?? domainscope.html
字號:
<a name="89" href="#89">89</a> <span class="string">" scope will be limited to the domain of its seeds. It will"</span> +<a name="90" href="#90">90</a> <span class="string">" however reach subdomains of the seeds' original domains."</span> +<a name="91" href="#91">91</a> <span class="string">" www[#].host is considered to be the same as host."</span>);<a name="92" href="#92">92</a> <strong>this</strong>.additionalFocusFilter = (Filter) addElementToDefinition(<a name="93" href="#93">93</a> <strong>new</strong> <a href="../../../../org/archive/crawler/filter/FilePatternFilter.html">FilePatternFilter</a>(ATTR_ADDITIONAL_FOCUS_FILTER));<a name="94" href="#94">94</a> <strong>this</strong>.transitiveFilter = (Filter) addElementToDefinition(<a name="95" href="#95">95</a> <strong>new</strong> <a href="../../../../org/archive/crawler/filter/TransclusionFilter.html">TransclusionFilter</a>(ATTR_TRANSITIVE_FILTER));<a name="96" href="#96">96</a> }<a name="97" href="#97">97</a> <a name="98" href="#98">98</a> <em>/**<em>*</em></em><a name="99" href="#99">99</a> <em> * @param o</em><a name="100" href="#100">100</a> <em> * @return True if transitive filter accepts passed object.</em><a name="101" href="#101">101</a> <em> */</em><a name="102" href="#102">102</a> <strong>protected</strong> <strong>boolean</strong> transitiveAccepts(Object o) {<a name="103" href="#103">103</a> <strong>return</strong> <strong>this</strong>.transitiveFilter.accepts(o);<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> * Check if an URI is part of this scope.</em><a name="108" href="#108">108</a> <em> *</em><a name="109" href="#109">109</a> <em> * @param o An instance of UURI or of CandidateURI.</em><a name="110" href="#110">110</a> <em> * @return True if focus filter accepts passed object.</em><a name="111" href="#111">111</a> <em> */</em><a name="112" href="#112">112</a> <strong>protected</strong> <strong>boolean</strong> focusAccepts(Object o) {<a name="113" href="#113">113</a> <a href="../../../../org/archive/net/UURI.html">UURI</a> u = UURI.from(o);<a name="114" href="#114">114</a> <strong>if</strong> (u == <strong>null</strong>) {<a name="115" href="#115">115</a> <strong>return</strong> false;<a name="116" href="#116">116</a> }<a name="117" href="#117">117</a> <em class="comment">// Get the seeds to refresh and then get an iterator inside a</em><a name="118" href="#118">118</a> <em class="comment">// synchronization block. The seeds list may get updated during our</em><a name="119" href="#119">119</a> <em class="comment">// iteration. This will throw a concurrentmodificationexception unless</em><a name="120" href="#120">120</a> <em class="comment">// we synchronize.</em><a name="121" href="#121">121</a> String seedDomain = <strong>null</strong>;<a name="122" href="#122">122</a> String candidateDomain =<strong>null</strong>;<a name="123" href="#123">123</a> <a name="124" href="#124">124</a> <em class="comment">// Get candidate domain where www[0-9]*\. is stripped.</em><a name="125" href="#125">125</a> <strong>try</strong> {<a name="126" href="#126">126</a> candidateDomain = u.getHostBasename();<a name="127" href="#127">127</a> }<a name="128" href="#128">128</a> <strong>catch</strong> (URIException e1) {<a name="129" href="#129">129</a> logger.severe(<a name="130" href="#130">130</a> <span class="string">"UURI getHostBasename failed for candidate URI: "</span> + u);<a name="131" href="#131">131</a> }<a name="132" href="#132">132</a> <strong>if</strong> (candidateDomain == <strong>null</strong>) {<a name="133" href="#133">133</a> <em class="comment">// either an opaque, unfetchable, or unparseable URI</em><a name="134" href="#134">134</a> <strong>return</strong> false;<a name="135" href="#135">135</a> }<a name="136" href="#136">136</a> <a name="137" href="#137">137</a> Iterator iter = seedsIterator();<a name="138" href="#138">138</a> <strong>while</strong>(iter.hasNext()) {<a name="139" href="#139">139</a> <a href="../../../../org/archive/net/UURI.html">UURI</a> s = (UURI)iter.next();<a name="140" href="#140">140</a> <em class="comment">// Get seed domain where www[0-9]*\. is stripped.</em><a name="141" href="#141">141</a> <strong>try</strong> {<a name="142" href="#142">142</a> seedDomain = s.getHostBasename();<a name="143" href="#143">143</a> }<a name="144" href="#144">144</a> <strong>catch</strong> (URIException e) {<a name="145" href="#145">145</a> logger.severe(<span class="string">"UURI getHostBasename failed for seed: "</span> +<a name="146" href="#146">146</a> s);<a name="147" href="#147">147</a> }<a name="148" href="#148">148</a> <strong>if</strong> (seedDomain == <strong>null</strong>) {<a name="149" href="#149">149</a> <em class="comment">// GetHost can come back null. See bug item</em><a name="150" href="#150">150</a> <em class="comment">// [ 910120 ] java.net.URI#getHost fails when leading digit</em><a name="151" href="#151">151</a> <strong>continue</strong>;<a name="152" href="#152">152</a> }<a name="153" href="#153">153</a> <a name="154" href="#154">154</a> <em class="comment">// Check if stripped hosts are same.</em><a name="155" href="#155">155</a> <strong>if</strong> (seedDomain.equals(candidateDomain)) {<a name="156" href="#156">156</a> checkClose(iter);<a name="157" href="#157">157</a> <strong>return</strong> <strong>true</strong>;<a name="158" href="#158">158</a> }<a name="159" href="#159">159</a> <a name="160" href="#160">160</a> <em class="comment">// Hosts are not same. Adjust seed basename to check if</em><a name="161" href="#161">161</a> <em class="comment">// candidate domain ends with .seedDomain</em><a name="162" href="#162">162</a> seedDomain = DOT + seedDomain;<a name="163" href="#163">163</a> <strong>if</strong> (seedDomain.regionMatches(0, candidateDomain,<a name="164" href="#164">164</a> candidateDomain.length() - seedDomain.length(),<a name="165" href="#165">165</a> seedDomain.length())) {<a name="166" href="#166">166</a> <em class="comment">// Domain suffix congruence</em><a name="167" href="#167">167</a> checkClose(iter);<a name="168" href="#168">168</a> <strong>return</strong> <strong>true</strong>;<a name="169" href="#169">169</a> } <em class="comment">// Else keep trying other seeds</em><a name="170" href="#170">170</a> }<a name="171" href="#171">171</a> <em class="comment">// if none found, fail</em><a name="172" href="#172">172</a> checkClose(iter);<a name="173" href="#173">173</a> <strong>return</strong> false;<a name="174" href="#174">174</a> }<a name="175" href="#175">175</a> <a name="176" href="#176">176</a> <strong>protected</strong> <strong>boolean</strong> additionalFocusAccepts(Object o) {<a name="177" href="#177">177</a> <strong>return</strong> additionalFocusFilter.accepts(o);<a name="178" href="#178">178</a> }<a name="179" href="#179">179</a> }</pre><hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body></html>
?? 快捷鍵說明
復制代碼
Ctrl + C
搜索代碼
Ctrl + F
全屏模式
F11
切換主題
Ctrl + Shift + D
顯示快捷鍵
?
增大字號
Ctrl + =
減小字號
Ctrl + -