NACO normalization is handy to have around

git-svn-id: svn://svn.open-ils.org/ILS/trunk@8942 dcc99617-32d9-48b4-a31d-7c20da2025e4

diff --git a/Open-ILS/src/perlmods/OpenILS/Application/Storage/FTS.pm b/Open-ILS/src/perlmods/OpenILS/Application/Storage/FTS.pm
index f8db6ea..6dd03c0 100644 (file)
--- a/Open-ILS/src/perlmods/OpenILS/Application/Storage/FTS.pm
+++ b/Open-ILS/src/perlmods/OpenILS/Application/Storage/FTS.pm
@@ -5,6 +5,7 @@ my $log = 'OpenSRF::Utils::Logger';
 package OpenILS::Application::Storage::FTS;
 use OpenSRF::Utils::Logger qw/:level/;
 use Parse::RecDescent;
+use Unicode::Normalize;
 
 my $_default_grammar_parser = new Parse::RecDescent ( <<'GRAMMAR' );
 
@@ -26,6 +27,49 @@ numeric_range: /\d+-\d*/
 
 GRAMMAR
 
+sub naco_normalize {
+
+    my $txt = lc(shift);
+    my $sf = shift;
+
+    $txt = NFD($txt);
+    $txt =~ s/\pM+//go; # Remove diacritics
+
+    $txt =~ s/\xE6/AE/go;   # Convert ae digraph
+    $txt =~ s/\x{153}/OE/go;# Convert oe digraph
+    $txt =~ s/\xFE/TH/go;   # Convert Icelandic thorn
+
+    $txt =~ tr/\x{2070}\x{2071}\x{2072}\x{2073}\x{2074}\x{2075}\x{2076}\x{2077}\x{2078}\x{2079}\x{207A}\x{207B}/0123456789+-/;# Convert superscript numbers
+    $txt =~ tr/\x{2080}\x{2081}\x{2082}\x{2083}\x{2084}\x{2085}\x{2086}\x{2087}\x{2088}\x{2089}\x{208A}\x{208B}/0123456889+-/;# Convert subscript numbers
+
+    $txt =~ tr/\x{0251}\x{03B1}\x{03B2}\x{0262}\x{03B3}/AABGG/;     # Convert Latin and Greek
+    $txt =~ tr/\x{2113}\xF0\!\"\(\)\-\{\}\<\>\;\:\.\?\xA1\xBF\/\\\@\*\%\=\xB1\+\xAE\xA9\x{2117}\$\xA3\x{FFE1}\xB0\^\_\~\`/LD /; # Convert Misc
+    $txt =~ tr/\'\[\]\|//d;                         # Remove Misc
+
+    if ($sf && $sf =~ /^a/o) {
+        my $commapos = index($txt,',');
+        if ($commapos > -1) {
+            if ($commapos != length($txt) - 1) {
+                my @list = split /,/, $txt;
+                my $first = shift @list;
+                $txt = $first . ',' . join(' ', @list);
+            } else {
+                $txt =~ s/,/ /go;
+            }
+        }
+    } else {
+        $txt =~ s/,/ /go;
+    }
+
+    $txt =~ s/\s+/ /go; # Compress multiple spaces
+    $txt =~ s/^\s+//o;  # Remove leading space
+    $txt =~ s/\s+$//o;  # Remove trailing space
+
+    return $txt;
+}
+
+#' stupid vim syntax highlighting ...
+
 sub compile {
 
        $log->debug("You must override me somewhere, or I will make searching really slow!!!!",ERROR);;