?? bdbmultipleworkqueues.html
字號:
<a name="137" href="#137">137</a> }<a name="138" href="#138">138</a> }<a name="139" href="#139">139</a> result = cursor.getNext(key, value, <strong>null</strong>);<a name="140" href="#140">140</a> }<a name="141" href="#141">141</a> } <strong>finally</strong> {<a name="142" href="#142">142</a> <strong>if</strong> (cursor != <strong>null</strong>) {<a name="143" href="#143">143</a> cursor.close();<a name="144" href="#144">144</a> }<a name="145" href="#145">145</a> }<a name="146" href="#146">146</a> <a name="147" href="#147">147</a> <strong>return</strong> deletedCount;<a name="148" href="#148">148</a> }<a name="149" href="#149">149</a> <a name="150" href="#150">150</a> <em>/**<em>*</em></em><a name="151" href="#151">151</a> <em> * @param m marker</em><a name="152" href="#152">152</a> <em> * @param maxMatches</em><a name="153" href="#153">153</a> <em> * @return list of matches starting from marker position</em><a name="154" href="#154">154</a> <em> * @throws DatabaseException</em><a name="155" href="#155">155</a> <em> */</em><a name="156" href="#156">156</a> <strong>public</strong> List getFrom(<a href="../../../../org/archive/crawler/framework/FrontierMarker.html">FrontierMarker</a> m, <strong>int</strong> maxMatches) throws DatabaseException {<a name="157" href="#157">157</a> <strong>int</strong> matches = 0;<a name="158" href="#158">158</a> <strong>int</strong> tries = 0;<a name="159" href="#159">159</a> ArrayList<CrawlURI> results = <strong>new</strong> ArrayList<CrawlURI>(maxMatches);<a name="160" href="#160">160</a> BdbFrontierMarker marker = (BdbFrontierMarker) m;<a name="161" href="#161">161</a> <a name="162" href="#162">162</a> DatabaseEntry key = marker.getStartKey();<a name="163" href="#163">163</a> DatabaseEntry value = <strong>new</strong> DatabaseEntry();<a name="164" href="#164">164</a> <a name="165" href="#165">165</a> <strong>if</strong> (key != <strong>null</strong>) {<a name="166" href="#166">166</a> Cursor cursor = <strong>null</strong>;<a name="167" href="#167">167</a> OperationStatus result = <strong>null</strong>;<a name="168" href="#168">168</a> <strong>try</strong> {<a name="169" href="#169">169</a> cursor = pendingUrisDB.openCursor(<strong>null</strong>,<strong>null</strong>);<a name="170" href="#170">170</a> result = cursor.getSearchKey(key, value, <strong>null</strong>);<a name="171" href="#171">171</a> <a name="172" href="#172">172</a> <strong>while</strong>(matches<maxMatches && result == OperationStatus.SUCCESS) {<a name="173" href="#173">173</a> <strong>if</strong>(value.getData().length>0) {<a name="174" href="#174">174</a> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> curi = (CrawlURI) crawlUriBinding.entryToObject(value);<a name="175" href="#175">175</a> <strong>if</strong>(marker.accepts(curi)) {<a name="176" href="#176">176</a> results.add(curi);<a name="177" href="#177">177</a> matches++;<a name="178" href="#178">178</a> }<a name="179" href="#179">179</a> tries++;<a name="180" href="#180">180</a> }<a name="181" href="#181">181</a> result = cursor.getNext(key,value,<strong>null</strong>);<a name="182" href="#182">182</a> }<a name="183" href="#183">183</a> } <strong>finally</strong> {<a name="184" href="#184">184</a> <strong>if</strong> (cursor !=<strong>null</strong>) {<a name="185" href="#185">185</a> cursor.close();<a name="186" href="#186">186</a> }<a name="187" href="#187">187</a> }<a name="188" href="#188">188</a> <a name="189" href="#189">189</a> <strong>if</strong>(result != OperationStatus.SUCCESS) {<a name="190" href="#190">190</a> <em class="comment">// end of scan</em><a name="191" href="#191">191</a> marker.setStartKey(<strong>null</strong>);<a name="192" href="#192">192</a> }<a name="193" href="#193">193</a> }<a name="194" href="#194">194</a> <strong>return</strong> results;<a name="195" href="#195">195</a> }<a name="196" href="#196">196</a> <a name="197" href="#197">197</a> <em>/**<em>*</em></em><a name="198" href="#198">198</a> <em> * Get a marker for beginning a scan over all contents</em><a name="199" href="#199">199</a> <em> * </em><a name="200" href="#200">200</a> <em> * @param regexpr</em><a name="201" href="#201">201</a> <em> * @return a marker pointing to the first item</em><a name="202" href="#202">202</a> <em> */</em><a name="203" href="#203">203</a> <strong>public</strong> <a href="../../../../org/archive/crawler/framework/FrontierMarker.html">FrontierMarker</a> getInitialMarker(String regexpr) {<a name="204" href="#204">204</a> <strong>try</strong> {<a name="205" href="#205">205</a> <strong>return</strong> <strong>new</strong> BdbFrontierMarker(getFirstKey(), regexpr);<a name="206" href="#206">206</a> } <strong>catch</strong> (DatabaseException e) {<a name="207" href="#207">207</a> e.printStackTrace();<a name="208" href="#208">208</a> <strong>return</strong> <strong>null</strong>; <a name="209" href="#209">209</a> }<a name="210" href="#210">210</a> }<a name="211" href="#211">211</a> <a name="212" href="#212">212</a> <em>/**<em>*</em></em><a name="213" href="#213">213</a> <em> * @return the key to the first item in the database</em><a name="214" href="#214">214</a> <em> * @throws DatabaseException</em><a name="215" href="#215">215</a> <em> */</em><a name="216" href="#216">216</a> <strong>protected</strong> DatabaseEntry getFirstKey() throws