xmlreader.html

来自「rsslibj-1_0RC2,RSS阅读」· HTML 代码 · 共 679 行 · 第 1/4 页

<a name="162" href="#162">162</a>             }
<a name="163" href="#163">163</a>         }
<a name="164" href="#164">164</a>     }
<a name="165" href="#165">165</a> 
<a name="166" href="#166">166</a>     <em>/**<em>*</em></em>
<a name="167" href="#167">167</a> <em>     * Creates a Reader using the InputStream of a URL.</em>
<a name="168" href="#168">168</a> <em>     * &lt;p></em>
<a name="169" href="#169">169</a> <em>     * If the URL is not of type HTTP and there is not 'content-type' header in the fetched</em>
<a name="170" href="#170">170</a> <em>     * data it uses the same logic used for Files.</em>
<a name="171" href="#171">171</a> <em>     * &lt;p></em>
<a name="172" href="#172">172</a> <em>     * If the URL is a HTTP Url or there is a 'content-type' header in the fetched</em>
<a name="173" href="#173">173</a> <em>     * data it uses the same logic used for an InputStream with content-type.</em>
<a name="174" href="#174">174</a> <em>     * &lt;p></em>
<a name="175" href="#175">175</a> <em>     * It does a lenient charset encoding detection, check the constructor with the lenient parameter</em>
<a name="176" href="#176">176</a> <em>     * for details.</em>
<a name="177" href="#177">177</a> <em>     * &lt;p></em>
<a name="178" href="#178">178</a> <em>     * @param url URL to create a Reader from.</em>
<a name="179" href="#179">179</a> <em>     * @throws IOException thrown if there is a problem reading the stream of the URL.</em>
<a name="180" href="#180">180</a> <em>     *</em>
<a name="181" href="#181">181</a> <em>     */</em>
<a name="182" href="#182">182</a>     <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(URL url) throws IOException {
<a name="183" href="#183">183</a>         <strong>this</strong>(url.openConnection());
<a name="184" href="#184">184</a>     }
<a name="185" href="#185">185</a> 
<a name="186" href="#186">186</a>     <em>/**<em>*</em></em>
<a name="187" href="#187">187</a> <em>     * Creates a Reader using the InputStream of a URLConnection.</em>
<a name="188" href="#188">188</a> <em>     * &lt;p></em>
<a name="189" href="#189">189</a> <em>     * If the URLConnection is not of type HttpURLConnection and there is not</em>
<a name="190" href="#190">190</a> <em>     * 'content-type' header in the fetched data it uses the same logic used for files.</em>
<a name="191" href="#191">191</a> <em>     * &lt;p></em>
<a name="192" href="#192">192</a> <em>     * If the URLConnection is a HTTP Url or there is a 'content-type' header in the fetched</em>
<a name="193" href="#193">193</a> <em>     * data it uses the same logic used for an InputStream with content-type.</em>
<a name="194" href="#194">194</a> <em>     * &lt;p></em>
<a name="195" href="#195">195</a> <em>     * It does a lenient charset encoding detection, check the constructor with the lenient parameter</em>
<a name="196" href="#196">196</a> <em>     * for details.</em>
<a name="197" href="#197">197</a> <em>     * &lt;p></em>
<a name="198" href="#198">198</a> <em>     * @param conn URLConnection to create a Reader from.</em>
<a name="199" href="#199">199</a> <em>     * @throws IOException thrown if there is a problem reading the stream of the URLConnection.</em>
<a name="200" href="#200">200</a> <em>     *</em>
<a name="201" href="#201">201</a> <em>     */</em>
<a name="202" href="#202">202</a>     <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(URLConnection conn) throws IOException {
<a name="203" href="#203">203</a>         _defaultEncoding = _staticDefaultEncoding;
<a name="204" href="#204">204</a>         <strong>boolean</strong> lenient = <strong>true</strong>;
<a name="205" href="#205">205</a>         <strong>if</strong> (conn instanceof HttpURLConnection) {
<a name="206" href="#206">206</a>             <strong>try</strong> {
<a name="207" href="#207">207</a>                 doHttpStream(conn.getInputStream(),conn.getContentType(),lenient);
<a name="208" href="#208">208</a>             }
<a name="209" href="#209">209</a>             <strong>catch</strong> (XmlReaderException ex) {
<a name="210" href="#210">210</a>                 doLenientDetection(conn.getContentType(),ex);
<a name="211" href="#211">211</a>             }
<a name="212" href="#212">212</a>         }
<a name="213" href="#213">213</a>         <strong>else</strong>
<a name="214" href="#214">214</a>         <strong>if</strong> (conn.getContentType()!=<strong>null</strong>) {
<a name="215" href="#215">215</a>             <strong>try</strong> {
<a name="216" href="#216">216</a>                 doHttpStream(conn.getInputStream(),conn.getContentType(),lenient);
<a name="217" href="#217">217</a>             }
<a name="218" href="#218">218</a>             <strong>catch</strong> (XmlReaderException ex) {
<a name="219" href="#219">219</a>                 doLenientDetection(conn.getContentType(),ex);
<a name="220" href="#220">220</a>             }
<a name="221" href="#221">221</a>         }
