mirror of
https://github.com/sigmasternchen/php-doc-en
synced 2025-03-15 08:28:54 +00:00
86e6094e86
git-svn-id: https://svn.php.net/repository/phpdoc/en/trunk@351133 c90b9560-bf6c-de11-be94-00142212c4b1
447 lines
14 KiB
XML
447 lines
14 KiB
XML
<?xml version="1.0" encoding="utf-8"?>
|
|
<!-- $Revision$ -->
|
|
<section xml:id="intl.collator-constants" xmlns="http://docbook.org/ns/docbook" xmlns:xlink="http://www.w3.org/1999/xlink">
|
|
&reftitle.constants;
|
|
<para>
|
|
<variablelist>
|
|
<varlistentry xml:id="collator.constants.french-collation">
|
|
<term>
|
|
<constant>Collator::FRENCH_COLLATION</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<para>
|
|
Sort strings with different accents from the back of the string. This
|
|
attribute is automatically set to
|
|
<emphasis>On</emphasis>
|
|
for the French locales and a few others. Users normally would not need
|
|
to explicitly set this attribute. There is a string comparison
|
|
performance cost when it is set <emphasis>On</emphasis>,
|
|
but sort key length is unaffected. Possible values are:
|
|
<simplelist>
|
|
<member><constant>Collator::ON</constant></member>
|
|
<member><constant>Collator::OFF</constant>(default)</member>
|
|
<member><constant>Collator::DEFAULT_VALUE</constant></member>
|
|
</simplelist>
|
|
</para>
|
|
<para>
|
|
<example>
|
|
<title>FRENCH_COLLATION rules</title>
|
|
<para>
|
|
<simplelist>
|
|
<member>F=OFF cote < coté < côte < côté </member>
|
|
<member>F=ON cote < côte < coté < côté</member>
|
|
</simplelist>
|
|
</para>
|
|
</example>
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.alternate-handling">
|
|
<term>
|
|
<constant>Collator::ALTERNATE_HANDLING</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<para>
|
|
The Alternate attribute is used to control the handling of the so called
|
|
variable characters in the UCA: whitespace, punctuation and symbols. If
|
|
Alternate is set to <emphasis>NonIgnorable</emphasis>
|
|
(N), then differences among these characters are of the same importance
|
|
as differences among letters. If Alternate is set to
|
|
<emphasis>Shifted</emphasis>
|
|
(S), then these characters are of only minor importance. The
|
|
<emphasis>Shifted</emphasis> value is often used in combination with
|
|
<emphasis>Strength</emphasis>
|
|
set to Quaternary. In such a case, whitespace, punctuation, and symbols
|
|
are considered when comparing strings, but only if all other aspects of
|
|
the strings (base letters, accents, and case) are identical. If
|
|
Alternate is not set to Shifted, then there is no difference between a
|
|
Strength of 3 and a Strength of 4. For more information and examples,
|
|
see Variable_Weighting in the
|
|
<link xlink:href="&url.icu.uca;">UCA</link>.
|
|
The reason the Alternate values are not simply
|
|
<emphasis>On</emphasis> and <emphasis>Off</emphasis>
|
|
is that additional Alternate values may be added in the future. The UCA
|
|
option Blanked is expressed with Strength set to 3, and Alternate set to
|
|
Shifted. The default for most locales is NonIgnorable. If Shifted is
|
|
selected, it may be slower if there are many strings that are the same
|
|
except for punctuation; sort key length will not be affected unless the
|
|
strength level is also increased.
