use PublicInbox::Spawn qw(spawn);
use PublicInbox::MID qw(mid_mime mid2path);
use PublicInbox::Address;
+use PublicInbox::ContentId qw(content_id);
+use PublicInbox::MsgTime qw(msg_timestamp);
sub new {
- my ($class, $git, $name, $email, $inbox) = @_;
+ my ($class, $git, $name, $email, $ibx) = @_;
+ my $ref = 'refs/heads/master';
+ if ($ibx) {
+ $ref = $ibx->{ref_head} || 'refs/heads/master';
+ $name ||= $ibx->{name};
+ $email ||= $ibx->{-primary_address};
+ }
bless {
git => $git,
ident => "$name <$email>",
mark => 1,
- ref => 'refs/heads/master',
- inbox => $inbox,
+ ref => $ref,
+ inbox => $ibx,
+ path_type => '2/38', # or 'v2'
+ ssoma_lock => 1, # disable for v2
+ bytes_added => 0,
}, $class
}
pipe($out_r, $out_w) or die "pipe failed: $!";
my $git = $self->{git};
my $git_dir = $git->{git_dir};
- my $lockpath = "$git_dir/ssoma.lock";
- sysopen(my $lockfh, $lockpath, O_WRONLY|O_CREAT) or
- die "failed to open lock $lockpath: $!";
- # wait for other processes to be done
- flock($lockfh, LOCK_EX) or die "lock failed: $!\n";
+ my $lockfh;
+ if ($self->{ssoma_lock}) {
+ my $lockpath = "$git_dir/ssoma.lock";
+ sysopen($lockfh, $lockpath, O_WRONLY|O_CREAT) or
+ die "failed to open lock $lockpath: $!";
+ # wait for other processes to be done
+ flock($lockfh, LOCK_EX) or die "lock failed: $!\n";
+ }
+
local $/ = "\n";
chomp($self->{tip} = $git->qx(qw(rev-parse --revs-only), $self->{ref}));
my @cmd = ('git', "--git-dir=$git_dir", qw(fast-import
- --quiet --done --date-format=rfc2822));
+ --quiet --done --date-format=raw));
my $rdr = { 0 => fileno($out_r), 1 => fileno($in_w) };
my $pid = spawn(\@cmd, undef, $rdr);
die "spawn fast-import failed: $!" unless defined $pid;
sub wfail () { die "write to fast-import failed: $!" }
-sub now2822 () {
- my @t = gmtime(time);
- my $day = qw(Sun Mon Tue Wed Thu Fri Sat)[$t[6]];
- my $mon = qw(Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec)[$t[4]];
-
- sprintf('%s, %2d %s %d %02d:%02d:%02d +0000',
- $day, $t[3], $mon, $t[5] + 1900, $t[2], $t[1], $t[0]);
-}
+sub now_raw () { time . ' +0000' }
sub norm_body ($) {
my ($mime) = @_;
$b
}
+# only used for v1 (ssoma) inboxes
sub _check_path ($$$$) {
my ($r, $w, $tip, $path) = @_;
return if $tip eq '';
$info =~ /\Amissing / ? undef : $info;
}
-# returns undef on non-existent
-# ('MISMATCH', msg) on mismatch
-# (:MARK, msg) on success
-sub remove {
- my ($self, $mime, $msg) = @_; # mime = Email::MIME
+sub check_remove_v1 {
+ my ($r, $w, $tip, $path, $mime) = @_;
- my $mid = mid_mime($mime);
- my $path = mid2path($mid);
-
- my ($r, $w) = $self->gfi_start;
- my $tip = $self->{tip};
my $info = _check_path($r, $w, $tip, $path) or return ('MISSING',undef);
$info =~ m!\A100644 blob ([a-f0-9]{40})\t!s or die "not blob: $info";
my $blob = $1;
if ($cur_s ne $cur_m || norm_body($cur) ne norm_body($mime)) {
return ('MISMATCH', $cur);
}
+ (undef, $cur);
+}
+
+# used for v2 (maybe)
+sub checkpoint {
+ my ($self) = @_;
+ return unless $self->{pid};
+ print { $self->{out} } "checkpoint\n" or wfail;
+ undef;
+}
+
+# used for v2
+sub get_mark {
+ my ($self, $mark) = @_;
+ die "not active\n" unless $self->{pid};
+ my ($r, $w) = $self->gfi_start;
+ print $w "get-mark $mark\n" or wfail;
+ defined(my $oid = <$r>) or die "get-mark failed, need git 2.6.0+\n";
+ $oid;
+}
+
+# returns undef on non-existent
+# ('MISMATCH', Email::MIME) on mismatch
+# (:MARK, Email::MIME) on success
+#
+# For v2 inboxes, the content_id is returned instead of the msg
+# v2 callers should check with Xapian before calling this as
+# it is not idempotent.
