You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tika.apache.org by ta...@apache.org on 2023/07/14 16:16:17 UTC

[tika] branch main updated: TIKA-3227 -- add unit test for skipping embedded documents with /rmeta

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

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


The following commit(s) were added to refs/heads/main by this push:
     new 41aa0cc62 TIKA-3227 -- add unit test for skipping embedded documents with /rmeta
41aa0cc62 is described below

commit 41aa0cc62f7e8b91816578085a0680fe9ca98463
Author: tallison <ta...@apache.org>
AuthorDate: Fri Jul 14 12:16:02 2023 -0400

    TIKA-3227 -- add unit test for skipping embedded documents with /rmeta
---
 .../standard/RecursiveMetadataResourceTest.java       | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/tika-server/tika-server-standard/src/test/java/org/apache/tika/server/standard/RecursiveMetadataResourceTest.java b/tika-server/tika-server-standard/src/test/java/org/apache/tika/server/standard/RecursiveMetadataResourceTest.java
index 691554edb..d4c059a1c 100644
--- a/tika-server/tika-server-standard/src/test/java/org/apache/tika/server/standard/RecursiveMetadataResourceTest.java
+++ b/tika-server/tika-server-standard/src/test/java/org/apache/tika/server/standard/RecursiveMetadataResourceTest.java
@@ -45,6 +45,7 @@ import org.apache.tika.metadata.OfficeOpenXMLExtended;
 import org.apache.tika.metadata.TikaCoreProperties;
 import org.apache.tika.metadata.serialization.JsonMetadataList;
 import org.apache.tika.server.core.CXFTestBase;
+import org.apache.tika.server.core.config.DocumentSelectorConfig;
 import org.apache.tika.server.core.resource.RecursiveMetadataResource;
 import org.apache.tika.server.core.writer.MetadataListMessageBodyWriter;
 
@@ -331,6 +332,24 @@ public class RecursiveMetadataResourceTest extends CXFTestBase {
         }
     }
 
+    // TIKA-3227
+    @Test
+    public void testSkipEmbedded() throws Exception {
+        Response response = WebClient.create(endPoint + META_PATH).accept("application/json")
+                .header(DocumentSelectorConfig.X_TIKA_SKIP_EMBEDDED_HEADER, "false")
+                .put(ClassLoader.getSystemResourceAsStream(TEST_RECURSIVE_DOC));
+        Reader reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
+        List<Metadata> metadataList = JsonMetadataList.fromJson(reader);
+        assertEquals(12, metadataList.size());
+
+        response = WebClient.create(endPoint + META_PATH).accept("application/json")
+                .header(DocumentSelectorConfig.X_TIKA_SKIP_EMBEDDED_HEADER, "true")
+                .put(ClassLoader.getSystemResourceAsStream(TEST_RECURSIVE_DOC));
+        reader = new InputStreamReader((InputStream) response.getEntity(), UTF_8);
+        metadataList = JsonMetadataList.fromJson(reader);
+        assertEquals(1, metadataList.size());
+    }
+
     @Test
     public void testWriteLimit() throws Exception {
         int writeLimit = 10;