<a name="222" href="#222">222</a>         <strong>else</strong> {
<a name="223" href="#223">223</a>             <strong>try</strong> {
<a name="224" href="#224">224</a>                 doRawStream(conn.getInputStream(),lenient);
<a name="225" href="#225">225</a>             }
<a name="226" href="#226">226</a>             <strong>catch</strong> (XmlReaderException ex) {
<a name="227" href="#227">227</a>                 doLenientDetection(<strong>null</strong>,ex);
<a name="228" href="#228">228</a>             }
<a name="229" href="#229">229</a>         }
<a name="230" href="#230">230</a>     }
<a name="231" href="#231">231</a> 
<a name="232" href="#232">232</a>     <em>/**<em>*</em></em>
<a name="233" href="#233">233</a> <em>     * Creates a Reader using an InputStream an the associated content-type header.</em>
<a name="234" href="#234">234</a> <em>     * &lt;p></em>
<a name="235" href="#235">235</a> <em>     * First it checks if the stream has BOM. If there is not BOM checks the content-type encoding.</em>
<a name="236" href="#236">236</a> <em>     * If there is not content-type encoding checks the XML prolog encoding. If there is not XML</em>
<a name="237" href="#237">237</a> <em>     * prolog encoding uses the default encoding mandated by the content-type MIME type.</em>
<a name="238" href="#238">238</a> <em>     * &lt;p></em>
<a name="239" href="#239">239</a> <em>     * It does a lenient charset encoding detection, check the constructor with the lenient parameter</em>
<a name="240" href="#240">240</a> <em>     * for details.</em>
<a name="241" href="#241">241</a> <em>     * &lt;p></em>
<a name="242" href="#242">242</a> <em>     * @param is InputStream to create the reader from.</em>
<a name="243" href="#243">243</a> <em>     * @param httpContentType content-type header to use for the resolution of the charset encoding.</em>
<a name="244" href="#244">244</a> <em>     * @throws IOException thrown if there is a problem reading the file.</em>
<a name="245" href="#245">245</a> <em>     *</em>
<a name="246" href="#246">246</a> <em>     */</em>
<a name="247" href="#247">247</a>     <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(InputStream is,String httpContentType) throws IOException {
<a name="248" href="#248">248</a>         <strong>this</strong>(is,httpContentType,<strong>true</strong>);
<a name="249" href="#249">249</a>     }
<a name="250" href="#250">250</a> 
<a name="251" href="#251">251</a>     <em>/**<em>*</em></em>
<a name="252" href="#252">252</a> <em>     * Creates a Reader using an InputStream an the associated content-type header. This constructor is</em>
<a name="253" href="#253">253</a> <em>     * lenient regarding the encoding detection.</em>
<a name="254" href="#254">254</a> <em>     * &lt;p></em>
<a name="255" href="#255">255</a> <em>     * First it checks if the stream has BOM. If there is not BOM checks the content-type encoding.</em>
<a name="256" href="#256">256</a> <em>     * If there is not content-type encoding checks the XML prolog encoding. If there is not XML</em>
<a name="257" href="#257">257</a> <em>     * prolog encoding uses the default encoding mandated by the content-type MIME type.</em>
<a name="258" href="#258">258</a> <em>     * &lt;p></em>
<a name="259" href="#259">259</a> <em>     * If lenient detection is indicated and the detection above fails as per specifications it then attempts</em>
<a name="260" href="#260">260</a> <em>     * the following:</em>
<a name="261" href="#261">261</a> <em>     * &lt;p></em>
<a name="262" href="#262">262</a> <em>     * If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.</em>
<a name="263" href="#263">263</a> <em>     * &lt;p></em>
<a name="264" href="#264">264</a> <em>     * Else if the XML prolog had a charset encoding that encoding is used.</em>
<a name="265" href="#265">265</a> <em>     * &lt;p></em>
<a name="266" href="#266">266</a> <em>     * Else if the content type had a charset encoding that encoding is used.</em>
<a name="267" href="#267">267</a> <em>     * &lt;p></em>
<a name="268" href="#268">268</a> <em>     * Else 'UTF-8' is used.</em>
<a name="269" href="#269">269</a> <em>     * &lt;p></em>
<a name="270" href="#270">270</a> <em>     * If lenient detection is indicated an XmlReaderException is never thrown.</em>
<a name="271" href="#271">271</a> <em>     * &lt;p></em>
<a name="272" href="#272">272</a> <em>     * @param is InputStream to create the reader from.</em>
<a name="273" href="#273">273</a> <em>     * @param httpContentType content-type header to use for the resolution of the charset encoding.</em>
<a name="274" href="#274">274</a> <em>     * @param lenient indicates if the charset encoding detection should be relaxed.</em>
<a name="275" href="#275">275</a> <em>     * @throws IOException thrown if there is a problem reading the file.</em>
<a name="276" href="#276">276</a> <em>     * @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.</em>
<a name="277" href="#277">277</a> <em>     *</em>
<a name="278" href="#278">278</a> <em>     */</em>
