use strict;
use Carp;
+use File::Glob qw(:globally :nocase);
+
use Data::Dumper;
BEGIN {
use Exporter ();
use vars qw ($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS);
- $VERSION = 0.01;
+ $VERSION = 0.08;
@ISA = qw (Exporter);
#Give a hoot don't pollute, do not export more than needed by default
@EXPORT = qw ();
=head1 NAME
-IsisDB - Read CDS/ISIS database
+IsisDB - Read CDS/ISIS, WinISIS and IsisMarc database
=head1 SYNOPSIS
- use IsisDB
+ use IsisDB;
+
my $isis = new IsisDB(
isisdb => './cds/cds',
);
+ for(my $mfn = 1; $mfn <= $isis->{'maxmfn'}; $mfn++) {
+ print $isis->to_ascii($mfn),"\n";
+ }
+
=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 which
+seems to depriciate it's old C<XS> bindings for perl.
+
+It can create hash values from data in ISIS database (using C<to_hash>),
+ASCII dump (using C<to_ascii>) or just hash with field names and packed
+values (like C<^asomething^belse>).
+
+Unique feature of this module is ability to C<include_deleted> 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<to_hash>.
+
+This 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
# some binary reads
#
-sub Read32 {
- my $self = shift;
-
- my $f = shift || die "Read32 needs file handle";
- read($$f,$b,4) || die "can't read 4 bytes from $$f from position ".tell($f);
- return unpack("l",$b);
-}
-
=head2 new
-Open CDS/ISIS database
+Open ISIS database
my $isis = new IsisDB(
isisdb => './cds/cds',
read_fdt => 1,
+ include_deleted => 1,
+ hash_filter => sub {
+ my $v = shift;
+ $v =~ s#foo#bar#g;
+ },
debug => 1,
);
=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<.MST>, and C<.XRF> and optionally C<.FDT> (if using
+C<read_fdt> option) 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 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 C<lot> of debugging output.
+Dump a B<lot> of debugging output.
=back
my $self = {};
bless($self, $class);
- $self->{isisdb} = {@_}->{isisdb} || croak "new needs database name as argument!";
+ croak "new needs database name (isisdb) as argument!" unless ({@_}->{isisdb});
+
+ foreach my $v (qw{isisdb debug include_deleted hash_filter}) {
+ $self->{$v} = {@_}->{$v};
+ }
+
+ my @isis_files = grep(/\.(FDT|MST|XRF|CNT)$/i,glob($self->{isisdb}."*"));
+
+ foreach my $f (@isis_files) {
+ my $ext = $1 if ($f =~ m/\.(\w\w\w)$/);
+ $self->{lc($ext)."_file"} = $f;
+ }
+
+ my @must_exist = qw(mst xrf);
+ push @must_exist, "fdt" if ($self->{read_fdt});
+
+ foreach my $ext (@must_exist) {
+ croak "missing ",uc($ext)," file in ",$self->{isisdb} unless ($self->{$ext."_file"});
+ }
- $self->{debug} = {@_}->{debug};
+ print STDERR "## using files: ",join(" ",@isis_files),"\n" if ($self->{debug});
# if you want to read .FDT file use read_fdt argument when creating class!
- if ({@_}->{read_fdt} && -e $self->{isisdb}.".FDT") {
+ if ($self->{read_fdt} && -e $self->{fdt_file}) {
# read the $db.FDT file for tags
my $fieldzone=0;
- open(fileFDT, $self->{isisdb}.".FDT") || croak "can't read '$self->{isisdb}.FDT': $!";
+ open(fileFDT, $self->{fdt_file}) || croak "can't read '$self->{fdt_file}': $!";
while (<fileFDT>) {
chomp;
# Get the Maximum MFN from $db.MST
- open(fileMST,$self->{isisdb}.".MST") || croak "can't read '$self->{isisdb}.MST': $!";
+ open($self->{'fileMST'}, $self->{mst_file}) || croak "can't open '$self->{mst_file}': $!";
# MST format: (* = 32 bit signed)
# CTLMFN* always 0
# NXTMFB* last block allocated to master file
# NXTMFP offset to next available position in last block
# MFTYPE always 0 for user db file (1 for system)
- seek(fileMST,4,0);
- $self->{'NXTMFN'}=$self->Read32(\*fileMST) || carp "NXTNFN is zero";
+ seek($self->{'fileMST'},4,0);
+
+ my $buff;
+
+ read($self->{'fileMST'}, $buff, 4);
+ $self->{'NXTMFN'}=unpack("l",$buff) || carp "NXTNFN is zero";
# save maximum MFN
$self->{'maxmfn'} = $self->{'NXTMFN'} - 1;
- close(fileMST);
+
+
+
+ print STDERR Dumper($self),"\n" if ($self->{debug});
+
+ # open files for later
+ open($self->{'fileXRF'}, $self->{xrf_file}) || croak "can't open '$self->{xrf_file}': $!";
+
+ $self ? return $self : return undef;
+}
+
+=head2 read_cnt
+
+Read content of C<.CNT> file and return hash containing it.
+
+ print Dumper($isis->read_cnt);
+
+This function is not used by module (C<.CNT> files are not required for this
+module to work), but it can be useful to examine your index (while debugging
+for example).
+
+=cut
+
+sub read_cnt {
+ my $self = shift;
+
+ croak "missing CNT file in ",$self->{isisdb} unless ($self->{cnt_file});
# Get the index information from $db.CNT
- open(fileCNT, $self->{isisdb}.".CNT") || croak "can't read '$self->{isisdb}.CNT': $!";
+ open(fileCNT, $self->{cnt_file}) || croak "can't read '$self->{cnt_file}': $!";
# There is two 26 Bytes fixed lenght records
my $buff = shift || return;
my @arr = unpack("ssssssllls", $buff);
+ print STDERR "unpack_cnt: ",join(" ",@arr),"\n" if ($self->{'debug'});
+
my $IDTYPE = shift @arr;
foreach (@flds) {
- $self->{$IDTYPE}->{$_} = abs(shift @arr);
+ $self->{cnt}->{$IDTYPE}->{$_} = abs(shift @arr);
}
}
my $buff;
+
read(fileCNT, $buff, 26);
$self->unpack_cnt($buff);
read(fileCNT, $buff, 26);
$self->unpack_cnt($buff);
-
close(fileCNT);
- print Dumper($self) if ($self->{debug});
-
- $self ? return $self : return undef;
+ return $self->{cnt};
}
-=head2 GetMFN
+=head2 fetch
Read record with selected MFN
- my $rec = $isis->GetMFN(55);
+ 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
-sub GetMFN {
+sub fetch {
my $self = shift;
- my $mfn = shift || croak "GetMFN needs MFN as argument!";
+ my $mfn = shift || croak "fetch needs MFN as argument!";
- print "GetMFN: $mfn\n" if ($self->{debug});
+ # is mfn allready in memory?
+ my $old_mfn = $self->{'current_mfn'} || -1;
+ return $self->{record} if ($mfn == $old_mfn);
- open(fileXRF, $self->{isisdb}.".XRF") || croak "can't open '$self->{isisdb}.XRF': $!";
+ print STDERR "## fetch: $mfn\n" if ($self->{debug});
# XXX check this?
my $mfnpos=($mfn+int(($mfn-1)/127))*4;
- print "seeking to $mfnpos in file '$self->{isisdb}.XRF'\n" if ($self->{debug});
- seek(fileXRF,$mfnpos,0);
+ print STDERR "## seeking to $mfnpos in file '$self->{xrf_file}'\n" if ($self->{debug});
+ seek($self->{'fileXRF'},$mfnpos,0);
- # read XRFMFB abd XRFMFP
- my $pointer=$self->Read32(\*fileXRF);
+ my $buff;
- my $XRFMFB = int($pointer/2048);
- my $XRFMFP = $pointer - ($XRFMFB*2048);
+ # delete old record
+ delete $self->{record};
- print "XRFMFB: $XRFMFB XRFMFP: $XRFMFP\n" if ($self->{debug});
+ # read XRFMFB abd XRFMFP
+ read($self->{'fileXRF'}, $buff, 4);
+ my $pointer=unpack("l",$buff) || carp "pointer is null";
+
+ # check for logically deleted record
+ if ($pointer < 0) {
+ print STDERR "## record $mfn is logically deleted\n" if ($self->{debug});
+ $self->{deleted} = $mfn;
- # XXX fix this to be more readable!!
- # e.g. (XRFMFB - 1) * 512 + XRFMFP
+ return unless $self->{include_deleted};
- my $offset = $pointer;
- my $offset2=int($offset/2048)-1;
- my $offset22=int($offset/4096);
- my $offset3=$offset-($offset22*4096);
- if ($offset3>512) {
- $offset3=$offset3-2048;
+ $pointer = abs($pointer);
}
- my $offset4=($offset2*512)+$offset3;
- print "$offset - $offset2 - $offset3 - $offset4\n" if ($self->{debug});
+ my $XRFMFB = int($pointer/2048);
+ my $XRFMFP = $pointer - ($XRFMFB*2048);
+
+ # (XRFMFB - 1) * 512 + XRFMFP
+ # why do i have to do XRFMFP % 1024 ?
- close(fileXRF);
+ my $blk_off = (($XRFMFB - 1) * 512) + ($XRFMFP % 512);
+
+ print STDERR "## pointer: $pointer XRFMFB: $XRFMFB XRFMFP: $XRFMFP offset: $blk_off\n" if ($self->{'debug'});
# Get Record Information
- open(fileMST, $self->{isisdb}.".MST") || croak "can't open '$self->{isisdb}.MST': $!";
+ seek($self->{'fileMST'},$blk_off,0);
- seek(fileMST,$offset4,0);
+ read($self->{'fileMST'}, $buff, 4);
+ my $value=unpack("l",$buff);
- my $value=$self->Read32(\*fileMST);
+ print STDERR "## offset for rowid $value is $blk_off (blk $XRFMFB off $XRFMFP)\n" if ($self->{debug});
if ($value!=$mfn) {
-print ("Error: The MFN:".$mfn." is not found in MST(".$value.")");
- return -1; # XXX deleted record?
- }
+ if ($value == 0) {
+ print STDERR "## record $mfn is physically deleted\n" if ($self->{debug});
+ $self->{deleted} = $mfn;
+ return;
+ }
-# $MFRL=$self->Read16($fileMST);
-# $MFBWB=$self->Read32($fileMST);
-# $MFBWP=$self->Read16($fileMST);
-# $BASE=$self->Read16($fileMST);
-# $NVF=$self->Read16($fileMST);
-# $STATUS=$self->Read16($fileMST);
+ carp "Error: MFN ".$mfn." not found in MST file, found $value";
+ return;
+ }
- my $buff;
- read(fileMST, $buff, 14);
+ read($self->{'fileMST'}, $buff, 14);
my ($MFRL,$MFBWB,$MFBWP,$BASE,$NVF,$STATUS) = unpack("slssss", $buff);
- print "MFRL: $MFRL MFBWB: $MFBWB MFBWP: $MFBWP BASE: $BASE NVF: $NVF STATUS: $STATUS\n" if ($self->{debug});
+ print STDERR "## MFRL: $MFRL MFBWB: $MFBWB MFBWP: $MFBWP BASE: $BASE NVF: $NVF STATUS: $STATUS\n" if ($self->{debug});
+
+ warn "MFRL $MFRL is not even number" unless ($MFRL % 2 == 0);
+
+ warn "BASE is not 18+6*NVF" unless ($BASE == 18 + 6 * $NVF);
# Get Directory Format
my @FieldLEN;
my @FieldTAG;
- for (my $i = 0 ; $i < $NVF ; $i++) {
+ read($self->{'fileMST'}, $buff, 6 * $NVF);
-# $TAG=$self->Read16($fileMST);
-# $POS=$self->Read16($fileMST);
-# $LEN=$self->Read16($fileMST);
+ my $rec_len = 0;
+
+ for (my $i = 0 ; $i < $NVF ; $i++) {
- read(fileMST, $buff, 6);
- my ($TAG,$POS,$LEN) = unpack("sss", $buff);
+ my ($TAG,$POS,$LEN) = unpack("sss", substr($buff,$i * 6, 6));
- print "TAG: $TAG POS: $POS LEN: $LEN\n" if ($self->{debug});
+ print STDERR "## TAG: $TAG POS: $POS LEN: $LEN\n" if ($self->{debug});
# The TAG does not exists in .FDT so we set it to 0.
#
push @FieldTAG,$TAG;
push @FieldPOS,$POS;
push @FieldLEN,$LEN;
+
+ $rec_len += $LEN;
}
# Get Variable Fields
- delete $self->{record};
+ read($self->{'fileMST'},$buff,$rec_len);
+
+ print STDERR "## rec_len: $rec_len poc: ",tell($self->{'fileMST'})."\n" if ($self->{debug});
for (my $i = 0 ; $i < $NVF ; $i++) {
- my $rec;
- read(fileMST,$rec,$FieldLEN[$i]);
- push @{$self->{record}->{$FieldTAG[$i]}}, $rec;
- }
- close(fileMST);
+ # skip zero-sized fields
+ next if ($FieldLEN[$i] == 0);
- # The record is marked for deletion
- if ($STATUS==1) {
- return -1;
+ push @{$self->{record}->{$FieldTAG[$i]}}, substr($buff,$FieldPOS[$i],$FieldLEN[$i]);
}
- print Dumper($self) if ($self->{debug});
+ $self->{'current_mfn'} = $mfn;
+
+ print STDERR Dumper($self),"\n" if ($self->{debug});
return $self->{'record'};
}
=head2 to_ascii
-Dump ascii output of selected MFN
+Returns ASCII output of record with specified MFN
+
+ print $isis->to_ascii(42);
+
+This 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<read_fdt> is specified when calling C<new> it will display field names
+from C<.FDT> file instead of numeric tags.
=cut
my $mfn = shift || croak "need MFN";
- my $rec = $self->GetMFN($mfn);
-
-print STDERR Dumper($rec);
+ my $rec = $self->fetch($mfn);
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";
return $out;
}
-################# old cruft which is not ported from php to perl
-
-=begin php
-
- # Load the dictionary from the $db.L0x files.
- # Not usefull Yet
-
- sub LoadDictionary()
- {
- $fileL01=fopen($self->{isisdb}.".L01","r");
- rewind($fileL01);
-
- do
- {
-
- $POS=$self->Read32($fileL01);
- $OCK=$self->Read16($fileL01);
- $IT=$self->Read16($fileL01);
- $PS=$self->Read32($fileL01);
-print "<br>PS:".$PS." ".$self->{ORDF}->{1}." ";
- for ($i=0;$i<$OCK;$i++)
- {
- $KEY=fread($fileL01,10);
-
- print $KEY." ### ";
-
- $INFO1=$self->Read32($fileL01);
- $INFO2=$self->Read32($fileL01);
-
- #L01Key->{$key}=array($INFO1,$INFO2);
- }
-
- rewind($fileL01);
- $offset=($PS-1)*(12+$self->{ORDF}->{1}*18*2);
- fseek($fileL01,$offset);
-
- } While (!feof($fileL01));
-
- fclose($fileL01);
- }
+=head2 to_hash
- # self function search through the tree and returns an array of pointers to IFP
- # The function must be recursive
-
- sub SearchTree($search,$fileNB,$PUNT)
- {
- $offset=(($PUNT-1)*(8+2*$self->{ORDN}->{1}*14));
-
- rewind($fileNB1);
-
- fseek($fileNB,$offset);
-
- $POS=$self->Read32($fileNB);
- $OCK=$self->Read16($fileNB);
- $IT=$self->Read16($fileNB);
-
-#print "<br>".$POS." - ".$OCK." - ".$IT;
-
- $OLDPUNT=$POS;
- $j=0;
- for ($i=0;$i<$OCK;$i++)
- {
- $KEY=fread($fileNB,10);
-
- $PUNT=$self->Read32($fileNB);
-
-#print " ## ".chop($KEY)."(".$PUNT."-".$OLDPUNT.") ## ";
-
- If (strcmp($search,chop($KEY))<0)
- {
- break;
- }
- $OLDPUNT=$PUNT;
- }
-#print $OLDPUNT;
- Return $OLDPUNT;
- }
+Read record with specified MFN and convert it to hash
- # Search ISIS for record containing search
- # Return a sorted array of MFN
+ my $hash = $isis->to_hash($mfn);
- sub Search($search)
- {
+It has ability to convert characters (using C<hash_filter>) from ISIS
+database before creating structures enabling character re-mapping or quick
+fix-up of data.
