* [PATCH 09/36] lei_to_mail: start --augment, dedupe, bz2 and xz
2020-12-31 13:51 7% [PATCH 00/36] another round of lei stuff Eric Wong
@ 2020-12-31 13:51 4% ` Eric Wong
0 siblings, 0 replies; 2+ results
From: Eric Wong @ 2020-12-31 13:51 UTC (permalink / raw)
To: meta
--augment will match the mairix(1) option of the same
name to augment existing search results. We'll need
to implement deduplication for a better user experience.
mutt ships with compressed mbox support for bz2 and xz,
at least, so we'll support those out-of-the-box.
---
lib/PublicInbox/LeiToMail.pm | 140 ++++++++++++++++++++++++++--------
lib/PublicInbox/Lock.pm | 7 ++
lib/PublicInbox/MboxReader.pm | 3 +
t/lei_to_mail.t | 47 ++++++++----
4 files changed, 150 insertions(+), 47 deletions(-)
diff --git a/lib/PublicInbox/LeiToMail.pm b/lib/PublicInbox/LeiToMail.pm
index ebb50c50..294291b2 100644
--- a/lib/PublicInbox/LeiToMail.pm
+++ b/lib/PublicInbox/LeiToMail.pm
@@ -8,10 +8,12 @@ use v5.10.1;
use PublicInbox::Eml;
use PublicInbox::Lock;
use PublicInbox::ProcessPipe;
-use PublicInbox::Spawn qw(which spawn);
+use PublicInbox::SharedKV;
+use PublicInbox::Spawn qw(which spawn popen_rd);
+use PublicInbox::ContentHash qw(content_hash);
use Symbol qw(gensym);
-use File::Temp ();
use IO::Handle; # ->autoflush
+use Fcntl qw(SEEK_SET);
my %kw2char = ( # Maildir characters
draft => 'D',
@@ -150,51 +152,123 @@ sub reap_compress { # dwaitpid callback
$lei->fail("@$cmd failed", $? >> 8);
}
-sub compress_dst {
- my ($out, $sfx, $lei) = @_;
- my $cmd = [];
- if ($sfx eq 'gz') {
- $cmd->[0] = which($lei->{env}->{GZIP} // 'pigz') //
- which('gzip') //
- die "pigz or gzip missing for $sfx\n";
- # TODO: use IO::Compress::Gzip
- push @$cmd, '-c'; # stdout
- push @$cmd, '--rsyncable' if $lei->{opt}->{rsyncable};
- } else {
- die "TODO $sfx"
+# all of these support -c for stdout and -d for decompression,
+# mutt is commonly distributed with hooks for gz, bz2 and xz, at least
+# { foo => '' } means "--foo" is passed to the command-line,
+# otherwise { foo => '--bar' } passes "--bar"
+our %zsfx2cmd = (
+ gz => [ qw(GZIP pigz gzip), {
+ rsyncable => '', threads => '-p' } ],
+ bz2 => [ 'bzip2', {} ],
+ xz => [ 'xz', { threads => '-T' } ],
+ # XXX does anybody care for these? I prefer zstd on entire FSes,
+ # so it's probably not necessary on a per-file basis
+ # zst => [ 'zstd', { -default => [ qw(-q) ], # it's noisy by default
+ # rsyncable => '', threads => '-T' } ],
+ # zz => [ 'pigz', { -default => [ '--zlib' ],
+ # rsyncable => '', threads => '-p' }],
+ # lzo => [ 'lzop', {} ],
+ # lzma => [ 'lzma', {} ],
+);
+
+sub zsfx2cmd ($$$) {
+ my ($zsfx, $decompress, $lei) = @_;
+ my $x = $zsfx2cmd{$zsfx} // die "no support for suffix=.$zsfx";
+ my @info = @$x;
+ my $cmd_opt = pop @info;
+ my @cmd = (undef, $decompress ? qw(-dc) : qw(-c));
+ for my $exe (@info) {
+ # I think respecting client's ENV{GZIP} is OK, not sure
+ # about ENV overrides for other, less-common compressors
+ if ($exe eq uc($exe)) {
+ $exe = $lei->{env}->{$exe} or next;
+ }
+ $cmd[0] = which($exe) and last;
+ }
+ $cmd[0] // die join(' or ', @info)." missing for .$zsfx";
+ # push @cmd, @{$cmd_opt->{-default}} if $cmd_opt->{-default};
+ for my $bool (qw(rsyncable)) {
+ my $switch = $cmd_opt->{rsyncable} // next;
+ push @cmd, '--'.($switch || $bool);
+ }
+ for my $key (qw(threads)) { # support compression level?
