From ab2e3b0e890a45202a9c360f444917a0ff336d50 Mon Sep 17 00:00:00 2001
From: Andreas Roussos <a.roussos@dataly.gr>
Date: Fri, 9 Oct 2020 13:39:52 +0200
Subject: [PATCH] Bug 26641: pass the MARC field as an argument to
 link_bibs_to_authorities.pl

When running link_bibs_to_authorities.pl, it could be useful to have
the ability to specify which MARC field the script should operate on.

For example, when you have a catalog where most links are in place,
and you don't want the script to process every MARC field but rather
limit it to a specific MARC field (e.g. 700) because you've observed
that there are many missing links for that particular MARC field.

This patch provides that enhancement.

Test plan:
1) Run the script as follows (preferably in a test DB):

   time link_bibs_to_authorities.pl -v -l --test

   ... and notice how long it takes to complete.

2) Apply the patch.

3) Run the script again, this time providing the MARC field to work on:

   time link_bibs_to_authorities.pl -v -l --test -g=700

   ... and, again, notice how long it takes to complete.

   The 2nd run should run faster than the 1st one.

Signed-off-by: David Cook <dcook@prosentient.com.au>
Signed-off-by: Martin Renvoize <martin.renvoize@ptfs-europe.com>

Signed-off-by: Jonathan Druart <jonathan.druart@bugs.koha-community.org>
---
 C4/Biblio.pm                     |  4 ++++
 misc/link_bibs_to_authorities.pl | 17 +++++++++++++----
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/C4/Biblio.pm b/C4/Biblio.pm
index 6b7e78e05b..1e7a7c3b67 100644
--- a/C4/Biblio.pm
+++ b/C4/Biblio.pm
@@ -482,6 +482,7 @@ sub LinkBibHeadingsToAuthorities {
     my $bib           = shift;
     my $frameworkcode = shift;
     my $allowrelink = shift;
+    my $tagtolink     = shift;
     my %results;
     if (!$bib) {
         carp 'LinkBibHeadingsToAuthorities called on undefined bib record';
@@ -493,6 +494,9 @@ sub LinkBibHeadingsToAuthorities {
     $allowrelink = 1 unless defined $allowrelink;
     my $num_headings_changed = 0;
     foreach my $field ( $bib->fields() ) {
+        if ( defined $tagtolink ) {
+          next unless $field->tag() == $tagtolink ;
+        }
         my $heading = C4::Heading->new_from_field( $field, $frameworkcode );
         next unless defined $heading;
 
diff --git a/misc/link_bibs_to_authorities.pl b/misc/link_bibs_to_authorities.pl
index 9044292185..41a9edb63f 100755
--- a/misc/link_bibs_to_authorities.pl
+++ b/misc/link_bibs_to_authorities.pl
@@ -36,6 +36,7 @@ my $want_help   = 0;
 my $auth_limit;
 my $bib_limit;
 my $commit = 100;
+my $tagtolink;
 
 my $result = GetOptions(
     'v|verbose'      => \$verbose,
@@ -44,6 +45,7 @@ my $result = GetOptions(
     'a|auth-limit=s' => \$auth_limit,
     'b|bib-limit=s'  => \$bib_limit,
     'c|commit=i'     => \$commit,
+    'g|tagtolink=i'  => \$tagtolink,
     'h|help'         => \$want_help
 );
 
@@ -77,13 +79,13 @@ my %linked_headings;
 my %fuzzy_headings;
 my $dbh = C4::Context->dbh;
 $dbh->{AutoCommit} = 0;
-process_bibs( $linker, $bib_limit, $auth_limit, $commit );
+process_bibs( $linker, $bib_limit, $auth_limit, $commit, $tagtolink );
 $dbh->commit();
 
 exit 0;
 
 sub process_bibs {
-    my ( $linker, $bib_limit, $auth_limit, $commit ) = @_;
+    my ( $linker, $bib_limit, $auth_limit, $commit, $tagtolink ) = @_;
     my $bib_where = '';
     my $starttime = time();
     if ($bib_limit) {
@@ -95,7 +97,7 @@ sub process_bibs {
     $sth->execute();
     while ( my ($biblionumber) = $sth->fetchrow_array() ) {
         $num_bibs_processed++;
-        process_bib( $linker, $biblionumber );
+        process_bib( $linker, $biblionumber, $tagtolink );
 
         if ( not $test_only and ( $num_bibs_processed % $commit ) == 0 ) {
             print_progress_and_commit($num_bibs_processed);
@@ -187,6 +189,7 @@ _FUZZY_HEADER_
 sub process_bib {
     my $linker       = shift;
     my $biblionumber = shift;
+    my $tagtolink    = shift;
 
     my $bib = GetMarcBiblio({ biblionumber => $biblionumber });
     unless ( defined $bib ) {
@@ -197,9 +200,10 @@ sub process_bib {
     }
 
     my $frameworkcode = GetFrameworkCode($biblionumber);
+    my $allowrelink = C4::Context->preference("CatalogModuleRelink") || '';
 
     my ( $headings_changed, $results ) =
-      LinkBibHeadingsToAuthorities( $linker, $bib, $frameworkcode );
+      LinkBibHeadingsToAuthorities( $linker, $bib, $frameworkcode, $allowrelink, $tagtolink );
     foreach my $key ( keys %{ $results->{'unlinked'} } ) {
         $unlinked_headings{$key} += $results->{'unlinked'}->{$key};
     }
@@ -246,6 +250,7 @@ link_bibs_to_authorities.pl
   link_bibs_to_authorities.pl --commit=1000
   link_bibs_to_authorities.pl --auth-limit=STRING
   link_bibs_to_authorities.pl --bib-limit=STRING
+  link_bibs_to_authorities.pl -g=700
 
 =head1 DESCRIPTION
 
@@ -281,6 +286,10 @@ Only process those bib records that match the user-specified WHERE clause.
 
 Commit the results to the database after every N records are processed.
 
+=item B<-g=N>
+
+Only process those headings found in MARC field N.
+
 =item B<--test>
 
 Only test the authority linking and report the results; do not change the bib
-- 
2.39.5