PHP: Sanitize & Format US Phone Numbers

sanitize_phone.php

<?php

function sanitize_phone( $phone, $international = false ) {
	$format = "/(?:(?:\+?1\s*(?:[.-]\s*)?)?(?:\(\s*([2-9]1[02-9]|[2-9][02-8]1|[2-9][02-8][02-9])\s*\)|([2-9]1[02-9]|[2-9][02-8]1|[2-9][02-8][02-9]))\s*(?:[.-]\s*)?)?([2-9]1[02-9]|[2-9][02-9]1|[2-9][02-9]{2})\s*(?:[.-]\s*)?([0-9]{4})(?:\s*(?:#|x\.?|ext\.?|extension)\s*(\d+))?$/";
	
	$alt_format = '/^(\+\s*)?((0{0,2}1{1,3}[^\d]+)?\(?\s*([2-9][0-9]{2})\s*[^\d]?\s*([2-9][0-9]{2})\s*[^\d]?\s*([\d]{4})){1}(\s*([[:alpha:]#][^\d]*\d.*))?$/';

	// Trim & Clean extension
    $phone = trim( $phone );
    $phone = preg_replace( '/\s+(#|x|ext(ension)?)\.?:?\s*(\d+)/', ' ext \3', $phone );

    if ( preg_match( $alt_format, $phone, $matches ) ) {
        return '(' . $matches[4] . ') ' . $matches[5] . '-' . $matches[6] . ( !empty( $matches[8] ) ? ' ' . $matches[8] : '' );
    } elseif( preg_match( $format, $phone, $matches ) ) {

    	// format
    	$phone = preg_replace( $format, "($2) $3-$4", $phone );

    	// Remove likely has a preceding dash
    	$phone = ltrim( $phone, '-' );

    	// Remove empty area codes
    	if ( false !== strpos( trim( $phone ), '()', 0 ) ) { 
    		$phone = ltrim( trim( $phone ), '()' );
    	}

    	// Trim and remove double spaces created
    	return preg_replace('/\\s+/', ' ', trim( $phone );
    }

    return false;
}

test-phone.php

$array = array(
	'-234-567-8901',
	'1-234-567-8901',
	'1-234-567-8901 x1234',
	'1-234-567-8901 ext1234',
	'1 (234) 567-8901',
	'1.234.567.8901',
	'1/234/567/8901',
	'12345678901',
	'(+351) 282 43 50 50',
	'90191919908',
	'555-8909',
	'001 6867684',
	'001 6867684x1',
	'1 (234) 567-8901',
	'1-234-567-8901 x1234',
	'1-234-567-8901 ext1234',
	'1-234 567.89/01 ext.1234',
	'1(234)5678901x1234',
	'(123)8575973',
	'(0055)(123)8575973',
	'(123)456-7890',
	'(123)-456-7890',
	'(123) 456-7890',
	'(123) 456-7890 x123',
	'12 1234 123 1 x1111',
	'12 12 12 12 12',
	'12 1 1234 123456 x12345',
	'+12 1234 1234',
	'+12 12 12 1234',
	'+12 1234 5678',
	'+12 12345678',
	'(123)456789',
	'(123456789',
	'(123 456 789',
	'(123.456.789',
	'(123-456-789',
	'123)456789',
	'123) 456 789',
	'123).456.789',
	'123)-456-789',
);

foreach( $array as $phone ) {
    	echo $phone . ': ';
	echo "\t\t" . sanitize_phone( $phone ) . "\n";
}

z-alternative-php.php

<?php

function validate_telephone_number($number, $formats) {
	$format = trim(ereg_replace("[0-9]", "#", $number));

	return (in_array($format, $formats)) ? true : false;
}

/* Usage Examples */

// List of possible formats: You can add new formats or modify the existing ones

$formats = array(
	'###-###-####',
	'####-###-###',
	'(###) ###-###',
	'####-####-####',
	'##-###-####-####',
	'####-####',
	'###-###-###',
	'#####-###-###',
	'##########',
);

$numbers = array(
	'08008-555-555',
	'123-555-555',
	'1800-1234-5678',
	'(800) 555-123',
	'1234567890',
);
foreach ( $numbers as $number ) {

	if ( validate_telephone_number( $number, $formats ) ) {
		echo $number.' is a valid phone number.';
		echo "<br />";
	}
	
