--- trunk/IsisDB.pm 2004/12/29 17:03:52 11 +++ trunk/IsisDB.pm 2004/12/29 22:46:40 15 @@ -7,7 +7,7 @@ BEGIN { use Exporter (); use vars qw ($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS); - $VERSION = 0.03; + $VERSION = 0.05; @ISA = qw (Exporter); #Give a hoot don't pollute, do not export more than needed by default @EXPORT = qw (); @@ -18,7 +18,7 @@ =head1 NAME -IsisDB - Read CDS/ISIS database +IsisDB - Read CDS/ISIS, WinISIS and IsisMarc database =head1 SYNOPSIS @@ -34,17 +34,28 @@ =head1 DESCRIPTION -This module will read CDS/ISIS databases and create hash values out of it. -It can be used as perl-only alternative to OpenIsis module. +This module will read ISIS databases created by DOS CDS/ISIS, WinIsis or +IsisMarc. It can be used as perl-only alternative to OpenIsis module. -This will module will always be slower that OpenIsis module which use C -library. However, since it's written in perl, it's platform independent (so -you don't need C compiler), and can be easily modified. +It can create hash values from data in ISIS database (using C), +ASCII dump (using C) or just hash with field names and packed +values (like C<^asomething^belse>). Unique feature of this module is ability to C records. It will also skip zero sized fields (OpenIsis has a bug in XS bindings, so fields which are zero sized will be filled with random junk from memory). +It also has support for identifiers (only if ISIS database is created by +IsisMarc), see C. + +This will module will always be slower than OpenIsis module which use C +library. However, since it's written in perl, it's platform independent (so +you don't need C compiler), and can be easily modified. I hope that it +creates data structures which are easier to use than ones created by +OpenIsis, so reduced time in other parts of the code should compensate for +slower performance of this module (speed of reading ISIS database is +rarely an issue). + =head1 METHODS =cut @@ -65,13 +76,17 @@ =head2 new -Open CDS/ISIS database +Open ISIS database my $isis = new IsisDB( isisdb => './cds/cds', read_fdt => 1, - debug => 1, include_deleted => 1, + hash_filter => sub { + my $v = shift; + $v =~ s#foo#bar#g; + }, + debug => 1, ); Options are described below: @@ -80,22 +95,28 @@ =item isisdb -Prefix path to CDS/ISIS. It should contain full or relative path to database -and common prefix of C<.FDT>, C<.MST>, C<.CNT>, C<.XRF> and C<.MST> files. +This is full or relative path to ISIS database files which include +common prefix of C<.FDT>, C<.MST>, C<.CNT>, C<.XRF> and C<.MST> files. + +In this example it uses C<./cds/cds.MST> and related files. =item read_fdt Boolean flag to specify if field definition table should be read. It's off by default. -=item debug - -Dump a C of debugging output. - =item include_deleted Don't skip logically deleted records in ISIS. +=item hash_filter + +Filter code ref which will be used before data is converted to hash. + +=item debug + +Dump a B of debugging output. + =back It will also set C<$isis-E{'maxmfn'}> which is maximum MFN stored in database. @@ -109,7 +130,7 @@ croak "new needs database name (isisdb) as argument!" unless ({@_}->{isisdb}); - foreach my $v (qw{isisdb debug include_deleted}) { + foreach my $v (qw{isisdb debug include_deleted hash_filter}) { $self->{$v} = {@_}->{$v}; } @@ -206,7 +227,7 @@ close(fileCNT); - print Dumper($self) if ($self->{debug}); + print Dumper($self),"\n" if ($self->{debug}); # open files for later open($self->{'fileXRF'}, $self->{isisdb}.".XRF") || croak "can't open '$self->{isisdb}.XRF': $!"; @@ -223,7 +244,12 @@ my $rec = $isis->fetch(55); Returns