|
|
</para>
|
|
<para>
|
|
Possible values are:
|
|
<simplelist>
|
|
<member><constant>Collator::NON_IGNORABLE</constant>(default)</member>
|
|
<member><constant>Collator::SHIFTED</constant></member>
|
|
<member><constant>Collator::DEFAULT_VALUE</constant></member>
|
|
</simplelist>
|
|
</para>
|
|
<para>
|
|
<example>
|
|
<title>ALTERNATE_HANDLING rules</title>
|
|
<para>
|
|
<simplelist>
|
|
<member>
|
|
S=3, A=N di Silva < Di Silva < diSilva < U.S.A. < USA
|
|
</member>
|
|
<member>
|
|
S=3, A=S di Silva = diSilva < Di Silva < U.S.A. = USA
|
|
</member>
|
|
<member>
|
|
S=4, A=S di Silva < diSilva < Di Silva < U.S.A. < USA
|
|
</member>
|
|
</simplelist>
|
|
</para>
|
|
</example>
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.case-first">
|
|
<term>
|
|
<constant>Collator::CASE_FIRST</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<para>
|
|
The Case_First attribute is used to control whether uppercase letters
|
|
come before lowercase letters or vice versa, in the absence of other
|
|
differences in the strings. The possible values are
|
|
<emphasis>Uppercase_First</emphasis>
|
|
(U) and <emphasis>Lowercase_First</emphasis>
|
|
(L), plus the standard <emphasis>Default</emphasis>
|
|
and <emphasis>Off</emphasis>.
|
|
There is almost no difference between the Off and Lowercase_First
|
|
options in terms of results, so typically users will not use
|
|
Lowercase_First: only Off or Uppercase_First. (People interested in the
|
|
detailed differences between X and L should consult the <literal>Collation
|
|
Customization</literal>). Specifying either L or U won't affect string comparison
|
|
performance, but will affect the sort key length.
|
|
</para>
|
|
<para>
|
|
Possible values are:
|
|
<simplelist>
|
|
<member><constant>Collator::OFF</constant>(default)</member>
|
|
<member><constant>Collator::LOWER_FIRST</constant></member>
|
|
<member><constant>Collator::UPPER_FIRST</constant></member>
|
|
<member><constant>Collator:DEFAULT</constant></member>
|
|
</simplelist>
|
|
</para>
|
|
<para>
|
|
<example>
|
|
<title>CASE_FIRST rules</title>
|
|
<para>
|
|
<simplelist>
|
|
<member>C=X or C=L "china" < "China" < "denmark" < "Denmark"</member>
|
|
<member>C=U "China" < "china" < "Denmark" < "denmark"</member>
|
|
</simplelist>
|
|
</para>
|
|
</example>
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.case-level">
|
|
<term>
|
|
<constant>Collator::CASE_LEVEL</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<para>
|
|
The Case_Level attribute is used when ignoring accents but not case. In
|
|
such a situation, set Strength to be <emphasis>Primary</emphasis>,
|
|
and Case_Level to be <emphasis>On</emphasis>.
|
|
In most locales, this setting is Off by default. There is a small
|
|
string comparison performance and sort key impact if this attribute is
|
|
set to be <emphasis>On</emphasis>.
|
|
</para>
|
|
<para>
|
|
Possible values are:
|
|
<simplelist>
|
|
<member><constant>Collator::OFF</constant>(default)</member>
|
|
<member><constant>Collator::ON</constant></member>
|
|
<member><constant>Collator::DEFAULT_VALUE</constant></member>
|
|
</simplelist>
|
|
</para>
|
|
<para>
|
|
<example>
|
|
<title>CASE_LEVEL rules</title>
|
|
<para>
|
|
<simplelist>
|
|
<member>S=1, E=X role = Role = rôle</member>
|
|
<member>S=1, E=O role = rôle < Role</member>
|
|
</simplelist>
|
|
</para>
|
|
</example>
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.normalization-mode">
|
|
<term>
|
|
<constant>Collator::NORMALIZATION_MODE</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<para>
|
|
The Normalization setting determines whether text is thoroughly
|
|
normalized or not in comparison. Even if the setting is off (which is
|
|
the default for many locales), text as represented in common usage will
|
|
compare correctly (for details, see UTN #5). Only if the accent marks
|
|
are in noncanonical order will there be a problem. If the setting is
|
|
<emphasis>On</emphasis>,
|
|
then the best results are guaranteed for all possible text input.
|
|
There is a medium string comparison performance cost if this attribute
|
|
is <emphasis>On</emphasis>,
|
|
depending on the frequency of sequences that require normalization.
|
|
There is no significant effect on sort key length. If the input text is
|
|
known to be in NFD or NFKD normalization forms, there is no need to
|
|
enable this Normalization option.
