Modified: tika/site/publish/1.7/examples.html URL: http://svn.apache.org/viewvc/tika/site/publish/1.7/examples.html?rev=1651638&r1=1651637&r2=1651638&view=diff ============================================================================== --- tika/site/publish/1.7/examples.html (original) +++ tika/site/publish/1.7/examples.html Wed Jan 14 12:25:49 2015 @@ -115,41 +115,41 @@ <p>The <a href="./apidocs/org/apache/tika/Tika.html">Tika facade</a>, provides a number of very quick and easy ways to have your content parsed by Tika, and return the resulting plain text</p><style type="text/css"> @import url('attached-includes/css/shCoreDefault.css'); </style> -<div id="highlighter_355685" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number37 index0 alt2"><code class="java keyword">public</code> <code class="java plain">String parseToStringExample() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number38 index1 alt1"><code class="java spaces"> </code><code class="java plain">InputStream stream = ParsingExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test.doc"</code><code class="java plain">);</code></div><div class="line number39 index2 alt2"><code class="java spaces"> </code><code class="java plain">Tika tika = </code><code class="java keyword">new</code> <code class="java plain">Tika();</code></div>< div class="line number40 index3 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number41 index4 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">tika.parseToString(stream);</code></div><div class="line number42 index5 alt1"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number43 index6 alt2"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number44 index7 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number45 index8 alt2"><code class="java plain">}</code></div></ div></td></tr></tbody></table></div></div> +<div id="highlighter_623484" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number37 index0 alt2"><code class="java keyword">public</code> <code class="java plain">String parseToStringExample() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number38 index1 alt1"><code class="java spaces"> </code><code class="java plain">InputStream stream = ParsingExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test.doc"</code><code class="java plain">);</code></div><div class="line number39 index2 alt2"><code class="java spaces"> </code><code class="java plain">Tika tika = </code><code class="java keyword">new</code> <code class="java plain">Tika();</code></div>< div class="line number40 index3 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number41 index4 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">tika.parseToString(stream);</code></div><div class="line number42 index5 alt1"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number43 index6 alt2"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number44 index7 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number45 index8 alt2"><code class="java plain">}</code></div></ div></td></tr></tbody></table></div></div> <div class="section"> <h4><a name="Parsing_using_the_Auto-Detect_Parser">Parsing using the Auto-Detect Parser</a></h4> -<p>For more control, you can call the <a href="./apidocs/org/apache/tika/parser/Parser.html">Tika Parsers</a> directly. Most likely, you'll want to start out using the <a href="./apidocs/org/apache/tika/parser/AutoDetectParser.html">Auto-Detect Parser</a>, which automatically figures out what kind of content you have, then calls the appropriate parser for you.</p><div id="highlighter_870950" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number66 index0 alt1"><code class="java keyword">public</code> <code class="java plain">String parseExample() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number67 index1 alt2"><code class="java spaces"> </code><code class="java plain">InputStream stream = ParsingExample.</code><code class="java keyword">class</code><c ode class="java plain">.getResourceAsStream(</code><code class="java string">"test.doc"</code><code class="java plain">);</code></div><div class="line number68 index2 alt1"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number69 index3 alt2"><code class="java spaces"> </code><code class="java plain">BodyContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">BodyContentHandler();</code></div><div class="line number70 index4 alt1"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number71 index5 alt2"><code class="java spaces"> </code><code class="java keyword">tr y</code> <code class="java plain">{</code></div><div class="line number72 index6 alt1"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number73 index7 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number74 index8 alt1"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number75 index9 alt2"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number76 index10 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="l ine number77 index11 alt2"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div></div> +<p>For more control, you can call the <a href="./apidocs/org/apache/tika/parser/Parser.html">Tika Parsers</a> directly. Most likely, you'll want to start out using the <a href="./apidocs/org/apache/tika/parser/AutoDetectParser.html">Auto-Detect Parser</a>, which automatically figures out what kind of content you have, then calls the appropriate parser for you.</p><div id="highlighter_542339" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number66 index0 alt1"><code class="java keyword">public</code> <code class="java plain">String parseExample() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number67 index1 alt2"><code class="java spaces"> </code><code class="java plain">InputStream stream = ParsingExample.</code><code class="java keyword">class</code><c ode class="java plain">.getResourceAsStream(</code><code class="java string">"test.doc"</code><code class="java plain">);</code></div><div class="line number68 index2 alt1"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number69 index3 alt2"><code class="java spaces"> </code><code class="java plain">BodyContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">BodyContentHandler();</code></div><div class="line number70 index4 alt1"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number71 index5 alt2"><code class="java spaces"> </code><code class="java keyword">tr y</code> <code class="java plain">{</code></div><div class="line number72 index6 alt1"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number73 index7 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number74 index8 alt1"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number75 index9 alt2"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number76 index10 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="l ine number77 index11 alt2"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div></div> <div class="section"> <h3><a name="Picking_different_output_formats">Picking different output formats</a></h3> <p>With Tika, you can get the textual content of your files returned in a number of different formats. These can be plain text, html, xhtml, xhtml of one part of the file etc. This is controlled based on the <a class="externalLink" href="http://docs.oracle.com/javase/7/docs/api/org/xml/sax/ContentHandler.html";>ContentHandler</a> you supply to the Parser.</p> <div class="section"> <h4><a name="Parsing_to_Plain_Text">Parsing to Plain Text</a></h4> -<p>By using the <a href="./apidocs/org/apache/tika/sax/BodyContentHandler.html">BodyContentHandler</a>, you can request that Tika return only the content of the document's body as a plain-text string.