Attachment 75968 Details for Bug 20664 – Bug 20664: Optimize retrieval of biblio and item data

[patch] Bug 20664: Optimize retrieval of biblio and item data

Bug-20664-Optimize-retrieval-of-biblio-and-item-da.patch (text/plain), 10.71 KB, created by Ere Maijala on 2018-06-12 08:05:19 UTC

(hide)

Description:

Filename:

MIME Type:

Creator: Ere Maijala

Created: 2018-06-12 08:05:19 UTC

Size: 10.71 KB

patch

obsolete

>From 7bf3f7e437e958db0f438430b808f3f443fdcb41 Mon Sep 17 00:00:00 2001
>From: Ere Maijala <ere.maijala@helsinki.fi>
>Date: Tue, 28 Nov 2017 10:14:20 +0200
>Subject: [PATCH] Bug 20664: Optimize retrieval of biblio and item data
>
>Optimizes embedding of item data in MARC and fixes several bottlenecks encountered while profiling OAI-PMH and exporting of records. There are three ways this is accomplished:
>
>1.) Use state variables to hold prepared SQL statements so that the preparation is done only once.
>2.) Create optimized method for fetching item fields for MARC embedding.
>3.) Use the cache service more and where repeated calls are made.
>
>Test plan:
>
>1.) Before applying the patch, time an export_records.pl run for a set of biblios that also have items. Run it a couple of times to account for initial slowness and possible fluctuations. For example:
>
>time misc/export_records.pl --record-type bibs --starting_biblionumber 960000 --ending_biblionumber 965000 --format xml --filename unoptimized.xml
>
>2.) Apply the patch.
>
>3.) Time the export process again with a different output file:
>
>time misc/export_records.pl --record-type bibs --starting_biblionumber 960000 --ending_biblionumber 965000 --format xml --filename optimized.xml
>
>4.) Verify that the optimized process is faster.
>
>5.) Compare the resulting export files to make sure they're identical:
>
>diff -u unoptimized.xml optimized.xml
>---
> C4/Biblio.pm | 101 +++++++++++++++++++++++++++++++++--------------------------
> C4/Items.pm  |  66 ++++++++++++++++++++++++++++++++++++++
> 2 files changed, 122 insertions(+), 45 deletions(-)
>
>diff --git a/C4/Biblio.pm b/C4/Biblio.pm
>index eaff256..b04999b 100644
>--- a/C4/Biblio.pm
>+++ b/C4/Biblio.pm
>@@ -344,7 +344,7 @@ sub ModBiblio {
> 
> =head2 _strip_item_fields
> 
>-  _strip_item_fields($record, $frameworkcode)
>+  _strip_item_fields($record)
> 
> Utility routine to remove item tags from a
> MARC bib.
>@@ -355,7 +355,7 @@ sub _strip_item_fields {
>     my $record = shift;
>     my $frameworkcode = shift;
>     # get the items before and append them to the biblio before updating the record, atm we just have the biblio
>-    my ( $itemtag, $itemsubfield ) = GetMarcFromKohaField( "items.itemnumber", $frameworkcode );
>+    my ( $itemtag, $itemsubfield ) = GetMarcFromKohaField( "items.itemnumber" );
> 
>     # delete any item fields from incoming record to avoid
>     # duplication or incorrect data - use AddItem() or ModItem()
>@@ -1053,14 +1053,22 @@ sub GetMarcSubfieldStructure {
> sub GetMarcFromKohaField {
>     my ( $kohafield ) = @_;
>     return unless $kohafield;
>-    # The next call uses the Default framework since it is AUTHORITATIVE
>-    # for all Koha to MARC mappings.
>-    my $mss = GetMarcSubfieldStructure( '' ); # Do not change framework
>-    my @retval;
>-    foreach( @{ $mss->{$kohafield} } ) {
>-        push @retval, $_->{tagfield}, $_->{tagsubfield};
>-    }
>-    return wantarray ? @retval : ( @retval ? $retval[0] : undef );
>+
>+    my $cache     = Koha::Caches->get_instance();
>+    my $cache_key = "MarcFromKohaField-$kohafield";
>+    my $cached    = $cache->get_from_cache($cache_key);
>+    if ( !defined $cached ) {
>+        # The next call uses the Default framework since it is AUTHORITATIVE
>+        # for all Koha to MARC mappings.
>+        my $mss = GetMarcSubfieldStructure( '' ); # Do not change framework
>+        my @retval;
>+        foreach( @{ $mss->{$kohafield} } ) {
>+            push @retval, $_->{tagfield}, $_->{tagsubfield};
>+        }
>+        $cached = \@retval;
>+        $cache->set_in_cache( $cache_key, $cached );
