📄 classicscope.html
字号:
<a name="116" href="#116">116</a> <em> * @param o</em><a name="117" href="#117">117</a> <em> * Object to test.</em><a name="118" href="#118">118</a> <em> * @return Whether the given object (typically a CandidateURI) falls within</em><a name="119" href="#119">119</a> <em> * this scope.</em><a name="120" href="#120">120</a> <em> */</em><a name="121" href="#121">121</a> <strong>protected</strong> <strong>final</strong> <strong>boolean</strong> innerAccepts(Object o) {<a name="122" href="#122">122</a> <strong>return</strong> forceAccepts(o) || (((isSeed(o) || focusAccepts(o)) ||<a name="123" href="#123">123</a> additionalFocusAccepts(o) || transitiveAccepts(o)) &&<a name="124" href="#124">124</a> !excludeAccepts(o));<a name="125" href="#125">125</a> }<a name="126" href="#126">126</a> <a name="127" href="#127">127</a> <em>/**<em>*</em></em><a name="128" href="#128">128</a> <em> * Check if URI is accepted by the additional focus of this scope.</em><a name="129" href="#129">129</a> <em> * </em><a name="130" href="#130">130</a> <em> * This method should be overridden in subclasses.</em><a name="131" href="#131">131</a> <em> * </em><a name="132" href="#132">132</a> <em> * @param o</em><a name="133" href="#133">133</a> <em> * the URI to check.</em><a name="134" href="#134">134</a> <em> * @return True if additional focus filter accepts passed object.</em><a name="135" href="#135">135</a> <em> */</em><a name="136" href="#136">136</a> <strong>protected</strong> <strong>boolean</strong> additionalFocusAccepts(Object o) {<a name="137" href="#137">137</a> <strong>return</strong> false;<a name="138" href="#138">138</a> }<a name="139" href="#139">139</a> <a name="140" href="#140">140</a> <em>/**<em>*</em></em><a name="141" href="#141">141</a> <em> * @param o</em><a name="142" href="#142">142</a> <em> * the URI to check.</em><a name="143" href="#143">143</a> <em> * @return True if transitive filter accepts passed object.</em><a name="144" href="#144">144</a> <em> */</em><a name="145" href="#145">145</a> <strong>protected</strong> <strong>boolean</strong> transitiveAccepts(Object o) {<a name="146" href="#146">146</a> <strong>return</strong> false;<a name="147" href="#147">147</a> }<a name="148" href="#148">148</a> <a name="149" href="#149">149</a> <em>/**<em>*</em></em><a name="150" href="#150">150</a> <em> * @param o the URI to check.</em><a name="151" href="#151">151</a> <em> * @return True if force-accepts filter accepts passed object.</em><a name="152" href="#152">152</a> <em> */</em><a name="153" href="#153">153</a> <strong>protected</strong> <strong>boolean</strong> forceAccepts(Object o) {<a name="154" href="#154">154</a> <strong>return</strong> false;<a name="155" href="#155">155</a> }<a name="156" href="#156">156</a> <a name="157" href="#157">157</a> <em>/**<em>*</em></em><a name="158" href="#158">158</a> <em> * Check if URI is accepted by the focus of this scope.</em><a name="159" href="#159">159</a> <em> * </em><a name="160" href="#160">160</a> <em> * This method should be overridden in subclasses.</em><a name="161" href="#161">161</a> <em> * </em><a name="162" href="#162">162</a> <em> * @param o</em><a name="163" href="#163">163</a> <em> * the URI to check.</em><a name="164" href="#164">164</a> <em> * @return True if focus filter accepts passed object.</em><a name="165" href="#165">165</a> <em> */</em><a name="166" href="#166">166</a> <strong>protected</strong> <strong>boolean</strong> focusAccepts(Object o) {<a name="167" href="#167">167</a> <em class="comment">// The CrawlScope doesn't accept any URIs</em><a name="168" href="#168">168</a> <strong>return</strong> false;<a name="169" href="#169">169</a> }<a name="170" href="#170">170</a> <a name="171" href="#171">171</a> <em>/**<em>*</em></em><a name="172" href="#172">172</a> <em> * Check if URI is excluded by any filters.</em><a name="173" href="#173">173</a> <em> * </em><a name="174" href="#174">174</a> <em> * @param o</em><a name="175" href="#175">175</a> <em> * the URI to check.