📄 pathscope.html
字号:
<a name="81" href="#81">81</a> <strong>public</strong> <a href="../../../../org/archive/crawler/scope/PathScope.html">PathScope</a>(String name) {<a name="82" href="#82">82</a> <strong>super</strong>(name);<a name="83" href="#83">83</a> setDescription(<a name="84" href="#84">84</a> <span class="string">"PathScope: A scope for path crawls *Deprecated* Use "</span> +<a name="85" href="#85">85</a> <span class="string">"DecidingScope instead. Crawls made with this scope"</span> +<a name="86" href="#86">86</a> <span class="string">" will be limited to a specific portion of the hosts its seeds"</span> +<a name="87" href="#87">87</a> <span class="string">" provide. More specifically the paths those seeds provide."</span> +<a name="88" href="#88">88</a> <span class="string">" For example if one of the seeds is 'archive.org/example/'"</span> + <a name="89" href="#89">89</a> <span class="string">" all URIs under the path 'examples' will be crawled (like"</span> +<a name="90" href="#90">90</a> <span class="string">" 'archive.org/examples/hello.html') but not URIs in other"</span> +<a name="91" href="#91">91</a> <span class="string">" paths or root (i.e. 'archive.org/index.html)."</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>if</strong> (<strong>this</strong>.transitiveFilter == <strong>null</strong>) {<a name="104" href="#104">104</a> <strong>return</strong> <strong>true</strong>;<a name="105" href="#105">105</a> }<a name="106" href="#106">106</a> <strong>return</strong> <strong>this</strong>.transitiveFilter.accepts(o);<a name="107" href="#107">107</a> }<a name="108" href="#108">108</a> <a name="109" href="#109">109</a> <em>/**<em>*</em></em><a name="110" href="#110">110</a> <em> * @param o</em><a name="111" href="#111">111</a> <em> * @return True if focus filter accepts passed object.</em><a name="112" href="#112">112</a> <em> */</em><a name="113" href="#113">113</a> <strong>protected</strong> <strong>boolean</strong> focusAccepts(Object o) {<a name="114" href="#114">114</a> <a href="../../../../org/archive/net/UURI.html">UURI</a> u = UURI.from(o);<a name="115" href="#115">115</a> <strong>if</strong> (u == <strong>null</strong>) {<a name="116" href="#116">116</a> <strong>return</strong> false;<a name="117" href="#117">117</a> }<a name="118" href="#118">118</a> <em class="comment">// Get the seeds to refresh </em><a name="119" href="#119">119</a> Iterator iter = seedsIterator();<a name="120" href="#120">120</a> <strong>while</strong>(iter.hasNext()) {<a name="121" href="#121">121</a> <a href="../../../../org/archive/net/UURI.html">UURI</a> s = (UURI) iter.next();<a name="122" href="#122">122</a> <strong>if</strong> (isSameHost(s, u)) {<a name="123" href="#123">123</a> <strong>try</strong> {<a name="124" href="#124">124</a> <em class="comment">// Protect against non-parseable URIs. See</em><a name="125" href="#125">125</a> <em class="comment">// "[ 910120 ] java.net.URI#getHost fails when</em><a name="126" href="#126">126</a> <em class="comment">// leading digit"</em><a name="127" href="#127">127</a> <strong>if</strong> (s.getPath() == <strong>null</strong> || u.getPath() == <strong>null</strong>) {<a name="128" href="#128">128</a> <strong>continue</strong>;<a name="129" href="#129">129</a> }<a name="130" href="#130">130</a> }<a name="131" href="#131">131</a> <strong>catch</strong> (URIException e) {<a name="132" href="#132">132</a> logger.severe(<span class="string">"Failed get path on "</span> + u + <span class="string">" or "</span> + s +<a name="133" href="#133">133</a> <span class="string">": "</span> + e.getMessage());<a name="134" href="#134">134</a> }<a name="135" href="#135">135</a> <strong>try</strong> {<a name="136" href="#136">136</a> <strong>if</strong> (s.getPath().regionMatches(0, u.getPath(), 0,<a name="137" href="#137">137</a> s.getPath().lastIndexOf('/'))) {<a name="138" href="#138">138</a> <em class="comment">// matches up to last '/'</em><a name="139" href="#139">139</a> checkClose(iter);<a name="140" href="#140">140</a> <strong>return</strong> <strong>true</strong>;<a name="141" href="#141">141</a> } <strong>else</strong> {<a name="142" href="#142">142</a> <em class="comment">// no match; try next seed</em><a name="143" href="#143">143</a> <strong>continue</strong>;<a name="144" href="#144">144</a> }<a name="145" href="#145">145</a> }<a name="146" href="#146">146</a> <strong>catch</strong> (URIException e) {<a name="147" href="#147">147</a> logger.severe(<span class="string">"Failed get path on "</span> + u + <span class="string">" or "</span> + s +<a name="148" href="#148">148</a> <span class="string">": "</span> + e.getMessage());<a name="149" href="#149">149</a> }<a name="150" href="#150">150</a> }<a name="151" href="#151">151</a> }<a name="152" href="#152">152</a> <em class="comment">// if none found, fail</em><a name="153" href="#153">153</a> checkClose(iter);<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 class="comment">// Javadoc inherited</em><a name="158" href="#158">158</a> @Override<a name="159" href="#159">159</a> <strong>protected</strong> <strong>boolean</strong> additionalFocusAccepts(Object o) {<a name="160" href="#160">160</a> <strong>return</strong> <strong>this</strong>.additionalFocusFilter.accepts(o);<a name="161" href="#161">161</a> }<a name="162" href="#162">162</a> <a name="163" href="#163">163</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 + -