From 0e2b06521971e095e50db8bc7ae58ccd828b4d86 Mon Sep 17 00:00:00 2001
From: Paul POULAIN <paul.poulain@biblibre.com>
Date: Wed, 20 Feb 2008 06:55:22 +1300
Subject: [PATCH] NoZebra : removing . and : before indexing

Signed-off-by: Chris Cormack <chris@bigballofwax.co.nz>
Signed-off-by: Joshua Ferraro <jmf@liblime.com>
---
 C4/Biblio.pm                            | 2 +-
 C4/Search.pm                            | 2 +-
 misc/migration_tools/rebuild_nozebra.pl | 8 ++++++--
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/C4/Biblio.pm b/C4/Biblio.pm
index 0340b81149..86f6310379 100755
--- a/C4/Biblio.pm
+++ b/C4/Biblio.pm
@@ -2269,7 +2269,7 @@ sub _AddBiblioNoZebra {
     }
 
     # remove blancks comma (that could cause problem when decoding the string for CQL retrieval) and regexp specific values
-    $title =~ s/ |,|;|\[|\]|\(|\)|\*|-|'|=//g;
+    $title =~ s/ |\.|,|;|\[|\]|\(|\)|\*|-|'|:|=//g;
     # limit to 10 char, should be enough, and limit the DB size
     $title = substr($title,0,10);
     #parse each field
diff --git a/C4/Search.pm b/C4/Search.pm
index 080d13a209..12ee86511c 100644
--- a/C4/Search.pm
+++ b/C4/Search.pm
@@ -1805,7 +1805,7 @@ sub NZoperatorAND{
                 "$value-$countvalue;$value-$countvalue;";
         }
     }
-    warn " $finalresult \n" if $DEBUG;
+    warn "NZAND DONE : $finalresult \n" if $DEBUG;
     return $finalresult;
 }
       
diff --git a/misc/migration_tools/rebuild_nozebra.pl b/misc/migration_tools/rebuild_nozebra.pl
index a1191af9e6..114d87fe26 100755
--- a/misc/migration_tools/rebuild_nozebra.pl
+++ b/misc/migration_tools/rebuild_nozebra.pl
@@ -108,7 +108,7 @@ while (my ($biblionumber) = $sth->fetchrow) {
     my $title = lc($record->subfield($titletag,$titlesubfield));
 
     # remove blancks comma (that could cause problem when decoding the string for CQL retrieval) and regexp specific values
-    $title =~ s/ |,|;|\[|\]|\(|\)|\*|-|'|=//g;
+    $title =~ s/ |\.|,|;|\[|\]|\(|\)|\*|-|'|=|://g;
     # limit to 10 char, should be enough, and limit the DB size
     $title = substr($title,0,10);
     #parse each field
@@ -214,7 +214,7 @@ while (my ($authid) = $sth->fetchrow) {
     $index{'auth_type'}    = '152b';
 
     # remove blancks comma (that could cause problem when decoding the string for CQL retrieval) and regexp specific values
-    $title =~ s/ |,|;|\[|\]|\(|\)|\*|-|'|=//g;
+    $title =~ s/ |\.|,|;|\[|\]|\(|\)|\*|-|'|:|=//g;
     $title = quotemeta $title;
     # limit to 10 char, should be enough, and limit the DB size
     $title = substr($title,0,10);
@@ -271,6 +271,9 @@ while (my ($authid) = $sth->fetchrow) {
 }
 print "\nInserting...\n";
 $i=0;
+
+my $commitnum = 100;
+$dbh->{AutoCommit} = 0;
 $sth = $dbh->prepare("INSERT INTO nozebra (server,indexname,value,biblionumbers) VALUES ('authorityserver',?,?,?)");
 foreach my $key (keys %result) {
     foreach my $index (keys %{$result{$key}}) {
@@ -280,6 +283,7 @@ foreach my $key (keys %result) {
         print "\r$i";
         $i++;
         $sth->execute($key,$index,$result{$key}->{$index});
+        $dbh->commit() if (0 == $i % $commitnum);
     }
 }
 print "\nauthorities done\n";
-- 
2.39.5