You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@stormcrawler.apache.org by rz...@apache.org on 2026/09/23 18:16:52 UTC
(stormcrawler) 01/01: #2097 ParserBoltTimeoutTest: use an explicit charset
This is an automated email from the ASF dual-hosted git repository.
rzo1 pushed a commit to branch fix-2097-tika-parse-timeout
in repository https://gitbox.apache.org/repos/asf/stormcrawler.git
commit 36670fc19dc037ce4cd9990ea398d9b68070b241
Author: Richard Zowalla <rz...@apache.org>
AuthorDate: Wed Sep 23 20:16:37 2026 +0200
#2097 ParserBoltTimeoutTest: use an explicit charset
---
.../test/java/org/apache/stormcrawler/tika/ParserBoltTimeoutTest.java | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/external/tika/src/test/java/org/apache/stormcrawler/tika/ParserBoltTimeoutTest.java b/external/tika/src/test/java/org/apache/stormcrawler/tika/ParserBoltTimeoutTest.java
index d995d9a1..38d8ce77 100644
--- a/external/tika/src/test/java/org/apache/stormcrawler/tika/ParserBoltTimeoutTest.java
+++ b/external/tika/src/test/java/org/apache/stormcrawler/tika/ParserBoltTimeoutTest.java
@@ -172,7 +172,8 @@ class ParserBoltTimeoutTest extends ParsingTester {
// not a valid PDF, the parser fails
Metadata metadata = new Metadata();
metadata.setValue("Content-Type", "application/pdf");
- parse("https://example.org/broken.pdf", "%PDF-1.4 broken".getBytes(), metadata);
+ byte[] content = "%PDF-1.4 broken".getBytes(StandardCharsets.UTF_8);
+ parse("https://example.org/broken.pdf", content, metadata);
List<List<Object>> status = output.getEmitted(Constants.StatusStreamName);
Assertions.assertEquals(1, status.size());