Online PHP editor | output for jv8vc

<?php function text2num($s) { // Enhanced the regex at http://www.rexegg.com/regex-trick-numbers-in-english.html#english-number-regex $reg = <<<REGEX (?x) # free-spacing mode (?(DEFINE) # Within this DEFINE block, we'll define many subroutines # They build on each other like lego until we can define # a "big number" (?<one_to_9> # The basic regex: # one|two|three|four|five|six|seven|eight|nine # We'll use an optimized version: # Option 1: four|eight|(?:fiv|(?:ni|o)n)e|t(?:wo|hree)| # s(?:ix|even) # Option 2: (?:f(?:ive|our)|s(?:even|ix)|t(?:hree|wo)|(?:ni|o)ne|eight) ) # end one_to_9 definition (?<ten_to_19> # The basic regex: # ten|eleven|twelve|thirteen|fourteen|fifteen|sixteen|seventeen| # eighteen|nineteen # We'll use an optimized version: # Option 1: twelve|(?:(?:elev|t)e|(?:fif|eigh|nine|(?:thi|fou)r| # s(?:ix|even))tee)n # Option 2: (?:(?:(?:s(?:even|ix)|f(?:our|if)|nine)te|e(?:ighte|lev))en| t(?:(?:hirte)?en|welve)) ) # end ten_to_19 definition (?<two_digit_prefix> # The basic regex: # twenty|thirty|forty|fifty|sixty|seventy|eighty|ninety # We'll use an optimized version: # Option 1: (?:fif|six|eigh|nine|(?:tw|sev)en|(?:thi|fo)r)ty # Option 2: (?:s(?:even|ix)|t(?:hir|wen)|f(?:if|or)|eigh|nine)ty ) # end two_digit_prefix definition (?<one_to_99> (?&two_digit_prefix)(?:[- ](?&one_to_9))?|(?&ten_to_19)| (?&one_to_9) ) # end one_to_99 definition (?<one_to_999> (?&one_to_9)[ ]hundred(?:[ ](?:and[ ])?(?&one_to_99))?| (?&one_to_99) ) # end one_to_999 definition (?<one_to_999_999> (?&one_to_999)[ ]thousand(?:[ ](?&one_to_999))?| (?&one_to_999) ) # end one_to_999_999 definition (?<one_to_999_999_999> (?&one_to_999)[ ]million(?:[ ](?&one_to_999_999))?| (?&one_to_999_999) ) # end one_to_999_999_999 definition (?<one_to_999_999_999_999> (?&one_to_999)[ ]billion(?:[ ](?&one_to_999_999_999))?| (?&one_to_999_999_999) ) # end one_to_999_999_999_999 definition (?<one_to_999_999_999_999_999> (?&one_to_999)[ ]trillion(?:[ ](?&one_to_999_999_999_999))?| (?&one_to_999_999_999_999) ) # end one_to_999_999_999_999_999 definition # ==== MORE ==== (?<one_to_quadrillion> (?&one_to_999)[ ]quadrillion(?:[ ](?&one_to_999_999_999_999_999))?| (?&one_to_999_999_999_999_999) ) # end one_to_quadrillion definition (?<one_to_quintillion> (?&one_to_999)[ ]quintillion(?:[ ](?&one_to_quadrillion))?| (?&one_to_quadrillion) ) # end one_to_quintillion definition (?<one_to_sextillion> (?&one_to_999)[ ]sextillion(?:[ ](?&one_to_quintillion))?| (?&one_to_quintillion) ) # end one_to_sextillion definition (?<one_to_septillion> (?&one_to_999)[ ]septillion(?:[ ](?&one_to_sextillion))?| (?&one_to_sextillion) ) # end one_to_septillion definition (?<one_to_octillion> (?&one_to_999)[ ]octillion(?:[ ](?&one_to_septillion))?| (?&one_to_septillion) ) # end one_to_octillion definition (?<one_to_nonillion> (?&one_to_999)[ ]nonillion(?:[ ](?&one_to_octillion))?| (?&one_to_octillion) ) # end one_to_nonillion definition (?<one_to_decillion> (?&one_to_999)[ ]decillion(?:[ ](?&one_to_nonillion))?| (?&one_to_nonillion) ) # end one_to_decillion definition (?<bignumber> zero|(?&one_to_decillion) ) # end bignumber definition (?<zero_to_9> (?&one_to_9)|zero ) # end zero to 9 definition # (?<decimals> # point(?:[ ](?&zero_to_9))+ # ) # end decimals definition ) # End DEFINE ####### The Regex Matching Starts Here ######## \b(?:(?&ten_to_19)\s+hundred|(?&bignumber))\b REGEX; return preg_replace_callback('~' . trim($reg) . '~i', function ($x) { return text2num_internal($x[0]); }, $s); } function text2num_internal($s) { // Port of https://github.com/ghewgill/text2num/blob/master/text2num.py $Small = [ 'zero'=> 0, '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 ]; $Magnitude = [ 'thousand'=> 1000, 'million'=> 1000000, 'billion'=> 1000000000, 'trillion'=> 1000000000000, 'quadrillion'=> 1000000000000000, 'quintillion'=> 1000000000000000000, 'sextillion'=> 1000000000000000000000, 'septillion'=> 1000000000000000000000000, 'octillion'=> 1000000000000000000000000000, 'nonillion'=> 1000000000000000000000000000000, 'decillion'=> 1000000000000000000000000000000000, ]; $a = preg_split("~[\s-]+(?:and[\s-]+)?~u", $s); $a = array_map('strtolower', $a); $n = 0; $g = 0; foreach ($a as $w) { # for w in a if (isset($Small[$w])) { $g = $g + $Small[$w]; } else if ($w == "hundred" && $g != 0) { $g = $g * 100; } else { $x = $Magnitude[$w]; if (strlen($x) > 0) { $n =$n + $g * $x; $g = 0; } else{ throw new Exception("Unknown number: " . $w); } } } return $n + $g; } echo text2num("one") . "\n"; // 1 echo text2num("twelve") . "\n"; // 12 echo text2num("seventy two") . "\n"; // 72 echo text2num("three hundred") . "\n"; // 300 echo text2num("twelve hundred") . "\n"; // 1200 echo text2num("twelve thousand three hundred four") . "\n"; // 12304 echo text2num("six million") . "\n"; // 6000000 echo text2num("six million four hundred thousand five") . "\n"; // 6400005 echo text2num("one hundred twenty three billion four hundred fifty six million seven hundred eighty nine thousand twelve") . "\n"; # // 123456789012 echo text2num("four decillion") . "\n"; // 4000000000000000000000000000000000 echo text2num("five hundred and thirty-seven") . "\n"; // 537 echo text2num("five hundred and thirty seven") . "\n"; // 537