Last active
September 26, 2016 23:12
-
-
Save enderandpeter/52236c4df006f0017b47eb4e0928f884 to your computer and use it in GitHub Desktop.
A spirited but perhaps ultimately futile attempt to programmatically extract the street name, number, and direction from thousands of non-standardized addresses, using one as an example, that were entered into the Murney Business Dashboard.
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
| $subject = 'LOT 3 PHS 2 S OZ NATURAL FALLS DR'; | |
| $directionals = array('north', 'east', 'south', 'west'); | |
| $pattern = "/(?P<number>^(?:(?:L(?:ot)?|PHS\w*)?(?:\d+(?:th)?(?:\s*\(\d+\))?)?(?:[[:^alnum:]]+)?(?:L(?:ot)?|PHS\w*)?(?:\d+(?:th)?(?:\s*\(\d+\))?)?)+)\s+(?P<direction>north|east|south|west|n|e|s|w)?(?P<street>.*)/i"; | |
| $result = preg_match($pattern, $subject, $matches); | |
| if($result === 1){ | |
| $matches_found = true; | |
| } else if ($result === 0) { | |
| $matches_found = false; | |
| } else { | |
| echo preg_last_error(); | |
| } | |
| ?> | |
| <?php | |
| if($matches_found){ | |
| echo 'Matches Found';?> | |
| <pre> <?php print_r($matches) ?> </pre> | |
| <?php | |
| $street = $matches['street']; | |
| $number = $matches['number']; | |
| $direction = $matches['direction']; | |
| loadModel( 'agentLifecycle/myBusinessDashboard/MyBusinessDashboardTransactions' ); | |
| $showHidden = true; | |
| $allTransactions = MyBusinessDashboardTransactions::GetAll($showHidden); | |
| $abbreviation_map = array( | |
| 'AG' => 'Ash Grove', | |
| 'AU' => 'Aurora', | |
| 'BF' => 'Battlefield', | |
| 'BG' => 'Billings', | |
| 'BD' => "Bois D'Arc", | |
| 'BV' => 'Bolivar', | |
| 'BL' => 'Bolivar', | |
| 'BR' => 'Branson', | |
| 'BT' => 'Brighton', | |
| 'BL' => 'Brookline', | |
| 'BF' => 'Brookline', // Not sure why this is the case, but hey. | |
| 'BN' => 'Bruner', | |
| 'CF' => 'Cape Fair', | |
| 'CA' => 'Carthage', | |
| 'CG' => 'Carthage', | |
| 'CV' => 'Clever', | |
| 'CW' => 'Conway', | |
| 'CR' => 'Crane', | |
| 'FG' => 'Fair Grove', | |
| 'FD' => 'Fordland', | |
| 'FH' => 'Fremont Hills', | |
| 'HV' => 'Highlandville', | |
| 'HS' => 'Hollister', | |
| 'KC' => 'Kimberling City', | |
| 'LB' => 'Louisburg', | |
| 'MF' => 'Marshfield', | |
| 'MV' => 'Mt Vernon', | |
| 'MV' => 'Mt Vernon', | |
| 'NX' => 'Nixa', | |
| 'OZ' => 'Ozark', | |
| 'PH' => 'Pleasant Hope', | |
| 'RS' => 'Reed Spring', | |
| 'RP' => 'Republic', | |
| 'RV' => 'Rogersville', | |
| 'SB' => 'Saddlebrook', | |
| 'SY' => 'Seymour', | |
| 'SP' => 'Sparta', | |
| 'SK' => 'Spokane', | |
| 'ST' => 'Stockton', | |
| 'SF' => 'Strafford', | |
| 'WG' => 'Walnut Grove', | |
| 'WD' => 'Willard', | |
| ); | |
| $street_array = explode(' ', $street); | |
| while(empty($street_array[0])){ | |
| array_shift($street_array); | |
| if(count($street_array) === 0){ | |
| break; | |
| } | |
| } | |
| $first_street_part = trim($street_array[0]); | |
| if(isset($abbreviation_map[$first_street_part])){ | |
| // The first part of the street name is a city abbreviation | |
| array_shift($street_array); | |
| } | |
| $street_name = implode(' ', $street_array); | |
| ?> | |
| <ul id="street_data"> | |
| <li style="font-size: 2em">Address: <?php echo $subject; ?></li> | |
| <li>Street Number: <?php echo $number; ?></li> | |
| <li>Street Direction: <?php echo $direction; ?></li> | |
| <li>Street Name: <?php echo $street_name; ?></li> | |
| </ul> | |
| <?php | |
| } else { | |
| echo 'Matches <strong>Not</strong> Found'; | |
| } | |
| ?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment