You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 

429 lines
13 KiB

<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1">
<meta name="theme-color" content="#375EAB">
<title>unicode - The Go Programming Language</title>
<link type="text/css" rel="stylesheet" href="../../../../../../lib/godoc/style.css">
<link rel="stylesheet" href="../../../../../../lib/godoc/jquery.treeview.css">
<script type="text/javascript">window.initFuncs = [];</script>
</head>
<body>
<div id='lowframe' style="position: fixed; bottom: 0; left: 0; height: 0; width: 100%; border-top: thin solid grey; background-color: white; overflow: auto;">
...
</div><!-- #lowframe -->
<div id="topbar" class="wide"><div class="container">
<div class="top-heading" id="heading-wide"><a href="http://localhost:6060/">The Go Programming Language</a></div>
<div class="top-heading" id="heading-narrow"><a href="http://localhost:6060/">Go</a></div>
<a href="index.html#" id="menu-button"><span id="menu-button-arrow">&#9661;</span></a>
<form method="GET" action="http://localhost:6060/search">
<div id="menu">
<a href="http://localhost:6060/doc/">Documents</a>
<a href="http://localhost:6060/pkg/">Packages</a>
<a href="http://localhost:6060/project/">The Project</a>
<a href="http://localhost:6060/help/">Help</a>
<a href="http://localhost:6060/blog/">Blog</a>
<input type="text" id="search" name="q" class="inactive" value="Search" placeholder="Search">
</div>
</form>
</div></div>
<div id="page" class="wide">
<div class="container">
<h1>Package unicode</h1>
<div id="nav"></div>
<!--
Copyright 2009 The Go Authors. All rights reserved.
Use of this source code is governed by a BSD-style
license that can be found in the LICENSE file.
-->
<!--
Note: Static (i.e., not template-generated) href and id
attributes start with "pkg-" to make it impossible for
them to conflict with generated attributes (some of which
correspond to Go identifiers).
-->
<script type='text/javascript'>
document.ANALYSIS_DATA = null;
document.CALLGRAPH = null;
</script>
<div id="short-nav">
<dl>
<dd><code>import "golang.org/x/text/encoding/unicode"</code></dd>
</dl>
<dl>
<dd><a href="index.html#pkg-overview" class="overviewLink">Overview</a></dd>
<dd><a href="index.html#pkg-index" class="indexLink">Index</a></dd>
<dd><a href="index.html#pkg-subdirectories">Subdirectories</a></dd>
</dl>
</div>
<!-- The package's Name is printed as title by the top-level template -->
<div id="pkg-overview" class="toggleVisible">
<div class="collapsed">
<h2 class="toggleButton" title="Click to show Overview section">Overview ▹</h2>
</div>
<div class="expanded">
<h2 class="toggleButton" title="Click to hide Overview section">Overview ▾</h2>
<p>
Package unicode provides Unicode encodings such as UTF-16.
</p>
</div>
</div>
<div id="pkg-index" class="toggleVisible">
<div class="collapsed">
<h2 class="toggleButton" title="Click to show Index section">Index ▹</h2>
</div>
<div class="expanded">
<h2 class="toggleButton" title="Click to hide Index section">Index ▾</h2>
<!-- Table of contents for API; must be named manual-nav to turn off auto nav. -->
<div id="manual-nav">
<dl>
<dd><a href="index.html#pkg-variables">Variables</a></dd>
<dd><a href="index.html#BOMOverride">func BOMOverride(fallback transform.Transformer) transform.Transformer</a></dd>
<dd><a href="index.html#UTF16">func UTF16(e Endianness, b BOMPolicy) encoding.Encoding</a></dd>
<dd><a href="index.html#BOMPolicy">type BOMPolicy</a></dd>
<dd><a href="index.html#Endianness">type Endianness</a></dd>
</dl>
</div><!-- #manual-nav -->
<h4>Package files</h4>
<p>
<span style="font-size:90%">
<a href="http://localhost:6060/src/golang.org/x/text/encoding/unicode/override.go">override.go</a>
<a href="http://localhost:6060/src/golang.org/x/text/encoding/unicode/unicode.go">unicode.go</a>
</span>
</p>
</div><!-- .expanded -->
</div><!-- #pkg-index -->
<div id="pkg-callgraph" class="toggle" style="display: none">
<div class="collapsed">
<h2 class="toggleButton" title="Click to show Internal Call Graph section">Internal call graph ▹</h2>
</div> <!-- .expanded -->
<div class="expanded">
<h2 class="toggleButton" title="Click to hide Internal Call Graph section">Internal call graph ▾</h2>
<p>
In the call graph viewer below, each node
is a function belonging to this package
and its children are the functions it
calls&mdash;perhaps dynamically.
</p>
<p>
The root nodes are the entry points of the
package: functions that may be called from
outside the package.
There may be non-exported or anonymous
functions among them if they are called
dynamically from another package.
</p>
<p>
Click a node to visit that function's source code.
From there you can visit its callers by
clicking its declaring <code>func</code>
token.
</p>
<p>
Functions may be omitted if they were
determined to be unreachable in the
particular programs or tests that were
analyzed.
</p>
<!-- Zero means show all package entry points. -->
<ul style="margin-left: 0.5in" id="callgraph-0" class="treeview"></ul>
</div>
</div> <!-- #pkg-callgraph -->
<h2 id="pkg-variables">Variables</h2>
<pre>var <span id="All">All</span> = []<a href="../index.html">encoding</a>.<a href="../index.html#Encoding">Encoding</a>{
<a href="index.html#UTF8">UTF8</a>,
<a href="index.html#UTF16">UTF16</a>(<a href="index.html#BigEndian">BigEndian</a>, <a href="index.html#UseBOM">UseBOM</a>),
<a href="index.html#UTF16">UTF16</a>(<a href="index.html#BigEndian">BigEndian</a>, <a href="index.html#IgnoreBOM">IgnoreBOM</a>),
<a href="index.html#UTF16">UTF16</a>(<a href="index.html#LittleEndian">LittleEndian</a>, <a href="index.html#IgnoreBOM">IgnoreBOM</a>),
}</pre>
<p>
All lists a configuration for each IANA-defined UTF-16 variant.
</p>
<pre>var <span id="ErrMissingBOM">ErrMissingBOM</span> = <a href="../../../../../errors/index.html">errors</a>.<a href="../../../../../errors/index.html#New">New</a>(&#34;encoding: missing byte order mark&#34;)</pre>
<p>
ErrMissingBOM means that decoding UTF-16 input with ExpectBOM did not find a
starting byte order mark.
</p>
<pre>var <span id="UTF8">UTF8</span> <a href="../index.html">encoding</a>.<a href="../index.html#Encoding">Encoding</a> = utf8enc</pre>
<p>
UTF8 is the UTF-8 encoding.
</p>
<h2 id="BOMOverride">func <a href="http://localhost:6060/src/golang.org/x/text/encoding/unicode/override.go?s=1109:1179#L17">BOMOverride</a></h2>
<pre>func BOMOverride(fallback <a href="../../transform/index.html">transform</a>.<a href="../../transform/index.html#Transformer">Transformer</a>) <a href="../../transform/index.html">transform</a>.<a href="../../transform/index.html#Transformer">Transformer</a></pre>
<p>
BOMOverride returns a new decoder transformer that is identical to fallback,
except that the presence of a Byte Order Mark at the start of the input
causes it to switch to the corresponding Unicode decoding. It will only
consider BOMs for UTF-8, UTF-16BE, and UTF-16LE.
</p>
<p>
This differs from using ExpectBOM by allowing a BOM to switch to UTF-8, not
just UTF-16 variants, and allowing falling back to any encoding scheme.
</p>
<p>
This technique is recommended by the W3C for use in HTML 5: &#34;For
compatibility with deployed content, the byte order mark (also known as BOM)
is considered more authoritative than anything else.&#34;
<a href="http://www.w3.org/TR/encoding/#specification-hooks">http://www.w3.org/TR/encoding/#specification-hooks</a>
</p>
<p>
Using BOMOverride is mostly intended for use cases where the first characters
of a fallback encoding are known to not be a BOM, for example, for valid HTML
and most encodings.
</p>
<h2 id="UTF16">func <a href="http://localhost:6060/src/golang.org/x/text/encoding/unicode/unicode.go?s=5459:5514#L142">UTF16</a></h2>
<pre>func UTF16(e <a href="index.html#Endianness">Endianness</a>, b <a href="index.html#BOMPolicy">BOMPolicy</a>) <a href="../index.html">encoding</a>.<a href="../index.html#Encoding">Encoding</a></pre>
<p>
UTF16 returns a UTF-16 Encoding for the given default endianness and byte
order mark (BOM) policy.
</p>
<p>
When decoding from UTF-16 to UTF-8, if the BOMPolicy is IgnoreBOM then
neither BOMs U+FEFF nor noncharacters U+FFFE in the input stream will affect
the endianness used for decoding, and will instead be output as their
standard UTF-8 encodings: &#34;\xef\xbb\xbf&#34; and &#34;\xef\xbf\xbe&#34;. If the BOMPolicy
is UseBOM or ExpectBOM a staring BOM is not written to the UTF-8 output.
Instead, it overrides the default endianness e for the remainder of the
transformation. Any subsequent BOMs U+FEFF or noncharacters U+FFFE will not
affect the endianness used, and will instead be output as their standard
UTF-8 encodings. For UseBOM, if there is no starting BOM, it will proceed
with the default Endianness. For ExpectBOM, in that case, the transformation
will return early with an ErrMissingBOM error.
</p>
<p>
When encoding from UTF-8 to UTF-16, a BOM will be inserted at the start of
the output if the BOMPolicy is UseBOM or ExpectBOM. Otherwise, a BOM will not
be inserted. The UTF-8 input does not need to contain a BOM.
</p>
<p>
There is no concept of a &#39;native&#39; endianness. If the UTF-16 data is produced
and consumed in a greater context that implies a certain endianness, use
IgnoreBOM. Otherwise, use ExpectBOM and always produce and consume a BOM.
</p>
<p>
In the language of <a href="http://www.unicode.org/faq/utf_bom.html#bom10">http://www.unicode.org/faq/utf_bom.html#bom10</a>, IgnoreBOM
corresponds to &#34;Where the precise type of the data stream is known... the
BOM should not be used&#34; and ExpectBOM corresponds to &#34;A particular
protocol... may require use of the BOM&#34;.
</p>
<h2 id="BOMPolicy">type <a href="http://localhost:6060/src/golang.org/x/text/encoding/unicode/unicode.go?s=6708:6728#L173">BOMPolicy</a></h2>
<pre>type BOMPolicy <a href="../../../../../builtin/index.html#uint8">uint8</a></pre>
<p>
BOMPolicy is a UTF-16 encoding&#39;s byte order mark policy.
</p>
<pre>const (
<span class="comment">// IgnoreBOM means to ignore any byte order marks.</span>
<span id="IgnoreBOM">IgnoreBOM</span> <a href="index.html#BOMPolicy">BOMPolicy</a> = 0
<span class="comment">// UseBOM means that the UTF-16 form may start with a byte order mark, which</span>
<span class="comment">// will be used to override the default encoding.</span>
<span id="UseBOM">UseBOM</span> <a href="index.html#BOMPolicy">BOMPolicy</a> = writeBOM | acceptBOM
<span class="comment">// ExpectBOM means that the UTF-16 form must start with a byte order mark,</span>
<span class="comment">// which will be used to override the default encoding.</span>
<span id="ExpectBOM">ExpectBOM</span> <a href="index.html#BOMPolicy">BOMPolicy</a> = writeBOM | acceptBOM | requireBOM
)</pre>
<h2 id="Endianness">type <a href="http://localhost:6060/src/golang.org/x/text/encoding/unicode/unicode.go?s=8326:8346#L212">Endianness</a></h2>
<pre>type Endianness <a href="../../../../../builtin/index.html#bool">bool</a></pre>
<p>
Endianness is a UTF-16 encoding&#39;s default endianness.
</p>
<pre>const (
<span class="comment">// BigEndian is UTF-16BE.</span>
<span id="BigEndian">BigEndian</span> <a href="index.html#Endianness">Endianness</a> = <a href="../../../../../builtin/index.html#false">false</a>
<span class="comment">// LittleEndian is UTF-16LE.</span>
<span id="LittleEndian">LittleEndian</span> <a href="index.html#Endianness">Endianness</a> = <a href="../../../../../builtin/index.html#true">true</a>
)</pre>
<h2 id="pkg-subdirectories">Subdirectories</h2>
<div class="pkg-dir">
<table>
<tr>
<th class="pkg-name">Name</th>
<th class="pkg-synopsis">Synopsis</th>
</tr>
<tr>
<td colspan="2"><a href="../index.html">..</a></td>
</tr>
<tr>
<td class="pkg-name" style="padding-left: 0px;">
<a href="utf32/index.html">utf32</a>
</td>
<td class="pkg-synopsis">
Package utf32 provides the UTF-32 Unicode encoding.
</td>
</tr>
</table>
</div>
<div id="footer">
Build version go1.6.<br>
Except as <a href="https://developers.google.com/site-policies#restrictions">noted</a>,
the content of this page is licensed under the
Creative Commons Attribution 3.0 License,
and code is licensed under a <a href="http://localhost:6060/LICENSE">BSD license</a>.<br>
<a href="http://localhost:6060/doc/tos.html">Terms of Service</a> |
<a href="http://www.google.com/intl/en/policies/privacy/">Privacy Policy</a>
</div>
</div><!-- .container -->
</div><!-- #page -->
<!-- TODO(adonovan): load these from <head> using "defer" attribute? -->
<script type="text/javascript" src="../../../../../../lib/godoc/jquery.js"></script>
<script type="text/javascript" src="../../../../../../lib/godoc/jquery.treeview.js"></script>
<script type="text/javascript" src="../../../../../../lib/godoc/jquery.treeview.edit.js"></script>
<script type="text/javascript" src="../../../../../../lib/godoc/godocs.js"></script>
</body>
</html>