mirror of
https://github.com/sigmasternchen/php-doc-en
synced 2025-03-20 10:58:54 +00:00
344 lines
12 KiB
XML
344 lines
12 KiB
XML
<?xml version="1.0" encoding="utf-8"?>
|
|
<!-- $Revision$ -->
|
|
<refentry xml:id="function.htmlspecialchars" xmlns="http://docbook.org/ns/docbook" xmlns:xlink="http://www.w3.org/1999/xlink">
|
|
<refnamediv>
|
|
<refname>htmlspecialchars</refname>
|
|
<refpurpose>Convert special characters to HTML entities</refpurpose>
|
|
</refnamediv>
|
|
|
|
<refsect1 role="description">
|
|
&reftitle.description;
|
|
<methodsynopsis>
|
|
<type>string</type><methodname>htmlspecialchars</methodname>
|
|
<methodparam><type>string</type><parameter>string</parameter></methodparam>
|
|
<methodparam choice="opt"><type>int</type><parameter>flags</parameter><initializer><constant>ENT_QUOTES</constant> | <constant>ENT_SUBSTITUTE</constant> | <constant>ENT_HTML401</constant></initializer></methodparam>
|
|
<methodparam choice="opt"><type class="union"><type>string</type><type>null</type></type><parameter>encoding</parameter><initializer>&null;</initializer></methodparam>
|
|
<methodparam choice="opt"><type>bool</type><parameter>double_encode</parameter><initializer>&true;</initializer></methodparam>
|
|
</methodsynopsis>
|
|
<para>
|
|
Certain characters have special significance in HTML, and should
|
|
be represented by HTML entities if they are to preserve their
|
|
meanings. This function returns a string with these
|
|
conversions made. If you require all input substrings that have associated
|
|
named entities to be translated, use <function>htmlentities</function>
|
|
instead.
|
|
</para>
|
|
<para>
|
|
If the input string passed to this function and the final document share the
|
|
same character set, this function is sufficient to prepare input for
|
|
inclusion in most contexts of an HTML document. If, however, the input can
|
|
represent characters that are not coded in the final document character set
|
|
and you wish to retain those characters (as numeric or named entities),
|
|
both this function and <function>htmlentities</function> (which only encodes
|
|
substrings that have named entity equivalents) may be insufficient.
|
|
You may have to use <function>mb_encode_numericentity</function> instead.
|
|
</para>
|
|
<para>
|
|
<table>
|
|
<title>Performed translations</title>
|
|
<tgroup cols="2">
|
|
<thead>
|
|
<row>
|
|
<entry>Character</entry>
|
|
<entry>Replacement</entry>
|
|
</row>
|
|
</thead>
|
|
<tbody>
|
|
<row>
|
|
<entry><literal>&</literal> (ampersand)</entry>
|
|
<entry><literal>&amp;</literal></entry>
|
|
</row>
|
|
<row>
|
|
<entry><literal>"</literal> (double quote)</entry>
|
|
<entry><literal>&quot;</literal>, unless <constant>ENT_NOQUOTES</constant> is set</entry>
|
|
</row>
|
|
<row>
|
|
<entry><literal>'</literal> (single quote)</entry>
|
|
<entry>
|
|
<literal>&#039;</literal> (for <constant>ENT_HTML401</constant>) or <literal>&apos;</literal> (for
|
|
<constant>ENT_XML1</constant>, <constant>ENT_XHTML</constant> or
|
|
<constant>ENT_HTML5</constant>), but only when
|
|
<constant>ENT_QUOTES</constant> is set
|
|
</entry>
|
|
</row>
|
|
<row>
|
|
<entry><literal><</literal> (less than)</entry>
|
|
<entry><literal>&lt;</literal></entry>
|
|
</row>
|
|
<row>
|
|
<entry><literal>></literal> (greater than)</entry>
|
|
<entry><literal>&gt;</literal></entry>
|
|
</row>
|
|
</tbody>
|
|
</tgroup>
|
|
</table>
|
|
</para>
|
|
</refsect1>
|
|
|
|
<refsect1 role="parameters">
|
|
&reftitle.parameters;
|
|
<para>
|
|
<variablelist>
|
|
<varlistentry>
|
|
<term><parameter>string</parameter></term>
|
|
<listitem>
|
|
<para>
|
|
The <type>string</type> being converted.
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
<varlistentry>
|
|
<term><parameter>flags</parameter></term>
|
|
<listitem>
|
|
<para>
|
|
A bitmask of one or more of the following flags, which specify how to handle quotes,
|
|
invalid code unit sequences and the used document type. The default is
|
|
<literal>ENT_QUOTES | ENT_SUBSTITUTE | ENT_HTML401</literal>.
|
|
<table>
|
|
<title>Available <parameter>flags</parameter> constants</title>
|
|
<tgroup cols="2">
|
|
<thead>
|
|
<row>
|
|
<entry>Constant Name</entry>
|
|
<entry>Description</entry>
|
|
</row>
|
|
</thead>
|
|
<tbody>
|
|
<row>
|
|
<entry><constant>ENT_COMPAT</constant></entry>
|
|
<entry>Will convert double-quotes and leave single-quotes alone.</entry>
|
|
</row>
|
|
<row>
|
|
<entry><constant>ENT_QUOTES</constant></entry>
|
|
<entry>Will convert both double and single quotes.</entry>
|
|
</row>
|
|
<row>
|
|
<entry><constant>ENT_NOQUOTES</constant></entry>
|
|
<entry>Will leave both double and single quotes unconverted.</entry>
|
|
</row>
|
|
<row>
|
|
<entry><constant>ENT_IGNORE</constant></entry>
|
|
<entry>
|
|
Silently discard invalid code unit sequences instead of returning
|
|
an empty string. Using this flag is discouraged as it
|
|
<link xlink:href="&url.delete.nonchars;">may have security implications</link>.
|
|
</entry>
|
|
</row>
|
|
<row>
|
|
<entry><constant>ENT_SUBSTITUTE</constant></entry>
|
|
<entry>
|
|
Replace invalid code unit sequences with a Unicode Replacement Character
|
|
U+FFFD (UTF-8) or &#xFFFD; (otherwise) instead of returning an empty string.
|
|
</entry>
|
|
</row>
|
|
<row>
|
|
<entry><constant>ENT_DISALLOWED</constant></entry>
|
|
<entry>
|
|
Replace invalid code points for the given document type with a
|
|
Unicode Replacement Character U+FFFD (UTF-8) or &#xFFFD;
|
|
(otherwise) instead of leaving them as is. This may be useful, for
|
|
instance, to ensure the well-formedness of XML documents with
|
|
embedded external content.
|
|
</entry>
|
|
</row>
|
|
<row>
|
|
<entry><constant>ENT_HTML401</constant></entry>
|
|
<entry>
|
|
Handle code as HTML 4.01.
|
|
</entry>
|
|
</row>
|
|
<row>
|
|
<entry><constant>ENT_XML1</constant></entry>
|
|
<entry>
|
|
Handle code as XML 1.
|
|
</entry>
|
|
</row>
|
|
<row>
|
|
<entry><constant>ENT_XHTML</constant></entry>
|
|
<entry>
|
|
Handle code as XHTML.
|
|
</entry>
|
|
</row>
|
|
<row>
|
|
<entry><constant>ENT_HTML5</constant></entry>
|
|
<entry>
|
|
Handle code as HTML 5.
|
|
</entry>
|
|
</row>
|
|
</tbody>
|
|
</tgroup>
|
|
</table>
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
<varlistentry>
|
|
<term><parameter>encoding</parameter></term>
|
|
<listitem>
|
|
&strings.parameter.encoding;
|
|
<para>
|
|
For the purposes of this function, the encodings
|
|
<literal>ISO-8859-1</literal>, <literal>ISO-8859-15</literal>,
|
|
<literal>UTF-8</literal>, <literal>cp866</literal>,
|
|
<literal>cp1251</literal>, <literal>cp1252</literal>, and
|
|
<literal>KOI8-R</literal> are effectively equivalent, provided the
|
|
<parameter>string</parameter> itself is valid for the encoding, as
|
|
the characters affected by <function>htmlspecialchars</function> occupy
|
|
the same positions in all of these encodings.
|
|
</para>
|
|
&reference.strings.charsets;
|
|
</listitem>
|
|
</varlistentry>
|
|
<varlistentry>
|
|
<term><parameter>double_encode</parameter></term>
|
|
<listitem>
|
|
<para>
|
|
When <parameter>double_encode</parameter> is turned off PHP will not
|
|
encode existing html entities, the default is to convert everything.
|
|
</para>
|
|
</listitem>
|
|
</varlistentry>
|
|
</variablelist>
|
|
</para>
|
|
</refsect1>
|
|
|
|
<refsect1 role="returnvalues">
|
|
&reftitle.returnvalues;
|
|
<para>
|
|
The converted <type>string</type>.
|
|
</para>
|
|
<para>
|
|
If the input <parameter>string</parameter> contains an invalid code unit
|
|
sequence within the given <parameter>encoding</parameter> an empty string
|
|
will be returned, unless either the <constant>ENT_IGNORE</constant> or
|
|
<constant>ENT_SUBSTITUTE</constant> flags are set.
