xmlreader.html

解析RSS工具源码

<a name="140" href="#140">140</a> <em>     * If the URL is a HTTP Url or there is a 'content-type' header in the fetched</em>
<a name="141" href="#141">141</a> <em>     * data it uses the same logic used for an InputStream with content-type.</em>
<a name="142" href="#142">142</a> <em>     * &lt;p></em>
<a name="143" href="#143">143</a> <em>     * It does a lenient charset encoding detection, check the constructor with the lenient parameter</em>
<a name="144" href="#144">144</a> <em>     * for details.</em>
<a name="145" href="#145">145</a> <em>     * &lt;p></em>
<a name="146" href="#146">146</a> <em>     * @param url URL to create a Reader from.</em>
<a name="147" href="#147">147</a> <em>     * @throws IOException thrown if there is a problem reading the stream of the URL.</em>
<a name="148" href="#148">148</a> <em>     *</em>
<a name="149" href="#149">149</a> <em>     */</em>
<a name="150" href="#150">150</a>     <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(URL url) throws IOException {
<a name="151" href="#151">151</a>         <strong>this</strong>(url.openConnection());
<a name="152" href="#152">152</a>     }
<a name="153" href="#153">153</a> 
<a name="154" href="#154">154</a>     <em>/**<em>*</em></em>
<a name="155" href="#155">155</a> <em>     * Creates a Reader using the InputStream of a URLConnection.</em>
<a name="156" href="#156">156</a> <em>     * &lt;p></em>
<a name="157" href="#157">157</a> <em>     * If the URLConnection is not of type HttpURLConnection and there is not</em>
<a name="158" href="#158">158</a> <em>     * 'content-type' header in the fetched data it uses the same logic used for files.</em>
<a name="159" href="#159">159</a> <em>     * &lt;p></em>
<a name="160" href="#160">160</a> <em>     * If the URLConnection is a HTTP Url or there is a 'content-type' header in the fetched</em>
<a name="161" href="#161">161</a> <em>     * data it uses the same logic used for an InputStream with content-type.</em>
<a name="162" href="#162">162</a> <em>     * &lt;p></em>
<a name="163" href="#163">163</a> <em>     * It does a lenient charset encoding detection, check the constructor with the lenient parameter</em>
<a name="164" href="#164">164</a> <em>     * for details.</em>
<a name="165" href="#165">165</a> <em>     * &lt;p></em>
<a name="166" href="#166">166</a> <em>     * @param conn URLConnection to create a Reader from.</em>
<a name="167" href="#167">167</a> <em>     * @throws IOException thrown if there is a problem reading the stream of the URLConnection.</em>
<a name="168" href="#168">168</a> <em>     *</em>
<a name="169" href="#169">169</a> <em>     */</em>
<a name="170" href="#170">170</a>     <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(URLConnection conn) throws IOException {
<a name="171" href="#171">171</a>         <strong>boolean</strong> lenient = <strong>true</strong>;
<a name="172" href="#172">172</a>         <strong>if</strong> (conn instanceof HttpURLConnection) {
<a name="173" href="#173">173</a>             <strong>try</strong> {
<a name="174" href="#174">174</a>                 doHttpStream(conn.getInputStream(),conn.getContentType(),lenient);
<a name="175" href="#175">175</a>             }
<a name="176" href="#176">176</a>             <strong>catch</strong> (XmlReaderException ex) {
<a name="177" href="#177">177</a>                 doLenientDetection(conn.getContentType(),ex);
<a name="178" href="#178">178</a>             }
<a name="179" href="#179">179</a>         }
<a name="180" href="#180">180</a>         <strong>else</strong>
<a name="181" href="#181">181</a>         <strong>if</strong> (conn.getContentType()!=<strong>null</strong>) {
<a name="182" href="#182">182</a>             <strong>try</strong> {
<a name="183" href="#183">183</a>                 doHttpStream(conn.getInputStream(),conn.getContentType(),lenient);
<a name="184" href="#184">184</a>             }
<a name="185" href="#185">185</a>             <strong>catch</strong> (XmlReaderException ex) {
<a name="186" href="#186">186</a>                 doLenientDetection(conn.getContentType(),ex);
<a name="187" href="#187">187</a>             }
<a name="188" href="#188">188</a>         }
<a name="189" href="#189">189</a>         <strong>else</strong> {