+sub remove {
+ my ($self, $mime, $msg) = @_; # mime = Email::MIME
+
+ my $path_type = $self->{path_type};
+ my ($path, $err, $cur, $blob);
+
+ my ($r, $w) = $self->gfi_start;
+ my $tip = $self->{tip};
+ if ($path_type eq '2/38') {
+ $path = mid2path(mid_mime($mime));
+ ($err, $cur) = check_remove_v1($r, $w, $tip, $path, $mime);
+ return ($err, $cur) if $err;
+ } else {
+ $cur = content_id($mime);
+ my $len = length($cur);
+ $blob = $self->{mark}++;
+ print $w "blob\nmark :$blob\ndata $len\n$cur\n" or wfail;
+ }
my $ref = $self->{ref};
my $commit = $self->{mark}++;
print $w "reset $ref\n" or wfail;
}
my $ident = $self->{ident};
- my $now = now2822();
+ my $now = now_raw();
$msg ||= 'rm';
my $len = length($msg) + 1;
print $w "commit $ref\nmark :$commit\n",
"committer $ident $now\n",
"data $len\n$msg\n\n",
'from ', ($parent ? $parent : $tip), "\n" or wfail;
- print $w "D $path\n\n" or wfail;
+ if (defined $path) {
+ print $w "D $path\n\n" or wfail;
+ } else {
+ print $w "M 100644 :$blob d\n\n" or wfail;
+ }
$self->{nchg}++;
(($self->{tip} = ":$commit"), $cur);
}
-# returns undef on duplicate
-sub add {
- my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
+sub parse_date ($) {
+ my ($mime) = @_;
+ my ($ts, $zone) = msg_timestamp($mime->header_obj);
+ $ts = 0 if $ts < 0; # git uses unsigned times
+ "$ts $zone";
+}
+sub extract_author_info ($) {
+ my ($mime) = @_;
+
+ my $sender = '';
my $from = $mime->header('From');
my ($email) = PublicInbox::Address::emails($from);
my ($name) = PublicInbox::Address::names($from);
+ if (!defined($name) || !defined($email)) {
+ $sender = $mime->header('Sender');
+ if (!defined($name)) {
+ ($name) = PublicInbox::Address::names($sender);
+ }
+ if (!defined($email)) {
+ ($email) = PublicInbox::Address::emails($sender);
+ }
+ }
+ if (defined $email) {
+ # quiet down wide character warnings with utf8::encode
+ utf8::encode($email);
+ } else {
+ $email = '';
+ warn "no email in From: $from or Sender: $sender\n";
+ }
+
# git gets confused with:
# "'A U Thor <u@example.com>' via foo" <foo@example.com>
# ref:
# <CAD0k6qSUYANxbjjbE4jTW4EeVwOYgBD=bXkSu=akiYC_CB7Ffw@mail.gmail.com>
- $name =~ tr/<>//d;
+ if (defined $name) {
+ $name =~ tr/<>//d;
+ utf8::encode($name);
+ } else {
+ $name = '';
+ warn "no name in From: $from or Sender: $sender\n";
+ }
+ ($name, $email);
+}
- my $date = $mime->header('Date');
+# returns undef on duplicate
+# returns the :MARK of the most recent commit
+sub add {
+ my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
+
+ my ($name, $email) = extract_author_info($mime);
+ my $date_raw = parse_date($mime);
my $subject = $mime->header('Subject');
$subject = '(no subject)' unless defined $subject;
- my $mid = mid_mime($mime);
- my $path = mid2path($mid);
+ my $path_type = $self->{path_type};
+
+ my $path;
+ if ($path_type eq '2/38') {
