StoneCypher/gist:9015456

## gistfile1.php
<html><body>
<?php

  // normally i'd write this more densely, but you said you wanted some exposure
  // so i'm writing it in single concepts per line and annotating it for reference :)


  // config

  $shouldToLower = false;

  // end config, editing below should be unnecessary


  $wordcount  = array();                                                                       // number of times each word is seen - initially empty (unlisted words = implicitly 0)

  $original   = file_get_contents('titles.csv');                                               // get the data from disk
  $work       = ($shouldToLower)? strtolower($original) : $original;                           // maybe drop uppercase first
  $normalized = str_replace("\r", "\n", str_replace("\r\n", "\n", $original));                 // change dos and mac style returns to unix style
  $lines      = explode("\n", $normalized);                                                    // split on returns to individual lines

  foreach ($lines as $line) {                                                                  // iterate each line
    $wl = trim($line);                                                                         // remove stray spaces from the line = work line
    $words = explode(" ", $wl);                                                                // split into individual words
    foreach ($words as $word) {                                                                // iterate over the words of this line
      if (isset($wordcount[$word])) {                                                          // have we seen this word before?
        ++$wordcount[$word];                                                                   // if so bump that count
      } else {                                                                                 // otherwise
        $wordcount[$word] = 1;                                                                 // initialize the count for that word to one
      }
    }
  }

  echo '<pre>';
  print_r($wordcount);
  echo '</pre>';

?>
</body></html>
	<html><body>
	<?php

	// normally i'd write this more densely, but you said you wanted some exposure
	// so i'm writing it in single concepts per line and annotating it for reference :)



	// config

	$shouldToLower = false;

	// end config, editing below should be unnecessary





	$wordcount = array(); // number of times each word is seen - initially empty (unlisted words = implicitly 0)

	$original = file_get_contents('titles.csv'); // get the data from disk
	$work = ($shouldToLower)? strtolower($original) : $original; // maybe drop uppercase first
	$normalized = str_replace("\r", "\n", str_replace("\r\n", "\n", $original)); // change dos and mac style returns to unix style
	$lines = explode("\n", $normalized); // split on returns to individual lines

	foreach ($lines as $line) { // iterate each line
	$wl = trim($line); // remove stray spaces from the line = work line
	$words = explode(" ", $wl); // split into individual words
	foreach ($words as $word) { // iterate over the words of this line
	if (isset($wordcount[$word])) { // have we seen this word before?
	++$wordcount[$word]; // if so bump that count
	} else { // otherwise
	$wordcount[$word] = 1; // initialize the count for that word to one
	}
	}
	}

	echo '<pre>';
	print_r($wordcount);
	echo '</pre>';

	?>
	</body></html>