- $search=strtoupper($search);
-#print "Searching....".$search." - ".$self->{POSRX}->{1}."<br>";
- # first search .x01
-
-
- # Search in .N01
-
-
- $fileN01=fopen($self->{isisdb}.".N01","r");
- $offset=(($self->{POSRX}->{1}-1)*(8+2*$self->{ORDN}->{1}*14));
-
- do
- {
- rewind($fileN01);
-
- fseek($fileN01,$offset);
-
- $POS=$self->Read32($fileN01);
- $OCK=$self->Read16($fileN01);
- $IT=$self->Read16($fileN01);
-
-#print "<br>".$POS." - ".$OCK." - ".$IT;
-
- $OLDPUNT=$POS;
- for ($i=0;$i<$OCK;$i++)
- {
- $KEY=fread($fileN01,10);
-
- $PUNT=$self->Read32($fileN01);
-
-#print " ## ".chop($KEY)."(".$PUNT."-".$OLDPUNT.") ## ";
-
- If (strcmp($search,chop($KEY))<0)
- {
- break;
- }
- $OLDPUNT=$PUNT;
- }
- $offset=(($OLDPUNT-1)*(8+2*$self->{ORDN}->{1}*14));
- } while ($OLDPUNT>0);
-#print $OLDPUNT;
-
-
- fclose($fileN01);
-
- # Now look for records in .L01 file
- $fileL01=fopen($self->{isisdb}.".L01","r");
- rewind($fileL01);
-
- $offset=(-$OLDPUNT-1)*(12+$self->{ORDF}->{1}*18*2);
- fseek($fileL01,$offset);
-
- $POS=$self->Read32($fileL01);
- $OCK=$self->Read16($fileL01);
- $IT=$self->Read16($fileL01);
- $PS=$self->Read32($fileL01);
-#print "<br>POS:".$POS." ".$self->{ORDF}->{1}." ";
- for ($i=0;$i<$OCK;$i++)
- {
- $KEY=fread($fileL01,10);
-
-#print $KEY." ### ";
-
- $INFO1=$self->Read32($fileL01);
- $INFO2=$self->Read32($fileL01);
-
- If (strcmp($search,chop($KEY))==0)
- {
- break;
- }
- }
-
- fclose($fileL01);
-
-#print $INFO1."--".$INFO2;
-
- # Now look in .IFP for the MFN
- $fileIFP=fopen($self->{isisdb}.".IFP","r");
- rewind($fileIFP);
- $offset=($INFO1-1)*512+($INFO2*4);
- fseek($fileIFP,$offset);
-
- $IFPBLK=$self->Read32($fileIFP);
-
- $IFPNXTB=$self->Read32($fileIFP);
- $IFPNXTP=$self->Read32($fileIFP);
- $IFPTOTP=$self->Read32($fileIFP);
- $IFPSEGP=$self->Read32($fileIFP);
- $IFPSEGC=$self->Read32($fileIFP);
-
-
-#print "<br>IFP:".$IFPBLK." # ".$IFPNXTB." - ".$IFPNXTP." - ".$IFPTOTP." - ".$IFPSEGP." - ".$IFPSEGC;
-
- rewind($fileIFP);
- $offset=($INFO1-1)*512+24+($INFO2*4);
- fseek($fileIFP,$offset);
-
- $j=24+($INFO2*4);
- $k=0;
- $l=1;
- $OLDPMFN="";
- for ($i=0;$i<$IFPSEGP;$i++)
- {
- $B1=$self->Read8($fileIFP);
- $B2=$self->Read8($fileIFP);
- $B3=$self->Read8($fileIFP);
- $B4=$self->Read8($fileIFP);
- $B5=$self->Read8($fileIFP);
- $B6=$self->Read8($fileIFP);
- $B7=$self->Read8($fileIFP);
- $B8=$self->Read8($fileIFP);
-
- $PMFN=$B1*65536+$B2*256+$B3;
- $PTAG=$B4*256+$B5;
- $POCC=$B6;
- $PCNT=$B7*256+$B8;
-
- if ($OLDPMFN!=$PMFN)
- {
- if ($PMFN!=0)
- {
- $self->{MFNArray}->{$l}=$PMFN;
- $OLDPMFN=$PMFN;
- $l+=1;
- }
- }
-
- $j=$j+8;
-#print "<br>".$PMFN."-".$PTAG." - ".$POCC." - ".$PCNT;
-#print "@@".$j."@@@@";
- if ($j>=504)
- {
- if ($IFPNXTB==0 && $IFPNXTP==0)
- {
- $k=$k+1;
- rewind($fileIFP);
- $offset=($INFO1-1+$k)*512;
- fseek($fileIFP,$offset);
- $B=$self->Read32($fileIFP);
-#print "<br>-".$B."-<br>";
- $j=0;
- } else
- {
- rewind($fileIFP);
- $offset=($IFPNXTB-1)*512;
- fseek($fileIFP,$offset);
-
- $OLDIFPNXTB=$IFPNXTB;
- $OLDIFPNXTP=$IFPNXTP;
-
- $IFPBLK=$self->Read32($fileIFP);
-
- $IFPNXTB=$self->Read32($fileIFP);
- $IFPNXTP=$self->Read32($fileIFP);
- $IFPTOTP=$self->Read32($fileIFP);
- $IFPSEGP=$self->Read32($fileIFP);
- $IFPSEGC=$self->Read32($fileIFP);
-
- rewind($fileIFP);
- $offset=($OLDIFPNXTB-1)*512+24+($OLDIFPNXTP*4);
- fseek($fileIFP,$offset);
-
- $j=24+($OLDIFPNXTP*4);
- $k=0;
- $j=0;
- }
- }
-
- }
- fclose($fileIFP);
- return $l-1;
- }
+This function returns hash which is like this:
-=cut
+ $hash = {
+ '210' => [
+ {
+ 'c' => 'New York University press',
+ 'a' => 'New York',
+ 'd' => 'cop. 1988'
+ }
+ ],
+ '990' => [
+ '2140',
+ '88',
+ 'HAY'
+ ],
+ };
-#
-# XXX porting from php left-over:
-#
-# do I *REALLY* need those methods, or should I use
-# $self->{something} directly?
-#
-# Probably direct usage is better!
-#
+You can later use that hash to produce any output from ISIS data.
-sub GetFieldName {
- my $self = shift;
- return $self->{FieldName};
-}
+If database is created using IsisMarc, it will also have to special fields
+which will be used for identifiers, C<i1> and C<i2> like this:
-sub GetTagName {
- my $self = shift;
- return $self->{TagName};
-}
+ '200' => [
+ {
+ 'i1' => '1',
+ 'i2' => ' '
+ 'a' => 'Goa',
+ 'f' => 'Valdo D\'Arienzo',
+ 'e' => 'tipografie e tipografi nel XVI secolo',
+ }
+ ],
-sub GetFieldTag {
- my $self = shift;
- return $self->{FieldTAG};
-}
+This method will also create additional field C<000> with MFN.
