⭐ 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

📄 scopeplusonedeciderule.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="97" href="#97">97</a>                  <em class="comment">// If there is no via and the URL doesn't match scope,reject it</em><a name="98" href="#98">98</a>                  <strong>return</strong> false;<a name="99" href="#99">99</a>              }<a name="100" href="#100">100</a>             <em class="comment">// If the via is within scope, accept it</em><a name="101" href="#101">101</a>             result = isInScope (via, set);<a name="102" href="#102">102</a>             <strong>if</strong> (logger.isLoggable(Level.FINE)) {<a name="103" href="#103">103</a>                 logger.fine(<span class="string">"Tested via UURI '"</span> + via +<a name="104" href="#104">104</a>                         <span class="string">" and result was "</span> + result);<a name="105" href="#105">105</a>             }            <a name="106" href="#106">106</a>         }<a name="107" href="#107">107</a>         <strong>return</strong> result;<a name="108" href="#108">108</a>     }<a name="109" href="#109">109</a>     <a name="110" href="#110">110</a>     <em>/**<em>*</em></em><a name="111" href="#111">111</a> <em>     * Synchronized get of prefix set to use</em><a name="112" href="#112">112</a> <em>     * </em><a name="113" href="#113">113</a> <em>     * @return SurtPrefixSet to use for check</em><a name="114" href="#114">114</a> <em>     *@see org.archive.crawler.deciderules.SurtPrefixedDecideRule#getPrefixes()</em><a name="115" href="#115">115</a> <em>     */</em><a name="116" href="#116">116</a>     <strong>protected</strong> <strong>synchronized</strong> <a href="../../../../org/archive/util/SurtPrefixSet.html">SurtPrefixSet</a> getPrefixes() {<a name="117" href="#117">117</a>         <strong>return</strong> getPrefixes(<strong>null</strong>);<a name="118" href="#118">118</a>     } <a name="119" href="#119">119</a>     <a name="120" href="#120">120</a>     <em>/**<em>*</em></em><a name="121" href="#121">121</a> <em>     * Synchronized get of prefix set to use.</em><a name="122" href="#122">122</a> <em>     * @param o Context object.</em><a name="123" href="#123">123</a> <em>     * </em><a name="124" href="#124">124</a> <em>     * @return SurtPrefixSet to use for check</em><a name="125" href="#125">125</a> <em>     * @see org.archive.crawler.deciderules.SurtPrefixedDecideRule#getPrefixes()</em><a name="126" href="#126">126</a> <em>     */</em><a name="127" href="#127">127</a>     <strong>protected</strong> <strong>synchronized</strong> <a href="../../../../org/archive/util/SurtPrefixSet.html">SurtPrefixSet</a> getPrefixes(Object o) {<a name="128" href="#128">128</a>         <strong>if</strong> (surtPrefixes == <strong>null</strong>) {<a name="129" href="#129">129</a>             readPrefixes(o);<a name="130" href="#130">130</a>         }<a name="131" href="#131">131</a>         <strong>return</strong> surtPrefixes;<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>     * Patch the SURT prefix set so that it only includes the appropriate</em><a name="136" href="#136">136</a> <em>     * prefixes.</em><a name="137" href="#137">137</a> <em>     * @param o Context object.</em><a name="138" href="#138">138</a> <em>     * @see org.archive.crawler.deciderules.SurtPrefixedDecideRule#readPrefixes()</em><a name="139" href="#139">139</a> <em>     */</em><a name="140" href="#140">140</a>     <strong>protected</strong> <strong>void</strong> readPrefixes(Object o) {<a name="141" href="#141">141</a>         buildSurtPrefixSet();<a name="142" href="#142">142</a>         <em class="comment">// See whether Host or Domain was chosen</em><a name="143" href="#143">143</a>         String scope = <strong>this</strong>.getScope(o);<a name="144" href="#144">144</a>         <strong>if</strong> (scope.equals(HOST)){<a name="145" href="#145">145</a>             surtPrefixes.convertAllPrefixesToHosts();            <a name="146" href="#146">146</a>         } <strong>else</strong> <strong>if</strong> (scope.equals(DOMAIN)) {<a name="147" href="#147">147</a>             surtPrefixes.convertAllPrefixesToDomains();            <a name="148" href="#148">148</a>         }<a name="149" href="#149">149</a>         dumpSurtPrefixSet();<a name="150" href="#150">150</a>     }        <a name="151" href="#151">151</a>     <a name="152" href="#152">152</a>     <strong>private</strong> <a href="../../../../org/archive/net/UURI.html">UURI</a> getVia(Object o){<a name="153" href="#153">153</a>         <strong>return</strong> (o instanceof CandidateURI)? ((CandidateURI)o).getVia(): <strong>null</strong>;<a name="154" href="#154">154</a>     }    <a name="155" href="#155">155</a> <a name="156" href="#156">156</a>     <em>/**<em>*</em></em><a name="157" href="#157">157</a> <em>     * Decide whether using host or domain scope</em><a name="158" href="#158">158</a> <em>     * @param o Context</em><a name="159" href="#159">159</a> <em>     * @return String Host or domain</em><a name="160" href="#160">160</a> <em>     * </em><a name="161" href="#161">161</a> <em>     */</em><a name="162" href="#162">162</a>     <strong>protected</strong> String getScope(Object o) {<a name="163" href="#163">163</a>         <strong>try</strong> {<a name="164" href="#164">164</a>             String scope = (String)getAttribute(o, ATTR_SCOPE);<a name="165" href="#165">165</a>             <strong>if</strong> (scope.equals(HOST)) {<a name="166" href="#166">166</a>                 <strong>return</strong> HOST;<a name="167" href="#167">167</a>             } <strong>else</strong> <strong>if</strong> (scope.equals(DOMAIN)) {<a name="168" href="#168">168</a>                 <strong>return</strong> DOMAIN;<a name="169" href="#169">169</a>             } <strong>else</strong> {<a name="170" href="#170">170</a>                 assert false : <span class="string">"Unrecognized scope "</span> + scope<a name="171" href="#171">171</a>                         + <span class="string">". Should never happen!"</span>;<a name="172" href="#172">172</a>             }<a name="173" href="#173">173</a>         } <strong>catch</strong> (AttributeNotFoundException e) {<a name="174" href="#174">174</a>             logger.severe(e.getMessage());<a name="175" href="#175">175</a>         }<a name="176" href="#176">176</a>         <strong>return</strong> <strong>null</strong>; <em class="comment">// Basically the rule is inactive if this occurs.</em><a name="177" href="#177">177</a>     }<a name="178" href="#178">178</a>     <a name="179" href="#179">179</a>     <em class="comment">//check that the URI is in scope</em><a name="180" href="#180">180</a>     <strong>private</strong> <strong>boolean</strong> isInScope (Object o, SurtPrefixSet set) {<a name="181" href="#181">181</a>         <strong>boolean</strong> iResult = false;<a name="182" href="#182">182</a>         <a href="../../../../org/archive/net/UURI.html">UURI</a> u = (UURI)o;<a name="183" href="#183">183</a>         <strong>if</strong> (u == <strong>null</strong>) {<a name="184" href="#184">184</a>             <strong>return</strong> false;<a name="185" href="#185">185</a>         }<a name="186" href="#186">186</a>         String candidateSurt = u.getSurtForm();<a name="187" href="#187">187</a>         <em class="comment">// also want to treat https as http</em><a name="188" href="#188">188</a>         <strong>if</strong> (candidateSurt.startsWith(<span class="string">"https:"</span>)) {<a name="189" href="#189">189</a>             candidateSurt = <span class="string">"http:"</span> + candidateSurt.substring(6);<a name="190" href="#190">190</a>         }<a name="191" href="#191">191</a>         <strong>if</strong> (set.containsPrefixOf(candidateSurt)){<a name="192" href="#192">192</a>             iResult = <strong>true</strong>;          <a name="193" href="#193">193</a>         }<a name="194" href="#194">194</a>         <strong>return</strong> iResult;<a name="195" href="#195">195</a>     }<a name="196" href="#196">196</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 + -