/[Biblio-Isis]/trunk/lib/Biblio/Isis.pm
This is repository of my old source code which isn't updated any more. Go to git.rot13.org for current projects!
ViewVC logotype

Diff of /trunk/lib/Biblio/Isis.pm

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

trunk/IsisDB.pm revision 10 by dpavlin, Wed Dec 29 16:04:07 2004 UTC trunk/lib/Biblio/Isis.pm revision 41 by dpavlin, Sat Mar 12 21:05:29 2005 UTC
# Line 1  Line 1 
1  package IsisDB;  package Biblio::Isis;
2  use strict;  use strict;
3    
4  use Carp;  use Carp;
5    use File::Glob qw(:globally :nocase);
6    
7  use Data::Dumper;  use Data::Dumper;
8    
9  BEGIN {  BEGIN {
10          use Exporter ();          use Exporter ();
11          use vars qw ($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS);          use vars qw ($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS);
12          $VERSION     = 0.03;          $VERSION     = 0.13;
13          @ISA         = qw (Exporter);          @ISA         = qw (Exporter);
14          #Give a hoot don't pollute, do not export more than needed by default          #Give a hoot don't pollute, do not export more than needed by default
15          @EXPORT      = qw ();          @EXPORT      = qw ();
# Line 18  BEGIN { Line 20  BEGIN {
20    
21  =head1 NAME  =head1 NAME
22    
23  IsisDB - Read CDS/ISIS database  Biblio::Isis - Read CDS/ISIS, WinISIS and IsisMarc database
24    
25  =head1 SYNOPSIS  =head1 SYNOPSIS
26    
27    use IsisDB    use Biblio::Isis;
28    my $isis = new IsisDB(  
29      my $isis = new Biblio::Isis(
30          isisdb => './cds/cds',          isisdb => './cds/cds',
31    );    );
32    
33      for(my $mfn = 1; $mfn <= $isis->count; $mfn++) {
34            print $isis->to_ascii($mfn),"\n";
35      }
36    
37  =head1 DESCRIPTION  =head1 DESCRIPTION
38    
39  This module will read CDS/ISIS databases and create hash values out of it.  This module will read ISIS databases created by DOS CDS/ISIS, WinIsis or
40  It can be used as perl-only alternative to OpenIsis module.  IsisMarc. It can be used as perl-only alternative to OpenIsis module which
41    seems to depriciate it's old C<XS> bindings for perl.
42    
43    It can create hash values from data in ISIS database (using C<to_hash>),
44    ASCII dump (using C<to_ascii>) or just hash with field names and packed
45    values (like C<^asomething^belse>).
46    
47    Unique feature of this module is ability to C<include_deleted> records.
48    It will also skip zero sized fields (OpenIsis has a bug in XS bindings, so
49    fields which are zero sized will be filled with random junk from memory).
50    
51    It also has support for identifiers (only if ISIS database is created by
52    IsisMarc), see C<to_hash>.
53    
54    This module will always be slower than OpenIsis module which use C
55    library. However, since it's written in perl, it's platform independent (so
56    you don't need C compiler), and can be easily modified. I hope that it
57    creates data structures which are easier to use than ones created by
58    OpenIsis, so reduced time in other parts of the code should compensate for
59    slower performance of this module (speed of reading ISIS database is
60    rarely an issue).
61    
62  =head1 METHODS  =head1 METHODS
63    
# Line 50  It can be used as perl-only alternative Line 77  It can be used as perl-only alternative
77  # some binary reads  # some binary reads
78  #  #
79    
 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);  
 }  
   
