X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FMID.pm;h=2613c8eb45601399ca929ab54152863b1c25f4e3;hb=09f1e000734bc431ec7b63e18959bf6f34f9c179;hp=169ffa76505f0e788868059d0c5491289060cd45;hpb=f564327fd1e694056a4b13ed398cabd8d0d4c173;p=public-inbox.git diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm index 169ffa76..2613c8eb 100644 --- a/lib/PublicInbox/MID.pm +++ b/lib/PublicInbox/MID.pm @@ -6,7 +6,8 @@ package PublicInbox::MID; use strict; use warnings; use base qw/Exporter/; -our @EXPORT_OK = qw/mid_clean id_compress mid2path/; +our @EXPORT_OK = qw/mid_clean id_compress mid2path mid_mime mid_escape MID_ESC/; +use URI::Escape qw(uri_escape_utf8); use Digest::SHA qw/sha1_hex/; use constant MID_MAX => 40; # SHA-1 hex length @@ -25,6 +26,7 @@ sub id_compress { my ($id, $force) = @_; if ($force || $id =~ /[^\w\-]/ || length($id) > MID_MAX) { + utf8::encode($id); return sha1_hex($id); } $id; @@ -36,10 +38,18 @@ sub mid2path { unless (defined $x38) { # compatibility with old links (or short Message-IDs :) - $mid = sha1_hex(mid_clean($mid)); + $mid = mid_clean($mid); + utf8::encode($mid); + $mid = sha1_hex($mid); ($x2, $x38) = ($mid =~ /\A([a-f0-9]{2})([a-f0-9]{38})\z/); } "$x2/$x38"; } +sub mid_mime ($) { $_[0]->header_obj->header_raw('Message-ID') } + +# RFC3986, section 3.3: +sub MID_ESC () { '^A-Za-z0-9\-\._~!\$\&\';\(\)\*\+,;=:@' } +sub mid_escape ($) { uri_escape_utf8($_[0], MID_ESC) } + 1;