We only support searching on prefixes matching /\A\w+\z/ because
Xapian requires ':' to delimit the prefix and splits on spaces
without quotes.
I've also verified Xapian supports multibyte UTF-8 characters,
underscores, and bare numbers as search prefixes, so there's
no need to restrict it beyond what Perl's UTF-8 aware \w
character class offers.
---
lib/PublicInbox/AltId.pm | 2 +-
lib/PublicInbox/Search.pm | 2 ++
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/lib/PublicInbox/AltId.pm b/lib/PublicInbox/AltId.pm
index 8ce70e46..3be6c73c 100644
--- a/lib/PublicInbox/AltId.pm
+++ b/lib/PublicInbox/AltId.pm
@@ -22,7 +22,7 @@ sub new {
my ($class, $ibx, $spec, $writable) = @_;
my ($type, $prefix, $query) = split(/:/, $spec, 3);
$type eq 'serial' or die "non-serial not supported, yet\n";
-
+ $prefix =~ /\A\w+\z/ or warn "non-word prefix not searchable\n";
my %params = map {
my ($k, $v) = split(/=/, uri_unescape($_), 2);
$v = '' unless defined $v;
diff --git a/lib/PublicInbox/Search.pm b/lib/PublicInbox/Search.pm
index 372dc5a7..00dddc6b 100644
--- a/lib/PublicInbox/Search.pm
+++ b/lib/PublicInbox/Search.pm
@@ -316,6 +316,8 @@ sub qp {
my $user_pfx = $self->{-user_pfx} = [];
for (@$altid) {
# $_ = 'serial:gmane:/path/to/gmane.msgmap.sqlite3'
+ # note: Xapian supports multibyte UTF-8, /^[0-9]+$/,
+ # and '_' with prefixes matching \w+
/\Aserial:(\w+):/ or next;
my $pfx = $1;
push @$user_pfx, "$pfx:", <<EOF;
--
unsubscribe: one-click, see List-Unsubscribe header
archive: https://public-inbox.org/meta/
