statisticstracking.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

<a name="108" href="#108">108</a> <em>     *</em>
<a name="109" href="#109">109</a> <em>     * @return The total number of uncompressed bytes written to disk</em>
<a name="110" href="#110">110</a> <em>     */</em>
<a name="111" href="#111">111</a>     <strong>public</strong> <strong>long</strong> totalBytesWritten();
<a name="112" href="#112">112</a>     
<a name="113" href="#113">113</a>     <em>/**<em>*</em></em>
<a name="114" href="#114">114</a> <em>     * Total amount of time spent actively crawling so far.&lt;p></em>
<a name="115" href="#115">115</a> <em>     * Returns the total amount of time (in milliseconds) that has elapsed from</em>
<a name="116" href="#116">116</a> <em>     * the start of the crawl and until the current time or if the crawl has</em>
<a name="117" href="#117">117</a> <em>     * ended until the the end of the crawl &lt;b>minus&lt;/b> any</em>
<a name="118" href="#118">118</a> <em>     * time spent paused.</em>
<a name="119" href="#119">119</a> <em>     * @return Total amount of time (in msec.) spent crawling so far.</em>
<a name="120" href="#120">120</a> <em>     */</em>
<a name="121" href="#121">121</a>     <strong>public</strong> <strong>long</strong> getCrawlerTotalElapsedTime();
<a name="122" href="#122">122</a>     
<a name="123" href="#123">123</a>     <em>/**<em>*</em></em>
<a name="124" href="#124">124</a> <em>     * Returns an estimate of recent document download rates</em>
<a name="125" href="#125">125</a> <em>     * based on a queue of recently seen CrawlURIs (as of last snapshot).</em>
<a name="126" href="#126">126</a> <em>     *</em>
<a name="127" href="#127">127</a> <em>     * @return The rate per second of documents gathered during the last</em>
<a name="128" href="#128">128</a> <em>     * snapshot</em>
<a name="129" href="#129">129</a> <em>     */</em>
<a name="130" href="#130">130</a>     <strong>public</strong> <strong>double</strong> currentProcessedDocsPerSec();
<a name="131" href="#131">131</a>     
<a name="132" href="#132">132</a>     <em>/**<em>*</em></em>
<a name="133" href="#133">133</a> <em>     * Returns the number of documents that have been processed</em>
<a name="134" href="#134">134</a> <em>     * per second over the life of the crawl (as of last snapshot)</em>
<a name="135" href="#135">135</a> <em>     *</em>
<a name="136" href="#136">136</a> <em>     * @return  The rate per second of documents gathered so far</em>
<a name="137" href="#137">137</a> <em>     */</em>
<a name="138" href="#138">138</a>     <strong>public</strong> <strong>double</strong> processedDocsPerSec();
<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>     * Calculates the rate that data, in kb, has been processed</em>
<a name="142" href="#142">142</a> <em>     * over the life of the crawl (as of last snapshot.)</em>
<a name="143" href="#143">143</a> <em>     *</em>
<a name="144" href="#144">144</a> <em>     * @return The rate per second of KB gathered so far</em>
<a name="145" href="#145">145</a> <em>     */</em>
<a name="146" href="#146">146</a>     <strong>public</strong> <strong>long</strong> processedKBPerSec();
<a name="147" href="#147">147</a> 
<a name="148" href="#148">148</a>     <em>/**<em>*</em></em>
<a name="149" href="#149">149</a> <em>     * Calculates an estimate of the rate, in kb, at which documents</em>
<a name="150" href="#150">150</a> <em>     * are currently being processed by the crawler.  For more</em>
<a name="151" href="#151">151</a> <em>     * accurate estimates set a larger queue size, or get</em>
<a name="152" href="#152">152</a> <em>     * and average multiple values (as of last snapshot).</em>
<a name="153" href="#153">153</a> <em>     *</em>
<a name="154" href="#154">154</a> <em>     * @return The rate per second of KB gathered during the last snapshot</em>
<a name="155" href="#155">155</a> <em>     */</em>
<a name="156" href="#156">156</a>     <strong>public</strong> <strong>int</strong> currentProcessedKBPerSec();
<a name="157" href="#157">157</a>     
<a name="158" href="#158">158</a>     <em>/**<em>*</em></em>
<a name="159" href="#159">159</a> <em>     * Get the number of active (non-paused) threads.</em>
<a name="160" href="#160">160</a> <em>     * </em>
<a name="161" href="#161">161</a> <em>     * @return The number of active (non-paused) threads</em>
<a name="162" href="#162">162</a> <em>     */</em>
<a name="163" href="#163">163</a>     <strong>public</strong> <strong>int</strong> activeThreadCount();
<a name="164" href="#164">164</a>     
<a name="165" href="#165">165</a>     <em>/**<em>*</em></em>
<a name="166" href="#166">166</a> <em>     * Number of &lt;i>successfully&lt;/i> processed URIs.</em>
<a name="167" href="#167">167</a> <em>     *</em>
<a name="168" href="#168">168</a> <em>     * &lt;p>If crawl not running (paused or stopped) this will return the value</em>
<a name="169" href="#169">169</a> <em>     * of the last snapshot.</em>
<a name="170" href="#170">170</a> <em>     *</em>
<a name="171" href="#171">171</a> <em>     * @return The number of successully fetched URIs</em>
<a name="172" href="#172">172</a> <em>     *</em>
<a name="173" href="#173">173</a> <em>     * @see org.archive.crawler.framework.Frontier#succeededFetchCount()</em>
<a name="174" href="#174">174</a> <em>     */</em>
<a name="175" href="#175">175</a>     <strong>public</strong> <strong>long</strong> successfullyFetchedCount();
<a name="176" href="#176">176</a>     
<a name="177" href="#177">177</a>     <em>/**<em>*</em></em>
<a name="178" href="#178">178</a> <em>     * @return Total number of URIs (processed + queued +</em>
<a name="179" href="#179">179</a> <em>     * currently being processed)</em>
<a name="180" href="#180">180</a> <em>     */</em>
<a name="181" href="#181">181</a>     <strong>public</strong> <strong>long</strong> totalCount();
<a name="182" href="#182">182</a>     
<a name="183" href="#183">183</a>     <strong>public</strong> <strong>float</strong> congestionRatio();
<a name="184" href="#184">184</a>     <strong>public</strong> <strong>long</strong> deepestUri();
<a name="185" href="#185">185</a>     <strong>public</strong> <strong>long</strong> averageDepth();
<a name="186" href="#186">186</a>     
<a name="187" href="#187">187</a>     <em>/**<em>*</em></em>
<a name="188" href="#188">188</a> <em>     * Get a SeedRecord iterator for the job being monitored. If job is no </em>
<a name="189" href="#189">189</a> <em>     * longer running, stored values will be returned. If job is running, </em>
<a name="190" href="#190">190</a> <em>     * current seed iterator will be fetched and stored values will be updated.</em>
<a name="191" href="#191">191</a> <em>     * &lt;p></em>
<a name="192" href="#192">192</a> <em>     * Sort order is:&lt;br></em>
<a name="193" href="#193">193</a> <em>     * No status code (not processed)&lt;br></em>
<a name="194" href="#194">194</a> <em>     * Status codes smaller then 0 (largest to smallest)&lt;br></em>
<a name="195" href="#195">195</a> <em>     * Status codes larger then 0 (largest to smallest)&lt;br></em>
<a name="196" href="#196">196</a> <em>     * &lt;p></em>
<a name="197" href="#197">197</a> <em>     * &lt;b>Note:&lt;/b> This iterator will iterate over a list of </em>
<a name="198" href="#198">198</a> <em>     * &lt;i>SeedRecords&lt;/i>.</em>
<a name="199" href="#199">199</a> <em>     * @return the seed iterator</em>
<a name="200" href="#200">200</a> <em>     */</em>
<a name="201" href="#201">201</a>     <strong>public</strong> Iterator getSeedRecordsSortedByStatusCode();
<a name="202" href="#202">202</a> 
<a name="203" href="#203">203</a>     <em>/**<em>*</em></em>
<a name="204" href="#204">204</a> <em>     * @return legend of progress-statistics</em>
<a name="205" href="#205">205</a> <em>     */</em>
<a name="206" href="#206">206</a>     <strong>public</strong> String progressStatisticsLegend();
<a name="207" href="#207">207</a> 
<a name="208" href="#208">208</a>     <em>/**<em>*</em></em>
<a name="209" href="#209">209</a> <em>     * @return line of progress-statistics</em>
<a name="210" href="#210">210</a> <em>     */</em>
<a name="211" href="#211">211</a>     <strong>public</strong> String getProgressStatisticsLine();
<a name="212" href="#212">212</a>     
<a name="213" href="#213">213</a>     <em>/**<em>*</em></em>
<a name="214" href="#214">214</a> <em>     * @return Map of progress-statistics.</em>
<a name="215" href="#215">215</a> <em>     */</em>
<a name="216" href="#216">216</a>     <strong>public</strong> Map getProgressStatistics();
<a name="217" href="#217">217</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>