statisticstracker.html

来自「网络爬虫开源代码」· HTML 代码 · 共 738 行 · 第 1/5 页

HTML
738
字号
<a name="436" href="#436">436</a>         <a href="../../../../org/archive/util/LongWrapper.html">LongWrapper</a> lw = (LongWrapper)map.get(key);<a name="437" href="#437">437</a>         <strong>if</strong>(lw == <strong>null</strong>) {<a name="438" href="#438">438</a>             map.put(key, <strong>new</strong> <a href="../../../../org/archive/util/LongWrapper.html">LongWrapper</a>(increment));<a name="439" href="#439">439</a>         } <strong>else</strong> {<a name="440" href="#440">440</a>             lw.longValue += increment;<a name="441" href="#441">441</a>         }<a name="442" href="#442">442</a>     }<a name="443" href="#443">443</a> <a name="444" href="#444">444</a>     <em>/**<em>*</em></em><a name="445" href="#445">445</a> <em>     * Sort the entries of the given HashMap in descending order by their</em><a name="446" href="#446">446</a> <em>     * values, which must be longs wrapped with &lt;code>LongWrapper&lt;/code>.</em><a name="447" href="#447">447</a> <em>     * &lt;p></em><a name="448" href="#448">448</a> <em>     * Elements are sorted by value from largest to smallest. Equal values are</em><a name="449" href="#449">449</a> <em>     * sorted in an arbitrary, but consistent manner by their keys. Only items</em><a name="450" href="#450">450</a> <em>     * with identical value and key are considered equal.</em><a name="451" href="#451">451</a> <em>     *</em><a name="452" href="#452">452</a> <em>     * If the passed-in map requires access to be synchronized, the caller</em><a name="453" href="#453">453</a> <em>     * should ensure this synchronization. </em><a name="454" href="#454">454</a> <em>     * </em><a name="455" href="#455">455</a> <em>     * @param mapOfLongWrapperValues</em><a name="456" href="#456">456</a> <em>     *            Assumes values are wrapped with LongWrapper.</em><a name="457" href="#457">457</a> <em>     * @return a sorted set containing the same elements as the map.</em><a name="458" href="#458">458</a> <em>     */</em><a name="459" href="#459">459</a>     <strong>public</strong> TreeMap&lt;String,LongWrapper> getReverseSortedCopy(<a name="460" href="#460">460</a>             <strong>final</strong> Map&lt;String,LongWrapper> mapOfLongWrapperValues) {<a name="461" href="#461">461</a>         TreeMap&lt;String,LongWrapper> sortedMap = <a name="462" href="#462">462</a>           <strong>new</strong> TreeMap&lt;String,LongWrapper>(<strong>new</strong> Comparator&lt;String>() {<a name="463" href="#463">463</a>             <strong>public</strong> <strong>int</strong> compare(String e1, String e2) {<a name="464" href="#464">464</a>                 <strong>long</strong> firstVal = mapOfLongWrapperValues.get(e1).<a name="465" href="#465">465</a>                     longValue;<a name="466" href="#466">466</a>                 <strong>long</strong> secondVal = mapOfLongWrapperValues.get(e2).<a name="467" href="#467">467</a>                     longValue;<a name="468" href="#468">468</a>                 <strong>if</strong> (firstVal &lt; secondVal) {<a name="469" href="#469">469</a>                     <strong>return</strong> 1;<a name="470" href="#470">470</a>                 }<a name="471" href="#471">471</a>                 <strong>if</strong> (secondVal &lt; firstVal) {<a name="472" href="#472">472</a>                     <strong>return</strong> -1;<a name="473" href="#473">473</a>                 }<a name="474" href="#474">474</a>                 <em class="comment">// If the values are the same, sort by keys.</em><a name="475" href="#475">475</a>                 <strong>return</strong> e1.compareTo(e2);<a name="476" href="#476">476</a>             }<a name="477" href="#477">477</a>         });<a name="478" href="#478">478</a>         <strong>try</strong> {<a name="479" href="#479">479</a>             sortedMap.putAll(mapOfLongWrapperValues);<a name="480" href="#480">480</a>         } <strong>catch</strong> (UnsupportedOperationException e) {<a name="481" href="#481">481</a>             Iterator&lt;String> i = mapOfLongWrapperValues.keySet().iterator();<a name="482" href="#482">482</a>             <strong>for</strong> (;i.hasNext();) {<a name="483" href="#483">483</a>                 <em class="comment">// Ok. Try doing it the slow way then.