Created
May 14, 2012 14:23
-
-
Save duggan/2694292 to your computer and use it in GitHub Desktop.
Mash dictionary words into a selected word to create neologism candidates
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
/** | |
* Neologism | |
* Mash a selected word into dictionary words, | |
* sort into a list for perusal. Not terribly memory friendly. | |
* | |
* @arg string $word The word to be mashed. | |
* @arg string $end_part The end part of the word to start the mashing from. | |
*/ | |
// Retrieve system dictionary (OSX) and split to array | |
$dict = file_get_contents('/usr/share/dict/words'); | |
$dict = explode("\n", $dict); | |
// Parse command line arguments into variables | |
list($filename, $word, $end_part) = $argv; | |
// Compile a list of words which contain the end part. | |
$wordlist = array(); | |
foreach ($dict as $entry) { | |
if (strpos($entry, $end_part)) { | |
$wordlist[]=$entry; | |
} | |
} | |
// The magic - mash the selected word into discovered dictionary words | |
$mashed = array(); | |
foreach ($wordlist as $entry) { | |
$result = trim(preg_replace('/(.+)'.$end_part.'(.+)?/', $word.'$2', $entry)); | |
if ($result != $word) { | |
$mashed[]= $result; | |
} | |
} | |
// De-dupe | |
$mashed = array_unique($mashed); | |
// Sort, shortest to longest | |
uasort($mashed, function($a, $b){ | |
if (strlen($a) == strlen($b)) { | |
return 0; | |
} | |
return (strlen($a) < strlen($b)) ? -1 : 1; | |
}); | |
foreach ($mashed as $entry) { | |
print $entry . PHP_EOL; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment