From: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
To: meta@public-inbox.org
Cc: "Eric Wong (Contractor, The Linux Foundation)" <e@80x24.org>
Subject: [PATCH 13/14] www: cleanup expensive fallback for legacy URLs
Date: Thu, 29 Mar 2018 10:28:18 +0000 [thread overview]
Message-ID: <20180329102819.15234-14-e@80x24.org> (raw)
In-Reply-To: <20180329102819.15234-1-e@80x24.org>
Back in the day, we compressed long Message-IDs to SHA-1
hexdigests for the URL. This now redirects to a 301 in
the hopes we can remove these checks some day to reduce
overhead.
---
lib/PublicInbox/Inbox.pm | 11 ++++++++---
lib/PublicInbox/WWW.pm | 23 +++++++++--------------
t/plack.t | 18 ++++++++++++++++++
3 files changed, 35 insertions(+), 17 deletions(-)
diff --git a/lib/PublicInbox/Inbox.pm b/lib/PublicInbox/Inbox.pm
index 01aa500..265360d 100644
--- a/lib/PublicInbox/Inbox.pm
+++ b/lib/PublicInbox/Inbox.pm
@@ -293,13 +293,18 @@ sub path_check {
git($self)->check('HEAD:'.$path);
}
+sub mid2num($$) {
+ my ($self, $mid) = @_;
+ my $mm = mm($self) or return;
+ $mm->num_for($mid);
+}
+
sub smsg_by_mid ($$) {
my ($self, $mid) = @_;
my $srch = search($self) or return;
# favor the Message-ID we used for the NNTP article number:
- my $mm = mm($self) or return;
- my $num = $mm->num_for($mid);
- $srch->lookup_article($num);
+ my $num = mid2num($self, $mid);
+ defined $num ? $srch->lookup_article($num) : undef;
}
sub msg_by_mid ($$;$) {
diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 7bd2973..24e24f1 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -169,14 +169,15 @@ sub invalid_inbox_mid {
return $ret if $ret;
$ctx->{mid} = $mid;
- if ($mid =~ /\A[a-f0-9]{40}\z/) {
- # this is horiffically wasteful for legacy URLs:
- if ($mid = mid2blob($ctx)) {
- require Email::Simple;
- use PublicInbox::MID qw/mid_clean/;
- my $s = Email::Simple->new($mid);
- $ctx->{mid} = mid_clean($s->header('Message-ID'));
- }
+ my $ibx = $ctx->{-inbox};
+ if ($mid =~ m!\A([a-f0-9]{2})([a-f0-9]{38})\z!) {
+ my ($x2, $x38) = ($1, $2);
+ # this is horrifically wasteful for legacy URLs:
+ my $str = $ctx->{-inbox}->msg_by_path("$x2/$x38") or return;
+ require Email::Simple;
+ my $s = Email::Simple->new($str);
+ $mid = PublicInbox::MID::mid_clean($s->header('Message-ID'));
+ return r301($ctx, $inbox, $mid);
}
undef;
}
@@ -208,12 +209,6 @@ sub get_index {
}
}
-# just returns a string ref for the blob in the current ctx
-sub mid2blob {
- my ($ctx) = @_;
- $ctx->{-inbox}->msg_by_mid($ctx->{mid});
-}
-
# /$INBOX/$MESSAGE_ID/raw -> raw mbox
sub get_mid_txt {
my ($ctx) = @_;
diff --git a/t/plack.t b/t/plack.t
index 26b0366..7eb7d7f 100644
--- a/t/plack.t
+++ b/t/plack.t
@@ -18,6 +18,7 @@ foreach my $mod (@mods) {
}
use_ok 'PublicInbox::Import';
use_ok 'PublicInbox::Git';
+my @ls;
foreach my $mod (@mods) { use_ok $mod; }
{
@@ -55,6 +56,8 @@ EOF
$im->done;
my $rev = `git --git-dir="$maindir" rev-list HEAD`;
like($rev, qr/\A[a-f0-9]{40}/, "good revision committed");
+ @ls = `git --git-dir="$maindir" ls-tree -r --name-only HEAD`;
+ chomp @ls;
}
my $app = eval {
local $ENV{PI_CONFIG} = $pi_config;
@@ -198,6 +201,21 @@ EOF
"$sfx redirected to /mbox.gz");
});
}
+ test_psgi($app, sub {
+ my ($cb) = @_;
+ # for a while, we used to support /$INBOX/$X40/
+ # when we "compressed" long Message-IDs to SHA-1
+ # Now we're stuck supporting them forever :<
+ foreach my $path (@ls) {
+ $path =~ tr!/!!d;
+ my $from = "http://example.com/test/$path/";
+ my $res = $cb->(GET($from));
+ is(301, $res->code, 'is permanent redirect');
+ like($res->header('Location'),
+ qr!/test/blah\@example\.com/!,
+ 'redirect from x40 MIDs works');
+ }
+ });
}
done_testing();
--
EW
next prev parent reply other threads:[~2018-03-29 10:28 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-29 10:28 [PATCH 00/14] purging support, v1 conversions, cleanups + more Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 01/14] www: remove unnecessary ghost checks Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 02/14] v2writable: append, instead of prepending generated Message-ID Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 03/14] lookup by Message-ID favors the "primary" one Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 04/14] www: fix attachment downloads for conflicted Message-IDs Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 05/14] searchmsg: document why we store To: and Cc: for NNTP Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 06/14] public-inbox-convert: tool for converting old to new inboxes Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 07/14] v2writable: support purging messages from git entirely Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 08/14] search: cleanup uniqueness checking Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 09/14] search: get rid of most lookup_* subroutines Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 10/14] search: move find_doc_ids to searchidx Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 11/14] v2writable: cleanup: get rid of unused fields Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` [PATCH 12/14] mbox: avoid extracting Message-ID for linkification Eric Wong (Contractor, The Linux Foundation)
2018-03-29 10:28 ` Eric Wong (Contractor, The Linux Foundation) [this message]
2018-03-29 10:28 ` [PATCH 14/14] view: get rid of some unnecessary imports Eric Wong (Contractor, The Linux Foundation)
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=20180329102819.15234-14-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).