This is an automated email from the ASF dual-hosted git repository. lewismc pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/nutch.git
The following commit(s) were added to refs/heads/master by this push: new 59c63c7 NUTCH-2841 Upgrade xercesImpl dependency (#563) 59c63c7 is described below commit 59c63c7d8a13b0de1fd1da6aa4a1ab6e20fa478d Author: Lewis John McGibbney <lewis.mcgibb...@gmail.com> AuthorDate: Wed Jan 13 10:56:07 2021 -0800 NUTCH-2841 Upgrade xercesImpl dependency (#563) * NUTCH-2841 Upgrade xercesImpl dependency --- ivy/ivy.xml | 2 +- src/java/org/apache/nutch/tools/DmozParser.java | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/ivy/ivy.xml b/ivy/ivy.xml index ad1e65f..3f1faf3 100644 --- a/ivy/ivy.xml +++ b/ivy/ivy.xml @@ -66,7 +66,7 @@ <dependency org="org.apache.tika" name="tika-core" rev="1.25" /> <dependency org="xml-apis" name="xml-apis" rev="1.4.01"/><!-- force this version as it is required by Tika --> - <dependency org="xerces" name="xercesImpl" rev="2.12.0" /> + <dependency org="xerces" name="xercesImpl" rev="2.12.1" /> <dependency org="com.ibm.icu" name="icu4j" rev="68.2" /> diff --git a/src/java/org/apache/nutch/tools/DmozParser.java b/src/java/org/apache/nutch/tools/DmozParser.java index 63dbde8..a447646 100644 --- a/src/java/org/apache/nutch/tools/DmozParser.java +++ b/src/java/org/apache/nutch/tools/DmozParser.java @@ -276,8 +276,11 @@ public class DmozParser { throws IOException, SAXException, ParserConfigurationException { SAXParserFactory parserFactory = SAXParserFactory.newInstance(); + parserFactory.setFeature("http://xml.org/sax/features/external-general-entities", false); + parserFactory.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true); SAXParser parser = parserFactory.newSAXParser(); XMLReader reader = parser.getXMLReader(); + reader.setFeature("http://xml.org/sax/features/external-general-entities", false); // Create our own processor to receive SAX events RDFProcessor rp = new RDFProcessor(reader, subsetDenom, includeAdult, skew,