mid: extract Message-ID from inside '<>'

[public-inbox.git] / lib / PublicInbox / MID.pm

diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm
index d097011bf4ae21b58075def04f2306cd66a22f54..8ca3c5797e314e6440aaf36ebc1c1fc4b7134e7c 100644 (file)
--- a/lib/PublicInbox/MID.pm
+++ b/lib/PublicInbox/MID.pm
@@ -4,7 +4,7 @@ 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);
 }