<a name="190" href="#190">190</a>             <strong>try</strong> {
<a name="191" href="#191">191</a>                 doRawStream(conn.getInputStream(),lenient);
<a name="192" href="#192">192</a>             }
<a name="193" href="#193">193</a>             <strong>catch</strong> (XmlReaderException ex) {
<a name="194" href="#194">194</a>                 doLenientDetection(<strong>null</strong>,ex);
<a name="195" href="#195">195</a>             }
<a name="196" href="#196">196</a>         }
<a name="197" href="#197">197</a>     }
<a name="198" href="#198">198</a> 
<a name="199" href="#199">199</a>     <em>/**<em>*</em></em>
<a name="200" href="#200">200</a> <em>     * Creates a Reader using an InputStream an the associated content-type header.</em>
<a name="201" href="#201">201</a> <em>     * &lt;p></em>
<a name="202" href="#202">202</a> <em>     * First it checks if the stream has BOM. If there is not BOM checks the content-type encoding.</em>
<a name="203" href="#203">203</a> <em>     * If there is not content-type encoding checks the XML prolog encoding. If there is not XML</em>
<a name="204" href="#204">204</a> <em>     * prolog encoding uses the default encoding mandated by the content-type MIME type.</em>
<a name="205" href="#205">205</a> <em>     * &lt;p></em>
<a name="206" href="#206">206</a> <em>     * It does a lenient charset encoding detection, check the constructor with the lenient parameter</em>
<a name="207" href="#207">207</a> <em>     * for details.</em>
<a name="208" href="#208">208</a> <em>     * &lt;p></em>
<a name="209" href="#209">209</a> <em>     * @param is InputStream to create the reader from.</em>
<a name="210" href="#210">210</a> <em>     * @param httpContentType content-type header to use for the resolution of the charset encoding.</em>
<a name="211" href="#211">211</a> <em>     * @throws IOException thrown if there is a problem reading the file.</em>
<a name="212" href="#212">212</a> <em>     *</em>
<a name="213" href="#213">213</a> <em>     */</em>
<a name="214" href="#214">214</a>     <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(InputStream is,String httpContentType) throws IOException {
<a name="215" href="#215">215</a>         <strong>this</strong>(is,httpContentType,<strong>true</strong>);
<a name="216" href="#216">216</a>     }
<a name="217" href="#217">217</a> 
<a name="218" href="#218">218</a>     <em>/**<em>*</em></em>
<a name="219" href="#219">219</a> <em>     * Creates a Reader using an InputStream an the associated content-type header. This constructor is</em>
<a name="220" href="#220">220</a> <em>     * lenient regarding the encoding detection.</em>
<a name="221" href="#221">221</a> <em>     * &lt;p></em>
<a name="222" href="#222">222</a> <em>     * First it checks if the stream has BOM. If there is not BOM checks the content-type encoding.</em>
<a name="223" href="#223">223</a> <em>     * If there is not content-type encoding checks the XML prolog encoding. If there is not XML</em>
<a name="224" href="#224">224</a> <em>     * prolog encoding uses the default encoding mandated by the content-type MIME type.</em>
<a name="225" href="#225">225</a> <em>     * &lt;p></em>
<a name="226" href="#226">226</a> <em>     * If lenient detection is indicated and the detection above fails as per specifications it then attempts</em>
<a name="227" href="#227">227</a> <em>     * the following:</em>
<a name="228" href="#228">228</a> <em>     * &lt;p></em>
<a name="229" href="#229">229</a> <em>     * If the content type was 'text/html' it replaces it with 'text/xml' and tries the detection again.</em>
<a name="230" href="#230">230</a> <em>     * &lt;p></em>
<a name="231" href="#231">231</a> <em>     * Else if the XML prolog had a charset encoding that encoding is used.</em>
<a name="232" href="#232">232</a> <em>     * &lt;p></em>
<a name="233" href="#233">233</a> <em>     * Else if the content type had a charset encoding that encoding is used.</em>
<a name="234" href="#234">234</a> <em>     * &lt;p></em>
<a name="235" href="#235">235</a> <em>     * Else 'UTF-8' is used.</em>
<a name="236" href="#236">236</a> <em>     * &lt;p></em>
<a name="237" href="#237">237</a> <em>     * If lenient detection is indicated an XmlReaderException is never thrown.</em>