DatabaseException {<a name="217" href="#217">217</a> DatabaseEntry key = <strong>new</strong> DatabaseEntry();<a name="218" href="#218">218</a> DatabaseEntry value = <strong>new</strong> DatabaseEntry();<a name="219" href="#219">219</a> Cursor cursor = pendingUrisDB.openCursor(<strong>null</strong>,<strong>null</strong>);<a name="220" href="#220">220</a> OperationStatus status = cursor.getNext(key,value,<strong>null</strong>);<a name="221" href="#221">221</a> cursor.close();<a name="222" href="#222">222</a> <strong>if</strong>(status == OperationStatus.SUCCESS) {<a name="223" href="#223">223</a> <strong>return</strong> key;<a name="224" href="#224">224</a> }<a name="225" href="#225">225</a> <strong>return</strong> <strong>null</strong>;<a name="226" href="#226">226</a> }<a name="227" href="#227">227</a> <a name="228" href="#228">228</a> <em>/**<em>*</em></em><a name="229" href="#229">229</a> <em> * Get the next nearest item after the given key. Relies on </em><a name="230" href="#230">230</a> <em> * external discipline -- we'll look at the queues count of how many</em><a name="231" href="#231">231</a> <em> * items it has -- to avoid asking for something from a</em><a name="232" href="#232">232</a> <em> * range where there are no associated items --</em><a name="233" href="#233">233</a> <em> * otherwise could get first item of next 'queue' by mistake. </em><a name="234" href="#234">234</a> <em> * </em><a name="235" href="#235">235</a> <em> * <p>TODO: hold within a queue's range</em><a name="236" href="#236">236</a> <em> * </em><a name="237" href="#237">237</a> <em> * @param headKey Key prefix that demarks the beginning of the range</em><a name="238" href="#238">238</a> <em> * in <code>pendingUrisDB</code> we're interested in.</em><a name="239" href="#239">239</a> <em> * @return CrawlURI.</em><a name="240" href="#240">240</a> <em> * @throws DatabaseException</em><a name="241" href="#241">241</a> <em> */</em><a name="242" href="#242">242</a> <strong>public</strong> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> get(DatabaseEntry headKey)<a name="243" href="#243">243</a> throws DatabaseException {<a name="244" href="#244">244</a> DatabaseEntry result = <strong>new</strong> DatabaseEntry();<a name="245" href="#245">245</a> <a name="246" href="#246">246</a> <em class="comment">// From Linda Lee of sleepycat:</em><a name="247" href="#247">247</a> <em class="comment">// "You want to check the status returned from Cursor.getSearchKeyRange</em><a name="248" href="#248">248</a> <em class="comment">// to make sure that you have OperationStatus.SUCCESS. In that case,</em><a name="249" href="#249">249</a> <em class="comment">// you have found a valid data record, and result.getData()</em><a name="250" href="#250">250</a> <em class="comment">// (called by internally by the binding code, in this case) will be</em><a name="251" href="#251">251</a> <em class="comment">// non-null. The other possible status return is</em><a name="252" href="#252">252</a> <em class="comment">// OperationStatus.NOTFOUND, in which case no data record matched</em><a name="253" href="#253">253</a> <em class="comment">// the criteria. "</em><a name="254" href="#254">254</a> OperationStatus status = getNextNearestItem(headKey, result);<a name="255" href="#255">255</a> <a href="../../../../org/archive/crawler/datamodel/CrawlURI.html">CrawlURI</a> retVal = <strong>null</strong>;<a name="256" href="#256">256</a> <strong>if</strong> (status != OperationStatus.SUCCESS) {<a name="257" href="#257">257</a> LOGGER.severe(<span class="string">"See '1219854 NPE je-2.0 "</span><a name="258" href="#258">258</a> + <span class="string">"entryToObject...'. OperationStatus "</span><a name="259" href="#259">259</a> + <span class="string">" was not SUCCESS: "</span><a name="260" href="#260">260</a> + status<a name="261" href="#261">261</a> + <span class="string">", headKey "</span><a name="262" href="#262">262</a> + BdbWorkQueue.getPrefixClassKey(headKey.getData()));<a name="263" href="#263">263</a> <strong>return</strong> <strong>null</strong>;<a name="264" href="#264">264</a> }<a name="265" href="#265">265</a> <strong>try</strong> {<a name="266" href="#266">266</a> retVal = (CrawlURI)crawlUriBinding.entryToObject(result);<a name="267" href="#267">267</a> } <strong>catch</strong> (RuntimeExceptionWrapper rw) {<a name="268" href="#268">268</a> LOGGER.log(<a name="269" href="#269">269</a> Level.SEVERE,<a name="270" href="#270">270</a> <span class="string">"expected object missing in queue "</span> +<a name="271" href="#271">271</a> BdbWorkQueue.getPrefixClassKey(headKey.getData()),<a name="272" href="#272">272</a> rw);<a name="273" href="#273">273</a> <strong>return</strong> <strong>null</strong>; <a name="274" href="#274">274</a> }<a name="275" href="#275">275</a> retVal.setHolderKey(headKey);<a name="276" href="#276">276</a> <strong>return</strong> retVal;<a name="277" href="#277">277</a> }<a name="278" href="#278">278</a> <a name="279" href="#279">279</a> <strong>protected</strong> OperationStatus getNextNearestItem(DatabaseEntry headKey,<a name="280" href="#280">280</a> DatabaseEntry result) throws DatabaseException {<a name="281" href="#281">281</a> Cursor cursor = <strong>null</strong>;
?? 快捷鍵說明
復制代碼
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
Ctrl + =
減小字號
Ctrl + -