?? filepatternfilter.html
字號(hào):
<a name="88" href="#88">88</a> CUSTOM};<a name="89" href="#89">89</a> <a name="90" href="#90">90</a> addElementToDefinition(<a name="91" href="#91">91</a> <strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_USE_DEFAULT, <span class="string">"URLs that match selected file "</span> +<a name="92" href="#92">92</a> <span class="string">"patterns will be crawled. Default file patterns are:\n"</span> +<a name="93" href="#93">93</a> <span class="string">"Images: .bmp, .gif, .jp(e)g, .png, .tif(f)\nAudio: .mid, "</span> +<a name="94" href="#94">94</a> <span class="string">".mp2, .mp3, .mp4, .wav\nVideo: .avi, .mov, .mpeg, .ram, "</span> +<a name="95" href="#95">95</a> <span class="string">".rm, .smil, .wmv\nMiscellaneous: .doc, .pdf, .ppt, .swf\n"</span> +<a name="96" href="#96">96</a> <span class="string">"All: All above patterns\nChoose 'Custom' to specify your own"</span> +<a name="97" href="#97">97</a> <span class="string">" pattern. These default patterns are case insensitive."</span>,<a name="98" href="#98">98</a> <span class="string">"All"</span>, options));<a name="99" href="#99">99</a> <a name="100" href="#100">100</a> addElementToDefinition(<a name="101" href="#101">101</a> <strong>new</strong> <a href="../../../../org/archive/crawler/settings/SimpleType.html">SimpleType</a>(ATTR_REGEXP, <span class="string">"Custom java regular expression.+n "</span> +<a name="102" href="#102">102</a> <span class="string">"This regular expression will be used instead of the "</span> +<a name="103" href="#103">103</a> <span class="string">"supplied pattern groups for matching.\nAn example "</span> +<a name="104" href="#104">104</a> <span class="string">"of such a regular expression (Miscellaneous):\n"</span> +<a name="105" href="#105">105</a> <span class="string">".*(?i)(//.(doc|pdf|ppt|swf))$\n"</span> +<a name="106" href="#106">106</a> <span class="string">"Any arbitrary reg.expr. is valid though and will be "</span> +<a name="107" href="#107">107</a> <span class="string">"applied to the URI."</span>, <span class="string">""</span>));<a name="108" href="#108">108</a> <a name="109" href="#109">109</a> <a name="110" href="#110">110</a> }<a name="111" href="#111">111</a> <a name="112" href="#112">112</a> <em>/**<em>*</em></em><a name="113" href="#113">113</a> <em> * @see org.archive.crawler.filter.URIRegExpFilter#getRegexp(java.lang.Object)</em><a name="114" href="#114">114</a> <em> */</em><a name="115" href="#115">115</a> <strong>protected</strong> String getRegexp(Object o) {<a name="116" href="#116">116</a> <strong>try</strong> {<a name="117" href="#117">117</a> String patternType = (String)getAttribute(o, ATTR_USE_DEFAULT);<a name="118" href="#118">118</a> <a name="119" href="#119">119</a> <strong>if</strong> (patternType.equals(ALL)) {<a name="120" href="#120">120</a> <strong>return</strong> ALL_DEFAULT_PATTERNS;<a name="121" href="#121">121</a> } <strong>else</strong> <strong>if</strong> (patternType.equals(IMAGES)) {<a name="122" href="#122">122</a> <strong>return</strong> IMAGES_PATTERNS;<a name="123" href="#123">123</a> }<strong>else</strong> <strong>if</strong> (patternType.equals(AUDIO)) {<a name="124" href="#124">124</a> <strong>return</strong> AUDIO_PATTERNS;<a name="125" href="#125">125</a> }<strong>else</strong> <strong>if</strong>(patternType.equals(VIDEO)) {<a name="126" href="#126">126</a> <strong>return</strong> VIDEO_PATTERNS;<a name="127" href="#127">127</a> }<strong>else</strong> <strong>if</strong>(patternType.equals(MISC)) {<a name="128" href="#128">128</a> <strong>return</strong> MISC_PATTERNS;<a name="129" href="#129">129</a> }<strong>else</strong> <strong>if</strong>(patternType.equals(CUSTOM)) {<a name="130" href="#130">130</a> <strong>return</strong> (String) getAttribute(o, ATTR_REGEXP);<a name="131" href="#131">131</a> }<strong>else</strong> {<a name="132" href="#132">132</a> assert false : <span class="string">"Unrecognized pattern type "</span> + patternType +<a name="133" href="#133">133</a> <span class="string">". Should never happened!"</span>;<a name="134" href="#134">134</a> }<a name="135" href="#135">135</a> <a name="136" href="#136">136</a> } <strong>catch</strong> (AttributeNotFoundException e) {<a name="137" href="#137">137</a> logger.log(Level.SEVERE,<span class="string">"necessary setting missing"</span>,e);<a name="138" href="#138">138</a> }<a name="139" href="#139">139</a> <em class="comment">// Basically the filter is inactive if this occurs (The caller</em><a name="140" href="#140">140</a> <em class="comment">// returns 'false' when regexp is null).</em><a name="141" href="#141">141</a> <strong>return</strong> <strong>null</strong>; <a name="142" href="#142">142</a> }<a name="143" href="#143">143</a> <a name="144" href="#144">144</a> <em>/**<em>*</em></em><a name="145" href="#145">145</a> <em> * @see org.archive.crawler.framework.Filter#accepts(java.lang.Object)</em><a name="146" href="#146">146</a> <em> */</em><a name="147" href="#147">147</a> <strong>public</strong> <strong>boolean</strong> accepts(Object o) {<a name="148" href="#148">148</a> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi = (o instanceof CrawlURI) ? (CrawlURI) o : <strong>null</strong>;<a name="149" href="#149">149</a> <a name="150" href="#150">150</a> <em class="comment">// Skip the evaluation if the filter is disabled.</em><a name="151" href="#151">151</a> <em class="comment">// Since this filter is primarily used with seed and focus filters</em><a name="152" href="#152">152</a> <em class="comment">// it has to return false when disabled -- unlike Filter's accepts</em><a name="153" href="#153">153</a> <em class="comment">// method.</em><a name="154" href="#154">154</a> <strong>try</strong> {<a name="155" href="#155">155</a> <strong>if</strong> (!((Boolean) getAttribute(ATTR_ENABLED, curi)).booleanValue()) {<a name="156" href="#156">156</a> <strong>return</strong> false;<a name="157" href="#157">157</a> }<a name="158" href="#158">158</a> } <strong>catch</strong> (AttributeNotFoundException e) {<a name="159" href="#159">159</a> logger.severe(e.getMessage());<a name="160" href="#160">160</a> }<a name="161" href="#161">161</a> <a name="162" href="#162">162</a> <strong>boolean</strong> accept = returnTrueIfMatches(curi) == innerAccepts(o);<a name="163" href="#163">163</a> <a name="164" href="#164">164</a> <strong>if</strong> (accept && logger.isLoggable(Level.FINEST)) {<a name="165" href="#165">165</a> <em class="comment">// Log if filter returns true</em><a name="166" href="#166">166</a> <a href="../../../../org/archive/crawler/settings/ComplexType.html">ComplexType</a> p = <strong>this</strong>.getParent();<a name="167" href="#167">167</a> <strong>if</strong> (p instanceof MapType) {<a name="168" href="#168">168</a> p = p.getParent();<a name="169" href="#169">169</a> }<a name="170" href="#170">170</a> String msg = <strong>this</strong>.toString() + <span class="string">" belonging to "</span> + p.toString()<a name="171" href="#171">171</a> + <span class="string">" accepted "</span> + o.toString();<a name="172" href="#172">172</a> logger.finest(msg);<a name="173" href="#173">173</a> }<a name="174" href="#174">174</a> <a name="175" href="#175">175</a> <strong>return</strong> accept;<a name="176" href="#176">176</a> }<a name="177" href="#177">177</a> <a name="178" href="#178">178</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(fù)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(hào)
Ctrl + =
減小字號(hào)
Ctrl + -