|
|
</para>
|
|
<para>
|
|
Possible values are:
|
|
<simplelist>
|
|
<member><constant>Collator::OFF</constant>(default)</member>
|
|
<member><constant>Collator::ON</constant></member>
|
|
<member><constant>Collator::DEFAULT_VALUE</constant></member>
|
|
</simplelist>
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.strength">
|
|
<term>
|
|
<constant>Collator::STRENGTH</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<para>
|
|
The ICU 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.
|
|
For more detailed information, see
|
|
<function>collator_set_strength</function> chapter.
|
|
</para>
|
|
<para>
|
|
Possible values are:
|
|
<simplelist>
|
|
<member><constant>Collator::PRIMARY</constant></member>
|
|
<member><constant>Collator::SECONDARY</constant></member>
|
|
<member><constant>Collator::TERTIARY</constant>(default)</member>
|
|
<member><constant>Collator::QUATERNARY</constant></member>
|
|
<member><constant>Collator::IDENTICAL</constant></member>
|
|
<member><constant>Collator::DEFAULT_VALUE</constant></member>
|
|
</simplelist>
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.hiragana-quaternary-mode">
|
|
<term>
|
|
<constant>Collator::HIRAGANA_QUATERNARY_MODE</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<para>
|
|
Compatibility with JIS x 4061 requires the introduction of an additional
|
|
level to distinguish Hiragana and Katakana characters. If compatibility
|
|
with that standard is required, then this attribute should be set
|
|
<emphasis>On</emphasis>,
|
|
and the strength set to Quaternary. This will affect sort key length
|
|
and string comparison string comparison performance.
|
|
</para>
|
|
<para>
|
|
Possible values are:
|
|
<simplelist>
|
|
<member><constant>Collator::OFF</constant>(default)</member>
|
|
<member><constant>Collator::ON</constant></member>
|
|
<member><constant>Collator::DEFAULT_VALUE</constant></member>
|
|
</simplelist>
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.numeric-collation">
|
|
<term>
|
|
<constant>Collator::NUMERIC_COLLATION</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<para>
|
|
When turned on, this attribute generates a collation key for the numeric
|
|
value of substrings of digits. This is a way to get '100' to sort AFTER
|
|
'2'.
|
|
</para>
|
|
<para>
|
|
Possible values are:
|
|
<simplelist>
|
|
<member><constant>Collator::OFF</constant>(default)</member>
|
|
<member><constant>Collator::ON</constant></member>
|
|
<member><constant>Collator::DEFAULT_VALUE</constant></member>
|
|
</simplelist>
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.default-value">
|
|
<term>
|
|
<constant>Collator::DEFAULT_VALUE</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.primary">
|
|
<term>
|
|
<constant>Collator::PRIMARY</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.secondary">
|
|
<term>
|
|
<constant>Collator::SECONDARY</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.tertiary">
|
|
<term>
|
|
<constant>Collator::TERTIARY</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.default-strength">
|
|
<term>
|
|
<constant>Collator::DEFAULT_STRENGTH</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.quaternary">
|
|
<term>
|
|
<constant>Collator::QUATERNARY</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.identical">
|
|
<term>
|
|
<constant>Collator::IDENTICAL</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.off">
|
|
<term>
|
|
<constant>Collator::OFF</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.on">
|
|
<term>
|
|
<constant>Collator::ON</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.shifted">
|
|
<term>
|
|
<constant>Collator::SHIFTED</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.non-ignorable">
|
|
<term>
|
|
<constant>Collator::NON_IGNORABLE</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.lower-first">
|
|
<term>
|
|
<constant>Collator::LOWER_FIRST</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
|
|
<varlistentry xml:id="collator.constants.upper-first">
|
|
<term>
|
|
<constant>Collator::UPPER_FIRST</constant>
|
|
(<type>int</type>)
|
|
</term>
|
|
<listitem>
|
|
<simpara>
|
|
|
|
</simpara>
|
|
</listitem>
|
|
</varlistentry>
|
|
</variablelist>
|
|
</para>
|
|
</section>
|