package PublicInbox::Import;
use strict;
use warnings;
-use Fcntl qw(:flock :DEFAULT);
+use base qw(PublicInbox::Lock);
use PublicInbox::Spawn qw(spawn);
-use PublicInbox::MID qw(mid_mime mid2path);
+use PublicInbox::MID qw(mids mid_mime mid2path);
use PublicInbox::Address;
-use PublicInbox::ContentId qw(content_id);
-use Date::Parse qw(str2time);
-use Time::Zone qw(tz_offset);
+use PublicInbox::MsgTime qw(msg_timestamp msg_datestamp);
+use PublicInbox::ContentId qw(content_digest);
+use PublicInbox::MDA;
+use POSIX qw(strftime);
sub new {
my ($class, $git, $name, $email, $ibx) = @_;
ref => $ref,
inbox => $ibx,
path_type => '2/38', # or 'v2'
- ssoma_lock => 1, # disable for v2
+ lock_path => "$git->{git_dir}/ssoma.lock", # v2 changes this
+ bytes_added => 0,
}, $class
}
pipe($in_r, $in_w) or die "pipe failed: $!";
pipe($out_r, $out_w) or die "pipe failed: $!";
my $git = $self->{git};
- my $git_dir = $git->{git_dir};
- 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";
- }
+ $self->lock_acquire;
local $/ = "\n";
- chomp($self->{tip} = $git->qx(qw(rev-parse --revs-only), $self->{ref}));
+ my $ref = $self->{ref};
+ chomp($self->{tip} = $git->qx(qw(rev-parse --revs-only), $ref));
+ if ($self->{path_type} ne '2/38' && $self->{tip}) {
+ local $/ = "\0";
+ my @tree = $git->qx(qw(ls-tree -r -z --name-only), $ref);
+ chomp @tree;
+ $self->{-tree} = { map { $_ => 1 } @tree };
+ }
+ my $git_dir = $git->{git_dir};
my @cmd = ('git', "--git-dir=$git_dir", qw(fast-import
--quiet --done --date-format=raw));
my $rdr = { 0 => fileno($out_r), 1 => fileno($in_w) };
$out_w->autoflush(1);
$self->{in} = $in_r;
$self->{out} = $out_w;
- $self->{lockfh} = $lockfh;
$self->{pid} = $pid;
$self->{nchg} = 0;
binmode $out_w, ':raw' or die "binmode :raw failed: $!";
$info =~ /\Amissing / ? undef : $info;
}
-sub check_remove_v1 {
- my ($r, $w, $tip, $path, $mime) = @_;
-
- 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;
-
- print $w "cat-blob $blob\n" or wfail;
+sub _cat_blob ($$$) {
+ my ($r, $w, $oid) = @_;
+ print $w "cat-blob $oid\n" or wfail;
local $/ = "\n";
- $info = <$r>;
+ my $info = <$r>;
defined $info or die "EOF from fast-import / cat-blob: $!";
- $info =~ /\A[a-f0-9]{40} blob (\d+)\n\z/ or
- die "unexpected cat-blob response: $info";
+ $info =~ /\A[a-f0-9]{40} blob (\d+)\n\z/ or return;
my $left = $1;
my $offset = 0;
my $buf = '';
$n = read($r, my $lf, 1);
defined($n) or die "read final byte of cat-blob failed: $!";
die "bad read on final byte: <$lf>" if $lf ne "\n";
- my $cur = PublicInbox::MIME->new($buf);
+
+ # fixup some bugginess in old versions:
+ $buf =~ s/\A[\r\n]*From [^\r\n]*\r?\n//s;
+ \$buf;
+}
+
+sub cat_blob {
+ my ($self, $oid) = @_;
+ my ($r, $w) = $self->gfi_start;
+ _cat_blob($r, $w, $oid);
+}
+
+sub check_remove_v1 {
+ my ($r, $w, $tip, $path, $mime) = @_;
+
+ my $info = _check_path($r, $w, $tip, $path) or return ('MISSING',undef);
+ $info =~ m!\A100644 blob ([a-f0-9]{40})\t!s or die "not blob: $info";
+ my $oid = $1;
+ my $msg = _cat_blob($r, $w, $oid) or die "BUG: cat-blob $1 failed";
+ my $cur = PublicInbox::MIME->new($msg);