<a name="238" href="#238">238</a> <em>     * &lt;p></em>
<a name="239" href="#239">239</a> <em>     * @param is InputStream to create the reader from.</em>
<a name="240" href="#240">240</a> <em>     * @param httpContentType content-type header to use for the resolution of the charset encoding.</em>
<a name="241" href="#241">241</a> <em>     * @param lenient indicates if the charset encoding detection should be relaxed.</em>
<a name="242" href="#242">242</a> <em>     * @throws IOException thrown if there is a problem reading the file.</em>
<a name="243" href="#243">243</a> <em>     * @throws XmlReaderException thrown if the charset encoding could not be determined according to the specs.</em>
<a name="244" href="#244">244</a> <em>     *</em>
<a name="245" href="#245">245</a> <em>     */</em>
<a name="246" href="#246">246</a>     <strong>public</strong> <a href="../../../../com/sun/syndication/io/XmlReader.html">XmlReader</a>(InputStream is,String httpContentType,<strong>boolean</strong> lenient) throws IOException, XmlReaderException {
<a name="247" href="#247">247</a>         <strong>try</strong> {
<a name="248" href="#248">248</a>             doHttpStream(is,httpContentType,lenient);
<a name="249" href="#249">249</a>         }
<a name="250" href="#250">250</a>         <strong>catch</strong> (XmlReaderException ex) {
<a name="251" href="#251">251</a>             <strong>if</strong> (!lenient) {
<a name="252" href="#252">252</a>                 <strong>throw</strong> ex;
<a name="253" href="#253">253</a>             }
<a name="254" href="#254">254</a>             <strong>else</strong> {
<a name="255" href="#255">255</a>                 doLenientDetection(httpContentType,ex);
<a name="256" href="#256">256</a>             }
<a name="257" href="#257">257</a>         }
<a name="258" href="#258">258</a>     }
<a name="259" href="#259">259</a> 
<a name="260" href="#260">260</a>     <strong>private</strong> <strong>void</strong> doLenientDetection(String httpContentType,XmlReaderException ex) throws IOException {
<a name="261" href="#261">261</a>         <strong>if</strong> (httpContentType!=<strong>null</strong>) {
<a name="262" href="#262">262</a>             <strong>if</strong> (httpContentType.startsWith(<span class="string">"text/html"</span>)) {
<a name="263" href="#263">263</a>                 httpContentType = httpContentType.substring(<span class="string">"text/html"</span>.length());
<a name="264" href="#264">264</a>                 httpContentType = <span class="string">"text/xml"</span> + httpContentType;
<a name="265" href="#265">265</a>                 <strong>try</strong> {
<a name="266" href="#266">266</a>                     doHttpStream(ex.getInputStream(),httpContentType,<strong>true</strong>);
<a name="267" href="#267">267</a>                     ex = <strong>null</strong>;
<a name="268" href="#268">268</a>                 }
<a name="269" href="#269">269</a>                 <strong>catch</strong> (XmlReaderException ex2) {
<a name="270" href="#270">270</a>                     ex = ex2;
<a name="271" href="#271">271</a>                 }
<a name="272" href="#272">272</a>             }
<a name="273" href="#273">273</a>         }
<a name="274" href="#274">274</a>         <strong>if</strong> (ex!=<strong>null</strong>) {
<a name="275" href="#275">275</a>             String encoding = ex.getXmlEncoding();
<a name="276" href="#276">276</a>             <strong>if</strong> (encoding==<strong>null</strong>) {
<a name="277" href="#277">277</a>                 encoding = ex.getContentTypeEncoding();
<a name="278" href="#278">278</a>             }
<a name="279" href="#279">279</a>             <strong>if</strong> (encoding==<strong>null</strong>) {
<a name="280" href="#280">280</a>                 encoding = UTF_8;
<a name="281" href="#281">281</a>             }
<a name="282" href="#282">282</a>             prepareReader(ex.getInputStream(),encoding);
<a name="283" href="#283">283</a>         }
<a name="284" href="#284">284</a>     }
<a name="285" href="#285">285</a> 
<a name="286" href="#286">286</a>     <em>/**<em>*</em></em>
<a name="287" href="#287">287</a> <em>     * Returns the charset encoding of the XmlReader.</em>