Work around a bug in libxml2

This commit works around a bug in libxml2 where parsing schemas can
result in dangling pointers which can lead to a segv.

Upstream bug is here:  https://gitlab.gnome.org/GNOME/libxml2/issues/148

Fixes #1985

Author: tenderlove

ext/nokogiri/xml_schema.c

@@ -133,6 +133,31 @@ static VALUE read_memory(VALUE klass, VALUE content)
   return rb_schema;
 }
 
+/* Schema creation will remove and deallocate "blank" nodes.
+ * If those blank nodes have been exposed to Ruby, they could get freed
+ * out from under the VALUE pointer.  This function checks to see if any of
+ * those nodes have been exposed to Ruby, and if so we should raise an exception.
+ */
+static int has_blank_nodes_p(VALUE cache)
+{
+    long i;
+
+    if (NIL_P(cache)) {
+        return 0;
+    }
+
+    for (i = 0; i < RARRAY_LEN(cache); i++) {
+        xmlNodePtr node;
+        VALUE element = rb_ary_entry(cache, i);
+        Data_Get_Struct(element, xmlNode, node);
+        if (xmlIsBlankNode(node)) {
+            return 1;
+        }
+    }
+
+    return 0;
+}
+
 /*
  * call-seq:
  *  from_document(doc)
@@ -152,6 +177,10 @@ static VALUE from_document(VALUE klass, VALUE document)
   /* In case someone passes us a node. ugh. */
   doc = doc->doc;
 
+  if (has_blank_nodes_p(DOC_NODE_CACHE(doc))) {
+    rb_raise(rb_eArgError, "Creating a schema from a document that has blank nodes exposed to Ruby is dangerous");
+  }
+
   ctx = xmlSchemaNewDocParserCtxt(doc);
 
   errors = rb_ary_new();

test/xml/test_schema.rb

@@ -7,6 +7,34 @@ def setup
         assert @xsd = Nokogiri::XML::Schema(File.read(PO_SCHEMA_FILE))
       end
 
+      def test_segv
+        skip("Pure Java version shouldn't have this bug") unless Nokogiri.uses_libxml?
+
+        # This is a test for a workaround for a bug in LibXML2.  The upstream
+        # bug is here: https://gitlab.gnome.org/GNOME/libxml2/issues/148
+        # Schema creation can result in dangling pointers.  If no nodes have
+        # been exposed, then it should be fine to create a schema.  If nodes
+        # have been exposed to Ruby, then we need to make sure they won't be
+        # freed out from under us.
+        doc = <<~doc
+<?xml version="1.0" encoding="UTF-8" ?><xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema">
+<xs:element name="foo" type="xs:string"/></xs:schema>
+        doc
+
+        # This is OK, no nodes have been exposed
+        xsd_doc = Nokogiri::XML(doc)
+        assert Nokogiri::XML::Schema.from_document(xsd_doc)
+
+        # This is not OK, nodes have been exposed to Ruby
+        xsd_doc = Nokogiri::XML(doc)
+        node = xsd_doc.root.children.find(&:blank?) # Finds a node
+
+        ex = assert_raise(ArgumentError) do
+          Nokogiri::XML::Schema.from_document(xsd_doc)
+        end
+        assert_match(/blank nodes/, ex.message)
+      end
+
       def test_schema_from_document
         doc = Nokogiri::XML(File.open(PO_SCHEMA_FILE))
         assert doc