Author: nick
Date: Sat May 23 14:05:20 2015
New Revision: 1681351
URL: http://svn.apache.org/r1681351
Log:
TIKA-1634 Two more kinds of matlab magic, and tests
Modified:
tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
Modified:
tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml?rev=1681351&r1=1681350&r2=1681351&view=diff
==============================================================================
---
tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
(original)
+++
tika/trunk/tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml
Sat May 23 14:05:20 2015
@@ -5752,9 +5752,23 @@
<mime-type type="text/x-matlab">
<_comment>Matlab source code</_comment>
+ <!-- Multiple-output function definition -->
<magic priority="50">
<match value="function [" type="string" offset="0"/>
</magic>
+ <!-- Single-output or no output function definition -->
+ <magic priority="40">
+ <match value="function [a-zA-Z][A-Za-z0-9_]{0,5}" type="regex"
offset="0"/>
+ </magic>
+ <!-- Two matlab-style comments fairly early in the file -->
+ <magic priority="25">
+ <match value="%" type="string" offset="0">
+ <match value="\n%" type="string" offset="2:120"/>
+ </match>
+ <match value="%" type="string" offset="0">
+ <match value="\r%" type="string" offset="2:120"/>
+ </match>
+ </magic>
<!-- <glob pattern="*.m"/> - conflicts with text/x-objcsrc -->
<sub-class-of type="text/plain"/>
</mime-type>
Modified:
tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
URL:
http://svn.apache.org/viewvc/tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java?rev=1681351&r1=1681350&r2=1681351&view=diff
==============================================================================
---
tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
(original)
+++
tika/trunk/tika-parsers/src/test/java/org/apache/tika/mime/TestMimeTypes.java
Sat May 23 14:05:20 2015
@@ -930,6 +930,15 @@ public class TestMimeTypes {
assertTypeByData("application/zlib", "testTXT.zlib5");
assertTypeByData("application/zlib", "testTXT.zlib9");
}
+
+ @Test
+ public void testCodeFormats() throws Exception {
+ assertType("text/x-csrc", "testC.c");
+
+ assertType("text/x-matlab", "testMATLAB.m");
+ assertType("text/x-matlab", "testMATLAB_wtsgaus.m");
+ assertType("text/x-matlab", "testMATLAB_barcast.m");
+ }
private void assertText(byte[] prefix) throws IOException {
assertMagic("text/plain", prefix);