+ my $switch = $cmd_opt->{$key} // next;
+ my $val = $lei->{opt}->{$key} // next;
+ push @cmd, $switch, $val;
}
+ \@cmd;
+}
+
+sub compress_dst {
+ my ($out, $zsfx, $lei) = @_;
+ my $cmd = zsfx2cmd($zsfx, undef, $lei);
pipe(my ($r, $w)) or die "pipe: $!";
my $rdr = { 0 => $r, 1 => $out, 2 => $lei->{2} };
my $pid = spawn($cmd, $lei->{env}, $rdr);
$lei->{"pid.$pid"} = $cmd;
my $pp = gensym;
tie *$pp, 'PublicInbox::ProcessPipe', $pid, $w, \&reap_compress, $lei;
- my $tmp = File::Temp->new("$sfx.lock-XXXXXX", TMPDIR => 1);
- my $pipe_lk = ($lei->{opt}->{jobs} // 0) > 1 ? bless({
- lock_path => $tmp->filename,
- tmp => $tmp
- }, 'PublicInbox::Lock') : undef;
+ my $pipe_lk = ($lei->{opt}->{jobs} // 0) > 1 ?
+ PublicInbox::Lock->new_tmp($zsfx) : undef;
($pp, $pipe_lk);
}
-sub write_cb {
- my ($cls, $dst, $lei) = @_;
- if ($dst =~ s!\A(mbox(?:rd|cl|cl2|o))?:!!) {
- my $m = "eml2$1";
- my $eml2mbox = $cls->can($m) or die "$cls->$m missing";
- my ($out, $pipe_lk);
- open $out, '>>', $dst or die "open $dst: $!";
- my $atomic = !!(($lei->{opt}->{jobs} // 0) > 1);
- if ($dst =~ /\.(gz|bz2|xz)\z/) {
- ($out, $pipe_lk) = compress_dst($out, $1, $lei);
- }
- sub {
- my ($buf, $oid, $kw) = @_;
- $buf = $eml2mbox->(PublicInbox::Eml->new($buf), $kw);
+sub decompress_src ($$$) {
+ my ($in, $zsfx, $lei) = @_;
+ my $cmd = zsfx2cmd($zsfx, 1, $lei);
+ my $rdr = { 0 => $in, 2 => $lei->{2} };
+ popen_rd($cmd, $lei->{env}, $rdr);
+}
+
+sub dup_src ($) {
+ my ($in) = @_;
+ open my $dup, '+>>&', $in or die "dup: $!";
+ $dup;
+}
+
+# --augment existing output destination, without duplicating anything
+sub _augment { # MboxReader eml_cb
+ my ($eml, $lei) = @_;
+ $lei->{skv}->set_maybe(content_hash($eml), '');
+}
+
+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 $atomic = !!(($lei->{opt}->{jobs} // 0) > 1);
+ $lei->{skv} = PublicInbox::SharedKV->new;
+ $lei->{skv}->dbh;
+ state $zsfx_allow = join('|', keys %zsfx2cmd);
+ my ($zsfx) = ($dst =~ /\.($zsfx_allow)\z/);
+ if ($lei->{opt}->{augment}) {
+ my $rd = $zsfx ? decompress_src($out, $zsfx, $lei) :
+ dup_src($out);
+ PublicInbox::MboxReader->$mbox($rd, \&_augment, $lei);
+ } else {
+ truncate($out, 0) or die "truncate $dst: $!";
+ }
+ ($out, $pipe_lk) = compress_dst($out, $zsfx, $lei) if $zsfx;
+ sub {
+ my ($buf, $oid, $kw) = @_;
+ my $eml = PublicInbox::Eml->new($buf);
+ if ($lei->{skv}->set_maybe(content_hash($eml), '')) {
+ $buf = $eml2mbox->($eml, $kw);
my $lock = $pipe_lk->lock_for_scope if $pipe_lk;
write_in_full($out, $buf, $atomic);
}
}
}
+sub write_cb { # returns a callback for git_to_mail
+ my ($cls, $dst, $lei) = @_;
+ if ($dst =~ s!\A(mbox(?:rd|cl|cl2|o))?:!!) {
+ _mbox_write_cb($cls, $1, $dst, $lei);
+ }
+}
+
1;
diff --git a/lib/PublicInbox/Lock.pm b/lib/PublicInbox/Lock.pm
index 7fd17745..f6eaa5ce 100644
--- a/lib/PublicInbox/Lock.pm
+++ b/lib/PublicInbox/Lock.pm
@@ -8,6 +8,7 @@ use v5.10.1;
use Fcntl qw(:flock :DEFAULT);
use Carp qw(croak);
use PublicInbox::OnDestroy;
+use File::Temp ();
