arcreader.html
来自「网络爬虫开源代码」· HTML 代码 · 共 753 行 · 第 1/5 页
HTML
753 行
<a name="445" href="#445">445</a> <strong>return</strong> values;<a name="446" href="#446">446</a> }<a name="447" href="#447">447</a> <em class="comment">// Test 3rd field is valid date.</em><a name="448" href="#448">448</a> <strong>if</strong> (!isDate((String) values.get(values.size() - 3))) {<a name="449" href="#449">449</a> <strong>return</strong> values;<a name="450" href="#450">450</a> }<a name="451" href="#451">451</a> <a name="452" href="#452">452</a> <em class="comment">// Test 4th field is valid IP.</em><a name="453" href="#453">453</a> <strong>if</strong> (!isLegitimateIPValue((String) values.get(values.size() - 4))) {<a name="454" href="#454">454</a> <strong>return</strong> values;<a name="455" href="#455">455</a> }<a name="456" href="#456">456</a> <a name="457" href="#457">457</a> List<String> <strong>new</strong>Values = <strong>new</strong> ArrayList<String>(requiredSize);<a name="458" href="#458">458</a> StringBuffer url = <strong>new</strong> StringBuffer();<a name="459" href="#459">459</a> <strong>for</strong> (<strong>int</strong> i = 0; i < (values.size() - 4); i++) {<a name="460" href="#460">460</a> <strong>if</strong> (i > 0) {<a name="461" href="#461">461</a> url.append(<span class="string">"%20"</span>);<a name="462" href="#462">462</a> }<a name="463" href="#463">463</a> url.append(values.get(i));<a name="464" href="#464">464</a> }<a name="465" href="#465">465</a> newValues.add(url.toString());<a name="466" href="#466">466</a> <strong>for</strong> (<strong>int</strong> i = values.size() - 4; i < values.size(); i++) {<a name="467" href="#467">467</a> newValues.add(values.get(i));<a name="468" href="#468">468</a> }<a name="469" href="#469">469</a> <strong>return</strong> newValues;<a name="470" href="#470">470</a> }<a name="471" href="#471">471</a> <a name="472" href="#472">472</a> <strong>protected</strong> <strong>boolean</strong> isAlignedOnFirstRecord() {<a name="473" href="#473">473</a> <strong>return</strong> alignedOnFirstRecord;<a name="474" href="#474">474</a> }<a name="475" href="#475">475</a> <a name="476" href="#476">476</a> <strong>protected</strong> <strong>void</strong> setAlignedOnFirstRecord(<strong>boolean</strong> alignedOnFirstRecord) {<a name="477" href="#477">477</a> <strong>this</strong>.alignedOnFirstRecord = alignedOnFirstRecord;<a name="478" href="#478">478</a> }<a name="479" href="#479">479</a> <a name="480" href="#480">480</a> <em>/**<em>*</em></em><a name="481" href="#481">481</a> <em> * @return Returns the parseHttpHeaders.</em><a name="482" href="#482">482</a> <em> */</em><a name="483" href="#483">483</a> <strong>public</strong> <strong>boolean</strong> isParseHttpHeaders() {<a name="484" href="#484">484</a> <strong>return</strong> <strong>this</strong>.parseHttpHeaders;<a name="485" href="#485">485</a> }<a name="486" href="#486">486</a> <a name="487" href="#487">487</a> <em>/**<em>*</em></em><a name="488" href="#488">488</a> <em> * @param parse The parseHttpHeaders to set.</em><a name="489" href="#489">489</a> <em> */</em><a name="490" href="#490">490</a> <strong>public</strong> <strong>void</strong> setParseHttpHeaders(<strong>boolean</strong> parse) {<a name="491" href="#491">491</a> <strong>this</strong>.parseHttpHeaders = parse;<a name="492" href="#492">492</a> }<a name="493" href="#493">493</a> <a name="494" href="#494">494</a> <strong>public</strong> String getFileExtension() {<a name="495" href="#495">495</a> <strong>return</strong> ARC_FILE_EXTENSION;<a name="496" href="#496">496</a> }<a name="497" href="#497">497</a> <a name="498" href="#498">498</a> <strong>public</strong> String getDotFileExtension() {<a name="499" href="#499">499</a> <strong>return</strong> DOT_ARC_FILE_EXTENSION;<a name="500" href="#500">500</a> }<a name="501" href="#501">501</a> <a name="502" href="#502">502</a> <strong>protected</strong> <strong>boolean</strong> output(<strong>final</strong> String format) <a name="503" href="#503">503</a> throws IOException, java.text.ParseException {<a name="504" href="#504">504</a> <strong>boolean</strong> result = <strong>super</strong>.output(format);<a name="505" href="#505">505</a> <strong>if</strong>(!result && (format.equals(NOHEAD) || format.equals(HEADER))) {<a name="506" href="#506">506</a> <strong>throw</strong> <strong>new</strong> IOException(format +<a name="507" href="#507">507</a> <span class="string">" format only supported for single Records"</span>);<a name="508" href="#508">508</a> }<a name="509" href="#509">509</a> <strong>return</strong> result;<a name="510" href="#510">510</a> }<a name="511" href="#511">511</a> <a name="512" href="#512">512</a> <strong>public</strong> <strong>boolean</strong> outputRecord(<strong>final</strong> String format) throws IOException {<a name="513" href="#513">513</a> <strong>boolean</strong> result = <strong>super</strong>.outputRecord(format);<a name="514" href="#514">514</a> <strong>if</strong> (result) {<a name="515" href="#515">515</a> <strong>return</strong> result;<a name="516" href="#516">516</a> }<a name="517" href="#517">517</a> <strong>if</strong> (format.equals(NOHEAD)) {<a name="518" href="#518">518</a> <em class="comment">// No point digesting if dumping content.</em><a name="519" href="#519">519</a> setDigest(false);<a name="520" href="#520">520</a> ARCRecord r = (ARCRecord) get();<a name="521" href="#521">521</a> r.skipHttpHeader();<a name="522" href="#522">522</a> r.dump();<a name="523" href="#523">523</a> result = <strong>true</strong>;<a name="524" href="#524">524</a> } <strong>else</strong> <strong>if</strong> (format.equals(HEADER)) {<a name="525" href="#525">525</a> <em class="comment">// No point digesting if dumping content.</em><a name="526" href="#526">526</a> setDigest(false);<a name="527" href="#527">527</a> ARCRecord r = (ARCRecord) get();<a name="528" href="#528">528</a> r.dumpHttpHeader();<a name="529" href="#529">529</a> result = <strong>true</strong>;<a name="530" href="#530">530</a> }<a name="531" href="#531">531</a> <a name="532" href="#532">532</a> <strong>return</strong> result;<a name="533" href="#533">533</a> }<a name="534" href="#534">534</a> <a name="535" href="#535">535</a> <strong>public</strong> <strong>void</strong> dump(<strong>final</strong> <strong>boolean</strong> compress)<a name="536" href="#536">536</a> throws IOException, java.text.ParseException {<a name="537" href="#537">537</a> <em class="comment">// No point digesting if we're doing a dump.</em><a name="538" href="#538">538</a> setDigest(false);<a name="539" href="#539">539</a> <strong>boolean</strong> firstRecord = <strong>true</strong>;<a name="540" href="#540">540</a> <a href="../../../../org/archive/io/arc/ARCWriter.html">ARCWriter</a> writer = <strong>null</strong>;<a name="541" href="#541">541</a> <strong>for</strong> (Iterator<ArchiveRecord> ii = iterator(); ii.hasNext();) {<a name="542" href="#542">542</a> <a href="../../../../org/archive/io/arc/ARCRecord.html">ARCRecord</a> r = (ARCRecord)ii.next();<a name="543" href="#543">543</a> <em class="comment">// We're to dump the arc on stdout.</em><a name="544" href="#544">544</a> <em class="comment">// Get the first record's data if any.</em><a name="545" href="#545">545</a> <a href="../../../../org/archive/io/arc/ARCRecordMetaData.html">ARCRecordMetaData</a> meta = r.getMetaData();<a name="546" href="#546">546</a> <strong>if</strong> (firstRecord) {<a name="547" href="#547">547</a> firstRecord = false;<a name="548" href="#548">548</a> <em class="comment">// Get an ARCWriter.