mirror of
https://github.com/sigmasternchen/php-doc-en
synced 2025-03-27 14:28:56 +00:00
656d1610af
git-svn-id: https://svn.php.net/repository/phpdoc/en/trunk@330543 c90b9560-bf6c-de11-be94-00142212c4b1
258 lines
8.2 KiB
XML
258 lines
8.2 KiB
XML
<?xml version="1.0" encoding="utf-8"?>
|
|
<!-- $Revision$ -->
|
|
<refentry xml:id="collator.setstrength" xmlns="http://docbook.org/ns/docbook" xmlns:xlink="http://www.w3.org/1999/xlink">
|
|
<refnamediv>
|
|
<refname>Collator::setStrength</refname>
|
|
<refname>collator_set_strength</refname>
|
|
<refpurpose>Set collation strength</refpurpose>
|
|
</refnamediv>
|
|
|
|
<refsect1 role="description">
|
|
&reftitle.description;
|
|
<para>
|
|
&style.oop;
|
|
</para>
|
|
<methodsynopsis>
|
|
<modifier>public</modifier>
|
|
<type>bool</type>
|
|
<methodname>Collator::setStrength</methodname>
|
|
<methodparam><type>int</type><parameter>strength</parameter></methodparam>
|
|
</methodsynopsis>
|
|
<para>
|
|
&style.procedural;
|
|
</para>
|
|
<methodsynopsis>
|
|
<type>bool</type>
|
|
<methodname>collator_set_strength</methodname>
|
|
<methodparam><type>Collator</type><parameter>coll</parameter></methodparam>
|
|
<methodparam><type>int</type><parameter>strength</parameter></methodparam>
|
|
</methodsynopsis>
|
|
<para>
|
|
The
|
|
<link xlink:href="&url.icu.home;">ICU</link>
|
|
Collation Service supports many levels of comparison (named "Levels", but
|
|
also known as "Strengths"). Having these categories enables ICU to sort
|
|
strings precisely according to local conventions. However, by allowing the
|
|
levels to be selectively employed, searching for a string in text can be
|
|
performed with various matching conditions.
|
|
</para>
|
|
<para>
|
|
<orderedlist>
|
|
<listitem>
|
|
<para>
|
|
<emphasis> Primary Level</emphasis>:
|
|
Typically, this is used to denote differences between base characters
|
|
(for example, "a" < "b"). It is the strongest difference. For
|
|
example, dictionaries are divided into different sections by base
|
|
character. This is also called the level1 strength.
|
|
</para>
|
|
</listitem>
|
|
<listitem>
|
|
<para>
|
|
<emphasis> Secondary Level</emphasis>:
|
|
Accents in the characters are considered secondary differences (for
|
|
example, "as" < "às" < "at"). Other differences between letters
|
|
can also be considered secondary differences, depending on the language.
|
|
A secondary difference is ignored when there is a primary difference
|
|
anywhere in the strings. This is also called the level2 strength.
|
|
<note>
|
|
<para>
|
|
Note: In some languages (such as Danish), certain accented letters are
|
|
considered to be separate base characters. In most languages, however,
|
|
an accented letter only has a secondary difference from the unaccented
|
|
version of that letter.
|
|
</para>
|
|
</note>
|
|
</para>
|
|
</listitem>
|
|
<listitem>
|
|
<para>
|
|
<emphasis> Tertiary Level</emphasis>:
|
|
Upper and lower case differences in characters are distinguished at
|
|
the tertiary level (for example, "ao" < "Ao" < "aò"). In addition,
|
|
a variant of a letter differs from the base form on the tertiary level
|
|
(such as "A" and " "). Another example is the difference between large
|
|
and small Kana. A tertiary difference is ignored when there is a primary
|
|
or secondary difference anywhere in the strings. This is also called the
|
|
level3 strength.
|
|
</para>
|
|
</listitem>
|
|
<listitem>
|
|
<para>
|
|
<emphasis> Quaternary Level</emphasis>:
|
|
When punctuation is ignored (see Ignoring Punctuations ) at level 13,
|
|
an additional level can be used to distinguish words with and without
|
|
punctuation (for example, "ab" < "a-b" < "aB"). This difference is
|
|
ignored when there is a primary, secondary or tertiary difference. This
|
|
is also known as the level4 strength. The quaternary level should only
|
|
be used if ignoring punctuation is required or when processing Japanese
|
|
text (see Hiragana processing).
