⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 lowdiskpauseprocessor.html

📁 用JAVA编写的,在做实验的时候留下来的,本来想删的,但是传上来,大家分享吧
💻 HTML
📖 第 1 页 / 共 2 页
字号:
<a name="82" href="#82">82</a>  <em>     */</em><a name="83" href="#83">83</a>      <strong>public</strong> <a href="../../../../org/archive/crawler/postprocessor/LowDiskPauseProcessor.html">LowDiskPauseProcessor</a>(String name) {<a name="84" href="#84">84</a>          <strong>super</strong>(name, <span class="string">"LowDiskPause processor"</span>);<a name="85" href="#85">85</a>          <a href="../../../../org/archive/crawler/settings/Type.html">Type</a> e = addElementToDefinition(<a name="86" href="#86">86</a>              <strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_MONITOR_MOUNTS, <a name="87" href="#87">87</a>                      <span class="string">"Space-delimited list of filessystem mounts whose "</span> +<a name="88" href="#88">88</a>                      <span class="string">"'available' space should be monitored via 'df' "</span> +<a name="89" href="#89">89</a>                      <span class="string">"(if available)."</span>,<a name="90" href="#90">90</a>                  DEFAULT_MONITOR_MOUNTS));<a name="91" href="#91">91</a>          e.setOverrideable(false);<a name="92" href="#92">92</a>          e = addElementToDefinition(<a name="93" href="#93">93</a>              <strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_PAUSE_THRESHOLD, <a name="94" href="#94">94</a>                      <span class="string">"When available space on any monitored mounts falls "</span> +<a name="95" href="#95">95</a>                      <span class="string">"below this threshold, the crawl will be paused. "</span>,<a name="96" href="#96">96</a>                      <strong>new</strong> Integer(DEFAULT_PAUSE_THRESHOLD)));<a name="97" href="#97">97</a>          e = addElementToDefinition(<a name="98" href="#98">98</a>              <strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_RECHECK_THRESHOLD, <a name="99" href="#99">99</a>                      <span class="string">"Available space via 'df' is rechecked after every "</span> +<a name="100" href="#100">100</a>                     <span class="string">"increment of this much content (uncompressed) is "</span> +<a name="101" href="#101">101</a>                     <span class="string">"observed. "</span>,<a name="102" href="#102">102</a>                     <strong>new</strong> Integer(DEFAULT_RECHECK_THRESHOLD)));<a name="103" href="#103">103</a>         e.setOverrideable(false);<a name="104" href="#104">104</a>     } <a name="105" href="#105">105</a>     <a name="106" href="#106">106</a>     <em>/**<em>*</em></em><a name="107" href="#107">107</a> <em>     * Notes a CrawlURI's content size in its running tally. If the </em><a name="108" href="#108">108</a> <em>     * recheck increment of content has passed through since the last</em><a name="109" href="#109">109</a> <em>     * available-space check, checks available space and pauses the </em><a name="110" href="#110">110</a> <em>     * crawl if any monitored mounts are below the configured threshold. </em><a name="111" href="#111">111</a> <em>     * </em><a name="112" href="#112">112</a> <em>     * @param curi CrawlURI to process.</em><a name="113" href="#113">113</a> <em>     */</em><a name="114" href="#114">114</a>     <strong>protected</strong> <strong>void</strong> innerProcess(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {<a name="115" href="#115">115</a>         contentSinceCheck += curi.getContentSize();<a name="116" href="#116">116</a>         <strong>synchronized</strong> (<strong>this</strong>) {<a name="117" href="#117">117</a>             <strong>if</strong> (contentSinceCheck/1024 > ((Integer) getUncheckedAttribute(<strong>null</strong>,<a name="118" href="#118">118</a>                     ATTR_RECHECK_THRESHOLD)).intValue()) {<a name="119" href="#119">119</a>                 checkAvailableSpace(curi);<a name="120" href="#120">120</a>                 contentSinceCheck = 0;<a name="121" href="#121">121</a>             }<a name="122" href="#122">122</a>         }<a name="123" href="#123">123</a>     }<a name="124" href="#124">124</a> <a name="125" href="#125">125</a> <a name="126" href="#126">126</a>     <em>/**<em>*</em></em><a name="127" href="#127">127</a> <em>     * Probe via 'df' to see if monitored mounts have fallen</em><a name="128" href="#128">128</a> <em>     * below the pause available threshold. If so, request a </em><a name="129" href="#129">129</a> <em>     * crawl pause. </em><a name="130" href="#130">130</a> <em>     * @param curi Current context.</em><a name="131" href="#131">131</a> <em>     */</em><a name="132" href="#132">132</a>     <strong>private</strong> <strong>void</strong> checkAvailableSpace(<a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi) {<a name="133" href="#133">133</a>         <strong>try</strong> {<a name="134" href="#134">134</a>             String df = IoUtils.readFullyAsString(Runtime.getRuntime().exec(<a name="135" href="#135">135</a>                     <span class="string">"df -k"</span>).getInputStream());<a name="136" href="#136">136</a>             Matcher matcher = VALID_DF_OUTPUT.matcher(df);<a name="137" href="#137">137</a>             <strong>if</strong>(!matcher.matches()) {<a name="138" href="#138">138</a>                 logger.severe(<span class="string">"'df -k' output unacceptable for low-disk checking"</span>);<a name="139" href="#139">139</a>                 <strong>return</strong>;<a name="140" href="#140">140</a>             }<a name="141" href="#141">141</a>             List monitoredMounts = Arrays.asList(((String) getUncheckedAttribute(<strong>null</strong>,<a name="142" href="#142">142</a>                     ATTR_MONITOR_MOUNTS)).split(<span class="string">"&#47;&#47;s*"</span>));<a name="143" href="#143">143</a>             matcher = AVAILABLE_EXTRACTOR.matcher(df);<a name="144" href="#144">144</a>             <strong>while</strong> (matcher.find()) {<a name="145" href="#145">145</a>                 String mount = matcher.group(2);<a name="146" href="#146">146</a>                 <strong>if</strong> (monitoredMounts.contains(mount)) {<a name="147" href="#147">147</a>                     <strong>long</strong> availKilobytes = Long.parseLong(matcher.group(1));<a name="148" href="#148">148</a>                     <strong>int</strong> thresholdKilobytes = ((Integer) getUncheckedAttribute(<a name="149" href="#149">149</a>                             <strong>null</strong>, ATTR_PAUSE_THRESHOLD)).intValue();<a name="150" href="#150">150</a>                     <strong>if</strong> (availKilobytes &lt; thresholdKilobytes ) {<a name="151" href="#151">151</a>                         getController().requestCrawlPause();<a name="152" href="#152">152</a>                         logger.log(Level.SEVERE, <span class="string">"Low Disk Pause"</span>,<a name="153" href="#153">153</a>                                 availKilobytes + <span class="string">"K available on "</span> + mount<a name="154" href="#154">154</a>                                         + <span class="string">" (below threshold "</span><a name="155" href="#155">155</a>                                         + thresholdKilobytes + <span class="string">"K)"</span>);<a name="156" href="#156">156</a>                         <strong>break</strong>;<a name="157" href="#157">157</a>                     }<a name="158" href="#158">158</a>                 }<a name="159" href="#159">159</a>             }<a name="160" href="#160">160</a>         } <strong>catch</strong> (IOException e) {<a name="161" href="#161">161</a>             curi.addLocalizedError(<strong>this</strong>.getName(), e,<a name="162" href="#162">162</a>                     <span class="string">"problem checking available space via 'df'"</span>);<a name="163" href="#163">163</a>         }<a name="164" href="#164">164</a>     }<a name="165" href="#165">165</a> }</pre><hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body></html>

⌨️ 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 + -