📄 uurifactory.html
字号:
<a name="272" href="#272">272</a> <strong>public</strong> <strong>static</strong> <a href="../../../org/archive/net/UURI.html">UURI</a> getInstance(String uri, String charset)<a name="273" href="#273">273</a> throws URIException {<a name="274" href="#274">274</a> <strong>return</strong> UURIFactory.factory.create(uri, charset);<a name="275" href="#275">275</a> }<a name="276" href="#276">276</a> <a name="277" href="#277">277</a> <em>/**<em>*</em></em><a name="278" href="#278">278</a> <em> * @param base Base uri to use resolving passed relative uri.</em><a name="279" href="#279">279</a> <em> * @param relative URI as string.</em><a name="280" href="#280">280</a> <em> * @return An instance of UURI</em><a name="281" href="#281">281</a> <em> * @throws URIException</em><a name="282" href="#282">282</a> <em> */</em><a name="283" href="#283">283</a> <strong>public</strong> <strong>static</strong> <a href="../../../org/archive/net/UURI.html">UURI</a> getInstance(<a href="../../../org/archive/net/UURI.html">UURI</a> base, String relative)<a name="284" href="#284">284</a> throws URIException {<a name="285" href="#285">285</a> <strong>return</strong> UURIFactory.factory.create(base, relative);<a name="286" href="#286">286</a> }<a name="287" href="#287">287</a> <a name="288" href="#288">288</a> <em>/**<em>*</em></em><a name="289" href="#289">289</a> <em> * Test of whether passed String has an allowed URI scheme.</em><a name="290" href="#290">290</a> <em> * First tests if likely scheme suffix. If so, we then test if its one of</em><a name="291" href="#291">291</a> <em> * the supported schemes.</em><a name="292" href="#292">292</a> <em> * @param possibleUrl URL string to examine.</em><a name="293" href="#293">293</a> <em> * @return True if passed string looks like it could be an URL.</em><a name="294" href="#294">294</a> <em> */</em><a name="295" href="#295">295</a> <strong>public</strong> <strong>static</strong> <strong>boolean</strong> hasSupportedScheme(String possibleUrl) {<a name="296" href="#296">296</a> <strong>boolean</strong> hasScheme = UURI.hasScheme(possibleUrl);<a name="297" href="#297">297</a> <strong>if</strong> (!hasScheme || UURIFactory.factory.schemes == <strong>null</strong>) {<a name="298" href="#298">298</a> <strong>return</strong> hasScheme;<a name="299" href="#299">299</a> }<a name="300" href="#300">300</a> String tmpStr = possibleUrl.substring(0, possibleUrl.indexOf(':'));<a name="301" href="#301">301</a> <strong>return</strong> Arrays.binarySearch(UURIFactory.factory.schemes, tmpStr) >= 0;<a name="302" href="#302">302</a> }<a name="303" href="#303">303</a> <a name="304" href="#304">304</a> <em>/**<em>*</em></em><a name="305" href="#305">305</a> <em> * @param uri URI as string.</em><a name="306" href="#306">306</a> <em> * @return Instance of UURI.</em><a name="307" href="#307">307</a> <em> * @throws URIException</em><a name="308" href="#308">308</a> <em> */</em><a name="309" href="#309">309</a> <strong>private</strong> <a href="../../../org/archive/net/UURI.html">UURI</a> create(String uri) throws URIException {<a name="310" href="#310">310</a> <strong>return</strong> create(uri, UURI.getDefaultProtocolCharset());<a name="311" href="#311">311</a> }<a name="312" href="#312">312</a> <a name="313" href="#313">313</a> <em>/**<em>*</em></em><a name="314" href="#314">314</a> <em> * @param uri URI as string.</em><a name="315" href="#315">315</a> <em> * @param charset Original encoding of the string.</em><a name="316" href="#316">316</a> <em> * @return Instance of UURI.</em><a name="317" href="#317">317</a> <em> * @throws URIException</em><a name="318" href="#318">318</a> <em> */</em><a name="319" href="#319">319</a> <strong>private</strong> <a href="../../../org/archive/net/UURI.html">UURI</a> create(String uri, String charset) throws URIException {<a name="320" href="#320">320</a> <a href="../../../org/archive/net/UURI.html">UURI</a> uuri = <strong>new</strong> UURI(fixup(uri, <strong>null</strong>, charset), <strong>true</strong>, charset);<a name="321" href="#321">321</a> <strong>if</strong> (logger.isLoggable(Level.FINE)) {<a name="322" href="#322">322</a> logger.fine(<span class="string">"URI "</span> + uri +<a name="323" href="#323">323</a> <span class="string">" PRODUCT "</span> + uuri.toString() +<a name="324" href="#324">324</a> <span class="string">" CHARSET "</span> + charset);<a name="325" href="#325">325</a> }<a name="326" href="#326">326</a> <strong>return</strong> validityCheck(uuri);<a name="327" href="#327">327</a> }<a name="328" href="#328">328</a> <a name="329" href="#329">329</a> <em>/**<em>*</em></em><a name="330" href="#330">330</a> <em> * @param base UURI to use as a base resolving <code>relative</code>.</em><a name="331" href="#331">331</a> <em> * @param relative Relative URI.</em><a name="332" href="#332">332</a> <em> * @return Instance of UURI.</em><a name="333" href="#333">333</a> <em> * @throws URIException</em><a name="334" href="#334">334</a> <em> */</em><a name="335" href="#335">335</a> <strong>private</strong> <a href="../../../org/archive/net/UURI.html">UURI</a> create(<a href="../../../org/archive/net/UURI.html">UURI</a> base, String relative) throws URIException {<a name="336" href="#336">336</a> <a href="../../../org/archive/net/UURI.html">UURI</a> uuri = <strong>new</strong> <a href="../../../org/archive/net/UURI.html">UURI</a>(base, <strong>new</strong> <a href="../../../org/archive/net/UURI.html">UURI</a>(fixup(relative, base, base.getProtocolCharset()),<a name="337" href="#337">337</a> <strong>true</strong>, base.getProtocolCharset()));<a name="338" href="#338">338</a> <strong>if</strong> (logger.isLoggable(Level.FINE)) {<a name="339" href="#339">339</a> logger.fine(<span class="string">" URI "</span> + relative +<a name="340" href="#340">340</a> <span class="string">" PRODUCT "</span> + uuri.toString() +<a name="341" href="#341">341</a> <span class="string">" CHARSET "</span> + base.getProtocolCharset() +<a name="342" href="#342">342</a> <span class="string">" BASE "</span> + base);<a name="343" href="#343">343</a> }<a name="344" href="#344">344</a> <strong>return</strong> validityCheck(uuri);<a name="345" href="#345">345</a> }<a name="346" href="#346">346</a> <a name="347" href="#347">347</a> <em>/**<em>*</em></em><a name="348" href="#348">348</a> <em> * Check the generated UURI.</em><a name="349" href="#349">349</a> <em> * </em><a name="350" href="#350">350</a> <em> * At the least look at length of uuri string. We were seeing case</em><a name="351" href="#351">351</a> <em> * where before escaping, string was &lt; MAX_URL_LENGTH but after was</em><a name="352" href="#352">352</a> <em> * &gt;. Letting out a too-big message was causing us troubles later</em><a name="353" href="#353">353</a> <em> * down the processing chain.</em><a name="354" href="#354">354</a> <em> * @param uuri Created uuri to check.</em><a name="355" href="#355">355</a> <em> * @return The passed <code>uuri</code> so can easily inline this check.</em><a name="356" href="#356">356</a> <em> * @throws URIException</em><a name="357" href="#357">357</a> <em> */</em><a name="358" href="#358">358</a> <strong>protected</strong> <a href="../../../org/archive/net/UURI.html">UURI</a> validityCheck(<a href="../../../org/archive/net/UURI.html">UURI</a> uuri) throws URIException {<a name="359" href="#359">359</a> <strong>if</strong> (uuri.getRawURI().length > UURI.MAX_URL_LENGTH) {<a name="360" href="#360">360</a> <strong>throw</strong> <strong>new</strong> URIException(<span class="string">"Created (escaped) uuri > "</span> +<a name="361" href="#361">361</a> UURI.MAX_URL_LENGTH +<span class="string">": "</span>+uuri.toString());<a name="362" href="#362">362</a> }<a name="363" href="#363">363</a> <strong>return</strong> uuri;<a name="364" href="#364">364</a> }<a name="365" href="#365">365</a> <a name="366" href="#366">366</a> <em>/**<em>*</em></em><a name="367" href="#367">367</a> <em> * Do heritrix fix-up on passed uri string.</em><a name="368" href="#368">368</a> <em> *</em><a name="369" href="#369">369</a> <em> * Does heritrix escaping; usually escaping done to make our behavior align</em><a name="370" href="#370">370</a> <em> * with IEs. This method codifies our experience pulling URIs from the</em><a name="371" href="#371">371</a> <em> * wilds. Its does all the escaping we want; its output can always be</em><a name="372" href="#372">372</a> <em> * assumed to be 'escaped' (though perhaps to a laxer standard than the </em><a name="373" href="#373">373</a> <em> * vanilla HttpClient URI class or official specs might suggest). </em><a name="374" href="#374">374</a> <em> *</em><a name="375" href="#375">375</a> <em> * @param uri URI as string.</em><a name="376" href="#376">376</a> <em> * @param base May be null.</em><a name="377" href="#377">377</a> <em> * @param e True if the uri is already escaped.</em><a name="378" href="#378">378</a> <em> * @return A fixed up URI string.</em><a name="379" href="#379">379</a> <em> * @throws URIException</em><a name="380" href="#380">380</a> <em> */</em><a name="381" href="#381">381</a> <strong>private</strong> String fixup(String uri, <strong>final</strong> URI base, <strong>final</strong> String charset)<a name="382" href="#382">382</a> throws URIException {<a name="383" href="#383">383</a> <strong>if</strong> (uri == <strong>null</strong>) {<a name="384" href="#384">384</a> <strong>throw</strong> <strong>new</strong> NullPointerException();<a name="385" href="#385">385</a> } <strong>else</strong> <strong>if</strong> (uri.length() == 0 && base == <strong>null</strong>) {<a name="386" href="#386">386</a> <strong>throw</strong> <strong>new</strong> URIException(<span class="string">"URI length is zero (and not relative)."</span>);<a name="387" href="#387">387</a> }<a name="388" href="#388">388</a> <a name="389" href="#389">389</a> <strong>if</strong> (uri.length() > UURI.MAX_URL_LENGTH) {<a name="390" href="#390">390</a> <em class="comment">// We check length here and again later after all convertions.</em><a name="391" href="#391">391</a> <strong>throw</strong> <strong>new</strong> URIException(<span class="string">"URI length > "</span> + UURI.MAX_URL_LENGTH +<a name="392" href="#392">392</a> <span class="string">": "</span> + uri);<a name="393" href="#393">393</a> }<a name="394" href="#394">394</a> <a name="395" href="#395">395</a> <em class="comment">// Replace nbsp with normal spaces (so that they get stripped if at</em><a name="396" href="#396">396</a> <em class="comment">// ends, or encoded if in middle)</em><a name="397" href="#397">397</a> <strong>if</strong> (uri.indexOf(NBSP) >= 0) {<a name="398" href="#398">398</a> uri = TextUtils.replaceAll(NBSP, uri, SPACE);<a name="399" href="#399">399</a> }<a name="400" href="#400">400</a> <a name="401" href="#401">401</a> <em class="comment">// Get rid of any trailing spaces or new-lines. </em><a name="402" href="#402">402</a> uri = uri.trim();<a name="403" href="#403">403</a> <a name="404" href="#404">404</a> <em class="comment">// IE actually converts backslashes to slashes rather than to %5C.</em><a name="405" href="#405">405</a> <em class="comment">// Since URIs that have backslashes usually work only with IE, we will</em><a name="406" href="#406">406</a> <em class="comment">// convert backslashes to slashes as well.</em><a name="407" href="#407">407</a> <em class="comment">// TODO: Maybe we can first convert backslashes by specs and than by IE</em><a name="408" href="#408">408</a> <em class="comment">// so that we fetch both versions.</em><a name="409" href="#409">409</a> <strong>if</strong> (uri.indexOf(BACKSLASH) >= 0) {<a name="410" href="#410">410</a> uri = TextUtils.replaceAll(BACKSLASH_PATTERN, uri, SLASH);<a name="411" href="#411">411</a> }
⌨️ 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 + -