php-doc-en/reference/strings/functions/levenshtein.xml

<?xml version="1.0" encoding="utf-8"?>
<!-- $Revision$ -->
<refentry xmlns="http://docbook.org/ns/docbook" xml:id="function.levenshtein" xmlns:xlink="http://www.w3.org/1999/xlink">
 <refnamediv>
  <refname>levenshtein</refname>
  <refpurpose>Calculate Levenshtein distance between two strings</refpurpose>
 </refnamediv>
 
 <refsect1 role="description">
  &reftitle.description;
  <methodsynopsis>
   <type>int</type><methodname>levenshtein</methodname>
   <methodparam><type>string</type><parameter>str1</parameter></methodparam>
   <methodparam><type>string</type><parameter>str2</parameter></methodparam>
  </methodsynopsis>
  <methodsynopsis>
   <type>int</type><methodname>levenshtein</methodname>
   <methodparam><type>string</type><parameter>str1</parameter></methodparam>
   <methodparam><type>string</type><parameter>str2</parameter></methodparam>
   <methodparam><type>int</type><parameter>cost_ins</parameter></methodparam>
   <methodparam><type>int</type><parameter>cost_rep</parameter></methodparam>
   <methodparam><type>int</type><parameter>cost_del</parameter></methodparam>
  </methodsynopsis>
  <para>
   The Levenshtein distance is defined as the minimal number of
   characters you have to replace, insert or delete to transform
   <parameter>str1</parameter> into <parameter>str2</parameter>.
   The complexity of the algorithm is <literal>O(m*n)</literal>,
   where <literal>n</literal> and <literal>m</literal> are the
   length of <parameter>str1</parameter> and
   <parameter>str2</parameter> (rather good when compared to
   <function>similar_text</function>, which is O(max(n,m)**3),
   but still expensive).
  </para>
  <para>
   In its simplest form the function will take only the two
   strings as parameter and will calculate just the number of
   insert, replace and delete operations needed to transform
   <parameter>str1</parameter> into <parameter>str2</parameter>.
  </para>
  <para>
   A second variant will take three additional parameters that
   define the cost of insert, replace and delete operations.  This
   is more general and adaptive than variant one, but not as
   efficient.
  </para>
 </refsect1>

<refsect1 role="parameters">
  &reftitle.parameters;
  <para>
   <variablelist>
    <varlistentry>
     <term><parameter>str1</parameter></term>
     <listitem>
      <para>
       One of the strings being evaluated for Levenshtein distance.
      </para>
     </listitem>
    </varlistentry>
    <varlistentry>
     <term><parameter>str2</parameter></term>
     <listitem>
      <para>
       One of the strings being evaluated for Levenshtein distance.
      </para>
     </listitem>
    </varlistentry>
    <varlistentry>
     <term><parameter>cost_ins</parameter></term>
     <listitem>
      <para>
       Defines the cost of insertion.
      </para>
     </listitem>
    </varlistentry>
    <varlistentry>
     <term><parameter>cost_rep</parameter></term>
     <listitem>
      <para>
       Defines the cost of replacement.
      </para>
     </listitem>
    </varlistentry>
    <varlistentry>
     <term><parameter>cost_del</parameter></term>
     <listitem>
      <para>
       Defines the cost of deletion.
      </para>
     </listitem>
    </varlistentry>
   </variablelist>
  </para>
 </refsect1>
 
 <refsect1 role="returnvalues">
  &reftitle.returnvalues;
  <para>
   This function returns the Levenshtein-Distance between the
   two argument strings or -1, if one of the argument strings
   is longer than the limit of 255 characters.
  </para>
 </refsect1>
 
 <refsect1 role="examples">
  &reftitle.examples;
  <para>
   <example>
    <title><function>levenshtein</function> example</title>
    <programlisting role="php">
<![CDATA[
<?php
// input misspelled word
$input = 'carrrot';

// array of words to check against
$words  = array('apple','pineapple','banana','orange',
                'radish','carrot','pea','bean','potato');

// no shortest distance found, yet
$shortest = -1;

// loop through words to find the closest
foreach ($words as $word) {

    // calculate the distance between the input word,
    // and the current word
    $lev = levenshtein($input, $word);

    // check for an exact match
    if ($lev == 0) {

        // closest word is this one (exact match)
        $closest = $word;
        $shortest = 0;

        // break out of the loop; we've found an exact match
        break;
    }

    // if this distance is less than the next found shortest
    // distance, OR if a next shortest word has not yet been found
    if ($lev <= $shortest || $shortest < 0) {
        // set the closest match, and shortest distance
        $closest  = $word;
        $shortest = $lev;
    }
}

echo "Input word: $input\n";
if ($shortest == 0) {
    echo "Exact match found: $closest\n";
} else {
    echo "Did you mean: $closest?\n";
}

?>
]]>
    </programlisting>
    &example.outputs;
    <screen>
<![CDATA[
Input word: carrrot
Did you mean: carrot?
]]>
    </screen>
   </example>
  </para>
 </refsect1>

 <refsect1 role="seealso">
  &reftitle.seealso;
  <para>
   <simplelist>
    <member><function>soundex</function></member>
    <member><function>similar_text</function></member>
    <member><function>metaphone</function></member>
   </simplelist>
  </para>
 </refsect1>

</refentry>

<!-- Keep this comment at the end of the file
Local variables:
mode: sgml
sgml-omittag:t
sgml-shorttag:t
sgml-minimize-attributes:nil
sgml-always-quote-attributes:t
sgml-indent-step:1
sgml-indent-data:t
indent-tabs-mode:nil
sgml-parent-document:nil
sgml-default-dtd-file:"~/.phpdoc/manual.ced"
sgml-exposed-tags:nil
sgml-local-catalogs:nil
sgml-local-ecat-files:nil
End:
vim600: syn=xml fen fdm=syntax fdl=2 si
vim: et tw=78 syn=sgml
vi: ts=1 sw=1
-->