Re: converting data for subfields in 1XX

[email protected] ("Saiful Amin") Fri, 10 Nov 2006 20:52:08 +0530

Newsgroups	perl.perl4lib
Message-ID	<[email protected]>

Hi Jackie,

Sorry for the delay, I was travelling past one week and couldn't get my hand
on this one. I've done two changes and it works now. Attached is the edited
script.

1. Pipe (|) is a special character in Perl and it needs to escaped (\|) on
line 88.
2. I'm not sure on the 'binmode' function to work on this module. I guess
you might have to use MARC::Charset::UTF8 or something similar.

Hope this helps.

Cheers,
Saiful


On 11/3/06, Jackie Shieh <[email protected]> wrote:
>
>
> Here is what I have... not working ver well.
> See attached.
>
> perl: pam2.pl
> input: FpamTest.txt
> outpu: Testout.dat
>
>
> On Thu, 2 Nov 2006, Saiful Amin wrote:
>
> > Hi,
> >
> > Can you share your code?
> >
> > -Saiful
> >
> > On 11/2/06, Jackie Shieh <[email protected]> wrote:
> >>
> >>
> >> I have a tab delimited text file of 8 columns.  Its 1st column
> >> contains author entry (most are main entry, others not) like
> >> this below.
> >>
> >>
> >> 1001 |a Du Moulin, Pierre, |d 1568-1658
> >> 11010|a France. |b Conseil d'Etat
> >> 1001 |a Vendme, Csar de Bourbon, |c duc de, |d 1594-1665.
> >> 130 0|a Interim of Augsburg (1548)
> >> 1001 |a Morgues, Matthieu de, |c sieur de Saint-Germain, |d 1582-1670.
> >> 10010|a Jouan, Abel.
> >> 7201 |a [Du Moulin, Pierre], |d 1568-1658
> >> 7201 |a Henrici IV. Christianissimi Franciae et Navarrae regis
> >> 1001 |a Morgues, Matthieu de, |c sieur de Saint-Germain, |d 1582-1670.
> >> 151  |a United Provinces of the Netherlands
> >> 10010|a Sirmond, Jean, |d 1589?-1649
> >> 1001 |a Scudry, |c M. de |q (Georges), |d 1601-1667
> >> 1001 |a Grenaille, |c M. de |q (Franois), |c sieur de Chatounieres, |d
> >> 1616-1680.
> >> 10010|a Sable, Abel Servien, |c marquis de, |d 1593-1669.
> >>
> >>
> >> I was successful in getting the tag and indicators proper placed
> >> using MARC::Record.
> >>
> >> At this time, I am strugging of putting the data beyond subfield a
> >> in its proper subfield code and position. I was wondering if anyone
> >> has come across something like this and have already had a solution
> >> to this?  Thank you very much for your help!
> >>
> >> Regards,
> >>
> >> --Jackie
> >>
> >> |Jackie Shieh
> >> |Special Projects & Collections Team
> >> |Harlan Hatcher Graduate Library
> >> |University of Michigan
> >> |920 North University
> >> |Ann Arbor, MI  48109-1205
> >> |Phone: 734.936.2401   FAX: 734.615.9788
> >> |E-mail: [email protected]
> >>
>

-- 
Saiful Amin
Information Specialist
Edutech India
2/2, Union Street
Off Infantry Road
Bangalore 560001, India
Tel: +91 80 4112 3437
M: +91 93438 26438
Fax: +91 80 4151 7801
www.edutechindia.com
"Enhancing knowledge and skills for success, lifelong."

pam2.pl (application/octet-stream, 3.2 KB)

#!/usr/bin/perl

## 7054 entries; test file 27 entries
## 
## 2006-10
## convert to MARC21; fix proper format later

use warnings;
use strict;
use MARC::Batch;
use MARC::Record;
use MARC::Field;

 my ($input,$output) = @ARGV;

 die "couldn't find $input" if !(-e $input);

# my $batch = MARC::Batch->new('USMARC', $input);

 open (IN, "$input");
 open (OUT, ">$output");

#binmode OUT, ':utf8';

while ( my $line = <IN> ) {

  chomp ($line);

  $line =~ s/"//g;

  my ($author,$lang, $title,$pubInfo,$ctry,$pdate,$note,$reel) = split /\t/, $line;
  chomp ($lang);
  chomp ($title);
  chomp ($pubInfo);
  chomp ($ctry);
  chomp ($pdate);
  chomp ($note);
  chomp ($reel);

  my $REEL = qq {reel $reel};

# Begin constructing MARC records

  my $record = MARC::Record->new();
  my $leader = $record->leader();
  substr($leader,5,3) = 'nam';

## Enc Lvl set to 3 abbreviated; descriptive set for unknown
  substr($leader,17,2) = '3u';
  $record->leader($leader);

# constructing MARC fields

  $record->append_fields(
      MARC::Field->new('003','SCL'),
      MARC::Field->new('008', '061110s                      000 0 fre d'),
      MARC::Field->new('040','','','a', 'EYM', 'c', 'EYM'),
## adding 100
      MARC::Field->new('100','1',' ','a', $author),
## adding 245
      MARC::Field->new('245','1','0','a', $title),
## adding 260
      MARC::Field->new('260',' ',' ','a',$pubInfo, 'c', $pdate),
## add note
      MARC::Field->new('533','','','a', 'Microfilm.', 'n', $REEL),
      MARC::Field->new('590','','','a', $note),
      );

##fixing 1XX field
## recording 1XX field by the first 3-digit

    my $f100 = $record->field('100');
    my $f100a = $record->field('100')->subfield('a');

if ( $f100a =~ /^\d{3}/ ) {
           my $tagField = substr($f100a, 0, 3);
           my $IndField1 = substr($f100a, 3, 1);
           my $SubA = substr($f100a, 5, );


## getting more subfields out of the 1XX string, $SubA,
## example:10000|a Henry |b II, |c King of France, |d 1519-1559
## example:1001 |a Grenaille, |c M. de |q (François), |c sieur de Chatounieres, |d 1616-168

##################### from B. Baldus 2006-11-01

        #my $subfield_delimiter = '|';
        my @subfields = split( / \|/, $SubA);

# Split the subfield data into subfield name and data pairs
        my @subfield_data = ();
        for ( @subfields ) {
                if ( length > 0 ) {
                #get code as 1st char, skip space, then rest for data
                        #print $_, "\n";
                        push( @subfield_data, substr($_,0,1), substr($_,2) );
                } else {
                        print "Entirely empty subfield found in tag $tagField $SubA", "\n" ;
                }  #else empty subfield
        } #for @subfields

        if ( !@subfield_data ) {
                print  "no subfield data found $author for tag $tagField", "\n" ;
                next;
        } #if not subfield data

#####################
                      
## put NEW 1XX field together
        my $new1XX= MARC::Field->new( $tagField, $IndField1, '', @subfield_data);
           $f100->replace_with($new1XX);
     }
# print out records

 print OUT $record->as_usmarc();
}