</em><a name="484" href="#484">484</a>                 String key = i.next();<a name="485" href="#485">485</a>                 sortedMap.put(key, mapOfLongWrapperValues.get(key));<a name="486" href="#486">486</a>             }<a name="487" href="#487">487</a>         }<a name="488" href="#488">488</a>         <strong>return</strong> sortedMap;<a name="489" href="#489">489</a>     }<a name="490" href="#490">490</a> <a name="491" href="#491">491</a>     <em>/**<em>*</em></em><a name="492" href="#492">492</a> <em>     * Return a HashMap representing the distribution of status codes for</em><a name="493" href="#493">493</a> <em>     * successfully fetched curis, as represented by a hashmap where key -&amp;gt;</em><a name="494" href="#494">494</a> <em>     * val represents (string)code -&amp;gt; (integer)count.</em><a name="495" href="#495">495</a> <em>     * </em><a name="496" href="#496">496</a> <em>     * &lt;b>Note: &lt;/b> All the values are wrapped with a</em><a name="497" href="#497">497</a> <em>     * {@link LongWrapper LongWrapper}</em><a name="498" href="#498">498</a> <em>     * </em><a name="499" href="#499">499</a> <em>     * @return statusCodeDistribution</em><a name="500" href="#500">500</a> <em>     */</em><a name="501" href="#501">501</a>     <strong>public</strong> Hashtable&lt;String,LongWrapper> getStatusCodeDistribution() {<a name="502" href="#502">502</a>         <strong>return</strong> statusCodeDistribution;<a name="503" href="#503">503</a>     }<a name="504" href="#504">504</a>     <a name="505" href="#505">505</a>     <em>/**<em>*</em></em><a name="506" href="#506">506</a> <em>     * Returns the time (in millisec) when a URI belonging to a given host was</em><a name="507" href="#507">507</a> <em>     * last finished processing. </em><a name="508" href="#508">508</a> <em>     * </em><a name="509" href="#509">509</a> <em>     * @param host The host to look up time of last completed URI.</em><a name="510" href="#510">510</a> <em>     * @return Returns the time (in millisec) when a URI belonging to a given </em><a name="511" href="#511">511</a> <em>     * host was last finished processing. If no URI has been completed for host</em><a name="512" href="#512">512</a> <em>     * -1 will be returned. </em><a name="513" href="#513">513</a> <em>     */</em><a name="514" href="#514">514</a>     <strong>public</strong> <strong>long</strong> getHostLastFinished(String host){<a name="515" href="#515">515</a>         Long l = <strong>null</strong>;<a name="516" href="#516">516</a>         <strong>synchronized</strong>(hostsLastFinished){<a name="517" href="#517">517</a>             l = (Long)hostsLastFinished.get(host);<a name="518" href="#518">518</a>         }<a name="519" href="#519">519</a>         <strong>return</strong> (l != <strong>null</strong>)? l.longValue(): -1;<a name="520" href="#520">520</a>     }<a name="521" href="#521">521</a> <a name="522" href="#522">522</a>     <em>/**<em>*</em></em><a name="523" href="#523">523</a> <em>     * Returns the accumulated number of bytes downloaded from a given host.</em><a name="524" href="#524">524</a> <em>     * @param host name of the host</em><a name="525" href="#525">525</a> <em>     * @return the accumulated number of bytes downloaded from a given host</em><a name="526" href="#526">526</a> <em>     */</em><a name="527" href="#527">527</a>     <strong>public</strong> <strong>long</strong> getBytesPerHost(String host){<a name="528" href="#528">528</a>         <strong>synchronized</strong>(hostsBytes){<a name="529" href="#529">529</a>             <strong>return</strong> ((LongWrapper)hostsBytes.get(host)).longValue;<a name="530" href="#530">530</a>         }<a name="531" href="#531">531</a>     }<a name="532" href="#532">532</a> <a name="533" href="#533">533</a>     <em>/**<em>*</em></em><a name="534" href="#534">534</a> <em>     * Returns the accumulated number of bytes from files of a given file type.