X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FInboxWritable.pm;h=4980904541af7f245c09787d6bea59f8082d64c6;hb=e3b57fe9f68e80fc85cff46ccec9246b670f1312;hp=c54be046f9557dcc5eb92312f9c6e3bf32707849;hpb=8722adec7acac538c1cb92de6d53002a4e4e33b8;p=public-inbox.git diff --git a/lib/PublicInbox/InboxWritable.pm b/lib/PublicInbox/InboxWritable.pm index c54be046..49809045 100644 --- a/lib/PublicInbox/InboxWritable.pm +++ b/lib/PublicInbox/InboxWritable.pm @@ -4,10 +4,12 @@ # 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, @@ -37,12 +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; + if (defined $skip_artnum) { + my $mm = PublicInbox::Msgmap->new($self->{inboxdir}, 1); + $mm->{dbh}->begin_work; + $mm->skip_artnum($skip_artnum); + $mm->{dbh}->commit; + } + $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->umask_prepare; + $self->with_umask(\&_init_v1, $self, $skip_artnum); } else { my $v2w = importer($self); $v2w->init_inbox($shards, $skip_epoch, $skip_artnum); @@ -79,7 +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 $f =~ /\s+/; @@ -111,19 +134,14 @@ sub is_maildir_path ($) { (is_maildir_basename($p[-1]) && -f $path) ? 1 : 0; } -sub mime_from_path ($) { +sub eml_from_path ($) { my ($path) = @_; if (open my $fh, '<', $path) { - local $/; - my $str = <$fh>; - $str or return; - return PublicInbox::Eml->new(\$str); - } elsif ($!{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; } } @@ -138,7 +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 $mime = mime_from_path("$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; @@ -240,9 +258,9 @@ sub _umask_for { } sub with_umask { - my ($self, $cb) = @_; + my ($self, $cb, @arg) = @_; my $old = umask $self->{umask}; - my $rv = eval { $cb->() }; + my $rv = eval { $cb->(@arg) }; my $err = $@; umask $old; die $err if $err; @@ -260,4 +278,45 @@ sub cleanup ($) { 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 / +} + +# this expects to be RHS in this assignment: "local $SIG{__WARN__} = ..." +sub warn_ignore_cb { + my $cb = $SIG{__WARN__} // sub { print STDERR @_ }; + sub { + return if warn_ignore(@_); + $cb->(@_); + } +} + +# v2+ only +sub git_dir_n { "$_[0]->{inboxdir}/git/$_[1].git" } + +# v2+ only +sub git_dir_latest { + my ($self, $max) = @_; + $$max = -1; + my $pfx = "$self->{inboxdir}/git"; + return unless -d $pfx; + my $latest; + opendir my $dh, $pfx or die "opendir $pfx: $!\n"; + while (defined(my $git_dir = readdir($dh))) { + $git_dir =~ m!\A([0-9]+)\.git\z! or next; + if ($1 > $$max) { + $$max = $1; + $latest = "$pfx/$git_dir"; + } + } + $latest; +} + 1;