my $cur_s = $cur->header('Subject');
$cur_s = '' unless defined $cur_s;
my $cur_m = $mime->header('Subject');
(undef, $cur);
}
-# used for v2 (maybe)
sub checkpoint {
my ($self) = @_;
return unless $self->{pid};
undef;
}
+sub progress {
+ my ($self, $msg) = @_;
+ return unless $self->{pid};
+ print { $self->{out} } "progress $msg\n" or wfail;
+ $self->{in}->getline eq "progress $msg\n" or die
+ "progress $msg not received\n";
+ undef;
+}
+
+sub _update_git_info ($$) {
+ my ($self, $do_gc) = @_;
+ # for compatibility with existing ssoma installations
+ # we can probably remove this entirely by 2020
+ my $git_dir = $self->{git}->{git_dir};
+ my @cmd = ('git', "--git-dir=$git_dir");
+ my $index = "$git_dir/ssoma.index";
+ if (-e $index && !$ENV{FAST}) {
+ my $env = { GIT_INDEX_FILE => $index };
+ run_die([@cmd, qw(read-tree -m -v -i), $self->{ref}], $env);
+ }
+ run_die([@cmd, 'update-server-info'], undef);
+ ($self->{path_type} eq '2/38') and eval {
+ require PublicInbox::SearchIdx;
+ my $inbox = $self->{inbox} || $git_dir;
+ my $s = PublicInbox::SearchIdx->new($inbox);
+ $s->index_sync({ ref => $self->{ref} });
+ };
+ eval { run_die([@cmd, qw(gc --auto)], undef) } if $do_gc;
+}
+
+sub barrier {
+ my ($self) = @_;
+
+ # For safety, we ensure git checkpoint is complete before because
+ # the data in git is still more important than what is in Xapian
+ # in v2. Performance may be gained by delaying the ->progress
+ # call but we lose safety
+ if ($self->{nchg}) {
+ $self->checkpoint;
+ $self->progress('checkpoint');
+ _update_git_info($self, 0);
+ $self->{nchg} = 0;
+ }
+}
+
# used for v2
sub get_mark {
my ($self, $mark) = @_;
my ($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";
+ chomp($oid);
$oid;
}
# ('MISMATCH', Email::MIME) on mismatch
# (:MARK, Email::MIME) on success
#
-# For v2 inboxes, the content_id is returned instead of the msg
# v2 callers should check with Xapian before calling this as
# it is not idempotent.
sub remove {
my ($r, $w) = $self->gfi_start;
my $tip = $self->{tip};
if ($path_type eq '2/38') {
- $path = mid2path(mid_mime($mime));
+ $path = mid2path(v1_mid0($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);
+ my $sref;
+ if (ref($mime) eq 'SCALAR') { # optimization used by V2Writable
+ $sref = $mime;
+ } else { # XXX should not be necessary:
+ my $str = $mime->as_string;
+ $sref = \$str;
+ }
+ my $len = length($$sref);
$blob = $self->{mark}++;
- print $w "blob\nmark :$blob\ndata $len\n$cur\n" or wfail;
+ print $w "blob\nmark :$blob\ndata $len\n",
+ $$sref, "\n" or wfail;
}
my $ref = $self->{ref};
if (defined $path) {
print $w "D $path\n\n" or wfail;
} else {
+ clean_tree_v2($self, $w, 'd');
print $w "M 100644 :$blob d\n\n" or wfail;
}
$self->{nchg}++;
(($self->{tip} = ":$commit"), $cur);
}
-sub parse_date ($) {
+sub git_timestamp {
+ my ($ts, $zone) = @_;
+ $ts = 0 if $ts < 0; # git uses unsigned times
+ "$ts $zone";
+}
+
+sub extract_author_info ($) {
my ($mime) = @_;
- my $hdr = $mime->header_obj;
- my $date = $hdr->header_raw('Date');
- my ($ts, $zone);
- my $mid = $hdr->header_raw('Message-ID');
- if ($date) {
