arcreaderfactory.html

用JAVA编写的,在做实验的时候留下来的,本来想删的,但是传上来,大家分享吧

<a name="139" href="#139">139</a> <em>	 * will not bring the ARC local but will try to stream across the net making</em>
<a name="140" href="#140">140</a> <em>	 * an HTTP 1.1 Range request on remote http server (RFC1435 Section 14.35).</em>
<a name="141" href="#141">141</a> <em>	 * </em>
<a name="142" href="#142">142</a> <em>	 * @param arcUrl HTTP URL for an ARC (All ARCs considered remote).</em>
<a name="143" href="#143">143</a> <em>	 * @param offset Offset into ARC at which to start fetching.</em>
<a name="144" href="#144">144</a> <em>	 * @return An ARCReader aligned at offset.</em>
<a name="145" href="#145">145</a> <em>	 * @throws IOException</em>
<a name="146" href="#146">146</a> <em>	 */</em>
<a name="147" href="#147">147</a>     <strong>public</strong> <strong>static</strong> <a href="../../../../org/archive/io/arc/ARCReader.html">ARCReader</a> get(<strong>final</strong> URL arcUrl, <strong>final</strong> <strong>long</strong> offset)
<a name="148" href="#148">148</a>     throws IOException {
<a name="149" href="#149">149</a>         <strong>return</strong> (ARCReader)ARCReaderFactory.factory.getArchiveReader(arcUrl,
<a name="150" href="#150">150</a>             offset);
<a name="151" href="#151">151</a>     }
<a name="152" href="#152">152</a>     
<a name="153" href="#153">153</a>     <em>/**<em>*</em></em>
<a name="154" href="#154">154</a> <em>     * Get an ARCReader.</em>
<a name="155" href="#155">155</a> <em>     * Pulls the ARC local into whereever the System Property</em>
<a name="156" href="#156">156</a> <em>     * &lt;code>java.io.tmpdir&lt;/code> points. It then hands back an ARCReader that</em>
<a name="157" href="#157">157</a> <em>     * points at this local copy.  A close on this ARCReader instance will</em>
<a name="158" href="#158">158</a> <em>     * remove the local copy.</em>
<a name="159" href="#159">159</a> <em>     * @param arcUrl An URL that points at an ARC.</em>
<a name="160" href="#160">160</a> <em>     * @return An ARCReader.</em>
<a name="161" href="#161">161</a> <em>     * @throws IOException </em>
<a name="162" href="#162">162</a> <em>     */</em>
<a name="163" href="#163">163</a>     <strong>public</strong> <strong>static</strong> <a href="../../../../org/archive/io/arc/ARCReader.html">ARCReader</a> get(<strong>final</strong> URL arcUrl)
<a name="164" href="#164">164</a>     throws IOException {
<a name="165" href="#165">165</a>         <strong>return</strong> (ARCReader)ARCReaderFactory.factory.getArchiveReader(arcUrl);
<a name="166" href="#166">166</a>     }
<a name="167" href="#167">167</a>     
<a name="168" href="#168">168</a>     <em>/**<em>*</em></em>
<a name="169" href="#169">169</a> <em>     * @param arcFile File to test.</em>
<a name="170" href="#170">170</a> <em>     * @return True if &lt;code>arcFile&lt;/code> is compressed ARC.</em>
<a name="171" href="#171">171</a> <em>     * @throws IOException</em>
<a name="172" href="#172">172</a> <em>     */</em>
<a name="173" href="#173">173</a>     <strong>public</strong> <strong>boolean</strong> isCompressed(File arcFile) throws IOException {
<a name="174" href="#174">174</a>         <strong>return</strong> testCompressedARCFile(arcFile);
<a name="175" href="#175">175</a>     }
<a name="176" href="#176">176</a>     
<a name="177" href="#177">177</a>     <em>/**<em>*</em></em>
<a name="178" href="#178">178</a> <em>     * Check file is compressed and in ARC GZIP format.</em>
<a name="179" href="#179">179</a> <em>     *</em>
<a name="180" href="#180">180</a> <em>     * @param arcFile File to test if its Internet Archive ARC file</em>
<a name="181" href="#181">181</a> <em>     * GZIP compressed.</em>
<a name="182" href="#182">182</a> <em>     *</em>
<a name="183" href="#183">183</a> <em>     * @return True if this is an Internet Archive GZIP'd ARC file (It begins</em>