</p><div id="highlighter_21206" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number46 index0 alt1"><code class="java keyword">public</code> <code class="java plain">String parseToPlainText() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number47 index1 alt2"><code class="java spaces"> </code><code class="java plain">BodyContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">BodyContentHandler();</code></div><div class="line number48 index2 alt1"><code class="java spaces"> </code> </div><d iv class="line number49 index3 alt2"><code class="java spaces"> </code><code class="java plain">InputStream stream = ContentHandlerExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test.doc"</code><code class="java plain">);</code></div><div class="line number50 index4 alt1"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number51 index5 alt2"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number52 index6 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></ div><div class="line number53 index7 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number54 index8 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number55 index9 alt2"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number56 index10 alt1"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number57 index11 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number58 index12 alt1"><code class="jav a plain">}</code></div></div></td></tr></tbody></table></div></div> +<p>By using the <a href="./apidocs/org/apache/tika/sax/BodyContentHandler.html">BodyContentHandler</a>, you can request that Tika return only the content of the document's body as a plain-text string.</p><div id="highlighter_923362" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number46 index0 alt1"><code class="java keyword">public</code> <code class="java plain">String parseToPlainText() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number47 index1 alt2"><code class="java spaces"> </code><code class="java plain">BodyContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">BodyContentHandler();</code></div><div class="line number48 index2 alt1"><code class="java spaces"> </code> </div>< div class="line number49 index3 alt2"><code class="java spaces"> </code><code class="java plain">InputStream stream = ContentHandlerExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test.doc"</code><code class="java plain">);</code></div><div class="line number50 index4 alt1"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number51 index5 alt2"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number52 index6 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code>< /div><div class="line number53 index7 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number54 index8 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number55 index9 alt2"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number56 index10 alt1"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number57 index11 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number58 index12 alt1"><code class="ja va plain">}</code></div></div></td></tr></tbody></table></div></div> <div class="section"> <h4><a name="Parsing_to_XHTML">Parsing to XHTML</a></h4> -<p>By using the <a href="./apidocs/org/apache/tika/sax/ToXMLContentHandler.html">ToXMLContentHandler</a>, you can get the XHTML content of the whole document as a string.</p><div id="highlighter_109231" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number63 index0 alt2"><code class="java keyword">public</code> <code class="java plain">String parseToHTML() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number64 index1 alt1"><code class="java spaces"> </code><code class="java plain">ContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">ToXMLContentHandler();</code></div><div class="line number65 index2 alt2"><code class="java spaces"> </code> </div><div class="line number66 index3 alt1"> <code class="java spaces"> </code><code class="java plain">InputStream stream = ContentHandlerExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test.doc"</code><code class="java plain">);</code></div><div class="line number67 index4 alt2"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number68 index5 alt1"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number69 index6 alt2"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number70 index7 alt1"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number71 index8 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number72 index9 alt1"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number73 index10 alt2"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number74 index11 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number75 index12 alt2"><code class="java plain">}</code></div></div></td></t r></tbody></table></div> -<p>If you just want the body of the xhtml document, without the header, you can chain together a <a href="./apidocs/org/apache/tika/sax/BodyContentHandler.html">BodyContentHandler</a> and a <a href="./apidocs/org/apache/tika/sax/ToXMLContentHandler.html">ToXMLContentHandler</a> as shown:</p><div id="highlighter_401330" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number81 index0 alt2"><code class="java keyword">public</code> <code class="java plain">String parseBodyToHTML() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number82 index1 alt1"><code class="java spaces"> </code><code class="java plain">ContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">BodyContentHandler(</code></div><div class="line number83 in dex2 alt2"><code class="java spaces"> </code><code class="java keyword">new</code> <code class="java plain">ToXMLContentHandler());</code></div><div class="line number84 index3 alt1"><code class="java spaces"> </code> </div><div class="line number85 index4 alt2"><code class="java spaces"> </code><code class="java plain">InputStream stream = ContentHandlerExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test.doc"</code><code class="java plain">);</code></div><div class="line number86 index5 alt1"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number87 index6 alt2"><code class="java spaces"> &n bsp; </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number88 index7 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number89 index8 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number90 index9 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number91 index10 alt2"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number92 index11 alt1"> <code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number93 index12 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number94 index13 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div> +<p>By using the <a href="./apidocs/org/apache/tika/sax/ToXMLContentHandler.html">ToXMLContentHandler</a>, you can get the XHTML content of the whole document as a string.