gitea
/
Koha-clms
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix for encoding issues. Usefull only for libraries with UNIMARC & latin1 framework. 

Note that this hack is necessary because of ZOOM behaviour that is different to Net::Z3950.
It must NOT be reported to rel_3 or dev_week, because they are full unicode.

PS : yes, it's quite a dirty hack, because it don't solve the problem, it just override it...
This commit is contained in:
tipaul 2006-09-25 14:02:42 +00:00
parent 96e63467a8
commit 79fe5e72ca
1 changed files with 41 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
z3950/processz3950queue
View File

@ -285,10 +285,47 @@ while (1) {
for ($i=1; $i<=(($numresults<80) ? ($numresults) : (80)); $i++) {
my $rec=$rs->record($i-1);
my $marcdata = $rec->raw();
#my $marcrecord = MARC::Record->new_from_usmarc($marcdata);
#warn $marcrecord->as_formatted();
$globalencoding = ref($rec);
$result.=$marcdata;
if (C4::Context->preference("MARCFLAVOUR") eq "UNIMARC"){
warn "marcdata :".$marcdata;
my $marcrecord = MARC::Record->new_from_usmarc($marcdata);
use Encode;
use Encode::Guess;
my $targetcharset="utf8" if (C4::Context->preference("TemplateEncoding") eq "utf-8");
$targetcharset="latin1" if (C4::Context->preference("TemplateEncoding") eq "iso-8859-1");
my $decoder = guess_encoding($marcdata, qw/utf8 latin1/);
die $decoder unless ref($decoder);
warn "decodage : ".$decoder->name;
warn "decodage cible : ".$targetcharset;
my $newRecord=MARC::Record->new();
foreach my $field ($marcrecord->fields()){
my $newField=$field->clone;
if ($field->tag()<'010'){
$newRecord->insert_grouped_field($field);
} else {
foreach my $subfield ($newField->subfields()){
# warn ' valeur avant encodage'.$subfield->[1];
# map {char_decode($_,"UNIMARC");Encode::from_to($_,$decoder->name,$targetcharset);$_=~tr#\r##} @$subfield;
map {char_decode($_,"UNIMARC");Encode::from_to($_,$decoder->name,$targetcharset);$_=~tr#\r##} @$subfield;
# warn ' valeur apres encodage'.$subfield->[1];
# warn ' valeur theorique'.Encode::from_to($_,$decoder->name,$targetcharset);
if (($newField->tag eq '100')) {
substr($subfield->[1],26,2,"0103") if ($targetcharset eq "latin1");
substr($subfield->[1],26,4,"5050") if ($targetcharset eq "utf8");
}
$newField->update($subfield->[0]=>$subfield->[1])
}
$newRecord->insert_grouped_field($newField);
}
}
$newRecord->encoding('UTF-8') if ($targetcharset eq 'utf8');
$newRecord->encoding('MARC-8') if ($targetcharset ne 'utf8');
warn $newRecord->as_formatted();
$globalencoding = $targetcharset;
$result.=$newRecord->as_usmarc;
} else {
$globalencoding = ref($rec);
$result.=$marcdata;
}
}
my @x=split /::/,$globalencoding;
my ($notmarcrecord,$alreadyindb,$alreadyinfarm,$imported) = ImportBreeding($result,-1,"Z3950-$globalname",$x[3],$random);