php-doc-en/reference/intl/functions/grapheme-extract.xml

<?xml version="1.0" encoding="utf-8"?>
<!-- $Revision: 1.6 $ -->
<refentry xml:id="function.grapheme-extract" xmlns="http://docbook.org/ns/docbook" xmlns:xlink="http://www.w3.org/1999/xlink">
 <refnamediv>
  <refname>grapheme_extract</refname>
  <refpurpose>Function to extract a sequence of default grapheme clusters from a text buffer, which must be encoded in UTF-8.</refpurpose>
 </refnamediv>
 <refsect1 role="description">
  &reftitle.description;
  <para>Procedural style</para>
  <methodsynopsis>
   <type>string</type><methodname>grapheme_extract</methodname>
   <methodparam><type>string</type><parameter>haystack</parameter></methodparam>
   <methodparam><type>int</type><parameter>size</parameter></methodparam>
   <methodparam choice='opt'><type>int</type><parameter>extract_type</parameter></methodparam>
   <methodparam choice='opt'><type>int</type><parameter>start</parameter></methodparam>
   <methodparam choice='opt'><type>int</type><parameter role="reference">next</parameter></methodparam>
  </methodsynopsis>
  <para>
   Function to extract a sequence of default grapheme clusters from a text buffer, which must be encoded in UTF-8. 
  </para> 
  </refsect1>

 <refsect1 role="parameters">
  &reftitle.parameters;
  <para>
   <variablelist>
    <varlistentry>
     <term><parameter>haystack</parameter></term>
     <listitem>
      <para>
       String to search.
      </para>
     </listitem>
    </varlistentry>
    <varlistentry>
     <term><parameter>size</parameter></term>
     <listitem>
      <para>
       Maximum number items - based on the $extract_type - to return.
      </para>
     </listitem>
    </varlistentry>
    <varlistentry>
     <term><parameter>extract_type</parameter></term>
     <listitem>
      <para>
       Defines the type of units referred to by the $size parameter:
      </para>
       <para>
        <simplelist>
         <member>GRAPHEME_EXTR_COUNT (default) - $size is the number of default
         grapheme clusters to extract.</member>
         <member>GRAPHEME_EXTR_MAXBYTES - $size is the maximum number of bytes
         returned.</member>
         <member>GRAPHEME_EXTR_MAXCHARS - $size is the maximum number of UTF-8
         characters returned.</member>
        </simplelist>
       </para>
     </listitem>
    </varlistentry>
    <varlistentry>
     <term><parameter>start</parameter></term>
     <listitem>
      <para>
       Starting position in $haystack in bytes - if given, it must be zero or a
       positive value that is less than or equal to the length of $haystack in
       bytes. The default is zero. If $start does not point to the first byte of a UTF-8
       character, the start position is moved to the next character boundary.
      </para>
     </listitem>
    </varlistentry>
    <varlistentry>
     <term><parameter>next</parameter></term>
     <listitem>
      <para>
       Reference to a value that will be set to the next starting position.
       When the call returns, this may point to the first byte position past the end of the string.
      </para>
     </listitem>
    </varlistentry>
 
   </variablelist>
  </para>
 </refsect1>
   
 
 <refsect1 role="returnvalues">
  &reftitle.returnvalues;
  <para>
   A string starting at offset $start and ending on a default grapheme cluster
   boundary that conforms to the $size and $extract_type specified.
  </para>
 </refsect1>
 
 <refsect1 role="examples">
  &reftitle.examples;
  <example>
   <title><function>grapheme_extract</function> example</title>
   <programlisting role="php">
<![CDATA[
<?php

$char_a_ring_nfd = "a\xCC\x8A";  // 'LATIN SMALL LETTER A WITH RING ABOVE' (U+00E5) normalization form "D"
$char_o_diaeresis_nfd = "o\xCC\x88"; // 'LATIN SMALL LETTER O WITH DIAERESIS' (U+00F6) normalization form "D"

print urlencode(grapheme_extract( $char_a_ring_nfd . $char_o_diaeresis_nfd, 1, GRAPHEME_EXTR_COUNT, 2));

?>
]]>
   </programlisting>
  </example>
  &example.outputs;
  <screen>
<![CDATA[
o%CC%88
]]>
  </screen>
 </refsect1>

 <refsect1 role="seealso">
  &reftitle.seealso;
  <para>
   <simplelist>
    <member><function>grapheme_substr</function></member>
     <member>
      <link xlink:href="&uri.unicode.graphemes;">
       Unicode Text Segmentation: Grapheme Cluster Boundaries
      </link>
     </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:"../../../../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
-->