</p><div id="highlighter_283484" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number63 index0 alt2"><code class="java keyword">public</code> <code class="java plain">String parseToHTML() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number64 index1 alt1"><code class="java spaces"> </code><code class="java plain">ContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">ToXMLContentHandler();</code></div><div class="line number65 index2 alt2"><code class="java spaces"> </code> </div><div class="line number66 index3 alt1"> <code class="java spaces"> </code><code class="java plain">InputStream stream = ContentHandlerExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test.doc"</code><code class="java plain">);</code></div><div class="line number67 index4 alt2"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number68 index5 alt1"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number69 index6 alt2"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number70 index7 alt1"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number71 index8 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number72 index9 alt1"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number73 index10 alt2"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number74 index11 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number75 index12 alt2"><code class="java plain">}</code></div></div></td></t r></tbody></table></div> +<p>If you just want the body of the xhtml document, without the header, you can chain together a <a href="./apidocs/org/apache/tika/sax/BodyContentHandler.html">BodyContentHandler</a> and a <a href="./apidocs/org/apache/tika/sax/ToXMLContentHandler.html">ToXMLContentHandler</a> as shown:</p><div id="highlighter_541873" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number81 index0 alt2"><code class="java keyword">public</code> <code class="java plain">String parseBodyToHTML() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number82 index1 alt1"><code class="java spaces"> </code><code class="java plain">ContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">BodyContentHandler(</code></div><div class="line number83 in dex2 alt2"><code class="java spaces"> </code><code class="java keyword">new</code> <code class="java plain">ToXMLContentHandler());</code></div><div class="line number84 index3 alt1"><code class="java spaces"> </code> </div><div class="line number85 index4 alt2"><code class="java spaces"> </code><code class="java plain">InputStream stream = ContentHandlerExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test.doc"</code><code class="java plain">);</code></div><div class="line number86 index5 alt1"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number87 index6 alt2"><code class="java spaces"> &n bsp; </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number88 index7 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number89 index8 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number90 index9 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number91 index10 alt2"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number92 index11 alt1"> <code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number93 index12 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number94 index13 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div> <div class="section"> <h4><a name="Fetching_just_certain_bits_of_the_XHTML">Fetching just certain bits of the XHTML</a></h4> -<p>It possible to execute XPath queries on the parse results, to fetch only certain bits of the XHTML. </p><div id="highlighter_942650" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number100 index0 alt1"><code class="java keyword">public</code> <code class="java plain">String parseOnePartToHTML() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number101 index1 alt2"><code class="java spaces"> </code><code class="java comments">// Only get things under html -> body -> div (class=header)</code></div><div class="line number102 index2 alt1"><code class="java spaces"> </code><code class="java plain">XPathParser xhtmlParser = </code><code class="java keyword">new</code> <code class="java plain">XPathParser(</code><code class="java strin g">"xhtml"</code><code class="java plain">, XHTMLContentHandler.XHTML);</code></div><div class="line number103 index3 alt2"><code class="java spaces"> </code><code class="java plain">Matcher divContentMatcher = xhtmlParser.parse(</code></div><div class="line number104 index4 alt1"><code class="java spaces"> </code><code class="java string">"/xhtml:html/xhtml:body/xhtml:div/descendant::node()"</code><code class="java plain">); </code></div><div class="line number105 index5 alt2"><code class="java spaces"> </code><code class="java plain">ContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">MatchingContentHandler(</code></div><div class="line number106 index6 alt1"><code class="java spaces"> </code><code class="java ke yword">new</code> <code class="java plain">ToXMLContentHandler(), divContentMatcher);</code></div><div class="line number107 index7 alt2"><code class="java spaces"> </code> </div><div class="line number108 index8 alt1"><code class="java spaces"> </code><code class="java plain">InputStream stream = ContentHandlerExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test2.doc"</code><code class="java plain">);</code></div><div class="line number109 index9 alt2"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number110 index10 alt1"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <cod e class="java plain">Metadata();</code></div><div class="line number111 index11 alt2"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number112 index12 alt1"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number113 index13 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number114 index14 alt1"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number115 index15 alt2"><code class="java spaces"> </code><code class="java plai n">stream.close();</code></div><div class="line number116 index16 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number117 index17 alt2"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div></div> +<p>It possible to execute XPath queries on the parse results, to fetch only certain bits of the XHTML. </p><div id="highlighter_571894" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number100 index0 alt1"><code class="java keyword">public</code> <code class="java plain">String parseOnePartToHTML() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number101 index1 alt2"><code class="java spaces"> </code><code class="java comments">// Only get things under html -> body -> div (class=header)</code></div><div class="line number102 index2 alt1"><code class="java spaces"> </code><code class="java plain">XPathParser xhtmlParser = </code><code class="java keyword">new</code> <code class="java plain">XPathParser(</code><code class="java strin g">"xhtml"</code><code class="java plain">, XHTMLContentHandler.XHTML);</code></div><div class="line number103 index3 alt2"><code class="java spaces"> </code><code class="java plain">Matcher divContentMatcher = xhtmlParser.parse(</code></div><div class="line number104 index4 alt1"><code class="java spaces"> </code><code class="java string">"/xhtml:html/xhtml:body/xhtml:div/descendant::node()"</code><code class="java plain">); </code></div><div class="line number105 index5 alt2"><code class="java spaces"> </code><code class="java plain">ContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">MatchingContentHandler(</code></div><div class="line number106 index6 alt1"><code class="java spaces"> </code><code class="java ke yword">new</code> <code class="java plain">ToXMLContentHandler(), divContentMatcher);</code></div><div class="line number107 index7 alt2"><code class="java spaces"> </code> </div><div class="line number108 index8 alt1"><code class="java spaces"> </code><code class="java plain">InputStream stream = ContentHandlerExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test2.doc"</code><code class="java plain">);</code></div><div class="line number109 index9 alt2"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number110 index10 alt1"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <cod e class="java plain">Metadata();</code></div><div class="line number111 index11 alt2"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number112 index12 alt1"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number113 index13 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number114 index14 alt1"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number115 index15 alt2"><code class="java spaces"> </code><code class="java plai n">stream.close();</code></div><div class="line number116 index16 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number117 index17 alt2"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div></div> <div class="section"> <h3><a name="Custom_Content_Handlers">Custom Content Handlers</a></h3> <p>The textual output of parsing a file with Tika is returned via the SAX <a class="externalLink" href="http://docs.oracle.com/javase/7/docs/api/org/xml/sax/ContentHandler.html";>ContentHandler</a> you pass to the parse method. It is possible to customise your parsing by supplying your own ContentHandler which does special things.</p> <div class="section"> <h4><a name="Extract_Phone_Numbers_from_Content_into_the_Metadata">Extract Phone Numbers from Content into the Metadata</a></h4> -<p>By using the <a href="./apidocs/org/apache/tika/sax/PhoneExtractingContentHandler.html">PhoneExtractingContentHandler</a>, you can have any phone numbers found in the textual content of the document extracted and placed into the Metadata object for you.</p><div id="highlighter_314119" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number69 index0 alt2"><code class="java keyword">public</code> <code class="java keyword">static</code> <code class="java keyword">void</code> <code class="java plain">process(File file) </code><code class="java keyword">throws</code> <code class="java plain">Exception {</code></div><div class="line number70 index1 alt1"><code class="java spaces"> </code><code class="java plain">Parser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number71 index2 alt2"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number72 index3 alt1"><code class="java spaces"> </code><code class="java comments">// The PhoneExtractingContentHandler will examine any characters for phone numbers before passing them</code></div><div class="line number73 index4 alt2"><code class="java spaces"> </code><code class="java comments">// to the underlying Handler.</code></div><div class="line number74 index5 alt1"><code class="java spaces"> </code><code class="java plain">PhoneExtractingContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">PhoneExtractingContentHandler(</code><code class="java keyword">new</code> <code class="java plain">BodyContentHandler(), metadata);</code></div><div cl ass="line number75 index6 alt2"><code class="java spaces"> </code><code class="java plain">InputStream stream = </code><code class="java keyword">new</code> <code class="java plain">FileInputStream(file);</code></div><div class="line number76 index7 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number77 index8 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata, </code><code class="java keyword">new</code> <code class="java plain">ParseContext());</code></div><div class="line number78 index9 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number79 index10 alt2"><code class="java spaces"> </code><code class="java keyword">finally</code> <code class="java plain">{ </code></div><div class="line number80 index11 alt1"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number81 index12 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number82 index13 alt1"><code class="java spaces"> </code><code class="java plain">String[] numbers = metadata.getValues(</code><code class="java string">"phonenumbers"</code><code class="java plain">);</code></div><div class="line number83 index14 alt2"><code class="java spaces"> </code><code class="java keyword">for</code> <code class="java plain">(String number : numbers) {</code></div><div class="line number84 index15 alt1"><code class="java spaces"> </code><code class="java plain">phoneNumbers.add(number);</code></div><div class="line number85 index16 al t2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number86 index17 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div> +<p>By using the <a href="./apidocs/org/apache/tika/sax/PhoneExtractingContentHandler.html">PhoneExtractingContentHandler</a>, you can have any phone numbers found in the textual content of the document extracted and placed into the Metadata object for you.</p><div id="highlighter_437812" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number69 index0 alt2"><code class="java keyword">public</code> <code class="java keyword">static</code> <code class="java keyword">void</code> <code class="java plain">process(File file) </code><code class="java keyword">throws</code> <code class="java plain">Exception {</code></div><div class="line number70 index1 alt1"><code class="java spaces"> </code><code class="java plain">Parser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number71 index2 alt2"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number72 index3 alt1"><code class="java spaces"> </code><code class="java comments">// The PhoneExtractingContentHandler will examine any characters for phone numbers before passing them</code></div><div class="line number73 index4 alt2"><code class="java spaces"> </code><code class="java comments">// to the underlying Handler.</code></div><div class="line number74 index5 alt1"><code class="java spaces"> </code><code class="java plain">PhoneExtractingContentHandler handler = </code><code class="java keyword">new</code> <code class="java plain">PhoneExtractingContentHandler(</code><code class="java keyword">new</code> <code class="java plain">BodyContentHandler(), metadata);</code></div><div cl ass="line number75 index6 alt2"><code class="java spaces"> </code><code class="java plain">InputStream stream = </code><code class="java keyword">new</code> <code class="java plain">FileInputStream(file);</code></div><div class="line number76 index7 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number77 index8 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata, </code><code class="java keyword">new</code> <code class="java plain">ParseContext());</code></div><div class="line number78 index9 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number79 index10 alt2"><code class="java spaces"> </code><code class="java keyword">finally</code> <code class="java plain">{ </code></div><div class="line number80 index11 alt1"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number81 index12 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number82 index13 alt1"><code class="java spaces"> </code><code class="java plain">String[] numbers = metadata.getValues(</code><code class="java string">"phonenumbers"</code><code class="java plain">);</code></div><div class="line number83 index14 alt2"><code class="java spaces"> </code><code class="java keyword">for</code> <code class="java plain">(String number : numbers) {</code></div><div class="line number84 index15 alt1"><code class="java spaces"> </code><code class="java plain">phoneNumbers.add(number);</code></div><div class="line number85 index16 al t2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number86 index17 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div> <div class="section"> <h4><a name="Streaming_the_plain_text_in_chunks">Streaming the plain text in chunks</a></h4> -<p>Sometimes, you want to chunk the resulting text up, perhaps to output as you go minimising memory use, perhaps to output to HDFS files, or any other reason! With a small custom content handler, you can do that.</p><div id="highlighter_819345" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number124 index0 alt1"><code class="java keyword">public</code> <code class="java plain">List<String> parseToPlainTextChunks() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number125 index1 alt2"><code class="java spaces"> </code><code class="java keyword">final</code> <code class="java plain">List<String> chunks = </code><code class="java keyword">new</code> <code class="java plain">ArrayList<String>();</code></div><div class="line number126 index2 alt1">< code class="java spaces"> </code><code class="java plain">chunks.add(</code><code class="java string">""</code><code class="java plain">);</code></div><div class="line number127 index3 alt2"><code class="java spaces"> </code><code class="java plain">ContentHandlerDecorator handler = </code><code class="java keyword">new</code> <code class="java plain">ContentHandlerDecorator() {</code></div><div class="line number128 index4 alt1"><code class="java spaces"> </code><code class="java color1">@Override</code></div><div class="line number129 index5 alt2"><code class="java spaces"> </code><code class="java keyword">public</code> <code class="java keyword">void</code> <code class="java plain">characters(</code><code class="java keyword">char</code><code class="java plain">[] ch, </code><code class="java keyword">int</code> <code class="java plain">star t, </code><code class="java keyword">int</code> <code class="java plain">length) {</code></div><div class="line number130 index6 alt1"><code class="java spaces"> </code><code class="java plain">String lastChunk = chunks.get(chunks.size()-</code><code class="java value">1</code><code class="java plain">);</code></div><div class="line number131 index7 alt2"><code class="java spaces"> </code><code class="java plain">String thisStr = </code><code class="java keyword">new</code> <code class="java plain">String(ch, start, length);</code></div><div class="line number132 index8 alt1"><code class="java spaces"> </code> </div><div class="line number133 index9 alt2"><code class="java spaces"> </code><code clas s="java keyword">if</code> <code class="java plain">(lastChunk.length()+length > MAXIMUM_TEXT_CHUNK_SIZE) {</code></div><div class="line number134 index10 alt1"><code class="java spaces"> </code><code class="java plain">chunks.add(thisStr);</code></div><div class="line number135 index11 alt2"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">else</code> <code class="java plain">{</code></div><div class="line number136 index12 alt1"><code class="java spaces"> </code><code class="java plain">chunks.set(chunks.size()-</code><code class="java value">1</code><code class="java plain">, lastChunk+thisStr);</code></div><div class="line number137 index13 alt2"><code class="java spaces">  ; </code><code class="java plain">}</code></div><div class="line number138 index14 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number139 index15 alt2"><code class="java spaces"> </code><code class="java plain">};</code></div><div class="line number140 index16 alt1"><code class="java spaces"> </code> </div><div class="line number141 index17 alt2"><code class="java spaces"> </code><code class="java plain">InputStream stream = ContentHandlerExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test2.doc"</code><code class="java plain">);</code></div><div class="line number142 index18 alt1"><code class="java spaces"> </code><code class="java plain">Aut oDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number143 index19 alt2"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number144 index20 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number145 index21 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number146 index22 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">chunks;</code></div><div class="line number147 index23 alt2"><code class ="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number148 index24 alt1"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number149 index25 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number150 index26 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div></div> +<p>Sometimes, you want to chunk the resulting text up, perhaps to output as you go minimising memory use, perhaps to output to HDFS files, or any other reason! With a small custom content handler, you can do that.</p><div id="highlighter_115126" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number124 index0 alt1"><code class="java keyword">public</code> <code class="java plain">List<String> parseToPlainTextChunks() </code><code class="java keyword">throws</code> <code class="java plain">IOException, SAXException, TikaException {</code></div><div class="line number125 index1 alt2"><code class="java spaces"> </code><code class="java keyword">final</code> <code class="java plain">List<String> chunks = </code><code class="java keyword">new</code> <code class="java plain">ArrayList<String>();</code></div><div class="line number126 index2 alt1">< code class="java spaces"> </code><code class="java plain">chunks.add(</code><code class="java string">""</code><code class="java plain">);</code></div><div class="line number127 index3 alt2"><code class="java spaces"> </code><code class="java plain">ContentHandlerDecorator handler = </code><code class="java keyword">new</code> <code class="java plain">ContentHandlerDecorator() {</code></div><div class="line number128 index4 alt1"><code class="java spaces"> </code><code class="java color1">@Override</code></div><div class="line number129 index5 alt2"><code class="java spaces"> </code><code class="java keyword">public</code> <code class="java keyword">void</code> <code class="java plain">characters(</code><code class="java keyword">char</code><code class="java plain">[] ch, </code><code class="java keyword">int</code> <code class="java plain">star t, </code><code class="java keyword">int</code> <code class="java plain">length) {</code></div><div class="line number130 index6 alt1"><code class="java spaces"> </code><code class="java plain">String lastChunk = chunks.get(chunks.size()-</code><code class="java value">1</code><code class="java plain">);</code></div><div class="line number131 index7 alt2"><code class="java spaces"> </code><code class="java plain">String thisStr = </code><code class="java keyword">new</code> <code class="java plain">String(ch, start, length);</code></div><div class="line number132 index8 alt1"><code class="java spaces"> </code> </div><div class="line number133 index9 alt2"><code class="java spaces"> </code><code clas s="java keyword">if</code> <code class="java plain">(lastChunk.length()+length > MAXIMUM_TEXT_CHUNK_SIZE) {</code></div><div class="line number134 index10 alt1"><code class="java spaces"> </code><code class="java plain">chunks.add(thisStr);</code></div><div class="line number135 index11 alt2"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">else</code> <code class="java plain">{</code></div><div class="line number136 index12 alt1"><code class="java spaces"> </code><code class="java plain">chunks.set(chunks.size()-</code><code class="java value">1</code><code class="java plain">, lastChunk+thisStr);</code></div><div class="line number137 index13 alt2"><code class="java spaces">  ; </code><code class="java plain">}</code></div><div class="line number138 index14 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number139 index15 alt2"><code class="java spaces"> </code><code class="java plain">};</code></div><div class="line number140 index16 alt1"><code class="java spaces"> </code> </div><div class="line number141 index17 alt2"><code class="java spaces"> </code><code class="java plain">InputStream stream = ContentHandlerExample.</code><code class="java keyword">class</code><code class="java plain">.getResourceAsStream(</code><code class="java string">"test2.doc"</code><code class="java plain">);</code></div><div class="line number142 index18 alt1"><code class="java spaces"> </code><code class="java plain">Aut oDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number143 index19 alt2"><code class="java spaces"> </code><code class="java plain">Metadata metadata = </code><code class="java keyword">new</code> <code class="java plain">Metadata();</code></div><div class="line number144 index20 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number145 index21 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number146 index22 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">chunks;</code></div><div class="line number147 index23 alt2"><code class ="java spaces"> </code><code class="java plain">} </code><code class="java keyword">finally</code> <code class="java plain">{</code></div><div class="line number148 index24 alt1"><code class="java spaces"> </code><code class="java plain">stream.close();</code></div><div class="line number149 index25 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number150 index26 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div></div> <div class="section"> <h3><a name="Translation">Translation</a></h3> <p>Tika provides a pluggable Translation system, which allow you to send the results of parsing off to an external system or program to have the text translated into another language.