}


function sanitize_phone( $phone, $international = false ) {
    $phone = trim( $phone );
    $phone = preg_replace( '/\s+(#|x|ext(ension)?)\.?:?\s*(\d+)/', ' ext \3', $phone );

    $us_number = preg_match( '/^(\+\s*)?((0{0,2}1{1,3}[^\d]+)?\(?\s*([2-9][0-9]{2})\s*[^\d]?\s*([2-9][0-9]{2})\s*[^\d]?\s*([\d]{4})){1}(\s*([[:alpha:]#][^\d]*\d.*))?$/', $phone, $matches );

    if ( $us_number ) {
        return 'US: ' . $matches[4] . '-' . $matches[5] . '-' . $matches[6] . ( !empty( $matches[8] ) ? ' ' . $matches[8] : '' );
    }

    if ( ! $international ) {
        /* SET ERROR: The field must be a valid U.S. phone number (e.g. 888-888-8888) */
        return false;
    }

    $valid_number = preg_match( '/^(\+\s*)?(?=([.,\s()-]*\d){8})([\d(][\d.,\s()-]*)([[:alpha:]#][^\d]*\d.*)?$/', $phone, $matches ) && preg_match( '/\d{2}/', $phone );

    if ( $valid_number ) {
        return trim( $matches[1] ) . trim( $matches[3] ) . ( !empty( $matches[4] ) ? ' ' . $matches[4] : '' );
    }

    /* SET ERROR: The field must be a valid phone number (e.g. 888-888-8888) */
    return false;
}

function formatPhoneNumber( $s ) {
	$rx = "/
	    (1)?\D*     # optional country code
	    (\d{3})?\D* # optional area code
	    (\d{3})\D*  # first three
	    (\d{4})     # last four
	    (?:\D+|$)   # extension delimiter or EOL
	    (\d*)       # optional extension
	/x";
	preg_match($rx, $s, $matches);
	if(!isset($matches[0])) return false;

	$country = $matches[1];
	$area = $matches[2];
	$three = $matches[3];
	$four = $matches[4];
	$ext = $matches[5];

	$out = "$three-$four";
	if(!empty($area)) $out = "$area-$out";
	if(!empty($country)) $out = "+$country-$out";
	if(!empty($ext)) $out .= "x$ext";

	// check that no digits were truncated
	// if (preg_replace('/\D/', '', $s) != preg_replace('/\D/', '', $out)) return false;
	return $out;
}

