From: Eric Wong <e@80x24.org>
To: meta@public-inbox.org
Subject: [PATCH] mbox: generate Archived-At, List-Post, List-Archive headers
Date: Sun, 4 Oct 2015 00:54:09 +0000 [thread overview]
Message-ID: <20151004005409.785-2-e@80x24.org> (raw)
Downloaded mboxen can be archived/stored indefinitely, try to
make it easy for future archaelogists to find the online
archive location.
---
lib/PublicInbox/Mbox.pm | 24 ++++++++++++++++++++----
lib/PublicInbox/WWW.pm | 2 +-
2 files changed, 21 insertions(+), 5 deletions(-)
diff --git a/lib/PublicInbox/Mbox.pm b/lib/PublicInbox/Mbox.pm
index 6aa0517..80e8efc 100644
--- a/lib/PublicInbox/Mbox.pm
+++ b/lib/PublicInbox/Mbox.pm
@@ -4,7 +4,8 @@
package PublicInbox::Mbox;
use strict;
use warnings;
-use PublicInbox::MID qw/mid2path/;
+use PublicInbox::MID qw/mid2path mid_clean/;
+use URI::Escape qw/uri_escape_utf8/;
require Email::Simple;
sub thread_mbox {
@@ -17,17 +18,18 @@ sub thread_mbox {
sub emit1 {
my $simple = Email::Simple->new(pop);
+ my $ctx = pop;
sub {
my ($response) = @_;
# single message should be easily renderable in browsers
my $fh = $response->([200, ['Content-Type'=>'text/plain']]);
- emit_msg($fh, $simple);
+ emit_msg($ctx, $fh, $simple);
$fh->close;
}
}
sub emit_msg {
- my ($fh, $simple) = @_; # Email::Simple object
+ my ($ctx, $fh, $simple) = @_; # Email::Simple object
my $header_obj = $simple->header_obj;
# drop potentially confusing headers, ssoma already should've dropped
@@ -35,6 +37,20 @@ sub emit_msg {
foreach my $d (qw(Lines Bytes Content-Length Status)) {
$header_obj->header_set($d);
}
+ my $feed_opts = $ctx->{feed_opts};
+ unless ($feed_opts) {
+ require PublicInbox::Feed; # FIXME: gross
+ $feed_opts = PublicInbox::Feed::get_feedopts($ctx);
+ $ctx->{feed_opts} = $feed_opts;
+ }
+ my $base = $feed_opts->{url};
+ my $mid = mid_clean($header_obj->header('Message-ID'));
+ $mid = uri_escape_utf8($mid);
+ my @archived_at = $header_obj->header('Archived-At');
+ push @archived_at, "<$base$mid/>";
+ $header_obj->header_set('Archived-At', @archived_at);
+ $header_obj->header_set('List-Archive', "<$base>");
+ $header_obj->header_set('List-Post', "<mailto:$feed_opts->{id_addr}>");
my $buf = $header_obj->as_string;
unless ($buf =~ /\AFrom /) {
@@ -82,7 +98,7 @@ sub emit_mbox {
my $p = 'HEAD:'.mid2path($smsg->mid);
Email::Simple->new($git->cat_file($p));
};
- emit_msg($fh, $msg) if $msg;
+ emit_msg($ctx, $fh, $msg) if $msg;
}
$opts{offset} += $nr;
diff --git a/lib/PublicInbox/WWW.pm b/lib/PublicInbox/WWW.pm
index 58a4256..fb57163 100644
--- a/lib/PublicInbox/WWW.pm
+++ b/lib/PublicInbox/WWW.pm
@@ -163,7 +163,7 @@ sub get_mid_txt {
my ($ctx) = @_;
my $x = mid2blob($ctx) or return r404($ctx);
require PublicInbox::Mbox;
- PublicInbox::Mbox::emit1($x);
+ PublicInbox::Mbox::emit1($ctx, $x);
}
# /$LISTNAME/$MESSAGE_ID/ -> HTML content (short quotes)
--
EW
reply other threads:[~2015-10-04 0:54 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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: https://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=20151004005409.785-2-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).