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 8b11962a4e9d248691ab36cc788284d7d6a5eaf1 Merge: 582cdd417 40881e8b7 Author: Sebastian Nagel <[email protected]> AuthorDate: Tue Sep 17 17:03:50 2024 +0200 Merge pull request #816 from sebastian-nagel/NUTCH-1942-domain-utils-to-use-crawler-commons NUTCH-1806 Delegate processing of URL domains to crawler-commons NUTCH-1942 Remove TopLevelDomain conf/domain-suffixes.xml.template | 4428 -------------------- conf/domain-suffixes.xsd | 130 - default.properties | 1 - src/bin/nutch | 2 +- .../nutch/util/{domain => }/DomainStatistics.java | 7 +- src/java/org/apache/nutch/util/URLUtil.java | 214 +- .../org/apache/nutch/util/domain/DomainSuffix.java | 78 - .../apache/nutch/util/domain/DomainSuffixes.java | 91 - .../nutch/util/domain/DomainSuffixesReader.java | 164 - .../apache/nutch/util/domain/TopLevelDomain.java | 66 - .../org/apache/nutch/util/domain/package-info.java | 28 - .../nutch/indexer/tld/TLDIndexingFilter.java | 13 +- .../apache/nutch/scoring/tld/TLDScoringFilter.java | 60 - .../org/apache/nutch/scoring/tld/package-info.java | 19 - .../nutch/urlfilter/domain/DomainURLFilter.java | 9 +- .../domaindenylist/DomainDenylistURLFilter.java | 9 +- src/test/org/apache/nutch/util/TestURLUtil.java | 81 +- 17 files changed, 208 insertions(+), 5192 deletions(-)
