Adding callnumber to serials standard number search

[srvgit] / C4 / Charset.pm

diff --git a/C4/Charset.pm b/C4/Charset.pm
index 2e2e831..bffd374 100644 (file)
--- a/C4/Charset.pm
+++ b/C4/Charset.pm
@@ -18,14 +18,17 @@ package C4::Charset;
 # Suite 330, Boston, MA  02111-1307 USA
 
 use strict;
+use warnings;
+
 use MARC::Charset qw/marc8_to_utf8/;
 use Text::Iconv;
+use C4::Debug;
 
 use vars qw($VERSION @ISA @EXPORT @EXPORT_OK %EXPORT_TAGS);
 
 BEGIN {
     # set the version for version checking
-    $VERSION = 3.00;
+    $VERSION = 3.01;
     require Exporter;
     @ISA    = qw(Exporter);
     @EXPORT = qw(
@@ -153,7 +156,23 @@ sub MarcToUTF8Record {
         $marc =~ s/^\s+//;
         $marc =~ s/\s+$//;
         $marc_blob_is_utf8 = IsStringUTF8ish($marc);
-        $marc_record = MARC::Record->new_from_usmarc($marc);
+        eval {
+            $marc_record = MARC::Record->new_from_usmarc($marc);
+        };
+        if ($@) {
+            # if we fail the first time, one likely problem
+            # is that we have a MARC21 record that says that it's
+            # UTF-8 (Leader/09 = 'a') but contains non-UTF-8 characters.
+            # We'll try parsing it again.
+            substr($marc, 9, 1) = ' ';
+            eval {
+                $marc_record = MARC::Record->new_from_usmarc($marc);
+            };
+            if ($@) {
+                # it's hopeless; return an empty MARC::Record
+                return MARC::Record->new(), 'failed', ['could not parse MARC blob'];
+            }
+        }
     }
 
     # If we do not know the source encoding, try some guesses
@@ -174,7 +193,7 @@ sub MarcToUTF8Record {
         } else {
             if ($marc_flavour eq 'MARC21') {
                 return _default_marc21_charconv_to_utf8($marc_record, $marc_flavour);
-            } elsif ($marc_flavour eq 'UNIMARC') {
+            } elsif ($marc_flavour =~/UNIMARC/) {
                 return _default_unimarc_charconv_to_utf8($marc_record, $marc_flavour);
             } else {
                 return _default_marc21_charconv_to_utf8($marc_record, $marc_flavour);
@@ -228,19 +247,36 @@ any actual character conversion.
 
 sub SetMarcUnicodeFlag {
     my $marc_record = shift;
-    my $marc_flavour = shift;
+    my $marc_flavour = shift; # || C4::Context->preference("marcflavour");
 
     $marc_record->encoding('UTF-8');
     if ($marc_flavour eq 'MARC21') {
         my $leader = $marc_record->leader();
         substr($leader, 9, 1) = 'a';
         $marc_record->leader($leader); 
-    } elsif ($marc_flavour eq "UNIMARC") {
-        if (my $field = $marc_record->field('100')) {
-            my $sfa = $field->subfield('a');
-            substr($sfa, 26, 4) = '5050';
-            $field->update('a' => $sfa);
+    } elsif ($marc_flavour =~/UNIMARC/) {
+        my $string; 
+               my ($subflength,$encodingposition)=($marc_flavour=~/AUTH/?(21,8):(36,22));
+               $string=$marc_record->subfield( 100, "a" );
+        if (length($string)==$subflength) { 
+                       $string = substr $string, 0,$subflength if (length($string)>$subflength);
+        } 
+        else { 
+            $string = POSIX::strftime( "%Y%m%d", localtime ); 
+            $string =~ s/\-//g; 
+            $string = sprintf( "%-*s", $subflength, $string ); 
+        } 
+        substr( $string, $encodingposition, 8, "frey50  " ); 
+        if ( $marc_record->subfield( 100, "a" ) ) { 
+                       $marc_record->field('100')->update(a=>$string);
+               }
+               else {
+            $marc_record->insert_grouped_field( 
+                MARC::Field->new( 100, '', '', "a" => $string ) ); 
         }
+               $debug && warn "encodage: ", substr( $marc_record->subfield(100, 'a'), $encodingposition, 8 );
+    } else {
+        warn "Unrecognized marcflavour: $marc_flavour";
     }
 }
 
@@ -275,6 +311,9 @@ to work, at the possible risk of some data loss.
 
 sub StripNonXmlChars {
     my $str = shift;
+    if (!defined($str) || $str eq ""){
+        return "";
+    }
     $str =~ s/[^\x09\x0A\x0D\x{0020}-\x{D7FF}\x{E000}-\x{FFFD}\x{10000}-\x{10FFFF}]//g;
     return $str;
 }
@@ -419,6 +458,16 @@ sub _marc_marc8_to_utf8 {
             my @converted_subfields;
             foreach my $subfield ($field->subfields()) {
                 my $utf8sf = MARC::Charset::marc8_to_utf8($subfield->[1]);
+                unless (IsStringUTF8ish($utf8sf)) {
+                    # Because of a bug in MARC::Charset 0.98, if the string
+                    # has (a) one or more diacritics that (b) are only in character positions
+                    # 128 to 255 inclusive, the resulting converted string is not in
+                    # UTF-8, but the legacy 8-bit encoding (e.g., ISO-8859-1).  If that
+                    # occurs, upgrade the string in place.  Moral of the story seems to be
+                    # that pack("U", ...) is better than chr(...) if you need to guarantee
+                    # that the resulting string is UTF-8.
+                    utf8::upgrade($utf8sf);
+                }
                 push @converted_subfields, $subfield->[0], $utf8sf;
             }
 
@@ -610,9 +659,7 @@ Converts a string from ISO-5426 to UTF-8.
 
 =cut
 
-sub char_decode5426 {
-    my ( $string) = @_;
-    my $result;
+
 my %chars;
 $chars{0xb0}=0x0101;#3/0ayn[ain]
 $chars{0xb1}=0x0623;#3/1alif/hamzah[alefwithhamzaabove]
@@ -985,6 +1032,11 @@ $chars{0xda20}=0x02cc; #
         # 5/14 right half of ligature sign
         # 5/15 right half of double tilde
 #     map {printf "%x :%x\n",$_,$chars{$_};}keys %chars;
+
+sub char_decode5426 {
+    my ( $string) = @_;
+    my $result;
+
     my @data = unpack("C*", $string);
     my @characters;
     my $length=scalar(@data);