|
|
</para>
|
|
</refsect1>
|
|
|
|
<refsect1 role="changelog">
|
|
&reftitle.changelog;
|
|
<informaltable>
|
|
<tgroup cols="2">
|
|
<thead>
|
|
<row>
|
|
<entry>&Version;</entry>
|
|
<entry>&Description;</entry>
|
|
</row>
|
|
</thead>
|
|
<tbody>
|
|
<row>
|
|
<entry>8.1.0</entry>
|
|
<entry>
|
|
<parameter>flags</parameter> changed from <constant>ENT_COMPAT</constant> to <constant>ENT_QUOTES</constant> | <constant>ENT_SUBSTITUTE</constant> | <constant>ENT_HTML401</constant>.
|
|
</entry>
|
|
</row>
|
|
</tbody>
|
|
</tgroup>
|
|
</informaltable>
|
|
</refsect1>
|
|
|
|
<refsect1 role="examples">
|
|
&reftitle.examples;
|
|
<para>
|
|
<example>
|
|
<title><function>htmlspecialchars</function> example</title>
|
|
<programlisting role="php">
|
|
<![CDATA[
|
|
<?php
|
|
$new = htmlspecialchars("<a href='test'>Test</a>", ENT_QUOTES);
|
|
echo $new; // <a href='test'>Test</a>
|
|
?>
|
|
]]>
|
|
</programlisting>
|
|
</example>
|
|
</para>
|
|
</refsect1>
|
|
|
|
<refsect1 role="notes">
|
|
&reftitle.notes;
|
|
<note>
|
|
<para>
|
|
Note that this function does not translate anything beyond what
|
|
is listed above. For full entity translation, see
|
|
<function>htmlentities</function>.
|
|
</para>
|
|
</note>
|
|
<note>
|
|
<para>
|
|
In case of an ambiguous <parameter>flags</parameter> value, the following rules apply:
|
|
</para>
|
|
<para>
|
|
<itemizedlist>
|
|
<listitem>
|
|
<simpara>
|
|
When neither of <constant>ENT_COMPAT</constant>, <constant>ENT_QUOTES</constant>,
|
|
<constant>ENT_NOQUOTES</constant> is present, the default is <constant>ENT_NOQUOTES</constant>.
|
|
</simpara>
|
|
</listitem>
|
|
<listitem>
|
|
<simpara>
|
|
When more than one of <constant>ENT_COMPAT</constant>, <constant>ENT_QUOTES</constant>,
|
|
<constant>ENT_NOQUOTES</constant> is present, <constant>ENT_QUOTES</constant> takes the
|
|
highest precedence, followed by <constant>ENT_COMPAT</constant>.
|
|
</simpara>
|
|
</listitem>
|
|
<listitem>
|
|
<simpara>
|
|
When neither of <constant>ENT_HTML401</constant>, <constant>ENT_HTML5</constant>,
|
|
<constant>ENT_XHTML</constant>, <constant>ENT_XML1</constant> is present, the default is
|
|
<constant>ENT_HTML401</constant>.
|
|
</simpara>
|
|
</listitem>
|
|
<listitem>
|
|
<simpara>
|
|
When more than one of <constant>ENT_HTML401</constant>, <constant>ENT_HTML5</constant>,
|
|
<constant>ENT_XHTML</constant>, <constant>ENT_XML1</constant> is present,
|
|
<constant>ENT_HTML5</constant> takes the highest precedence,
|
|
followed by <constant>ENT_XHTML</constant>, <constant>ENT_XML1</constant> and <constant>ENT_HTML401</constant>.
|
|
</simpara>
|
|
</listitem>
|
|
<listitem>
|
|
<simpara>
|
|
When more than one of <constant>ENT_DISALLOWED</constant>, <constant>ENT_IGNORE</constant>,
|
|
<constant>ENT_SUBSTITUTE</constant> are present, <constant>ENT_IGNORE</constant> takes the
|
|
highest precedence, followed by <constant>ENT_SUBSTITUTE</constant>.
|
|
</simpara>
|
|
</listitem>
|
|
</itemizedlist>
|
|
</para>
|
|
</note>
|
|
</refsect1>
|
|
|
|
<refsect1 role="seealso">
|
|
&reftitle.seealso;
|
|
<para>
|
|
<simplelist>
|
|
<member><function>get_html_translation_table</function></member>
|
|
<member><function>htmlspecialchars_decode</function></member>
|
|
<member><function>strip_tags</function></member>
|
|
<member><function>htmlentities</function></member>
|
|
<member><function>nl2br</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
|
|
-->
|