www: do not mangle characters from search queries

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

diff --git a/lib/PublicInbox/MID.pm b/lib/PublicInbox/MID.pm
index d097011bf4ae21b58075def04f2306cd66a22f54..2613c8eb45601399ca929ab54152863b1c25f4e3 100644 (file)
--- a/lib/PublicInbox/MID.pm
+++ b/lib/PublicInbox/MID.pm
@@ -1,10 +1,13 @@
-# 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)
+#
+# Various Message-ID-related functions.
 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 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
 
@@ -12,16 +15,21 @@ 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);
-       sha1_hex($mid);
+sub id_compress {
+       my ($id, $force) = @_;
+
+       if ($force || $id =~ /[^\w\-]/ || length($id) > MID_MAX) {
+               utf8::encode($id);
+               return sha1_hex($id);
+       }
+       $id;
 }
 
 sub mid2path {
@@ -30,10 +38,18 @@ sub mid2path {
 
        unless (defined $x38) {
                # compatibility with old links (or short Message-IDs :)
+               $mid = mid_clean($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;