Picking out a subject

sub.clj

;; This is O(n*m) for all cases, where n is the length of a, and m is the length of b
user=> a
"8th grade biology"
user=> b
["chemistry" "biology" "algebra"]
user=> (def s (cstr/split a #" "))
#'user/s
user=> s
["8th" "grade" "biology"]
user=> (for [w b
             ww s
             :when (.contains w ww)] w)
("biology")

user=> ;;  OR MORE LIKE THE PHP -- O(m) in the best case O(n*m) in the worst

user=> (def a "8th grade biology")
user=> (def b ["chemistry" "biology" "algebra"])

user=> (reduce (fn [ret w] (if (neg? (.indexOf a w)) ret (conj ret w))) [] b)
["biology"]
user=> (for [w b :when (> (.indexOf a w) -1)] w)
("biology")

;;;  ---  Now let's sort by longest name descending :: sort is timsort, so O(n) best, O(nlogn)
;;                where n is the length of ret

user=> (def a "8th grade microbiology")
user=> (def b ["chemistry" "biology" "algebra" "microbiology"])
user=> (def ret (for [w b :when (> (.indexOf a w) -1)] w))

user=> (sort-by count > ret)
("microbiology" "biology")

sub.php

//O(m) in the best case O(n*m) in the worst - where m is the length of b and n is the length of a
$a = "8th grade microbiology";
$b = array("chemistry", "biology", "algebra", "microbiology");
$ret_array = array();

foreach($b as $wi => $w) {
    if (strpos($a, $w)) {
        $ret_array[] = $w;
    }
}

function wCmp($a, $b)
{
    if ($a == $b) {
        return 0;
    }
    return (strlen($a) > strlen($b)) ? -1 : 1;
}

// O(nlogn) -- n is the length of ret_array
usort($ret_array, 'wCmp'); // Believe it or not, this is destructive


/*  -- From my PHPSH session

php> $a = "8th grade microbiology";
php> $b = array("chemistry", "biology", "algebra", "microbiology");
php> $ret_array = array();

php> foreach($b as $wi => $w) {
 ...   if (strpos($a, $w)) {
 ...     $ret_array[] = $w;
 ...   }
 ... }

php> var_dump($ret_array);
array(2) {
  [0]=>
  string(7) "biology"
  [1]=>
  string(12) "microbiology"
}

php> function wCmp($a, $b)
 ... {
 ...   if ($a == $b) {
 ...     return 0;
 ...   }
 ...   return (strlen($a) > strlen($b)) ? -1 : 1;
 ... }

php> usort($ret_array, 'wCmp'); // Believe it or not, this is destructive

php> var_dump($ret_array);
array(2) {
  [0]=>
  string(12) "microbiology"
  [1]=>
  string(7) "biology"
}

php> 
*/

sub.py

>>> a = "8th grade microbiology"
>>> b = ["chemistry", "biology", "algebra", "microbiology"]
>>> ret = [w for w in b if w in a]
>>> sorted(ret, key=len, reverse=True)
['microbiology', 'biology']