</p> <div class="section"> <h4><a name="Translation_using_the_Microsoft_Translation_API">Translation using the Microsoft Translation API</a></h4> -<p>In order to use the Microsoft Translation API, you need to sign up for a Microsoft account, get an API key, then pass the key to Tika before translating.</p><div id="highlighter_318159" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number23 index0 alt2"><code class="java keyword">public</code> <code class="java plain">String microsoftTranslateToFrench(String text) {</code></div><div class="line number24 index1 alt1"><code class="java spaces"> </code><code class="java plain">MicrosoftTranslator translator = </code><code class="java keyword">new</code> <code class="java plain">MicrosoftTranslator();</code></div><div class="line number25 index2 alt2"><code class="java spaces"> </code><code class="java comments">// Change the id and secret! See <a href="http://msdn.microsoft.com/en-us/library/hh454950.aspx.";>http://msdn.microso ft.com/en-us/library/hh454950.aspx.</a></code></div><div class="line number26 index3 alt1"><code class="java spaces"> </code><code class="java plain">translator.setId(</code><code class="java string">"dummy-id"</code><code class="java plain">);</code></div><div class="line number27 index4 alt2"><code class="java spaces"> </code><code class="java plain">translator.setSecret(</code><code class="java string">"dummy-secret"</code><code class="java plain">);</code></div><div class="line number28 index5 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number29 index6 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">translator.translate(text, </code><code class="java string">"fr"</code><code class="java plain">);</code></div><div class= "line number30 index7 alt1"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">catch</code> <code class="java plain">(Exception e) {</code></div><div class="line number31 index8 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java string">"Error while translating."</code><code class="java plain">;</code></div><div class="line number32 index9 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number33 index10 alt2"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div></div> +<p>In order to use the Microsoft Translation API, you need to sign up for a Microsoft account, get an API key, then pass the key to Tika before translating.</p><div id="highlighter_401204" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number23 index0 alt2"><code class="java keyword">public</code> <code class="java plain">String microsoftTranslateToFrench(String text) {</code></div><div class="line number24 index1 alt1"><code class="java spaces"> </code><code class="java plain">MicrosoftTranslator translator = </code><code class="java keyword">new</code> <code class="java plain">MicrosoftTranslator();</code></div><div class="line number25 index2 alt2"><code class="java spaces"> </code><code class="java comments">// Change the id and secret! See <a href="http://msdn.microsoft.com/en-us/library/hh454950.aspx.";>http://msdn.microso ft.com/en-us/library/hh454950.aspx.</a></code></div><div class="line number26 index3 alt1"><code class="java spaces"> </code><code class="java plain">translator.setId(</code><code class="java string">"dummy-id"</code><code class="java plain">);</code></div><div class="line number27 index4 alt2"><code class="java spaces"> </code><code class="java plain">translator.setSecret(</code><code class="java string">"dummy-secret"</code><code class="java plain">);</code></div><div class="line number28 index5 alt1"><code class="java spaces"> </code><code class="java keyword">try</code> <code class="java plain">{</code></div><div class="line number29 index6 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">translator.translate(text, </code><code class="java string">"fr"</code><code class="java plain">);</code></div><div class= "line number30 index7 alt1"><code class="java spaces"> </code><code class="java plain">} </code><code class="java keyword">catch</code> <code class="java plain">(Exception e) {</code></div><div class="line number31 index8 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java string">"Error while translating."</code><code class="java plain">;</code></div><div class="line number32 index9 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number33 index10 alt2"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div></div> <div class="section"> <h3><a name="Language_Identification">Language Identification</a></h3> -<p>Tika provides support for identifying the language of text, through the <a href="./apidocs/org/apache/tika/language/LanguageIdentifier.html">LanguageIdentifier</a> class.</p><div id="highlighter_471964" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number23 index0 alt2"><code class="java keyword">public</code> <code class="java plain">String identifyLanguage(String text) {</code></div><div class="line number24 index1 alt1"><code class="java spaces"> </code><code class="java plain">LanguageIdentifier identifier = </code><code class="java keyword">new</code> <code class="java plain">LanguageIdentifier(text);</code></div><div class="line number25 index2 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">identifier.getLanguage();</code></div><div class="line number26 index3 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div></div> +<p>Tika provides support for identifying the language of text, through the <a href="./apidocs/org/apache/tika/language/LanguageIdentifier.html">LanguageIdentifier</a> class.</p><div id="highlighter_707425" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number23 index0 alt2"><code class="java keyword">public</code> <code class="java plain">String identifyLanguage(String text) {</code></div><div class="line number24 index1 alt1"><code class="java spaces"> </code><code class="java plain">LanguageIdentifier identifier = </code><code class="java keyword">new</code> <code class="java plain">LanguageIdentifier(text);</code></div><div class="line number25 index2 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">identifier.getLanguage();</code></div><div class="line number26 index3 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div></div> </div> <div id="sidebar"> <div id="navigation"> @@ -332,7 +332,7 @@ </div> <div id="footer"> <p> - Copyright © 2014 + Copyright © 2015 <a href="http://www.apache.org/";>The Apache Software Foundation</a>. Site powered by <a href="http://maven.apache.org/";>Apache Maven</a>. Search powered by
Modified: tika/site/publish/1.7/formats.html URL: http://svn.apache.org/viewvc/tika/site/publish/1.7/formats.html?rev=1651638&r1=1651637&r2=1651638&view=diff ============================================================================== --- tika/site/publish/1.7/formats.html (original) +++ tika/site/publish/1.7/formats.html Wed Jan 14 12:25:49 2015 @@ -194,7 +194,390 @@ <p>The <a href="./api/org/apache/tika/parser/crypto/Pkcs7Parser.html">Pkcs7Parser</a> is able to parse the contents of PKCS7 signed messages, but doesn't include any information from the outer PKCS7 wrapper.</p></div></div> <div class="section"> <h2>Full list of supported formats:<a name="Full_list_of_supported_formats:"></a></h2> -<p>TODO Populate this at release time</p></div> +<ul> +<li>org.apache.tika.parser.asm.<a href="./api/org/apache/tika/parser/asm/ClassParser">ClassParser</a> +<ul> +<li>application/java-vm</li></ul></li> +<li>org.apache.tika.parser.audio.<a href="./api/org/apache/tika/parser/audio/AudioParser">AudioParser</a> +<ul> +<li>audio/x-wav</li> +<li>audio/x-aiff</li> +<li>audio/basic</li></ul></li> +<li>org.apache.tika.parser.audio.<a href="./api/org/apache/tika/parser/audio/MidiParser">MidiParser</a> +<ul> +<li>application/x-midi</li> +<li>audio/midi</li></ul></li> +<li>org.apache.tika.parser.chm.<a href="./api/org/apache/tika/parser/chm/ChmParser">ChmParser</a> +<ul> +<li>application/vnd.ms-htmlhelp</li> +<li>application/chm</li> +<li>application/x-chm</li></ul></li> +<li>org.apache.tika.parser.code.<a href="./api/org/apache/tika/parser/code/SourceCodeParser">SourceCodeParser</a> +<ul> +<li>text/x-java-source</li> +<li>text/x-c++src</li> +<li>text/x-groovy</li></ul></li> +<li>org.apache.tika.parser.crypto.<a href="./api/org/apache/tika/parser/crypto/Pkcs7Parser">Pkcs7Parser</a> +<ul> +<li>application/pkcs7-signature</li> +<li>application/pkcs7-mime</li></ul></li> +<li>org.apache.tika.parser.dwg.<a href="./api/org/apache/tika/parser/dwg/DWGParser">DWGParser</a> +<ul> +<li>image/vnd.dwg</li></ul></li> +<li>org.apache.tika.parser.epub.<a href="./api/org/apache/tika/parser/epub/EpubParser">EpubParser</a> +<ul> +<li>application/x-ibooks+zip</li> +<li>application/epub+zip</li></ul></li> +<li>org.apache.tika.parser.executable.<a href="./api/org/apache/tika/parser/executable/ExecutableParser">ExecutableParser</a> +<ul> +<li>application/x-elf</li> +<li>application/x-sharedlib</li> +<li>application/x-executable</li> +<li>application/x-msdownload</li> +<li>application/x-coredump</li> +<li>application/x-object</li></ul></li> +<li>org.apache.tika.parser.feed.<a href="./api/org/apache/tika/parser/feed/FeedParser">FeedParser</a> +<ul> +<li>application/atom+xml</li> +<li>application/rss+xml</li></ul></li> +<li>org.apache.tika.parser.font.<a href="./api/org/apache/tika/parser/font/AdobeFontMetricParser">AdobeFontMetricParser</a> +<ul> +<li>application/x-font-adobe-metric</li></ul></li> +<li>org.apache.tika.parser.font.<a href="./api/org/apache/tika/parser/font/TrueTypeParser">TrueTypeParser</a> +<ul> +<li>application/x-font-ttf</li></ul></li> +<li>org.apache.tika.parser.gdal.<a href="./api/org/apache/tika/parser/gdal/GDALParser">GDALParser</a> +<ul> +<li>image/x-ozi</li> +<li>application/x-snodas</li> +<li>application/x-ecrg-toc</li> +<li>image/envisat</li> +<li>application/x-doq2</li> +<li>application/x-rs2</li> +<li>application/x-gsag</li> +<li>application/x-ers</li> +<li>application/fits</li> +<li>application/x-pnm</li> +<li>image/adrg</li> +<li>image/gif</li> +<li>application/x-generic-bin</li> +<li>application/x-bt</li> +<li>application/x-zmap</li> +<li>application/x-hdf</li> +<li>image/eir</li> +<li>application/x-ace2</li> +<li>application/grass-ascii-grid</li> +<li>application/x-l1b</li> +<li>application/x-gsc</li> +<li>image/jp2</li> +<li>image/hfa</li> +<li>image/fits</li> +<li>image/raster</li> +<li>application/x-epsilon</li> +<li>image/x-srp</li> +<li>application/x-envi-hdr</li> +<li>application/x-ctable2</li> +<li>application/x-srtmhgt</li> +<li>application/jaxa-pal-sar</li> +<li>application/x-ndf</li> +<li>application/sdts-raster</li> +<li>application/x-gtx</li> +<li>application/x-rst</li> +<li>application/x-xyz</li> +<li>application/terragen</li> +<li>application/x-gs7bg</li> +<li>image/arg</li> +<li>application/elas</li> +<li>image/big-gif</li> +<li>application/x-geo-pdf</li> +<li>application/x-ctg</li> +<li>application/aaigrid</li> +<li>application/x-lcp</li> +<li>application/x-nwt-grc</li> +<li>application/x-fast</li> +<li>application/x-usgs-dem</li> +<li>application/x-nwt-grd</li> +<li>application/x-ingr</li> +<li>application/x-envi</li> +<li>application/x-rik</li> +<li>application/x-blx</li> +<li>application/x-wcs</li> +<li>image/ceos</li> +<li>application/x-ngs-geoid</li> +<li>application/x-r</li> +<li>image/bmp</li> +<li>application/x-til</li> +<li>application/x-pds</li> +<li>application/x-http</li> +<li>application/x-rasterlite</li> +<li>application/x-gmt</li> +<li>application/x-msgn</li> +<li>image/ilwis</li> +<li>application/aig</li> +<li>application/x-rmf</li> +<li>image/x-hdf5-image</li> +<li>image/sar-ceos</li> +<li>application/x-kro</li> +<li>application/vrt</li> +<li>application/x-netcdf</li> +<li>image/png</li> +<li>image/geotiff</li> +<li>image/x-mff2</li> +<li>application/x-webp</li> +<li>image/ida</li> +<li>application/x-gsbg</li> +<li>application/x-ntv2</li> +<li>application/x-coasp</li> +<li>application/x-los-las</li> +<li>application/x-tsx</li> +<li>application/x-bag</li> +<li>image/fit</li> +<li>application/x-lan</li> +<li>application/x-map</li> +<li>image/jpeg</li> +<li>application/x-dods</li> +<li>application/jdem</li> +<li>application/gff</li> +<li>application/x-isis2</li> +<li>application/x-isis3</li> +<li>application/xpm</li> +<li>application/x-pcidsk</li> +<li>application/x-gxf</li> +<li>image/ntif</li> +<li>application/x-wms</li> +<li>application/x-cosar</li> +<li>image/bsb</li> +<li>application/x-grib</li> +<li>application/x-mbtiles</li> +<li>application/x-cappi</li> +<li>application/x-rpf-toc</li> +<li>image/x-mff</li> +<li>image/x-dimap</li> +<li>image/x-pcraster</li> +<li>application/x-ppi</li> +<li>application/x-sdat</li> +<li>application/pcisdk</li> +<li>application/x-cpg</li> +<li>application/leveller</li> +<li>image/sgi</li> +<li>image/x-fujibas</li> +<li>image/x-airsar</li> +<li>application/x-e00-grid</li> +<li>application/x-kml</li> +<li>application/x-p-aux</li> +<li>application/x-doq1</li> +<li>application/dted</li> +<li>application/x-dipex</li></ul></li> +<li>org.apache.tika.parser.hdf.<a href="./api/org/apache/tika/parser/hdf/HDFParser">HDFParser</a> +<ul> +<li>application/x-hdf</li></ul></li> +<li>org.apache.tika.parser.html.<a href="./api/org/apache/tika/parser/html/HtmlParser">HtmlParser</a> +<ul> +<li>application/x-asp</li> +<li>application/xhtml+xml</li> +<li>application/vnd.wap.xhtml+xml</li> +<li>text/html</li></ul></li> +<li>org.apache.tika.parser.image.<a href="./api/org/apache/tika/parser/image/BPGParser">BPGParser</a> +<ul> +<li>image/bpg</li> +<li>image/x-bpg</li></ul></li> +<li>org.apache.tika.parser.image.<a href="./api/org/apache/tika/parser/image/ImageParser">ImageParser</a> +<ul> +<li>image/x-ms-bmp</li> +<li>image/png</li> +<li>image/x-icon</li> +<li>image/vnd.wap.wbmp</li> +<li>image/gif</li> +<li>image/bmp</li> +<li>image/x-xcf</li></ul></li> +<li>org.apache.tika.parser.image.<a href="./api/org/apache/tika/parser/image/PSDParser">PSDParser</a> +<ul> +<li>image/vnd.adobe.photoshop</li></ul></li> +<li>org.apache.tika.parser.iptc.<a href="./api/org/apache/tika/parser/iptc/IptcAnpaParser">IptcAnpaParser</a> +<ul> +<li>text/vnd.iptc.anpa</li></ul></li> +<li>org.apache.tika.parser.iwork.<a href="./api/org/apache/tika/parser/iwork/IWorkPackageParser">IWorkPackageParser</a> +<ul> +<li>application/vnd.apple.iwork</li> +<li>application/vnd.apple.numbers</li> +<li>application/vnd.apple.keynote</li> +<li>application/vnd.apple.pages</li></ul></li> +<li>org.apache.tika.parser.mail.<a href="./api/org/apache/tika/parser/mail/RFC822Parser">RFC822Parser</a> +<ul> +<li>message/rfc822</li></ul></li> +<li>org.apache.tika.parser.mat.<a href="./api/org/apache/tika/parser/mat/MatParser">MatParser</a> +<ul> +<li>application/x-matlab-data</li></ul></li> +<li>org.apache.tika.parser.mbox.<a href="./api/org/apache/tika/parser/mbox/MboxParser">MboxParser</a> +<ul> +<li>application/mbox</li></ul></li> +<li>org.apache.tika.parser.mbox.<a href="./api/org/apache/tika/parser/mbox/OutlookPSTParser">OutlookPSTParser</a> +<ul> +<li>application/vnd.ms-outlook-pst</li></ul></li> +<li>org.apache.tika.parser.microsoft.<a href="./api/org/apache/tika/parser/microsoft/OfficeParser">OfficeParser</a> +<ul> +<li>application/x-mspublisher</li> +<li>application/x-tika-msoffice</li> +<li>application/vnd.ms-excel</li> +<li>application/sldworks</li> +<li>application/x-tika-msworks-spreadsheet</li> +<li>application/vnd.ms-powerpoint</li> +<li>application/x-tika-msoffice-embedded; format=ole10_native</li> +<li>application/vnd.ms-project</li> +<li>application/x-tika-ooxml-protected</li> +<li>application/msword</li> +<li>application/vnd.ms-outlook</li> +<li>application/vnd.visio</li></ul></li> +<li>org.apache.tika.parser.microsoft.<a href="./api/org/apache/tika/parser/microsoft/OldExcelParser">OldExcelParser</a> +<ul> +<li>application/vnd.ms-excel.sheet.3</li> +<li>application/vnd.ms-excel.sheet.2</li> +<li>application/vnd.ms-excel.workspace.3</li> +<li>application/vnd.ms-excel.workspace.4</li> +<li>application/vnd.ms-excel.sheet.4</li></ul></li> +<li>org.apache.tika.parser.microsoft.<a href="./api/org/apache/tika/parser/microsoft/TNEFParser">TNEFParser</a> +<ul> +<li>application/x-tnef</li> +<li>application/ms-tnef</li> +<li>application/vnd.ms-tnef</li></ul></li> +<li>org.apache.tika.parser.microsoft.ooxml.<a href="./api/org/apache/tika/parser/microsoft/ooxml/OOXMLParser">OOXMLParser</a> +<ul> +<li>application/vnd.ms-excel.sheet.macroenabled.12</li> +<li>application/vnd.ms-powerpoint.presentation.macroenabled.12</li> +<li>application/vnd.openxmlformats-officedocument.spreadsheetml.template</li> +<li>application/vnd.openxmlformats-officedocument.wordprocessingml.document</li> +<li>application/vnd.openxmlformats-officedocument.presentationml.template</li> +<li>application/vnd.openxmlformats-officedocument.spreadsheetml.sheet</li> +<li>application/vnd.openxmlformats-officedocument.presentationml.presentation</li> +<li>application/vnd.ms-excel.addin.macroenabled.12</li> +<li>application/vnd.ms-word.document.macroenabled.12</li> +<li>application/vnd.ms-excel.template.macroenabled.12</li> +<li>application/vnd.openxmlformats-officedocument.wordprocessingml.template</li> +<li>application/vnd.ms-powerpoint.slideshow.macroenabled.12</li> +<li>application/vnd.ms-powerpoint.addin.macroenabled.12</li> +<li>application/vnd.ms-word.template.macroenabled.12</li> +<li>application/x-tika-ooxml</li> +<li>application/vnd.openxmlformats-officedocument.presentationml.slideshow</li></ul></li> +<li>org.apache.tika.parser.mp3.<a href="./api/org/apache/tika/parser/mp3/Mp3Parser">Mp3Parser</a> +<ul> +<li>audio/mpeg</li></ul></li> +<li>org.apache.tika.parser.mp4.<a href="./api/org/apache/tika/parser/mp4/MP4Parser">MP4Parser</a> +<ul> +<li>video/3gpp2</li> +<li>video/mp4</li> +<li>video/quicktime</li> +<li>audio/mp4</li> +<li>application/mp4</li> +<li>video/x-m4v</li> +<li>video/3gpp</li></ul></li> +<li>org.apache.tika.parser.netcdf.<a href="./api/org/apache/tika/parser/netcdf/NetCDFParser">NetCDFParser</a> +<ul> +<li>application/x-netcdf</li></ul></li> +<li>org.apache.tika.parser.ocr.<a href="./api/org/apache/tika/parser/ocr/TesseractOCRParser">TesseractOCRParser</a> +<ul> +<li>image/x-ms-bmp</li> +<li>image/jpeg</li> +<li>image/png</li> +<li>image/tiff</li> +<li>image/gif</li></ul></li> +<li>org.apache.tika.parser.odf.<a href="./api/org/apache/tika/parser/odf/OpenDocumentParser">OpenDocumentParser</a> +<ul> +<li>application/x-vnd.oasis.opendocument.graphics-template</li> +<li>application/vnd.sun.xml.writer</li> +<li>application/x-vnd.oasis.opendocument.text</li> +<li>application/x-vnd.oasis.opendocument.text-web</li> +<li>application/x-vnd.oasis.opendocument.spreadsheet-template</li> +<li>application/vnd.oasis.opendocument.formula-template</li> +<li>application/vnd.oasis.opendocument.presentation</li> +<li>application/vnd.oasis.opendocument.image-template</li> +<li>application/x-vnd.oasis.opendocument.graphics</li> +<li>application/vnd.oasis.opendocument.chart-template</li> +<li>application/vnd.oasis.opendocument.presentation-template</li> +<li>application/x-vnd.oasis.opendocument.image-template</li> +<li>application/vnd.oasis.opendocument.formula</li> +<li>application/x-vnd.oasis.opendocument.image</li> +<li>application/vnd.oasis.opendocument.spreadsheet-template</li> +<li>application/x-vnd.oasis.opendocument.chart-template</li> +<li>application/x-vnd.oasis.opendocument.formula</li> +<li>application/vnd.oasis.opendocument.spreadsheet</li> +<li>application/vnd.oasis.opendocument.text-web</li> +<li>application/vnd.oasis.opendocument.text-template</li> +<li>application/vnd.oasis.opendocument.text</li> +<li>application/x-vnd.oasis.opendocument.formula-template</li> +<li>application/x-vnd.oasis.opendocument.spreadsheet</li> +<li>application/x-vnd.oasis.opendocument.chart</li> +<li>application/vnd.oasis.opendocument.text-master</li> +<li>application/x-vnd.oasis.opendocument.text-master</li> +<li>application/x-vnd.oasis.opendocument.text-template</li> +<li>application/vnd.oasis.opendocument.graphics</li> +<li>application/vnd.oasis.opendocument.graphics-template</li> +<li>application/x-vnd.oasis.opendocument.presentation</li> +<li>application/vnd.oasis.opendocument.image</li> +<li>application/x-vnd.oasis.opendocument.presentation-template</li> +<li>application/vnd.oasis.opendocument.chart</li></ul></li> +<li>org.apache.tika.parser.pdf.<a href="./api/org/apache/tika/parser/pdf/PDFParser">PDFParser</a> +<ul> +<li>application/pdf</li></ul></li> +<li>org.apache.tika.parser.pkg.<a href="./api/org/apache/tika/parser/pkg/CompressorParser">CompressorParser</a> +<ul> +<li>application/x-bzip</li> +<li>application/x-bzip2</li> +<li>application/gzip</li> +<li>application/x-gzip</li> +<li>application/x-xz</li></ul></li> +<li>org.apache.tika.parser.pkg.<a href="./api/org/apache/tika/parser/pkg/PackageParser">PackageParser</a> +<ul> +<li>application/x-tar</li> +<li>application/x-tika-unix-dump</li> +<li>application/java-archive</li> +<li>application/x-7z-compressed</li> +<li>application/x-archive</li> +<li>application/x-cpio</li> +<li>application/zip</li></ul></li> +<li>org.apache.tika.parser.rtf.<a href="./api/org/apache/tika/parser/rtf/RTFParser">RTFParser</a> +<ul> +<li>application/rtf</li></ul></li> +<li>org.apache.tika.parser.txt.<a href="./api/org/apache/tika/parser/txt/TXTParser">TXTParser</a> +<ul> +<li>text/plain</li></ul></li> +<li>org.apache.tika.parser.video.<a href="./api/org/apache/tika/parser/video/FLVParser">FLVParser</a> +<ul> +<li>video/x-flv</li></ul></li> +<li>org.apache.tika.parser.xml.<a href="./api/org/apache/tika/parser/xml/DcXMLParser">DcXMLParser</a> +<ul> +<li>application/xml</li> +<li>image/svg+xml</li></ul></li> +<li>org.apache.tika.parser.xml.<a href="./api/org/apache/tika/parser/xml/FictionBookParser">FictionBookParser</a> +<ul> +<li>application/x-fictionbook+xml</li></ul></li> +<li>org.gagravarr.tika.<a href="./api/org/gagravarr/tika/FlacParser">FlacParser</a> +<ul> +<li>audio/x-oggflac</li> +<li>audio/x-flac</li></ul></li> +<li>org.gagravarr.tika.<a href="./api/org/gagravarr/tika/OggParser">OggParser</a> +<ul> +<li>application/kate</li> +<li>application/ogg</li> +<li>audio/x-oggpcm</li> +<li>video/x-oggyuv</li> +<li>video/x-dirac</li> +<li>video/x-ogm</li> +<li>audio/ogg</li> +<li>video/x-ogguvs</li> +<li>video/theora</li> +<li>video/x-oggrgb</li> +<li>video/ogg</li></ul></li> +<li>org.gagravarr.tika.<a href="./api/org/gagravarr/tika/OpusParser">OpusParser</a> +<ul> +<li>audio/opus</li> +<li>audio/ogg; codecs=opus</li></ul></li> +<li>org.gagravarr.tika.<a href="./api/org/gagravarr/tika/SpeexParser">SpeexParser</a> +<ul> +<li>audio/speex</li> +<li>audio/ogg; codecs=speex</li></ul></li> +<li>org.gagravarr.tika.<a href="./api/org/gagravarr/tika/VorbisParser">VorbisParser</a> +<ul> +<li>audio/vorbis</li></ul></li></ul></div> </div> <div id="sidebar"> <div id="navigation"> @@ -377,7 +760,7 @@ </div> <div id="footer"> <p> - Copyright © 2014 + Copyright © 2015 <a href="http://www.apache.org/";>The Apache Software Foundation</a>. Site powered by <a href="http://maven.apache.org/";>Apache Maven</a>. Search powered by
