diff --git a/eod1.pl b/eod1.pl index afc8d52c86eb03e3b86c061a85fefc096b93c74b..43339b37c61ae474431f0d089cdaf2dda029bdad 100755 --- a/eod1.pl +++ b/eod1.pl @@ -39,16 +39,15 @@ my @tsv_columns= qw( pid verdict ownerId state model ac_number alma_notes ac_number_note aleph_url marc_record ts_fetched fetched ts_marc mms_id lib_code - ticket ticket_status vt + ticket ticket_status ticket_pid ticket_url vt df_doi val_doi doi update_doi df_urn val_urn urn update_urn df_hdl val_hdl hdl update_hdl df_phaidra val_phaidra phaidra_url update_phaidra_url - ); +); my (@pars, @ac_numbers, @pids); -my $arg; -while (defined ($arg= shift (@ARGV))) +while (defined (my $arg= shift (@ARGV))) { if ($arg eq '-') { push (@pars, '-'); } elsif ($arg eq '--') { push (@pars, @ARGV); @ARGV= (); } @@ -151,7 +150,7 @@ print __LINE__, " found $book_count books\n"; { push (@books_ok, $book); } - elsif ($verdict eq 'has_ac_number_note') + elsif ($verdict eq 'ac_number_note' && $book->{ac_number_note} eq 'dup') { push (@books_duplicate_ac_number, $book); } @@ -169,8 +168,8 @@ sub write_tsv_file open (TSV, '>:utf8', $tsv_filename) or die "can't write to $tsv_filename"; my $count_books_ok= @$book_list; - print "saving $count_books_ok to $tsv_filename\n"; print TSV join("\t", @tsv_columns), "\n"; + print "saving $count_books_ok to $tsv_filename\n"; BOOKx: foreach my $book (@$book_list) { print TSV join("\t", map { $book->{$_} } @tsv_columns), "\n"; @@ -231,5 +230,53 @@ update_phaidra_url | https://phaidra.univie.ac.at/o:90496 o:90495 is a collection, o:90496 is the only member; this is a ZS record, so this is ok and the suggested change is not correct. Filtered for now +=head2 request queue entry example (edited) + +/home/gg/perl/Phaidra/Stage/JobQueue.pm 128 insert_new_job() +* job: $VAR1 = { + 'requested_by' => $my_agent_name, + 'ac_number' => 'AC08824094', + 'ts_iso' => '20230327T133843', + 'action' => 'update_alma_2xml', + 'status' => 'new', + 'agent' => 'alma_cat' +}; + + +=head2 update queue (stand 2023-03-27T1340) + +ac_number | AC08838287 +ts_marc | 20211219214345.0 + +ac_number | AC08824094 +ts_marc | 20171115013000.0 + + +=head1 config file + +=head2 prefiltered_pids + +List of pids which are removed from the search results and thus are +never entered into any result set. E.g. objects that should be deleted +but are not yet. + +=head2 filtered_pids + +List of pids which should not be processed further due to some reason. +See ticket for details. + +=head2 filtered_pids_resolved + +List of pids that were dealt with already. The script does not do +anything with this list actually, it is only used to store items from +one of the other lists for reference only. + +=head1 DOIs + +stage:gg> find alma_cat/ -type f -print |xargs fgrep 10.25365/digital-copy +alma_cat/082/AC07818082/alma.xml: <subfield code="a">10.25365/digital-copy.1</subfield> +alma_cat/405/AC15515405/alma.xml: <subfield code="a">10.25365/digital-copy.1</subfield> +stage:gg> date +Mon Mar 27 16:40:26 CEST 2023