multibytereplaycharsequence.html
来自「网络爬虫开源代码」· HTML 代码 · 共 356 行 · 第 1/2 页
HTML
356 行
<a name="170" href="#170">170</a> <em> * the in-memory prefix buffer and the backing file. Returns a</em><a name="171" href="#171">171</a> <em> * charSequence view onto this new file.</em><a name="172" href="#172">172</a> <em> *</em><a name="173" href="#173">173</a> <em> * @param buffer In-memory buffer of recordings prefix. We read from</em><a name="174" href="#174">174</a> <em> * here first and will only go to the backing file if <code>size</code></em><a name="175" href="#175">175</a> <em> * requested is greater than <code>buffer.length</code>.</em><a name="176" href="#176">176</a> <em> * @param size Total size of stream to replay in bytes. Used to find</em><a name="177" href="#177">177</a> <em> * EOS. This is total length of content including HTTP headers if</em><a name="178" href="#178">178</a> <em> * present.</em><a name="179" href="#179">179</a> <em> * @param responseBodyStart Where the response body starts in bytes.</em><a name="180" href="#180">180</a> <em> * Used to skip over the HTTP headers if present.</em><a name="181" href="#181">181</a> <em> * @param backingFilename Path to backing file with content in excess of</em><a name="182" href="#182">182</a> <em> * whats in <code>buffer</code>.</em><a name="183" href="#183">183</a> <em> * @param encoding Encoding to use reading the passed prefix buffer and</em><a name="184" href="#184">184</a> <em> * backing file. For now, should be java canonical name for the</em><a name="185" href="#185">185</a> <em> * encoding. (If null is passed, we will default to</em><a name="186" href="#186">186</a> <em> * ByteReplayCharSequence).</em><a name="187" href="#187">187</a> <em> *</em><a name="188" href="#188">188</a> <em> * @return A CharBuffer view on decodings of the contents of passed</em><a name="189" href="#189">189</a> <em> * buffer.</em><a name="190" href="#190">190</a> <em> * @throws IOException</em><a name="191" href="#191">191</a> <em> */</em><a name="192" href="#192">192</a> <strong>private</strong> CharBuffer decodeToFile(<a href="../../../org/archive/io/ReplayInputStream.html">ReplayInputStream</a> inStream, <a name="193" href="#193">193</a> String backingFilename, String encoding)<a name="194" href="#194">194</a> throws IOException {<a name="195" href="#195">195</a> <a name="196" href="#196">196</a> CharBuffer charBuffer = <strong>null</strong>;<a name="197" href="#197">197</a> <a name="198" href="#198">198</a> BufferedReader reader = <strong>new</strong> BufferedReader(<a name="199" href="#199">199</a> <strong>new</strong> InputStreamReader(inStream,encoding));<a name="200" href="#200">200</a> <a name="201" href="#201">201</a> <strong>this</strong>.decodedFile = <strong>new</strong> File(backingFilename + <span class="string">"."</span> + WRITE_ENCODING);<a name="202" href="#202">202</a> BufferedWriter writer = <strong>new</strong> BufferedWriter(<a name="203" href="#203">203</a> <strong>new</strong> OutputStreamWriter(<a name="204" href="#204">204</a> <strong>new</strong> FileOutputStream(<strong>this</strong>.decodedFile), <a name="205" href="#205">205</a> WRITE_ENCODING)); <a name="206" href="#206">206</a> <a name="207" href="#207">207</a> <strong>int</strong> c;<a name="208" href="#208">208</a> <strong>while</strong>((c = reader.read())>=0) {<a name="209" href="#209">209</a> writer.write(c);<a name="210" href="#210">210</a> }<a name="211" href="#211">211</a> writer.close();<a name="212" href="#212">212</a> <a name="213" href="#213">213</a> charBuffer = getReadOnlyMemoryMappedBuffer(<strong>this</strong>.decodedFile).<a name="214" href="#214">214</a> asCharBuffer();<a name="215" href="#215">215</a> <a name="216" href="#216">216</a> <strong>return</strong> charBuffer;<a name="217" href="#217">217</a> }<a name="218" href="#218">218</a> <a name="219" href="#219">219</a> <em>/**<em>*</em></em><a name="220" href="#220">220</a> <em> * Decode passed buffer into a CharBuffer.</em><a name="221" href="#221">221</a> <em> *</em><a name="222" href="#222">222</a> <em> * This method decodes a memory buffer returning a memory buffer.</em><a name="223" href="#223">223</a> <em> *</em><a name="224" href="#224">224</a> <em> * @param buffer In-memory buffer of recordings prefix. We read from</em><a name="225" href="#225">225</a> <em> * here first and will only go to the backing file if <code>size</code></em><a name="226" href="#226">226</a> <em> * requested is greater than <code>buffer.length</code>.