This is an automated email from the ASF dual-hosted git repository. snagel pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/nutch.git
commit c7cf56964e4f901510d2a795213c6e649b8cc3b7 Author: Sebastian Nagel <[email protected]> AuthorDate: Fri Dec 12 15:14:04 2025 +0100 NUTCH-3136 Upgrade crawler-commons dependency Update URLUtil test to adapt to a change in the public suffix list --- src/test/org/apache/nutch/util/TestURLUtil.java | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/src/test/org/apache/nutch/util/TestURLUtil.java b/src/test/org/apache/nutch/util/TestURLUtil.java index 59e486d69..32dda0929 100644 --- a/src/test/org/apache/nutch/util/TestURLUtil.java +++ b/src/test/org/apache/nutch/util/TestURLUtil.java @@ -78,8 +78,13 @@ public class TestURLUtil { assertEquals("example.2000.hu", URLUtil.getDomainName(url)); // test non-ascii - url = new URL("http://www.example.商業.tw"); - assertEquals("example.商業.tw", URLUtil.getDomainName(url)); + url = new URL("http://www.example.flå.no"); + assertEquals("example.flå.no", URLUtil.getDomainName(url)); + url = new URL("http://www.example.栃木.jp"); + assertEquals("example.栃木.jp", URLUtil.getDomainName(url)); + // broken by https://github.com/publicsuffix/list/commit/408a7b0bdec993884865baaa2f0d14cc9a060885 + // url = new URL("http://www.example.商業.tw"); + // Assert.assertEquals("example.商業.tw", URLUtil.getDomainName(url)); // test URL without host/authority url = new URL("file:/path/index.html"); @@ -141,9 +146,14 @@ public class TestURLUtil { url = new URL("http://www.example.2000.hu"); assertEquals("2000.hu", URLUtil.getDomainSuffix(url)); - // test non-ascii - url = new URL("http://www.example.商業.tw"); - assertEquals("xn--czrw28b.tw", URLUtil.getDomainSuffix(url)); + // test non-ASCII + url = new URL("http://www.example.flå.no"); + assertEquals("xn--fl-zia.no", URLUtil.getDomainSuffix(url)); + url = new URL("http://www.example.栃木.jp"); + assertEquals("xn--4pvxs.jp", URLUtil.getDomainSuffix(url)); + // broken by https://github.com/publicsuffix/list/commit/408a7b0bdec993884865baaa2f0d14cc9a060885 + // url = new URL("http://www.example.商業.tw"); + // assertEquals("xn--czrw28b.tw", URLUtil.getDomainSuffix(url)); } @Test
