📄 xmlreader.html
字号:
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"><html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en"><head><meta http-equiv="content-type" content="text/html; charset=ISO-8859-1" /><title>XmlReader xref</title><link type="text/css" rel="stylesheet" href="../../../../stylesheet.css" /></head><body><div id="overview"><a href="../../../../../apidocs/com/sun/syndication/io/XmlReader.html">View Javadoc</a></div><pre><a name="1" href="#1">1</a> <em class="comment">/*</em><a name="2" href="#2">2</a> <em class="comment"> * Copyright 2004 Sun Microsystems, Inc.</em><a name="3" href="#3">3</a> <em class="comment"> *</em><a name="4" href="#4">4</a> <em class="comment"> * Licensed under the Apache License, Version 2.0 (the "License");</em><a name="5" href="#5">5</a> <em class="comment"> * you may not use this file except in compliance with the License.</em><a name="6" href="#6">6</a> <em class="comment"> * You may obtain a copy of the License at</em><a name="7" href="#7">7</a> <em class="comment"> *</em><a name="8" href="#8">8</a> <em class="comment"> * <a href="http://www.apache.org/licenses/LICENSE-2.0" target="alexandria_uri">http://www.apache.org/licenses/LICENSE-2.0</a></em><a name="9" href="#9">9</a> <em class="comment"> *</em><a name="10" href="#10">10</a> <em class="comment"> * Unless required by applicable law or agreed to in writing, software</em><a name="11" href="#11">11</a> <em class="comment"> * distributed under the License is distributed on an "AS IS" BASIS,</em><a name="12" href="#12">12</a> <em class="comment"> * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</em><a name="13" href="#13">13</a> <em class="comment"> * See the License for the specific language governing permissions and</em><a name="14" href="#14">14</a> <em class="comment"> * limitations under the License.</em><a name="15" href="#15">15</a> <em class="comment"> *</em><a name="16" href="#16">16</a> <em class="comment"> */</em><a name="17" href="#17">17</a> <strong>package</strong> <a href="../../../../com/sun/syndication/io/package-summary.html">com.sun.syndication.io</a>;<a name="18" href="#18">18</a> <a name="19" href="#19">19</a> <strong>import</strong> java.io.*;<a name="20" href="#20">20</a> <strong>import</strong> java.net.URL;<a name="21" href="#21">21</a> <strong>import</strong> java.net.URLConnection;<a name="22" href="#22">22</a> <strong>import</strong> java.net.HttpURLConnection;<a name="23" href="#23">23</a> <strong>import</strong> java.util.regex.Pattern;<a name="24" href="#24">24</a> <strong>import</strong> java.util.regex.Matcher;<a name="25" href="#25">25</a> <strong>import</strong> java.text.MessageFormat;<a name="26" href="#26">26</a> <a name="27" href="#27">27</a> <em>/**<em>*</em></em><a name="28" href="#28">28</a> <em> * Character stream that handles (or at least attemtps to) all the necessary Voodo to figure out</em><a name="29" href="#29">29</a> <em> * the charset encoding of the XML document within the stream.</em><a name="30" href="#30">30</a> <em> * <p></em><a name="31" href="#31">31</a> <em> * IMPORTANT: This class is not related in any way to the org.xml.sax.XMLReader. This one IS a</em><a name="32" href="#32">32</a> <em> * character stream.</em><a name="33" href="#33">33</a> <em> * <p></em><a name="34" href="#34">34</a> <em> * All this has to be done without consuming characters from the stream, if not the XML parser</em><a name="35" href="#35">35</a> <em> * will not recognized the document as a valid XML. This is not 100% true, but it's close enough</em><a name="36" href="#36">36</a> <em> * (UTF-8 BOM is not handled by all parsers right now, XmlReader handles it and things work in all</em><a name="37" href="#37">37</a> <em> * parsers).</em><a name="38" href="#38">38</a> <em> * <p></em><a name="39" href="#39">39</a> <em> * The XmlReader class handles the charset encoding of XML documents in Files, raw streams and</em><a name="40" href="#40">40</a> <em> * HTTP streams by offering a wide set of constructors.