⭐ 欢迎来到虫虫下载站! | 📦 资源下载 📁 资源专辑 ℹ️ 关于我们
⭐ 虫虫下载站

📄 candidateuri.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
💻 HTML
📖 第 1 页 / 共 4 页
字号:
<a name="356" href="#356">356</a>     <strong>public</strong> <strong>boolean</strong> needsImmediateScheduling() {<a name="357" href="#357">357</a>         <strong>return</strong> schedulingDirective == HIGH;<a name="358" href="#358">358</a>     }<a name="359" href="#359">359</a> <a name="360" href="#360">360</a>     <em>/**<em>*</em></em><a name="361" href="#361">361</a> <em>     * @return True if needs soon but not top scheduling.</em><a name="362" href="#362">362</a> <em>     */</em><a name="363" href="#363">363</a>     <strong>public</strong> <strong>boolean</strong> needsSoonScheduling() {<a name="364" href="#364">364</a>         <strong>return</strong> schedulingDirective == MEDIUM;<a name="365" href="#365">365</a>     }<a name="366" href="#366">366</a> <a name="367" href="#367">367</a>     <em>/**<em>*</em></em><a name="368" href="#368">368</a> <em>     * Tally up the number of transitive (non-simple-link) hops at</em><a name="369" href="#369">369</a> <em>     * the end of this CandidateURI's pathFromSeed.</em><a name="370" href="#370">370</a> <em>     * </em><a name="371" href="#371">371</a> <em>     * In some cases, URIs with greater than zero but less than some</em><a name="372" href="#372">372</a> <em>     * threshold such hops are treated specially. </em><a name="373" href="#373">373</a> <em>     * </em><a name="374" href="#374">374</a> <em>     * &lt;p>TODO: consider moving link-count in here as well, caching</em><a name="375" href="#375">375</a> <em>     * calculation, and refactoring CrawlScope.exceedsMaxHops() to use this. </em><a name="376" href="#376">376</a> <em>     * </em><a name="377" href="#377">377</a> <em>     * @return Transhop count.</em><a name="378" href="#378">378</a> <em>     */</em><a name="379" href="#379">379</a>     <strong>public</strong> <strong>int</strong> getTransHops() {<a name="380" href="#380">380</a>         String path = getPathFromSeed();<a name="381" href="#381">381</a>         <strong>int</strong> transCount = 0;<a name="382" href="#382">382</a>         <strong>for</strong>(<strong>int</strong> i=path.length()-1;i>=0;i--) {<a name="383" href="#383">383</a>             <strong>if</strong>(path.charAt(i)==Link.NAVLINK_HOP) {<a name="384" href="#384">384</a>                 <strong>break</strong>;<a name="385" href="#385">385</a>             }<a name="386" href="#386">386</a>             transCount++;<a name="387" href="#387">387</a>         }<a name="388" href="#388">388</a>         <strong>return</strong> transCount;<a name="389" href="#389">389</a>     }<a name="390" href="#390">390</a> <a name="391" href="#391">391</a>     <em>/**<em>*</em></em><a name="392" href="#392">392</a> <em>     * Given a string containing a URI, then optional whitespace</em><a name="393" href="#393">393</a> <em>     * delimited hops-path and via info, create a CandidateURI </em><a name="394" href="#394">394</a> <em>     * instance.</em><a name="395" href="#395">395</a> <em>     * </em><a name="396" href="#396">396</a> <em>     * @param uriHopsViaString String with a URI.</em><a name="397" href="#397">397</a> <em>     * @return A CandidateURI made from passed &lt;code>uriHopsViaString&lt;/code>.</em><a name="398" href="#398">398</a> <em>     * @throws URIException</em><a name="399" href="#399">399</a> <em>     */</em><a name="400" href="#400">400</a>     <strong>public</strong> <strong>static</strong> <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> fromString(String uriHopsViaString)<a name="401" href="#401">401</a>             throws URIException {<a name="402" href="#402">402</a>         String args[] = uriHopsViaString.split(<span class="string">"&#47;&#47;s+"</span>);<a name="403" href="#403">403</a>         String pathFromSeeds = (args.length > 1 &amp;&amp; !args[1].equals(<span class="string">"-"</span>)) ?