_step may delete {$pid}
+ awaitpid($p) if defined($p) && $$ == $self->{"$pid.owner"};
}
sub async_abort ($) {
while (scalar(@{$self->{inflight_c} // []}) ||
scalar(@{$self->{inflight} // []})) {
for my $c ('', '_c') {
- my $q = $self->{"inflight$c"};
+ my $q = $self->{"inflight$c"} or next;
while (@$q) {
my ($req, $cb, $arg) = splice(@$q, 0, 3);
$req = $$req if ref($req);
+ $self->{-bc} and
+ $req =~ s/\A(?:contents|info) //;
$req =~ s/ .*//; # drop git_dir for Gcf2Client
eval { $cb->(undef, $req, undef, undef, $arg) };
warn "E: (in abort) $req: $@" if $@;
return 1 if $lazy && (scalar(@{$self->{inflight_c} // []}) ||
scalar(@{$self->{inflight} // []}));
local $in_cleanup = 1;
- delete $self->{async_cat};
+ delete @$self{qw(async_cat async_chk)};
async_wait_all($self);
- delete $self->{inflight};
- delete $self->{inflight_c};
- _destroy($self, qw(rbuf in out pid));
- _destroy($self, qw(rbuf_c in_c out_c pid_c err_c));
+ delete @$self{qw(inflight inflight_c -bc)};
+ _destroy($self, qw(pid rbuf in out err_c));
+ _destroy($self, qw(pid_c rbuf_c in_c out_c err_c));
undef;
}
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 = "$1.git";
- }
- wantarray ? ($ret) : $ret;
+ $_[0]->{nick} // ($_[0]->{git_dir} =~ m!/([^/]+?)(?:/*\.git/*)?\z! ?
+ "$1.git" : undef);
}
sub host_prefix_url ($$) {
my ($env, $url) = @_;
return $url if index($url, '//') >= 0;
- my $scheme = $env->{'psgi.url_scheme'};
my $host_port = $env->{HTTP_HOST} //
"$env->{SERVER_NAME}:$env->{SERVER_PORT}";
- "$scheme://$host_port". ($env->{SCRIPT_NAME} || '/') . $url;
+ my $sn = $env->{SCRIPT_NAME} // '';
+ "$env->{'psgi.url_scheme'}://$host_port$sn/$url";
}
+sub base_url { # for coderepos, PSGI-only
+ my ($self, $env) = @_; # env - PSGI env
+ my $nick = $self->{nick} // return undef;
+ my $url = host_prefix_url($env, '');
+ # for mount in Plack::Builder
+ $url .= '/' if substr($url, -1, 1) ne '/';
+ $url . $nick . '/';
+}
+
+sub isrch {} # TODO
+
sub pub_urls {
my ($self, $env) = @_;
if (my $urls = $self->{cgit_url}) {
- return map { host_prefix_url($env, $_) } @$urls;
+ map { host_prefix_url($env, $_) } @$urls;
+ } else {
+ (base_url($self, $env) // '???');
}
- local_nick($self);
}
sub cat_async_begin {
my ($self) = @_;
cleanup($self) if $self->alternates_changed;
- $self->batch_prepare;
die 'BUG: already in async' if $self->{inflight};
- $self->{inflight} = [];
+ batch_prepare($self);
}
sub cat_async ($$$;$) {
my ($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: $!");
+ substr($oid, 0, 0) = 'contents ' if $self->{-bc};
+ write_all($self, $self->{out}, $oid."\n", \&cat_async_step, $inflight);
push(@$inflight, $oid, $cb, $arg);
}
(split(/ /, <$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 : $desc;
+}
+
+sub description {
+ cat_desc("$_[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, $env), 0, -1) ];
+}
+
# for grokmirror, which doesn't read gitweb.description
# templates/hooks--update.sample and git-multimail in git.git
# only match "Unnamed repository", not the full contents of
sub manifest_entry {
my ($self, $epoch, $default_desc) = @_;
my $fh = $self->popen('show-ref');
- my $dig = Digest::SHA->new(1);
+ my $dig = PublicInbox::SHA->new(1);
while (read($fh, my $buf, 65536)) {
$dig->add($buf);
}
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/) {
+ my $desc = description($self);
+ if (defined $epoch && index($desc, 'Unnamed repository') == 0) {
$desc = "$default_desc [epoch $epoch]";
}
$ent->{description} = $desc;