</em><a name="41" href="#41">41</a> <em> * <P></em><a name="42" href="#42">42</a> <em> * By default the charset encoding detection is lenient, the constructor with the lenient flag</em><a name="43" href="#43">43</a> <em> * can be used for an script (following HTTP MIME and XML specifications).</em><a name="44" href="#44">44</a> <em> * All this is nicely explained by Mark Pilgrim in his blog,</em><a name="45" href="#45">45</a> <em> * <a href="<a href="http://diveintomark.org/archives/2004/02/13/xml-media-types" target="alexandria_uri">http://diveintomark.org/archives/2004/02/13/xml-media-types</a>"></em><a name="46" href="#46">46</a> <em> * Determining the character encoding of a feed</a>.</em><a name="47" href="#47">47</a> <em> * <p></em><a name="48" href="#48">48</a> <em> * @author Alejandro Abdelnur</em><a name="49" href="#49">49</a> <em> *</em><a name="50" href="#50">50</a> <em> */</em><a name="51" href="#51">51</a> <strong>public</strong> <strong>class</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a> <strong>extends</strong> Reader {<a name="52" href="#52">52</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> <strong>int</strong> PUSHBACK_MAX_SIZE = 4096;<a name="53" href="#53">53</a> <a name="54" href="#54">54</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> String UTF_8 = <span class="string">"UTF-8"</span>;<a name="55" href="#55">55</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> String US_ASCII = <span class="string">"US-ASCII"</span>;<a name="56" href="#56">56</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> String UTF_16BE = <span class="string">"UTF-16BE"</span>;<a name="57" href="#57">57</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> String UTF_16LE = <span class="string">"UTF-16LE"</span>;<a name="58" href="#58">58</a> <strong>private</strong> <strong>static</strong> <strong>final</strong> String UTF_16 = <span class="string">"UTF-16"</span>;<a name="59" href="#59">59</a> <a name="60" href="#60">60</a> <strong>private</strong> Reader _reader;<a name="61" href="#61">61</a> <strong>private</strong> String _encoding;<a name="62" href="#62">62</a> <a name="63" href="#63">63</a> <em>/**<em>*</em></em><a name="64" href="#64">64</a> <em> * Creates a Reader for a File.</em><a name="65" href="#65">65</a> <em> * <p></em><a name="66" href="#66">66</a> <em> * It looks for the UTF-8 BOM first, if none sniffs the XML prolog charset, if this is also</em><a name="67" href="#67">67</a> <em> * missing defaults to UTF-8.</em><a name="68" href="#68">68</a> <em> * <p></em><a name="69" href="#69">69</a> <em> * It does a lenient charset encoding detection, check the constructor with the lenient parameter</em><a name="70" href="#70">70</a> <em> * for details.</em><a name="71" href="#71">71</a> <em> * <p></em><a name="72" href="#72">72</a> <em> * @param file File to create a Reader from.</em><a name="73" href="#73">73</a> <em> * @throws IOException thrown if there is a problem reading the file.</em><a name="74" href="#74">74</a> <em> *</em><a name="75" href="#75">75</a> <em> */</em><a name="76" href="#76">76</a> <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(File file) throws IOException {<a name="77" href="#77">77</a> <strong>this</strong>(<strong>new</strong> FileInputStream(file));<a name="78" href="#78">78</a> }<a name="79" href="#79">79</a> <a name="80" href="#80">80</a> <em>/**<em>*</em></em><a name="81" href="#81">81</a> <em> * Creates a Reader for a raw InputStream.</em><a name="82" href="#82">82</a> <em> * <p></em><a name="83" href="#83">83</a> <em> * It follows the same logic used for files.</em><a name="84" href="#84">84</a> <em> * <p></em><a name="85" href="#85">85</a> <em> * It does a lenient charset encoding detection, check the constructor with the lenient parameter</em><a name="86" href="#86">86</a> <em> * for details.