use C4::Dates qw(format_date);
use C4::XSLT;
use C4::Branch;
+use C4::Debug;
+use YAML;
use URI::Escape;
use vars qw($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS $DEBUG);
# we use IsAlpha unicode definition, to deal correctly with diacritics.
# otherwise, a French word like "leçon" woudl be split into "le" "çon", "le"
# is a stopword, we'd get "çon" and wouldn't find anything...
+#
foreach ( keys %{ C4::Context->stopwords } ) {
next if ( $_ =~ /(and|or|not)/ ); # don't remove operators
+ $debug && warn "$_ Dump($operand)";
if ( my ($matched) = ($operand =~
- /(\P{IsAlnum}\Q$_\E\P{IsAlnum}|^\Q$_\E\P{IsAlnum}|\P{IsAlnum}\Q$_\E$|^\Q$_\E$)/gi) )
+ /([^\X\p{isAlnum}]\Q$_\E[^\X\p{isAlnum}]|[^\X\p{isAlnum}]\Q$_\E$|^\Q$_\E[^\X\p{isAlnum}])/gi))
{
$operand =~ s/\Q$matched\E/ /gi;
push @stopwords_removed, $_;
--- /dev/null
+#!/usr/bin/perl
+#
+# This Koha test module is a stub!
+# Add more tests here!!!
+
+use strict;
+use warnings;
+use YAML;
+
+use C4::Debug;
+use C4::Context;
+use C4::Search;
+
+use Test::More tests => 3;
+
+BEGIN {
+ use_ok('C4::Search');
+}
+foreach my $string ("Leçon","mod\xc3\xa8les"){
+my @results=C4::Search::_remove_stopwords($string,"kw");
+$debug && warn "$string ",Dump(@results);
+ok($results[0] eq $string,"$string is not modified");
+}
+foreach my $string ("Les chaussettes de l'archiduchesse"){
+my @results=C4::Search::_remove_stopwords($string,"kw");
+$debug && warn "$string ",Dump(@results);
+ok($results[0] ne $string,"$results[0] from $string");
+}