📄 arcreader.html
字号:
<a name="282" href="#282">282</a> <strong>if</strong> (c == LINE_SEPARATOR) {<a name="283" href="#283">283</a> <strong>if</strong> (buffer.length() == 0) {<a name="284" href="#284">284</a> <em class="comment">// Empty line at start of buffer. Skip it and try again.</em><a name="285" href="#285">285</a> <strong>continue</strong>;<a name="286" href="#286">286</a> }<a name="287" href="#287">287</a> <a name="288" href="#288">288</a> <strong>if</strong> (list != <strong>null</strong>) {<a name="289" href="#289">289</a> list.add(buffer.toString());<a name="290" href="#290">290</a> }<a name="291" href="#291">291</a> <em class="comment">// LOOP TERMINATION.</em><a name="292" href="#292">292</a> <strong>break</strong>;<a name="293" href="#293">293</a> } <strong>else</strong> <strong>if</strong> (c == HEADER_FIELD_SEPARATOR) {<a name="294" href="#294">294</a> <strong>if</strong> (list != <strong>null</strong>) {<a name="295" href="#295">295</a> list.add(buffer.toString());<a name="296" href="#296">296</a> }<a name="297" href="#297">297</a> buffer = <strong>new</strong> StringBuffer();<a name="298" href="#298">298</a> } <strong>else</strong> {<a name="299" href="#299">299</a> buffer.append((<strong>char</strong>)c);<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> <em class="comment">// List must have at least 3 elements in it and no more than 10. If</em><a name="304" href="#304">304</a> <em class="comment">// it has other than this, then bogus parse.</em><a name="305" href="#305">305</a> <strong>if</strong> (list != <strong>null</strong> && (list.size() < 3 || list.size() > 100)) {<a name="306" href="#306">306</a> <strong>throw</strong> <strong>new</strong> IOException(<span class="string">"Unparseable header line: "</span> + list);<a name="307" href="#307">307</a> }<a name="308" href="#308">308</a> <a name="309" href="#309">309</a> <strong>return</strong> read;<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> * Compute metadata fields.</em><a name="314" href="#314">314</a> <em> *</em><a name="315" href="#315">315</a> <em> * Here we check the meta field has right number of items in it.</em><a name="316" href="#316">316</a> <em> *</em><a name="317" href="#317">317</a> <em> * @param keys Keys to use composing headerFields map.</em><a name="318" href="#318">318</a> <em> * @param values Values to set into the headerFields map.</em><a name="319" href="#319">319</a> <em> * @param v The version of this ARC file.</em><a name="320" href="#320">320</a> <em> * @param offset Offset into arc file.</em><a name="321" href="#321">321</a> <em> *</em><a name="322" href="#322">322</a> <em> * @return Metadata structure for this record.</em><a name="323" href="#323">323</a> <em> *</em><a name="324" href="#324">324</a> <em> * @exception IOException If no. of keys doesn't match no. of values.</em><a name="325" href="#325">325</a> <em> */</em><a name="326" href="#326">326</a> <strong>private</strong> <a href="../../../../org/archive/io/arc/ARCRecordMetaData.html">ARCRecordMetaData</a> computeMetaData(List<String> keys,<a name="327" href="#327">327</a> List<String> values, String v, <strong>long</strong> offset)<a name="328" href="#328">328</a> throws IOException {<a name="329" href="#329">329</a> <strong>if</strong> (keys.size() != values.size()) {<a name="330" href="#330">330</a> List<String> originalValues = values;<a name="331" href="#331">331</a> <strong>if</strong> (!isStrict()) {<a name="332" href="#332">332</a> values = fixSpaceInMetadataLine(values, keys.size());<a name="333" href="#333">333</a> }<a name="334" href="#334">334</a> <strong>if</strong> (keys.size() != values.size()) {<a name="335" href="#335">335</a> <strong>throw</strong> <strong>new</strong> IOException(<span class="string">"Size of field name keys does"</span> +<a name="336" href="#336">336</a> <span class="string">" not match count of field values: "</span> + values);<a name="337" href="#337">337</a> }<a name="338" href="#338">338</a> <em class="comment">// Note that field was fixed on stderr.</em><a name="339" href="#339">339</a> logStdErr(Level.WARNING, <span class="string">"Fixed spaces in metadata URL."</span> +<a name="340" href="#340">340</a> <span class="string">" Original: "</span> + originalValues + <span class="string">", New: "</span> + values);<a name="341" href="#341">341</a> }<a name="342" href="#342">342</a> <a name="343" href="#343">343</a> Map<Object, Object> headerFields =<a name="344" href="#344">344</a> <strong>new</strong> HashMap<Object, Object>(keys.size() + 2);<a name="345" href="#345">345</a> <strong>for</strong> (<strong>int</strong> i = 0; i < keys.size(); i++) {<a name="346" href="#346">346</a> headerFields.put(keys.get(i), values.get(i));<a name="347" href="#347">347</a> }<a name="348" href="#348">348</a> <a name="349" href="#349">349</a> <em class="comment">// Add a check for tabs in URLs. If any, replace with '%09'.</em><a name="350" href="#350">350</a> <em class="comment">// See https://sourceforge.net/tracker/?group_id=73833&atid=539099&func=detail&aid=1010966,</em><a name="351" href="#351">351</a> <em class="comment">// [ 1010966 ] crawl.log has URIs with spaces in them.</em><a name="352" href="#352">352</a> String url = (String)headerFields.get(URL_FIELD_KEY);<a name="353" href="#353">353</a> <strong>if</strong> (url != <strong>null</strong> && url.indexOf('\t') >= 0) {<a name="354" href="#354">354</a> headerFields.put(URL_FIELD_KEY,<a name="355" href="#355">355</a> TextUtils.replaceAll(<span class="string">"\t"</span>, url, <span class="string">"%09"</span>));<a name="356" href="#356">356</a> }<a name="357" href="#357">357</a> <a name="358" href="#358">358</a> headerFields.put(VERSION_FIELD_KEY, v);<a name="359" href="#359">359</a> headerFields.put(ABSOLUTE_OFFSET_KEY, <strong>new</strong> Long(offset));<a name="360" href="#360">360</a> <a name="361" href="#361">361</a> <strong>return</strong> <strong>new</strong> <a href="../../../../org/archive/io/arc/ARCRecordMetaData.html">ARCRecordMetaData</a>(getReaderIdentifier(), headerFields);<a name="362" href="#362">362</a> }<a name="363" href="#363">363</a> <a name="364" href="#364">364</a> <em>/**<em>*</em></em><a name="365" href="#365">365</a> <em> * Fix space in URLs.</em><a name="366" href="#366">366</a> <em> * The ARCWriter used to write into the ARC URLs with spaces in them.</em><a name="367" href="#367">367</a> <em> * See <a</em><a name="368" href="#368">368</a> <em> * href="https://sourceforge.net/tracker/?group_id=73833&atid=539099&func=detail&aid=1010966">[ 1010966 ]</em><a name="369" href="#369">369</a> <em> * crawl.log has URIs with spaces in them</a>.</em><a name="370" href="#370">370</a> <em> * This method does fix up on such headers converting all spaces found</em><a name="371" href="#371">371</a> <em> * to '%20'.</em><a name="372" href="#372">372</a> <em> * @param values List of metadata values.</em><a name="373" href="#373">373</a> <em> * @param requiredSize Expected size of resultant values list.</em><a name="374" href="#374">374</a> <em> * @return New list if we successfully fixed up values or original if</em><a name="375" href="#375">375</a> <em> * fixup failed.</em><a name="376" href="#376">376</a> <em> */</em><a name="377" href="#377">377</a> <strong>protected</strong> List<String> fixSpaceInMetadataLine(List<String> values,<a name="378" href="#378">378</a> <strong>int</strong> requiredSize) {<a name="379" href="#379">379</a> <em class="comment">// Do validity check. 