PHP code example of iliaal / phonetic

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

iliaal / phonetic example snippets

double_metaphone_match("Catherine", "Kathryn");   // 2  (strong match)
dm_soundex_match("Moskowitz", "Moskovitz");        // true
bmpm_match("Peterson", "Petersen");                // true

double_metaphone(string $string, int $max_length = 4): array

double_metaphone("Schwarzenegger");        // ['primary' => 'XRSN', 'alternate' => 'XFRT']
double_metaphone("Smith");                 // ['primary' => 'SM0',  'alternate' => 'XMT']
double_metaphone("Catherine", 3);          // ['primary' => 'K0R',  'alternate' => 'KTR']

bmpm(string $string, int $name_type = BMPM_GENERIC, int $accuracy = BMPM_APPROX, string $language = ""): string

bmpm("Jackson");                           // "iakson|iaksun|...|zokson"
bmpm("Garcia", BMPM_SEPHARDIC, BMPM_EXACT);// "garsia|gartSa"

dm_soundex(string $string): array

dm_soundex("Auerbach");                    // ['097400', '097500']
dm_soundex("Peters");                      // ['734000', '739400']
dm_soundex("");                            // []  (API: empty list, not ["000000"])

nysiis(string $string, int $max_length = 6): string

nysiis("Larson");                          // "LARSAN"
nysiis("Larsen");                          // "LARSAN"  (same key)
nysiis("Macdonald", 0);                    // "MCDANALD"  (full, untruncated)

match_rating(string $string): string

match_rating("Smith");                     // "SMTH"
match_rating("Catherine");                 // "CTHRN"

// Double Metaphone: 2 = primary keys agree, 1 = an alternate crosses, 0 = no match
// (a word-final J emits a trailing space into the alternate code, per the
// published algorithm; compare codes as returned, don't trim them)
double_metaphone_match(string $a, string $b, int $max_length = 4): int
double_metaphone_match("Catherine", "Kathryn");          // 2
double_metaphone_match("Vagner", "Wagner");              // 1

// BMPM: true when the phoneme token sets intersect (same args/validation as bmpm())
bmpm_match(string $a, string $b, int $name_type = BMPM_GENERIC, int $accuracy = BMPM_APPROX, string $language = ""): bool
bmpm_match("Moskowitz", "Moskovitz");                    // true
bmpm_match("Peterson", "Petersen", BMPM_GENERIC, BMPM_APPROX); // true
bmpm_match("Peterson", "Petersen", BMPM_GENERIC, BMPM_EXACT);  // false

// Daitch-Mokotoff: true when the code sets intersect among *actually coded* inputs
dm_soundex_match(string $a, string $b): bool
dm_soundex_match("Moskowitz", "Moskovitz");              // true

// NYSIIS: true when the single keys are equal
nysiis_match(string $a, string $b, int $max_length = 6): bool
nysiis_match("Smith", "Schmit");                         // true (both SNAT)

// Match Rating Approach: true when the two names clear the MRA similarity threshold
match_rating_compare(string $a, string $b): bool
match_rating_compare("Catherine", "Kathryn");            // true

double_metaphone_match("Catherine", "Kathryn");   // 2 (strong)
dm_soundex_match("Moskowitz", "Moskovitz");       // true
bmpm_match("Peterson", "Petersen");               // true
match_rating_compare("Catherine", "Kathryn");     // true

// Build a phonetic index, then look up by shared code
$index = [];
foreach ($records as $id => $name) {
    foreach (dm_soundex($name) as $code) {
        // Skip the dual-purpose "000000" sentinel (unencodable *and* pure vowels).
        if ($code === "000000") {
            continue;
        }
        $index[$code][] = $id;
    }
}
// Query every code in the set (not only [0]): branching names like Auerbach
// share a secondary code with Oerback that the first code alone would miss.
$hits = [];
foreach (dm_soundex("Moskovitz") as $code) {
    if ($code === "000000") {
        continue;
    }
    foreach ($index[$code] ?? [] as $id) {
        $hits[$id] = true;
    }
}
$hits = array_keys($hits);

// Splitting a BMPM token string into its individual codes. Prefixed names emit
// grouped output with parentheses (e.g. bmpm("van Smith") => "(zmit)-(...)"), so
// split on '(', ')', '|' and '-' -- the same separators bmpm_match() tokenizes on.
$codes = preg_split('/[()|-]+/', bmpm("van Smith"), -1, PREG_SPLIT_NO_EMPTY);