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 2016/02/20 08:37:57 UTC
svn commit: r1731338 [38/38] - in /tika/site: publish/ publish/0.10/
publish/0.5/ publish/0.6/ publish/0.7/ publish/0.8/ publish/0.9/
publish/1.0/ publish/1.1/ publish/1.10/ publish/1.11/ publish/1.11/miredot/
publish/1.11/miredot/css/ publish/1.11/mir...
Modified: tika/site/publish/1.9/examples.html
URL: http://svn.apache.org/viewvc/tika/site/publish/1.9/examples.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/1.9/examples.html (original)
+++ tika/site/publish/1.9/examples.html Sat Feb 20 07:37:52 2016
@@ -116,23 +116,23 @@
<p>The <a href="./api/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_848346" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number54 index0 alt1"><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 number55 index1 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 number56 index2 alt1"><code class="java spaces"> </code><code class="java keyword">try</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><c
ode class="java plain">)) {</code></div><div class="line number57 index3 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">tika.parseToString(stream);</code></div><div class="line number58 index4 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number59 index5 alt2"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div>
+<div id="highlighter_810966" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number54 index0 alt1"><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 number55 index1 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 number56 index2 alt1"><code class="java spaces"> </code><code class="java keyword">try</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><c
ode class="java plain">)) {</code></div><div class="line number57 index3 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">tika.parseToString(stream);</code></div><div class="line number58 index4 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number59 index5 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="./api/org/apache/tika/parser/Parser.html">Tika Parsers</a> directly. Most likely, you'll want to start out using the <a href="./api/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_803486" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number85 index0 alt2"><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 number86 index1 alt1"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java pla
in">AutoDetectParser();</code></div><div class="line number87 index2 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 number88 index3 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 number89 index4 alt2"><code class="java spaces"> </code><code class="java keyword">try</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 number90 index5 alt1"><code class="java spaces"> &nb
sp; </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number91 index6 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number92 index7 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number93 index8 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="./api/org/apache/tika/parser/Parser.html">Tika Parsers</a> directly. Most likely, you'll want to start out using the <a href="./api/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_485363" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number85 index0 alt2"><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 number86 index1 alt1"><code class="java spaces"> </code><code class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java pla
in">AutoDetectParser();</code></div><div class="line number87 index2 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 number88 index3 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 number89 index4 alt2"><code class="java spaces"> </code><code class="java keyword">try</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 number90 index5 alt1"><code class="java spaces"> &nb
sp; </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number91 index6 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number92 index7 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number93 index8 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="./api/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_151510" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number47 index0 alt2"><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 number48 index1 alt1"><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 number49 index2 alt2"> </div><div class="line number50 index3 alt1"><code class="java space
s"> </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 index4 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 index5 alt1"><code class="java spaces"> </code><code class="java keyword">try</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 number53 index6 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</c
ode></div><div class="line number54 index7 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number55 index8 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number56 index9 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div>
+<p>By using the <a href="./api/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_739558" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number47 index0 alt2"><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 number48 index1 alt1"><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 number49 index2 alt2"> </div><div class="line number50 index3 alt1"><code class="java space
s"> </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 index4 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 index5 alt1"><code class="java spaces"> </code><code class="java keyword">try</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 number53 index6 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</c
ode></div><div class="line number54 index7 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number55 index8 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number56 index9 alt1"><code class="java 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="./api/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_80599" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number61 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 number62 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 number63 index2 alt2"> </div><div class="line number64 index3 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 number65 index4 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 number66 index5 alt1"><code class="java spaces"> </code><code class="java keyword">try</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 index6 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number68 ind
ex7 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number69 index8 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number70 index9 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div>
-<p>If you just want the body of the xhtml document, without the header, you can chain together a <a href="./api/org/apache/tika/sax/BodyContentHandler.html">BodyContentHandler</a> and a <a href="./api/org/apache/tika/sax/ToXMLContentHandler.html">ToXMLContentHandler</a> as shown:</p><div id="highlighter_465571" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number76 index0 alt1"><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 number77 index1 alt2"><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 number78 index2 alt
1"><code class="java spaces"> </code><code class="java keyword">new</code> <code class="java plain">ToXMLContentHandler());</code></div><div class="line number79 index3 alt2"> </div><div class="line number80 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 number81 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 number82 index6 alt1"><code class="java spaces"> </code><code class="java keyword">try</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 number83 index7 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number84 index8 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number85 index9 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number86 index10 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div>
+<p>By using the <a href="./api/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_290297" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number61 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 number62 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 number63 index2 alt2"> </div><div class="line number64 index3 alt1"><code class="java spaces"> </code><cod
e class="java plain">AutoDetectParser parser = </code><code class="java keyword">new</code> <code class="java plain">AutoDetectParser();</code></div><div class="line number65 index4 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 number66 index5 alt1"><code class="java spaces"> </code><code class="java keyword">try</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 index6 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number68 in
dex7 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number69 index8 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number70 index9 alt1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div>
+<p>If you just want the body of the xhtml document, without the header, you can chain together a <a href="./api/org/apache/tika/sax/BodyContentHandler.html">BodyContentHandler</a> and a <a href="./api/org/apache/tika/sax/ToXMLContentHandler.html">ToXMLContentHandler</a> as shown:</p><div id="highlighter_771628" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number76 index0 alt1"><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 number77 index1 alt2"><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 number78 index2 alt