- $ts = eval { str2time($date) };
- if ($@) {
- warn "bad Date: $date in $mid: $@\n";
- } elsif ($date =~ /\s+([\+\-]\d+)\s*\z/) {
- $zone = $1;
+
+ 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);
}
- }
- unless ($ts) {
- my @recvd = $hdr->header_raw('Received');
- foreach my $r (@recvd) {
- $zone = undef;
- $r =~ /\s*(\d+\s+[[:alpha:]]+\s+\d{2,4}\s+
- \d+\D\d+(?:\D\d+)\s+([\+\-]\d+))/osx or next;
- $zone = $2;
- $ts = eval { str2time($1) } and last;
- warn "no date in Received: $r\n";
+ if (!defined($email)) {
+ ($email) = PublicInbox::Address::emails($sender);
}
}
- $zone ||= '+0000';
- # "-1200" is the furthest westermost zone offset,
- # but git fast-import is liberal so we use "-1400"
- if ($zone >= 1400 || $zone <= -1400) {
- warn "bogus TZ offset: $zone, ignoring and assuming +0000\n";
- $zone = '+0000';
+ 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";
}
- $ts ||= time;
- $ts = 0 if $ts < 0; # git uses unsigned times
- "$ts $zone";
+
+ # git gets confused with:
+ # "'A U Thor <u@example.com>' via foo" <foo@example.com>
+ # ref:
+ # <CAD0k6qSUYANxbjjbE4jTW4EeVwOYgBD=bXkSu=akiYC_CB7Ffw@mail.gmail.com>
+ if (defined $name) {
+ $name =~ tr/<>//d;
+ utf8::encode($name);
+ } else {
+ $name = '';
+ warn "no name in From: $from or Sender: $sender\n";
+ }
+ ($name, $email);
+}
+
+# kill potentially confusing/misleading headers
+sub drop_unwanted_headers ($) {
+ my ($mime) = @_;
+
+ $mime->header_set($_) for qw(bytes lines content-length status);
+ $mime->header_set($_) for @PublicInbox::MDA::BAD_HEADERS;
+}
+
+# used by V2Writable, too
+sub append_mid ($$) {
+ my ($hdr, $mid0) = @_;
+ # @cur is likely empty if we need to call this sub, but it could
+ # have random unparseable crap which we'll preserve, too.
+ my @cur = $hdr->header_raw('Message-ID');
+ $hdr->header_set('Message-ID', @cur, "<$mid0>");
+}
+
+sub v1_mid0 ($) {
+ my ($mime) = @_;
+ my $hdr = $mime->header_obj;
+ my $mids = mids($hdr);
+
+ if (!scalar(@$mids)) { # spam often has no Message-Id
+ my $mid0 = digest2mid(content_digest($mime), $hdr);
+ append_mid($hdr, $mid0);
+ return $mid0;
+ }
+ $mids->[0];
+}
+sub clean_tree_v2 ($$$) {
+ my ($self, $w, $keep) = @_;
+ my $tree = $self->{-tree} or return; #v2 only
+ delete $tree->{$keep};
+ foreach (keys %$tree) {
+ print $w "D $_\n" or wfail;
+ }
+ %$tree = ($keep => 1);
}
# returns undef on duplicate
sub add {
my ($self, $mime, $check_cb) = @_; # mime = Email::MIME
- my $from = $mime->header('From');
- my ($email) = PublicInbox::Address::emails($from);
- my ($name) = PublicInbox::Address::names($from);
-
- my $date_raw = parse_date($mime);
+ my ($name, $email) = extract_author_info($mime);
+ my $hdr = $mime->header_obj;
+ my @at = msg_datestamp($hdr);
+ my @ct = msg_timestamp($hdr);
+ my $author_time_raw = git_timestamp(@at);
+ my $commit_time_raw = git_timestamp(@ct);
my $subject = $mime->header('Subject');
$subject = '(no subject)' unless defined $subject;
my $path_type = $self->{path_type};
my $path;
if ($path_type eq '2/38') {
- $path = mid2path(mid_mime($mime));
+ $path = mid2path(v1_mid0($mime));
} else { # v2 layout, one file:
