Attachment 82585 Details for Bug 21872 – Bug 21872: Fix some issues with record_batches.pl

[patch] Bug 21872: Fix some issues with record_batches.pl

Bug-21872-Fix-some-issues-with-recordbatchespl.patch (text/plain), 3.97 KB, created by David Gustafsson on 2018-11-22 18:10:35 UTC

(hide)

Description:

Filename:

MIME Type:

Creator: David Gustafsson

Created: 2018-11-22 18:10:35 UTC

Size: 3.97 KB

patch

obsolete

>From a0feb355eeca7c2f68abe08e82b6b684a7c60d4e Mon Sep 17 00:00:00 2001
>From: David Gustafsson <david.gustafsson@ub.gu.se>
>Date: Thu, 22 Nov 2018 19:01:04 +0100
>Subject: [PATCH] Bug 21872: Fix some issues with record_batches.pl
>
>Fix behavior for case where no biblios or just one biblio exists.
>Improve performance by only selecting items greater than last end
>of range instead of increasing offset by batch size. Also don't use
>underscore for option names.
>---
> misc/record_batches.pl | 61 ++++++++++++++++++++++++++++----------------------
> 1 file changed, 34 insertions(+), 27 deletions(-)
> mode change 100644 => 100755 misc/record_batches.pl
>
>diff --git a/misc/record_batches.pl b/misc/record_batches.pl
>old mode 100644
>new mode 100755
>index e003c8ef5c..1e1e442287
>--- a/misc/record_batches.pl
>+++ b/misc/record_batches.pl
>@@ -5,12 +5,12 @@ use C4::Context;
> use Getopt::Long;
> use Pod::Usage;
> 
>-my $gt_biblionumber;
>+my $start_biblionumber;
> my $batch_size;
> my $help;
> GetOptions(
>-    'gt_biblionumber=i' => \$gt_biblionumber,
>-    'batch_size=i' => \$batch_size,
>+    'startbiblionumber=i' => \$start_biblionumber,
>+    'batchsize=i' => \$batch_size,
>     'h|help|?' => \$help
> );
> if ($help) {
>@@ -18,31 +18,38 @@ if ($help) {
> }
> 
> my $dbh = C4::Context->dbh;
>-my $step = $batch_size || 25000;
>-my $offset = 0;
>-my $prev_biblionumber;
>-my ($max_biblionumber) = @{ $dbh->selectcol_arrayref(qq{SELECT MAX(`biblionumber`) FROM `biblio`}) };
>-my @ranges;
>-my $biblionumber;
>+$batch_size ||= 25000; # TODO: Assert positive number
>+
>+if (!$start_biblionumber) {
>+    my ($min_biblionumber) = @{ $dbh->selectcol_arrayref(qq{SELECT MIN(`biblionumber`) FROM `biblio`}) };
>+    $start_biblionumber = $min_biblionumber;
>+}
> 
> while (1) {
>-    my $query = $gt_biblionumber ?
>-        qq{SELECT `biblionumber` FROM `biblio` WHERE `biblionumber` >= $gt_biblionumber ORDER BY `biblionumber` ASC LIMIT 1 OFFSET $offset} :
>-        qq{SELECT `biblionumber` FROM `biblio` ORDER BY `biblionumber` ASC LIMIT 1 OFFSET $offset};
>-    my ($biblionumber) = @{ $dbh->selectcol_arrayref($query) };
>-    if (!$biblionumber) {
>-        push @ranges, [$prev_biblionumber, $max_biblionumber];
>+    my $offset = $batch_size - 1;
>+    my $query =
>+        qq{SELECT `biblionumber` FROM `biblio` WHERE `biblionumber` >= $start_biblionumber ORDER BY `biblionumber` ASC LIMIT 2 OFFSET $offset};
>+    my ($end_biblionumber, $next_biblionumber) = @{ $dbh->selectcol_arrayref($query) };
>+    if (!$end_biblionumber) {
>+        if ($start_biblionumber) {
>+            my ($max_biblionumber) = @{ $dbh->selectcol_arrayref(qq{SELECT MAX(`biblionumber`) FROM `biblio`}) };
>+            if($max_biblionumber >= $start_biblionumber) {
>+                # @TODO: Option for argument and range separator?
>+                print join(' ', ($start_biblionumber, $max_biblionumber)) . "\n";
>+
>+            }
>+        }
>         last;
>     }
>-    elsif ($prev_biblionumber) {
>-        push @ranges, [$prev_biblionumber, $biblionumber - 1];
>+    else {
>+        print join(' ', ($start_biblionumber, $end_biblionumber)) . "\n";
>+    }
>+    if ($next_biblionumber) {
>+        $start_biblionumber = $next_biblionumber;
>+    }
>+    else {
>+        last;
>     }
>-    $prev_biblionumber = $biblionumber;
>-    $offset += $step;
>-}
>-
>-foreach my $range (@ranges) {
>-    print join(' ', @{$range}) . "\n"; # @TODO: Option for argument and range separtor?
> }
> 
> =head1 NAME
>@@ -51,7 +58,7 @@ record batches - This script outputs ranges of biblionumbers
> 
> =head1 SYNOPSIS
> 
>-record_batches.pl [-h|--help] [--gt_biblionumber=BIBLIONUMBER]
>+record_batches.pl [-h|--help] [--startbiblionumber=BIBLIONUMBER]
> 
> =head1 OPTIONS
> 
>@@ -61,8 +68,8 @@ record_batches.pl [-h|--help] [--gt_biblionumber=BIBLIONUMBER]
> 
> Print a brief help message.
> 
>-=item B<--gt_biblionumber>
>+=item B<--startbiblionumber>
> 
>- --gt_biblionumber=BIBLIONUMBER Output batches with biblionumber >= BIBLIONUMBER
>+ --startbiblionumber=BIBLIONUMBER Output batches with biblionumber >= BIBLIONUMBER
> 
>-=item B<--batch_size>
>+=item B<--batchsize>
>-- 
>2.11.0

Actions: View | Diff | Splinter Review

Attachments on bug 21872: 82582 | 82583 | 82584 | 82585 | 82586 | 82598 | 82599 | 82780 | 85119 | 85121 | 85975 | 85976 | 85977 | 85978 | 85979 | 86053 | 86054 | 86055 | 86056 | 86057 | 89109 | 89110 | 89111 | 89112 | 89113