function format_phone_number ( $mynum, $mask ) {
    /*********************************************************************/
    /*   Purpose: Return either masked phone number or false             */
    /*     Masks: Val=1 or xxx xxx xxxx                                             */
    /*            Val=2 or xxx xxx.xxxx                                             */
    /*            Val=3 or xxx.xxx.xxxx                                             */
    /*            Val=4 or (xxx) xxx xxxx                                           */
    /*            Val=5 or (xxx) xxx.xxxx                                           */
    /*            Val=6 or (xxx).xxx.xxxx                                           */
    /*            Val=7 or (xxx) xxx-xxxx                                           */
    /*            Val=8 or (xxx)-xxx-xxxx                                           */
    /*********************************************************************/         
    $val_num        = validate_phone_number ( $mynum );
    if ( !$val_num && !is_string ( $mynum ) ) { 
        echo "Number $mynum is not a valid phone number! \n";
        return false;
    }   // end if !$val_num
    if ( ( $mask == 1 ) || ( $mask == 'xxx xxx xxxx' ) ) { 
        $phone = preg_replace('~.*(\d{3})[^\d]*(\d{3})[^\d]*(\d{4}).*~', 
                '$1 $2 $3'." \n", $mynum);
        return $phone;
    }   // end if $mask == 1
    if ( ( $mask == 2 ) || ( $mask == 'xxx xxx.xxxx' ) ) { 
        $phone = preg_replace('~.*(\d{3})[^\d]*(\d{3})[^\d]*(\d{4}).*~', 
                '$1 $2.$3'." \n", $mynum);
        return $phone;
    }   // end if $mask == 2
    if ( ( $mask == 3 ) || ( $mask == 'xxx.xxx.xxxx' ) ) { 
        $phone = preg_replace('~.*(\d{3})[^\d]*(\d{3})[^\d]*(\d{4}).*~', 
                '$1.$2.$3'." \n", $mynum);
        return $phone;
    }   // end if $mask == 3
    if ( ( $mask == 4 ) || ( $mask == '(xxx) xxx xxxx' ) ) { 
        $phone = preg_replace('~.*(\d{3})[^\d]*(\d{3})[^\d]*(\d{4}).*~', 
                '($1) $2 $3'." \n", $mynum);
        return $phone;
    }   // end if $mask == 4
    if ( ( $mask == 5 ) || ( $mask == '(xxx) xxx.xxxx' ) ) { 
        $phone = preg_replace('~.*(\d{3})[^\d]*(\d{3})[^\d]*(\d{4}).*~', 
                '($1) $2.$3'." \n", $mynum);
        return $phone;
    }   // end if $mask == 5
    if ( ( $mask == 6 ) || ( $mask == '(xxx).xxx.xxxx' ) ) { 
        $phone = preg_replace('~.*(\d{3})[^\d]*(\d{3})[^\d]*(\d{4}).*~', 
                '($1).$2.$3'." \n", $mynum);
        return $phone;
    }   // end if $mask == 6
    if ( ( $mask == 7 ) || ( $mask == '(xxx) xxx-xxxx' ) ) { 
        $phone = preg_replace('~.*(\d{3})[^\d]*(\d{3})[^\d]*(\d{4}).*~', 
                '($1) $2-$3'." \n", $mynum);
        return $phone;
    }   // end if $mask == 7
    if ( ( $mask == 8 ) || ( $mask == '(xxx)-xxx-xxxx' ) ) { 
        $phone = preg_replace('~.*(\d{3})[^\d]*(\d{3})[^\d]*(\d{4}).*~', 
                '($1)-$2-$3'." \n", $mynum);
        return $phone;
    }   // end if $mask == 8
    return false;       // Returns false if no conditions meet or input
}  // end function format_phone_number

function validate_phone_number ( $phone ) {
    /*********************************************************************/
    /*   Purpose:   To determine if the passed string is a valid phone  */
    /*              number following one of the establish formatting        */
    /*                  styles for phone numbers.  This function also breaks    */
    /*                  a valid number into it's respective components of:      */
    /*                          3-digit area code,                                      */
    /*                          3-digit exchange code,                                  */
    /*                          4-digit subscriber number                               */
    /*                  and validates the number against 10 digit US NANPA  */
    /*                  guidelines.                                                         */
    /*********************************************************************/         
    $format_pattern =   '/^(?:(?:\((?=\d{3}\)))?(\d{3})(?:(?<=\(\d{3})\))'.
                                '?[\s.\/-]?)?(\d{3})[\s\.\/-]?(\d{4})\s?(?:(?:(?:'.
                                '(?:e|x|ex|ext)\.?\:?|extension\:?)\s?)(?=\d+)'.
                                '(\d+))?$/';
    $nanpa_pattern      =   '/^(?:1)?(?(?!(37|96))[2-9][0-8][0-9](?<!(11)))?'.
                                '[2-9][0-9]{2}(?<!(11))[0-9]{4}(?<!(555(01([0-9]'.
                                '[0-9])|1212)))$/';

    // Init array of variables to false
    $valid = array('format' =>  false,
                        'nanpa' => false,
                        'ext'       => false,
                        'all'       => false);

    //Check data against the format analyzer
    if ( preg_match ( $format_pattern, $phone, $matchset ) ) {
        $valid['format'] = true;    
    }

    //If formatted properly, continue
    //if($valid['format']) {
    if ( !$valid['format'] ) {
        return false;
    } else {
        //Set array of new components
        $components =   array ( 'ac' => $matchset[1], //area code
                                                        'xc' => $matchset[2], //exchange code
                                                        'sn' => $matchset[3] //subscriber number
                                                        );
        //              $components =   array ( 'ac' => $matchset[1], //area code
        //                                              'xc' => $matchset[2], //exchange code
        //                                              'sn' => $matchset[3], //subscriber number
        //                                              'xn' => $matchset[4] //extension number             
        //                                              );

        //Set array of number variants
        $numbers    =   array ( 'original' => $matchset[0],
                                    'stripped' => substr(preg_replace('[\D]', '', $matchset[0]), 0, 10)
                                    );

