You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ma...@apache.org on 2008/01/07 04:06:42 UTC
svn commit: r609491 [8/11] - in /incubator/tika/site: ./ apidocs/
apidocs/org/apache/tika/config/ apidocs/org/apache/tika/config/class-use/
apidocs/org/apache/tika/exception/
apidocs/org/apache/tika/exception/class-use/
apidocs/org/apache/tika/metadata...
Modified: incubator/tika/site/xref/org/apache/tika/mime/MimeTypes.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/mime/MimeTypes.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/mime/MimeTypes.html (original)
+++ incubator/tika/site/xref/org/apache/tika/mime/MimeTypes.html Sun Jan 6 19:06:26 2008
@@ -130,240 +130,244 @@
<a name="120" href="#120">120</a> <em class="jxr_javadoccomment"> * @return matching MIME type, or <code>null</code> if no match is found</em>
<a name="121" href="#121">121</a> <em class="jxr_javadoccomment"> */</em>
<a name="122" href="#122">122</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> getMimeType(byte[] data) {
-<a name="123" href="#123">123</a> assert data != <strong class="jxr_keyword">null</strong>;
-<a name="124" href="#124">124</a>
-<a name="125" href="#125">125</a> <em class="jxr_comment">// First, check for XML descriptions (level by level)</em>
-<a name="126" href="#126">126</a> <strong class="jxr_keyword">for</strong> (MimeType type : xmls) {
-<a name="127" href="#127">127</a> <strong class="jxr_keyword">if</strong> (type.matchesXML(data)) {
-<a name="128" href="#128">128</a> <strong class="jxr_keyword">return</strong> type;
-<a name="129" href="#129">129</a> }
-<a name="130" href="#130">130</a> }
-<a name="131" href="#131">131</a>
-<a name="132" href="#132">132</a> <em class="jxr_comment">// Then, check for magic bytes</em>
-<a name="133" href="#133">133</a> <strong class="jxr_keyword">for</strong> (Magic magic : magics) {
-<a name="134" href="#134">134</a> <strong class="jxr_keyword">if</strong> (magic.eval(data)) {
-<a name="135" href="#135">135</a> <strong class="jxr_keyword">return</strong> magic.getType();
-<a name="136" href="#136">136</a> }
-<a name="137" href="#137">137</a> }
-<a name="138" href="#138">138</a>
-<a name="139" href="#139">139</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">null</strong>;
-<a name="140" href="#140">140</a> }
-<a name="141" href="#141">141</a>
-<a name="142" href="#142">142</a> <em class="jxr_javadoccomment">/**</em>
-<a name="143" href="#143">143</a> <em class="jxr_javadoccomment"> * Returns the MIME type that best matches the first few bytes of the</em>
-<a name="144" href="#144">144</a> <em class="jxr_javadoccomment"> * given document stream.</em>
-<a name="145" href="#145">145</a> <em class="jxr_javadoccomment"> *</em>
-<a name="146" href="#146">146</a> <em class="jxr_javadoccomment"> * @see #getMimeType(byte[])</em>
-<a name="147" href="#147">147</a> <em class="jxr_javadoccomment"> * @param stream document stream</em>
-<a name="148" href="#148">148</a> <em class="jxr_javadoccomment"> * @return matching MIME type, or <code>null</code> if no match is found</em>
-<a name="149" href="#149">149</a> <em class="jxr_javadoccomment"> * @throws IOException if the stream can be read</em>
-<a name="150" href="#150">150</a> <em class="jxr_javadoccomment"> */</em>
-<a name="151" href="#151">151</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> getMimeType(InputStream stream) <strong class="jxr_keyword">throws</strong> IOException {
-<a name="152" href="#152">152</a> <strong class="jxr_keyword">return</strong> getMimeType(readMagicHeader(stream));
-<a name="153" href="#153">153</a> }
-<a name="154" href="#154">154</a>
-<a name="155" href="#155">155</a> <em class="jxr_javadoccomment">/**</em>
-<a name="156" href="#156">156</a> <em class="jxr_javadoccomment"> * Reads the first {@link #getMinLength()} bytes from the given stream.</em>
-<a name="157" href="#157">157</a> <em class="jxr_javadoccomment"> * If the stream is shorter, then the entire content of the stream is</em>
-<a name="158" href="#158">158</a> <em class="jxr_javadoccomment"> * returned.</em>
-<a name="159" href="#159">159</a> <em class="jxr_javadoccomment"> * <p></em>
-<a name="160" href="#160">160</a> <em class="jxr_javadoccomment"> * The given stream is never {@link InputStream#close() closed},</em>
-<a name="161" href="#161">161</a> <em class="jxr_javadoccomment"> * {@link InputStream#mark(int) marked}, or</em>
-<a name="162" href="#162">162</a> <em class="jxr_javadoccomment"> * {@link InputStream#reset() reset} by this method.</em>
-<a name="163" href="#163">163</a> <em class="jxr_javadoccomment"> *</em>
-<a name="164" href="#164">164</a> <em class="jxr_javadoccomment"> * @param stream stream to be read</em>
-<a name="165" href="#165">165</a> <em class="jxr_javadoccomment"> * @return first {@link #getMinLength()} (or fewer) bytes of the stream</em>
-<a name="166" href="#166">166</a> <em class="jxr_javadoccomment"> * @throws IOException if the stream can not be read</em>
-<a name="167" href="#167">167</a> <em class="jxr_javadoccomment"> */</em>
-<a name="168" href="#168">168</a> <strong class="jxr_keyword">private</strong> byte[] readMagicHeader(InputStream stream) <strong class="jxr_keyword">throws</strong> IOException {
-<a name="169" href="#169">169</a> assert stream != <strong class="jxr_keyword">null</strong>;
-<a name="170" href="#170">170</a>
-<a name="171" href="#171">171</a> byte[] bytes = <strong class="jxr_keyword">new</strong> byte[getMinLength()];
-<a name="172" href="#172">172</a> <strong class="jxr_keyword">int</strong> totalRead = 0;
-<a name="173" href="#173">173</a>
-<a name="174" href="#174">174</a> <strong class="jxr_keyword">int</strong> lastRead = stream.read(bytes);
-<a name="175" href="#175">175</a> <strong class="jxr_keyword">while</strong> (lastRead != -1) {
-<a name="176" href="#176">176</a> totalRead += lastRead;
-<a name="177" href="#177">177</a> <strong class="jxr_keyword">if</strong> (totalRead == bytes.length) {
-<a name="178" href="#178">178</a> <strong class="jxr_keyword">return</strong> bytes;
-<a name="179" href="#179">179</a> }
-<a name="180" href="#180">180</a> lastRead = stream.read(bytes, totalRead, bytes.length - totalRead);
-<a name="181" href="#181">181</a> }
-<a name="182" href="#182">182</a>
-<a name="183" href="#183">183</a> byte[] shorter = <strong class="jxr_keyword">new</strong> byte[totalRead];
-<a name="184" href="#184">184</a> System.arraycopy(bytes, 0, shorter, 0, totalRead);
-<a name="185" href="#185">185</a> <strong class="jxr_keyword">return</strong> shorter;
-<a name="186" href="#186">186</a> }
-<a name="187" href="#187">187</a>
-<a name="188" href="#188">188</a> <strong class="jxr_keyword">public</strong> String getType(String typeName, String url, byte[] data) {
-<a name="189" href="#189">189</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type = getMimeType(url, data);
-<a name="190" href="#190">190</a>
-<a name="191" href="#191">191</a> <strong class="jxr_keyword">if</strong> (type == <strong class="jxr_keyword">null</strong> && typeName != <strong class="jxr_keyword">null</strong>) {
-<a name="192" href="#192">192</a> <strong class="jxr_keyword">try</strong> {
-<a name="193" href="#193">193</a> type = forName(typeName);
-<a name="194" href="#194">194</a> } <strong class="jxr_keyword">catch</strong> (MimeTypeException e) {
-<a name="195" href="#195">195</a> <em class="jxr_comment">// Invalid type name hint</em>
-<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> <strong class="jxr_keyword">if</strong> (type == <strong class="jxr_keyword">null</strong>) {
-<a name="200" href="#200">200</a> type = root;
+<a name="123" href="#123">123</a> <strong class="jxr_keyword">if</strong> (data == <strong class="jxr_keyword">null</strong>) {
+<a name="124" href="#124">124</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> IllegalArgumentException(<span class="jxr_string">"Data is missing"</span>);
+<a name="125" href="#125">125</a> }
+<a name="126" href="#126">126</a>
+<a name="127" href="#127">127</a> <em class="jxr_comment">// First, check for XML descriptions (level by level)</em>
+<a name="128" href="#128">128</a> <strong class="jxr_keyword">for</strong> (MimeType type : xmls) {
+<a name="129" href="#129">129</a> <strong class="jxr_keyword">if</strong> (type.matchesXML(data)) {
+<a name="130" href="#130">130</a> <strong class="jxr_keyword">return</strong> type;
+<a name="131" href="#131">131</a> }
+<a name="132" href="#132">132</a> }
+<a name="133" href="#133">133</a>
+<a name="134" href="#134">134</a> <em class="jxr_comment">// Then, check for magic bytes</em>
+<a name="135" href="#135">135</a> <strong class="jxr_keyword">for</strong> (Magic magic : magics) {
+<a name="136" href="#136">136</a> <strong class="jxr_keyword">if</strong> (magic.eval(data)) {
+<a name="137" href="#137">137</a> <strong class="jxr_keyword">return</strong> magic.getType();
+<a name="138" href="#138">138</a> }
+<a name="139" href="#139">139</a> }
+<a name="140" href="#140">140</a>
+<a name="141" href="#141">141</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">null</strong>;
+<a name="142" href="#142">142</a> }
+<a name="143" href="#143">143</a>
+<a name="144" href="#144">144</a> <em class="jxr_javadoccomment">/**</em>
+<a name="145" href="#145">145</a> <em class="jxr_javadoccomment"> * Returns the MIME type that best matches the first few bytes of the</em>
+<a name="146" href="#146">146</a> <em class="jxr_javadoccomment"> * given document stream.</em>
+<a name="147" href="#147">147</a> <em class="jxr_javadoccomment"> *</em>
+<a name="148" href="#148">148</a> <em class="jxr_javadoccomment"> * @see #getMimeType(byte[])</em>
+<a name="149" href="#149">149</a> <em class="jxr_javadoccomment"> * @param stream document stream</em>
+<a name="150" href="#150">150</a> <em class="jxr_javadoccomment"> * @return matching MIME type, or <code>null</code> if no match is found</em>
+<a name="151" href="#151">151</a> <em class="jxr_javadoccomment"> * @throws IOException if the stream can be read</em>
+<a name="152" href="#152">152</a> <em class="jxr_javadoccomment"> */</em>
+<a name="153" href="#153">153</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> getMimeType(InputStream stream) <strong class="jxr_keyword">throws</strong> IOException {
+<a name="154" href="#154">154</a> <strong class="jxr_keyword">return</strong> getMimeType(readMagicHeader(stream));
+<a name="155" href="#155">155</a> }
+<a name="156" href="#156">156</a>
+<a name="157" href="#157">157</a> <em class="jxr_javadoccomment">/**</em>
+<a name="158" href="#158">158</a> <em class="jxr_javadoccomment"> * Reads the first {@link #getMinLength()} bytes from the given stream.</em>
+<a name="159" href="#159">159</a> <em class="jxr_javadoccomment"> * If the stream is shorter, then the entire content of the stream is</em>
+<a name="160" href="#160">160</a> <em class="jxr_javadoccomment"> * returned.</em>
+<a name="161" href="#161">161</a> <em class="jxr_javadoccomment"> * <p></em>
+<a name="162" href="#162">162</a> <em class="jxr_javadoccomment"> * The given stream is never {@link InputStream#close() closed},</em>
+<a name="163" href="#163">163</a> <em class="jxr_javadoccomment"> * {@link InputStream#mark(int) marked}, or</em>
+<a name="164" href="#164">164</a> <em class="jxr_javadoccomment"> * {@link InputStream#reset() reset} by this method.</em>
+<a name="165" href="#165">165</a> <em class="jxr_javadoccomment"> *</em>
+<a name="166" href="#166">166</a> <em class="jxr_javadoccomment"> * @param stream stream to be read</em>
+<a name="167" href="#167">167</a> <em class="jxr_javadoccomment"> * @return first {@link #getMinLength()} (or fewer) bytes of the stream</em>
+<a name="168" href="#168">168</a> <em class="jxr_javadoccomment"> * @throws IOException if the stream can not be read</em>
+<a name="169" href="#169">169</a> <em class="jxr_javadoccomment"> */</em>
+<a name="170" href="#170">170</a> <strong class="jxr_keyword">private</strong> byte[] readMagicHeader(InputStream stream) <strong class="jxr_keyword">throws</strong> IOException {
+<a name="171" href="#171">171</a> <strong class="jxr_keyword">if</strong> (stream == <strong class="jxr_keyword">null</strong>) {
+<a name="172" href="#172">172</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> IllegalArgumentException(<span class="jxr_string">"InputStream is missing"</span>);
+<a name="173" href="#173">173</a> }
+<a name="174" href="#174">174</a>
+<a name="175" href="#175">175</a> byte[] bytes = <strong class="jxr_keyword">new</strong> byte[getMinLength()];
+<a name="176" href="#176">176</a> <strong class="jxr_keyword">int</strong> totalRead = 0;
+<a name="177" href="#177">177</a>
+<a name="178" href="#178">178</a> <strong class="jxr_keyword">int</strong> lastRead = stream.read(bytes);
+<a name="179" href="#179">179</a> <strong class="jxr_keyword">while</strong> (lastRead != -1) {
+<a name="180" href="#180">180</a> totalRead += lastRead;
+<a name="181" href="#181">181</a> <strong class="jxr_keyword">if</strong> (totalRead == bytes.length) {
+<a name="182" href="#182">182</a> <strong class="jxr_keyword">return</strong> bytes;
+<a name="183" href="#183">183</a> }
+<a name="184" href="#184">184</a> lastRead = stream.read(bytes, totalRead, bytes.length - totalRead);
+<a name="185" href="#185">185</a> }
+<a name="186" href="#186">186</a>
+<a name="187" href="#187">187</a> byte[] shorter = <strong class="jxr_keyword">new</strong> byte[totalRead];
+<a name="188" href="#188">188</a> System.arraycopy(bytes, 0, shorter, 0, totalRead);
+<a name="189" href="#189">189</a> <strong class="jxr_keyword">return</strong> shorter;
+<a name="190" href="#190">190</a> }
+<a name="191" href="#191">191</a>
+<a name="192" href="#192">192</a> <strong class="jxr_keyword">public</strong> String getType(String typeName, String url, byte[] data) {
+<a name="193" href="#193">193</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type = getMimeType(url, data);
+<a name="194" href="#194">194</a>
+<a name="195" href="#195">195</a> <strong class="jxr_keyword">if</strong> (type == <strong class="jxr_keyword">null</strong> && typeName != <strong class="jxr_keyword">null</strong>) {
+<a name="196" href="#196">196</a> <strong class="jxr_keyword">try</strong> {
+<a name="197" href="#197">197</a> type = forName(typeName);
+<a name="198" href="#198">198</a> } <strong class="jxr_keyword">catch</strong> (MimeTypeException e) {
+<a name="199" href="#199">199</a> <em class="jxr_comment">// Invalid type name hint</em>
+<a name="200" href="#200">200</a> }
<a name="201" href="#201">201</a> }
<a name="202" href="#202">202</a>
-<a name="203" href="#203">203</a> <strong class="jxr_keyword">return</strong> type.getName();
-<a name="204" href="#204">204</a> }
-<a name="205" href="#205">205</a>
-<a name="206" href="#206">206</a> <em class="jxr_javadoccomment">/**</em>
-<a name="207" href="#207">207</a> <em class="jxr_javadoccomment"> * Determines the MIME type of the resource pointed to by the specified URL.</em>
-<a name="208" href="#208">208</a> <em class="jxr_javadoccomment"> * Examines the file's header, and if it cannot determine the MIME type</em>
-<a name="209" href="#209">209</a> <em class="jxr_javadoccomment"> * from the header, guesses the MIME type from the URL extension</em>
-<a name="210" href="#210">210</a> <em class="jxr_javadoccomment"> * (e.g. "pdf).</em>
-<a name="211" href="#211">211</a> <em class="jxr_javadoccomment"> *</em>
-<a name="212" href="#212">212</a> <em class="jxr_javadoccomment"> * @param url</em>
-<a name="213" href="#213">213</a> <em class="jxr_javadoccomment"> * @return</em>
-<a name="214" href="#214">214</a> <em class="jxr_javadoccomment"> * @throws IOException</em>
-<a name="215" href="#215">215</a> <em class="jxr_javadoccomment"> */</em>
-<a name="216" href="#216">216</a> <strong class="jxr_keyword">public</strong> String getType(URL url) <strong class="jxr_keyword">throws</strong> IOException {
-<a name="217" href="#217">217</a> InputStream stream = url.openStream();
-<a name="218" href="#218">218</a> <strong class="jxr_keyword">try</strong> {
-<a name="219" href="#219">219</a> <strong class="jxr_keyword">return</strong> getType(<strong class="jxr_keyword">null</strong>, url.toString(), readMagicHeader(stream));
-<a name="220" href="#220">220</a> } <strong class="jxr_keyword">finally</strong> {
-<a name="221" href="#221">221</a> stream.close();
-<a name="222" href="#222">222</a> }
-<a name="223" href="#223">223</a> }
-<a name="224" href="#224">224</a>
-<a name="225" href="#225">225</a> <em class="jxr_javadoccomment">/**</em>
-<a name="226" href="#226">226</a> <em class="jxr_javadoccomment"> * Find the Mime Content Type of a document from its name and its content.</em>
-<a name="227" href="#227">227</a> <em class="jxr_javadoccomment"> * The policy used to guess the Mime Content Type is:</em>
-<a name="228" href="#228">228</a> <em class="jxr_javadoccomment"> * <ol></em>
-<a name="229" href="#229">229</a> <em class="jxr_javadoccomment"> * <li>Try to find the type based on the provided data.</li></em>
-<a name="230" href="#230">230</a> <em class="jxr_javadoccomment"> * <li>If a type is found, then return it, otherwise try to find the type</em>
-<a name="231" href="#231">231</a> <em class="jxr_javadoccomment"> * based on the file name</li></em>
-<a name="232" href="#232">232</a> <em class="jxr_javadoccomment"> * </ol></em>
-<a name="233" href="#233">233</a> <em class="jxr_javadoccomment"> * </em>
-<a name="234" href="#234">234</a> <em class="jxr_javadoccomment"> * @param name</em>
-<a name="235" href="#235">235</a> <em class="jxr_javadoccomment"> * of the document to analyze.</em>
-<a name="236" href="#236">236</a> <em class="jxr_javadoccomment"> * @param data</em>
-<a name="237" href="#237">237</a> <em class="jxr_javadoccomment"> * are the first bytes of the document's content.</em>
-<a name="238" href="#238">238</a> <em class="jxr_javadoccomment"> * @return the Mime Content Type of the specified document, or</em>
-<a name="239" href="#239">239</a> <em class="jxr_javadoccomment"> * <code>null</code> if none is found.</em>
-<a name="240" href="#240">240</a> <em class="jxr_javadoccomment"> * @see #getMinLength()</em>
-<a name="241" href="#241">241</a> <em class="jxr_javadoccomment"> */</em>
-<a name="242" href="#242">242</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> getMimeType(String name, byte[] data) {
-<a name="243" href="#243">243</a> <em class="jxr_comment">// First, try to get the mime-type from the content</em>
-<a name="244" href="#244">244</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> mimeType = getMimeType(data);
-<a name="245" href="#245">245</a>
-<a name="246" href="#246">246</a> <em class="jxr_comment">// If no mime-type found, then try to get the mime-type from</em>
-<a name="247" href="#247">247</a> <em class="jxr_comment">// the document name</em>
-<a name="248" href="#248">248</a> <strong class="jxr_keyword">if</strong> (mimeType == <strong class="jxr_keyword">null</strong>) {
-<a name="249" href="#249">249</a> mimeType = getMimeType(name);
-<a name="250" href="#250">250</a> }
-<a name="251" href="#251">251</a>
-<a name="252" href="#252">252</a> <strong class="jxr_keyword">return</strong> mimeType;
-<a name="253" href="#253">253</a> }
-<a name="254" href="#254">254</a>
-<a name="255" href="#255">255</a> <em class="jxr_javadoccomment">/**</em>
-<a name="256" href="#256">256</a> <em class="jxr_javadoccomment"> * Returns the MIME type that best matches the given document name and</em>
-<a name="257" href="#257">257</a> <em class="jxr_javadoccomment"> * the first few bytes of the given document stream.</em>
-<a name="258" href="#258">258</a> <em class="jxr_javadoccomment"> *</em>
-<a name="259" href="#259">259</a> <em class="jxr_javadoccomment"> * @see #getMimeType(String, byte[])</em>
