TIKA-4257 -- lower dbf priority (#1773)

apache · May 20, 2024 · 0190411 · 0190411
1 parent 7a03331
commit 0190411
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 2 deletions.
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
@@ -157,7 +157,8 @@
     <glob pattern="*.davmount"/>
   </mime-type>
   <mime-type type="application/x-dbf">
-    <magic priority="100">
+    <!-- this looks unique/precise. It isn't. False positives are common. Keep priority low. -->
+    <magic priority="40">
       <match value="(?s)^[\\x02\\x03\\x30\\x31\\x32\\x43\\x63\\x83\\x8B\\xCB\\xF5\\xE5\\xFB].[\\x01-\\x0C][\\x01-\\x1F].{4}(?:.[^\\x00]|[\\x41-\\xFF].)(?:[^\\x00\\x01].|.[^\\x00]).{31}(?&lt;=[\\x00][^\\x00]{0,10})[A-Z@+]" type="regex" offset="0"/>
     </magic>
     <glob pattern="*.dbf"/>

diff --git a/.../tika-parser-crypto-module/src/test/java/org/apache/tika/parser/crypto/TSDParserTest.java b/.../tika-parser-crypto-module/src/test/java/org/apache/tika/parser/crypto/TSDParserTest.java
@@ -116,7 +116,7 @@ public void testTSDFileData() throws Exception {
     @Test
     public void testTSDFileDataRecursiveMetadataXML() throws Exception {
         List<Metadata> list = getRecursiveMetadata("MANIFEST.XML.TSD");
-        assertEquals(2, list.size());
+        assertEquals(3, list.size());
         assertContains(TSDParser.class.getName(),
                 Arrays.asList(list.get(0).getValues(TikaCoreProperties.TIKA_PARSED_BY)));
     }