You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by us...@apache.org on 2018/03/01 18:29:47 UTC

lucene-solr:branch_6_6: SOLR-11971: Don't allow referal to external resources in DataImportHandler's dataConfig request parameter

Repository: lucene-solr
Updated Branches:
  refs/heads/branch_6_6 51e712c06 -> dd3be31f7


SOLR-11971: Don't allow referal to external resources in DataImportHandler's dataConfig request parameter


Project: http://git-wip-us.apache.org/repos/asf/lucene-solr/repo
Commit: http://git-wip-us.apache.org/repos/asf/lucene-solr/commit/dd3be31f
Tree: http://git-wip-us.apache.org/repos/asf/lucene-solr/tree/dd3be31f
Diff: http://git-wip-us.apache.org/repos/asf/lucene-solr/diff/dd3be31f

Branch: refs/heads/branch_6_6
Commit: dd3be31f7062dcb2f3b2d7f0e89df29e197dee63
Parents: 51e712c
Author: Uwe Schindler <us...@apache.org>
Authored: Sun Feb 18 22:41:06 2018 +0100
Committer: Uwe Schindler <us...@apache.org>
Committed: Thu Mar 1 19:25:50 2018 +0100

----------------------------------------------------------------------
 solr/CHANGES.txt                                |  6 ++++--
 .../solr/handler/dataimport/DataImporter.java   | 17 +++++++++++++----
 .../handler/dataimport/TestErrorHandling.java   | 20 ++++++++++++++++++++
 3 files changed, 37 insertions(+), 6 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/dd3be31f/solr/CHANGES.txt
----------------------------------------------------------------------
diff --git a/solr/CHANGES.txt b/solr/CHANGES.txt
index 6cef677..1dda7a3 100644
--- a/solr/CHANGES.txt
+++ b/solr/CHANGES.txt
@@ -29,9 +29,11 @@ Apache UIMA 2.3.1
 Apache ZooKeeper 3.4.10
 Jetty 9.3.14.v20161028
 
+Bug Fixes
+----------------------
 
-(No Changes)
-
+* SOLR-11971: Don't allow referal to external resources in DataImportHandler's dataConfig request parameter.
+  (麦 香浓郁, Uwe Schindler)
 
 ==================  6.6.2 ==================
 

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/dd3be31f/solr/contrib/dataimporthandler/src/java/org/apache/solr/handler/dataimport/DataImporter.java
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/java/org/apache/solr/handler/dataimport/DataImporter.java b/solr/contrib/dataimporthandler/src/java/org/apache/solr/handler/dataimport/DataImporter.java
index a49b4f6..4825fd1 100644
--- a/solr/contrib/dataimporthandler/src/java/org/apache/solr/handler/dataimport/DataImporter.java
+++ b/solr/contrib/dataimporthandler/src/java/org/apache/solr/handler/dataimport/DataImporter.java
@@ -16,6 +16,7 @@
  */
 package org.apache.solr.handler.dataimport;
 
+import org.apache.solr.common.EmptyEntityResolver;
 import org.apache.solr.common.SolrException;
 import org.apache.solr.core.SolrCore;
 import org.apache.solr.schema.IndexSchema;
@@ -178,11 +179,11 @@ public class DataImporter {
   /**
    * Used by tests
    */
-  public void loadAndInit(String configStr) {
+  void loadAndInit(String configStr) {
     config = loadDataConfig(new InputSource(new StringReader(configStr)));
   }
 
-  public void loadAndInit(InputSource configFile) {
+  void loadAndInit(InputSource configFile) {
     config = loadDataConfig(configFile);
   }
 
@@ -191,8 +192,10 @@ public class DataImporter {
     DIHConfiguration dihcfg = null;
     try {
       DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
+      dbf.setValidating(false);
       
-      // only enable xinclude, if a a SolrCore and SystemId is present (makes no sense otherwise)
+      // only enable xinclude, if XML is coming from safe source (local file)
+      // and a a SolrCore and SystemId is present (makes no sense otherwise):
       if (core != null && configFile.getSystemId() != null) {
         try {
           dbf.setXIncludeAware(true);
@@ -203,8 +206,14 @@ public class DataImporter {
       }
       
       DocumentBuilder builder = dbf.newDocumentBuilder();
-      if (core != null)
+      // only enable xinclude / external entities, if XML is coming from
+      // safe source (local file) and a a SolrCore and SystemId is present:
+      if (core != null && configFile.getSystemId() != null) {
         builder.setEntityResolver(new SystemIdResolver(core.getResourceLoader()));
+      } else {
+        // Don't allow external entities without having a system ID:
+        builder.setEntityResolver(EmptyEntityResolver.SAX_INSTANCE);
+      }
       builder.setErrorHandler(XMLLOG);
       Document document;
       try {

http://git-wip-us.apache.org/repos/asf/lucene-solr/blob/dd3be31f/solr/contrib/dataimporthandler/src/test/org/apache/solr/handler/dataimport/TestErrorHandling.java
----------------------------------------------------------------------
diff --git a/solr/contrib/dataimporthandler/src/test/org/apache/solr/handler/dataimport/TestErrorHandling.java b/solr/contrib/dataimporthandler/src/test/org/apache/solr/handler/dataimport/TestErrorHandling.java
index 74eaf9e..1ea1ad4 100644
--- a/solr/contrib/dataimporthandler/src/test/org/apache/solr/handler/dataimport/TestErrorHandling.java
+++ b/solr/contrib/dataimporthandler/src/test/org/apache/solr/handler/dataimport/TestErrorHandling.java
@@ -89,6 +89,13 @@ public class TestErrorHandling extends AbstractDataImportHandlerTestCase {
     assertQ(req("*:*"), "//*[@numFound='3']");
   }
 
+  public void testExternalEntity() throws Exception {
+    StringDataSource.xml = wellformedXml;
+    // This should not fail as external entities are replaced by an empty string during parsing:
+    runFullImport(dataConfigWithEntity);
+    assertQ(req("*:*"), "//*[@numFound='3']");
+  }
+
   public static class StringDataSource extends DataSource<Reader> {
     public static String xml = "";
 
@@ -157,6 +164,19 @@ public class TestErrorHandling extends AbstractDataImportHandlerTestCase {
           "    </document>\n" +
           "</dataConfig>";
 
+  private String dataConfigWithEntity = "<!DOCTYPE dataConfig [\n" + 
+          "  <!ENTITY internalTerm \"node\">\n" + 
+          "  <!ENTITY externalTerm SYSTEM \"foo://bar.xyz/external\">\n" + 
+          "]><dataConfig>\n" +
+          "    <dataSource name=\"str\" type=\"TestErrorHandling$StringDataSource\" />" +
+          "    <document>\n" +
+          "        <entity name=\"&internalTerm;\" dataSource=\"str\" processor=\"XPathEntityProcessor\" url=\"test\" forEach=\"/root/node\" onError=\"skip\">\n" +
+          "            <field column=\"id\" xpath=\"/root/node/id\">&externalTerm;</field>\n" +
+          "            <field column=\"desc\" xpath=\"/root/node/desc\" />\n" +
+          "        </entity>\n" +
+          "    </document>\n" +
+          "</dataConfig>";
+
   private String malformedXml = "<root>\n" +
           "    <node>\n" +
           "        <id>1</id>\n" +