X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FInboxWritable.pm;h=17dfbe18500a6dfa00e87f50209baec4126f61c3;hb=23af251dd607c4e75ab1e68063f2c885c48cc035;hp=5c11a36c27631e4b82bed1de1dabe222e41ef484;hpb=c4aa293b2320feb805c5afeaa373f608e5bc8618;p=public-inbox.git

diff --git a/lib/PublicInbox/InboxWritable.pm b/lib/PublicInbox/InboxWritable.pm
index 5c11a36c..17dfbe18 100644
--- a/lib/PublicInbox/InboxWritable.pm
+++ b/lib/PublicInbox/InboxWritable.pm
@@ -1,14 +1,16 @@
-# Copyright (C) 2018 all contributors <meta@public-inbox.org>
+# Copyright (C) 2018-2021 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
 package PublicInbox::InboxWritable;
 use strict;
-use warnings;
-use base qw(PublicInbox::Inbox);
+use v5.10.1;
+use parent qw(PublicInbox::Inbox Exporter);
 use PublicInbox::Import;
-use PublicInbox::Filter::Base;
-*REJECT = *PublicInbox::Filter::Base::REJECT;
+use PublicInbox::Filter::Base qw(REJECT);
+use Errno qw(ENOENT);
+our @EXPORT_OK = qw(eml_from_path);
+use Fcntl qw(O_RDONLY O_NONBLOCK);
 
 use constant {
 	PERM_UMASK => 0,
@@ -19,36 +21,89 @@ 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 $self->{name}\n";
+}
+
+sub _init_v1 {
+	my ($self, $skip_artnum) = @_;
+	if (defined($self->{indexlevel}) || defined($skip_artnum)) {
+		require PublicInbox::SearchIdx;
+		require PublicInbox::Msgmap;
+		my $sidx = PublicInbox::SearchIdx->new($self, 1); # just create
+		$sidx->begin_txn_lazy;
+		my $mm = PublicInbox::Msgmap->new_file($self, 1);
+		if (defined $skip_artnum) {
+			$mm->{dbh}->begin_work;
+			$mm->skip_artnum($skip_artnum);
+			$mm->{dbh}->commit;
+		}
+		undef $mm; # ->created_at set
+		$sidx->commit_txn_lazy;
+	} else {
+		open my $fh, '>>', "$self->{inboxdir}/ssoma.lock" or
+			die "$self->{inboxdir}/ssoma.lock: $!\n";
+	}
+}
+
+sub init_inbox {
+	my ($self, $shards, $skip_epoch, $skip_artnum) = @_;
+	if ($self->version == 1) {
+		my $dir = assert_usable_dir($self);
+		PublicInbox::Import::init_bare($dir);
+		$self->with_umask(\&_init_v1, $self, $skip_artnum);
+	} 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 {
-			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 if defined $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 =~ /::/) {
-		my @args = (-inbox => $self);
+		# v2 keeps msgmap open, which causes conflicts for filters
+		# such as PublicInbox::Filter::RubyLang which overload msgmap
+		# for a predictable serial number.
+		if ($im && $self->version >= 2 && $self->{altid}) {
+			$im->done;
+		}
+
+		my @args = (ibx => $self);
 		# basic line splitting, only
 		# Perhaps we can have proper quote splitting one day...
 		($f, @args) = split(/\s+/, $f) if $f =~ /\s+/;
@@ -64,110 +119,65 @@ sub filter {
 	undef;
 }
 
-sub is_maildir_basename ($) {
-	my ($bn) = @_;
-	return 0 if $bn !~ /\A[a-zA-Z0-9][\-\w:,=\.]+\z/;
-	if ($bn =~ /:2,([A-Z]+)\z/i) {
-		my $flags = $1;
-		return 0 if $flags =~ /[DT]/; # no [D]rafts or [T]rashed mail
-	}
-	1;
-}
-
-sub is_maildir_path ($) {
+sub eml_from_path ($) {
 	my ($path) = @_;
-	my @p = split(m!/+!, $path);
-	(is_maildir_basename($p[-1]) && -f $path) ? 1 : 0;
+	if (sysopen(my $fh, $path, O_RDONLY|O_NONBLOCK)) {
+		return unless -f $fh; # no FIFOs or directories
+		my $str = do { local $/; <$fh> } or return;
+		PublicInbox::Eml->new(\$str);
+	} else { # ENOENT is common with Maildir
+		warn "failed to open $path: $!\n" if $! != ENOENT;
+		undef;
+	}
 }
 
