gzippedinputstream.html

来自「网络爬虫开源代码」· HTML 代码 · 共 442 行 · 第 1/3 页

HTML
442
字号
<a name="288" href="#288">288</a>                             <em class="comment">// Found gzip header. Backup the stream the</em><a name="289" href="#289">289</a>                             <em class="comment">// bytes we just found and set result true.</em><a name="290" href="#290">290</a>                             getInputStream().reset();<a name="291" href="#291">291</a>                             result = <strong>true</strong>;<a name="292" href="#292">292</a>                             <strong>break</strong>;<a name="293" href="#293">293</a>                         }<a name="294" href="#294">294</a>                     }<a name="295" href="#295">295</a>                     <em class="comment">// Didn't find gzip header.  Reset stream but one byte</em><a name="296" href="#296">296</a>                     <em class="comment">// futher on then redo header tests.</em><a name="297" href="#297">297</a>                     ps.position(ps.position() - headerRead);<a name="298" href="#298">298</a>                 }<a name="299" href="#299">299</a>             }<a name="300" href="#300">300</a>         } <strong>catch</strong> (IOException e) {<a name="301" href="#301">301</a>             <strong>throw</strong> <strong>new</strong> RuntimeException(<span class="string">"Failed i/o: "</span> + e.getMessage());<a name="302" href="#302">302</a>         }<a name="303" href="#303">303</a>         <strong>return</strong> result;<a name="304" href="#304">304</a>     }<a name="305" href="#305">305</a>     <a name="306" href="#306">306</a>     <strong>protected</strong> <strong>boolean</strong> compareBytes(<strong>final</strong> <strong>int</strong> a, <strong>final</strong> <strong>int</strong> b) {<a name="307" href="#307">307</a>     	<strong>return</strong> ((byte)(a &amp; 0xff)) == ((byte)(b &amp; 0xff));<a name="308" href="#308">308</a>     }<a name="309" href="#309">309</a>   <a name="310" href="#310">310</a>     <strong>protected</strong> Inflater getInflater() {<a name="311" href="#311">311</a>         <strong>return</strong> <strong>this</strong>.inf;<a name="312" href="#312">312</a>     }<a name="313" href="#313">313</a>     <a name="314" href="#314">314</a>     <strong>protected</strong> InputStream getInputStream() {<a name="315" href="#315">315</a>         <strong>return</strong> <strong>this</strong>.in;<a name="316" href="#316">316</a>     }<a name="317" href="#317">317</a>     <a name="318" href="#318">318</a>     <strong>protected</strong> <a href="../../../org/archive/io/GzipHeader.html">GzipHeader</a> getGzipHeader() {<a name="319" href="#319">319</a>         <strong>return</strong> <strong>this</strong>.gzipHeader;<a name="320" href="#320">320</a>     }<a name="321" href="#321">321</a>     <a name="322" href="#322">322</a>     <em>/**<em>*</em></em><a name="323" href="#323">323</a> <em>     * Move to next gzip member in the file.</em><a name="324" href="#324">324</a> <em>     */</em><a name="325" href="#325">325</a>     <strong>protected</strong> <strong>void</strong> resetInflater() {<a name="326" href="#326">326</a>         <strong>this</strong>.eos = false;<a name="327" href="#327">327</a>         <strong>this</strong>.inf.reset();<a name="328" href="#328">328</a>     }<a name="329" href="#329">329</a>     <a name="330" href="#330">330</a>     <em>/**<em>*</em></em><a name="331" href="#331">331</a> <em>     * Read in the gzip header.</em><a name="332" href="#332">332</a> <em>     * @throws IOException</em><a name="333" href="#333">333</a> <em>     */</em><a name="334" href="#334">334</a>     <strong>protected</strong> <strong>void</strong> readHeader() throws IOException {<a name="335" href="#335">335</a>         <strong>new</strong> <a href="../../../org/archive/io/GzipHeader.html">GzipHeader</a>(<strong>this</strong>.in);<a name="336" href="#336">336</a>         <em class="comment">// Reset the crc for subsequent reads.</em><a name="337" href="#337">337</a>         <strong>this</strong>.crc.reset();<a name="338" href="#338">338</a>     }<a name="339" href="#339">339</a> <a name="340" href="#340">340</a>     <em>/**<em>*</em></em><a name="341" href="#341">341</a> <em>     * Seek to passed offset.</em><a name="342" href="#342">342</a> <em>     * </em><a name="343" href="#343">343</a> <em>     * After positioning the stream, it resets the inflater.</em><a name="344" href="#344">344</a> <em>     * Assumption is that public use of this method is only</em><a name="345" href="#345">345</a> <em>     * to position stream at start of a gzip member.</em><a name="346" href="#346">346</a> <em>     * </em><a name="347" href="#347">347</a> <em>     * @param position Absolute position of a gzip member start.</em><a name="348" href="#348">348</a> <em>     * @throws IOException</em><a name="349" href="#349">349</a> <em>     */</em><a name="350" href="#350">350</a>     <strong>public</strong> <strong>void</strong> position(<strong>long</strong> position) throws IOException {<a name="351" href="#351">351</a>         ((RepositionableStream)<strong>this</strong>.in).position(position);<a name="352" href="#352">352</a>         resetInflater();<a name="353" href="#353">353</a>     }<a name="354" href="#354">354</a> <a name="355" href="#355">355</a>     <strong>public</strong> <strong>long</strong> position() throws IOException {<a name="356" href="#356">356</a>        <strong>return</strong>  ((RepositionableStream)<strong>this</strong>.in).position();<a name="357" href="#357">357</a>     }<a name="358" href="#358">358</a>     <a name="359" href="#359">359</a>     <em>/**<em>*</em></em><a name="360" href="#360">360</a> <em>     * Seek to a gzip member.