* [PATCH 12/36] lei_to_mail: support for non-seekable outputs
2020-12-31 13:51 7% [PATCH 00/36] another round of lei stuff Eric Wong
@ 2020-12-31 13:51 6% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-12-31 13:51 UTC (permalink / raw)
To: meta
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;
^ permalink raw reply related [relevance 6%]
* [PATCH 00/36] another round of lei stuff
@ 2020-12-31 13:51 7% Eric Wong
2020-12-31 13:51 6% ` [PATCH 12/36] lei_to_mail: support for non-seekable outputs Eric Wong
0 siblings, 1 reply; 2+ results
From: Eric Wong @ 2020-12-31 13:51 UTC (permalink / raw)
To: meta
This is against lei branch @ commit
0c8106d44f317175e122744b43407bf067183175 in
https://public-inbox.org/public-inbox.git
Infrastructure stuff for reading + writing local Maildirs and a
bunch of mbox formats are done (including gz/bz2/xz support)
and it's usage should be familiar to mairix(1) users.
Infrastructure for deduplication + augmenting search results
in place and tested.
Going to skip MH and MMDF for now; but IMAP/JMAP might happen
sooner but deduplication needs low-latency.
"extinbox" renamed "external"
Basic infrastructure like PublicInbox::IPC and SharedKV
should've been done and in use ages ago... I look forward to
using them, at least.
Some DS safety fixes since lei will use it in stranger ways
than current.
Bad enough we have messages with duplicate Message-IDs, lei will
need to deal with Unsent/Drafts messages w/o Message-IDs at all!
Eric Wong (36):
import: respect init.defaultBranch
lei_store: use per-machine refname as git HEAD
revert "lei_store: use per-machine refname as git HEAD"
lei_to_mail: initial implementation for writing mbox formats
sharedkv: fork()-friendly key-value store
sharedkv: split out index_values
lei_to_mail: start atomic and compressed mbox writing
mboxreader: new class for reading various mbox formats
lei_to_mail: start --augment, dedupe, bz2 and xz
lei: implement various deduplication strategies
lei_to_mail: lazy-require LeiDedupe
lei_to_mail: support for non-seekable outputs
lei_to_mail: support Maildir, fix+test --augment
ipc: generic IPC dispatch based on Storable
ipc: support Sereal
lei_store: add ->set_eml, ->add_eml can return smsg
lei: rename "extinbox" => "external"
mid: use defined-or with `push' for uniqueness check
mid: hoist out mids_in sub
lei_store: handle messages without Message-ID at all
ipc: use shutdown(2), base atfork* callback
lei_to_mail: unlink mboxes if not augmenting
lei: add --mfolder as an option
spawn: move run_die here from PublicInbox::Import
init: remove embedded UnlinkMe package
t/run.perl: avoid uninitialized var on incomplete test
gcf2client: reap process on DESTROY
lei_to_mail: open FIFOs O_WRONLY so we block
searchidxshard: call DS->Reset at worker start
t/ipc.t: test for references via `die'
use PublicInbox::DS for dwaitpid
syscall: SFD_NONBLOCK can be a constant, again
lei: avoid Spawn package when starting daemon
avoid calling waitpid from children in DESTROY
ds: clobber $in_loop first at reset
on_destroy: support PID owner guard
MANIFEST | 12 +-
lib/PublicInbox/DS.pm | 42 +-
lib/PublicInbox/DSKQXS.pm | 4 +-
lib/PublicInbox/Daemon.pm | 4 +-
lib/PublicInbox/Gcf2Client.pm | 18 +-
lib/PublicInbox/Git.pm | 7 +-
lib/PublicInbox/IPC.pm | 165 ++++++++
lib/PublicInbox/Import.pm | 36 +-
lib/PublicInbox/LEI.pm | 44 +--
lib/PublicInbox/LeiDedupe.pm | 100 +++++
.../{LeiExtinbox.pm => LeiExternal.pm} | 18 +-
lib/PublicInbox/LeiStore.pm | 32 +-
lib/PublicInbox/LeiToMail.pm | 361 ++++++++++++++++++
lib/PublicInbox/LeiXSearch.pm | 2 +-
lib/PublicInbox/Lock.pm | 17 +-
lib/PublicInbox/MID.pm | 15 +-
lib/PublicInbox/MboxReader.pm | 127 ++++++
lib/PublicInbox/OnDestroy.pm | 5 +
lib/PublicInbox/OverIdx.pm | 2 +
lib/PublicInbox/ProcessPipe.pm | 34 +-
lib/PublicInbox/Qspawn.pm | 43 +--
lib/PublicInbox/SearchIdxShard.pm | 1 +
lib/PublicInbox/SharedKV.pm | 148 +++++++
lib/PublicInbox/Sigfd.pm | 4 +-
lib/PublicInbox/Smsg.pm | 6 +-
lib/PublicInbox/Spawn.pm | 9 +-
lib/PublicInbox/Syscall.pm | 4 +-
lib/PublicInbox/TestCommon.pm | 25 +-
lib/PublicInbox/V2Writable.pm | 10 +-
script/lei | 17 +-
script/public-inbox-init | 32 +-
script/public-inbox-watch | 4 +-
t/convert-compact.t | 4 +-
t/index-git-times.t | 3 +-
t/ipc.t | 80 ++++
t/lei.t | 22 +-
t/lei_dedupe.t | 59 +++
t/lei_store.t | 47 ++-
t/lei_to_mail.t | 246 ++++++++++++
t/lei_xsearch.t | 2 +-
t/mbox_reader.t | 75 ++++
t/on_destroy.t | 9 +
t/plack.t | 4 +-
t/run.perl | 3 +-
t/shared_kv.t | 58 +++
t/sigfd.t | 6 +-
46 files changed, 1755 insertions(+), 211 deletions(-)
create mode 100644 lib/PublicInbox/IPC.pm
create mode 100644 lib/PublicInbox/LeiDedupe.pm
rename lib/PublicInbox/{LeiExtinbox.pm => LeiExternal.pm} (75%)
create mode 100644 lib/PublicInbox/LeiToMail.pm
create mode 100644 lib/PublicInbox/MboxReader.pm
create mode 100644 lib/PublicInbox/SharedKV.pm
create mode 100644 t/ipc.t
create mode 100644 t/lei_dedupe.t
create mode 100644 t/lei_to_mail.t
create mode 100644 t/mbox_reader.t
create mode 100644 t/shared_kv.t
^ permalink raw reply [relevance 7%]
Results 1-2 of 2 | reverse | options above
-- pct% links below jump to the message on this page, permalinks otherwise --
2020-12-31 13:51 7% [PATCH 00/36] another round of lei stuff Eric Wong
2020-12-31 13:51 6% ` [PATCH 12/36] lei_to_mail: support for non-seekable outputs Eric Wong
Code repositories for project(s) associated with this public inbox
https://80x24.org/public-inbox.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).