3rd from last is a date of 14 numeric</em><a name="380" href="#380">380</a> <em class="comment">// characters. The 4th from last is IP, all before the IP</em><a name="381" href="#381">381</a> <em class="comment">// should be concatenated together with a '%20' joiner.</em><a name="382" href="#382">382</a> <em class="comment">// In the below, '4' is 4th field from end which has the IP.</em><a name="383" href="#383">383</a> <strong>if</strong> (!(values.size() > requiredSize) || values.size() < 4) {<a name="384" href="#384">384</a> <strong>return</strong> values;<a name="385" href="#385">385</a> }<a name="386" href="#386">386</a> <em class="comment">// Test 3rd field is valid date.</em><a name="387" href="#387">387</a> String date = (String)values.get(values.size() - 3);<a name="388" href="#388">388</a> <strong>if</strong> (date.length() != 14) {<a name="389" href="#389">389</a> <strong>return</strong> values;<a name="390" href="#390">390</a> }<a name="391" href="#391">391</a> <strong>for</strong> (<strong>int</strong> i = 0; i < date.length(); i++) {<a name="392" href="#392">392</a> <strong>if</strong> (!Character.isDigit(date.charAt(i))) {<a name="393" href="#393">393</a> <strong>return</strong> values;<a name="394" href="#394">394</a> }<a name="395" href="#395">395</a> }<a name="396" href="#396">396</a> <em class="comment">// Test 4th field is valid IP.</em><a name="397" href="#397">397</a> String ip = (String)values.get(values.size() - 4);<a name="398" href="#398">398</a> Matcher m = InetAddressUtil.IPV4_QUADS.matcher(ip);<a name="399" href="#399">399</a> <strong>if</strong> (ip == <span class="string">"-"</span> || m.matches()) {<a name="400" href="#400">400</a> List<String> <strong>new</strong>Values = <strong>new</strong> ArrayList<String>(requiredSize);<a name="401" href="#401">401</a> StringBuffer url = <strong>new</strong> StringBuffer();<a name="402" href="#402">402</a> <strong>for</strong> (<strong>int</strong> i = 0; i < (values.size() - 4); i++) {<a name="403" href="#403">403</a> <strong>if</strong> (i > 0) {<a name="404" href="#404">404</a> url.append(<span class="string">"%20"</span>);<a name="405" href="#405">405</a> }<a name="406" href="#406">406</a> url.append(values.get(i));<a name="407" href="#407">407</a> } <a name="408" href="#408">408</a> newValues.add(url.toString());<a name="409" href="#409">409</a> <strong>for</strong> (<strong>int</strong> i = values.size() - 4; i < values.size(); i++) {<a name="410" href="#410">410</a> newValues.add(values.get(i));<a name="411" href="#411">411</a> }<a name="412" href="#412">412</a> values = newValues;<a name="413" href="#413">413</a> }<a name="414" href="#414">414</a> <strong>return</strong> values;<a name="415" href="#415">415</a> }<a name="416" href="#416">416</a> <a name="417" href="#417">417</a> <strong>protected</strong> <strong>boolean</strong> isAlignedOnFirstRecord() {<a name="418" href="#418">418</a> <strong>return</strong> alignedOnFirstRecord;<a name="419" href="#419">419</a> }<a name="420" href="#420">420</a> <a name="421" href="#421">421</a> <strong>protected</strong> <strong>void</strong> setAlignedOnFirstRecord(<strong>boolean</strong> alignedOnFirstRecord) {<a name="422" href="#422">422</a> <strong>this</strong>.alignedOnFirstRecord = alignedOnFirstRecord;<a name="423" href="#423">423</a> }<a name="424" href="#424">424</a> <a name="425" href="#425">425</a> <em>/**<em>*</em></em><a name="426" href="#426">426</a> <em> * @return Returns the parseHttpHeaders.</em>
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -