archivereader.html
来自「网络爬虫开源代码」· HTML 代码 · 共 786 行 · 第 1/5 页
HTML
786 行
<a name="150" href="#150">150</a> }<a name="151" href="#151">151</a> <a name="152" href="#152">152</a> <em>/**<em>*</em></em><a name="153" href="#153">153</a> <em> * @return Return Archive Record created against current offset.</em><a name="154" href="#154">154</a> <em> * @throws IOException</em><a name="155" href="#155">155</a> <em> */</em><a name="156" href="#156">156</a> <strong>public</strong> <a href="../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> get() throws IOException {<a name="157" href="#157">157</a> <strong>return</strong> createArchiveRecord(<strong>this</strong>.in,<a name="158" href="#158">158</a> ((RepositionableStream)<strong>this</strong>.in).position());<a name="159" href="#159">159</a> }<a name="160" href="#160">160</a> <a name="161" href="#161">161</a> <strong>public</strong> <strong>void</strong> close() throws IOException {<a name="162" href="#162">162</a> <strong>if</strong> (<strong>this</strong>.in != <strong>null</strong>) {<a name="163" href="#163">163</a> <strong>this</strong>.in.close();<a name="164" href="#164">164</a> <strong>this</strong>.in = <strong>null</strong>;<a name="165" href="#165">165</a> }<a name="166" href="#166">166</a> }<a name="167" href="#167">167</a> <a name="168" href="#168">168</a> <em>/**<em>*</em></em><a name="169" href="#169">169</a> <em> * Rewinds stream to start of the Archive file.</em><a name="170" href="#170">170</a> <em> * @throws IOException if stream is not resettable.</em><a name="171" href="#171">171</a> <em> */</em><a name="172" href="#172">172</a> <strong>protected</strong> <strong>void</strong> rewind() throws IOException {<a name="173" href="#173">173</a> cleanupCurrentRecord();<a name="174" href="#174">174</a> <strong>if</strong> (<strong>this</strong>.in instanceof RepositionableStream) {<a name="175" href="#175">175</a> <strong>try</strong> {<a name="176" href="#176">176</a> ((RepositionableStream)<strong>this</strong>.in).position(0);<a name="177" href="#177">177</a> } <strong>catch</strong> (IOException e) {<a name="178" href="#178">178</a> <strong>throw</strong> <strong>new</strong> RuntimeException(e);<a name="179" href="#179">179</a> }<a name="180" href="#180">180</a> } <strong>else</strong> {<a name="181" href="#181">181</a> <strong>throw</strong> <strong>new</strong> IOException(<span class="string">"Stream is not resettable."</span>);<a name="182" href="#182">182</a> }<a name="183" href="#183">183</a> }<a name="184" href="#184">184</a> <a name="185" href="#185">185</a> <em>/**<em>*</em></em><a name="186" href="#186">186</a> <em> * Cleanout the current record if there is one.</em><a name="187" href="#187">187</a> <em> * @throws IOException</em><a name="188" href="#188">188</a> <em> */</em><a name="189" href="#189">189</a> <strong>protected</strong> <strong>void</strong> cleanupCurrentRecord() throws IOException {<a name="190" href="#190">190</a> <strong>if</strong> (<strong>this</strong>.currentRecord != <strong>null</strong>) {<a name="191" href="#191">191</a> <strong>this</strong>.currentRecord.close();<a name="192" href="#192">192</a> gotoEOR(<strong>this</strong>.currentRecord);<a name="193" href="#193">193</a> <strong>this</strong>.currentRecord = <strong>null</strong>;<a name="194" href="#194">194</a> }<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> * Return an Archive Record homed on <code>offset</code> into</em><a name="199" href="#199">199</a> <em> * <code>is</code>.</em><a name="200" href="#200">200</a> <em> * @param is Stream to read Record from.</em><a name="201" href="#201">201</a> <em> * @param offset Offset to find Record at.</em><a name="202" href="#202">202</a> <em> * @return ArchiveRecord instance.</em><a name="203" href="#203">203</a> <em> * @throws IOException</em><a name="204" href="#204">204</a> <em> */</em><a name="205" href="#205">205</a> <strong>protected</strong> <strong>abstract</strong> <a href="../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> createArchiveRecord(InputStream is,<a name="206" href="#206">206</a> <strong>long</strong> offset)<a name="207" href="#207">207</a> throws IOException;<a name="208" href="#208">208</a> <a name="209" href="#209">209</a> <em>/**<em>*</em></em><a name="210" href="#210">210</a> <em> * Skip over any trailing new lines at end of the record so we're lined up</em><a name="211" href="#211">211</a> <em> * ready to read the next.</em><a name="212" href="#212">212</a> <em> * @param record</em><a name="213" href="#213">213</a> <em> * @throws IOException</em><a name="214" href="#214">214</a> <em> */</em><a name="215" href="#215">215</a> <strong>protected</strong> <strong>abstract</strong> <strong>void</strong> gotoEOR(<a href="../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> record) throws IOException;<a name="216" href="#216">216</a> <a name="217" href="#217">217</a> <strong>public</strong> <strong>abstract</strong> String getFileExtension();<a name="218" href="#218">218</a> <strong>public</strong> <strong>abstract</strong> String getDotFileExtension();<a name="219" href="#219">219</a> <a name="220" href="#220">220</a> <em>/**<em>*</em></em><a name="221" href="#221">221</a> <em> * @return Version of this Archive file.</em><a name="222" href="#222">222</a> <em> */</em><a name="223" href="#223">223</a> <strong>public</strong> String getVersion() {<a name="224" href="#224">224</a> <strong>return</strong> <strong>this</strong>.version;<a name="225" href="#225">225</a> }<a name="226" href="#226">226</a> <a name="227" href="#227">227</a> <em>/**<em>*</em></em><a name="228" href="#228">228</a> <em> * Validate the Archive file.</em><a name="229" href="#229">229</a> <em> *</em><a name="230" href="#230">230</a> <em> * This method iterates over the file throwing exception if it fails</em><a name="231" href="#231">231</a> <em> * to successfully parse any record.</em><a name="232" href="#232">232</a> <em> *</em><a name="233" href="#233">233</a> <em> * <p>Assumes the stream is at the start of the file.</em><a name="234" href="#234">234</a> <em> * @return List of all read Archive Headers.</em><a name="235" href="#235">235</a> <em> *</em><a name="236" href="#236">236</a> <em> * @throws IOException</em><a name="237" href="#237">237</a> <em> */</em><a name="238" href="#238">238</a> <strong>public</strong> List validate() throws IOException {<a name="239" href="#239">239</a> <strong>return</strong> validate(-1);<a name="240" href="#240">240</a> }<a name="241" href="#241">241</a> <a name="242" href="#242">242</a> <em>/**<em>*</em></em><a name="243" href="#243">243</a> <em> * Validate the Archive file.</em><a name="244" href="#244">244</a> <em> *</em><a name="245" href="#245">245</a> <em> * This method iterates over the file throwing exception if it fails</em><a name="246" href="#246">246</a> <em> * to successfully parse.</em><a name="247" href="#247">247</a> <em> *</em><a name="248" href="#248">248</a> <em> * <p>We start validation from whereever we are in the stream.</em><a name="249" href="#249">249</a> <em> *</em><a name="250" href="#250">250</a> <em> * @param noRecords Number of records expected. Pass -1 if number is</em><a name="251" href="#251">251</a> <em> * unknown.</em><a name="252" href="#252">252</a> <em> *</em><a name="253" href="#253">253</a> <em> * @return List of all read metadatas. As we validate records, we add</em><a name="254" href="#254">254</a> <em> * a reference to the read metadata.</em><a name="255" href="#255">255</a> <em> *</em><a name="256" href="#256">256</a> <em> * @throws IOException</em><a name="257" href="#257">257</a> <em> */</em><a name="258" href="#258">258</a> <strong>public</strong> List validate(<strong>int</strong> noRecords) throws IOException {<a name="259" href="#259">259</a> List<ArchiveRecordHeader> hs = <strong>new</strong> ArrayList<ArchiveRecordHeader>();<a name="260" href="#260">260</a> <strong>int</strong> count = 0;<a name="261" href="#261">261</a> setStrict(<strong>true</strong>);<a name="262" href="#262">262</a> <strong>for</strong> (Iterator<ArchiveRecord> i = iterator(); i.hasNext();) {<a name="263" href="#263">263</a> count++;<a name="264" href="#264">264</a> <a href="../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> r = i.next();<a name="265" href="#265">265</a> <strong>if</strong> (r.getHeader().getLength() <= 0<a name="266" href="#266">266</a> && r.getHeader().getMimetype().<a name="267" href="#267">267</a> equals(MimetypeUtils.NO_TYPE_MIMETYPE)) {<a name="268" href="#268">268</a> <strong>throw</strong> <strong>new</strong> IOException(<span class="string">"ARCRecord content is empty."</span>);<a name="269" href="#269">269</a> }<a name="270" href="#270">270</a> r.close();<a name="271" href="#271">271</a> <em class="comment">// Add reference to metadata into a list of metadatas.</em><a name="272" href="#272">272</a> hs.add(r.getHeader());<a name="273" href="#273">273</a> }<a name="274" href="#274">274</a> <a name="275" href="#275">275</a> <strong>if</strong> (noRecords != -1) {<a name="276" href="#276">276</a> <strong>if</strong> (count != noRecords) {<a name="277" href="#277">277</a> <strong>throw</strong> <strong>new</strong> IOException(<span class="string">"Count of records, "</span> +<a name="278" href="#278">278</a> Integer.toString(count) + <span class="string">" is less than expected "</span> +<a name="279" href="#279">279</a> Integer.toString(noRecords));<a name="280" href="#280">280</a> }<a name="281" href="#281">281</a> }<a name="282" href="#282">282</a> <a name="283" href="#283">283</a> <strong>return</strong> hs;<a name="284" href="#284">284</a> }<a name="285" href="#285">285</a> <a name="286" href="#286">286</a> <em>/**<em>*</em></em><a name="287" href="#287">287</a> <em> * Test Archive file is valid.</em><a name="288" href="#288">288</a> <em> * Assumes the stream is at the start of the file. Be aware that this</em><a name="289" href="#289">289</a> <em> * method makes a pass over the whole file. </em><a name="290" href="#290">290</a> <em> * @return True if file can be successfully parsed.</em><a name="291" href="#291">291</a> <em> */</em><a name="292" href="#292">292</a> <strong>public</strong> <strong>boolean</strong> isValid() {<a name="293" href="#293">293</a> <strong>boolean</strong> valid = false;<a name="294" href="#294">294</a> <strong>try</strong> {<a name="295" href="#295">295</a> validate();<a name="296" href="#296">296</a> valid = <strong>true</strong>;<a name="297" href="#297">297</a> } <strong>catch</strong>(Exception e) {<a name="298" href="#298">298</a> <em class="comment">// File is not valid if exception thrown parsing.</em><a name="299" href="#299">299</a> valid = false;<a name="300" href="#300">300</a> }<a name="301" href="#301">301</a> <a name="302" href="#302">302</a> <strong>return</strong> valid;<a name="303" href="#303">303</a> }<a name="304" href="#304">304</a> <a name="305" href="#305">305</a> <em>/**<em>*</em></em><a name="306" href="#306">306</a> <em> * @return Returns the strict.</em><a name="307" href="#307">307</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?