From 59c26ce5f35f3f18830090b048d0cd6c2a1eb6fc Mon Sep 17 00:00:00 2001
From: Petro Vashchuk <stalkernoid@gmail.com>
Date: Mon, 14 Jun 2021 16:38:51 +0300
Subject: [PATCH] Bug 28316: avoid messing up regexes in the search queries

This patch ensures that the behavior with
QueryRegexEscapeOptions set to values other than
"Escape" still will works as expected.

It does so by storing the contents of regexes
before escaping special characters and
then restores the contents of regexes back to how
it was before, ensuring that searching with regex is possible.

Signed-off-by: Alex Buckley <alexbuckley@catalyst.net.nz>
Signed-off-by: Martin Renvoize <martin.renvoize@ptfs-europe.com>
Signed-off-by: Martin Renvoize <martin.renvoize@ptfs-europe.com>

Signed-off-by: Jonathan Druart <jonathan.druart@bugs.koha-community.org>
Signed-off-by: Kyle M Hall <kyle@bywatersolutions.com>
---
 .../SearchEngine/Elasticsearch/QueryBuilder.pm | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm b/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm
index d1a6065e7d..d6f28ac38f 100644
--- a/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm
+++ b/Koha/SearchEngine/Elasticsearch/QueryBuilder.pm
@@ -939,6 +939,19 @@ sub _clean_search_term {
     }
     $term = $self->_query_regex_escape_process($term);
 
+    # save all regex contents away before escaping brackets:
+    my @saved_regexes;
+    my $rgx_i = 0;
+    while(
+            $term =~ s@(
+                (?<!\\)(?:[\\]{2})*/
+                (?:[^/]+|(?<=\\)(?:[\\]{2})*/)+
+                (?<!\\)(?:[\\]{2})*/
+            )$lookahead@~~RE$rgx_i~~@x
+    ) {
+        @saved_regexes[$rgx_i++] = $1;
+    }
+
     # remove leading and trailing colons mixed with optional slashes and spaces
     $term =~ s/^([\s\\]*:\s*)+//;
     $term =~ s/([\s\\]*:\s*)+$//;
@@ -956,6 +969,11 @@ sub _clean_search_term {
 
     # screen all brackets with backslash
     $term =~ s/(?<!\\)(?:[\\]{2})*([\{\}\[\]])$lookahead/\\$1/g;
+
+    # restore all regex contents after escaping brackets:
+    for (my $i = 0; $i < @saved_regexes; $i++) {
+        $term =~ s/~~RE$i~~/$saved_regexes[$i]/;
+    }
     return $term;
 }
 
-- 
2.39.5