X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMID.pm;h=677a9d59e2f4727937eaf815509ee6e59ec2bf50;hb=f76f265a851944b5dedcc3be5f3b5224b6ebda89;hp=d097011bf4ae21b58075def04f2306cd66a22f54;hpb=118ac5c2dc0e7a193ff58f2a9003636e1353583c;p=public-inbox.git

diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm
index d097011b..677a9d59 100644
--- a/lib/PublicInbox/MID.pm
+++ b/lib/PublicInbox/MID.pm
@@ -1,10 +1,10 @@
-# Copyright (C) 2015, all contributors <meta@public-inbox.org>
+# Copyright (C) 2015 all contributors <meta@public-inbox.org>
 # License: AGPLv3 or later (https://www.gnu.org/licenses/agpl-3.0.txt)
 package PublicInbox::MID;
 use strict;
 use warnings;
 use base qw/Exporter/;
-our @EXPORT_OK = qw/mid_clean mid_compressed mid2path/;
+our @EXPORT_OK = qw/mid_clean mid_compress mid2path/;
 use Digest::SHA qw/sha1_hex/;
 use constant MID_MAX => 40; # SHA-1 hex length
 
@@ -12,15 +12,24 @@ sub mid_clean {
 	my ($mid) = @_;
 	defined($mid) or die "no Message-ID";
 	# MDA->precheck did more checking for us
-	$mid =~ s/\A\s*<?//;
-	$mid =~ s/>?\s*\z//;
+	if ($mid =~ /<([^>]+)>/) {
+		$mid = $1;
+	}
 	$mid;
 }
 
 # this is idempotent
-sub mid_compressed {
-	my ($mid) = @_;
-	return $mid if (length($mid) <= MID_MAX);
+sub mid_compress {
+	my ($mid, $force) = @_;
+
+	# XXX dirty hack! FIXME!
+	# Some HTTP servers (apache2 2.2.22-13+deb7u5 on my system)
+	# apparently do not handle "%25" in the URL path component correctly.
+	# I'm not yet sure if it's something weird with my rewrite rules
+	# or what; will need to debug...
+	return sha1_hex($mid) if (index($mid, '%') >= 0);
+
+	return $mid if (!$force && length($mid) <= MID_MAX);
 	sha1_hex($mid);
 }
 
@@ -30,7 +39,7 @@ sub mid2path {
 
 	unless (defined $x38) {
 		# compatibility with old links (or short Message-IDs :)
-		$mid = sha1_hex($mid);
+		$mid = sha1_hex(mid_clean($mid));
 		($x2, $x38) = ($mid =~ /\A([a-f0-9]{2})([a-f0-9]{38})\z/);
 	}
 	"$x2/$x38";