-<a name="260" href="#260">260</a> <em class="jxr_javadoccomment"> * @param name document name</em>
-<a name="261" href="#261">261</a> <em class="jxr_javadoccomment"> * @param stream document stream</em>
-<a name="262" href="#262">262</a> <em class="jxr_javadoccomment"> * @return matching MIME type, or <code>null</code> if no match is found</em>
-<a name="263" href="#263">263</a> <em class="jxr_javadoccomment"> * @throws IOException if the stream can not be read</em>
-<a name="264" href="#264">264</a> <em class="jxr_javadoccomment"> */</em>
-<a name="265" href="#265">265</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> getMimeType(String name, InputStream stream)
-<a name="266" href="#266">266</a> <strong class="jxr_keyword">throws</strong> IOException {
-<a name="267" href="#267">267</a> <strong class="jxr_keyword">return</strong> getMimeType(name, readMagicHeader(stream));
-<a name="268" href="#268">268</a> }
-<a name="269" href="#269">269</a>
-<a name="270" href="#270">270</a> <em class="jxr_javadoccomment">/**</em>
-<a name="271" href="#271">271</a> <em class="jxr_javadoccomment"> * Returns the registered media type with the given name (or alias).</em>
-<a name="272" href="#272">272</a> <em class="jxr_javadoccomment"> * The named media type is automatically registered (and returned) if</em>
-<a name="273" href="#273">273</a> <em class="jxr_javadoccomment"> * it doesn't already exist.</em>
-<a name="274" href="#274">274</a> <em class="jxr_javadoccomment"> *</em>
-<a name="275" href="#275">275</a> <em class="jxr_javadoccomment"> * @param name media type name (case-insensitive)</em>
-<a name="276" href="#276">276</a> <em class="jxr_javadoccomment"> * @return the registered media type with the given name or alias</em>
-<a name="277" href="#277">277</a> <em class="jxr_javadoccomment"> * @throws MimeTypeException if the given media type name is invalid</em>
-<a name="278" href="#278">278</a> <em class="jxr_javadoccomment"> */</em>
-<a name="279" href="#279">279</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">synchronized</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> forName(String name)
-<a name="280" href="#280">280</a> <strong class="jxr_keyword">throws</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a> {
-<a name="281" href="#281">281</a> <strong class="jxr_keyword">if</strong> (MimeType.isValid(name)) {
-<a name="282" href="#282">282</a> name = name.toLowerCase();
-<a name="283" href="#283">283</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type = types.get(name);
-<a name="284" href="#284">284</a> <strong class="jxr_keyword">if</strong> (type == <strong class="jxr_keyword">null</strong>) {
-<a name="285" href="#285">285</a> type = <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a>(<strong class="jxr_keyword">this</strong>, name);
-<a name="286" href="#286">286</a> type.setSuperType(root);
-<a name="287" href="#287">287</a> types.put(name, type);
-<a name="288" href="#288">288</a> }
-<a name="289" href="#289">289</a> <strong class="jxr_keyword">return</strong> type;
-<a name="290" href="#290">290</a> } <strong class="jxr_keyword">else</strong> {
-<a name="291" href="#291">291</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a>(<span class="jxr_string">"Invalid media type name: "</span> + name);
-<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 class="jxr_javadoccomment">/**</em>
-<a name="296" href="#296">296</a> <em class="jxr_javadoccomment"> * Adds an alias for the given media type. This method should only</em>
-<a name="297" href="#297">297</a> <em class="jxr_javadoccomment"> * be called from {@link MimeType#addAlias(String)}.</em>
-<a name="298" href="#298">298</a> <em class="jxr_javadoccomment"> *</em>
-<a name="299" href="#299">299</a> <em class="jxr_javadoccomment"> * @param type media type</em>
-<a name="300" href="#300">300</a> <em class="jxr_javadoccomment"> * @param alias media type alias (normalized to lower case)</em>
-<a name="301" href="#301">301</a> <em class="jxr_javadoccomment"> * @throws MimeTypeException if the alias already exists</em>
-<a name="302" href="#302">302</a> <em class="jxr_javadoccomment"> */</em>
-<a name="303" href="#303">303</a> <strong class="jxr_keyword">synchronized</strong> <strong class="jxr_keyword">void</strong> addAlias(<a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type, String alias)
-<a name="304" href="#304">304</a> <strong class="jxr_keyword">throws</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a> {
-<a name="305" href="#305">305</a> <strong class="jxr_keyword">if</strong> (!types.containsKey(alias)) {
-<a name="306" href="#306">306</a> types.put(alias, type);
-<a name="307" href="#307">307</a> } <strong class="jxr_keyword">else</strong> {
-<a name="308" href="#308">308</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a>(
-<a name="309" href="#309">309</a> <span class="jxr_string">"Media type alias already exists: "</span> + alias);
-<a name="310" href="#310">310</a> }
-<a name="311" href="#311">311</a> }
-<a name="312" href="#312">312</a>
-<a name="313" href="#313">313</a> <em class="jxr_javadoccomment">/**</em>
-<a name="314" href="#314">314</a> <em class="jxr_javadoccomment"> * Adds a file name pattern for the given media type.</em>
-<a name="315" href="#315">315</a> <em class="jxr_javadoccomment"> *</em>
-<a name="316" href="#316">316</a> <em class="jxr_javadoccomment"> * @param type media type</em>
-<a name="317" href="#317">317</a> <em class="jxr_javadoccomment"> * @param pattern file name pattern</em>
-<a name="318" href="#318">318</a> <em class="jxr_javadoccomment"> * @throws MimeTypeException if the pattern conflicts with existing ones</em>
-<a name="319" href="#319">319</a> <em class="jxr_javadoccomment"> */</em>
-<a name="320" href="#320">320</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> addPattern(<a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type, String pattern)
-<a name="321" href="#321">321</a> <strong class="jxr_keyword">throws</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a> {
-<a name="322" href="#322">322</a> patterns.add(pattern, type);
-<a name="323" href="#323">323</a> }
-<a name="324" href="#324">324</a>
-<a name="325" href="#325">325</a> <em class="jxr_javadoccomment">/**</em>
-<a name="326" href="#326">326</a> <em class="jxr_javadoccomment"> * Return the minimum length of data to provide to analyzing methods based</em>
-<a name="327" href="#327">327</a> <em class="jxr_javadoccomment"> * on the document's content in order to check all the known MimeTypes.</em>
-<a name="328" href="#328">328</a> <em class="jxr_javadoccomment"> * </em>
-<a name="329" href="#329">329</a> <em class="jxr_javadoccomment"> * @return the minimum length of data to provide.</em>
-<a name="330" href="#330">330</a> <em class="jxr_javadoccomment"> * @see #getMimeType(byte[])</em>
-<a name="331" href="#331">331</a> <em class="jxr_javadoccomment"> * @see #getMimeType(String, byte[])</em>
-<a name="332" href="#332">332</a> <em class="jxr_javadoccomment"> */</em>
-<a name="333" href="#333">333</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">int</strong> getMinLength() {
-<a name="334" href="#334">334</a> <strong class="jxr_keyword">return</strong> 1024;
-<a name="335" href="#335">335</a> <em class="jxr_comment">// return minLength;</em>
-<a name="336" href="#336">336</a> }
-<a name="337" href="#337">337</a>
-<a name="338" href="#338">338</a> <em class="jxr_javadoccomment">/**</em>
-<a name="339" href="#339">339</a> <em class="jxr_javadoccomment"> * Add the specified mime-type in the repository.</em>
-<a name="340" href="#340">340</a> <em class="jxr_javadoccomment"> * </em>
-<a name="341" href="#341">341</a> <em class="jxr_javadoccomment"> * @param type</em>
-<a name="342" href="#342">342</a> <em class="jxr_javadoccomment"> * is the mime-type to add.</em>
-<a name="343" href="#343">343</a> <em class="jxr_javadoccomment"> */</em>
-<a name="344" href="#344">344</a> <strong class="jxr_keyword">void</strong> add(<a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type) {
-<a name="345" href="#345">345</a> <em class="jxr_comment">// Update the magics index...</em>
-<a name="346" href="#346">346</a> <strong class="jxr_keyword">if</strong> (type.hasMagic()) {
-<a name="347" href="#347">347</a> magics.addAll(Arrays.asList(type.getMagics()));
-<a name="348" href="#348">348</a> }
-<a name="349" href="#349">349</a>
-<a name="350" href="#350">350</a> <em class="jxr_comment">// Update the xml (xmlRoot) index...</em>
-<a name="351" href="#351">351</a> <strong class="jxr_keyword">if</strong> (type.hasRootXML()) {
-<a name="352" href="#352">352</a> xmls.add(type);
-<a name="353" href="#353">353</a> }
-<a name="354" href="#354">354</a> }
-<a name="355" href="#355">355</a>
-<a name="356" href="#356">356</a> }
+<a name="203" href="#203">203</a> <strong class="jxr_keyword">if</strong> (type == <strong class="jxr_keyword">null</strong>) {
+<a name="204" href="#204">204</a> type = root;
+<a name="205" href="#205">205</a> }
+<a name="206" href="#206">206</a>
+<a name="207" href="#207">207</a> <strong class="jxr_keyword">return</strong> type.getName();
+<a name="208" href="#208">208</a> }
+<a name="209" href="#209">209</a>
+<a name="210" href="#210">210</a> <em class="jxr_javadoccomment">/**</em>
+<a name="211" href="#211">211</a> <em class="jxr_javadoccomment"> * Determines the MIME type of the resource pointed to by the specified URL.</em>
+<a name="212" href="#212">212</a> <em class="jxr_javadoccomment"> * Examines the file's header, and if it cannot determine the MIME type</em>
+<a name="213" href="#213">213</a> <em class="jxr_javadoccomment"> * from the header, guesses the MIME type from the URL extension</em>
+<a name="214" href="#214">214</a> <em class="jxr_javadoccomment"> * (e.g. "pdf).</em>
+<a name="215" href="#215">215</a> <em class="jxr_javadoccomment"> *</em>
