It is uft8 as well ... It does not change the results but also it gives some errors as well regarding the wide character ...
even i change my code to this:
#!/usr/bin/perl
use Lingua::AR::Word::Encode;
use Encode::Arabic;
open (STOPWORDS, $ARGV[1]) || die "Error opening the stopwords file\n"
+;
$count = 0;
while ($word = <STOPWORDS>)
{
$word=Lingua::AR::Word::encode($word);
chop($word);
$stopword[$count] = lc($word);
$count++;
}
close(STOPWORDS);
open (INFILE , $ARGV[0]) || die "Error opening the input file\n";
while ($line = <INFILE>)
{
$line=Lingua::AR::Word::encode($line);
chop($line);
@entry = split(/ /, $line);
$i = 0;
while ($entry[$i])
{
$found = 0;
$j = 0;
while (($j<=$count) && ($found==0))
{
if (lc($entry[$i]) eq $stopword[$j])
{
$found = 1;
}
$j++;
}
if ($found == 0)
{
print "$entry[$i]\n ";
}
$i++;
}
}
close(INFILE);
still does not work , it does not remove my stop words :(
|