# we only acquire the flock if creating or reindexing;
# PublicInbox::Import already has the lock on its own.
@@ -40,4 +41,10 @@ sub lock_for_scope {
PublicInbox::OnDestroy->new(\&lock_release, $self);
}
+sub new_tmp {
+ my ($cls, $ident) = @_;
+ my $tmp = File::Temp->new("$ident.lock-XXXXXX", TMPDIR => 1);
+ bless { lock_path => $tmp->filename, tmp => $tmp }, $cls;
+}
+
1;
diff --git a/lib/PublicInbox/MboxReader.pm b/lib/PublicInbox/MboxReader.pm
index e1944aaf..ac0c0f52 100644
--- a/lib/PublicInbox/MboxReader.pm
+++ b/lib/PublicInbox/MboxReader.pm
@@ -5,6 +5,7 @@
package PublicInbox::MboxReader;
use strict;
use v5.10.1;
+use PublicInbox::DS (); # localize $in_loop for error detection :<
use Data::Dumper;
$Data::Dumper::Useqq = 1; # should've been the default, for bad data
@@ -13,6 +14,7 @@ my $from_strict =
sub _mbox_from {
my ($mbfh, $from_re, $eml_cb, @arg) = @_;
+ local $PublicInbox::DS::in_loop; # disable dwaitpid
my $buf = '';
my @raw;
while (defined(my $r = read($mbfh, $buf, 65536, length($buf)))) {
@@ -73,6 +75,7 @@ sub _extract_hdr {
sub _mbox_cl ($$$;@) {
my ($mbfh, $uxs_from, $eml_cb, @arg) = @_;
+ local $PublicInbox::DS::in_loop; # disable dwaitpid
my $buf = '';
while (defined(my $r = read($mbfh, $buf, 65536, length($buf)))) {
if ($r == 0) { # detect "curl --fail"
diff --git a/t/lei_to_mail.t b/t/lei_to_mail.t
index 231cf543..e4551e69 100644
--- a/t/lei_to_mail.t
+++ b/t/lei_to_mail.t
@@ -92,21 +92,40 @@ my $orig = do {
is($raw, do { local $/; <$fh> }, 'jobs > 1');
$raw;
};
-SKIP: {
- use PublicInbox::Spawn qw(which);
- my $gzip = which('gzip') or skip 'gzip not found', 1;
- my $wcb = PublicInbox::LeiToMail->write_cb("mboxcl2:$fn.gz", $lei);
- $wcb->(\(my $dup = $buf), 'deadbeef', [ qw(seen) ]);
- undef $wcb;
- my $uncompressed = xqx([$gzip, '-dc', "$fn.gz"]);
- is($uncompressed, $orig, 'gzip works');
+for my $zsfx (qw(gz bz2 xz)) { # XXX should we support zst, zz, lzo, lzma?
+ my $zsfx2cmd = PublicInbox::LeiToMail->can('zsfx2cmd');
+ SKIP: {
+ my $cmd = eval { $zsfx2cmd->($zsfx, 0, $lei) };
+ skip $@, 3 if $@;
+ my $dc_cmd = eval { $zsfx2cmd->($zsfx, 1, $lei) };
+ ok($dc_cmd, "decompressor for .$zsfx");
+ my $f = "$fn.$zsfx";
+ my $dst = "mboxcl2:$f";
+ my $wcb = PublicInbox::LeiToMail->write_cb($dst, $lei);
+ $wcb->(\(my $dup = $buf), 'deadbeef', [ qw(seen) ]);
+ undef $wcb;
+ my $uncompressed = xqx([@$dc_cmd, $f]);
+ is($uncompressed, $orig, "$zsfx works unlocked");
- local $lei->{opt} = { jobs => 2 };
- unlink "$fn.gz" or die "unlink $!";
- $wcb = PublicInbox::LeiToMail->write_cb("mboxcl2:$fn.gz", $lei);
- $wcb->(\(my $dupe = $buf), 'deadbeef', [ qw(seen) ]);
- undef $wcb;
- is(xqx([$gzip, '-dc', "$fn.gz"]), $orig);
+ local $lei->{opt} = { jobs => 2 }; # for atomic writes
+ unlink $f or BAIL_OUT "unlink $!";
+ $wcb = PublicInbox::LeiToMail->write_cb($dst, $lei);
+ $wcb->(\($dup = $buf), 'deadbeef', [ qw(seen) ]);
+ undef $wcb;
+ is(xqx([@$dc_cmd, $f]), $orig, "$zsfx matches with lock");
+ }
+}
+
+unlink $fn or BAIL_OUT $!;
+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');
}
done_testing;
^ permalink raw reply related [relevance 4%]
* [PATCH 00/36] another round of lei stuff
@ 2020-12-31 13:51 7% Eric Wong
2020-12-31 13:51 4% ` [PATCH 09/36] lei_to_mail: start --augment, dedupe, bz2 and xz 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 4% ` [PATCH 09/36] lei_to_mail: start --augment, dedupe, bz2 and xz 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).