+<a name="216" href="#216">216</a> <em class="jxr_javadoccomment"> * @param url</em>
+<a name="217" href="#217">217</a> <em class="jxr_javadoccomment"> * @return</em>
+<a name="218" href="#218">218</a> <em class="jxr_javadoccomment"> * @throws IOException</em>
+<a name="219" href="#219">219</a> <em class="jxr_javadoccomment"> */</em>
+<a name="220" href="#220">220</a> <strong class="jxr_keyword">public</strong> String getType(URL url) <strong class="jxr_keyword">throws</strong> IOException {
+<a name="221" href="#221">221</a> InputStream stream = url.openStream();
+<a name="222" href="#222">222</a> <strong class="jxr_keyword">try</strong> {
+<a name="223" href="#223">223</a> <strong class="jxr_keyword">return</strong> getType(<strong class="jxr_keyword">null</strong>, url.toString(), readMagicHeader(stream));
+<a name="224" href="#224">224</a> } <strong class="jxr_keyword">finally</strong> {
+<a name="225" href="#225">225</a> stream.close();
+<a name="226" href="#226">226</a> }
+<a name="227" href="#227">227</a> }
+<a name="228" href="#228">228</a>
+<a name="229" href="#229">229</a> <em class="jxr_javadoccomment">/**</em>
+<a name="230" href="#230">230</a> <em class="jxr_javadoccomment"> * Find the Mime Content Type of a document from its name and its content.</em>
+<a name="231" href="#231">231</a> <em class="jxr_javadoccomment"> * The policy used to guess the Mime Content Type is:</em>
+<a name="232" href="#232">232</a> <em class="jxr_javadoccomment"> * <ol></em>
+<a name="233" href="#233">233</a> <em class="jxr_javadoccomment"> * <li>Try to find the type based on the provided data.</li></em>
+<a name="234" href="#234">234</a> <em class="jxr_javadoccomment"> * <li>If a type is found, then return it, otherwise try to find the type</em>
+<a name="235" href="#235">235</a> <em class="jxr_javadoccomment"> * based on the file name</li></em>
+<a name="236" href="#236">236</a> <em class="jxr_javadoccomment"> * </ol></em>
+<a name="237" href="#237">237</a> <em class="jxr_javadoccomment"> * </em>
+<a name="238" href="#238">238</a> <em class="jxr_javadoccomment"> * @param name</em>
+<a name="239" href="#239">239</a> <em class="jxr_javadoccomment"> * of the document to analyze.</em>
+<a name="240" href="#240">240</a> <em class="jxr_javadoccomment"> * @param data</em>
+<a name="241" href="#241">241</a> <em class="jxr_javadoccomment"> * are the first bytes of the document's content.</em>
+<a name="242" href="#242">242</a> <em class="jxr_javadoccomment"> * @return the Mime Content Type of the specified document, or</em>
+<a name="243" href="#243">243</a> <em class="jxr_javadoccomment"> * <code>null</code> if none is found.</em>
+<a name="244" href="#244">244</a> <em class="jxr_javadoccomment"> * @see #getMinLength()</em>
+<a name="245" href="#245">245</a> <em class="jxr_javadoccomment"> */</em>
+<a name="246" href="#246">246</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> getMimeType(String name, byte[] data) {
+<a name="247" href="#247">247</a> <em class="jxr_comment">// First, try to get the mime-type from the content</em>
+<a name="248" href="#248">248</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> mimeType = getMimeType(data);
+<a name="249" href="#249">249</a>
+<a name="250" href="#250">250</a> <em class="jxr_comment">// If no mime-type found, then try to get the mime-type from</em>
+<a name="251" href="#251">251</a> <em class="jxr_comment">// the document name</em>
+<a name="252" href="#252">252</a> <strong class="jxr_keyword">if</strong> (mimeType == <strong class="jxr_keyword">null</strong>) {
+<a name="253" href="#253">253</a> mimeType = getMimeType(name);
+<a name="254" href="#254">254</a> }
+<a name="255" href="#255">255</a>
+<a name="256" href="#256">256</a> <strong class="jxr_keyword">return</strong> mimeType;
+<a name="257" href="#257">257</a> }
+<a name="258" href="#258">258</a>
+<a name="259" href="#259">259</a> <em class="jxr_javadoccomment">/**</em>
+<a name="260" href="#260">260</a> <em class="jxr_javadoccomment"> * Returns the MIME type that best matches the given document name and</em>
+<a name="261" href="#261">261</a> <em class="jxr_javadoccomment"> * the first few bytes of the given document stream.</em>
+<a name="262" href="#262">262</a> <em class="jxr_javadoccomment"> *</em>
+<a name="263" href="#263">263</a> <em class="jxr_javadoccomment"> * @see #getMimeType(String, byte[])</em>
+<a name="264" href="#264">264</a> <em class="jxr_javadoccomment"> * @param name document name</em>
+<a name="265" href="#265">265</a> <em class="jxr_javadoccomment"> * @param stream document stream</em>
+<a name="266" href="#266">266</a> <em class="jxr_javadoccomment"> * @return matching MIME type, or <code>null</code> if no match is found</em>
+<a name="267" href="#267">267</a> <em class="jxr_javadoccomment"> * @throws IOException if the stream can not be read</em>
+<a name="268" href="#268">268</a> <em class="jxr_javadoccomment"> */</em>
+<a name="269" href="#269">269</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> getMimeType(String name, InputStream stream)
+<a name="270" href="#270">270</a> <strong class="jxr_keyword">throws</strong> IOException {
+<a name="271" href="#271">271</a> <strong class="jxr_keyword">return</strong> getMimeType(name, readMagicHeader(stream));
+<a name="272" href="#272">272</a> }
+<a name="273" href="#273">273</a>
+<a name="274" href="#274">274</a> <em class="jxr_javadoccomment">/**</em>
+<a name="275" href="#275">275</a> <em class="jxr_javadoccomment"> * Returns the registered media type with the given name (or alias).</em>
+<a name="276" href="#276">276</a> <em class="jxr_javadoccomment"> * The named media type is automatically registered (and returned) if</em>
+<a name="277" href="#277">277</a> <em class="jxr_javadoccomment"> * it doesn't already exist.</em>
+<a name="278" href="#278">278</a> <em class="jxr_javadoccomment"> *</em>
+<a name="279" href="#279">279</a> <em class="jxr_javadoccomment"> * @param name media type name (case-insensitive)</em>
+<a name="280" href="#280">280</a> <em class="jxr_javadoccomment"> * @return the registered media type with the given name or alias</em>
+<a name="281" href="#281">281</a> <em class="jxr_javadoccomment"> * @throws MimeTypeException if the given media type name is invalid</em>
+<a name="282" href="#282">282</a> <em class="jxr_javadoccomment"> */</em>
+<a name="283" href="#283">283</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">synchronized</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> forName(String name)
+<a name="284" href="#284">284</a> <strong class="jxr_keyword">throws</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a> {
+<a name="285" href="#285">285</a> <strong class="jxr_keyword">if</strong> (MimeType.isValid(name)) {
+<a name="286" href="#286">286</a> name = name.toLowerCase();
+<a name="287" href="#287">287</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type = types.get(name);
+<a name="288" href="#288">288</a> <strong class="jxr_keyword">if</strong> (type == <strong class="jxr_keyword">null</strong>) {
+<a name="289" href="#289">289</a> type = <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a>(<strong class="jxr_keyword">this</strong>, name);
+<a name="290" href="#290">290</a> type.setSuperType(root);
+<a name="291" href="#291">291</a> types.put(name, type);
+<a name="292" href="#292">292</a> }
+<a name="293" href="#293">293</a> <strong class="jxr_keyword">return</strong> type;
+<a name="294" href="#294">294</a> } <strong class="jxr_keyword">else</strong> {
+<a name="295" href="#295">295</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a>(<span class="jxr_string">"Invalid media type name: "</span> + name);
+<a name="296" href="#296">296</a> }
+<a name="297" href="#297">297</a> }
+<a name="298" href="#298">298</a>
+<a name="299" href="#299">299</a> <em class="jxr_javadoccomment">/**</em>
+<a name="300" href="#300">300</a> <em class="jxr_javadoccomment"> * Adds an alias for the given media type. This method should only</em>
+<a name="301" href="#301">301</a> <em class="jxr_javadoccomment"> * be called from {@link MimeType#addAlias(String)}.</em>
+<a name="302" href="#302">302</a> <em class="jxr_javadoccomment"> *</em>
+<a name="303" href="#303">303</a> <em class="jxr_javadoccomment"> * @param type media type</em>
+<a name="304" href="#304">304</a> <em class="jxr_javadoccomment"> * @param alias media type alias (normalized to lower case)</em>
+<a name="305" href="#305">305</a> <em class="jxr_javadoccomment"> * @throws MimeTypeException if the alias already exists</em>
+<a name="306" href="#306">306</a> <em class="jxr_javadoccomment"> */</em>
+<a name="307" href="#307">307</a> <strong class="jxr_keyword">synchronized</strong> <strong class="jxr_keyword">void</strong> addAlias(<a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type, String alias)
+<a name="308" href="#308">308</a> <strong class="jxr_keyword">throws</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a> {
+<a name="309" href="#309">309</a> <strong class="jxr_keyword">if</strong> (!types.containsKey(alias)) {
+<a name="310" href="#310">310</a> types.put(alias, type);
+<a name="311" href="#311">311</a> } <strong class="jxr_keyword">else</strong> {
+<a name="312" href="#312">312</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a>(
+<a name="313" href="#313">313</a> <span class="jxr_string">"Media type alias already exists: "</span> + alias);
+<a name="314" href="#314">314</a> }
+<a name="315" href="#315">315</a> }
+<a name="316" href="#316">316</a>
+<a name="317" href="#317">317</a> <em class="jxr_javadoccomment">/**</em>
+<a name="318" href="#318">318</a> <em class="jxr_javadoccomment"> * Adds a file name pattern for the given media type.</em>
+<a name="319" href="#319">319</a> <em class="jxr_javadoccomment"> *</em>
+<a name="320" href="#320">320</a> <em class="jxr_javadoccomment"> * @param type media type</em>