1"><code class="java spaces"> </code><code class="java keyword">new</code> <code class="java plain">ToXMLContentHandler());</code></div><div class="line number79 index3 alt2"> </div><div class="line number80 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 number81 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 number82 index6 alt1"><code class="java spaces"> </code><code class="java keyword">try</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 number83 index7 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number84 index8 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number85 index9 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number86 index10 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_567589" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number92 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 number93 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 number94 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 string">
"xhtml"</code><code class="java plain">, XHTMLContentHandler.XHTML);</code></div><div class="line number95 index3 alt2"><code class="java spaces"> </code><code class="java plain">Matcher divContentMatcher = xhtmlParser.parse(</code><code class="java string">"/xhtml:html/xhtml:body/xhtml:div/descendant::node()"</code><code class="java plain">);</code></div><div class="line number96 index4 alt1"><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 number97 index5 alt2"><code class="java spaces"> </code><code class="java keyword">new</code> <code class="java plain">ToXMLContentHandler(), divContentMatcher);</code></div><div class="line number98 index6 alt1"> </div><div class="line number99 index7 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 number100 index8 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 number101 index9 alt2"><code class="java spaces"> </code><code class="java keyword">try</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 number102 index10 alt1"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handle
r, metadata);</code></div><div class="line number103 index11 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number104 index12 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number105 index13 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_568087" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number92 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 number93 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 number94 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 string">
"xhtml"</code><code class="java plain">, XHTMLContentHandler.XHTML);</code></div><div class="line number95 index3 alt2"><code class="java spaces"> </code><code class="java plain">Matcher divContentMatcher = xhtmlParser.parse(</code><code class="java string">"/xhtml:html/xhtml:body/xhtml:div/descendant::node()"</code><code class="java plain">);</code></div><div class="line number96 index4 alt1"><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 number97 index5 alt2"><code class="java spaces"> </code><code class="java keyword">new</code> <code class="java plain">ToXMLContentHandler(), divContentMatcher);</code></div><div class="line number98 index6 alt1"> </div><div class="line number99 index7 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 number100 index8 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 number101 index9 alt2"><code class="java spaces"> </code><code class="java keyword">try</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 number102 index10 alt1"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handle
r, metadata);</code></div><div class="line number103 index11 alt2"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">handler.toString();</code></div><div class="line number104 index12 alt1"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number105 index13 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>
@@ -141,16 +141,16 @@
<p>By using the <a href="./api/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>
<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_829073" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number113 index0 alt2"><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 number114 index1 alt1"><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<>();</code></div><div class="line number115 index2 alt2"><code c
lass="java spaces"> </code><code class="java plain">chunks.add(</code><code class="java string">""</code><code class="java plain">);</code></div><div class="line number116 index3 alt1"><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 number117 index4 alt2"><code class="java spaces"> </code><code class="java color1">@Override</code></div><div class="line number118 index5 alt1"><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">start, </c
ode><code class="java keyword">int</code> <code class="java plain">length) {</code></div><div class="line number119 index6 alt2"><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 number120 index7 alt1"><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 number121 index8 alt2"> </div><div class="line number122 index9 alt1"><code class="java spaces"> </code><code class="java keyword">if</code> <code class="java plain">(lastChunk.length() + length > MAXIMUM_TEXT_CHUNK_SIZE) {
</code></div><div class="line number123 index10 alt2"><code class="java spaces"> </code><code class="java plain">chunks.add(thisStr);</code></div><div class="line number124 index11 alt1"><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 number125 index12 alt2"><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 number126 index13 alt1"><code class="java spaces"> </code><code class="java plain">}</c
ode></div><div class="line number127 index14 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number128 index15 alt1"><code class="java spaces"> </code><code class="java plain">};</code></div><div class="line number129 index16 alt2"> </div><div class="line number130 index17 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 number131 index18 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 number132 index19 alt1"><code class="java spaces"> </code><code class="java keyword">try</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 number133 index20 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number134 index21 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">chunks;</code></div><div class="line number135 index22 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number136 index23 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_297143" class="syntaxhighlighter nogutter java"><table border="0" cellpadding="0" cellspacing="0"><tbody><tr><td class="code"><div class="container"><div class="line number113 index0 alt2"><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 number114 index1 alt1"><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<>();</code></div><div class="line number115 index2 alt2"><code c
lass="java spaces"> </code><code class="java plain">chunks.add(</code><code class="java string">""</code><code class="java plain">);</code></div><div class="line number116 index3 alt1"><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 number117 index4 alt2"><code class="java spaces"> </code><code class="java color1">@Override</code></div><div class="line number118 index5 alt1"><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">start, </c
ode><code class="java keyword">int</code> <code class="java plain">length) {</code></div><div class="line number119 index6 alt2"><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 number120 index7 alt1"><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 number121 index8 alt2"> </div><div class="line number122 index9 alt1"><code class="java spaces"> </code><code class="java keyword">if</code> <code class="java plain">(lastChunk.length() + length > MAXIMUM_TEXT_CHUNK_SIZE) {
</code></div><div class="line number123 index10 alt2"><code class="java spaces"> </code><code class="java plain">chunks.add(thisStr);</code></div><div class="line number124 index11 alt1"><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 number125 index12 alt2"><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 number126 index13 alt1"><code class="java spaces"> </code><code class="java plain">}</c
ode></div><div class="line number127 index14 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number128 index15 alt1"><code class="java spaces"> </code><code class="java plain">};</code></div><div class="line number129 index16 alt2"> </div><div class="line number130 index17 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 number131 index18 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 number132 index19 alt1"><code class="java spaces"> </code><code class="java keyword">try</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 number133 index20 alt2"><code class="java spaces"> </code><code class="java plain">parser.parse(stream, handler, metadata);</code></div><div class="line number134 index21 alt1"><code class="java spaces"> </code><code class="java keyword">return</code> <code class="java plain">chunks;</code></div><div class="line number135 index22 alt2"><code class="java spaces"> </code><code class="java plain">}</code></div><div class="line number136 index23 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_375506" 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_603977" 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="./api/org/apache/tika/language/LanguageIdentifier.html">LanguageIdentifier</a> class.</p><div id="highlighter_355246" 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 alt
1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div>
+<p>Tika provides support for identifying the language of text, through the <a href="./api/org/apache/tika/language/LanguageIdentifier.html">LanguageIdentifier</a> class.</p><div id="highlighter_276997" 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 alt
1"><code class="java plain">}</code></div></div></td></tr></tbody></table></div></div>
<div class="section">
<h3><a name="Additional_Examples">Additional Examples</a></h3>
<p>A number of other examples are also available, including all of the examples from the <a class="externalLink" href="http://manning.com/mattmann/">Tika In Action book</a>. These can all be found in the <a class="externalLink" href="https://svn.apache.org/repos/asf/tika/trunk/tika-example">Tika Example module</a> in SVN.</p></div></div>
@@ -196,6 +196,7 @@
+
<li class="expanded">
<a href="../1.12/index.html">Apache Tika 1.12</a>
@@ -232,6 +233,10 @@
<li class="none">
<a href="../1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="../1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -244,6 +249,7 @@
+
<li class="collapsed">
<a href="../1.11/index.html">Apache Tika 1.11</a>
@@ -254,6 +260,7 @@
+
Modified: tika/site/publish/1.9/formats.html
URL: http://svn.apache.org/viewvc/tika/site/publish/1.9/formats.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/1.9/formats.html (original)
+++ tika/site/publish/1.9/formats.html Sat Feb 20 07:37:52 2016
@@ -657,6 +657,7 @@
+
<li class="expanded">
<a href="../1.12/index.html">Apache Tika 1.12</a>
@@ -693,6 +694,10 @@
<li class="none">
<a href="../1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="../1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -705,6 +710,7 @@
+
<li class="collapsed">
<a href="../1.11/index.html">Apache Tika 1.11</a>
@@ -715,6 +721,7 @@
+
Modified: tika/site/publish/1.9/gettingstarted.html
URL: http://svn.apache.org/viewvc/tika/site/publish/1.9/gettingstarted.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/1.9/gettingstarted.html (original)
+++ tika/site/publish/1.9/gettingstarted.html Sat Feb 20 07:37:52 2016
@@ -262,6 +262,7 @@ curl http://.../document.doc \
+
<li class="expanded">
<a href="../1.12/index.html">Apache Tika 1.12</a>
@@ -298,6 +299,10 @@ curl http://.../document.doc \
<li class="none">
<a href="../1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="../1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -310,6 +315,7 @@ curl http://.../document.doc \
+
<li class="collapsed">
<a href="../1.11/index.html">Apache Tika 1.11</a>
@@ -320,6 +326,7 @@ curl http://.../document.doc \
+
Modified: tika/site/publish/1.9/index.html
URL: http://svn.apache.org/viewvc/tika/site/publish/1.9/index.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/1.9/index.html (original)
+++ tika/site/publish/1.9/index.html Sat Feb 20 07:37:52 2016
@@ -172,6 +172,7 @@
+
<li class="expanded">
<a href="../1.12/index.html">Apache Tika 1.12</a>
@@ -208,6 +209,10 @@
<li class="none">
<a href="../1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="../1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -220,6 +225,7 @@
+
<li class="collapsed">
<a href="../1.11/index.html">Apache Tika 1.11</a>
@@ -230,6 +236,7 @@
+
Modified: tika/site/publish/1.9/parser.html
URL: http://svn.apache.org/viewvc/tika/site/publish/1.9/parser.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/1.9/parser.html (original)
+++ tika/site/publish/1.9/parser.html Sat Feb 20 07:37:52 2016
@@ -219,6 +219,7 @@ try {
+
<li class="expanded">
<a href="../1.12/index.html">Apache Tika 1.12</a>
@@ -255,6 +256,10 @@ try {
<li class="none">
<a href="../1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="../1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -267,6 +272,7 @@ try {
+
<li class="collapsed">
<a href="../1.11/index.html">Apache Tika 1.11</a>
@@ -277,6 +283,7 @@ try {
+
Modified: tika/site/publish/1.9/parser_guide.html
URL: http://svn.apache.org/viewvc/tika/site/publish/1.9/parser_guide.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/1.9/parser_guide.html (original)
+++ tika/site/publish/1.9/parser_guide.html Sat Feb 20 07:37:52 2016
@@ -217,6 +217,7 @@ public class HelloParser extends Abstrac
+
<li class="expanded">
<a href="../1.12/index.html">Apache Tika 1.12</a>
@@ -253,6 +254,10 @@ public class HelloParser extends Abstrac
<li class="none">
<a href="../1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="../1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -265,6 +270,7 @@ public class HelloParser extends Abstrac
+
<li class="collapsed">
<a href="../1.11/index.html">Apache Tika 1.11</a>
@@ -275,6 +281,7 @@ public class HelloParser extends Abstrac
+
Modified: tika/site/publish/contribute.html
URL: http://svn.apache.org/viewvc/tika/site/publish/contribute.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/contribute.html (original)
+++ tika/site/publish/contribute.html Sat Feb 20 07:37:52 2016
@@ -165,6 +165,7 @@
+
<li class="expanded">
<a href="1.12/index.html">Apache Tika 1.12</a>
@@ -201,6 +202,10 @@
<li class="none">
<a href="1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -213,6 +218,7 @@
+
<li class="collapsed">
<a href="1.11/index.html">Apache Tika 1.11</a>
@@ -223,6 +229,7 @@
+
Modified: tika/site/publish/download.html
URL: http://svn.apache.org/viewvc/tika/site/publish/download.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/download.html (original)
+++ tika/site/publish/download.html Sat Feb 20 07:37:52 2016
@@ -158,6 +158,7 @@
+
<li class="expanded">
<a href="1.12/index.html">Apache Tika 1.12</a>
@@ -194,6 +195,10 @@
<li class="none">
<a href="1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -206,6 +211,7 @@
+
<li class="collapsed">
<a href="1.11/index.html">Apache Tika 1.11</a>
@@ -216,6 +222,7 @@
+
Modified: tika/site/publish/index.html
URL: http://svn.apache.org/viewvc/tika/site/publish/index.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/index.html (original)
+++ tika/site/publish/index.html Sat Feb 20 07:37:52 2016
@@ -254,6 +254,7 @@
+
<li class="expanded">
<a href="1.12/index.html">Apache Tika 1.12</a>
@@ -290,6 +291,10 @@
<li class="none">
<a href="1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -302,6 +307,7 @@
+
<li class="collapsed">
<a href="1.11/index.html">Apache Tika 1.11</a>
@@ -312,6 +318,7 @@