</em><a name="227" href="#227">227</a> <em> * @param size Total size of stream to replay in bytes. Used to find</em><a name="228" href="#228">228</a> <em> * EOS. This is total length of content including HTTP headers if</em><a name="229" href="#229">229</a> <em> * present.</em><a name="230" href="#230">230</a> <em> * @param responseBodyStart Where the response body starts in bytes.</em><a name="231" href="#231">231</a> <em> * Used to skip over the HTTP headers if present.</em><a name="232" href="#232">232</a> <em> * @param encoding Encoding to use reading the passed prefix buffer and</em><a name="233" href="#233">233</a> <em> * backing file. For now, should be java canonical name for the</em><a name="234" href="#234">234</a> <em> * encoding. (If null is passed, we will default to</em><a name="235" href="#235">235</a> <em> * ByteReplayCharSequence).</em><a name="236" href="#236">236</a> <em> *</em><a name="237" href="#237">237</a> <em> * @return A CharBuffer view on decodings of the contents of passed</em><a name="238" href="#238">238</a> <em> * buffer.</em><a name="239" href="#239">239</a> <em> */</em><a name="240" href="#240">240</a> <strong>private</strong> CharBuffer decodeInMemory(byte[] buffer, <strong>long</strong> size,<a name="241" href="#241">241</a> <strong>long</strong> responseBodyStart, String encoding)<a name="242" href="#242">242</a> {<a name="243" href="#243">243</a> ByteBuffer bb = ByteBuffer.wrap(buffer);<a name="244" href="#244">244</a> <em class="comment">// Move past the HTTP header if present.</em><a name="245" href="#245">245</a> bb.position((<strong>int</strong>)responseBodyStart);<a name="246" href="#246">246</a> <em class="comment">// Set the end-of-buffer to be end-of-content.</em><a name="247" href="#247">247</a> bb.limit((<strong>int</strong>)size);<a name="248" href="#248">248</a> <strong>return</strong> (Charset.forName(encoding)).decode(bb).asReadOnlyBuffer();<a name="249" href="#249">249</a> }<a name="250" href="#250">250</a> <a name="251" href="#251">251</a> <em>/**<em>*</em></em><a name="252" href="#252">252</a> <em> * Create read-only memory-mapped buffer onto passed file.</em><a name="253" href="#253">253</a> <em> *</em><a name="254" href="#254">254</a> <em> * @param file File to get memory-mapped buffer on.</em><a name="255" href="#255">255</a> <em> * @return Read-only memory-mapped ByteBuffer view on to passed file.</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>private</strong> ByteBuffer getReadOnlyMemoryMappedBuffer(File file)<a name="259" href="#259">259</a> throws IOException {<a name="260" href="#260">260</a> <a name="261" href="#261">261</a> ByteBuffer bb = <strong>null</strong>;<a name="262" href="#262">262</a> FileInputStream in = <strong>null</strong>;<a name="263" href="#263">263</a> FileChannel c = <strong>null</strong>;<a name="264" href="#264">264</a> assert file.exists(): <span class="string">"No file "</span> + file.getAbsolutePath();<a name="265" href="#265">265</a> <a name="266" href="#266">266</a> <strong>try</strong> {<a name="267" href="#267">267</a> in = <strong>new</strong> FileInputStream(file);<a name="268" href="#268">268</a> c = in.getChannel();<a name="269" href="#269">269</a> <em class="comment">// TODO: Confirm the READ_ONLY works. I recall it not working.</em><a name="270" href="#270">270</a> <em class="comment">// The buffers seem to always say that the buffer is writeable.</em><a name="271" href="#271">271</a> bb = c.map(FileChannel.MapMode.READ_ONLY, 0, c.size()).<a name="272" href="#272">272</a> asReadOnlyBuffer();<a name="273" href="#273">273</a> }<a name="274" href="#274">274</a> <a name="275" href="#275">275</a> <strong>finally</strong> {<a name="276" href="#276">276</a> <strong>if</strong> (c != <strong>null</strong> && c.isOpen()) {<a name="277" href="#277">277</a> c.close();<a name="278" href="#278">278</a> }<a name="279" href="#279">279</a> <strong>if</strong> (in != <strong>null</strong>) {<a name="280" href="#280">280</a> in.close();<a name="281" href="#281">281</a> }<a name="282" href="#282">282</a> }<a name="283" href="#283">283</a> <a name="284" href="#284">284</a> <strong>return</strong> bb;<a name="285" href="#285">285</a> }<a name="286" href="#286">286</a> <a name="287" href="#287">287</a> <strong>private</strong> <strong>void</strong> deleteFile(File fileToDelete) {<a name="288" href="#288">288</a> deleteFile(fileToDelete, <strong>null</strong>); <a name="289" href="#289">289</a> }<a name="290" href="#290">290</a> <a name="291" href="#291">291</a> <strong>private</strong> <strong>void</strong> deleteFile(File fileToDelete, <strong>final</strong> Exception e) {<a name="292" href="#292">292</a> <strong>if</strong> (e != <strong>null</strong>) {<a name="293" href="#293">293</a> <em class="comment">// Log why the delete to help with debug of java.io.FileNotFoundException:</em><a name="294" href="#294">294</a> <em class="comment">// ....tt53http.ris.UTF-16BE.</em><a name="295" href="#295">295</a> logger.severe(<span class="string">"Deleting "</span> + fileToDelete + <span class="string">" because of "</span><a name="296" href="#296">296</a> + e.toString());<a name="297" href="#297">297</a> }<a name="298" href="#298">298</a> <strong>if</strong> (fileToDelete != <strong>null</strong> && fileToDelete.exists()) {<a name="299" href="#299">299</a> fileToDelete.delete();<a name="300" href="#300">300</a> }<a name="301" href="#301">301</a> }<a name="302" href="#302">302</a> <a name="303" href="#303">303</a> <strong>public</strong> <strong>void</strong> close()<a name="304" href="#304">304</a> {<a name="305" href="#305">305</a> <strong>this</strong>.content = <strong>null</strong>;<a name="306" href="#306">306</a> deleteFile(<strong>this</strong>.decodedFile);<a name="307" href="#307">307</a> <em class="comment">// clear decodedFile -- so that double-close (as in </em><a name="308" href="#308">308</a> <em class="comment">// finalize()) won't delete a later instance with same name</em><a name="309" href="#309">309</a> <em class="comment">// see bug [ 1218961 ] "failed get of replay" in ExtractorHTML... usu: UTF-16BE</em><a name="310" href="#310">310</a> <strong>this</strong>.decodedFile = <strong>null</strong>;<a name="311" href="#311">311</a> }<a name="312" href="#312">312</a> <a name="313" href="#313">313</a> <strong>protected</strong> <strong>void</strong> finalize() throws Throwable<a name="314" href="#314">314</a> {<a name="315" href="#315">315</a> <strong>super</strong>.finalize();<a name="316" href="#316">316</a> <em class="comment">// Maybe TODO: eliminate close here, requiring explicit close instead</em><a name="317" href="#317">317</a> close();<a name="318" href="#318">318</a> }<a name="319" href="#319">319</a> <a name="320" href="#320">320</a> <strong>public</strong> <strong>int</strong> length()<a name="321" href="#321">321</a> {<a name="322" href="#322">322</a> <strong>return</strong> <strong>this</strong>.content.limit();<a name="323" href="#323">323</a> }<a name="324" href="#324">324</a> <a name="325" href="#325">325</a> <strong>public</strong> <strong>char</strong> <strong>char</strong>At(<strong>int</strong> index)<a name="326" href="#326">326</a> {<a name="327" href="#327">327</a> <strong>return</strong> <strong>this</strong>.content.get(index);<a name="328" href="#328">328</a> }<a name="329" href="#329">329</a> <a name="330" href="#330">330</a> <strong>public</strong> CharSequence subSequence(<strong>int</strong> start, <strong>int</strong> end) {<a name="331" href="#331">331</a> <strong>return</strong> <strong>new</strong> <a href="../../../org/archive/io/CharSubSequence.html">CharSubSequence</a>(<strong>this</strong>, start, end);<a name="332" href="#332">332</a> }<a name="333" href="#333">333</a> <a name="334" href="#334">334</a> <strong>public</strong> String toString() {<a name="335" href="#335">335</a> StringBuffer sb = <strong>new</strong> StringBuffer(length());<a name="336" href="#336">336</a> <em class="comment">// could use StringBuffer.append(CharSequence) if willing to do 1.5 & up</em><a name="337" href="#337">337</a> <strong>for</strong> (<strong>int</strong> i = 0;i<length();i++) {<a name="338" href="#338">338</a> sb.append(charAt(i)); <a name="339" href="#339">339</a> }<a name="340" href="#340">340</a> <strong>return</strong> sb.toString();<a name="341" href="#341">341</a> }<a name="342" href="#342">342</a> }</pre><hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body></html>
⌨️ 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?