</em><a name="535" href="#535">535</a> <em>     * @param filetype Filetype to check.</em><a name="536" href="#536">536</a> <em>     * @return the accumulated number of bytes from files of a given mime type</em><a name="537" href="#537">537</a> <em>     */</em><a name="538" href="#538">538</a>     <strong>public</strong> <strong>long</strong> getBytesPerFileType(String filetype){<a name="539" href="#539">539</a>         <strong>return</strong> ((LongWrapper)mimeTypeBytes.get(filetype)).longValue;<a name="540" href="#540">540</a>     }<a name="541" href="#541">541</a> <a name="542" href="#542">542</a>     <em>/**<em>*</em></em><a name="543" href="#543">543</a> <em>     * Get the total number of ToeThreads (sleeping and active)</em><a name="544" href="#544">544</a> <em>     *</em><a name="545" href="#545">545</a> <em>     * @return The total number of ToeThreads</em><a name="546" href="#546">546</a> <em>     */</em><a name="547" href="#547">547</a>     <strong>public</strong> <strong>int</strong> threadCount() {<a name="548" href="#548">548</a>         <strong>return</strong> <strong>this</strong>.controller != <strong>null</strong>? controller.getToeCount(): 0;<a name="549" href="#549">549</a>     }<a name="550" href="#550">550</a> <a name="551" href="#551">551</a>     <em>/**<em>*</em></em><a name="552" href="#552">552</a> <em>     * @return Current thread count (or zero if can't figure it out).</em><a name="553" href="#553">553</a> <em>     */</em> <a name="554" href="#554">554</a>     <strong>public</strong> <strong>int</strong> activeThreadCount() {<a name="555" href="#555">555</a>         <strong>return</strong> <strong>this</strong>.controller != <strong>null</strong>? controller.getActiveToeCount(): 0;<a name="556" href="#556">556</a>         <em class="comment">// note: reuse of old busy value seemed misleading: anyone asking</em><a name="557" href="#557">557</a>         <em class="comment">// for thread count when paused or stopped still wants accurate reading</em><a name="558" href="#558">558</a>     }<a name="559" href="#559">559</a> <a name="560" href="#560">560</a>     <em>/**<em>*</em></em><a name="561" href="#561">561</a> <em>     * This returns the number of completed URIs as a percentage of the total</em><a name="562" href="#562">562</a> <em>     * number of URIs encountered (should be inverse to the discovery curve)</em><a name="563" href="#563">563</a> <em>     *</em><a name="564" href="#564">564</a> <em>     * @return The number of completed URIs as a percentage of the total</em><a name="565" href="#565">565</a> <em>     * number of URIs encountered</em><a name="566" href="#566">566</a> <em>     */</em><a name="567" href="#567">567</a>     <strong>public</strong> <strong>int</strong> percentOfDiscoveredUrisCompleted() {<a name="568" href="#568">568</a>         <strong>long</strong> completed = finishedUriCount();<a name="569" href="#569">569</a>         <strong>long</strong> total = discoveredUriCount();<a name="570" href="#570">570</a> <a name="571" href="#571">571</a>         <strong>if</strong> (total == 0) {<a name="572" href="#572">572</a>             <strong>return</strong> 0;<a name="573" href="#573">573</a>         }<a name="574" href="#574">574</a> <a name="575" href="#575">575</a>         <strong>return</strong> (<strong>int</strong>) (100 * completed / total);<a name="576" href="#576">576</a>     }<a name="577" href="#577">577</a> <a name="578" href="#578">578</a>     <em>/**<em>*</em></em><a name="579" href="#579">579</a> <em>     * Number of &lt;i>discovered&lt;/i> URIs.</em><a name="580" href="#580">580</a> <em>     *</em><a name="581" href="#581">581</a> <em>     * &lt;p>If crawl not running (paused or stopped) this will return the value of</em><a name="582" href="#582">582</a> <em>     * the last snapshot.</em><a name="583" href="#583">583</a> <em>     *</em>

⌨️ 快捷键说明

复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?