Skip to site navigation (Press enter)
(tika) branch main updated: TIKA-4350 HTML snippet containing
as root element erroneously recognized as application/xml (#2045)</span></a></span> </h1> <p class="darkgray font13"> <span class="sender pipe"><a href="/search?l=commits@tika.apache.org&q=from:%22tallison%22" rel="nofollow"><span itemprop="author" itemscope itemtype="http://schema.org/Person"><span itemprop="name">tallison</span></span></a></span> <span class="date"><a href="/search?l=commits@tika.apache.org&q=date:20241114" rel="nofollow">Thu, 14 Nov 2024 13:23:09 -0800</a></span> </p> </div> <div itemprop="articleBody" class="msgBody"> <!--X-Body-of-Message--> <pre>This is an automated email from the ASF dual-hosted git repository. tallison pushed a commit to branch main in repository <a rel="nofollow" href="https://gitbox.apache.org/repos/asf/tika.git">https://gitbox.apache.org/repos/asf/tika.git</a></pre><pre> The following commit(s) were added to refs/heads/main by this push: new bd878d373 TIKA-4350 HTML snippet containing <iframe> as root element erroneously recognized as application/xml (#2045) bd878d373 is described below commit bd878d3733853d0a9c6ffef32e18fba61f505760 Author: Sebastian Nagel <sna...@apache.org> AuthorDate: Thu Nov 14 15:04:33 2024 +0100 TIKA-4350 HTML snippet containing <iframe> as root element erroneously recognized as application/xml (#2045) --- tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml | 2 ++ tika-core/src/test/java/org/apache/tika/mime/MimeDetectionTest.java | 2 ++ .../test/resources/org/apache/tika/mime/test-html-snippet-iframe.jsp | 2 ++ 3 files changed, 6 insertions(+) diff --git a/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml b/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml index 87cc7aae8..9ea801f60 100644 --- a/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml +++ b/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml @@ -7680,6 +7680,8 @@ <root-XML localName="SCRIPT"/> <root-XML localName="frameset"/> <root-XML localName="FRAMESET"/> + <root-XML localName="iframe"/> + <root-XML localName="IFRAME"/> <magic priority="60"> <match value="(?i)&lt;(html|head|body|title|div)[ >]" type="regex" offset="0"/> <match value="(?i)&lt;h[123][ >]" type="regex" offset="0"/> diff --git a/tika-core/src/test/java/org/apache/tika/mime/MimeDetectionTest.java b/tika-core/src/test/java/org/apache/tika/mime/MimeDetectionTest.java index 6e844a0bf..690290cbd 100644 --- a/tika-core/src/test/java/org/apache/tika/mime/MimeDetectionTest.java +++ b/tika-core/src/test/java/org/apache/tika/mime/MimeDetectionTest.java @@ -74,6 +74,8 @@ public class MimeDetectionTest { testFile("text/html", "testlargerbuffer.html"); // test fragment of HTML with <div> (TIKA-1102) testFile("text/html", "htmlfragment"); + // test fragment of HTML with <iframe> and potentially misleading file suffix + testFile("text/html", "test-html-snippet-iframe.jsp"); // test binary CGM detection (TIKA-1170) testFile("image/cgm", "plotutils-bin-cgm-v3.cgm"); // test HTML detection of malformed file, previously identified as image/cgm (TIKA-1170) diff --git a/tika-core/src/test/resources/org/apache/tika/mime/test-html-snippet-iframe.jsp b/tika-core/src/test/resources/org/apache/tika/mime/test-html-snippet-iframe.jsp new file mode 100644 index 000000000..2681fecdc --- /dev/null +++ b/tika-core/src/test/resources/org/apache/tika/mime/test-html-snippet-iframe.jsp @@ -0,0 +1,2 @@ +<!-- this is a comment: <a rel="nofollow" href="https://www.example.org/path/file.pdf">https://www.example.org/path/file.pdf</a> --> + <iframe src='/path/file.pdf' width='100%' height='100%' target='_blank'> </pre> </div> <div class="msgButtons margintopdouble"> <ul class="overflow"> <li class="msgButtonItems"><a class="button buttonleft " accesskey="p" href="msg16830.html">Previous message</a></li> <li class="msgButtonItems textaligncenter"><a class="button" accesskey="c" href="index.html#16832">View by thread</a></li> <li class="msgButtonItems textaligncenter"><a class="button" accesskey="i" href="maillist.html#16832">View by date</a></li> <li class="msgButtonItems textalignright"><a class="button buttonright " accesskey="n" href="msg16833.html">Next message</a></li> </ul> </div> <a name="tslice"></a> <div class="tSliceList margintopdouble"> <ul class="icons monospace"> </ul> </div> <div class="overflow msgActions margintopdouble"> <div class="msgReply" > <h2> Reply via email to </h2> <form method="POST" action="/mailto.php"> <input type="hidden" name="subject" value="(tika) branch main updated: TIKA-4350 HTML snippet containing <iframe> as root element erroneously recognized as application/xml (#2045)"> <input type="hidden" name="msgid" value="173159307848.2880414.3559746934303739614@gitbox2-he-fi.apache.org"> <input type="hidden" name="relpath" value="commits@tika.apache.org/msg16832.html"> <input type="submit" value=" tallison "> </form> </div> </div> </div> <div class="aside" role="complementary"> <div class="logo"> <a href="/"><img src="/logo.png" width=247 height=88 alt="The Mail Archive"></a> </div> <form class="overflow" action="/search" method="get"> <input type="hidden" name="l" value="commits@tika.apache.org"> <label class="hidden" for="q">Search the site</label> <input class="submittext" type="text" id="q" name="q" placeholder="Search commits"> <input class="submitbutton" name="submit" type="image" src="/submit.png" alt="Submit"> </form> <div class="nav margintop" id="nav" role="navigation"> <ul class="icons font16"> <li class="icons-home"><a href="/">The Mail Archive home</a></li> <li class="icons-list"><a href="/commits@tika.apache.org/">commits - all messages</a></li> <li class="icons-about"><a href="/commits@tika.apache.org/info.html">commits - about the list</a></li> <li class="icons-expand"><a href="/search?l=commits@tika.apache.org&q=subject:%22%5C%28tika%5C%29+branch+main+updated%5C%3A+TIKA%5C-4350+HTML+snippet+containing+%3Ciframe%3E+as+root+element+erroneously+recognized+as+application%5C%2Fxml+%5C%28%232045%5C%29%22&o=newest&f=1" title="e" id="e">Expand</a></li> <li class="icons-prev"><a href="msg16830.html" title="p">Previous message</a></li> <li class="icons-next"><a href="msg16833.html" title="n">Next message</a></li> </ul> </div> <div class="listlogo margintopdouble"> </div> <div class="margintopdouble"> </div> </div> </div> <div class="footer" role="contentinfo"> <ul> <li><a href="/">The Mail Archive home</a></li> <li><a href="/faq.html#newlist">Add your mailing list</a></li> <li><a href="/faq.html">FAQ</a></li> <li><a href="/faq.html#support">Support</a></li> <li><a href="/faq.html#privacy">Privacy</a></li> <li class="darkgray">173159307848.2880414.3559746934303739614@gitbox2-he-fi.apache.org</li> </ul> </div> </body> </html> <script>(function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9d318576eb19cc36',t:'MTc3MTk2MjkzNA=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();</script>