Created
June 15, 2010 20:04
-
-
Save paranoiq/439646 to your computer and use it in GitHub Desktop.
This file contains hidden or 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 // regular expression for tokenization of english numerals from 1 to 999.999 | |
$re = "/(?<=\W)(?:(?:(?:(?:(?:(?:(?:(one)|(two)|(three)|(four)|(five)|(six)|(seven)|(eight)|(nine))) )?(hundred)s?)? ?(?:and )?(?:(?:(?:(?:(twenty)|(thirty)|(forty)|(fifty)|(sixty)|(seventy)|(eighty)|(ninety))(?:[- ]?(?:(one)|(two)|(three)|(four)|(five)|(six)|(seven)|(eight)|(nine)))?)|(?:(?:(eleven)|(twelve)|(thirteen)|(fourteen)|(fifteen)|(sixteen)|(seventeen)|(eighteen)|(nineteen)))|(?:(?:(one)|(two)|(three)|(four)|(five)|(six)|(seven)|(eight)|(nine)))|(?:(ten))))?) )?(thousand)s?)? ?(?:(?:(?:(?:(?:(one)|(two)|(three)|(four)|(five)|(six)|(seven)|(eight)|(nine))) )?(hundred)s?)? ?(?:and )?(?:(?:(?:(?:(twenty)|(thirty)|(forty)|(fifty)|(sixty)|(seventy)|(eighty)|(ninety))(?:[- ]?(?:(one)|(two)|(three)|(four)|(five)|(six)|(seven)|(eight)|(nine)))?)|(?:(?:(eleven)|(twelve)|(thirteen)|(fourteen)|(fifteen)|(sixteen)|(seventeen)|(eighteen)|(nineteen)))|(?:(?:(one)|(two)|(three)|(four)|(five)|(six)|(seven)|(eight)|(nine)))|(?:(ten))))?)? ?(?:and)? ?(?:(quarter)|(half)|(three quarter)s?)?(?=\W)/um"; | |
// and tokens | |
$tokens = array( | |
'one' => 1, | |
'two' => 2, | |
'three' => 3, | |
'four' => 4, | |
'five' => 5, | |
'six' => 6, | |
'seven' => 7, | |
'eight' => 8, | |
'nine' => 9, | |
'ten' => 10, | |
'eleven' => 11, | |
'twelve' => 12, | |
'thirteen' => 13, | |
'fourteen' => 14, | |
'fifteen' => 15, | |
'sixteen' => 16, | |
'seventeen' => 17, | |
'eighteen' => 18, | |
'nineteen' => 19, | |
'twenty' => 20, | |
'thirty' => 30, | |
'forty' => 40, | |
'fifty' => 50, | |
'sixty' => 60, | |
'seventy' => 70, | |
'eighty' => 80, | |
'ninety' => 90, | |
'hundred' => 100, | |
'thousand' => 1000, | |
'quarter' => '0.25', | |
'half' => '0.5', | |
'three quarter' => '0.75', | |
); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment