use strict;

my $match = &ret_match_any(
  "0  OBS",
  "AT LEAST",
  "EXTRANEOUS",
  "CARTESIAN",
  "CLOSING",
  "CONVERT",
  "DIVISION BY ZERO",
  "DOES NOT EXIST",
  "DUE TO LOOPING",
  "END OF MACRO",
  "ENDING EXECUTION",
  "ERROR",
  "ERRORABEND",
  "ERRORCHECK=STRICT",
  "EXCEED",
  "HANGING",
  "HAS 0 OBSERVATIONS",
  "ILLEGAL",
  "INCOMPLETE",
  "INVALID",
  "LOST CARD",
  "MATHEMAT",
  "MERGE STATEMENT",
  "MISSING",
  "MULTIPLE",
  "NOT FOUND",
  "NOT RESOLVED",
  "OBS=0",
  "REFERENCE",
  "REPEAT",
  "SAS CAMPUS DRIVE",
  "SAS SET OPTION OBS=0",
  "SAS WENT",
  "SHIFTED",
  "STOP",
  "TOO SMALL",
  "UNBALANCED",
  "UNCLOSED",
  "UNREF",
  "UNRESOLVED",
  "WARNING"
);

while(<>) {                        
  if ($_ =~ $match) {
    print "line $., file $ARGV, problem $1\n$_\n";
  }
}


# Takes a list of strings and returns an RE that matches any.
sub ret_match_any {
  my $match_str = &trie_strs(map quotemeta, @_);
  return qr /($match_str)/;
}

# Takes a list of escaped strings and returns a single string
# suitable for building a match in an efficient way.
# Works recursively by grouping strings that share one character
sub trie_strs {
  unless (@_) {
    return ();
  }
  my %rest;
  foreach my $str (@_) {
    if (length($str)) {
      my $chr = substr($str, 0, 1);
      if ("\\" eq $chr) {
        $chr = substr($str, 0, 2);
        push @{$rest{$chr}}, substr($str, 2);
      }
      else {
        push @{$rest{$chr}}, substr($str, 1);
      }
    }
    else {
      $rest{''} = [''];
    }
  }
  my @to_join;
  foreach my $chr (keys %rest) {
    my $list_ref = $rest{$chr};
    if (1 < @$list_ref) {
      push @to_join, $chr . &trie_strs(@$list_ref);
    }
    else {
      push @to_join, $chr . $list_ref->[0];
    }
  }
  if (1 < @to_join) {
    return '(?:' . (join '|', @to_join) . ')';
  }
  else {
    return $to_join[0];
  }     
}