init: add --skip-artnum parameter

[public-inbox.git] / lib / PublicInbox / InboxWritable.pm

diff --git a/lib/PublicInbox/InboxWritable.pm b/lib/PublicInbox/InboxWritable.pm
index ce979ea2bf8c65fe2f5f72ce16ef5d58515b5762..f9e28502001499b72d7f6e7766f4e824920862db 100644 (file)
--- a/lib/PublicInbox/InboxWritable.pm
+++ b/lib/PublicInbox/InboxWritable.pm
@@ -39,10 +39,21 @@ sub assert_usable_dir {
 
 sub init_inbox {
        my ($self, $shards, $skip_epoch, $skip_artnum) = @_;
-       # TODO: honor skip_artnum
        if ($self->version == 1) {
                my $dir = assert_usable_dir($self);
                PublicInbox::Import::init_bare($dir);
+               if (defined($self->{indexlevel}) || defined($skip_artnum)) {
+                       require PublicInbox::SearchIdx;
+                       my $sidx = PublicInbox::SearchIdx->new($self, 1); # just create
+                       $sidx->begin_txn_lazy;
+                       $self->with_umask(sub {
+                               my $mm = PublicInbox::Msgmap->new($dir, 1);
+                               $mm->{dbh}->begin_work;
+                               $mm->skip_artnum($skip_artnum);
+                               $mm->{dbh}->commit;
+                       }) if defined($skip_artnum);
+                       $sidx->commit_txn_lazy;
+               }
        } else {
                my $v2w = importer($self);
                $v2w->init_inbox($shards, $skip_epoch, $skip_artnum);
@@ -57,7 +68,7 @@ sub importer {
                die "v2 not supported: $@\n" if $@;
                my $opt = $self->{-creat_opt};
                my $v2w = PublicInbox::V2Writable->new($self, $opt);
-               $v2w->{parallel} = $parallel;
+               $v2w->{parallel} = $parallel if defined $parallel;
                $v2w;
        } elsif ($v == 1) {
                my @arg = (undef, undef, undef, $self);
@@ -111,13 +122,13 @@ sub is_maildir_path ($) {
        (is_maildir_basename($p[-1]) && -f $path) ? 1 : 0;
 }
 
-sub maildir_path_load ($) {
+sub mime_from_path ($) {
        my ($path) = @_;
        if (open my $fh, '<', $path) {
                local $/;
                my $str = <$fh>;
                $str or return;
-               return PublicInbox::MIME->new(\$str);
+               return PublicInbox::Eml->new(\$str);
        } elsif ($!{ENOENT}) {
                # common with Maildir
                return;
@@ -138,7 +149,7 @@ sub import_maildir {
                opendir my $dh, "$dir/$sub" or die "opendir $dir/$sub: $!\n";
                while (defined(my $fn = readdir($dh))) {
                        next unless is_maildir_basename($fn);
-                       my $mime = maildir_path_load("$dir/$fn") or next;
+                       my $mime = mime_from_path("$dir/$fn") or next;
 
                        if (my $filter = $self->filter($im)) {
                                my $ret = $filter->scrub($mime) or return;
@@ -157,12 +168,12 @@ my $from_strict = qr/^From \S+ +\S+ \S+ +\S+ [^:]+:[^:]+:[^:]+ [^:]+/;
 sub mb_add ($$$$) {
        my ($im, $variant, $filter, $msg) = @_;
        $$msg =~ s/(\r?\n)+\z/$1/s;
-       my $mime = PublicInbox::MIME->new($msg);
        if ($variant eq 'mboxrd') {
-               $$msg =~ s/^>(>*From )/$1/sm;
+               $$msg =~ s/^>(>*From )/$1/gms;
        } elsif ($variant eq 'mboxo') {
-               $$msg =~ s/^>From /From /sm;
+               $$msg =~ s/^>From /From /gms;
        }
+       my $mime = PublicInbox::Eml->new($msg);
        if ($filter) {
                my $ret = $filter->scrub($mime) or return;
                return if $ret == REJECT();