LP#1373601: Consider relevant characters before using word-boundary checks

To perform unanchored phrase limits, we make sure that the phrase supplied
by the user does not end in the middle of a word by bounding the condition
with word-boundary bracket expresssions.  However, if the phrase starts
or ends with a non-word character (that is, something other than numbers,
letters, or the underscore) then the word-boundary expression won't match.
The effect of this is to cause phrase searches starting or ending in
punctuation to fail when the user would not expect them to.

To address this, we now test the phrase for word-iness at the front and
back before applying word-boundary bracket expressions.

Signed-off-by: Mike Rylander <mrylander@gmail.com>
Signed-off-by: Kathy Lussier <klussier@masslnc.org>

diff --git a/Open-ILS/src/perlmods/lib/OpenILS/Application/Storage/Driver/Pg/QueryParser.pm b/Open-ILS/src/perlmods/lib/OpenILS/Application/Storage/Driver/Pg/QueryParser.pm
index f08b1e5..ea55769 100644 (file)
--- a/Open-ILS/src/perlmods/lib/OpenILS/Application/Storage/Driver/Pg/QueryParser.pm
+++ b/Open-ILS/src/perlmods/lib/OpenILS/Application/Storage/Driver/Pg/QueryParser.pm
@@ -85,15 +85,24 @@ sub quote_phrase_value {
 
     my $left_anchored = '';
     my $right_anchored = '';
+    my $left_wb = 0;
+    my $right_wb = 0;
+
     $left_anchored  = $1 if $value =~ m/^([*\^])/;
     $right_anchored = $1 if $value =~ m/([*\$])$/;
+
+    # We can't use word-boundary bracket expressions if the relevant char
+    # is not actually a "word" characters.
+    $left_wb  = $wb if $value =~ m/^\w+/;
+    $right_wb = $wb if $value =~ m/\w+$/;
+
     $value =~ s/^[*\^]//   if $left_anchored;
     $value =~ s/[*\$]$//  if $right_anchored;
     $value = quotemeta($value);
     $value = '^' . $value if $left_anchored eq '^';
     $value = "$value\$"   if $right_anchored eq '$';
-    $value = '[[:<:]]' . $value if $wb && !$left_anchored;
-    $value .= '[[:>:]]' if $wb && !$right_anchored;
+    $value = '[[:<:]]' . $value if $left_wb && !$left_anchored;
+    $value .= '[[:>:]]' if $right_wb && !$right_anchored;
     return $self->quote_value($value);
 }