Created
October 25, 2016 06:46
-
-
Save ubermichael/b0a6f0da4b5271f2ddd91a5b570adc22 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Based heavily on https://gist.github.com/gmcharlt/f7e3bcb3680a5bf748aacd7e21c13175 | |
```perl | |
#!/usr/bin/env perl | |
use 5.014; | |
use utf8; | |
use strict; | |
use warnings; | |
use version; our $VERSION = qv(0.0_1); | |
use Data::Dumper; $Data::Dumper::Indent = 1; | |
use MARC::Charset qw/ marc8_to_utf8 /; | |
use MARC::Batch; | |
binmode(STDIN, ':encoding(utf-8)'); | |
binmode(STDOUT, ':encoding(utf-8)'); | |
$|++; | |
# ------------------------------------- | |
my $dots = 50; | |
my $line = 70 * $dots; | |
sub convert { | |
my $marc = shift; | |
my $ldr = $marc->leader(); | |
if(substr($ldr, 9, 1) eq 'a') { | |
return; | |
} else { | |
substr($ldr, 9, 1) = 'a'; | |
$marc->leader($ldr); | |
} | |
foreach my $field ($marc->fields()) { | |
next if($field->is_control_field()); | |
my @converted = (); | |
foreach my $sf ($field->subfields()) { | |
$sf->[1] = marc8_to_utf8($sf->[1]); | |
push @converted, @$sf; | |
} | |
$field->replace_with(MARC::Field->new( | |
$field->tag(), | |
$field->indicator(1), | |
$field->indicator(2), | |
@converted | |
)); | |
} | |
} | |
sub main { | |
my $inPath = shift; | |
my $outPath = shift; | |
open(my $in, '<:raw', $inPath) || die "cannot open $inPath: $!\n"; | |
binmode($in); | |
open(my $out, '>:utf8', $outPath) || die "cannot open $outPath: $!\n"; | |
my $batch = MARC::Batch->new('USMARC', $in); | |
my $i = 0; | |
MARC::Charset->ignore_errors(1); | |
while(my $marc = $batch->next()) { | |
convert($marc); | |
print $out $marc->as_usmarc(); | |
$i++; | |
if($i % $dots == 0) { | |
print '.'; | |
}; | |
if($i % $line == 0) { | |
printf("%7d\n", $i); | |
} | |
} | |
printf("%7d\n", $i); | |
} | |
# ------------------------------------- | |
&main(@ARGV); | |
``` |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment