[tika] branch master updated: TIKA-2039 -- extra unit test... ensure standard handling of exception in embedded file

[ta...@apache.org]

This is an automated email from the ASF dual-hosted git repository.

tallison pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/tika.git

The following commit(s) were added to refs/heads/master by this push:
       new  11ad0fd   TIKA-2039 -- extra unit test... ensure standard handling of exception in embedded file
11ad0fd is described below

commit 11ad0fd294fd4b673ecbed451c2057eae42a9f27
Author: tballison <ta...@mitre.org>
AuthorDate: Wed Apr 26 10:47:09 2017 -0400

    TIKA-2039 -- extra unit test... ensure standard handling of
    exception in embedded file
---
 .../org/apache/tika/parser/crypto/TSDParserTest.java    |  12 ++++++++++++
 .../resources/test-documents/testTSD_broken_pdf.tsd     | Bin 0 -> 91985 bytes
 2 files changed, 12 insertions(+)

diff --git a/tika-parsers/src/test/java/org/apache/tika/parser/crypto/TSDParserTest.java b/tika-parsers/src/test/java/org/apache/tika/parser/crypto/TSDParserTest.java
index 2a73020..97a4130 100644
--- a/tika-parsers/src/test/java/org/apache/tika/parser/crypto/TSDParserTest.java
+++ b/tika-parsers/src/test/java/org/apache/tika/parser/crypto/TSDParserTest.java
@@ -10,6 +10,7 @@ import java.util.List;
 import org.apache.tika.TikaTest;
 import org.apache.tika.metadata.Metadata;
 import org.apache.tika.parser.ParseContext;
+import org.apache.tika.parser.RecursiveParserWrapper;
 import org.apache.tika.sax.BodyContentHandler;
 import org.junit.Test;
 import org.xml.sax.ContentHandler;
@@ -148,4 +149,15 @@ public class TSDParserTest extends TikaTest {
         assertContains(TSDParser.class.getName(),
                 Arrays.asList(list.get(0).getValues("X-Parsed-By")));
     }
+
+    @Test
+    public void testBrokenPdf() throws Exception {
+        //make sure that embedded file appears in list
+        //and make sure embedded exception is recorded
+        List<Metadata> list = getRecursiveMetadata("testTSD_broken_pdf.tsd");
+        assertEquals(2, list.size());
+        assertEquals("application/pdf", list.get(1).get(Metadata.CONTENT_TYPE));
+        assertNotNull(list.get(1).get(RecursiveParserWrapper.EMBEDDED_EXCEPTION));
+        assertContains("org.apache.pdfbox.pdmodel.PDDocument.load", list.get(1).get(RecursiveParserWrapper.EMBEDDED_EXCEPTION));
+    }
 }
diff --git a/tika-parsers/src/test/resources/test-documents/testTSD_broken_pdf.tsd b/tika-parsers/src/test/resources/test-documents/testTSD_broken_pdf.tsd
new file mode 100644
index 0000000..9fe32a1
Binary files /dev/null and b/tika-parsers/src/test/resources/test-documents/testTSD_broken_pdf.tsd differ

-- 
To stop receiving notification emails like this one, please contact
['"commits@tika.apache.org" <co...@tika.apache.org>'].