#!/usr/bin/perl

use strict;
use CGI;
use URI::Escape;


##############################################################################
#
#
##############################################################################
if ($ARGV[0]=~/\.gz$/i) {
  open STDIN,"zcat $ARGV[0] |";
  shift @ARGV;
}
##############################################################################
## 
sub breakquery {
  my $sz=shift;
  my %res;

  $sz="\L$sz";
  $sz=~s/\.[a-z]{2}\.//g;
  $sz=~s/\@[a-z]{2}.\d+//g;

  while ($sz=~s/[\"\']([^\"\']+?)[\"\']//) {
    $res{$1}++;
  }

  $sz=~s/\s{2}/ /g;
  $sz=~s/[\+\'\"\$\(\)]//g;
       
  if ($sz) {
    my @terms=split /[\s,]/,$sz;

    for my $t (@terms) {
      $t=~s/^\s+//;
      $t=~s/\s+$//;
      next if $t=~/^\s*$/ || $t=~/^..{0,1}$/ || $t!~/^[a-z0-9\-]+$/ || $t=~/^[0-9]+$/;
      $res{$t}++ unless grep /^$t$/,qw( and not or adj of the for with );
    }
  }

  sort keys %res;
}

##############################################################################

while (<>) {
  next unless m{GET /netacgi/nph-brs\?([^\s]+)};

  my $cgi=new CGI($1);
  next unless defined $cgi;

  my $db=$cgi->param("d");
  next if $db=~/^\s*$/;

  $db="\U$db";

  next if grep /^$db$/,qw( CHNH CHCA );
  next if length($db)!=4;

  my $s4=$cgi->param("s4");
  next unless defined $s4;

  next if $s4=~/^\s*$/;

  my @terms=breakquery $s4;

  print STDERR "\r";
  printf STDERR "%.100s","$db ".join("  ",@terms);


  # $db $t 


}

##</code><code>##

anx57-105.dialup.emory.edu - - [01/Mar/2001:00:00:21 -0500] "GET /detail/detail.html HTTP/1.0" 200 19308 "http://chid.nih.gov/netacgi/nph-brs?op4=and&op5=and&op6=and&op7=and&op8=and&op9=and&op10=and&d=CHCP&l=20&Sect1=CINK&co3=and&pg4=all&s4=underserved&co4=and&pg5=mj&s5=cervical+cancer&co5=and&pg6=de&s6=&co6=and&pg7=au,cn&s7=&co7=and&pg8=ti&s8=&co8=and&pg9=ac&s9=&co9=and&pg10=so,av&s10=&s1=@YR%3E=1995+or+199X.&co1=and&s3=&co2=and&s2=&Sect2=IMAGE&Sect3=THESOFF&Sect3=PLUROFF&Sect4=HITOFF&p=1&u=/detail/detail.html&r=8&f=G" "Mozilla/4.73 [en] (Win95; U)"