80  =head2 new  =head2 new
81    
82  Open CDS/ISIS database  Open ISIS database
83    
84   my $isis = new IsisDB(   my $isis = new Biblio::Isis(
85          isisdb => './cds/cds',          isisdb => './cds/cds',
86          read_fdt => 1,          read_fdt => 1,
         debug => 1,  
87          include_deleted => 1,          include_deleted => 1,
88            hash_filter => sub {
89                    my $v = shift;
90                    $v =~ s#foo#bar#g;
91            },
92            debug => 1,
93   );   );
94    
95  Options are described below:  Options are described below:
# Line 75  Options are described below: Line 98  Options are described below:
98    
99  =item isisdb  =item isisdb
100    
101  Prefix path to CDS/ISIS. It should contain full or relative path to database  This is full or relative path to ISIS database files which include
102  and common prefix of C<.FDT>, C<.MST>, C<.CNT>, C<.XRF> and C<.MST> files.  common prefix of C<.MST>, and C<.XRF> and optionally C<.FDT> (if using
103    C<read_fdt> option) files.
104    
105    In this example it uses C<./cds/cds.MST> and related files.
106    
107  =item read_fdt  =item read_fdt
108    
109  Boolean flag to specify if field definition table should be read. It's off  Boolean flag to specify if field definition table should be read. It's off
110  by default.  by default.
111    
112  =item debug  =item include_deleted
113    
114  Dump a C<lot> of debugging output.  Don't skip logically deleted records in ISIS.
115    
116  =item include_deleted  =item hash_filter
117    
118  Don't skip logically deleted records.  Filter code ref which will be used before data is converted to hash.
119    
120  =back  =item debug
121    
122    Dump a B<lot> of debugging output.
123    
124  It will also set C<$isis-E<gt>{'maxmfn'}> which is maximum MFN stored in database.  =back
125    
126  =cut  =cut
127    
# Line 104  sub new { Line 132  sub new {
132    
133          croak "new needs database name (isisdb) as argument!" unless ({@_}->{isisdb});          croak "new needs database name (isisdb) as argument!" unless ({@_}->{isisdb});
134    
135          foreach my $v (qw{isisdb debug include_deleted}) {          foreach my $v (qw{isisdb debug include_deleted hash_filter}) {
136                  $self->{$v} = {@_}->{$v};                  $self->{$v} = {@_}->{$v};
137          }          }
138    
139            my @isis_files = grep(/\.(FDT|MST|XRF|CNT)$/i,glob($self->{isisdb}."*"));
140    
141            foreach my $f (@isis_files) {
142                    my $ext = $1 if ($f =~ m/\.(\w\w\w)$/);
143                    $self->{lc($ext)."_file"} = $f;
144            }
145    
146            my @must_exist = qw(mst xrf);
147            push @must_exist, "fdt" if ($self->{read_fdt});
148    
149            foreach my $ext (@must_exist) {
150                    unless ($self->{$ext."_file"}) {
151                            carp "missing ",uc($ext)," file in ",$self->{isisdb};
152                            return;
153                    }
154            }
155    
156            print STDERR "## using files: ",join(" ",@isis_files),"\n" if ($self->{debug});
157    
158          # if you want to read .FDT file use read_fdt argument when creating class!          # if you want to read .FDT file use read_fdt argument when creating class!
159          if ({@_}->{read_fdt} && -e $self->{isisdb}.".FDT") {          if ($self->{read_fdt} && -e $self->{fdt_file}) {
160    
161                  # read the $db.FDT file for tags                  # read the $db.FDT file for tags
162                  my $fieldzone=0;                  my $fieldzone=0;
163    
164                  open(fileFDT, $self->{isisdb}.".FDT") || croak "can't read '$self->{isisdb}.FDT': $!";                  open(my $fileFDT, $self->{fdt_file}) || croak "can't read '$self->{fdt_file}': $!";
165                    binmode($fileFDT);
166    
167                  while (<fileFDT>) {                  while (<$fileFDT>) {
168                          chomp;                          chomp;
169                          if ($fieldzone) {                          if ($fieldzone) {
170                                  my $name=substr($_,0,30);                                  my $name=substr($_,0,30);
# Line 133  sub new { Line 181  sub new {
181                          }                          }
182                  }                  }
183                                    
184                  close(fileFDT);                  close($fileFDT);
185          }          }
186    
187          # Get the Maximum MFN from $db.MST          # Get the Maximum MFN from $db.MST
188    
189          open(fileMST,$self->{isisdb}.".MST") || croak "can't read '$self->{isisdb}.MST': $!";          open($self->{'fileMST'}, $self->{mst_file}) || croak "can't open '$self->{mst_file}': $!";
190            binmode($self->{'fileMST'});
191    
192          # MST format:   (* = 32 bit signed)          # MST format:   (* = 32 bit signed)
193          # CTLMFN*       always 0          # CTLMFN*       always 0
# Line 146  sub new { Line 195  sub new {
195          # NXTMFB*       last block allocated to master file          # NXTMFB*       last block allocated to master file
196          # NXTMFP        offset to next available position in last block          # NXTMFP        offset to next available position in last block
197          # MFTYPE        always 0 for user db file (1 for system)          # MFTYPE        always 0 for user db file (1 for system)
198          seek(fileMST,4,0);          seek($self->{'fileMST'},4,0) || croak "can't seek to offset 0 in MST: $!";
         $self->{'NXTMFN'}=$self->Read32(\*fileMST) || carp "NXTNFN is zero";  
   