        //Now let's check the first ten digits against NANPA standards
        if(preg_match($nanpa_pattern, $numbers['stripped'])) {
            $valid['nanpa'] = true;
        }

        //If the NANPA guidelines have been met, continue
        if ( $valid['nanpa'] ) {
            if ( !empty ( $components['xn'] ) ) {
                if ( preg_match ( '/^[\d]{1,6}$/', $components['xn'] ) ) {
                    $valid['ext'] = true;
                }   // end if if preg_match 
            } else {
                $valid['ext'] = true;
            }   // end if if  !empty
        }   // end if $valid nanpa

        //If the extension number is valid or non-existent, continue
        if ( $valid['ext'] ) {
            $valid['all'] = true;
        }   // end if $valid ext
    }   // end if $valid
    return $valid['all'];
}   // end functon validate_phone_number

z-alternative-regex.txt

#0
^(?:(?:\+?1\s*(?:[.-]\s*)?)?(?:\(\s*([2-9]1[02-9]|[2-9][02-8]1|[2-9][02-8][02-9])\s*\)|([2-9]1[02-9]|[2-9][02-8]1|[2-9][02-8][02-9]))\s*(?:[.-]\s*)?)?([2-9]1[02-9]|[2-9][02-9]1|[2-9][02-9]{2})\s*(?:[.-]\s*)?([0-9]{4})(?:\s*(?:#|x\.?|ext\.?|extension)\s*(\d+))?$

#1
1?\W*([2-9][0-8][0-9])\W*([2-9][0-9]{2})\W*([0-9]{4})(\se?x?t?(\d*))?
'1?\s*\W?\s*([2-9][0-8][0-9])\s*\W?\s*([2-9][0-9]{2})\s*\W?\s*([0-9]{4})(\se?x?t?(\d*))?';

print "match [$1-$2-$3]\n" if not defined $4;
print "match [$1-$2-$3 $5]\n" if defined $4;

#2
/^(?:(?:\(?(?:00|\+)([1-4]\d\d|[1-9]\d?)\)?)?[\-\.\ \\\/]?)?((?:\(?\d{1,}\)?[\-\.\ \\\/]?){0,})(?:[\-\.\ \\\/]?(?:#|ext\.?|extension|x)[\-\.\ \\\/]?(\d+))?$/i

#3
^((((\(\d{3}\))|(\d{3}-))\d{3}-\d{4})|(\+?\d{2}((-| )\d{1,8}){1,5}))(( x| ext)\d{1,5}){0,1}$

#4
^\d?(?:(?:[\+]?(?:[\d]{1,3}(?:[ ]+|[\-.])))?[(]?(?:[\d]{3})[\-/)]?(?:[ ]+)?)?(?:[a-zA-Z2-9][a-zA-Z0-9 \-.]{6,})(?:(?:[ ]+|[xX]|(i:ext[\.]?)){1,2}(?:[\d]{1,5}))?$

#5
$replace = array( ' ', '-', '/', '(', ')', ',', '.' ); //etc; as needed
 preg_match( '/1?[0-9]{10}((ext|x)[0-9]{1,4})?/i', str_replace( $replace, '', $phone_num );

#6
^(\\(?\\d\\d\\d\\)?)( |-|\\.)?\\d\\d\\d( |-|\\.)?\\d{4,4}(( |-|\\.)?[ext\\.]+ ?\\d+)?$

#7
/\(?([0-9]{3})\)?([ .-]?)([0-9]{3})\2([0-9]{4})/

#8
^(\(?\d{3}\)?)([ .-])(\d{3})([ .-])(\d{4})$

#9
/\(?([0-9]{3})\)?([ .-]?)([0-9]{3})\2([0-9]{4})/

#10
/\(([0-9]{3})\)([ .-]?)([0-9]{3})\2([0-9]{4})|([0-9]{3})([ .-]?)([0-9]{3})\5([0-9]{4})/

#11
^(?:\([2-9]\d{2}\)\ ?|[2-9]\d{2}(?:\-?|\ ?))[2-9]\d{2}[- ]?\d{4}$

+7 (777) 777-7777 ext 777

Fails to validate using sanitize_phone() within the sanitize_phone.php file.

It returns:

+7 (777) 777-7777 ext 777 :: +7 () 777-7777