</em><a name="87" href="#87">87</a> <em> * <p></em><a name="88" href="#88">88</a> <em> * @param is InputStream to create a Reader from.</em><a name="89" href="#89">89</a> <em> * @throws IOException thrown if there is a problem reading the stream.</em><a name="90" href="#90">90</a> <em> *</em><a name="91" href="#91">91</a> <em> */</em><a name="92" href="#92">92</a> <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(InputStream is) throws IOException {<a name="93" href="#93">93</a> <strong>this</strong>(is,<strong>true</strong>);<a name="94" href="#94">94</a> }<a name="95" href="#95">95</a> <a name="96" href="#96">96</a> <em>/**<em>*</em></em><a name="97" href="#97">97</a> <em> * Creates a Reader for a raw InputStream.</em><a name="98" href="#98">98</a> <em> * <p></em><a name="99" href="#99">99</a> <em> * It follows the same logic used for files.</em><a name="100" href="#100">100</a> <em> * <p></em><a name="101" href="#101">101</a> <em> * If lenient detection is indicated and the detection above fails as per specifications it then attempts</em><a name="102" href="#102">102</a> <em> * the following:</em><a name="103" href="#103">103</a> <em> * <p></em><a name="104" href="#104">104</a> <em> * If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.</em><a name="105" href="#105">105</a> <em> * <p></em><a name="106" href="#106">106</a> <em> * Else if the XML prolog had a charset encoding that encoding is used.</em><a name="107" href="#107">107</a> <em> * <p></em><a name="108" href="#108">108</a> <em> * Else if the content type had a charset encoding that encoding is used.</em><a name="109" href="#109">109</a> <em> * <p></em><a name="110" href="#110">110</a> <em> * Else 'UTF-8' is used.</em><a name="111" href="#111">111</a> <em> * <p></em><a name="112" href="#112">112</a> <em> * If lenient detection is indicated an XmlReaderException is never thrown.</em><a name="113" href="#113">113</a> <em> * <p></em><a name="114" href="#114">114</a> <em> * @param is InputStream to create a Reader from.</em><a name="115" href="#115">115</a> <em> * @param lenient indicates if the charset encoding detection should be relaxed.</em><a name="116" href="#116">116</a> <em> * @throws IOException thrown if there is a problem reading the stream.</em><a name="117" href="#117">117</a> <em> * @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.</em><a name="118" href="#118">118</a> <em> *</em><a name="119" href="#119">119</a> <em> */</em><a name="120" href="#120">120</a> <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(InputStream is,<strong>boolean</strong> lenient) throws IOException, XmlReaderException {<a name="121" href="#121">121</a> <strong>try</strong> {<a name="122" href="#122">122</a> doRawStream(is,lenient);<a name="123" href="#123">123</a> }<a name="124" href="#124">124</a> <strong>catch</strong> (XmlReaderException ex) {<a name="125" href="#125">125</a> <strong>if</strong> (!lenient) {<a name="126" href="#126">126</a> <strong>throw</strong> ex;<a name="127" href="#127">127</a> }<a name="128" href="#128">128</a> <strong>else</strong> {<a name="129" href="#129">129</a> doLenientDetection(<strong>null</strong>,ex);<a name="130" href="#130">130</a> }<a name="131" href="#131">131</a> }<a name="132" href="#132">132</a> }<a name="133" href="#133">133</a> <a name="134" href="#134">134</a> <em>/**<em>*</em></em><a name="135" href="#135">135</a> <em> * Creates a Reader using the InputStream of a URL.</em><a name="136" href="#136">136</a> <em> * <p></em><a name="137" href="#137">137</a> <em> * If the URL is not of type HTTP and there is not 'content-type' header in the fetched</em><a name="138" href="#138">138</a> <em> * data it uses the same logic used for Files.</em><a name="139" href="#139">139</a> <em> * <p></em>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -