adding functionality to perlfect search

sub create_query {
  my $query_str = $query->param('q');

  if ($query_str=~ /^\s+"/ || $query_str=~ /^"){ ## Looks like a phrase, lets check further
   $query_str=~ /\s+"/"/; ## Remove leading & ..
   $query_str=~ /"\s+$/"/; ## .. trailing spaces

   if ($query_str=~ /".*"/){ ## it is a phrase
  push(@terms, $query_str);
  }else{
    @terms = split " ", $query_str;
  }
  }else{
  @terms = split " ", $query_str;
  }

  my $buffer;
  my ($sterm, $nterm);
.....

I dont know that your normalize subroutine does, so i can only provide you with this snippet.

Not knowing the surrounding code, it is difficult to say.  The specific approach would be to set apart your phrase(s) (i.e. the quoted words) and handle them in an entirely different code segment.  However, you could generalize by setting apart the phrases, then translating each of the words in the phrase to + words, then doing a brute for search for the phrase(s) on the results of the keyword search.  Of course, any of the words in the phrase don't show up in %terms_db, create_query returns failure.

If the search is based on pre-indexing of the source, then it will be more involved.  If the full source (i.e. the information being searched) is available to the program, it may be easier.

There are really too many what-ifs right now.  We do need to see the rest of the code.

However, in all cases the first thing will be to isolate the phrases:

sub create_query {
  my $query_str = $query->param('q');

  my @phrases = $query_str=~/"(.+?)"/g;
  $query_str=~s/"(.+?"//g;
 
  my @terms = split " ", $query_str;
 

Later, we can figure out how to use @phrases to advantage.

Looking forward to seeing the rest of the code.

Here is the entire script:

#!/usr/bin/perl
#$rcs = ' $Id: search.pl,v 1.12 2000/02/06 13:31:36 perlfect Exp $ ' ;

use locale;
use CGI;
use CGI::Carp qw(fatalsToBrowser);
use Fcntl;
use Perlfect::Template;

package AnyDBM_File;
@ISA = qw(DB_File GDBM_File SDBM_File ODBM_File NDBM_File) unless @ISA;

for (@ISA) {
  last if eval "require $_";
}

package main;
require './conf.pl';

my %inv_index_db;
my %docs_db;
my %desc_db;
my %titles_db;
my %terms_db;

tie %inv_index_db, AnyDBM_File, $INV_INDEX_DB_FILE, O_RDONLY, 0755 or die "Cannot open $INV_INDEX_DB_FILE: $!";  
tie %docs_db,      AnyDBM_File, $DOCS_DB_FILE, O_RDONLY, 0755      or die "Cannot open $DOCS_DB_FILE: $!";  
tie %desc_db,      AnyDBM_File, $DESC_DB_FILE, O_RDONLY, 0755      or die "Cannot open $DESC_DB_FILE: $!";  
tie %titles_db,    AnyDBM_File, $TITLES_DB_FILE, O_RDONLY, 0755    or die "Cannot open $TITLES_DB_FILE: $!";  
tie %terms_db,     AnyDBM_File, $TERMS_DB_FILE, O_RDONLY, 0755     or die "Cannot open $TERMS_DB_FILE: $!";  

my (@force, @not, @other);
my (@docs, @valid_docs);
my %answer;

my $query = new CGI;

if (create_query()) { #if some valid documents exist
  apply_booleans();
  answer_query();
}  

my $html = cast_template();
print $query->header;
print $html;

sub answer_query {
  my @term_ids = (@force, @other);

  foreach my $term_id (@term_ids) {
    my %v = unpack('f*', $inv_index_db{$term_id});
    foreach my $doc_id (keys %v) {
      $answer{$doc_id} += $v{$doc_id} if grep {/^$doc_id$/} @valid_docs;
    }
  }
}

sub apply_booleans {
  #locate the valid documents by applying the booleans
  my ($term_id, $doc_id, $first_doc_id);
  my %v;
  my (@ary, @not_docs);

  foreach $term_id (@not) {
    %v = unpack("f*", $inv_index_db{$term_id});
    foreach $doc_id (keys %v) {
      push @not_docs, $doc_id unless grep {/^$doc_id$/} @not_docs;
    }
  }
 
  if (@force) {
    $first_doc_id = pop @force;
    %v  = unpack("f*", $inv_index_db{$first_doc_id});
    @valid_docs = keys %v;
    foreach $term_id (@force) {
      %v = unpack("f*", $inv_index_db{$term_id});
      @ary = keys %v;
      @valid_docs = intersection(\@valid_docs, \@ary);
    }
    push @force, $first_doc_id;
  } else {
    @valid_docs = keys %docs_db;
  }

  @valid_docs = minus(\@valid_docs, \@not_docs);
}

sub create_query {
  my $query_str = $query->param('q');
  my @terms = split " ", $query_str;
  my $buffer;
  my ($sterm, $nterm);
 
  foreach my $term (@terms) {
    $buffer = normalize($term);
    foreach my $nterm (split " ",$buffer) {
      $sterm = stem($nterm);
#      if ($term =~ /^\+/) {
      if ($terms_db{$sterm}) {
        push @force, $terms_db{$sterm};
#      } else {
#        return 0;
#      }
#     } elsif ($term =~ /^\-/) {
#      push @not, $terms_db{$sterm} if $terms_db{$sterm};
      } else {
      push @other, $terms_db{$sterm} if $terms_db{$sterm};
      }
    }
  }

  return 1;
}

sub cast_template {
  my %h;
  my $template = new Perlfect::Template($SEARCH_TEMPLATE);
  my $rank = 0;

  $h{script_name} = "Perlfect Search $VERSION";
  $h{query_str}   = $query->param('q');
  $h{results_num} = keys %answer;
 
  my $current_page = $query->param('p');
  $current_page ||= 1;

  my $first = ($current_page - 1) * $RESULTS_PER_PAGE;
  my $last  = $first + $RESULTS_PER_PAGE - 1;
 
  my $real_last = keys %answer;
  if ($last >= $real_last) {
    $last = $real_last - 1;
  }
 
  foreach ((sort {$answer{$b} <=> $answer{$a}} keys %answer)[$first..$last]) {
    my $score = sprintf "%.2f", $answer{$_};
    $template->cast_loop ("results", [{rank => $first+(++$rank),
                               url => $BASE_URL.$docs_db{$_},
                               title => $titles_db{$_},
                               score => $score,
                               description => $desc_db{$_},
                              }]);
  }
  $template->finalize("results");
 
  my $last_page = ceil($real_last, $RESULTS_PER_PAGE);
  $last_page ||= 1;
  my $query_str = CGI::escape($query->param('q'));
  if ($current_page == 1) {
    $h{previous} = "";
    if ($last_page > $current_page) {
      $h{next} = "<A href=\"$SEARCH_URL?q=".$query_str."&p=2\"> Next</A>";  
    } else {
      $h{next} = "";
    }
  } elsif ($current_page == $last_page) {
    $h{previous} = "<A href=\"$SEARCH_URL?q=".$query_str."&p=".($last_page-1)."\">Previous </A>";  
    $h{next} = "";
  } else {
    $h{previous} = "<A href=\"$SEARCH_URL?q=".$query_str."&p=".($current_page-1)."\">Previous </A>";  
    $h{next} = "<A href=\"$SEARCH_URL?q=".$query_str."&p=".($current_page+1)."\"> Next</A>";  
  }
 
  for (1..$last_page) {
    if ($_ != $current_page) {
      $h{navbar} .= "<A href=\"$SEARCH_URL?q=".$query_str."&p=$_\">$_</A> ";
    } else {
      $h{navbar} .= "<B>$_</B> ";
    }
  }

  $h{current_page} = $current_page;
  $h{total_pages}  = $last_page;
  $h{search_url}   = $SEARCH_URL;

  $template->cast(\%h);
  return $template->html;
}

sub normalize {
  my $buffer = $_[0];
 
  $buffer =~ s/-//gs;
  $buffer =~ s/\W/ /gs;
  $buffer =~ s/\b\d+\b/ /gs;
  $buffer =~ s/[\n\s]+/ /gs;
  $buffer =~ s/^\s+//gs;
  $buffer =~ s/\s+$//gs;
  $buffer = lc $buffer;

  return $buffer;
}

sub stem {
  my $str = $_[0];
  $str = substr $str, 0, $STEMCHARS if $STEMCHARS;
  return $str;
}

sub ceil {
  my $x = $_[0];
  my $y = $_[1];

  if ($x % $y == 0) {
    return $x / $y;
  } else {
    return int($x / $y + 1);
  }
}

sub intersection {
  my ($ra, $rb) = @_;
  my @i;
 
  foreach my $doc_id (@{$ra}) {
    push @i, $doc_id if grep {/^$doc_id$/} @{$rb};
  }

  return @i;
}

sub minus {
  my ($ra, $rb) = @_;
  my @i;

  foreach my $doc_id (@{$ra}) {
    push @i, $doc_id unless grep {/^$doc_id$/} @{$rb};
  }
 
  return @i;
}

use Text::ParseWords;
@terms=quotewords('\s+', 0,  $query_str);

That sounds easy enough ozo... where exactly do I put those lines... I am kind of new.

maneshr,

Will your snippet work with the script I pasted?

Thank you... I was afraid of that.  You are right the index will not work with phrases so being able to set the terms won't help.

Aaron