+<a name="321" href="#321">321</a> <em class="jxr_javadoccomment"> * @param pattern file name pattern</em>
+<a name="322" href="#322">322</a> <em class="jxr_javadoccomment"> * @throws MimeTypeException if the pattern conflicts with existing ones</em>
+<a name="323" href="#323">323</a> <em class="jxr_javadoccomment"> */</em>
+<a name="324" href="#324">324</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> addPattern(<a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type, String pattern)
+<a name="325" href="#325">325</a> <strong class="jxr_keyword">throws</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a> {
+<a name="326" href="#326">326</a> patterns.add(pattern, type);
+<a name="327" href="#327">327</a> }
+<a name="328" href="#328">328</a>
+<a name="329" href="#329">329</a> <em class="jxr_javadoccomment">/**</em>
+<a name="330" href="#330">330</a> <em class="jxr_javadoccomment"> * Return the minimum length of data to provide to analyzing methods based</em>
+<a name="331" href="#331">331</a> <em class="jxr_javadoccomment"> * on the document's content in order to check all the known MimeTypes.</em>
+<a name="332" href="#332">332</a> <em class="jxr_javadoccomment"> * </em>
+<a name="333" href="#333">333</a> <em class="jxr_javadoccomment"> * @return the minimum length of data to provide.</em>
+<a name="334" href="#334">334</a> <em class="jxr_javadoccomment"> * @see #getMimeType(byte[])</em>
+<a name="335" href="#335">335</a> <em class="jxr_javadoccomment"> * @see #getMimeType(String, byte[])</em>
+<a name="336" href="#336">336</a> <em class="jxr_javadoccomment"> */</em>
+<a name="337" href="#337">337</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">int</strong> getMinLength() {
+<a name="338" href="#338">338</a> <strong class="jxr_keyword">return</strong> 1024;
+<a name="339" href="#339">339</a> <em class="jxr_comment">// return minLength;</em>
+<a name="340" href="#340">340</a> }
+<a name="341" href="#341">341</a>
+<a name="342" href="#342">342</a> <em class="jxr_javadoccomment">/**</em>
+<a name="343" href="#343">343</a> <em class="jxr_javadoccomment"> * Add the specified mime-type in the repository.</em>
+<a name="344" href="#344">344</a> <em class="jxr_javadoccomment"> * </em>
+<a name="345" href="#345">345</a> <em class="jxr_javadoccomment"> * @param type</em>
+<a name="346" href="#346">346</a> <em class="jxr_javadoccomment"> * is the mime-type to add.</em>
+<a name="347" href="#347">347</a> <em class="jxr_javadoccomment"> */</em>
+<a name="348" href="#348">348</a> <strong class="jxr_keyword">void</strong> add(<a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type) {
+<a name="349" href="#349">349</a> <em class="jxr_comment">// Update the magics index...</em>
+<a name="350" href="#350">350</a> <strong class="jxr_keyword">if</strong> (type.hasMagic()) {
+<a name="351" href="#351">351</a> magics.addAll(Arrays.asList(type.getMagics()));
+<a name="352" href="#352">352</a> }
+<a name="353" href="#353">353</a>
+<a name="354" href="#354">354</a> <em class="jxr_comment">// Update the xml (xmlRoot) index...</em>
+<a name="355" href="#355">355</a> <strong class="jxr_keyword">if</strong> (type.hasRootXML()) {
+<a name="356" href="#356">356</a> xmls.add(type);
+<a name="357" href="#357">357</a> }
+<a name="358" href="#358">358</a> }
+<a name="359" href="#359">359</a>
+<a name="360" href="#360">360</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>
Modified: incubator/tika/site/xref/org/apache/tika/mime/Patterns.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/mime/Patterns.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/mime/Patterns.html (original)
+++ incubator/tika/site/xref/org/apache/tika/mime/Patterns.html Sun Jan 6 19:06:26 2008
@@ -68,123 +68,127 @@
<a name="58" href="#58">58</a> });
<a name="59" href="#59">59</a>
<a name="60" href="#60">60</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> add(String pattern, <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type) <strong class="jxr_keyword">throws</strong> MimeTypeException {
-<a name="61" href="#61">61</a> assert pattern != <strong class="jxr_keyword">null</strong> && type != <strong class="jxr_keyword">null</strong>;
-<a name="62" href="#62">62</a>
-<a name="63" href="#63">63</a> <strong class="jxr_keyword">if</strong> (pattern.indexOf('*') == -1
-<a name="64" href="#64">64</a> && pattern.indexOf('?') == -1
-<a name="65" href="#65">65</a> && pattern.indexOf('[') == -1) {
-<a name="66" href="#66">66</a> addName(pattern, type);
-<a name="67" href="#67">67</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (pattern.startsWith(<span class="jxr_string">"*"</span>)
-<a name="68" href="#68">68</a> && pattern.indexOf('*', 1) == -1
-<a name="69" href="#69">69</a> && pattern.indexOf('?') == -1
-<a name="70" href="#70">70</a> && pattern.indexOf('[') == -1) {
-<a name="71" href="#71">71</a> addExtension(pattern.substring(1), type);
-<a name="72" href="#72">72</a> } <strong class="jxr_keyword">else</strong> {
-<a name="73" href="#73">73</a> addGlob(compile(pattern), type);
-<a name="74" href="#74">74</a> }
-<a name="75" href="#75">75</a> }
-<a name="76" href="#76">76</a>
-<a name="77" href="#77">77</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> addName(String name, <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type) <strong class="jxr_keyword">throws</strong> MimeTypeException {
-<a name="78" href="#78">78</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> previous = names.get(name);
-<a name="79" href="#79">79</a> <strong class="jxr_keyword">if</strong> (previous == <strong class="jxr_keyword">null</strong> || previous.isDescendantOf(type)) {
-<a name="80" href="#80">80</a> names.put(name, type);
-<a name="81" href="#81">81</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (previous == type || type.isDescendantOf(previous)) {
-<a name="82" href="#82">82</a> <em class="jxr_comment">// do nothing</em>
-<a name="83" href="#83">83</a> } <strong class="jxr_keyword">else</strong> {
-<a name="84" href="#84">84</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a>(<span class="jxr_string">"Conflicting name pattern: "</span> + name);
-<a name="85" href="#85">85</a> }
-<a name="86" href="#86">86</a> }
-<a name="87" href="#87">87</a>
-<a name="88" href="#88">88</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> addExtension(String extension, <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type)
-<a name="89" href="#89">89</a> <strong class="jxr_keyword">throws</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a> {
-<a name="90" href="#90">90</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> previous = extensions.get(extension);
-<a name="91" href="#91">91</a> <strong class="jxr_keyword">if</strong> (previous == <strong class="jxr_keyword">null</strong> || previous.isDescendantOf(type)) {
-<a name="92" href="#92">92</a> extensions.put(extension, type);
-<a name="93" href="#93">93</a> <strong class="jxr_keyword">int</strong> length = extension.length();
-<a name="94" href="#94">94</a> minExtensionLength = Math.min(minExtensionLength, length);
-<a name="95" href="#95">95</a> maxExtensionLength = Math.max(maxExtensionLength, length);
-<a name="96" href="#96">96</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (previous == type || type.isDescendantOf(previous)) {
-<a name="97" href="#97">97</a> <em class="jxr_comment">// do nothing</em>
-<a name="98" href="#98">98</a> } <strong class="jxr_keyword">else</strong> {
-<a name="99" href="#99">99</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a>(
-<a name="100" href="#100">100</a> <span class="jxr_string">"Conflicting extension pattern: "</span> + extension);
-<a name="101" href="#101">101</a> }
-<a name="102" href="#102">102</a> }
-<a name="103" href="#103">103</a>
-<a name="104" href="#104">104</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> addGlob(String glob, <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type)
-<a name="105" href="#105">105</a> <strong class="jxr_keyword">throws</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a> {
-<a name="106" href="#106">106</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> previous = globs.get(glob);
-<a name="107" href="#107">107</a> <strong class="jxr_keyword">if</strong> (previous == <strong class="jxr_keyword">null</strong> || previous.isDescendantOf(type)) {
-<a name="108" href="#108">108</a> extensions.put(glob, type);
-<a name="109" href="#109">109</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (previous == type || type.isDescendantOf(previous)) {
-<a name="110" href="#110">110</a> <em class="jxr_comment">// do nothing</em>
-<a name="111" href="#111">111</a> } <strong class="jxr_keyword">else</strong> {
-<a name="112" href="#112">112</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a>(<span class="jxr_string">"Conflicting glob pattern: "</span> + glob);
-<a name="113" href="#113">113</a> }
-<a name="114" href="#114">114</a> }
-<a name="115" href="#115">115</a>
-<a name="116" href="#116">116</a> <em class="jxr_javadoccomment">/**</em>
-<a name="117" href="#117">117</a> <em class="jxr_javadoccomment"> * Find the MimeType corresponding to a resource name.</em>
-<a name="118" href="#118">118</a> <em class="jxr_javadoccomment"> * </em>
-<a name="119" href="#119">119</a> <em class="jxr_javadoccomment"> * It applies the recommendations detailed in FreeDesktop Shared MIME-info</em>
-<a name="120" href="#120">120</a> <em class="jxr_javadoccomment"> * Database for guessing MimeType from a resource name: It first tries a</em>
-<a name="121" href="#121">121</a> <em class="jxr_javadoccomment"> * case-sensitive match, then try again with the resource name converted to</em>
-<a name="122" href="#122">122</a> <em class="jxr_javadoccomment"> * lower-case if that fails. If several patterns match then the longest</em>
