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="308" href="#308">308</a> <strong>public</strong> <strong>boolean</strong> isStrict() {<a name="309" href="#309">309</a> <strong>return</strong> <strong>this</strong>.strict;<a name="310" href="#310">310</a> }<a name="311" href="#311">311</a> <a name="312" href="#312">312</a> <em>/**<em>*</em></em><a name="313" href="#313">313</a> <em> * @param s The strict to set.</em><a name="314" href="#314">314</a> <em> */</em><a name="315" href="#315">315</a> <strong>public</strong> <strong>void</strong> setStrict(<strong>boolean</strong> s) {<a name="316" href="#316">316</a> <strong>this</strong>.strict = s;<a name="317" href="#317">317</a> }<a name="318" href="#318">318</a> <a name="319" href="#319">319</a> <em>/**<em>*</em></em><a name="320" href="#320">320</a> <em> * @param d True if we're to digest.</em><a name="321" href="#321">321</a> <em> */</em><a name="322" href="#322">322</a> <strong>public</strong> <strong>void</strong> setDigest(<strong>boolean</strong> d) {<a name="323" href="#323">323</a> <strong>this</strong>.digest = d;<a name="324" href="#324">324</a> }<a name="325" href="#325">325</a> <a name="326" href="#326">326</a> <em>/**<em>*</em></em><a name="327" href="#327">327</a> <em> * @return True if we're digesting as we read.</em><a name="328" href="#328">328</a> <em> */</em><a name="329" href="#329">329</a> <strong>public</strong> <strong>boolean</strong> isDigest() {<a name="330" href="#330">330</a> <strong>return</strong> <strong>this</strong>.digest;<a name="331" href="#331">331</a> }<a name="332" href="#332">332</a> <a name="333" href="#333">333</a> <strong>protected</strong> Logger getLogger() {<a name="334" href="#334">334</a> <strong>return</strong> Logger.getLogger(<strong>this</strong>.getClass().getName());<a name="335" href="#335">335</a> }<a name="336" href="#336">336</a> <a name="337" href="#337">337</a> <strong>protected</strong> InputStream getInputStream() {<a name="338" href="#338">338</a> <strong>return</strong> <strong>this</strong>.in;<a name="339" href="#339">339</a> }<a name="340" href="#340">340</a> <a name="341" href="#341">341</a> <em>/**<em>*</em></em><a name="342" href="#342">342</a> <em> * Returns an ArchiveRecord iterator.</em><a name="343" href="#343">343</a> <em> * Of note, on IOException, especially if ZipException reading compressed</em><a name="344" href="#344">344</a> <em> * ARCs, rather than fail the iteration, try moving to the next record.</em><a name="345" href="#345">345</a> <em> * If {@link ArchiveReader#strict} is not set, this will usually succeed.</em><a name="346" href="#346">346</a> <em> * @return An iterator over ARC records.</em><a name="347" href="#347">347</a> <em> */</em><a name="348" href="#348">348</a> <strong>public</strong> Iterator<ArchiveRecord> iterator() {<a name="349" href="#349">349</a> <em class="comment">// Eat up any record outstanding.</em><a name="350" href="#350">350</a> <strong>try</strong> {<a name="351" href="#351">351</a> cleanupCurrentRecord();<a name="352" href="#352">352</a> } <strong>catch</strong> (IOException e) {<a name="353" href="#353">353</a> <strong>throw</strong> <strong>new</strong> RuntimeException(e);<a name="354" href="#354">354</a> }<a name="355" href="#355">355</a> <a name="356" href="#356">356</a> <em class="comment">// Now reset stream to the start of the arc file.</em><a name="357" href="#357">357</a> <strong>try</strong> {<a name="358" href="#358">358</a> rewind();<a name="359" href="#359">359</a> } <strong>catch</strong> (IOException e) {<a name="360" href="#360">360</a> <strong>throw</strong> <strong>new</strong> RuntimeException(e);<a name="361" href="#361">361</a> }<a name="362" href="#362">362</a> <strong>return</strong> <strong>new</strong> ArchiveRecordIterator();<a name="363" href="#363">363</a> }<a name="364" href="#364">364</a> <a name="365" href="#365">365</a> <strong>protected</strong> <strong>void</strong> setCompressed(<strong>boolean</strong> compressed) {<a name="366" href="#366">366</a> <strong>this</strong>.compressed = compressed;<a name="367" href="#367">367</a> }<a name="368" href="#368">368</a> <a name="369" href="#369">369</a> <em>/**<em>*</em></em><a name="370" href="#370">370</a> <em> * @return The current ARC record or null if none.</em><a name="371" href="#371">371</a> <em> * After construction has the arcfile header record.</em><a name="372" href="#372">372</a> <em> * @see #get()</em><a name="373" href="#373">373</a> <em> */</em><a name="374" href="#374">374</a> <strong>protected</strong> <a href="../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> getCurrentRecord() {<a name="375" href="#375">375</a> <strong>return</strong> <strong>this</strong>.currentRecord;<a name="376" href="#376">376</a> }<a name="377" href="#377">377</a> <a name="378" href="#378">378</a> <strong>protected</strong> <a href="../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> currentRecord(<strong>final</strong> <a href="../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> currentRecord) {<a name="379" href="#379">379</a> <strong>this</strong>.currentRecord = currentRecord;<a name="380" href="#380">380</a> <strong>return</strong> currentRecord;<a name="381" href="#381">381</a> }<a name="382" href="#382">382</a> <a name="383" href="#383">383</a> <strong>protected</strong> InputStream getIn() {<a name="384" href="#384">384</a> <strong>return</strong> in;<a name="385" href="#385">385</a> }<a name="386" href="#386">386</a> <a name="387" href="#387">387</a> <strong>protected</strong> <strong>void</strong> setIn(InputStream in) {<a name="388" href="#388">388</a> <strong>this</strong>.in = in;<a name="389" href="#389">389</a> }<a name="390" href="#390">390</a> <a name="391" href="#391">391</a> <strong>protected</strong> <strong>void</strong> setVersion(String version) {<a name="392" href="#392">392</a> <strong>this</strong>.version = version;<a name="393" href="#393">393</a> }<a name="394" href="#394">394</a> <a name="395" href="#395">395</a> <strong>public</strong> String getReaderIdentifier() {<a name="396" href="#396">396</a> <strong>return</strong> <strong>this</strong>.identifier;<a name="397" href="#397">397</a> }<a name="398" href="#398">398</a> <a name="399" href="#399">399</a> <strong>protected</strong> <strong>void</strong> setReaderIdentifier(<strong>final</strong> String i) {<a name="400" href="#400">400</a> <strong>this</strong>.identifier = i;<a name="401" href="#401">401</a> }<a name="402" href="#402">402</a> <a name="403" href="#403">403</a> <em>/**<em>*</em></em><a name="404" href="#404">404</a> <em> * Log on stderr.</em><a name="405" href="#405">405</a> <em> * Logging should go via the logging system. This method</em><a name="406" href="#406">406</a> <em> * bypasses the logging system going direct to stderr.</em><a name="407" href="#407">407</a> <em> * Should not generally be used. Its used for rare messages</em><a name="408" href="#408">408</a> <em> * that come of cmdline usage of ARCReader ERRORs and WARNINGs.</em><a name="409" href="#409">409</a> <em> * Override if using ARCReader in a context where no stderr or</em><a name="410" href="#410">410</a> <em> * where you'd like to redirect stderr to other than System.err.</em><a name="411" href="#411">411</a> <em> * @param level Level to log message at.</em><a name="412" href="#412">412</a> <em> * @param message Message to log.</em><a name="413" href="#413">413</a> <em> */</em><a name="414" href="#414">414</a> <strong>public</strong> <strong>void</strong> logStdErr(Level level, String message) {<a name="415" href="#415">415</a> System.err.println(level.toString() + <span class="string">" "</span> + message);<a name="416" href="#416">416</a> }<a name="417" href="#417">417</a> <a name="418" href="#418">418</a> <em>/**<em>*</em></em><a name="419" href="#419">419</a> <em> * Add buffering to RandomAccessInputStream.</em><a name="420" href="#420">420</a> <em> */</em><a name="421" href="#421">421</a> <strong>protected</strong> <strong>class</strong> RandomAccessBufferedInputStream<a name="422" href="#422">422</a> <strong>extends</strong> BufferedInputStream implements RepositionableStream {<a name="423" href="#423">423</a> <a name="424" href="#424">424</a> <strong>public</strong> RandomAccessBufferedInputStream(<a href="../../../org/archive/io/RandomAccessInputStream.html">RandomAccessInputStream</a> is)<a name="425" href="#425">425</a> throws IOException {<a name="426" href="#426">426</a> <strong>super</strong>(is);<a name="427" href="#427">427</a> }<a name="428" href="#428">428</a> <a name="429" href="#429">429</a> <strong>public</strong> RandomAccessBufferedInputStream(<a href="../../../org/archive/io/RandomAccessInputStream.html">RandomAccessInputStream</a> is, <strong>int</strong> size)<a name="430" href="#430">430</a> throws IOException {<a name="431" href="#431">431</a> <strong>super</strong>(is, size);<a name="432" href="#432">432</a> }<a name="433" href="#433">433</a> <a name="434" href="#434">434</a> <strong>public</strong> <strong>long</strong> position() throws IOException {<a name="435" href="#435">435</a> <em class="comment">// Current position is the underlying files position</em><a name="436" href="#436">436</a> <em class="comment">// minus the amount thats in the buffer yet to be read.</em><a name="437" href="#437">437</a> <strong>return</strong> ((RandomAccessInputStream)<strong>this</strong>.in).position() -<a name="438" href="#438">438</a> (<strong>this</strong>.count - <strong>this</strong>.pos);<a name="439" href="#439">439</a> }<a name="440" href="#440">440</a> <a name="441" href="#441">441</a> <strong>public</strong> <strong>void</strong> position(<strong>long</strong> position) throws IOException {<a name="442" href="#442">442</a> <em class="comment">// Force refill of buffer whenever there's been a seek.</em><a name="443" href="#443">443</a> <strong>this</strong>.pos = 0;<a name="444" href="#444">444</a> <strong>this</strong>.count = 0;<a name="445" href="#445">445</a> ((<a href="../../../org/archive/io/RandomAccessInputStream.html">RandomAccessInputStream</a>)<strong>this</strong>.in).position(position);<a name="446" href="#446">446</a> }<a name="447" href="#447">447</a> }<a name="448" href="#448">448</a> <a name="449" href="#449">449</a> <em>/**<em>*</em></em><a name="450" href="#450">450</a> <em> * Inner ArchiveRecord Iterator class.</em><a name="451" href="#451">451</a> <em> * Throws RuntimeExceptions in {@link #hasNext()} and {@link #next()} if</em><a name="452" href="#452">452</a> <em> * trouble pulling record from underlying stream.</em><a name="453" href="#453">453</a> <em> * @author stack</em><a name="454" href="#454">454</a> <em> */</em><a name="455" href="#455">455</a> <strong>protected</strong> <strong>class</strong> ArchiveRecordIterator implements Iterator<ArchiveRecord> {<a name="456" href="#456">456</a> <strong>private</strong> <strong>final</strong> Logger logger =<a name="457" href="#457">457</a> Logger.getLogger(<strong>this</strong>.getClass().getName());<a name="458" href="#458">458</a> <em>/**<em>*</em></em><a name="459" href="#459">459</a> <em> * @return True if we have more records to read.</em><a name="460" href="#460">460</a> <em> * @exception RuntimeException Can throw an IOException wrapped in a</em><a name="461" href="#461">461</a> <em> * RuntimeException if a problem reading underlying stream (Corrupted</em><a name="462" href="#462">462</a> <em> * gzip, etc.).</em><a name="463" href="#463">463</a> <em> */</em><a name="464" href="#464">464</a> <strong>public</strong> <strong>boolean</strong> hasNext() {<a name="465" href="#465">465</a> <em class="comment">// Call close on any extant record. This will scoot us past</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?