<a name="404" href="#404">404</a>                 args[1]: <span class="string">""</span>;<a name="405" href="#405">405</a>         <a href="../../../../org/archive/net/UURI.html">UURI</a> via = (args.length > 2 &amp;&amp; !args[2].equals(<span class="string">"-"</span>)) ?<a name="406" href="#406">406</a>                 UURIFactory.getInstance(args[2]) : <strong>null</strong>;<a name="407" href="#407">407</a>         CharSequence viaContext = (args.length > 3 &amp;&amp; !args[3].equals(<span class="string">"-"</span>)) ?<a name="408" href="#408">408</a>                 args[2]: <strong>null</strong>;<a name="409" href="#409">409</a>         <strong>return</strong> <strong>new</strong> <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a>(UURIFactory.getInstance(args[0]),<a name="410" href="#410">410</a>                 pathFromSeeds, via, viaContext);<a name="411" href="#411">411</a>     }<a name="412" href="#412">412</a>     <a name="413" href="#413">413</a>     <strong>public</strong> <strong>static</strong> <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> createSeedCandidateURI(<a href="../../../../org/archive/net/UURI.html">UURI</a> uuri) {<a name="414" href="#414">414</a>         <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> c = <strong>new</strong> <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a>(uuri);<a name="415" href="#415">415</a>         c.setIsSeed(<strong>true</strong>);<a name="416" href="#416">416</a>         <strong>return</strong> c;<a name="417" href="#417">417</a>     }<a name="418" href="#418">418</a>     <a name="419" href="#419">419</a>     <em>/**<em>*</em></em><a name="420" href="#420">420</a> <em>     * Utility method for creation of CandidateURIs found extracting</em><a name="421" href="#421">421</a> <em>     * links from this CrawlURI.</em><a name="422" href="#422">422</a> <em>     * @param baseUURI BaseUURI for &lt;code>link&lt;/code>.</em><a name="423" href="#423">423</a> <em>     * @param link Link to wrap CandidateURI in.</em><a name="424" href="#424">424</a> <em>     * @return New candidateURI wrapper around &lt;code>link&lt;/code>.</em><a name="425" href="#425">425</a> <em>     * @throws URIException</em><a name="426" href="#426">426</a> <em>     */</em><a name="427" href="#427">427</a>     <strong>public</strong> <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> createCandidateURI(<a href="../../../../org/archive/net/UURI.html">UURI</a> baseUURI, <a href="../../../../org/archive/crawler/extractor/Link.html">Link</a> link)<a name="428" href="#428">428</a>     throws URIException {<a name="429" href="#429">429</a>         <a href="../../../../org/archive/net/UURI.html">UURI</a> u = (link.getDestination() instanceof UURI)?<a name="430" href="#430">430</a>             (<a href="../../../../org/archive/net/UURI.html">UURI</a>)link.getDestination():<a name="431" href="#431">431</a>             UURIFactory.getInstance(baseUURI,<a name="432" href="#432">432</a>                 link.getDestination().toString());<a name="433" href="#433">433</a>         <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> <strong>new</strong>CaURI = <strong>new</strong> <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a>(u, getPathFromSeed() + link.getHopType(),<a name="434" href="#434">434</a>                 getUURI(), link.getContext());<a name="435" href="#435">435</a>         newCaURI.inheritFrom(<strong>this</strong>);<a name="436" href="#436">436</a>         <strong>return</strong> newCaURI;<a name="437" href="#437">437</a>     }<a name="438" href="#438">438</a> <a name="439" href="#439">439</a>     <em>/**<em>*</em></em><a name="440" href="#440">440</a> <em>     * Utility method for creation of CandidateURIs found extracting</em><a name="441" href="#441">441</a> <em>     * links from this CrawlURI.