<a name="184" href="#184">184</a> <em>     * w/ the Internet Archive GZIP header and has the</em>
<a name="185" href="#185">185</a> <em>     * COMPRESSED_ARC_FILE_EXTENSION suffix).</em>
<a name="186" href="#186">186</a> <em>     *</em>
<a name="187" href="#187">187</a> <em>     * @exception IOException If file does not exist or is not unreadable.</em>
<a name="188" href="#188">188</a> <em>     */</em>
<a name="189" href="#189">189</a>     <strong>public</strong> <strong>static</strong> <strong>boolean</strong> testCompressedARCFile(File arcFile)
<a name="190" href="#190">190</a>     throws IOException {
<a name="191" href="#191">191</a>         <strong>return</strong> testCompressedARCFile(arcFile, false);
<a name="192" href="#192">192</a>     }
<a name="193" href="#193">193</a> 
<a name="194" href="#194">194</a>     <em>/**<em>*</em></em>
<a name="195" href="#195">195</a> <em>     * Check file is compressed and in ARC GZIP format.</em>
<a name="196" href="#196">196</a> <em>     *</em>
<a name="197" href="#197">197</a> <em>     * @param arcFile File to test if its Internet Archive ARC file</em>
<a name="198" href="#198">198</a> <em>     * GZIP compressed.</em>
<a name="199" href="#199">199</a> <em>     * @param skipSuffixCheck Set to true if we're not to test on the</em>
<a name="200" href="#200">200</a> <em>     * '.arc.gz' suffix.</em>
<a name="201" href="#201">201</a> <em>     *</em>
<a name="202" href="#202">202</a> <em>     * @return True if this is an Internet Archive GZIP'd ARC file (It begins</em>
<a name="203" href="#203">203</a> <em>     * w/ the Internet Archive GZIP header).</em>
<a name="204" href="#204">204</a> <em>     *</em>
<a name="205" href="#205">205</a> <em>     * @exception IOException If file does not exist or is not unreadable.</em>
<a name="206" href="#206">206</a> <em>     */</em>
<a name="207" href="#207">207</a>     <strong>public</strong> <strong>static</strong> <strong>boolean</strong> testCompressedARCFile(File arcFile,
<a name="208" href="#208">208</a>             <strong>boolean</strong> skipSuffixCheck)
<a name="209" href="#209">209</a>     throws IOException {
<a name="210" href="#210">210</a>         <strong>boolean</strong> compressedARCFile = false;
<a name="211" href="#211">211</a>         FileUtils.isReadable(arcFile);
<a name="212" href="#212">212</a>         <strong>if</strong>(!skipSuffixCheck &amp;&amp; !arcFile.getName().toLowerCase()
<a name="213" href="#213">213</a>                 .endsWith(COMPRESSED_ARC_FILE_EXTENSION)) {
<a name="214" href="#214">214</a>             <strong>return</strong> compressedARCFile;
<a name="215" href="#215">215</a>         }
<a name="216" href="#216">216</a>         
<a name="217" href="#217">217</a>         <strong>final</strong> InputStream is = <strong>new</strong> FileInputStream(arcFile);
<a name="218" href="#218">218</a>         <strong>try</strong> {
<a name="219" href="#219">219</a>             compressedARCFile = testCompressedARCStream(is);
<a name="220" href="#220">220</a>         } <strong>finally</strong> {
<a name="221" href="#221">221</a>             is.close();
<a name="222" href="#222">222</a>         }
<a name="223" href="#223">223</a>         <strong>return</strong> compressedARCFile;
<a name="224" href="#224">224</a>     }
<a name="225" href="#225">225</a>     
<a name="226" href="#226">226</a>     <strong>public</strong> <strong>static</strong> <strong>boolean</strong> isARCSuffix(<strong>final</strong> String arcName) {
<a name="227" href="#227">227</a>     	<strong>return</strong> (arcName == <strong>null</strong>)?
<a name="228" href="#228">228</a>     		false:
<a name="229" href="#229">229</a>     		(arcName.toLowerCase().endsWith(DOT_COMPRESSED_ARC_FILE_EXTENSION))?
<a name="230" href="#230">230</a>     		    <strong>true</strong>:
<a name="231" href="#231">231</a>     			(arcName.toLowerCase().endsWith(DOT_ARC_FILE_EXTENSION))?
<a name="232" href="#232">232</a>     			<strong>true</strong>: false;
<a name="233" href="#233">233</a>     }
<a name="234" href="#234">234</a>     
<a name="235" href="#235">235</a>     <em>/**<em>*</em></em>
<a name="236" href="#236">236</a> <em>     * Tests passed stream is gzip stream by reading in the HEAD.</em>
<a name="237" href="#237">237</a> <em>     * Does not reposition the stream.  That is left up to the caller.</em>
<a name="238" href="#238">238</a> <em>     * @param is An InputStream.</em>
<a name="239" href="#239">239</a> <em>     * @return True if compressed stream.</em>
<a name="240" href="#240">240</a> <em>     * @throws IOException</em>
<a name="241" href="#241">241</a> <em>     */</em>
<a name="242" href="#242">242</a>     <strong>public</strong> <strong>static</strong> <strong>boolean</strong> testCompressedARCStream(<strong>final</strong> InputStream is)
<a name="243" href="#243">243</a>             throws IOException {
<a name="244" href="#244">244</a>         <strong>boolean</strong> compressedARCFile = false;
<a name="245" href="#245">245</a>         <a href="../../../../org/archive/io/GzipHeader.html">GzipHeader</a> gh = <strong>null</strong>;
<a name="246" href="#246">246</a>         <strong>try</strong> {
<a name="247" href="#247">247</a>             gh = <strong>new</strong> <a href="../../../../org/archive/io/GzipHeader.html">GzipHeader</a>(is);
<a name="248" href="#248">248</a>         } <strong>catch</strong> (NoGzipMagicException e ) {
<a name="249" href="#249">249</a>             <strong>return</strong> compressedARCFile;
<a name="250" href="#250">250</a>         }
<a name="251" href="#251">251</a>         
<a name="252" href="#252">252</a>         byte[] fextra = gh.getFextra();
<a name="253" href="#253">253</a>         <em class="comment">// Now make sure following bytes are IA GZIP comment.</em>
<a name="254" href="#254">254</a>         <em class="comment">// First check length. ARC_GZIP_EXTRA_FIELD includes length</em>
<a name="255" href="#255">255</a>         <em class="comment">// so subtract two and start compare to ARC_GZIP_EXTRA_FIELD</em>
<a name="256" href="#256">256</a>         <em class="comment">// at +2.</em>
<a name="257" href="#257">257</a>         <strong>if</strong> (fextra != <strong>null</strong> &amp;&amp;
<a name="258" href="#258">258</a>                 ARC_GZIP_EXTRA_FIELD.length - 2 == fextra.length) {
<a name="259" href="#259">259</a>             compressedARCFile = <strong>true</strong>;
<a name="260" href="#260">260</a>             <strong>for</strong> (<strong>int</strong> i = 0; i &lt; fextra.length; i++) {
<a name="261" href="#261">261</a>                 <strong>if</strong> (fextra[i] != ARC_GZIP_EXTRA_FIELD[i + 2]) {
<a name="262" href="#262">262</a>                     compressedARCFile = false;
<a name="263" href="#263">263</a>                     <strong>break</strong>;
<a name="264" href="#264">264</a>                 }
<a name="265" href="#265">265</a>             }
<a name="266" href="#266">266</a>         }
<a name="267" href="#267">267</a>         <strong>return</strong> compressedARCFile;
<a name="268" href="#268">268</a>     }
<a name="269" href="#269">269</a> 
<a name="270" href="#270">270</a>     <em>/**<em>*</em></em>
<a name="271" href="#271">271</a> <em>     * Uncompressed arc file reader.</em>
<a name="272" href="#272">272</a> <em>     * @author stack</em>
<a name="273" href="#273">273</a> <em>     */</em>
<a name="274" href="#274">274</a>     <strong>private</strong> <strong>class</strong> UncompressedARCReader <strong>extends</strong> <a href="../../../../org/archive/io/arc/ARCReader.html">ARCReader</a> {
<a name="275" href="#275">275</a>         <em>/**<em>*</em></em>
<a name="276" href="#276">276</a> <em>         * Constructor.</em>
<a name="277" href="#277">277</a> <em>         * @param f Uncompressed arcfile to read.</em>
<a name="278" href="#278">278</a> <em>         * @throws IOException</em>
<a name="279" href="#279">279</a> <em>         */</em>
<a name="280" href="#280">280</a>         <strong>public</strong> UncompressedARCReader(<strong>final</strong> File f)
<a name="281" href="#281">281</a>         throws IOException {
<a name="282" href="#282">282</a>             <strong>this</strong>(f, 0);
<a name="283" href="#283">283</a>         }
<a name="284" href="#284">284</a> 
<a name="285" href="#285">285</a>         <em>/**<em>*</em></em>