+
Modified: tika/site/publish/issue-tracking.html
URL: http://svn.apache.org/viewvc/tika/site/publish/issue-tracking.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/issue-tracking.html (original)
+++ tika/site/publish/issue-tracking.html Sat Feb 20 07:37:52 2016
@@ -134,6 +134,7 @@
+
<li class="expanded">
<a href="1.12/index.html">Apache Tika 1.12</a>
@@ -170,6 +171,10 @@
<li class="none">
<a href="1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -182,6 +187,7 @@
+
<li class="collapsed">
<a href="1.11/index.html">Apache Tika 1.11</a>
@@ -192,6 +198,7 @@
+
Modified: tika/site/publish/license.html
URL: http://svn.apache.org/viewvc/tika/site/publish/license.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/license.html (original)
+++ tika/site/publish/license.html Sat Feb 20 07:37:52 2016
@@ -337,6 +337,7 @@
+
<li class="expanded">
<a href="1.12/index.html">Apache Tika 1.12</a>
@@ -373,6 +374,10 @@
<li class="none">
<a href="1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -385,6 +390,7 @@
+
<li class="collapsed">
<a href="1.11/index.html">Apache Tika 1.11</a>
@@ -395,6 +401,7 @@
+
Modified: tika/site/publish/mail-lists.html
URL: http://svn.apache.org/viewvc/tika/site/publish/mail-lists.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/mail-lists.html (original)
+++ tika/site/publish/mail-lists.html Sat Feb 20 07:37:52 2016
@@ -140,6 +140,7 @@
+
<li class="expanded">
<a href="1.12/index.html">Apache Tika 1.12</a>
@@ -176,6 +177,10 @@
<li class="none">
<a href="1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -188,6 +193,7 @@
+
<li class="collapsed">
<a href="1.11/index.html">Apache Tika 1.11</a>
@@ -198,6 +204,7 @@
+
Modified: tika/site/publish/project-info.html
URL: http://svn.apache.org/viewvc/tika/site/publish/project-info.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/project-info.html (original)
+++ tika/site/publish/project-info.html Sat Feb 20 07:37:52 2016
@@ -152,6 +152,7 @@
+
<li class="expanded">
<a href="1.12/index.html">Apache Tika 1.12</a>
@@ -188,6 +189,10 @@
<li class="none">
<a href="1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -200,6 +205,7 @@
+
<li class="collapsed">
<a href="1.11/index.html">Apache Tika 1.11</a>
@@ -210,6 +216,7 @@
+
Modified: tika/site/publish/source-repository.html
URL: http://svn.apache.org/viewvc/tika/site/publish/source-repository.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/source-repository.html (original)
+++ tika/site/publish/source-repository.html Sat Feb 20 07:37:52 2016
@@ -162,6 +162,7 @@ http-proxy-port = 3128
+
<li class="expanded">
<a href="1.12/index.html">Apache Tika 1.12</a>
@@ -198,6 +199,10 @@ http-proxy-port = 3128
<li class="none">
<a href="1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -210,6 +215,7 @@ http-proxy-port = 3128
+
<li class="collapsed">
<a href="1.11/index.html">Apache Tika 1.11</a>
@@ -220,6 +226,7 @@ http-proxy-port = 3128
+
Modified: tika/site/publish/team-list.html
URL: http://svn.apache.org/viewvc/tika/site/publish/team-list.html?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/publish/team-list.html (original)
+++ tika/site/publish/team-list.html Sat Feb 20 07:37:52 2016
@@ -359,6 +359,7 @@ window.onLoad = init();
+
<li class="expanded">
<a href="1.12/index.html">Apache Tika 1.12</a>
@@ -395,6 +396,10 @@ window.onLoad = init();
<li class="none">
<a href="1.12/api/">API Documentation</a>
</li>
+
+ <li class="none">
+ <a href="1.12/miredot/">REST API Documentation (Miredot)</a>
+ </li>
</ul>
</li>
@@ -407,6 +412,7 @@ window.onLoad = init();
+
<li class="collapsed">
<a href="1.11/index.html">Apache Tika 1.11</a>
@@ -417,6 +423,7 @@ window.onLoad = init();
+
Modified: tika/site/src/site/site.xml
URL: http://svn.apache.org/viewvc/tika/site/src/site/site.xml?rev=1731338&r1=1731337&r2=1731338&view=diff
==============================================================================
--- tika/site/src/site/site.xml (original)
+++ tika/site/src/site/site.xml Sat Feb 20 07:37:52 2016
@@ -49,6 +49,7 @@
<item name="Configuring Tika" href="1.12/configuring.html"/>
<item name="Usage Examples" href="1.12/examples.html"/>
<item name="API Documentation" href="1.12/api/"/>
+ <item name="REST API Documentation (Miredot)" href="1.12/miredot/"/>
</item>
<item name="Apache Tika 1.11" href="1.11/index.html" collapse="true">
<item name="Getting Started" href="1.11/gettingstarted.html"/>
@@ -59,6 +60,7 @@
<item name="Configuring Tika" href="1.11/configuring.html"/>
<item name="Usage Examples" href="1.11/examples.html"/>
<item name="API Documentation" href="1.11/api/"/>
+ <item name="REST API Documentation (Miredot)" href="1.11/miredot/"/>
</item>
<item name="Apache Tika 1.10" href="1.10/index.html" collapse="true">
<item name="Getting Started" href="1.10/gettingstarted.html"/>
@@ -69,6 +71,7 @@
<item name="Configuring Tika" href="1.10/configuring.html"/>
<item name="Usage Examples" href="1.10/examples.html"/>
<item name="API Documentation" href="1.10/api/"/>
+ <item name="REST API Documentation (Miredot)" href="1.10/miredot/"/>
</item>
<item name="Apache Tika 1.9" href="1.9/index.html" collapse="true">
<item name="Getting Started" href="1.9/gettingstarted.html"/>