         # save maximum MFN  
         $self->{'maxmfn'} = $self->{'NXTMFN'} - 1;  
   
         close(fileMST);  
199    
200          # Get the index information from $db.CNT          my $buff;
     
         open(fileCNT, $self->{isisdb}.".CNT") || croak "can't read '$self->{isisdb}.CNT': $!";  
   
         # There is two 26 Bytes fixed lenght records  
201    
202          #  0: IDTYPE    BTree type                              16          read($self->{'fileMST'}, $buff, 4) || croak "can't read NXTMFN from MST: $!";
203          #  2: ORDN      Nodes Order                             16          $self->{'NXTMFN'}=unpack("V",$buff) || croak "NXTNFN is zero";
         #  4: ORDF      Leafs Order                             16  
         #  6: N         Number of Memory buffers for nodes      16  
         #  8: K         Number of buffers for first level index 16  
         # 10: LIV       Current number of Index Levels          16  
         # 12: POSRX*    Pointer to Root Record in N0x           32  
         # 16: NMAXPOS*  Next Available position in N0x          32  
         # 20: FMAXPOS*  Next available position in L0x          32  
         # 24: ABNORMAL  Formal BTree normality indicator        16  
         # length: 26 bytes  
   
         sub unpack_cnt {  
                 my $self = shift;  
   
                 my @flds = qw(ORDN ORDF N K LIV POSRX NMAXPOS FMAXPOS ABNORMAL);  
   
                 my $buff = shift || return;  
                 my @arr = unpack("ssssssllls", $buff);  
   
                 print "unpack_cnt: ",join(" ",@arr),"\n" if ($self->{'debug'});  
   