-<a name="123" href="#123">123</a> <em class="jxr_javadoccomment"> * pattern is used. In particular, files with multiple extensions (such as</em>
-<a name="124" href="#124">124</a> <em class="jxr_javadoccomment"> * Data.tar.gz) match the longest sequence of extensions (eg '*.tar.gz' in</em>
-<a name="125" href="#125">125</a> <em class="jxr_javadoccomment"> * preference to '*.gz'). Literal patterns (eg, 'Makefile') are matched</em>
-<a name="126" href="#126">126</a> <em class="jxr_javadoccomment"> * before all others. Patterns beginning with `*.' and containing no other</em>
-<a name="127" href="#127">127</a> <em class="jxr_javadoccomment"> * special characters (`*?[') are matched before other wildcarded patterns</em>
-<a name="128" href="#128">128</a> <em class="jxr_javadoccomment"> * (since this covers the majority of the patterns).</em>
-<a name="129" href="#129">129</a> <em class="jxr_javadoccomment"> */</em>
-<a name="130" href="#130">130</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> matches(String name) {
-<a name="131" href="#131">131</a> assert name != <strong class="jxr_keyword">null</strong>;
-<a name="132" href="#132">132</a>
-<a name="133" href="#133">133</a> <em class="jxr_comment">// First, try exact match of the provided resource name</em>
-<a name="134" href="#134">134</a> <strong class="jxr_keyword">if</strong> (names.containsKey(name)) {
-<a name="135" href="#135">135</a> <strong class="jxr_keyword">return</strong> names.get(name);
-<a name="136" href="#136">136</a> }
-<a name="137" href="#137">137</a>
-<a name="138" href="#138">138</a> <em class="jxr_comment">// Then try "extension" (*.xxx) matching</em>
-<a name="139" href="#139">139</a> <strong class="jxr_keyword">int</strong> maxLength = Math.min(maxExtensionLength, name.length());
-<a name="140" href="#140">140</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> n = maxLength; n >= minExtensionLength; n--) {
-<a name="141" href="#141">141</a> String extension = name.substring(name.length() - n);
-<a name="142" href="#142">142</a> <strong class="jxr_keyword">if</strong> (extensions.containsKey(extension)) {
-<a name="143" href="#143">143</a> <strong class="jxr_keyword">return</strong> extensions.get(extension);
-<a name="144" href="#144">144</a> }
-<a name="145" href="#145">145</a> }
-<a name="146" href="#146">146</a>
-<a name="147" href="#147">147</a> <em class="jxr_comment">// And finally, try complex regexp matching</em>
-<a name="148" href="#148">148</a> <strong class="jxr_keyword">for</strong> (Map.Entry<String, MimeType> entry : globs.entrySet()) {
-<a name="149" href="#149">149</a> <strong class="jxr_keyword">if</strong> (name.matches(entry.getKey())) {
-<a name="150" href="#150">150</a> <strong class="jxr_keyword">return</strong> entry.getValue();
-<a name="151" href="#151">151</a> }
-<a name="152" href="#152">152</a> }
-<a name="153" href="#153">153</a>
-<a name="154" href="#154">154</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">null</strong>;
-<a name="155" href="#155">155</a> }
-<a name="156" href="#156">156</a>
-<a name="157" href="#157">157</a> <strong class="jxr_keyword">private</strong> String compile(String glob) {
-<a name="158" href="#158">158</a> StringBuilder pattern = <strong class="jxr_keyword">new</strong> StringBuilder();
-<a name="159" href="#159">159</a> pattern.append(<span class="jxr_string">"\\A"</span>);
-<a name="160" href="#160">160</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> i = 0; i < glob.length(); i++) {
-<a name="161" href="#161">161</a> <strong class="jxr_keyword">char</strong> ch = glob.charAt(i);
-<a name="162" href="#162">162</a> <strong class="jxr_keyword">if</strong> (ch == '?') {
-<a name="163" href="#163">163</a> pattern.append('.');
-<a name="164" href="#164">164</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (ch == '*') {
-<a name="165" href="#165">165</a> pattern.append(<span class="jxr_string">".*"</span>);
-<a name="166" href="#166">166</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (<span class="jxr_string">"\\[]^.-$+(){}|"</span>.indexOf(ch) != -1) {
-<a name="167" href="#167">167</a> pattern.append('\\');
-<a name="168" href="#168">168</a> pattern.append(ch);
-<a name="169" href="#169">169</a> } <strong class="jxr_keyword">else</strong> {
-<a name="170" href="#170">170</a> pattern.append(ch);
-<a name="171" href="#171">171</a> }
-<a name="172" href="#172">172</a> }
-<a name="173" href="#173">173</a> pattern.append(<span class="jxr_string">"\\z"</span>);
-<a name="174" href="#174">174</a> <strong class="jxr_keyword">return</strong> pattern.toString();
-<a name="175" href="#175">175</a> }
-<a name="176" href="#176">176</a>
-<a name="177" href="#177">177</a> }
+<a name="61" href="#61">61</a> <strong class="jxr_keyword">if</strong> (pattern == <strong class="jxr_keyword">null</strong> || type == <strong class="jxr_keyword">null</strong>) {
+<a name="62" href="#62">62</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> IllegalArgumentException(<span class="jxr_string">"Pattern and/or mime type is missing"</span>);
+<a name="63" href="#63">63</a> }
+<a name="64" href="#64">64</a>
+<a name="65" href="#65">65</a> <strong class="jxr_keyword">if</strong> (pattern.indexOf('*') == -1
+<a name="66" href="#66">66</a> && pattern.indexOf('?') == -1
+<a name="67" href="#67">67</a> && pattern.indexOf('[') == -1) {
+<a name="68" href="#68">68</a> addName(pattern, type);
+<a name="69" href="#69">69</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (pattern.startsWith(<span class="jxr_string">"*"</span>)
+<a name="70" href="#70">70</a> && pattern.indexOf('*', 1) == -1
+<a name="71" href="#71">71</a> && pattern.indexOf('?') == -1
+<a name="72" href="#72">72</a> && pattern.indexOf('[') == -1) {
+<a name="73" href="#73">73</a> addExtension(pattern.substring(1), type);
+<a name="74" href="#74">74</a> } <strong class="jxr_keyword">else</strong> {
+<a name="75" href="#75">75</a> addGlob(compile(pattern), type);
+<a name="76" href="#76">76</a> }
+<a name="77" href="#77">77</a> }
+<a name="78" href="#78">78</a>
+<a name="79" href="#79">79</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> addName(String name, <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type) <strong class="jxr_keyword">throws</strong> MimeTypeException {
+<a name="80" href="#80">80</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> previous = names.get(name);
+<a name="81" href="#81">81</a> <strong class="jxr_keyword">if</strong> (previous == <strong class="jxr_keyword">null</strong> || previous.isDescendantOf(type)) {
+<a name="82" href="#82">82</a> names.put(name, type);
+<a name="83" href="#83">83</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (previous == type || type.isDescendantOf(previous)) {
+<a name="84" href="#84">84</a> <em class="jxr_comment">// do nothing</em>
+<a name="85" href="#85">85</a> } <strong class="jxr_keyword">else</strong> {
+<a name="86" href="#86">86</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a>(<span class="jxr_string">"Conflicting name pattern: "</span> + name);
+<a name="87" href="#87">87</a> }
+<a name="88" href="#88">88</a> }
+<a name="89" href="#89">89</a>
+<a name="90" href="#90">90</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> addExtension(String extension, <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type)
+<a name="91" href="#91">91</a> <strong class="jxr_keyword">throws</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a> {
+<a name="92" href="#92">92</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> previous = extensions.get(extension);
+<a name="93" href="#93">93</a> <strong class="jxr_keyword">if</strong> (previous == <strong class="jxr_keyword">null</strong> || previous.isDescendantOf(type)) {
+<a name="94" href="#94">94</a> extensions.put(extension, type);
+<a name="95" href="#95">95</a> <strong class="jxr_keyword">int</strong> length = extension.length();
+<a name="96" href="#96">96</a> minExtensionLength = Math.min(minExtensionLength, length);
+<a name="97" href="#97">97</a> maxExtensionLength = Math.max(maxExtensionLength, length);
+<a name="98" href="#98">98</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (previous == type || type.isDescendantOf(previous)) {
+<a name="99" href="#99">99</a> <em class="jxr_comment">// do nothing</em>
+<a name="100" href="#100">100</a> } <strong class="jxr_keyword">else</strong> {
+<a name="101" href="#101">101</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a>(
+<a name="102" href="#102">102</a> <span class="jxr_string">"Conflicting extension pattern: "</span> + extension);
+<a name="103" href="#103">103</a> }
+<a name="104" href="#104">104</a> }
+<a name="105" href="#105">105</a>
+<a name="106" href="#106">106</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">void</strong> addGlob(String glob, <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> type)
+<a name="107" href="#107">107</a> <strong class="jxr_keyword">throws</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a> {
+<a name="108" href="#108">108</a> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> previous = globs.get(glob);
+<a name="109" href="#109">109</a> <strong class="jxr_keyword">if</strong> (previous == <strong class="jxr_keyword">null</strong> || previous.isDescendantOf(type)) {
+<a name="110" href="#110">110</a> extensions.put(glob, type);
+<a name="111" href="#111">111</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (previous == type || type.isDescendantOf(previous)) {
+<a name="112" href="#112">112</a> <em class="jxr_comment">// do nothing</em>
+<a name="113" href="#113">113</a> } <strong class="jxr_keyword">else</strong> {
+<a name="114" href="#114">114</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/mime/MimeTypeException.html">MimeTypeException</a>(<span class="jxr_string">"Conflicting glob pattern: "</span> + glob);
+<a name="115" href="#115">115</a> }