-sub GetNextMFN {
- my $self = shift;
- return $self->{NXTMFN};
-}
+=cut
-sub GetMFNArray {
+sub to_hash {
my $self = shift;
- return $self->{MFNArray};
-}
-=begin php
-
- sub Read32($fileNB)
- {
- $B1=ord(fread($fileNB,1));
- $B2=ord(fread($fileNB,1));
- $B3=ord(fread($fileNB,1));
- $B4=ord(fread($fileNB,1));
-
- if ($B4<=128)
- {
- $value=$B1+$B2*256+$B3*65536+$B4*16777216;
- } else
- {
- $value=$self->Not8($B1)+$self->Not8($B2)*256+$self->Not8($B3)*65536+$self->Not8($B4)*16777216;
- $value=-($value+1);
- }
-# print "(".$B1.",".$B2.",".$B3.",".$B4.":".$value.")";
-
- return $value;
- }
- sub Read24($fileNB)
- {
- $B1=ord(fread($fileNB,1));
- $B2=ord(fread($fileNB,1));
- $B3=ord(fread($fileNB,1));
+ my $mfn = shift || confess "need mfn!";
- $value=$B1+$B2*256+$B3*65536;
+ # init record to include MFN as field 000
+ my $rec = { '000' => [ $mfn ] };
-# print "(".$B1.",".$B2.",".$B3.":".$value.")";
+ my $row = $self->fetch($mfn);
- return $value;
- }
-
- sub Read16($fileNB)
- {
- $B1=ord(fread($fileNB,1));
- $B2=ord(fread($fileNB,1));
+ foreach my $k (keys %{$row}) {
+ foreach my $l (@{$row->{$k}}) {
- $value=$B1+$B2*256;
-# print "(".$B1.",".$B2.":".$value.")";
+ # filter output
+ $l = $self->{'hash_filter'}->($l) if ($self->{'hash_filter'});
- return $value;
- }
+ my $val;
- sub Read8($fileNB)
- {
- $B1=ord(fread($fileNB,1));
+ # has identifiers?
+ ($val->{'i1'},$val->{'i2'}) = ($1,$2) if ($l =~ s/^([01 #])([01 #])\^/\^/);
- $value=$B1;
-# print "(".$value.")";
+ # has subfields?
+ if ($l =~ m/\^/) {
+ foreach my $t (split(/\^/,$l)) {
+ next if (! $t);
+ $val->{substr($t,0,1)} = substr($t,1);
+ }
+ } else {
+ $val = $l;
+ }
- return $value;
- }
+ push @{$rec->{$k}}, $val;
+ }
+ }
- sub Not8($value)
- {
- $value=decbin($value);
- if (strlen($value)<8)
- {
- $buffer="";
- for($i=0;$i<(8-strlen($value));$i++)
- {
- $buffer.="0";
- }
- $value=$buffer.$value;
- }
- $value=ereg_replace("0","3",$value);
- $value=ereg_replace("1","0",$value);
- $value=ereg_replace("3","1",$value);
- $value=bindec($value);
- return $value;
- }
+ return $rec;
}
+=head2 tag_name
+
+Return name of selected tag
+
+ print $isis->tag_name('200');
+
=cut
+sub tag_name {
+ my $self = shift;
+ my $tag = shift || return;
+ return $self->{'TagName'}->{$tag} || $tag;
+}
+
1;
-__END__
=head1 BUGS
-This module has been very lightly tested. Use with caution and report bugs.
+Some parts of CDS/ISIS documentation are not detailed enough to exmplain
+some variations in input databases which has been tested with this module.
+When I was in doubt, I assumed that OpenIsis's implementation was right
+(except for obvious bugs).
+
+However, every effort has been made to test this module with as much
+databases (and programs that create them) as possible.
+
+I would be very greatful for success or failure reports about usage of this
+module with databases from programs other than WinIsis and IsisMarc. I had
+tested this against ouput of one C<isis.dll>-based application, but I don't
+know any details about it's version.
=head1 AUTHOR
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 - <franck@sopac.org> released under LGPL.
+This module is based heavily on code from C<LIBISIS.PHP> library to read ISIS files V0.1.1
+written in php and (c) 2000 Franck Martin <franck@sopac.org> and released under LGPL.
=head1 COPYRIGHT
=head1 SEE ALSO
-L<http://www.openisis.org|OpenIsis>, perl(1).
+OpenIsis web site L<http://www.openisis.org>
+
+perl4lib site L<http://perl4lib.perl.org>