$path = 'm';
}
_check_path($r, $w, $tip, $path) and return;
}
- # kill potentially confusing/misleading headers
- $mime->header_set($_) for qw(bytes lines content-length status);
+ drop_unwanted_headers($mime);
# spam check:
if ($check_cb) {
my $blob = $self->{mark}++;
my $str = $mime->as_string;
- print $w "blob\nmark :$blob\ndata ", length($str), "\n" or wfail;
+ my $n = length($str);
+ $self->{bytes_added} += $n;
+ print $w "blob\nmark :$blob\ndata ", $n, "\n" or wfail;
print $w $str, "\n" or wfail;
- $str = undef;
# v2: we need this for Xapian
- if ($self->{want_object_id}) {
- chomp($self->{last_object_id} = $self->get_mark(":$blob"));
+ if ($self->{want_object_info}) {
+ 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;
}
- # quiet down wide character warnings with utf8::encode
- if (defined $email) {
- utf8::encode($email);
- } else {
- $email = '';
- warn "no email in From: $from\n";
- }
-
- # git gets confused with:
- # "'A U Thor <u@example.com>' via foo" <foo@example.com>
- # ref:
- # <CAD0k6qSUYANxbjjbE4jTW4EeVwOYgBD=bXkSu=akiYC_CB7Ffw@mail.gmail.com>
- if (defined $name) {
- $name =~ tr/<>//d;
- utf8::encode($name);
- } else {
- $name = '';
- warn "no name in From: $from\n";
- }
utf8::encode($subject);
print $w "commit $ref\nmark :$commit\n",
- "author $name <$email> $date_raw\n",
- "committer $self->{ident} ", now_raw(), "\n" or wfail;
+ "author $name <$email> $author_time_raw\n",
+ "committer $self->{ident} $commit_time_raw\n" or wfail;
print $w "data ", (length($subject) + 1), "\n",
$subject, "\n\n" or wfail;
if ($tip ne '') {
print $w 'from ', ($parent ? $parent : $tip), "\n" or wfail;
}
+ clean_tree_v2($self, $w, $path);
print $w "M 100644 :$blob $path\n\n" or wfail;
$self->{nchg}++;
$self->{tip} = ":$commit";
}
-sub run_die ($$) {
- my ($cmd, $env) = @_;
- my $pid = spawn($cmd, $env, undef);
+sub run_die ($;$$) {
+ my ($cmd, $env, $rdr) = @_;
+ my $pid = spawn($cmd, $env, $rdr);
defined $pid or die "spawning ".join(' ', @$cmd)." failed: $!";
waitpid($pid, 0) == $pid or die join(' ', @$cmd) .' did not finish';
$? == 0 or die join(' ', @$cmd) . " failed: $?\n";
my $pid = delete $self->{pid} or die 'BUG: missing {pid} when done';
waitpid($pid, 0) == $pid or die 'fast-import did not finish';
$? == 0 or die "fast-import failed: $?";
- my $nchg = delete $self->{nchg};
- # for compatibility with existing ssoma installations
- # we can probably remove this entirely by 2020
- my $git_dir = $self->{git}->{git_dir};
- my @cmd = ('git', "--git-dir=$git_dir");
- 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}], $env);
+ _update_git_info($self, 1) if delete $self->{nchg};
+
+ $self->lock_release;
+}
+
+sub atfork_child {
+ my ($self) = @_;
+ foreach my $f (qw(in out)) {
+ close $self->{$f} or die "failed to close import[$f]: $!\n";
}
- if ($nchg) {
- run_die([@cmd, 'update-server-info'], undef);
- eval {
- require PublicInbox::SearchIdx;
- my $inbox = $self->{inbox} || $git_dir;
- my $s = PublicInbox::SearchIdx->new($inbox);
- $s->index_sync({ ref => $self->{ref} });
- };
-
- eval { run_die([@cmd, qw(gc --auto)], undef) };
+}
+