                 my $IDTYPE = shift @arr;  
                 foreach (@flds) {  
                         $self->{$IDTYPE}->{$_} = abs(shift @arr);  
                 }  
         }  
204    
205          my $buff;          print STDERR Dumper($self),"\n" if ($self->{debug});
         read(fileCNT, $buff, 26);  
         $self->unpack_cnt($buff);  
206    
207          read(fileCNT, $buff, 26);          # open files for later
208          $self->unpack_cnt($buff);          open($self->{'fileXRF'}, $self->{xrf_file}) || croak "can't open '$self->{xrf_file}': $!";
209            binmode($self->{'fileXRF'});
210    
211            $self ? return $self : return undef;
212    }
213    
214          close(fileCNT);  =head2 count
215    
216          print Dumper($self) if ($self->{debug});  Return number of records in database
217    
218          # open files for later    print $isis->count;
         open($self->{'fileXRF'}, $self->{isisdb}.".XRF") || croak "can't open '$self->{isisdb}.XRF': $!";  
219    
220          open($self->{'fileMST'}, $self->{isisdb}.".MST") || croak "can't open '$self->{isisdb}.MST': $!";  =cut
221    
222          $self ? return $self : return undef;  sub count {
223            my $self = shift;
224            return $self->{'NXTMFN'} - 1;
225  }  }
226    
227  =head2 fetch  =head2 fetch
# Line 215  Read record with selected MFN Line 231  Read record with selected MFN
231    my $rec = $isis->fetch(55);    my $rec = $isis->fetch(55);
232    
233  Returns hash with keys which are field names and values are unpacked values  Returns hash with keys which are field names and values are unpacked values
234  for that field.  for that field like this:
235    
236      $rec = {
237        '210' => [ '^aNew York^cNew York University press^dcop. 1988' ],
238        '990' => [ '2140', '88', 'HAY' ],
239      };
240    
241  =cut  =cut
242    
# Line 224  sub fetch { Line 245  sub fetch {
245    
246          my $mfn = shift || croak "fetch needs MFN as argument!";          my $mfn = shift || croak "fetch needs MFN as argument!";
247    
248          print "fetch: $mfn\n" if ($self->{debug});          # is mfn allready in memory?
249            my $old_mfn = $self->{'current_mfn'} || -1;
250            return $self->{record} if ($mfn == $old_mfn);
251    
252            print STDERR "## fetch: $mfn\n" if ($self->{debug});
253    
254          # XXX check this?          # XXX check this?
255          my $mfnpos=($mfn+int(($mfn-1)/127))*4;          my $mfnpos=($mfn+int(($mfn-1)/127))*4;
256    
257          print "seeking to $mfnpos in file '$self->{isisdb}.XRF'\n" if ($self->{debug});          print STDERR "## seeking to $mfnpos in file '$self->{xrf_file}'\n" if ($self->{debug});
258          seek($self->{'fileXRF'},$mfnpos,0);          seek($self->{'fileXRF'},$mfnpos,0);
259    
260            my $buff;
261    
262            # delete old record
263            delete $self->{record};
264    
265          # read XRFMFB abd XRFMFP          # read XRFMFB abd XRFMFP
266          my $pointer=$self->Read32(\*{$self->{'fileXRF'}});          read($self->{'fileXRF'}, $buff, 4);
267            my $pointer=unpack("V",$buff);
268            if (! $pointer) {
269                    if ($self->{include_deleted}) {
270                            return;
271                    } else {
272                            warn "pointer for MFN $mfn is null\n";
273                            return;
274                    }
275            }
276    
277            # check for logically deleted record
278            if ($pointer & 0x80000000) {
279                    print STDERR "## record $mfn is logically deleted\n" if ($self->{debug});
280                    $self->{deleted} = $mfn;
281    
282                    return unless $self->{include_deleted};
283    
284                    # abs
285                    $pointer = ($pointer ^ 0xffffffff) + 1;
286            }
287    
288          my $XRFMFB = int($pointer/2048);          my $XRFMFB = int($pointer/2048);
289          my $XRFMFP = $pointer - ($XRFMFB*2048);          my $XRFMFP = $pointer - ($XRFMFB*2048);
290    
291          print "XRFMFB: $XRFMFB XRFMFP: $XRFMFP\n" if ($self->{debug});          # (XRFMFB - 1) * 512 + XRFMFP
292            # why do i have to do XRFMFP % 1024 ?
293    
294          # XXX fix this to be more readable!!          my $blk_off = (($XRFMFB - 1) * 512) + ($XRFMFP % 512);
         # e.g. (XRFMFB - 1) * 512 + XRFMFP  
   
