From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-Status: No, score=-4.0 required=3.0 tests=ALL_TRUSTED,BAYES_00 shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from localhost (dcvr.yhbt.net [127.0.0.1]) by dcvr.yhbt.net (Postfix) with ESMTP id CAFB81FF9C for ; Thu, 31 Dec 2020 13:51:55 +0000 (UTC) From: Eric Wong To: meta@public-inbox.org Subject: [PATCH 12/36] lei_to_mail: support for non-seekable outputs Date: Thu, 31 Dec 2020 13:51:30 +0000 Message-Id: <20201231135154.6070-13-e@80x24.org> In-Reply-To: <20201231135154.6070-1-e@80x24.org> References: <20201231135154.6070-1-e@80x24.org> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit List-Id: Users may wish to pipe output to "git am", "spamc", or similar, so we need to support those cases and not bail out on lseek(2) or ftruncate(2) failures. --- lib/PublicInbox/LeiToMail.pm | 24 ++++++++++++++++-------- t/lei_to_mail.t | 29 ++++++++++++++++++++++++++++- 2 files changed, 44 insertions(+), 9 deletions(-) diff --git a/lib/PublicInbox/LeiToMail.pm b/lib/PublicInbox/LeiToMail.pm index 1c0f3108..4476d84c 100644 --- a/lib/PublicInbox/LeiToMail.pm +++ b/lib/PublicInbox/LeiToMail.pm @@ -12,7 +12,7 @@ use PublicInbox::Spawn qw(which spawn popen_rd); use PublicInbox::LeiDedupe; use Symbol qw(gensym); use IO::Handle; # ->autoflush -use Fcntl qw(SEEK_SET); +use Fcntl qw(SEEK_SET SEEK_END); my %kw2char = ( # Maildir characters draft => 'D', @@ -236,26 +236,34 @@ sub _mbox_write_cb ($$$$) { my ($cls, $mbox, $dst, $lei) = @_; my $m = "eml2$mbox"; my $eml2mbox = $cls->can($m) or die "$cls->$m missing"; - my ($out, $pipe_lk); - open $out, '+>>', $dst or die "open $dst: $!"; - # Perl does SEEK_END even with O_APPEND :< - seek($out, 0, SEEK_SET) or die "seek $dst: $!"; + my ($out, $pipe_lk, $seekable); + # XXX should we support /dev/stdout.gz ? + if ($dst eq '/dev/stdout') { + $out = $lei->{1}; + } else { # TODO: mbox locking + open $out, '+>>', $dst or die "open $dst: $!"; + # Perl does SEEK_END even with O_APPEND :< + $seekable = seek($out, 0, SEEK_SET); + die "seek $dst: $!\n" if !$seekable && !$!{ESPIPE}; + } my $jobs = $lei->{opt}->{jobs} // 0; my $atomic = $jobs > 1; my $dedupe = $lei->{dedupe} = PublicInbox::LeiDedupe->new($lei); state $zsfx_allow = join('|', keys %zsfx2cmd); my ($zsfx) = ($dst =~ /\.($zsfx_allow)\z/); if ($lei->{opt}->{augment}) { - if (-s $out && $dedupe->prepare_dedupe) { + if ($seekable && -s $out && $dedupe->prepare_dedupe) { my $rd = $zsfx ? decompress_src($out, $zsfx, $lei) : dup_src($out); PublicInbox::MboxReader->$mbox($rd, \&_augment, $lei); + } elsif ($seekable && !$atomic) { + seek($out, 0, SEEK_END) or die "seek: $!"; } $dedupe->pause_dedupe if $jobs; # are we forking? - } else { + } elsif ($seekable) { truncate($out, 0) or die "truncate $dst: $!"; - $dedupe->prepare_dedupe if !$jobs; } + $dedupe->prepare_dedupe if !$jobs; ($out, $pipe_lk) = compress_dst($out, $zsfx, $lei) if $zsfx; sub { my ($buf, $oid, $kw) = @_; diff --git a/t/lei_to_mail.t b/t/lei_to_mail.t index 5be4e285..f3cc71ad 100644 --- a/t/lei_to_mail.t +++ b/t/lei_to_mail.t @@ -6,6 +6,7 @@ use v5.10.1; use Test::More; use PublicInbox::TestCommon; use PublicInbox::Eml; +use Fcntl qw(SEEK_SET); require_mods(qw(DBD::SQLite)); use_ok 'PublicInbox::LeiToMail'; my $from = "Content-Length: 10\nSubject: x\n\nFrom hell\n"; @@ -120,15 +121,41 @@ for my $zsfx (qw(gz bz2 xz)) { # XXX should we support zst, zz, lzo, lzma? } unlink $fn or BAIL_OUT $!; +require PublicInbox::MboxReader; if ('default deduplication uses content_hash') { my $wcb = PublicInbox::LeiToMail->write_cb("mboxo:$fn", $lei); $wcb->(\(my $x = $buf), 'deadbeef', []) for (1..2); undef $wcb; # undef to commit changes my $cmp = ''; open my $fh, '<', $fn or BAIL_OUT $!; - require PublicInbox::MboxReader; PublicInbox::MboxReader->mboxo($fh, sub { $cmp .= shift->as_string }); is($cmp, $buf, 'only one message written'); } +{ # stdout support + open my $tmp, '+>', undef or BAIL_OUT $!; + local $lei->{1} = $tmp; + my $wcb = PublicInbox::LeiToMail->write_cb("mboxrd:/dev/stdout", $lei); + $wcb->(\(my $x = $buf), 'deadbeef', []); + undef $wcb; # commit + seek($tmp, 0, SEEK_SET) or BAIL_OUT $!; + my $cmp = ''; + PublicInbox::MboxReader->mboxrd($tmp, sub { $cmp .= shift->as_string }); + is($cmp, $buf, 'message written to stdout'); +} + +SKIP: { # FIFO support + use PublicInbox::Spawn qw(popen_rd which); + use POSIX qw(mkfifo); + my $fn = "$tmpdir/fifo"; + mkfifo($fn, 0600) or skip("mkfifo not supported: $!", 1); + my $cat = popen_rd([which('cat'), $fn]); + my $wcb = PublicInbox::LeiToMail->write_cb("mboxo:$fn", $lei); + $wcb->(\(my $x = $buf), 'deadbeef', []); + undef $wcb; # commit + my $cmp = ''; + PublicInbox::MboxReader->mboxo($cat, sub { $cmp .= shift->as_string }); + is($cmp, $buf, 'message written to FIFO'); +} + done_testing;