+sub digest2mid ($$) {
+ my ($dig, $hdr) = @_;
+ my $b64 = $dig->clone->b64digest;
+ # Make our own URLs nicer:
+ # See "Base 64 Encoding with URL and Filename Safe Alphabet" in RFC4648
+ $b64 =~ tr!+/=!-_!d;
+
+ # Add a date prefix to prevent a leading '-' in case that trips
+ # up some tools (e.g. if a Message-ID were a expected as a
+ # command-line arg)
+ my $dt = msg_datestamp($hdr);
+ $dt = POSIX::strftime('%Y%m%d%H%M%S', gmtime($dt));
+ "$dt.$b64" . '@z';
+}
+
+sub clean_purge_buffer {
+ my ($oids, $buf) = @_;
+ my $cmt_msg = 'purged '.join(' ',@$oids)."\n";
+ @$oids = ();
+
+ foreach my $i (0..$#$buf) {
+ my $l = $buf->[$i];
+ if ($l =~ /^author .* (\d+ [\+-]?\d+)$/) {
+ $buf->[$i] = "author <> $1\n";
+ } elsif ($l =~ /^data (\d+)/) {
+ $buf->[$i++] = "data " . length($cmt_msg) . "\n";
+ $buf->[$i] = $cmt_msg;
+ last;
+ }
+ }
+}
+
+sub purge_oids {
+ my ($self, $purge) = @_;
+ my $tmp = "refs/heads/purge-".((keys %$purge)[0]);
+ my $old = $self->{'ref'};
+ my $git = $self->{git};
+ my @export = (qw(fast-export --no-data --use-done-feature), $old);
+ my ($rd, $pid) = $git->popen(@export);
+ my ($r, $w) = $self->gfi_start;
+ my @buf;
+ my $npurge = 0;
+ my @oids;
+ my ($done, $mark);
+ my $tree = $self->{-tree};
+ while (<$rd>) {
+ if (/^reset (?:.+)/) {
+ push @buf, "reset $tmp\n";
+ } elsif (/^commit (?:.+)/) {
+ if (@buf) {
+ $w->print(@buf) or wfail;
+ @buf = ();
+ }
+ push @buf, "commit $tmp\n";
+ } elsif (/^data (\d+)/) {
+ # only commit message, so $len is small:
+ my $len = $1; # + 1 for trailing "\n"
+ push @buf, $_;
+ my $n = read($rd, my $buf, $len) or die "read: $!";
+ $len == $n or die "short read ($n < $len)";
+ push @buf, $buf;
+ } elsif (/^M 100644 ([a-f0-9]+) (\w+)/) {
+ my ($oid, $path) = ($1, $2);
+ if ($purge->{$oid}) {
+ push @oids, $oid;
+ delete $tree->{$path};
+ } else {
+ $tree->{$path} = 1;
+ push @buf, $_;
+ }
+ } elsif (/^D (\w+)/) {
+ my $path = $1;
+ push @buf, $_ if $tree->{$path};
+ } elsif ($_ eq "\n") {
+ if (@oids) {
+ my $out = join('', @buf);
+ $out =~ s/^/# /sgm;
+ warn "purge rewriting\n", $out, "\n";
+ clean_purge_buffer(\@oids, \@buf);
+ $npurge++;
+ }
+ $w->print(@buf, "\n") or wfail;
+ @buf = ();
+ } elsif ($_ eq "done\n") {
+ $done = 1;
+ } elsif (/^mark :(\d+)$/) {
+ push @buf, $_;
+ $mark = $1;
+ } else {
+ push @buf, $_;
+ }
}
+ if (@buf) {
+ $w->print(@buf) or wfail;
+ }
+ die 'done\n not seen from fast-export' unless $done;
+ chomp(my $cmt = $self->get_mark(":$mark")) if $npurge;
+ $self->{nchg} = 0; # prevent _update_git_info until update-ref:
+ $self->done;
+ my @git = ('git', "--git-dir=$git->{git_dir}");
+
+ run_die([@git, qw(update-ref), $old, $tmp]) if $npurge;
- $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: $!";
+ run_die([@git, qw(update-ref -d), $tmp]);
+
+ return if $npurge == 0;
+
+ run_die([@git, qw(-c gc.reflogExpire=now gc --prune=all)]);
+ my $err = 0;
+ foreach my $oid (keys %$purge) {
+ my @info = $git->check($oid);
+ if (@info) {
+ warn "$oid not purged\n";
+ $err++;
+ }
+ }
+ _update_git_info($self, 0);
+ die "Failed to purge $err object(s)\n" if $err;
+ $cmt;
}
1;