+ $path = mid2path(mid_mime($mime));
+ } else { # v2 layout, one file:
+ $path = 'm';
+ }
my ($r, $w) = $self->gfi_start;
my $tip = $self->{tip};
- _check_path($r, $w, $tip, $path) and return;
+ if ($path_type eq '2/38') {
+ _check_path($r, $w, $tip, $path) and return;
+ }
# kill potentially confusing/misleading headers
$mime->header_set($_) for qw(bytes lines content-length status);
+
+ # spam check:
if ($check_cb) {
$mime = $check_cb->($mime) or return;
}
- $mime = $mime->as_string;
my $blob = $self->{mark}++;
- print $w "blob\nmark :$blob\ndata ", length($mime), "\n" or wfail;
- print $w $mime, "\n" or wfail;
+ my $str = $mime->as_string;
+ my $n = length($str);
+ $self->{bytes_added} += $n;
+ print $w "blob\nmark :$blob\ndata ", $n, "\n" or wfail;
+ print $w $str, "\n" or wfail;
+
+ # v2: we need this for Xapian
+ if ($self->{want_object_info}) {
+ chomp(my $oid = $self->get_mark(":$blob"));
+ $self->{last_object} = [ $oid, $n, \$str ];
+ }
my $ref = $self->{ref};
my $commit = $self->{mark}++;
my $parent = $tip =~ /\A:/ ? $tip : undef;
print $w "reset $ref\n" or wfail;
}
- utf8::encode($email);
- utf8::encode($name);
utf8::encode($subject);
- # quiet down wide character warnings:
print $w "commit $ref\nmark :$commit\n",
- "author $name <$email> $date\n",
- "committer $self->{ident} ", now2822(), "\n" or wfail;
+ "author $name <$email> $date_raw\n",
+ "committer $self->{ident} ", now_raw(), "\n" or wfail;
print $w "data ", (length($subject) + 1), "\n",
$subject, "\n\n" or wfail;
if ($tip ne '') {
$self->{tip} = ":$commit";
}
-sub run_die ($$) {
+sub run_die ($;$) {
my ($cmd, $env) = @_;
my $pid = spawn($cmd, $env, undef);
defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
# for compatibility with existing ssoma installations
# we can probably remove this entirely by 2020
my $git_dir = $self->{git}->{git_dir};
- # XXX: change the following scope to: if (-e $index) # in 2018 or so..
my @cmd = ('git', "--git-dir=$git_dir");
- if ($nchg && !$ENV{FAST}) {
- my $index = "$git_dir/ssoma.index";
+ my $index = "$git_dir/ssoma.index";
+ if ($nchg && -e $index && !$ENV{FAST}) {
my $env = { GIT_INDEX_FILE => $index };
run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env);
}
if ($nchg) {
run_die([@cmd, 'update-server-info'], undef);
- eval {
+ ($self->{path_type} eq '2/38') and eval {
require PublicInbox::SearchIdx;
my $inbox = $self->{inbox} || $git_dir;
my $s = PublicInbox::SearchIdx->new($inbox);
eval { run_die([@cmd, qw(gc --auto)], undef) };
}
+ $self->{ssoma_lock} or return;
my $lockfh = delete $self->{lockfh} or die "BUG: not locked: $!";
flock($lockfh, LOCK_UN) or die "unlock failed: $!";
close $lockfh or die "close lock failed: $!";
}
+sub atfork_child {
+ my ($self) = @_;
+ foreach my $f (qw(in out)) {
+ close $self->{$f} or die "failed to close import[$f]: $!\n";
+ }
+}
+
1;
__END__
=pod