+<a name="116" href="#116">116</a> }
+<a name="117" href="#117">117</a>
+<a name="118" href="#118">118</a> <em class="jxr_javadoccomment">/**</em>
+<a name="119" href="#119">119</a> <em class="jxr_javadoccomment"> * Find the MimeType corresponding to a resource name.</em>
+<a name="120" href="#120">120</a> <em class="jxr_javadoccomment"> * </em>
+<a name="121" href="#121">121</a> <em class="jxr_javadoccomment"> * It applies the recommendations detailed in FreeDesktop Shared MIME-info</em>
+<a name="122" href="#122">122</a> <em class="jxr_javadoccomment"> * Database for guessing MimeType from a resource name: It first tries a</em>
+<a name="123" href="#123">123</a> <em class="jxr_javadoccomment"> * case-sensitive match, then try again with the resource name converted to</em>
+<a name="124" href="#124">124</a> <em class="jxr_javadoccomment"> * lower-case if that fails. If several patterns match then the longest</em>
+<a name="125" href="#125">125</a> <em class="jxr_javadoccomment"> * pattern is used. In particular, files with multiple extensions (such as</em>
+<a name="126" href="#126">126</a> <em class="jxr_javadoccomment"> * Data.tar.gz) match the longest sequence of extensions (eg '*.tar.gz' in</em>
+<a name="127" href="#127">127</a> <em class="jxr_javadoccomment"> * preference to '*.gz'). Literal patterns (eg, 'Makefile') are matched</em>
+<a name="128" href="#128">128</a> <em class="jxr_javadoccomment"> * before all others. Patterns beginning with `*.' and containing no other</em>
+<a name="129" href="#129">129</a> <em class="jxr_javadoccomment"> * special characters (`*?[') are matched before other wildcarded patterns</em>
+<a name="130" href="#130">130</a> <em class="jxr_javadoccomment"> * (since this covers the majority of the patterns).</em>
+<a name="131" href="#131">131</a> <em class="jxr_javadoccomment"> */</em>
+<a name="132" href="#132">132</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/mime/MimeType.html">MimeType</a> matches(String name) {
+<a name="133" href="#133">133</a> <strong class="jxr_keyword">if</strong> (name == <strong class="jxr_keyword">null</strong>) {
+<a name="134" href="#134">134</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> IllegalArgumentException(<span class="jxr_string">"Name is missing"</span>);
+<a name="135" href="#135">135</a> }
+<a name="136" href="#136">136</a>
+<a name="137" href="#137">137</a> <em class="jxr_comment">// First, try exact match of the provided resource name</em>
+<a name="138" href="#138">138</a> <strong class="jxr_keyword">if</strong> (names.containsKey(name)) {
+<a name="139" href="#139">139</a> <strong class="jxr_keyword">return</strong> names.get(name);
+<a name="140" href="#140">140</a> }
+<a name="141" href="#141">141</a>
+<a name="142" href="#142">142</a> <em class="jxr_comment">// Then try "extension" (*.xxx) matching</em>
+<a name="143" href="#143">143</a> <strong class="jxr_keyword">int</strong> maxLength = Math.min(maxExtensionLength, name.length());
+<a name="144" href="#144">144</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> n = maxLength; n >= minExtensionLength; n--) {
+<a name="145" href="#145">145</a> String extension = name.substring(name.length() - n);
+<a name="146" href="#146">146</a> <strong class="jxr_keyword">if</strong> (extensions.containsKey(extension)) {
+<a name="147" href="#147">147</a> <strong class="jxr_keyword">return</strong> extensions.get(extension);
+<a name="148" href="#148">148</a> }
+<a name="149" href="#149">149</a> }
+<a name="150" href="#150">150</a>
+<a name="151" href="#151">151</a> <em class="jxr_comment">// And finally, try complex regexp matching</em>
+<a name="152" href="#152">152</a> <strong class="jxr_keyword">for</strong> (Map.Entry<String, MimeType> entry : globs.entrySet()) {
+<a name="153" href="#153">153</a> <strong class="jxr_keyword">if</strong> (name.matches(entry.getKey())) {
+<a name="154" href="#154">154</a> <strong class="jxr_keyword">return</strong> entry.getValue();
+<a name="155" href="#155">155</a> }
+<a name="156" href="#156">156</a> }
+<a name="157" href="#157">157</a>
+<a name="158" href="#158">158</a> <strong class="jxr_keyword">return</strong> <strong class="jxr_keyword">null</strong>;
+<a name="159" href="#159">159</a> }
+<a name="160" href="#160">160</a>
+<a name="161" href="#161">161</a> <strong class="jxr_keyword">private</strong> String compile(String glob) {
+<a name="162" href="#162">162</a> StringBuilder pattern = <strong class="jxr_keyword">new</strong> StringBuilder();
+<a name="163" href="#163">163</a> pattern.append(<span class="jxr_string">"\\A"</span>);
+<a name="164" href="#164">164</a> <strong class="jxr_keyword">for</strong> (<strong class="jxr_keyword">int</strong> i = 0; i < glob.length(); i++) {
+<a name="165" href="#165">165</a> <strong class="jxr_keyword">char</strong> ch = glob.charAt(i);
+<a name="166" href="#166">166</a> <strong class="jxr_keyword">if</strong> (ch == '?') {
+<a name="167" href="#167">167</a> pattern.append('.');
+<a name="168" href="#168">168</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (ch == '*') {
+<a name="169" href="#169">169</a> pattern.append(<span class="jxr_string">".*"</span>);
+<a name="170" href="#170">170</a> } <strong class="jxr_keyword">else</strong> <strong class="jxr_keyword">if</strong> (<span class="jxr_string">"\\[]^.-$+(){}|"</span>.indexOf(ch) != -1) {
+<a name="171" href="#171">171</a> pattern.append('\\');
+<a name="172" href="#172">172</a> pattern.append(ch);
+<a name="173" href="#173">173</a> } <strong class="jxr_keyword">else</strong> {
+<a name="174" href="#174">174</a> pattern.append(ch);
+<a name="175" href="#175">175</a> }
+<a name="176" href="#176">176</a> }
+<a name="177" href="#177">177</a> pattern.append(<span class="jxr_string">"\\z"</span>);
+<a name="178" href="#178">178</a> <strong class="jxr_keyword">return</strong> pattern.toString();
+<a name="179" href="#179">179</a> }
+<a name="180" href="#180">180</a>
+<a name="181" href="#181">181</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>
Modified: incubator/tika/site/xref/org/apache/tika/mime/package-frame.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/mime/package-frame.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/mime/package-frame.html (original)
+++ incubator/tika/site/xref/org/apache/tika/mime/package-frame.html Sun Jan 6 19:06:26 2008
@@ -3,7 +3,7 @@
<html xml:lang="en" lang="en">
<head>
<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1" />
- <title>Apache Tika 0.1-SNAPSHOT Reference Package org.apache.tika.mime</title>
+ <title>Apache Tika 0.2-SNAPSHOT Reference Package org.apache.tika.mime</title>
<link rel="stylesheet" type="text/css" href="../../../../stylesheet.css" title="style" />
</head>
<body>
Modified: incubator/tika/site/xref/org/apache/tika/mime/package-summary.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/mime/package-summary.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/mime/package-summary.html (original)
+++ incubator/tika/site/xref/org/apache/tika/mime/package-summary.html Sun Jan 6 19:06:26 2008
@@ -3,7 +3,7 @@
<html xml:lang="en" lang="en">
<head>
<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1" />
- <title>Apache Tika 0.1-SNAPSHOT Reference Package org.apache.tika.mime</title>
+ <title>Apache Tika 0.2-SNAPSHOT Reference Package org.apache.tika.mime</title>
<link rel="stylesheet" type="text/css" href="../../../../stylesheet.css" title="style" />
</head>
<body>
@@ -142,6 +142,6 @@
</ul>
</div>
<hr />
- Copyright © 2007 The Apache Software Foundation. All Rights Reserved.
+ Copyright © 2008 The Apache Software Foundation. All Rights Reserved.
</body>
</html>
Modified: incubator/tika/site/xref/org/apache/tika/parser/ParserPostProcessor.html
URL: http://svn.apache.org/viewvc/incubator/tika/site/xref/org/apache/tika/parser/ParserPostProcessor.html?rev=609491&r1=609490&r2=609491&view=diff
==============================================================================
--- incubator/tika/site/xref/org/apache/tika/parser/ParserPostProcessor.html (original)
+++ incubator/tika/site/xref/org/apache/tika/parser/ParserPostProcessor.html Sun Jan 6 19:06:26 2008
@@ -30,66 +30,56 @@
<a name="20" href="#20">20</a> <strong class="jxr_keyword">import</strong> java.io.InputStream;
<a name="21" href="#21">21</a> <strong class="jxr_keyword">import</strong> java.io.StringWriter;
<a name="22" href="#22">22</a>
-<a name="23" href="#23">23</a> <strong class="jxr_keyword">import</strong> org.apache.oro.text.regex.MalformedPatternException;
-<a name="24" href="#24">24</a> <strong class="jxr_keyword">import</strong> org.apache.tika.exception.TikaException;
-<a name="25" href="#25">25</a> <strong class="jxr_keyword">import</strong> org.apache.tika.metadata.Metadata;
-<a name="26" href="#26">26</a> <strong class="jxr_keyword">import</strong> org.apache.tika.sax.TeeContentHandler;
-<a name="27" href="#27">27</a> <strong class="jxr_keyword">import</strong> org.apache.tika.sax.WriteOutContentHandler;
-<a name="28" href="#28">28</a> <strong class="jxr_keyword">import</strong> org.apache.tika.utils.RegexUtils;
-<a name="29" href="#29">29</a> <strong class="jxr_keyword">import</strong> org.xml.sax.ContentHandler;
-<a name="30" href="#30">30</a> <strong class="jxr_keyword">import</strong> org.xml.sax.SAXException;
-<a name="31" href="#31">31</a>
-<a name="32" href="#32">32</a> <em class="jxr_javadoccomment">/**</em>
-<a name="33" href="#33">33</a> <em class="jxr_javadoccomment"> * Parser decorator that post-processes the results from a decorated parser.</em>
-<a name="34" href="#34">34</a> <em class="jxr_javadoccomment"> * The post-processing takes care of filling in any "fulltext", "summary", and</em>
-<a name="35" href="#35">35</a> <em class="jxr_javadoccomment"> * regexp {@link Content} objects with the full text content returned by</em>
-<a name="36" href="#36">36</a> <em class="jxr_javadoccomment"> * the decorated parser. The post-processing also catches and logs any</em>
-<a name="37" href="#37">37</a> <em class="jxr_javadoccomment"> * exceptions thrown by the decorated parser.</em>
-<a name="38" href="#38">38</a> <em class="jxr_javadoccomment"> */</em>
-<a name="39" href="#39">39</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">class</strong> <a href="../../../../org/apache/tika/parser/ParserPostProcessor.html">ParserPostProcessor</a> <strong class="jxr_keyword">extends</strong> <a href="../../../../org/apache/tika/parser/ParserDecorator.html">ParserDecorator</a> {
-<a name="40" href="#40">40</a>
-<a name="41" href="#41">41</a> <strong class="jxr_keyword">private</strong> <strong class="jxr_keyword">static</strong> <strong class="jxr_keyword">final</strong> String LINK_PATTERN =
-<a name="42" href="#42">42</a> <span class="jxr_string">"([A-Za-z][A-Za-z0-9+.-]{1,120}:"</span>
-<a name="43" href="#43">43</a> + <span class="jxr_string">"[A-Za-z0-9/](([A-Za-z0-9$_.+!*,;/?:@&~=-])|%[A-Fa-f0-9]{2}){1,333}"</span>
-<a name="44" href="#44">44</a> + <span class="jxr_string">"(#([a-zA-Z0-9][a-zA-Z0-9$_.+!*,;/?:@&~=%-]{0,1000}))?)"</span>;
-<a name="45" href="#45">45</a>
-<a name="46" href="#46">46</a> <em class="jxr_javadoccomment">/**</em>
-<a name="47" href="#47">47</a> <em class="jxr_javadoccomment"> * Creates a post-processing decorator for the given parser.</em>
-<a name="48" href="#48">48</a> <em class="jxr_javadoccomment"> *</em>
-<a name="49" href="#49">49</a> <em class="jxr_javadoccomment"> * @param parser the parser to be decorated</em>
-<a name="50" href="#50">50</a> <em class="jxr_javadoccomment"> */</em>
-<a name="51" href="#51">51</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/parser/ParserPostProcessor.html">ParserPostProcessor</a>(<a href="../../../../org/apache/tika/parser/Parser.html">Parser</a> parser) {
-<a name="52" href="#52">52</a> <strong class="jxr_keyword">super</strong>(parser);
-<a name="53" href="#53">53</a> }
-<a name="54" href="#54">54</a>
-<a name="55" href="#55">55</a> <em class="jxr_javadoccomment">/**</em>
-<a name="56" href="#56">56</a> <em class="jxr_javadoccomment"> * Forwards the call to the delegated parser and post-processes the</em>
-<a name="57" href="#57">57</a> <em class="jxr_javadoccomment"> * results as described above.</em>
-<a name="58" href="#58">58</a> <em class="jxr_javadoccomment"> */</em>
-<a name="59" href="#59">59</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> parse(
-<a name="60" href="#60">60</a> InputStream stream, ContentHandler handler, <a href="../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata)
-<a name="61" href="#61">61</a> <strong class="jxr_keyword">throws</strong> IOException, SAXException, <a href="../../../../org/apache/tika/exception/TikaException.html">TikaException</a> {
-<a name="62" href="#62">62</a> StringWriter writer = <strong class="jxr_keyword">new</strong> StringWriter();
-<a name="63" href="#63">63</a> handler = <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/sax/TeeContentHandler.html">TeeContentHandler</a>(
-<a name="64" href="#64">64</a> handler, <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/sax/WriteOutContentHandler.html">WriteOutContentHandler</a>(writer));
-<a name="65" href="#65">65</a> <strong class="jxr_keyword">super</strong>.parse(stream, handler, metadata);
+<a name="23" href="#23">23</a> <strong class="jxr_keyword">import</strong> org.apache.tika.exception.TikaException;
+<a name="24" href="#24">24</a> <strong class="jxr_keyword">import</strong> org.apache.tika.metadata.Metadata;
+<a name="25" href="#25">25</a> <strong class="jxr_keyword">import</strong> org.apache.tika.sax.TeeContentHandler;
+<a name="26" href="#26">26</a> <strong class="jxr_keyword">import</strong> org.apache.tika.sax.WriteOutContentHandler;
+<a name="27" href="#27">27</a> <strong class="jxr_keyword">import</strong> org.apache.tika.utils.RegexUtils;
+<a name="28" href="#28">28</a> <strong class="jxr_keyword">import</strong> org.xml.sax.ContentHandler;
+<a name="29" href="#29">29</a> <strong class="jxr_keyword">import</strong> org.xml.sax.SAXException;
+<a name="30" href="#30">30</a>
+<a name="31" href="#31">31</a> <em class="jxr_javadoccomment">/**</em>
+<a name="32" href="#32">32</a> <em class="jxr_javadoccomment"> * Parser decorator that post-processes the results from a decorated parser.</em>
+<a name="33" href="#33">33</a> <em class="jxr_javadoccomment"> * The post-processing takes care of filling in any "fulltext", "summary", and</em>
+<a name="34" href="#34">34</a> <em class="jxr_javadoccomment"> * regexp {@link Content} objects with the full text content returned by</em>
+<a name="35" href="#35">35</a> <em class="jxr_javadoccomment"> * the decorated parser. The post-processing also catches and logs any</em>
+<a name="36" href="#36">36</a> <em class="jxr_javadoccomment"> * exceptions thrown by the decorated parser.</em>
+<a name="37" href="#37">37</a> <em class="jxr_javadoccomment"> */</em>
+<a name="38" href="#38">38</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">class</strong> <a href="../../../../org/apache/tika/parser/ParserPostProcessor.html">ParserPostProcessor</a> <strong class="jxr_keyword">extends</strong> <a href="../../../../org/apache/tika/parser/ParserDecorator.html">ParserDecorator</a> {
+<a name="39" href="#39">39</a>
+<a name="40" href="#40">40</a> <em class="jxr_javadoccomment">/**</em>
+<a name="41" href="#41">41</a> <em class="jxr_javadoccomment"> * Creates a post-processing decorator for the given parser.</em>
+<a name="42" href="#42">42</a> <em class="jxr_javadoccomment"> *</em>
+<a name="43" href="#43">43</a> <em class="jxr_javadoccomment"> * @param parser the parser to be decorated</em>
+<a name="44" href="#44">44</a> <em class="jxr_javadoccomment"> */</em>
+<a name="45" href="#45">45</a> <strong class="jxr_keyword">public</strong> <a href="../../../../org/apache/tika/parser/ParserPostProcessor.html">ParserPostProcessor</a>(<a href="../../../../org/apache/tika/parser/Parser.html">Parser</a> parser) {
+<a name="46" href="#46">46</a> <strong class="jxr_keyword">super</strong>(parser);
+<a name="47" href="#47">47</a> }
+<a name="48" href="#48">48</a>
+<a name="49" href="#49">49</a> <em class="jxr_javadoccomment">/**</em>
+<a name="50" href="#50">50</a> <em class="jxr_javadoccomment"> * Forwards the call to the delegated parser and post-processes the</em>
+<a name="51" href="#51">51</a> <em class="jxr_javadoccomment"> * results as described above.</em>
+<a name="52" href="#52">52</a> <em class="jxr_javadoccomment"> */</em>
+<a name="53" href="#53">53</a> <strong class="jxr_keyword">public</strong> <strong class="jxr_keyword">void</strong> parse(
+<a name="54" href="#54">54</a> InputStream stream, ContentHandler handler, <a href="../../../../org/apache/tika/metadata/Metadata.html">Metadata</a> metadata)
+<a name="55" href="#55">55</a> <strong class="jxr_keyword">throws</strong> IOException, SAXException, <a href="../../../../org/apache/tika/exception/TikaException.html">TikaException</a> {
+<a name="56" href="#56">56</a> StringWriter writer = <strong class="jxr_keyword">new</strong> StringWriter();
+<a name="57" href="#57">57</a> handler = <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/sax/TeeContentHandler.html">TeeContentHandler</a>(
+<a name="58" href="#58">58</a> handler, <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/sax/WriteOutContentHandler.html">WriteOutContentHandler</a>(writer));
+<a name="59" href="#59">59</a> <strong class="jxr_keyword">super</strong>.parse(stream, handler, metadata);
+<a name="60" href="#60">60</a>
+<a name="61" href="#61">61</a> String content = writer.toString();
+<a name="62" href="#62">62</a> metadata.set(<span class="jxr_string">"fulltext"</span>, content);
+<a name="63" href="#63">63</a>
+<a name="64" href="#64">64</a> <strong class="jxr_keyword">int</strong> length = Math.min(content.length(), 500);
+<a name="65" href="#65">65</a> metadata.set(<span class="jxr_string">"summary"</span>, content.substring(0, length));
<a name="66" href="#66">66</a>
-<a name="67" href="#67">67</a> String content = writer.toString();
-<a name="68" href="#68">68</a> metadata.set(<span class="jxr_string">"fulltext"</span>, content);
-<a name="69" href="#69">69</a>
-<a name="70" href="#70">70</a> <strong class="jxr_keyword">int</strong> length = Math.min(content.length(), 500);
-<a name="71" href="#71">71</a> metadata.set(<span class="jxr_string">"summary"</span>, content.substring(0, length));
-<a name="72" href="#72">72</a>
-<a name="73" href="#73">73</a> <strong class="jxr_keyword">try</strong> {
-<a name="74" href="#74">74</a> <strong class="jxr_keyword">for</strong> (String link : RegexUtils.extract(content, LINK_PATTERN)) {
-<a name="75" href="#75">75</a> metadata.add(<span class="jxr_string">"outlinks"</span>, link);
-<a name="76" href="#76">76</a> }
-<a name="77" href="#77">77</a> } <strong class="jxr_keyword">catch</strong> (MalformedPatternException e) {
-<a name="78" href="#78">78</a> <strong class="jxr_keyword">throw</strong> <strong class="jxr_keyword">new</strong> <a href="../../../../org/apache/tika/exception/TikaException.html">TikaException</a>(<span class="jxr_string">"Malformed URL pattern"</span>, e);
-<a name="79" href="#79">79</a> }
-<a name="80" href="#80">80</a> }
-<a name="81" href="#81">81</a>
-<a name="82" href="#82">82</a> }
+<a name="67" href="#67">67</a> <strong class="jxr_keyword">for</strong> (String link : RegexUtils.extractLinks(content)) {
+<a name="68" href="#68">68</a> metadata.add(<span class="jxr_string">"outlinks"</span>, link);
+<a name="69" href="#69">69</a> }
+<a name="70" href="#70">70</a> }
+<a name="71" href="#71">71</a>
+<a name="72" href="#72">72</a> }
</pre>
<hr/><div id="footer">This page was automatically generated by <a href="http://maven.apache.org/">Maven</a></div></body>
</html>