         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;  
         }  
         my $offset4=($offset2*512)+$offset3;  
295    
296          print "$offset - $offset2 - $offset3 - $offset4\n" if ($self->{debug});          print STDERR "## pointer: $pointer XRFMFB: $XRFMFB XRFMFP: $XRFMFP offset: $blk_off\n" if ($self->{'debug'});
297    
298          # Get Record Information          # Get Record Information
299    
300          seek($self->{'fileMST'},$offset4,0);          seek($self->{'fileMST'},$blk_off,0) || croak "can't seek to $blk_off: $!";
301    
302          my $value=$self->Read32(\*{$self->{'fileMST'}});          read($self->{'fileMST'}, $buff, 4) || croak "can't read 4 bytes at offset $blk_off from MST file: $!";
303            my $value=unpack("V",$buff);
304    
305            print STDERR "## offset for rowid $value is $blk_off (blk $XRFMFB off $XRFMFP)\n" if ($self->{debug});
306    
307          if ($value!=$mfn) {          if ($value!=$mfn) {
308  print ("Error: The MFN:".$mfn." is not found in MST(".$value.")");                      if ($value == 0) {
309                  return -1;      # XXX deleted record?                          print STDERR "## record $mfn is physically deleted\n" if ($self->{debug});
310          }                          $self->{deleted} = $mfn;
311                            return;
312                    }
313    
314  #       $MFRL=$self->Read16($fileMST);                  carp "Error: MFN ".$mfn." not found in MST file, found $value";    
315  #       $MFBWB=$self->Read32($fileMST);                  return;
316  #       $MFBWP=$self->Read16($fileMST);          }
 #       $BASE=$self->Read16($fileMST);  
 #       $NVF=$self->Read16($fileMST);  
 #       $STATUS=$self->Read16($fileMST);  
317    
         my $buff;  
318          read($self->{'fileMST'}, $buff, 14);          read($self->{'fileMST'}, $buff, 14);
319    
320          my ($MFRL,$MFBWB,$MFBWP,$BASE,$NVF,$STATUS) = unpack("slssss", $buff);          my ($MFRL,$MFBWB,$MFBWP,$BASE,$NVF,$STATUS) = unpack("vVvvvv", $buff);
321    
322          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});
323    
324          # delete old record          warn "MFRL $MFRL is not even number" unless ($MFRL % 2 == 0);
         delete $self->{record};  
325    
326          if (! $self->{'include_deleted'} && $MFRL < 0) {          warn "BASE is not 18+6*NVF" unless ($BASE == 18 + 6 * $NVF);
                 print "## logically deleted record $mfn, skipping...\n" if ($self->{debug});  
                 return;  
         }  
327    
328          # Get Directory Format          # Get Directory Format
329    
# Line 295  print ("Error: The MFN:".$mfn." is not f Line 333  print ("Error: The MFN:".$mfn." is not f
333    
334          read($self->{'fileMST'}, $buff, 6 * $NVF);          read($self->{'fileMST'}, $buff, 6 * $NVF);
335    
336          my $fld_len = 0;          my $rec_len = 0;
337    
338          for (my $i = 0 ; $i < $NVF ; $i++) {          for (my $i = 0 ; $i < $NVF ; $i++) {
339    
340  #               $TAG=$self->Read16($fileMST);                  my ($TAG,$POS,$LEN) = unpack("vvv", substr($buff,$i * 6, 6));
 #               $POS=$self->Read16($fileMST);  
 #               $LEN=$self->Read16($fileMST);  
341    
342                  my ($TAG,$POS,$LEN) = unpack("sss", substr($buff,$i * 6, 6));                  print STDERR "## TAG: $TAG POS: $POS LEN: $LEN\n" if ($self->{debug});
   