>+    }
>+    return wantarray ? @$cached : ( @$cached ? $cached->[0] : undef );
> }
> 
> =head2 GetMarcSubfieldStructureFromKohaField
>@@ -1137,10 +1145,11 @@ sub GetMarcBiblio {
>         return;
>     }
> 
>-    my $dbh          = C4::Context->dbh;
>-    my $sth          = $dbh->prepare("SELECT biblioitemnumber FROM biblioitems WHERE biblionumber=? ");
>+    # Use state to speed up repeated calls in batch processes
>+    state $sth = C4::Context->dbh->prepare("SELECT biblioitemnumber FROM biblioitems WHERE biblionumber=? ");
>     $sth->execute($biblionumber);
>     my $row     = $sth->fetchrow_hashref;
>+    $sth->finish;
>     my $biblioitemnumber = $row->{'biblioitemnumber'};
>     my $marcxml = GetXmlBiblio( $biblionumber );
>     $marcxml = StripNonXmlChars( $marcxml );
>@@ -1179,17 +1188,22 @@ The XML should only contain biblio information (item information is no longer st
> 
> sub GetXmlBiblio {
>     my ($biblionumber) = @_;
>-    my $dbh = C4::Context->dbh;
>     return unless $biblionumber;
>-    my ($marcxml) = $dbh->selectrow_array(
>+
>+    # Use state to speed up repeated calls in batch processes
>+    state $sth = C4::Context->dbh->prepare(
>         q|
>         SELECT metadata
>         FROM biblio_metadata
>         WHERE biblionumber=?
>             AND format='marcxml'
>             AND marcflavour=?
>-    |, undef, $biblionumber, C4::Context->preference('marcflavour')
>+        |
>     );
>+
>+    $sth->execute( $biblionumber, C4::Context->preference('marcflavour') );
>+    my ($marcxml) = $sth->fetchrow();
>+    $sth->finish;
>     return $marcxml;
> }
> 
>@@ -2090,10 +2104,11 @@ sub UpsertMarcControlField {
> 
> sub GetFrameworkCode {
>     my ($biblionumber) = @_;
>-    my $dbh            = C4::Context->dbh;
>-    my $sth            = $dbh->prepare("SELECT frameworkcode FROM biblio WHERE biblionumber=?");
>+    # Use state to speed up repeated calls in batch processes
>+    state $sth         = C4::Context->dbh->prepare("SELECT frameworkcode FROM biblio WHERE biblionumber=?");
>     $sth->execute($biblionumber);
>     my ($frameworkcode) = $sth->fetchrow;
>+    $sth->finish;
>     return $frameworkcode;
> }
> 
>@@ -2756,36 +2771,32 @@ sub EmbedItemsInMarcBiblio {
> 
>     $itemnumbers = [] unless defined $itemnumbers;
> 
>-    my $frameworkcode = GetFrameworkCode($biblionumber);
>-    _strip_item_fields($marc, $frameworkcode);
>+    _strip_item_fields($marc);
>+
>+    my $cache     = Koha::Caches->get_instance();
>+    my $cache_key = "OpacHiddenItems-parsed" . ($opac ? '-opac' : '');
>+    my $hidingrules    = $cache->get_from_cache($cache_key);
>+    if ( !defined $hidingrules ) {
>+        my $yaml = $opac ? C4::Context->preference('OpacHiddenItems') : '';
>+        if ( $yaml =~ /\S/ ) {
>+            $yaml = "$yaml\n\n"; # YAML is anal on ending \n. Surplus does not hurt
>+            eval {
>+                $hidingrules = YAML::Load($yaml);
>+            };
>+            if ($@) {
>+                carp "Unable to parse OpacHiddenItems syspref : $@";
>+            }
>+        } else {
>+            $hidingrules = {};
>+        }
>+        $cache->set_in_cache( $cache_key, $hidingrules );
>+    }
> 
>-    # ... and embed the current items
>-    my $dbh = C4::Context->dbh;
>-    my $sth = $dbh->prepare("SELECT itemnumber FROM items WHERE biblionumber = ?");
>-    $sth->execute($biblionumber);
>-    my @item_fields;
>-    my ( $itemtag, $itemsubfield ) = GetMarcFromKohaField( "items.itemnumber", $frameworkcode );
>-    my @items;
>-    my $opachiddenitems = $opac
>-      && ( C4::Context->preference('OpacHiddenItems') !~ /^\s*$/ );
>     require C4::Items;
>-    while ( my ($itemnumber) = $sth->fetchrow_array ) {
>-        next if @$itemnumbers and not grep { $_ == $itemnumber } @$itemnumbers;
>-        my $i = $opachiddenitems ? C4::Items::GetItem($itemnumber) : undef;
>-        push @items, { itemnumber => $itemnumber, item => $i };
>-    }
>-    my @hiddenitems =
>-      $opachiddenitems