</em><a name="361" href="#361">361</a> <em>     * </em><a name="362" href="#362">362</a> <em>     * Moves stream to new position, resets inflater and reads in the gzip</em><a name="363" href="#363">363</a> <em>     * header ready for subsequent calls to read.</em><a name="364" href="#364">364</a> <em>     * </em><a name="365" href="#365">365</a> <em>     * @param position Absolute position of a gzip member start.</em><a name="366" href="#366">366</a> <em>     * @throws IOException</em><a name="367" href="#367">367</a> <em>     */</em><a name="368" href="#368">368</a>     <strong>public</strong> <strong>void</strong> gzipMemberSeek(<strong>long</strong> position) throws IOException {<a name="369" href="#369">369</a>         position(position);<a name="370" href="#370">370</a>         readHeader();<a name="371" href="#371">371</a>     }<a name="372" href="#372">372</a>     <a name="373" href="#373">373</a>     <strong>public</strong> <strong>void</strong> gzipMemberSeek() throws IOException {<a name="374" href="#374">374</a>         gzipMemberSeek(position());<a name="375" href="#375">375</a>     }<a name="376" href="#376">376</a>     <a name="377" href="#377">377</a>     <em>/**<em>*</em></em><a name="378" href="#378">378</a> <em>     * Gzip passed bytes.</em><a name="379" href="#379">379</a> <em>     * Use only when bytes is small.</em><a name="380" href="#380">380</a> <em>     * @param bytes What to gzip.</em><a name="381" href="#381">381</a> <em>     * @return A gzip member of bytes.</em><a name="382" href="#382">382</a> <em>     * @throws IOException</em><a name="383" href="#383">383</a> <em>     */</em><a name="384" href="#384">384</a>     <strong>public</strong> <strong>static</strong> byte [] gzip(byte [] bytes) throws IOException {<a name="385" href="#385">385</a>         ByteArrayOutputStream baos = <strong>new</strong> ByteArrayOutputStream();<a name="386" href="#386">386</a>         GZIPOutputStream gzipOS = <strong>new</strong> GZIPOutputStream(baos);<a name="387" href="#387">387</a>         gzipOS.write(bytes, 0, bytes.length);<a name="388" href="#388">388</a>         gzipOS.close();<a name="389" href="#389">389</a>         <strong>return</strong> baos.toByteArray();<a name="390" href="#390">390</a>     }<a name="391" href="#391">391</a>     <a name="392" href="#392">392</a>     <em>/**<em>*</em></em><a name="393" href="#393">393</a> <em>     * Tests passed stream is GZIP stream by reading in the HEAD.</em><a name="394" href="#394">394</a> <em>     * Does reposition of stream when done.</em><a name="395" href="#395">395</a> <em>     * @param rs An InputStream that is Repositionable.</em><a name="396" href="#396">396</a> <em>     * @return True if compressed stream.</em><a name="397" href="#397">397</a> <em>     * @throws IOException</em><a name="398" href="#398">398</a> <em>     */</em><a name="399" href="#399">399</a>     <strong>public</strong> <strong>static</strong> <strong>boolean</strong> isCompressedRepositionableStream(<a name="400" href="#400">400</a>             <strong>final</strong> RepositionableStream rs)<a name="401" href="#401">401</a>     throws IOException {<a name="402" href="#402">402</a>         <strong>boolean</strong> result = false;<a name="403" href="#403">403</a>         <strong>long</strong> p = rs.position();<a name="404" href="#404">404</a>         <strong>try</strong> {<a name="405" href="#405">405</a>             result = isCompressedStream((InputStream)rs);<a name="406" href="#406">406</a>         } <strong>finally</strong> {<a name="407" href="#407">407</a>             rs.position(p);<a name="408" href="#408">408</a>         }<a name="409" href="#409">409</a>         <strong>return</strong> result; <a name="410" href="#410">410</a>     }<a name="411" href="#411">411</a>     <a name="412" href="#412">412</a>     <em>/**<em>*</em></em><a name="413" href="#413">413</a> <em>     * Tests passed stream is gzip stream by reading in the HEAD.</em><a name="414" href="#414">414</a> <em>     * Does not reposition stream when done.</em><a name="415" href="#415">415</a> <em>     * @param is An InputStream.</em><a name="416" href="#416">416</a> <em>     * @return True if compressed stream.</em><a name="417" href="#417">417</a> <em>     * @throws IOException</em><a name="418" href="#418">418</a> <em>     */</em><a name="419" href="#419">419</a>     <strong>public</strong> <strong>static</strong> <strong>boolean</strong> isCompressedStream(<strong>final</strong> InputStream is)<a name="420" href="#420">420</a>     throws IOException {<a name="421" href="#421">421</a>         <strong>try</strong> {<a name="422" href="#422">422</a>             <strong>new</strong> <a href="../../../org/archive/io/GzipHeader.html">GzipHeader</a>(is);<a name="423" href="#423">423</a>         } <strong>catch</strong> (NoGzipMagicException e) {<a name="424" href="#424">424</a>             <strong>return</strong> false;<a name="425" href="#425">425</a>         }<a name="426" href="#426">426</a>         <strong>return</strong> <strong>true</strong>;<a name="427" href="#427">427</a>     }<a name="428" href="#428">428</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?