|
|
</para>
|
|
</listitem>
|
|
<listitem>
|
|
<para>
|
|
<emphasis> Identical Level</emphasis>:
|
|
When all other levels are equal, the identical level is used as a
|
|
tiebreaker. The Unicode code point values of the NFD form of each string
|
|
are compared at this level, just in case there is no difference at
|
|
levels 14. For example, Hebrew cantillation marks are only distinguished
|
|
at this level. This level should be used sparingly, as only code point
|
|
values differences between two strings is an extremely rare occurrence.
|
|
Using this level substantially decreases the performance for both
|
|
incremental comparison and sort key generation (as well as increasing
|
|
the sort key length). It is also known as level 5 strength.
|
|
</para>
|
|
</listitem>
|
|
</orderedlist>
|
|
</para>
|
|
<para>
|
|
For example, people may choose to ignore accents or ignore accents and case
|
|
when searching for text. Almost all characters are distinguished by the
|
|
first three levels, and in most locales the default value is thus Tertiary.
|
|
However, if Alternate is set to be Shifted, then the Quaternary strength
|
|
can be used to break ties among whitespace, punctuation, and symbols that
|
|
would otherwise be ignored. If very fine distinctions among characters are
|
|
required, then the Identical strength can be used (for example, Identical
|
|
Strength distinguishes between the Mathematical Bold Small A and the
|
|
Mathematical Italic Small A.). However, using levels higher than Tertiary
|
|
the Identical strength result in significantly longer sort keys, and slower
|
|
string comparison performance for equal strings.
|
|
</para>
|
|
</refsect1>
|
|
|
|
<refsect1 role="parameters">
|
|
&reftitle.parameters;
|
|
<para>
|
|
<variablelist>
|
|
<varlistentry>
|
|
<term><parameter>coll</parameter></term>
|
|
<listitem>
|
|
<para>
|
|
<classname>Collator</classname> object.
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
<varlistentry>
|
|
<term><parameter>strength</parameter></term>
|
|
<listitem>
|
|
<para>Strength to set.</para>
|
|
<para>
|
|
Possible values are:
|
|
<itemizedlist>
|
|
<listitem>
|
|
<para>
|
|
<constant>Collator::PRIMARY</constant>
|
|
</para>
|
|
</listitem>
|
|
<listitem>
|
|
<para>
|
|
<constant>Collator::SECONDARY</constant>
|
|
</para>
|
|
</listitem>
|
|
<listitem>
|
|
<para>
|
|
<constant>Collator::TERTIARY</constant>
|
|
</para>
|
|
</listitem>
|
|
<listitem>
|
|
<para>
|
|
<constant>Collator::QUATERNARY</constant>
|
|
</para>
|
|
</listitem>
|
|
<listitem>
|
|
<para>
|
|
<constant>Collator::IDENTICAL</constant>
|
|
</para>
|
|
</listitem>
|
|
<listitem>
|
|
<para>
|
|
<constant>Collator::DEFAULT</constant>
|
|
</para>
|
|
</listitem>
|
|
</itemizedlist>
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
</variablelist>
|
|
</para>
|
|
</refsect1>
|
|
|
|
<refsect1 role="returnvalues">
|
|
&reftitle.returnvalues;
|
|
<para>
|
|
&return.success;
|
|
</para>
|
|
</refsect1>
|
|
|
|
<refsect1 role="examples">
|
|
&reftitle.examples;
|
|
<para>
|
|
<example>
|
|
<title><function>collator_set_strength</function> example</title>
|
|
<programlisting role="php">
|
|
<![CDATA[
|
|
<?php
|
|
$arr = array( 'aò', 'Ao', 'ao' );
|
|
$coll = collator_create( 'en_US' );
|
|
|
|
// Sort array using default strength.
|
|
collator_sort( $coll, $arr );
|
|
var_export( $arr );
|
|
|
|
// Sort array using primary strength.
|
|
collator_set_strength( $coll, Collator::PRIMARY );
|
|
collator_sort( $coll, $arr );
|
|
var_export( $arr );
|
|
?>
|
|
]]>
|
|
</programlisting>
|
|
&example.outputs;
|
|
<screen>
|
|
<![CDATA[
|
|
array (
|
|
0 => 'ao',
|
|
1 => 'Ao',
|
|
2 => 'aò',
|
|
)
|
|
array (
|
|
0 => 'aò',
|
|
1 => 'Ao',
|
|
2 => 'ao',
|
|
)
|
|
]]>
|
|
</screen>
|
|
</example>
|
|
</para>
|
|
</refsect1>
|
|
|
|
<refsect1 role="seealso">
|
|
&reftitle.seealso;
|
|
<para>
|
|
<simplelist>
|
|
<member><link linkend="intl.collator-constants"><classname>Collator</classname> constants</link></member>
|
|
<member><function>collator_get_strength</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
|
|
-->
|