</em><a name="176" href="#176">176</a> <em> * @return True if exclude filter accepts passed object.</em><a name="177" href="#177">177</a> <em> */</em><a name="178" href="#178">178</a> <strong>protected</strong> <strong>boolean</strong> excludeAccepts(Object o) {<a name="179" href="#179">179</a> <strong>return</strong> (<strong>this</strong>.excludeFilter.isEmpty(o)) ? exceedsMaxHops(o)<a name="180" href="#180">180</a> : <strong>this</strong>.excludeFilter.accepts(o) || exceedsMaxHops(o);<a name="181" href="#181">181</a> }<a name="182" href="#182">182</a> <a name="183" href="#183">183</a> <em>/**<em>*</em></em><a name="184" href="#184">184</a> <em> * Check if there are too many hops</em><a name="185" href="#185">185</a> <em> * </em><a name="186" href="#186">186</a> <em> * @param o</em><a name="187" href="#187">187</a> <em> * URI to check.</em><a name="188" href="#188">188</a> <em> * @return true if too many hops.</em><a name="189" href="#189">189</a> <em> */</em><a name="190" href="#190">190</a> <strong>protected</strong> <strong>boolean</strong> exceedsMaxHops(Object o) {<a name="191" href="#191">191</a> <strong>if</strong> (!(o instanceof CandidateURI)) {<a name="192" href="#192">192</a> <strong>return</strong> false;<a name="193" href="#193">193</a> }<a name="194" href="#194">194</a> <a name="195" href="#195">195</a> <strong>int</strong> maxLinkHops = 0;<a name="196" href="#196">196</a> <strong>int</strong> maxTransHops = 0;<a name="197" href="#197">197</a> <a name="198" href="#198">198</a> <strong>try</strong> {<a name="199" href="#199">199</a> maxLinkHops = ((Integer) getAttribute(o, ATTR_MAX_LINK_HOPS))<a name="200" href="#200">200</a> .intValue();<a name="201" href="#201">201</a> maxTransHops = ((Integer) getAttribute(o, ATTR_MAX_TRANS_HOPS))<a name="202" href="#202">202</a> .intValue();<a name="203" href="#203">203</a> } <strong>catch</strong> (AttributeNotFoundException e) {<a name="204" href="#204">204</a> <em class="comment">// TODO Auto-generated catch block</em><a name="205" href="#205">205</a> e.printStackTrace();<a name="206" href="#206">206</a> }<a name="207" href="#207">207</a> <a name="208" href="#208">208</a> <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> cand = (CandidateURI) o;<a name="209" href="#209">209</a> <a name="210" href="#210">210</a> String path = cand.getPathFromSeed();<a name="211" href="#211">211</a> <strong>int</strong> linkCount = 0;<a name="212" href="#212">212</a> <strong>int</strong> transCount = 0;<a name="213" href="#213">213</a> <strong>for</strong> (<strong>int</strong> i = path.length() - 1; i >= 0; i--) {<a name="214" href="#214">214</a> <strong>if</strong> (path.charAt(i) == Link.NAVLINK_HOP) {<a name="215" href="#215">215</a> linkCount++;<a name="216" href="#216">216</a> } <strong>else</strong> <strong>if</strong> (linkCount == 0) {<a name="217" href="#217">217</a> transCount++;<a name="218" href="#218">218</a> }<a name="219" href="#219">219</a> }<a name="220" href="#220">220</a> <em class="comment">// return (linkCount > maxLinkHops) || (transCount > maxTransHops);</em><a name="221" href="#221">221</a> <em class="comment">// base only on links, don't treat trans count as hard max</em><a name="222" href="#222">222</a> <strong>return</strong> (linkCount > maxLinkHops);<a name="223" href="#223">223</a> }<a name="224" href="#224">224</a> <a name="225" href="#225">225</a> <em>/**<em>*</em></em><a name="226" href="#226">226</a> <em> * Take note of a situation (such as settings edit) where involved</em><a name="227" href="#227">227</a> <em> * reconfiguration (such as reading from external files) may be necessary.</em><a name="228" href="#228">228</a> <em> */</em><a name="229" href="#229">229</a> <strong>public</strong> <strong>void</strong> kickUpdate() {<a name="230" href="#230">230</a> <strong>super</strong>.kickUpdate();<a name="231" href="#231">231</a> excludeFilter.kickUpdate();<a name="232" href="#232">232</a> }<a name="233" href="#233">233</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 + -