</em><a name="442" href="#442">442</a> <em>     * @param baseUURI BaseUURI for &lt;code>link&lt;/code>.</em><a name="443" href="#443">443</a> <em>     * @param link Link to wrap CandidateURI in.</em><a name="444" href="#444">444</a> <em>     * @param scheduling How new CandidateURI should be scheduled.</em><a name="445" href="#445">445</a> <em>     * @param seed True if this CandidateURI is a seed.</em><a name="446" href="#446">446</a> <em>     * @return New candidateURI wrapper around &lt;code>link&lt;/code>.</em><a name="447" href="#447">447</a> <em>     * @throws URIException</em><a name="448" href="#448">448</a> <em>     */</em><a name="449" href="#449">449</a>     <strong>public</strong> <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> createCandidateURI(<a href="../../../../org/archive/net/UURI.html">UURI</a> baseUURI, <a href="../../../../org/archive/crawler/extractor/Link.html">Link</a> link,<a name="450" href="#450">450</a>         <strong>int</strong> scheduling, <strong>boolean</strong> seed)<a name="451" href="#451">451</a>     throws URIException {<a name="452" href="#452">452</a>         <strong>final</strong> <a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> caURI = createCandidateURI(baseUURI, link);<a name="453" href="#453">453</a>         caURI.setSchedulingDirective(scheduling);<a name="454" href="#454">454</a>         caURI.setIsSeed(seed);<a name="455" href="#455">455</a>         <strong>return</strong> caURI;<a name="456" href="#456">456</a>     }<a name="457" href="#457">457</a>     <a name="458" href="#458">458</a>     <em>/**<em>*</em></em><a name="459" href="#459">459</a> <em>     * Inherit (copy) the relevant keys-values from the ancestor. </em><a name="460" href="#460">460</a> <em>     * </em><a name="461" href="#461">461</a> <em>     * @param ancestor</em><a name="462" href="#462">462</a> <em>     */</em><a name="463" href="#463">463</a>     <strong>protected</strong> <strong>void</strong> inheritFrom(<a href="../../../../org/archive/crawler/datamodel/CandidateURI.html">CandidateURI</a> ancestor) {<a name="464" href="#464">464</a>         List heritableKeys = (List) ancestor.getObject(A_HERITABLE_KEYS);<a name="465" href="#465">465</a>         <strong>if</strong>(heritableKeys!=<strong>null</strong>) {<a name="466" href="#466">466</a>             getAList().copyKeysFrom(heritableKeys.iterator(),ancestor.getAList());<a name="467" href="#467">467</a>         }<a name="468" href="#468">468</a>     }<a name="469" href="#469">469</a>     <a name="470" href="#470">470</a>     <em>/**<em>*</em></em><a name="471" href="#471">471</a> <em>     * Get the token (usually the hostname + port) which indicates</em><a name="472" href="#472">472</a> <em>     * what "class" this CrawlURI should be grouped with,</em><a name="473" href="#473">473</a> <em>     * for the purposes of ensuring only one item of the</em><a name="474" href="#474">474</a> <em>     * class is processed at once, all items of the class</em><a name="475" href="#475">475</a> <em>     * are held for a politeness period, etc.</em><a name="476" href="#476">476</a> <em>     *</em><a name="477" href="#477">477</a> <em>     * @return Token (usually the hostname) which indicates</em><a name="478" href="#478">478</a> <em>     * what "class" this CrawlURI should be grouped with.</em><a name="479" href="#479">479</a> <em>     */</em><a name="480" href="#480">480</a>     <strong>public</strong> String getClassKey() {<a name="481" href="#481">481</a>         <strong>return</strong> classKey;<a name="482" href="#482">482</a>     }<a name="483" href="#483">483</a> <a name="484" href="#484">484</a>     <strong>public</strong> <strong>void</strong> setClassKey(String key) {<a name="485" href="#485">485</a>         classKey = key;<a name="486" href="#486">486</a>     }<a name="487" href="#487">487</a>     <a name="488" href="#488">488</a>     <em>/**<em>*</em></em><a name="489" href="#489">489</a> <em>     * Assumption is that only one thread at a time will ever be accessing</em><a name="490" href="#490">490</a> <em>     * a particular CandidateURI.