>-      ? C4::Items::GetHiddenItemnumbers( map { $_->{item} } @items )
>-      : ();
>-    # Convert to a hash for quick searching
>-    my %hiddenitems = map { $_ => 1 } @hiddenitems;
>-    foreach my $itemnumber ( map { $_->{itemnumber} } @items ) {
>-        next if $hiddenitems{$itemnumber};
>-        my $item_marc = C4::Items::GetMarcItem( $biblionumber, $itemnumber );
>-        push @item_fields, $item_marc->field($itemtag);
>-    }
>-    $marc->append_fields(@item_fields);
>+
>+    my $item_fields = C4::Items::GetMarcItemFields( $biblionumber, $itemnumbers, $hidingrules );
>+
>+    $marc->append_fields(@$item_fields) if ( @$item_fields );
> }
> 
> =head1 INTERNAL FUNCTIONS
>diff --git a/C4/Items.pm b/C4/Items.pm
>index e7279ff..9a069d5 100644
>--- a/C4/Items.pm
>+++ b/C4/Items.pm
>@@ -21,6 +21,7 @@ package C4::Items;
> use strict;
> #use warnings; FIXME - Bug 2505
> 
>+use Modern::Perl;
> use Carp;
> use C4::Context;
> use C4::Koha;
>@@ -1524,6 +1525,71 @@ sub Item2Marc {
> 	return $itemmarc;
> }
> 
>+=head2 GetMarcItemFields
>+
>+  my @marc_fields = GetMarcItemFields($biblionumber);
>+
>+Returns an array of MARC::Record objects of the items for the biblio.
>+
>+=cut
>+
>+sub GetMarcItemFields {
>+	my ( $biblionumber, $itemnumbers, $hidingrules ) = @_;
>+
>+    my $item_level_itype = C4::Context->preference('item-level_itypes');
>+    # This is so much faster than using Koha::Items->search that it makes sense even if it's ugly.
>+    state $sth = C4::Context->dbh->prepare( 'SELECT * FROM items WHERE biblionumber = ?' );
>+    $sth->execute( $biblionumber );
>+    my $items = $sth->fetchall_arrayref({});
>+    $sth->finish();
>+    my @item_fields;
>+    my ( $itemtag, $itemsubfield ) = GetMarcFromKohaField( 'items.itemnumber' );
>+
>+    ITEMLOOP: foreach my $item (@$items) {
>+
>+        # Check itemnumbers
>+        next if ( @$itemnumbers && !any { $_ == $item->{itemnumber} } @$itemnumbers );
>+
>+        # Check hiding rules
>+        if ( defined $hidingrules ) {
>+            foreach my $field (keys %$hidingrules) {
>+                my $val = $item->{$field};
>+                $val = '' unless defined $val;
>+
>+                # If the results matches the values in the hiding rules, skip the item
>+                if (any { $val eq $_ } @{$hidingrules->{$field}}) {
>+                    next ITEMLOOP;
>+                }
>+            }
>+        }
>+
>+        # Set correct item type
>+        if ( !$item_level_itype || !$item->{itype} ) {
>+            warn 'item-level_itypes set but no itemtype set for item (' . $item->{itemnumber} . ')' if ( !$item->{itype} );
>+            my $biblioitem = Koha::Biblioitem::find( $item->{biblioitemnumber} );
>+            $item->itype = $biblioitem->itemtype();
>+        }
>+
>+        my $mungeditem = {
>+            map {
>+                defined($item->{$_}) && $item->{$_} ne '' ? ("items.$_" => $item->{$_}) : ()
>+            } keys %{ $item }
>+        };
>+        my $itemmarc = TransformKohaToMarc($mungeditem);
>+
>+        my $unlinked_item_subfields = _parse_unlinked_item_subfields_from_xml($mungeditem->{'items.more_subfields_xml'});
>+        if (defined $unlinked_item_subfields and $#$unlinked_item_subfields > -1) {
>+            foreach my $field ($itemmarc->field($itemtag)){
>+                $field->add_subfields(@$unlinked_item_subfields);
>+            }
>+        }
>+
>+        push @item_fields, $itemmarc->field( $itemtag );
>+    }
>+
>+    return \@item_fields;
>+}
>+
> =head1 PRIVATE FUNCTIONS AND VARIABLES
> 
> The following functions are not meant to be called
>-- 
>2.7.4

Actions: View | Diff | Splinter Review

Attachments on bug 20664: 74873 | 75968 | 76045 | 76046 | 76669 | 78868 | 78869 | 78870 | 79225 | 79227 | 79228 | 79229 | 79276 | 79277 | 79278 | 79279 | 84516 | 84517 | 84518 | 84519 | 84520 | 85106 | 85107 | 85108 | 85109 | 85110 | 85776 | 85777 | 85778 | 85779 | 85780 | 85781 | 85898 | 85899 | 85900 | 85901 | 85902 | 85903 | 85904 | 85905 | 86002 | 86003 | 86004 | 86005 | 86006 | 86007 | 86008 | 86009