This is an automated email from the ASF dual-hosted git repository. stevel pushed a commit to branch trunk in repository https://gitbox.apache.org/repos/asf/hadoop.git
The following commit(s) were added to refs/heads/trunk by this push: new 4fe079f85fb HDFS-16795. Use secure XML parsers (#4979) 4fe079f85fb is described below commit 4fe079f85fb3d288f1b53a9f4668ad0025919e50 Author: PJ Fanning <pjfann...@users.noreply.github.com> AuthorDate: Mon Oct 10 18:56:35 2022 +0100 HDFS-16795. Use secure XML parsers (#4979) Contributed by P J Fanning --- .../java/org/apache/hadoop/hdfs/util/ECPolicyLoader.java | 9 +++------ .../hdfs/tools/offlineEditsViewer/XmlEditsVisitor.java | 2 +- .../tools/offlineImageViewer/OfflineImageReconstructor.java | 3 +++ .../java/org/apache/hadoop/hdfs/TestEncryptionZones.java | 4 ++-- .../tools/offlineImageViewer/TestOfflineImageViewer.java | 12 ++++++------ .../offlineImageViewer/TestOfflineImageViewerForAcl.java | 4 +++- 6 files changed, 18 insertions(+), 16 deletions(-) diff --git a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/util/ECPolicyLoader.java b/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/util/ECPolicyLoader.java index fcba618c94a..0d1be4b8e67 100644 --- a/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/util/ECPolicyLoader.java +++ b/hadoop-hdfs-project/hadoop-hdfs-client/src/main/java/org/apache/hadoop/hdfs/util/ECPolicyLoader.java @@ -20,6 +20,8 @@ package org.apache.hadoop.hdfs.util; import org.apache.hadoop.io.erasurecode.ECSchema; import org.apache.hadoop.classification.InterfaceAudience; import org.apache.hadoop.hdfs.protocol.ErasureCodingPolicy; +import org.apache.hadoop.util.XMLUtils; + import org.w3c.dom.Node; import org.w3c.dom.Text; import org.w3c.dom.Element; @@ -87,13 +89,8 @@ public class ECPolicyLoader { LOG.info("Loading EC policy file " + policyFile); // Read and parse the EC policy file. - DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance(); + DocumentBuilderFactory dbf = XMLUtils.newSecureDocumentBuilderFactory(); dbf.setIgnoringComments(true); - dbf.setFeature("http://apache.org/xml/features/disallow-doctype-decl", true); - dbf.setFeature("http://apache.org/xml/features/nonvalidating/load-external-dtd", false); - dbf.setFeature("http://xml.org/sax/features/external-general-entities", false); - dbf.setFeature("http://xml.org/sax/features/external-parameter-entities", false); - dbf.setFeature("http://apache.org/xml/features/dom/create-entity-ref-nodes", false); DocumentBuilder builder = dbf.newDocumentBuilder(); Document doc = builder.parse(policyFile); Element root = doc.getDocumentElement(); diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/tools/offlineEditsViewer/XmlEditsVisitor.java b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/tools/offlineEditsViewer/XmlEditsVisitor.java index ddf7933f032..9fabd1887ce 100644 --- a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/tools/offlineEditsViewer/XmlEditsVisitor.java +++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/tools/offlineEditsViewer/XmlEditsVisitor.java @@ -60,8 +60,8 @@ public class XmlEditsVisitor implements OfflineEditsVisitor { public XmlEditsVisitor(OutputStream out) throws IOException { this.out = out; - factory =(SAXTransformerFactory)SAXTransformerFactory.newInstance(); try { + factory = org.apache.hadoop.util.XMLUtils.newSecureSAXTransformerFactory(); TransformerHandler handler = factory.newTransformerHandler(); handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "xml"); handler.getTransformer().setOutputProperty(OutputKeys.ENCODING, "UTF-8"); diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/OfflineImageReconstructor.java b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/OfflineImageReconstructor.java index 78a7301db04..6a2049acb4b 100644 --- a/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/OfflineImageReconstructor.java +++ b/hadoop-hdfs-project/hadoop-hdfs/src/main/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/OfflineImageReconstructor.java @@ -56,6 +56,7 @@ import org.apache.hadoop.thirdparty.protobuf.TextFormat; import org.slf4j.Logger; import org.slf4j.LoggerFactory; + import org.apache.hadoop.classification.InterfaceAudience; import org.apache.hadoop.classification.InterfaceStability; import org.apache.hadoop.fs.permission.AclEntry; @@ -147,6 +148,8 @@ class OfflineImageReconstructor { InputStreamReader reader) throws XMLStreamException { this.out = out; XMLInputFactory factory = XMLInputFactory.newInstance(); + factory.setProperty(XMLInputFactory.SUPPORT_DTD, false); + factory.setProperty(XMLInputFactory.IS_SUPPORTING_EXTERNAL_ENTITIES, false); this.events = factory.createXMLEventReader(reader); this.sections = new HashMap<>(); this.sections.put(NameSectionProcessor.NAME, new NameSectionProcessor()); diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestEncryptionZones.java b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestEncryptionZones.java index 1900160ed91..12bc75a9f78 100644 --- a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestEncryptionZones.java +++ b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/TestEncryptionZones.java @@ -105,6 +105,7 @@ import org.apache.hadoop.util.ToolRunner; import org.apache.hadoop.crypto.key.KeyProviderDelegationTokenExtension.DelegationTokenExtension; import org.apache.hadoop.crypto.key.KeyProviderCryptoExtension.CryptoExtension; import org.apache.hadoop.io.Text; +import org.apache.hadoop.util.XMLUtils; import org.junit.After; import org.junit.Assert; import org.junit.Before; @@ -153,7 +154,6 @@ import org.xml.sax.InputSource; import org.xml.sax.helpers.DefaultHandler; import javax.xml.parsers.SAXParser; -import javax.xml.parsers.SAXParserFactory; public class TestEncryptionZones { static final Logger LOG = LoggerFactory.getLogger(TestEncryptionZones.class); @@ -1734,7 +1734,7 @@ public class TestEncryptionZones { PBImageXmlWriter v = new PBImageXmlWriter(new Configuration(), pw); v.visit(new RandomAccessFile(originalFsimage, "r")); final String xml = output.toString(); - SAXParser parser = SAXParserFactory.newInstance().newSAXParser(); + SAXParser parser = XMLUtils.newSecureSAXParserFactory().newSAXParser(); parser.parse(new InputSource(new StringReader(xml)), new DefaultHandler()); } diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/TestOfflineImageViewer.java b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/TestOfflineImageViewer.java index 9878469c89e..047750de225 100644 --- a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/TestOfflineImageViewer.java +++ b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/TestOfflineImageViewer.java @@ -95,6 +95,7 @@ import org.apache.hadoop.security.token.Token; import org.apache.hadoop.test.GenericTestUtils; import org.apache.hadoop.test.LambdaTestUtils; import org.apache.hadoop.util.Lists; +import org.apache.hadoop.util.XMLUtils; import org.apache.hadoop.thirdparty.com.google.common.collect.ImmutableMap; import org.apache.hadoop.thirdparty.com.google.common.collect.Maps; @@ -565,7 +566,7 @@ public class TestOfflineImageViewer { try (RandomAccessFile r = new RandomAccessFile(originalFsimage, "r")) { v.visit(r); } - SAXParserFactory spf = SAXParserFactory.newInstance(); + SAXParserFactory spf = XMLUtils.newSecureSAXParserFactory(); SAXParser parser = spf.newSAXParser(); final String xml = output.toString(); ECXMLHandler ecxmlHandler = new ECXMLHandler(); @@ -1028,13 +1029,13 @@ public class TestOfflineImageViewer { private void deleteINodeFromXML(File inputFile, File outputFile, List<Long> corruptibleIds) throws Exception { - DocumentBuilderFactory docFactory = DocumentBuilderFactory.newInstance(); + DocumentBuilderFactory docFactory = XMLUtils.newSecureDocumentBuilderFactory(); DocumentBuilder docBuilder = docFactory.newDocumentBuilder(); Document doc = docBuilder.parse(inputFile); properINodeDelete(corruptibleIds, doc); - TransformerFactory transformerFactory = TransformerFactory.newInstance(); + TransformerFactory transformerFactory = XMLUtils.newSecureTransformerFactory(); Transformer transformer = transformerFactory.newTransformer(); DOMSource source = new DOMSource(doc); StreamResult result = new StreamResult(outputFile); @@ -1370,10 +1371,9 @@ public class TestOfflineImageViewer { v.visit(new RandomAccessFile(originalFsimage, "r")); final String xml = output.toString(); - DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance(); + DocumentBuilderFactory dbf = XMLUtils.newSecureDocumentBuilderFactory(); DocumentBuilder db = dbf.newDocumentBuilder(); - InputSource is = new InputSource(); - is.setCharacterStream(new StringReader(xml)); + InputSource is = new InputSource(new StringReader(xml)); Document dom = db.parse(is); NodeList ecSection = dom.getElementsByTagName(ERASURE_CODING_SECTION_NAME); assertEquals(1, ecSection.getLength()); diff --git a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/TestOfflineImageViewerForAcl.java b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/TestOfflineImageViewerForAcl.java index 31dec3f5e5c..3af8e03d898 100644 --- a/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/TestOfflineImageViewerForAcl.java +++ b/hadoop-hdfs-project/hadoop-hdfs/src/test/java/org/apache/hadoop/hdfs/tools/offlineImageViewer/TestOfflineImageViewerForAcl.java @@ -47,6 +47,8 @@ import org.apache.hadoop.hdfs.server.namenode.FSImageTestUtil; import org.apache.hadoop.hdfs.web.WebHdfsFileSystem; import org.apache.hadoop.net.NetUtils; import org.apache.hadoop.util.Lists; +import org.apache.hadoop.util.XMLUtils; + import org.junit.AfterClass; import org.junit.BeforeClass; import org.junit.Test; @@ -221,7 +223,7 @@ public class TestOfflineImageViewerForAcl { PrintStream o = new PrintStream(output); PBImageXmlWriter v = new PBImageXmlWriter(new Configuration(), o); v.visit(new RandomAccessFile(originalFsimage, "r")); - SAXParserFactory spf = SAXParserFactory.newInstance(); + SAXParserFactory spf = XMLUtils.newSecureSAXParserFactory(); SAXParser parser = spf.newSAXParser(); final String xml = output.toString(); parser.parse(new InputSource(new StringReader(xml)), new DefaultHandler()); --------------------------------------------------------------------- To unsubscribe, e-mail: common-commits-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-commits-h...@hadoop.apache.org