hash with keys which are field names and values are unpacked values -for that field. +for that field like this: + + $rec = { + '210' => [ '^aNew York^cNew York University press^dcop. 1988' ], + '990' => [ '2140', '88', 'HAY' ], + }; =cut @@ -347,16 +373,26 @@ } close(fileMST); - print Dumper($self) if ($self->{debug}); + print Dumper($self),"\n" if ($self->{debug}); return $self->{'record'}; } =head2 to_ascii -Dump ascii output of selected MFN +Dump ASCII output of record with specified MFN + + print $isis->to_ascii(42); + +It outputs something like this: - print $isis->to_ascii(55); + 210 ^aNew York^cNew York University press^dcop. 1988 + 990 2140 + 990 88 + 990 HAY + +If C is specified when calling C it will display field names +from C<.FDT> file instead of numeric tags. =cut @@ -370,7 +406,8 @@ my $out = "0\t$mfn"; foreach my $f (sort keys %{$rec}) { - $out .= "\n$f\t".join("\n$f\t",@{$self->{record}->{$f}}); + my $fn = $self->tag_name($f); + $out .= "\n$fn\t".join("\n$fn\t",@{$self->{record}->{$f}}); } $out .= "\n"; @@ -378,23 +415,102 @@ return $out; } -# -# XXX porting from php left-over: -# -# do I *REALLY* need those methods, or should I use -# $self->{something} directly? -# -# Probably direct usage is better! -# +=head2 to_hash + +Read record with specified MFN and convert it to hash -sub TagName { + my $hash = $isis->to_hash($mfn); + +It has ability to convert characters (using C from ISIS +database before creating structures enabling character re-mapping or quick +fix-up of data. + +This function returns hash which is like this: + + $hash = { + '210' => [ + { + 'c' => 'New York University press', + 'a' => 'New York', + 'd' => 'cop. 1988' + } + ], + '990' => [ + '2140', + '88', + 'HAY' + ], + }; + +You can later use that hash to produce any output from ISIS data. + +If database is created using IsisMarc, it will also have to special fields +which will be used for identifiers, C and C like this: + + '200' => [ + { + 'i1' => '1', + 'i2' => ' ' + 'a' => 'Goa', + 'f' => 'Valdo D\'Arienzo', + 'e' => 'tipografie e tipografi nel XVI secolo', + } + ], + +This method will also create additional field C<000> with MFN. + +=cut + +sub to_hash { my $self = shift; - return $self->{TagName}; + + my $mfn = shift || confess "need mfn!"; + + # init record to include MFN as field 000 + my $rec = { '000' => $mfn }; + + my $row = $self->fetch($mfn); + + foreach my $k (keys %{$row}) { + foreach my $l (@{$row->{$k}}) { + + # filter output + $l = $self->{'hash_filter'}->($l) if ($self->{'hash_filter'}); + + my $val; + + # has identifiers? + ($val->{'i1'},$val->{'i2'}) = ($1,$2) if ($l =~ s/^([01 #])([01 #])//); + + # has subfields? + if ($l =~ m/\^/) { + foreach my $t (split(/\^/,$l)) { + next if (! $t); + $val->{substr($t,0,1)} = substr($t,1); + } + } else { + $val = $l; + } + + push @{$rec->{$k}}, $val; + } + } + + return $rec; } -sub NextMFN { +=head2 tag_name + +Return name of selected tag + + print $isis->tag_name('200'); + +=cut + +sub tag_name { my $self = shift; - return $self->{NXTMFN}; + my $tag = shift || return; + return $self->{'TagName'}->{$tag} || $tag; } 1; @@ -410,8 +526,8 @@ dpavlin@rot13.org http://www.rot13.org/~dpavlin/ -This module is based heavily on code from LIBISIS.PHP - Library to read ISIS files V0.1.1 -written in php and (c) 2000 Franck Martin - released under LGPL. +This module is based heavily on code from C library to read ISIS files V0.1.1 +written in php and (c) 2000 Franck Martin and released under LGPL. =head1 COPYRIGHT @@ -424,5 +540,7 @@ =head1 SEE ALSO -L, perl(1). +OpenIsis web site L + +perl4lib site L