</em><a name="491" href="#491">491</a> <em>     * </em><a name="492" href="#492">492</a> <em>     * @deprecated Public access will be deprecated. This methods access</em><a name="493" href="#493">493</a> <em>     * will change in next release.  Use specialized accessors instead such</em><a name="494" href="#494">494</a> <em>     * as {@link #getString(String)}.</em><a name="495" href="#495">495</a> <em>     * </em><a name="496" href="#496">496</a> <em>     * @return the attribute list.</em><a name="497" href="#497">497</a> <em>     */</em><a name="498" href="#498">498</a>     <strong>public</strong> <a href="../../../../st/ata/util/AList.html">AList</a> getAList() {<a name="499" href="#499">499</a>         <strong>if</strong> (<strong>this</strong>.alist == <strong>null</strong>) {<a name="500" href="#500">500</a>             <strong>this</strong>.alist = <strong>new</strong> <a href="../../../../st/ata/util/HashtableAList.html">HashtableAList</a>();<a name="501" href="#501">501</a>         }<a name="502" href="#502">502</a>         <strong>return</strong> <strong>this</strong>.alist;<a name="503" href="#503">503</a>     }<a name="504" href="#504">504</a>     <a name="505" href="#505">505</a>     <strong>protected</strong> <strong>void</strong> clearAList() {<a name="506" href="#506">506</a>         <strong>this</strong>.alist = <strong>null</strong>;<a name="507" href="#507">507</a>     }<a name="508" href="#508">508</a>     <a name="509" href="#509">509</a>     <strong>public</strong> <strong>void</strong> putObject(String key, Object value) {<a name="510" href="#510">510</a>         getAList().putObject(key, value);<a name="511" href="#511">511</a>     }<a name="512" href="#512">512</a>     <a name="513" href="#513">513</a>     <strong>public</strong> Object getObject(String key) {<a name="514" href="#514">514</a>         <strong>return</strong> getAList().getObject(key);<a name="515" href="#515">515</a>     }<a name="516" href="#516">516</a>     <a name="517" href="#517">517</a>     <strong>public</strong> String getString(String key) {<a name="518" href="#518">518</a>         <strong>return</strong> getAList().getString(key);<a name="519" href="#519">519</a>     }<a name="520" href="#520">520</a>     <a name="521" href="#521">521</a>     <strong>public</strong> <strong>void</strong> putString(String key, String value) {<a name="522" href="#522">522</a>         getAList().putString(key, value);<a name="523" href="#523">523</a>     }<a name="524" href="#524">524</a>     <a name="525" href="#525">525</a>     <strong>public</strong> <strong>long</strong> getLong(String key) {<a name="526" href="#526">526</a>         <strong>return</strong> getAList().getLong(key);<a name="527" href="#527">527</a>     }<a name="528" href="#528">528</a>     <a name="529" href="#529">529</a>     <strong>public</strong> <strong>void</strong> putLong(String key, <strong>long</strong> value) {<a name="530" href="#530">530</a>         getAList().putLong(key, value);<a name="531" href="#531">531</a>     }<a name="532" href="#532">532</a>     <a name="533" href="#533">533</a>     <strong>public</strong> <strong>int</strong> getInt(String key) {<a name="534" href="#534">534</a>         <strong>return</strong> getAList().getInt(key);<a name="535" href="#535">535</a>     }<a name="536" href="#536">536</a>     <a name="537" href="#537">537</a>     <strong>public</strong> <strong>void</strong> putInt(String key, <strong>int</strong> value) {

⌨️ 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 + -