-sub maildir_path_load ($) {
-	my ($path) = @_;
-	if (open my $fh, '<', $path) {
-		local $/;
-		my $str = <$fh>;
-		$str or return;
-		return PublicInbox::MIME->new(\$str);
-	} elsif ($!{ENOENT}) {
-		# common with Maildir
-		return;
-	} else {
-		warn "failed to open $path: $!\n";
-		return;
+sub _each_maildir_eml {
+	my ($fn, $kw, $eml, $im, $self) = @_;
+	return if grep(/\Adraft\z/, @$kw);
+	if ($self && (my $filter = $self->filter($im))) {
+		my $ret = $filter->scrub($eml) or return;
+		return if $ret == REJECT();
+		$eml = $ret;
 	}
+	$im->add($eml);
 }
 
+# XXX does anybody use this?
 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";
 	}
-	foreach my $sub (qw(cur new)) {
-		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 $ret = $filter->scrub($mime) or return;
-				return if $ret == REJECT();
-				$mime = $ret;
-			}
-			$im->add($mime);
-		}
-	}
+	my $im = $self->importer(1);
+	my @self = $self->filter($im) ? ($self) : ();
+	require PublicInbox::MdirReader;
+	PublicInbox::MdirReader->new->maildir_each_eml($dir,
+					\&_each_maildir_eml, $im, @self);
 	$im->done;
 }
 
-# asctime: From example@example.com Fri Jun 23 02:56:55 2000
-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') {
-		$$msg =~ s/^>(>*From )/$1/sm;
-	} elsif ($variant eq 'mboxo') {
-		$$msg =~ s/^>From /From /sm;
-	}
+sub _mbox_eml_cb { # MboxReader->mbox* callback
+	my ($eml, $im, $filter) = @_;
 	if ($filter) {
-		my $ret = $filter->scrub($mime) or return;
+		my $ret = $filter->scrub($eml) or return;
 		return if $ret == REJECT();
-		$mime = $ret;
+		$eml = $ret;
 	}
-	$im->add($mime)
+	$im->add($eml);
 }
 
 sub import_mbox {
 	my ($self, $fh, $variant) = @_;
-	if ($variant !~ /\A(?:mboxrd|mboxo)\z/) {
-		die "variant must be 'mboxrd' or 'mboxo'\n";
-	}
+	require PublicInbox::MboxReader;
+	my $cb = PublicInbox::MboxReader->reads($variant) or
+		die "$variant not supported\n";
 	my $im = $self->importer(1);
-	my $prev = undef;
-	my $msg = '';
-	my $filter = $self->filter;
-	while (defined(my $l = <$fh>)) {
-		if ($l =~ /$from_strict/o) {
-			if (!defined($prev) || $prev =~ /^\r?$/) {
-				mb_add($im, $variant, $filter, \$msg) if $msg;
-				$msg = '';
-				$prev = $l;
-				next;
-			}
-			warn "W[$.] $l\n";
-		}
-		$prev = $l;
-		$msg .= $l;
-	}
-	mb_add($im, $variant, $filter, \$msg) if $msg;
+	$cb->(undef, $fh, \&_mbox_eml_cb, $im, $self->filter);
 	$im->done;
 }
 
 sub _read_git_config_perm {
 	my ($self) = @_;
-	my @cmd = qw(config);
 	chomp(my $perm = $self->git->qx('config', 'core.sharedRepository'));
 	$perm;
 }
@@ -175,7 +185,7 @@ sub _read_git_config_perm {
 sub _git_config_perm {
 	my $self = shift;
 	my $perm = scalar @_ ? $_[0] : _read_git_config_perm($self);
-	return PERM_GROUP if (!defined($perm) || $perm eq '');
+	return PERM_UMASK if (!defined($perm) || $perm eq '');
 	return PERM_UMASK if ($perm eq 'umask');
 	return PERM_GROUP if ($perm eq 'group');
 	if ($perm =~ /\A(?:all|world|everybody)\z/) {
@@ -209,9 +219,9 @@ sub _umask_for {
 }
 
 sub with_umask {
-	my ($self, $cb) = @_;
-	my $old = umask $self->{umask};
-	my $rv = eval { $cb->() };
+	my ($self, $cb, @arg) = @_;
+	my $old = umask($self->{umask} //= umask_prepare($self));
+	my $rv = eval { $cb->(@arg) };
 	my $err = $@;
 	umask $old;
 	die $err if $err;
@@ -221,8 +231,18 @@ sub with_umask {
 sub umask_prepare {
 	my ($self) = @_;
 	my $perm = _git_config_perm($self);
-	my $umask = _umask_for($perm);
-	$self->{umask} = $umask;
+	_umask_for($perm);
+}
+
+sub cleanup ($) {
+	delete @{$_[0]}{qw(over mm git search)};
+}
+
+# v2+ only, XXX: maybe we can just rely on ->max_git_epoch and remove
+sub git_dir_latest {
+	my ($self, $max) = @_;
+	defined($$max = $self->max_git_epoch) ?
+		"$self->{inboxdir}/git/$$max.git" : undef;
 }
 
 1;