From 5240ee7346322c30bc98b1317158949530e653bf Mon Sep 17 00:00:00 2001
From: Gerhard Gonter <ggonter@gmail.com>
Date: Mon, 17 Jan 2022 13:03:35 +0100
Subject: [PATCH] migration table with more information from alma
---
eprints1.pl | 82 +++++++++++++++++++++++++++++++++++++++++++++++++----
1 file changed, 77 insertions(+), 5 deletions(-)
diff --git a/eprints1.pl b/eprints1.pl
index d7cae7a..771df7f 100755
--- a/eprints1.pl
+++ b/eprints1.pl
@@ -3155,9 +3155,9 @@ sub ot2ut
while (my $attachment= shift(@docs))
{
$attachment_number++;
- my $fnm_attachment_md= 'othes/utheses_json/' . $eprint_id . '_' . $attachment_number . '_md.json';
- my $fnm_attachment_res= 'othes/utheses_json/' . $eprint_id . '_' . $attachment_number . '_res.json';
- my $fnm_attachment_chg= 'othes/utheses_json/' . $eprint_id . '_' . $attachment_number . '_chg.json';
+ my $fnm_attachment_md= 'othes/utheses_json/' . $ot2ut_context . '/' . $eprint_id . '_' . $attachment_number . '_md.json';
+ my $fnm_attachment_res= 'othes/utheses_json/' . $ot2ut_context . '/' . $eprint_id . '_' . $attachment_number . '_res.json';
+ my $fnm_attachment_chg= 'othes/utheses_json/' . $ot2ut_context . '/' . $eprint_id . '_' . $attachment_number . '_chg.json';
my $attachment_md=
{
@@ -5211,7 +5211,6 @@ sub policies_stats
<p><font color="red">$msg</font></p>
<p><a href="buckets.html" target="buckets">$bucket_cnt buckets</a></p>
<h2>upload counters</h2>
-<p><a href="http://xx2.test.univie.ac.at:3001/html/metablocks" target="opa">Live Counter</a></p>
<table border="1">
<tr>
<th>metablock</th>
@@ -5228,6 +5227,7 @@ sub policies_stats
<th>count</th><th>pct</th><th>err</th>
</tr>
EOX
+# <p><a href="http://xx2.test.univie.ac.at:3001/html/metablocks" target="opa">Live Counter</a></p>
my %incomplete_blocks= ();
@@ -5571,6 +5571,7 @@ sub export_migration_data
my %data;
# pass 1: get data from sync db
+ print __LINE__, " get data from sync db\n";
my @sync_fields= qw(eprint_id eprint_status utheses_id ts_upload upload_status);
{
my $col_sync= $db_ot2ut->get_collection('sync');
@@ -5589,6 +5590,7 @@ sub export_migration_data
}
# pass 2: get data from utheses.policies
+ print __LINE__, " get data from utheses.policies\n";
my @utp_fields= qw(eprint_id ac_nummer urn doi lastmod);
{
my $col_utp= $db_ot2ut->get_collection('utheses.policies');
@@ -5609,6 +5611,7 @@ sub export_migration_data
}
# 3: get data from alma.marc
+ print __LINE__, " get data from alma.marc\n";
my @marc_fields= qw(ac_number mms_id fetched lib_code);
my @marc_extra_fields= qw(marc_record ts_fetched);
{
@@ -5647,6 +5650,67 @@ sub export_migration_data
next MARC;
}
$rec->{marc_record}= 'marc_data_found';
+
+ # print __LINE__, " mrd: ", Dumper($mrd);
+ my ($df_urn, $val_urn, $df_doi, $val_doi, $df_othes, $val_othes, $df_utheses, $val_utheses);
+ foreach my $df (@{$mrd->{datafield}})
+ {
+ foreach my $sf (@{$df->{subfield}})
+ {
+ if ($sf->{content} =~ m#urn:nbn#)
+ {
+ $df_urn= join(':', (map { $df->{$_} } qw(tag ind1 ind2)), $sf->{code});
+ $val_urn= $sf->{content};
+ }
+ elsif ($sf->{content} =~ m#10\.25365#)
+ {
+ $df_doi= join(':', (map { $df->{$_} } qw(tag ind1 ind2)), $sf->{code});
+ $val_doi= $sf->{content};
+ }
+ elsif ($sf->{content} =~ m#othes\.univie#)
+ {
+ $df_othes= join(':', (map { $df->{$_} } qw(tag ind1 ind2)), $sf->{code});
+ $val_othes= $sf->{content};
+ }
+ elsif ($sf->{content} =~ m#utheses\.univie#)
+ {
+ $df_utheses= join(':', (map { $df->{$_} } qw(tag ind1 ind2)), $sf->{code});
+ $val_utheses= $sf->{content};
+ }
+ }
+ }
+ $rec->{ df_urn}= $df_urn;
+ $rec->{val_urn}= $val_urn;
+ $rec->{ df_doi}= $df_doi;
+ $rec->{val_doi}= $val_doi;
+ $rec->{ df_othes}= $df_othes;
+ $rec->{val_othes}= $val_othes;
+ $rec->{ df_utheses}= $df_utheses;
+ $rec->{val_utheses}= $val_utheses;
+ }
+ }
+
+ # 4: get bucket codes from bucket.lists
+ print __LINE__, " get data from bucket.lists\n";
+ {
+ $db_ot2ut= IRMA::db::get_any_db($cnf, 'ot2ut_database') unless (defined ($db_ot2ut));
+ my $col_bl= $db_ot2ut->get_collection('bucket.lists');
+ my $cur_bl= $col_bl->find();
+ print __LINE__, " cur_bl=[$cur_bl]\n";
+
+ BUCKET: while ($running)
+ {
+ my $bucket= $cur_bl->next();
+ last BUCKET unless (defined ($bucket));
+ my ($bucket_code, $eprint_ids)= map { $bucket->{$_} } qw( code ids );
+ # print __LINE__, " bucket_code=[bucket_code] eprint_ids=[$eprint_ids]\n";
+
+ foreach my $id (keys %$eprint_ids)
+ {
+ # print __LINE__, " id=[$id]\n";
+ next unless (exists ($data{$id}));
+ $data{$id}->{bucket_code}= $bucket_code;
+ }
}
}
@@ -5655,7 +5719,15 @@ sub export_migration_data
my $tsv_fnm= sprintf ("%s/sync_%s.tsv", $base_path, $ot2ut_context);
print __LINE__, " writing migration table [$tsv_fnm]\n";
- my @tsv_columns= (@sync_fields, @utp_fields, @marc_fields, @marc_extra_fields); # NOTE: eprint_id is there several times
+ # my @tsv_columns= (@sync_fields, @utp_fields, @marc_fields, @marc_extra_fields); # NOTE: eprint_id is there several times
+
+ my @tsv_columns= qw( eprint_id eprint_status lastmod
+ urn doi ac_nummer bucket_code
+ utheses_id ts_upload upload_status
+ ac_number mms_id fetched lib_code marc_record ts_fetched
+ df_urn val_urn df_doi val_doi df_othes val_othes df_utheses val_utheses
+ );
+
open (TSV, '>:utf8', $tsv_fnm) or die;
print TSV join("\t", @tsv_columns), "\n";
foreach my $eprint_id (sort { $a <=> $b } keys %data)
--
GitLab