index: support --compact / -c on command-line

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

diff --git a/lib/PublicInbox/InboxWritable.pm b/lib/PublicInbox/InboxWritable.pm
index 87c9ada9757c375ad97cf79207f428386f74565e..ce979ea2bf8c65fe2f5f72ce16ef5d58515b5762 100644 (file)
--- a/lib/PublicInbox/InboxWritable.pm
+++ b/lib/PublicInbox/InboxWritable.pm
@@ -1,4 +1,4 @@
-# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2020 all contributors <meta@public-inbox.org>
 # License: AGPL-3.0+ <https://www.gnu.org/licenses/agpl-3.0.txt>
 
 # Extends read-only Inbox for writing
@@ -7,8 +7,7 @@ use strict;
 use warnings;
 use base qw(PublicInbox::Inbox);
 use PublicInbox::Import;
-use PublicInbox::Filter::Base;
-*REJECT = *PublicInbox::Filter::Base::REJECT;
+use PublicInbox::Filter::Base qw(REJECT);
 
 use constant {
        PERM_UMASK => 0,
@@ -19,36 +18,67 @@ use constant {
 };
 
 sub new {
-       my ($class, $ibx) = @_;
-       bless $ibx, $class;
+       my ($class, $ibx, $creat_opt) = @_;
+       return $ibx if ref($ibx) eq $class;
+       my $self = bless $ibx, $class;
+
+       # TODO: maybe stop supporting this
+       if ($creat_opt) { # for { nproc => $N }
+               $self->{-creat_opt} = $creat_opt;
+               init_inbox($self) if $self->version == 1;
+       }
+       $self;
+}
+
+sub assert_usable_dir {
+       my ($self) = @_;
+       my $dir = $self->{inboxdir};
+       return $dir if defined($dir) && $dir ne '';
+       die "no inboxdir defined for $self->{name}\n";
+}
+
+sub init_inbox {
+       my ($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);
+       } else {
+               my $v2w = importer($self);
+               $v2w->init_inbox($shards, $skip_epoch, $skip_artnum);
+       }
 }
 
 sub importer {
        my ($self, $parallel) = @_;
-       $self->{-importer} ||= eval {
-               my $v = $self->{version} || 1;
-               if ($v == 2) {
-                       eval { require PublicInbox::V2Writable };
-                       die "v2 not supported: $@\n" if $@;
-                       my $v2w = PublicInbox::V2Writable->new($self);
-                       $v2w->{parallel} = $parallel;
-                       $v2w;
-               } elsif ($v == 1) {
-                       my $git = $self->git;
-                       my $name = $self->{name};
-                       my $addr = $self->{-primary_address};
-                       PublicInbox::Import->new($git, $name, $addr, $self);
-               } else {
-                       $! = 78; # EX_CONFIG 5.3.5 local configuration error
-                       die "unsupported inbox version: $v\n";
-               }
+       my $v = $self->version;
+       if ($v == 2) {
+               eval { require PublicInbox::V2Writable };
+               die "v2 not supported: $@\n" if $@;
+               my $opt = $self->{-creat_opt};
+               my $v2w = PublicInbox::V2Writable->new($self, $opt);
+               $v2w->{parallel} = $parallel;
+               $v2w;
+       } elsif ($v == 1) {
+               my @arg = (undef, undef, undef, $self);
+               PublicInbox::Import->new(@arg);
+       } else {
+               $! = 78; # EX_CONFIG 5.3.5 local configuration error
+               die "unsupported inbox version: $v\n";
        }
 }
 
 sub filter {
-       my ($self) = @_;
+       my ($self, $im) = @_;
        my $f = $self->{filter};
        if ($f && $f =~ /::/) {
+               # v2 keeps msgmap open, which causes conflicts for filters
+               # such as PublicInbox::Filter::RubyLang which overload msgmap
+               # for a predictable serial number.
+               if ($im && $self->version >= 2 && $self->{altid}) {
+                       $im->done;
+               }
+
                my @args = (-inbox => $self);
                # basic line splitting, only
                # Perhaps we can have proper quote splitting one day...
@@ -100,7 +130,7 @@ sub maildir_path_load ($) {
 sub import_maildir {
        my ($self, $dir) = @_;
        my $im = $self->importer(1);
-       my $filter = $self->filter;
+
        foreach my $sub (qw(cur new tmp)) {
                -d "$dir/$sub" or die "$dir is not a Maildir (missing $sub)\n";
        }
@@ -108,8 +138,9 @@ 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 $mime = maildir_file_load("$dir/$fn") or next;
-                       if ($filter) {
+                       my $mime = maildir_path_load("$dir/$fn") or next;
+
+                       if (my $filter = $self->filter($im)) {
                                my $ret = $filter->scrub($mime) or return;
                                return if $ret == REJECT();
                                $mime = $ret;
@@ -225,4 +256,8 @@ sub umask_prepare {
        $self->{umask} = $umask;
 }
 
+sub cleanup ($) {
+       delete @{$_[0]}{qw(over mm git search)};
+}
+
 1;