user/dev discussion of public-inbox itself
 help / color / mirror / code / Atom feed
From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH 2/3] lei q: fix warning on remote imports
Date: Sun, 21 Mar 2021 15:50:46 +0600	[thread overview]
Message-ID: <20210321095047.13855-3-e@80x24.org> (raw)
In-Reply-To: <20210321095047.13855-1-e@80x24.org>

This will let us tie keywords from remote externals
to those which only exist in local externals.
---
 lib/PublicInbox/ContentHash.pm | 15 ++++++++++++---
 lib/PublicInbox/LeiDedupe.pm   |  9 ++-------
 lib/PublicInbox/LeiXSearch.pm  |  6 +++++-
 t/lei-q-remote-import.t        |  3 ++-
 4 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/lib/PublicInbox/ContentHash.pm b/lib/PublicInbox/ContentHash.pm
index 4dbe7b50..112b1ea6 100644
--- a/lib/PublicInbox/ContentHash.pm
+++ b/lib/PublicInbox/ContentHash.pm
@@ -8,9 +8,9 @@
 # See L<public-inbox-v2-format(5)> manpage for more details.
 package PublicInbox::ContentHash;
 use strict;
-use warnings;
-use base qw/Exporter/;
-our @EXPORT_OK = qw/content_hash content_digest/;
+use v5.10.1;
+use parent qw(Exporter);
+our @EXPORT_OK = qw(content_hash content_digest git_sha);
 use PublicInbox::MID qw(mids references);
 use PublicInbox::MsgIter;
 
@@ -94,4 +94,13 @@ sub content_hash ($) {
 	content_digest($_[0])->digest;
 }
 
+sub git_sha ($$) {
+	my ($n, $eml) = @_;
+	my $dig = Digest::SHA->new($n);
+	my $buf = $eml->as_string;
+	$dig->add('blob '.length($buf)."\0");
+	$dig->add($buf);
+	$dig;
+}
+
 1;
diff --git a/lib/PublicInbox/LeiDedupe.pm b/lib/PublicInbox/LeiDedupe.pm
index 5fec9384..a62b3a7c 100644
--- a/lib/PublicInbox/LeiDedupe.pm
+++ b/lib/PublicInbox/LeiDedupe.pm
@@ -3,7 +3,7 @@
 package PublicInbox::LeiDedupe;
 use strict;
 use v5.10.1;
-use PublicInbox::ContentHash qw(content_hash);
+use PublicInbox::ContentHash qw(content_hash git_sha);
 use Digest::SHA ();
 
 # n.b. mutt sets most of these headers not sure about Bytes
@@ -18,12 +18,7 @@ sub _regen_oid ($) {
 		push @stash, [ $k, \@v ];
 		$eml->header_set($k); # restore below
 	}
-	my $dig = Digest::SHA->new(1); # XXX SHA256 later
-	my $buf = $eml->as_string;
-	$dig->add('blob '.length($buf)."\0");
-	$dig->add($buf);
-	undef $buf;
-
+	my $dig = git_sha(1, $eml);
 	for my $kv (@stash) { # restore stashed headers
 		my ($k, @v) = @$kv;
 		$eml->header_set($k, @v);
diff --git a/lib/PublicInbox/LeiXSearch.pm b/lib/PublicInbox/LeiXSearch.pm
index 17171a7f..b6aaf3e1 100644
--- a/lib/PublicInbox/LeiXSearch.pm
+++ b/lib/PublicInbox/LeiXSearch.pm
@@ -18,6 +18,7 @@ use PublicInbox::MID qw(mids);
 use PublicInbox::Smsg;
 use PublicInbox::Eml;
 use Fcntl qw(SEEK_SET F_SETFL O_APPEND O_RDWR);
+use PublicInbox::ContentHash qw(git_sha);
 
 sub new {
 	my ($class) = @_;
@@ -207,10 +208,13 @@ sub query_mset { # non-parallel for non-"--threads" users
 
 sub each_remote_eml { # callback for MboxReader->mboxrd
 	my ($eml, $self, $lei, $each_smsg) = @_;
-	if ($self->{import_sto} && !$lei->{ale}->xoids_for($eml, 1)) {
+	my $xoids = $lei->{ale}->xoids_for($eml, 1);
+	if ($self->{import_sto} && !$xoids) {
 		$self->{import_sto}->ipc_do('add_eml', $eml);
 	}
 	my $smsg = bless {}, 'PublicInbox::Smsg';
+	$smsg->{blob} = $xoids ? (keys(%$xoids))[0]
+				: git_sha(1, $eml)->hexdigest;
 	$smsg->populate($eml);
 	$smsg->parse_references($eml, mids($eml));
 	$smsg->{$_} //= '' for qw(from to cc ds subject references mid);
diff --git a/t/lei-q-remote-import.t b/t/lei-q-remote-import.t
index 25e461ac..93828a24 100644
--- a/t/lei-q-remote-import.t
+++ b/t/lei-q-remote-import.t
@@ -65,8 +65,9 @@ test_lei({ tmpdir => $tmpdir }, sub {
 		$im->add(eml_load('t/utf8.eml')) or BAIL_OUT '->add';
 	};
 	lei_ok(qw(add-external -q), $ibx->{inboxdir});
-	lei_ok(qw(q -o), "mboxrd:$o", '--only', $url,
+	lei_ok(qw(q -q -o), "mboxrd:$o", '--only', $url,
 		'm:testmessage@example.com');
+	is($lei_err, '', 'no warnings or errors');
 	ok(-s $o, 'got result from remote external');
 	my $exp = eml_load('t/utf8.eml');
 	is_deeply($slurp_emls->($o), [$exp], 'got expected result');

  parent reply	other threads:[~2021-03-21  9:50 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-21  9:50 [PATCH 0/3] lei import fix, other fixes Eric Wong
2021-03-21  9:50 ` [PATCH 1/3] lei import: vivify external-only messages Eric Wong
2021-03-21  9:50 ` Eric Wong [this message]
2021-03-21  9:50 ` [PATCH 3/3] lei: fix some warnings in tests Eric Wong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://public-inbox.org/README

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210321095047.13855-3-e@80x24.org \
    --to=e@80x24.org \
    --cc=meta@public-inbox.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).