X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FInboxWritable.pm;h=982ad6e59d6afc43c265c0b4e454878985238094;hb=af0b0fb7a454470a32c452119d0392e0dedb3fe1;hp=5b2aeed34a1647fbf408800f7e34e12f87f47661;hpb=227a1d886672767e37cc86a3432952c14eb8a143;p=public-inbox.git

diff --git a/lib/PublicInbox/InboxWritable.pm b/lib/PublicInbox/InboxWritable.pm
index 5b2aeed3..982ad6e5 100644
--- a/lib/PublicInbox/InboxWritable.pm
+++ b/lib/PublicInbox/InboxWritable.pm
@@ -1,13 +1,15 @@
-# Copyright (C) 2018-2019 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 qw(REJECT);
+use Errno qw(ENOENT);
+our @EXPORT_OK = qw(eml_from_path warn_ignore_cb);
 
 use constant {
 	PERM_UMASK => 0,
@@ -19,6 +21,7 @@ use constant {
 
 sub new {
 	my ($class, $ibx, $creat_opt) = @_;
+	return $ibx if ref($ibx) eq $class;
 	my $self = bless $ibx, $class;
 
 	# TODO: maybe stop supporting this
@@ -36,12 +39,33 @@ sub assert_usable_dir {
 	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 $mm = PublicInbox::Msgmap->new($self->{inboxdir}, 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, $skip_artnum) = @_;
-	# TODO: honor skip_artnum
 	if ($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);
@@ -56,7 +80,7 @@ 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);
@@ -78,7 +102,7 @@ sub filter {
 			$im->done;
 		}
 
-		my @args = (-inbox => $self);
+		my @args = (ibx => $self);
 		# basic line splitting, only
 		# Perhaps we can have proper quote splitting one day...
 		($f, @args) = split(/\s+/, $f) if $f =~ /\s+/;
@@ -110,19 +134,14 @@ sub is_maildir_path ($) {
 	(is_maildir_basename($p[-1]) && -f $path) ? 1 : 0;
 }
 
-sub maildir_path_load ($) {
+sub eml_from_path ($) {
 	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;
+		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;
 	}
 }
 
@@ -137,7 +156,7 @@ 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 $mime = eml_from_path("$dir/$fn") or next;
 
 			if (my $filter = $self->filter($im)) {
 				my $ret = $filter->scrub($mime) or return;
@@ -156,12 +175,12 @@ 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();
@@ -239,9 +258,9 @@ 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 $err;
@@ -251,12 +270,40 @@ sub with_umask {
 sub umask_prepare {
 	my ($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)};
 }
 
+# warnings to ignore when handling spam mailboxes and maybe other places
+sub warn_ignore {
+	my $s = "@_";
+	# Email::Address::XS warnings
+	$s =~ /^Argument contains empty address at /
+	|| $s =~ /^Element at index [0-9]+ contains /
+	# PublicInbox::MsgTime
+	|| $s =~ /^bogus TZ offset: .+?, ignoring and assuming \+0000/
+	|| $s =~ /^bad Date: .+? in /
+	# Encode::Unicode::UTF7
+	|| $s =~ /^Bad UTF7 data escape at /
+}
+
+# this expects to be RHS in this assignment: "local $SIG{__WARN__} = ..."
+sub warn_ignore_cb {
+	my $cb = $SIG{__WARN__} // \&CORE::warn;
+	sub {
+		return if warn_ignore(@_);
+		$cb->(@_);
+	}
+}
+
+# v2+ only, XXX: maybe we can just rely on ->max_git_epoch and remove
+sub git_dir_latest {
+	my ($self, $max) = @_;
+	defined($$max = $self->max_git_epoch) ?
+		"$self->{inboxdir}/git/$$max.git" : undef;
+}
+
 1;