Bug#299870: libspreadsheet-parseexcel-perl: Choking on NULLs

[Niko Tyni]

tags 299870 patch
forwarded 299870 http://rt.cpan.org/NoAuth/Bug.html?id=16786
thanks

>   perl -MSpreadsheet::ParseExcel -le 'print unpack "H*", Spreadsheet::ParseExcel->new->Parse("products.xls")->{Worksheet}[0]{Cells}[0][0]->Value'
> 
>   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

Hi,

the nulls show up because Spreadsheet::ParseExcel doesn't handle the
string as Unicode, although it should. The attached patch fixes this. I
have reported this to the upstream author as CPAN bug 299870,
<http://rt.cpan.org/NoAuth/Bug.html?id=16786>.

Cheers,
-- 
Niko Tyni	ntyni at iki.fi
-------------- next part --------------
--- libspreadsheet-parseexcel-perl-0.2603.orig/ParseExcel.pm
+++ libspreadsheet-parseexcel-perl-0.2603/ParseExcel.pm
@@ -620,10 +620,21 @@
     my($oBook, $bOp, $bLen, $sWk) = @_;
     my($iR, $iC, $iF, $iL, $sTxt);
     ($iR, $iC, $iF, $iL) = unpack("v4", $sWk);
-    $sTxt = substr($sWk, 8, $iL);
+    my $bver = $oBook->{BIFFVersion};
+    my ($rich, $sCode);
+    if($bver == verBIFF8) {
+        my( $raBuff, @rest) = _convBIFF8String($oBook, substr($sWk, 6), 1);
+        $sTxt  = $raBuff->[0];
+        $sCode = ($raBuff->[1])? 'ucs2': undef;
+        $rich = $raBuff->[2];
+    } else {
+        $sTxt = substr($sWk, 8, $iL);
+        $sCode = '_native_';
+        $rich = substr($sWk, (8+$iL)+1)
+            if (length($sWk) > (8+$iL));
+    }
 
-    #Has STRUN
-    if(length($sWk) > (8+$iL)) {
+    if($rich) {
         _NewCell (
             $oBook, $iR, $iC,
             Kind    => 'RString',
@@ -631,9 +642,9 @@
             FormatNo=> $iF,
             Format  => $oBook->{Format}[$iF],
             Numeric => 0,
-            Code    => '_native_', #undef,
+            Code    => $sCode,
             Book    => $oBook,
-            Rich    => substr($sWk, (8+$iL)+1),
+            Rich    => $rich,
         );
     }
     else {
@@ -644,7 +657,7 @@
             FormatNo=> $iF,
             Format  => $oBook->{Format}[$iF],
             Numeric => 0,
-            Code    => '_native_',
+            Code    => $sCode,
             Book    => $oBook,
         );
     }