<a name="279" href="#279">279</a>     <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(InputStream is,String httpContentType,<strong>boolean</strong> lenient, String defaultEncoding)
<a name="280" href="#280">280</a>         throws IOException, <a href="../../../../com/sun/syndication/io/XmlReaderException.html">XmlReaderException</a> {
<a name="281" href="#281">281</a>         _defaultEncoding = (defaultEncoding == <strong>null</strong>) ? _staticDefaultEncoding : defaultEncoding;
<a name="282" href="#282">282</a>         <strong>try</strong> {
<a name="283" href="#283">283</a>             doHttpStream(is,httpContentType,lenient);
<a name="284" href="#284">284</a>         }
<a name="285" href="#285">285</a>         <strong>catch</strong> (XmlReaderException ex) {
<a name="286" href="#286">286</a>             <strong>if</strong> (!lenient) {
<a name="287" href="#287">287</a>                 <strong>throw</strong> ex;
<a name="288" href="#288">288</a>             }
<a name="289" href="#289">289</a>             <strong>else</strong> {
<a name="290" href="#290">290</a>                 doLenientDetection(httpContentType,ex);
<a name="291" href="#291">291</a>             }
<a name="292" href="#292">292</a>         }
<a name="293" href="#293">293</a>     }
<a name="294" href="#294">294</a> 
<a name="295" href="#295">295</a>     <em>/**<em>*</em></em>
<a name="296" href="#296">296</a> <em>     * Creates a Reader using an InputStream an the associated content-type header. This constructor is</em>
<a name="297" href="#297">297</a> <em>     * lenient regarding the encoding detection.</em>
<a name="298" href="#298">298</a> <em>     * &lt;p></em>
<a name="299" href="#299">299</a> <em>     * First it checks if the stream has BOM. If there is not BOM checks the content-type encoding.</em>
<a name="300" href="#300">300</a> <em>     * If there is not content-type encoding checks the XML prolog encoding. If there is not XML</em>
<a name="301" href="#301">301</a> <em>     * prolog encoding uses the default encoding mandated by the content-type MIME type.</em>
<a name="302" href="#302">302</a> <em>     * &lt;p></em>
<a name="303" href="#303">303</a> <em>     * If lenient detection is indicated and the detection above fails as per specifications it then attempts</em>
<a name="304" href="#304">304</a> <em>     * the following:</em>
<a name="305" href="#305">305</a> <em>     * &lt;p></em>
<a name="306" href="#306">306</a> <em>     * If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.</em>
<a name="307" href="#307">307</a> <em>     * &lt;p></em>
<a name="308" href="#308">308</a> <em>     * Else if the XML prolog had a charset encoding that encoding is used.</em>
<a name="309" href="#309">309</a> <em>     * &lt;p></em>
<a name="310" href="#310">310</a> <em>     * Else if the content type had a charset encoding that encoding is used.</em>
<a name="311" href="#311">311</a> <em>     * &lt;p></em>
<a name="312" href="#312">312</a> <em>     * Else 'UTF-8' is used.</em>
<a name="313" href="#313">313</a> <em>     * &lt;p></em>
<a name="314" href="#314">314</a> <em>     * If lenient detection is indicated an XmlReaderException is never thrown.</em>
<a name="315" href="#315">315</a> <em>     * &lt;p></em>
<a name="316" href="#316">316</a> <em>     * @param is InputStream to create the reader from.</em>
<a name="317" href="#317">317</a> <em>     * @param httpContentType content-type header to use for the resolution of the charset encoding.</em>
<a name="318" href="#318">318</a> <em>     * @param lenient indicates if the charset encoding detection should be relaxed.</em>
<a name="319" href="#319">319</a> <em>     * @throws IOException thrown if there is a problem reading the file.</em>
<a name="320" href="#320">320</a> <em>     * @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.</em>
<a name="321" href="#321">321</a> <em>     *</em>
<a name="322" href="#322">322</a> <em>     */</em>
<a name="323" href="#323">323</a>     <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(InputStream is, String httpContentType, <strong>boolean</strong> lenient)
<a name="324" href="#324">324</a>         throws IOException, <a href="../../../../com/sun/syndication/io/XmlReaderException.html">XmlReaderException</a> {
<a name="325" href="#325">325</a>         <strong>this</strong>(is, httpContentType, lenient, <strong>null</strong>);
<a name="326" href="#326">326</a>     }
<a name="327" href="#327">327</a> 
<a name="328" href="#328">328</a>     <strong>private</strong> <strong>void</strong> doLenientDetection(String httpContentType,XmlReaderException ex) throws IOException {
<a name="329" href="#329">329</a>         <strong>if</strong> (httpContentType!=<strong>null</strong>) {
<a name="330" href="#330">330</a>             <strong>if</strong> (httpContentType.startsWith(<span class="string">"text/html"</span>)) {
<a name="331" href="#331">331</a>                 httpContentType = httpContentType.substring(<span class="string">"text/html"</span>.length());