Hi Readers and helpers, I am trying to count the occurreneces of the various elements of the keys of the Hash.More than one occurrence of the key occurs in the hash. I need to group all the keys and get the occurrences of each of their values 
use XML::TreeBuilder;
        
sub tokenizefast ($) {

    $line = $_[0];
    $line =~ s/^\s*//;
    $line =~ s/\s*$//;

    # split into words to respect word boundaries
    # and ignore space-containing bigrams
    @words = split /\s+/, $line;
    @ngrams = @words; #a copy
    @ngramLengths = (2,3);
    #now perform the grouping
    foreach $slength (@ngramLengths) {
            for(my $i=0;$i+$slength<=$#words+1;$i++){
                     my @tempwords= @words;
      #              print "tempwords: i: $i length $slength " ;
print @tempwords ; print  "\n";
                    @tsome = splice(@tempwords,$i,$slength);
         #           print "after splice: ";
print @tsome; print "\n";
                    push(@ngrams,join(" ",@tsome));
            }
    }
    return @ngrams;

}
## end of tokenize function

my $file= 'swbd_50k_42tags.xml';
my $tree = XML::TreeBuilder->new();
my %textHash;
$tree->parse_file($file);

foreach my $dialogue ($tree->find_by_tag_name ('dialogue')){
            $dialogue_name = $dialogue->attr_get_i('name');
        foreach my $turn ($dialogue->find_by_tag_name('turn')){
            $turn_no = $turn->attr_get_i('no');
            $turn_speaker = $turn->attr_get_i('speaker');

            foreach my $utt ($dialogue->find_by_tag_name('utt')){
                $da = $utt->attr_get_i('da');
                $id = $utt->attr_get_i('id');
                $inline = $utt->as_text;
                @textarray = tokenizefast( $inline);
#                print join(",",@textarray); print "\n";
                if ($textHash{$da}) {
                    @someArray  = @{ $textHash{$da} };
                    push @someArray , @textarray;
                    #print @someArray;
                }
                else {
                    $textHash{$da} = [ @textarray];
                }
            }
        }
}
# extract different elements of xml doc

#write the final thing to a file
for $somekey (keys %textHash) {
    @ans = @{ $textHash{$somekey} };
     print " the key: $somekey" ;print " text {" ;
    print join(", ", @ans);
    print "}\n";
}

[download]

20050404 Edit by ysth: code tags

Retitled by BazB from 'Cry for Help'.

In reply to Help needed to understand hashes and hashes of arrays by D'Femstar

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.