</em><a name="549" href="#549">549</a> ByteArrayOutputStream baos =<a name="550" href="#550">550</a> <strong>new</strong> ByteArrayOutputStream(r.available());<a name="551" href="#551">551</a> <em class="comment">// This is slow but done only once at top of ARC.</em><a name="552" href="#552">552</a> <strong>while</strong> (r.available() > 0) {<a name="553" href="#553">553</a> baos.write(r.read());<a name="554" href="#554">554</a> }<a name="555" href="#555">555</a> List<String> listOfMetadata = <strong>new</strong> ArrayList<String>();<a name="556" href="#556">556</a> listOfMetadata.add(baos.toString(WriterPoolMember.UTF8));<a name="557" href="#557">557</a> <em class="comment">// Assume getArc returns full path to file. ARCWriter</em><a name="558" href="#558">558</a> <em class="comment">// or new File will complain if it is otherwise.</em><a name="559" href="#559">559</a> writer = <strong>new</strong> <a href="../../../../org/archive/io/arc/ARCWriter.html">ARCWriter</a>(<strong>new</strong> AtomicInteger(), System.out,<a name="560" href="#560">560</a> <strong>new</strong> File(meta.getArc()),<a name="561" href="#561">561</a> compress, meta.getDate(), listOfMetadata);<a name="562" href="#562">562</a> <strong>continue</strong>;<a name="563" href="#563">563</a> }<a name="564" href="#564">564</a> <a name="565" href="#565">565</a> writer.write(meta.getUrl(), meta.getMimetype(), meta.getIp(),<a name="566" href="#566">566</a> ArchiveUtils.parse14DigitDate(meta.getDate()).getTime(),<a name="567" href="#567">567</a> (<strong>int</strong>)meta.getLength(), r);<a name="568" href="#568">568</a> }<a name="569" href="#569">569</a> <em class="comment">// System.out.println(System.currentTimeMillis() - start);</em><a name="570" href="#570">570</a> }<a name="571" href="#571">571</a> <a name="572" href="#572">572</a> <em>/**<em>*</em></em><a name="573" href="#573">573</a> <em> * @return an ArchiveReader that will delete a local file on close. Used</em><a name="574" href="#574">574</a> <em> * when we bring Archive files local and need to clean up afterward.</em><a name="575" href="#575">575</a> <em> */</em><a name="576" href="#576">576</a> <strong>public</strong> <a href="../../../../org/archive/io/arc/ARCReader.html">ARCReader</a> getDeleteFileOnCloseReader(<strong>final</strong> File f) {<a name="577" href="#577">577</a> <strong>final</strong> <a href="../../../../org/archive/io/arc/ARCReader.html">ARCReader</a> d = <strong>this</strong>;<a name="578" href="#578">578</a> <strong>return</strong> <strong>new</strong> <a href="../../../../org/archive/io/arc/ARCReader.html">ARCReader</a>() {<a name="579" href="#579">579</a> <strong>private</strong> <strong>final</strong> <a href="../../../../org/archive/io/arc/ARCReader.html">ARCReader</a> delegate = d;<a name="580" href="#580">580</a> <strong>private</strong> File archiveFile = f;<a name="581" href="#581">581</a> <a name="582" href="#582">582</a> <strong>public</strong> <strong>void</strong> close() throws IOException {<a name="583" href="#583">583</a> <strong>this</strong>.delegate.close();<a name="584" href="#584">584</a> <strong>if</strong> (<strong>this</strong>.archiveFile != <strong>null</strong>) {<a name="585" href="#585">585</a> <strong>if</strong> (archiveFile.exists()) {<a name="586" href="#586">586</a> archiveFile.delete();<a name="587" href="#587">587</a> }<a name="588" href="#588">588</a> <strong>this</strong>.archiveFile = <strong>null</strong>;<a name="589" href="#589">589</a> }<a name="590" href="#590">590</a> }<a name="591" href="#591">591</a> <a name="592" href="#592">592</a> <strong>public</strong> <a href="../../../../org/archive/io/ArchiveRecord.html">ArchiveRecord</a> get(<strong>long</strong> o) throws IOException {<a name="593" href="#593">593</a> <strong>return</strong> <strong>this</strong>.delegate.get(o);<a name="594" href="#594">594</a> }<a name="595" href="#595">595</a>
⌨️ 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?