                 print "TAG: $TAG POS: $POS LEN: $LEN\n" if ($self->{debug});  
343    
344                  # The TAG does not exists in .FDT so we set it to 0.                  # The TAG does not exists in .FDT so we set it to 0.
345                  #                  #
# Line 321  print ("Error: The MFN:".$mfn." is not f Line 355  print ("Error: The MFN:".$mfn." is not f
355                  push @FieldPOS,$POS;                  push @FieldPOS,$POS;
356                  push @FieldLEN,$LEN;                  push @FieldLEN,$LEN;
357    
358                  $fld_len += $LEN;                  $rec_len += $LEN;
359          }          }
360    
361          # Get Variable Fields          # Get Variable Fields
362    
363          read($self->{'fileMST'},$buff,$fld_len);          read($self->{'fileMST'},$buff,$rec_len);
364    
365            print STDERR "## rec_len: $rec_len poc: ",tell($self->{'fileMST'})."\n" if ($self->{debug});
366    
367          for (my $i = 0 ; $i < $NVF ; $i++) {          for (my $i = 0 ; $i < $NVF ; $i++) {
368                  # skip zero-sized fields                  # skip zero-sized fields
# Line 334  print ("Error: The MFN:".$mfn." is not f Line 370  print ("Error: The MFN:".$mfn." is not f
370    
371                  push @{$self->{record}->{$FieldTAG[$i]}}, substr($buff,$FieldPOS[$i],$FieldLEN[$i]);                  push @{$self->{record}->{$FieldTAG[$i]}}, substr($buff,$FieldPOS[$i],$FieldLEN[$i]);
372          }          }
         close(fileMST);  
373    
374          print Dumper($self) if ($self->{debug});          $self->{'current_mfn'} = $mfn;
375    
376            print STDERR Dumper($self),"\n" if ($self->{debug});
377    
378          return $self->{'record'};          return $self->{'record'};
379  }  }
380    
381  =head2 to_ascii  =head2 to_ascii
382    
383  Dump ascii output of selected MFN  Returns ASCII output of record with specified MFN
384    
385      print $isis->to_ascii(42);
386    
387    This outputs something like this:
388    
389    print $isis->to_ascii(55);    210   ^aNew York^cNew York University press^dcop. 1988
390      990   2140
391      990   88
392      990   HAY
393    
394    If C<read_fdt> is specified when calling C<new> it will display field names
395    from C<.FDT> file instead of numeric tags.
396    
397  =cut  =cut
398    
# Line 354  sub to_ascii { Line 401  sub to_ascii {
401    
402          my $mfn = shift || croak "need MFN";          my $mfn = shift || croak "need MFN";
403    
404          my $rec = $self->fetch($mfn);          my $rec = $self->fetch($mfn) || return;
405    
406          my $out = "0\t$mfn";          my $out = "0\t$mfn";
407    
408          foreach my $f (sort keys %{$rec}) {          foreach my $f (sort keys %{$rec}) {
409                  $out .= "\n$f\t".join("\n$f\t",@{$self->{record}->{$f}});                  my $fn = $self->tag_name($f);
410                    $out .= "\n$fn\t".join("\n$fn\t",@{$self->{record}->{$f}});
411          }          }
412    
413          $out .= "\n";          $out .= "\n";
# Line 367  sub to_ascii { Line 415  sub to_ascii {
415          return $out;          return $out;
416  }  }
417    
418  #  =head2 to_hash
419  # XXX porting from php left-over:  
420  #  Read record with specified MFN and convert it to hash
421  # do I *REALLY* need those methods, or should I use  
422  # $self->{something} directly?    my $hash = $isis->to_hash($mfn);
423  #  
424  # Probably direct usage is better!  It has ability to convert characters (using C<hash_filter>) from ISIS
425  #  database before creating structures enabling character re-mapping or quick
426    fix-up of data.
427    
428    This function returns hash which is like this:
429    
430      $hash = {
431        '210' => [
432                   {
433                     'c' => 'New York University press',
434                     'a' => 'New York',
435                     'd' => 'cop. 1988'
436                   }
437                 ],
438        '990' => [
439                   '2140',
440                   '88',
441                   'HAY'
442                 ],
443      };
444    
445    You can later use that hash to produce any output from ISIS data.
446    
447    If database is created using IsisMarc, it will also have to special fields
448    which will be used for identifiers, C<i1> and C<i2> like this:
449    
450      '200' => [
451                 {
452                   'i1' => '1',
453                   'i2' => ' '
454                   'a' => 'Goa',
455                   'f' => 'Valdo D\'Arienzo',
456                   'e' => 'tipografie e tipografi nel XVI secolo',
457                 }
458               ],
459    
460    This method will also create additional field C<000> with MFN.
461    
462    =cut
463    
464    sub to_hash {
465            my $self = shift;
466    
467            my $mfn = shift || confess "need mfn!";
468    
469            # init record to include MFN as field 000
470            my $rec = { '000' => [ $mfn ] };
471    
472            my $row = $self->fetch($mfn) || return;
473    
474            foreach my $k (keys %{$row}) {
475                    foreach my $l (@{$row->{$k}}) {
476    
477                            # filter output
478                            $l = $self->{'hash_filter'}->($l) if ($self->{'hash_filter'});
479    
480                            my $val;
481    
482                            # has identifiers?
483                            ($val->{'i1'},$val->{'i2'}) = ($1,$2) if ($l =~ s/^([01 #])([01 #])\^/\^/);
484    
485                            # has subfields?
486                            if ($l =~ m/\^/) {
487                                    foreach my $t (split(/\^/,$l)) {
488                                            next if (! $t);
489                                            $val->{substr($t,0,1)} = substr($t,1);
490                                    }
491                            } else {
492                                    $val = $l;
493                            }
494    
495                            push @{$rec->{$k}}, $val;
496                    }
497            }
498    
499            return $rec;
500    }
501    
502    =head2 tag_name
503    
504    Return name of selected tag
505    
506     print $isis->tag_name('200');
507    
508    =cut
509    
510  sub TagName {  sub tag_name {
511          my $self = shift;          my $self = shift;
512          return $self->{TagName};          my $tag = shift || return;
513            return $self->{'TagName'}->{$tag} || $tag;
514  }  }
515    
516  sub NextMFN {  
517    =head2 read_cnt
518    
519    Read content of C<.CNT> file and return hash containing it.
520    
521      print Dumper($isis->read_cnt);
522    
523    This function is not used by module (C<.CNT> files are not required for this
524    module to work), but it can be useful to examine your index (while debugging
525    for example).
526    
527    =cut
528    
529    sub read_cnt  {
530          my $self = shift;          my $self = shift;
531          return $self->{NXTMFN};  
532            croak "missing CNT file in ",$self->{isisdb} unless ($self->{cnt_file});
533    
534            # Get the index information from $db.CNT
535      
536            open(my $fileCNT, $self->{cnt_file}) || croak "can't read '$self->{cnt_file}': $!";
537            binmode($fileCNT);
538    
539            my $buff;
540    
541            read($fileCNT, $buff, 26) || croak "can't read first table from CNT: $!";
542            $self->unpack_cnt($buff);
543    
544            read($fileCNT, $buff, 26) || croak "can't read second table from CNT: $!";
545            $self->unpack_cnt($buff);
546    
547            close($fileCNT);
548    
549            return $self->{cnt};
550    }
551    
552    =head2 unpack_cnt
553    
554    Unpack one of two 26 bytes fixed length record in C<.CNT> file.
555    
556    Here is definition of record:
557    
558     off key        description                             size
559      0: IDTYPE     BTree type                              s
560      2: ORDN       Nodes Order                             s
561      4: ORDF       Leafs Order                             s
562      6: N          Number of Memory buffers for nodes      s
563      8: K          Number of buffers for first level index s
564     10: LIV        Current number of Index Levels          s
565     12: POSRX      Pointer to Root Record in N0x           l
566     16: NMAXPOS    Next Available position in N0x          l
567     20: FMAXPOS    Next available position in L0x          l
568     24: ABNORMAL   Formal BTree normality indicator        s
569     length: 26 bytes
570    
571    This will fill C<$self> object under C<cnt> with hash. It's used by C<read_cnt>.
572    
573    =cut
574    
575    sub unpack_cnt {
576            my $self = shift;
577    
578            my @flds = qw(ORDN ORDF N K LIV POSRX NMAXPOS FMAXPOS ABNORMAL);
579    
580            my $buff = shift || return;
581            my @arr = unpack("vvvvvvVVVv", $buff);
582    
583            print STDERR "unpack_cnt: ",join(" ",@arr),"\n" if ($self->{'debug'});
584    
585            my $IDTYPE = shift @arr;
586            foreach (@flds) {
587                    $self->{cnt}->{$IDTYPE}->{$_} = abs(shift @arr);
588            }
589  }  }
590    
591  1;  1;
592    
593  =head1 BUGS  =head1 BUGS
594    
595  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
596    some variations in input databases which has been tested with this module.
597    When I was in doubt, I assumed that OpenIsis's implementation was right
598    (except for obvious bugs).
599    
600    However, every effort has been made to test this module with as much
601    databases (and programs that create them) as possible.
602    
603    I would be very greatful for success or failure reports about usage of this
604    module with databases from programs other than WinIsis and IsisMarc. I had
605    tested this against ouput of one C<isis.dll>-based application, but I don't
606    know any details about it's version.
607    
608  =head1 AUTHOR  =head1 AUTHOR
609    
# Line 399  This module has been very lightly tested Line 612  This module has been very lightly tested
612          dpavlin@rot13.org          dpavlin@rot13.org
613          http://www.rot13.org/~dpavlin/          http://www.rot13.org/~dpavlin/
614    
615  This module is based heavily on code from LIBISIS.PHP - Library to read ISIS files V0.1.1  This module is based heavily on code from C<LIBISIS.PHP> library to read ISIS files V0.1.1
616  written in php and (c) 2000 Franck Martin - <franck@sopac.org> released under LGPL.  written in php and (c) 2000 Franck Martin <franck@sopac.org> and released under LGPL.
617    
618  =head1 COPYRIGHT  =head1 COPYRIGHT
619    
# Line 413  LICENSE file included with this module. Line 626  LICENSE file included with this module.
626    
627  =head1 SEE ALSO  =head1 SEE ALSO
628    
629  L<http://www.openisis.org|OpenIsis>, perl(1).  OpenIsis web site L<http://www.openisis.org>
630    
631    perl4lib site L<http://perl4lib.perl.org>
632    
Legend:
Removed from v.10  
changed lines
  Added in v.41
  ViewVC Help
Powered by ViewVC 1.1.26