--- trunk/tools/mods2unimarc.pl 2004/05/14 16:38:22 325 +++ trunk/tools/mods2unimarc.pl 2004/05/14 17:22:39 326 @@ -19,7 +19,10 @@ This script B to MODS export from Faculty of Electrical Engineering and Computing -so you might want to edit it +so you might want to edit it (among other thing, it includes a lot +of fields which are in Croatian). + +Feel free to hack this script and convert it to your own needs. =head1 WARNING @@ -82,11 +85,11 @@ ContentKey => '-content', ); - my $m=$marc->createrecord(); + my $m_cache; - sub marc_arr { - my $m = shift || die "no marc record?"; - my $fld = shift || die "no marc field?"; + sub marc_add { + my $m_cache = \shift; + my $fld = shift || die "need field!"; my $sf = shift || ''; return if (! @_); @@ -94,7 +97,7 @@ my @a; foreach (@_) { next if (! $_); - push @a,$sf; + push @a,$sf if ($sf); # push @a,$utf2iso->convert($_) || $_; push @a,$_; } @@ -103,14 +106,14 @@ # print "storing $fld: ",join("|",@a),"\n"; - $marc->addfield({record=>$m, - field=>$fld, - # i1=>$i1, - # i2=>$i2, - value=>\@a}); + push @{$$m_cache->{$fld}}, @a; + } - marc_arr($m,'610','a',@{$ref->{subject}->{topic}}); + my $journal = 0; + $journal = 1 if ($ref->{recordInfo}->{recordIdentifier} =~ m/^c-/); + + marc_add($m_cache,'610','a',@{$ref->{subject}->{topic}}); my $fld = '700'; @@ -118,16 +121,16 @@ my $role = $name->{role}->{roleTerm}->{content}; next if (! $role); if ($role eq "author") { - marc_arr($m,$fld,'a',$name->{namePart}->{family}); - marc_arr($m,$fld,'b',$name->{namePart}->{given}); - marc_arr($m,$fld,'4',$role); + marc_add($m_cache,$fld,'a',$name->{namePart}->{family}); + marc_add($m_cache,$fld,'b',$name->{namePart}->{given}); + marc_add($m_cache,$fld,'4',$role); # first author goes in 700, others in 701 $fld = '701'; } elsif ($role eq "editor" or $role eq "illustrator") { - marc_arr($m,'702','a',$name->{namePart}->{family}); - marc_arr($m,'702','b',$name->{namePart}->{given}); - marc_arr($m,'702','4',$role); + marc_add($m_cache,'702','a',$name->{namePart}->{family}); + marc_add($m_cache,'702','b',$name->{namePart}->{given}); + marc_add($m_cache,'702','4',$role); } else { die "FATAL: don't know how to map role '$role'" if ($role); } @@ -138,11 +141,11 @@ if ($note) { foreach my $n (split(/\s*;\s+/, $note)) { if ($n =~ s/bibliogr:\s+//i) { - marc_arr($m,'320','a',"Bibliografija: $n"); + marc_add($m_cache,'320','a',"Bibliografija: $n"); } elsif ($n =~ s/ilustr:\s+//i) { - marc_arr($m,'215','c', $n); + marc_add($m_cache,'215','c', $n); } else { - marc_arr($m,'320','a',$n); + marc_add($m_cache,'320','a',$n); } } } @@ -152,9 +155,9 @@ if ($type) { if ($type eq "isbn") { - marc_arr($m,'010','a',$ref->{identifier}->{content}); + marc_add($m_cache,'010','a',$ref->{identifier}->{content}); } elsif ($type eq "issn") { - marc_arr($m,'011','a',$ref->{identifier}->{content}); + marc_add($m_cache,'011','a',$ref->{identifier}->{content}); } else { die "unknown identifier type $type"; } @@ -175,163 +178,58 @@ if ($tmp->{str}) { $data .= $tmp->{str}." str"; } - marc_arr($m,'210','a', $data) if ($data); - marc_arr($m,'210','d', $tmp->{visina}); + marc_add($m_cache,'215','a', $data) if ($data); + marc_add($m_cache,'215','d', $tmp->{visina}); } - marc_arr($m,'001','',$ref->{recordInfo}->{recordIdentifier}); + marc_add($m_cache,'001',undef,$ref->{recordInfo}->{recordIdentifier}); - marc_arr($m,'200','a',$ref->{titleInfo}->{title}); - marc_arr($m,'200','e',$ref->{titleInfo}->{subTitle}); + marc_add($m_cache,'200','a',$ref->{titleInfo}->{title}); + marc_add($m_cache,'200','e',$ref->{titleInfo}->{subTitle}); - marc_arr($m,'675','a',$ref->{classification}->{udc}); + marc_add($m_cache,'675','a',$ref->{classification}->{udc}); my $related = $ref->{relatedItem}->{type}; if ($related) { if ($related eq "series") { - marc_arr($m,'675','a',$ref->{relatedItem}->{titleInfo}->{title}); - marc_arr($m,'999','a',$ref->{relatedItem}->{titleInfo}->{partNumber}); + marc_add($m_cache,'225','a',$ref->{relatedItem}->{titleInfo}->{title}); + marc_add($m_cache,'999','a',$ref->{relatedItem}->{titleInfo}->{partNumber}); } elsif ($related eq "preceding") { - marc_arr($m,'430','a',$ref->{relatedItem}->{titleInfo}->{title}); + marc_add($m_cache,'430','a',$ref->{relatedItem}->{titleInfo}->{title}); } else { die "can't parse related item type $related" if ($related); } } - marc_arr($m,'205','a',$ref->{originInfo}->{edition}); + marc_add($m_cache,'205','a',$ref->{originInfo}->{edition}); my $publisher = $ref->{originInfo}->{publisher}; if ($publisher =~ m,^(.+?)\s*/\s*(.+)$,) { - marc_arr($m,'210','a', $2); - marc_arr($m,'210','c', $1); + marc_add($m_cache,'210','a', $2); + marc_add($m_cache,'210','c', $1); } else { - marc_arr($m,'210','c', $publisher); + marc_add($m_cache,'210','c', $publisher); } - marc_arr($m,'326','a',$ref->{originInfo}->{frequency}); - marc_arr($m,'326','a',$ref->{originInfo}->{place}); + marc_add($m_cache,'326','a',$ref->{originInfo}->{frequency}) if ($journal); + + marc_add($m_cache,'210','a',$ref->{originInfo}->{place}); - marc_arr($m,'210','d',$ref->{originInfo}->{dateIssued}); + marc_add($m_cache,'210','d',$ref->{originInfo}->{dateIssued}); $nr++; print "$nr " if ($nr % 100 == 0); + # dump record + my $m=$marc->createrecord(); + foreach my $fld (keys %{$m_cache}) { +# print "$fld: ",join(" * ",@{$m_cache->{$fld}}),"\n"; + $marc->addfield({record=>$m, + field=>$fld, + value=>\@{$m_cache->{$fld}} + }); + } + $t->purge; # frees the memory } -__END__ - -KNJIGA = { -610a 'subject' => [ - { - 'topic' => [ - 'LIBRARIES-AUTOMATION', - 'ELECTRONIC DATA PROCESSING-LIBRARY SCIENCE' - ] - } - ], - 'name' => [ - { - 'namePart' => { -700b,701a... 'given' => 'Robert M.', -700a,701b... 'family' => 'Hayes' - }, - 'type' => 'personal', - 'role' => { - 'roleTerm' => { -7004,7014... 'content' => 'author', - 'type' => 'text' - } - } - }, - { - 'namePart' => { -702b 'given' => 'Joseph', -702a 'family' => 'Becker' - }, - 'type' => 'personal', - 'role' => { - 'roleTerm' => { -7024 'content' => 'editor', - 'type' => 'text' - } - } - }, - { - 'namePart' => { -702b 'given' => 'Joseph', -702a 'family' => 'Becker' - }, - 'type' => 'personal', - 'role' => { - 'roleTerm' => { -7024 'content' => 'illustrator', - 'type' => 'text' - } - } - } - ], - 'note' => 'bibliogr: 645-647; kazalo; ilustr: ilustr.', - 'identifier' => { -010a 'content' => '0-471-36483-5', - 'type' => 'isbn' - }, -215a;215d 'physicalDescription' => 'str: 688; pagin: xvi; visina: 24. cm', -001 'recordInfo' => { - 'recordIdentifier' => 'k-7996-8073' - }, -200a 'titleInfo' => { - 'title' => 'Handbook of data processing for libraries' - }, - 'typeOfResource' => 'text', -675a 'classification' => { - 'udc' => '=20' - }, -225a 'relatedItem' => { - 'titleInfo' => { - 'title' => 'A WILEY-BECKER & HAYES SERIES BOOK' - }, - 'type' => 'series' - }, - 'originInfo' => { - 'issuance' => 'monographic', -205a 'edition' => '2.', -210c/210a 'publisher' => 'MELVILLE PUBLISHING COMPANY /LOS ANGELES, CALIFORNIA/', -210d 'dateIssued' => '1974' - } - }; - - - - CASOPIS = { - 'identifier' => { -011a 'content' => '1041-5173', - 'type' => 'issn' - }, - 'recordInfo' => { - 'recordIdentifier' => 'c-1' - }, - 'titleInfo' => { - 'title' => 'DBMS - CLIENT/SERVER COMPUTING' - }, - 'typeOfResource' => 'text', -999a 'relatedItem' => { - 'titleInfo' => { - 'partNumber' => 'g. 1990, vol. 137, br. 5' - }, - 'type' => 'series' - }, - 'classification' => { - 'udc' => '=20' - }, - 'originInfo' => { -326a 'frequency' => 'mjese�no', - 'issuance' => 'continuing', -210a 'place' => 'SAN MATEO, KANADA', -210c 'publisher' => 'M&T PUBLISHING INC.' - } - }; - - -=cut -