Merge pull request #94 from rowland66/fix-superfluous-namespace-decla…

…ration-cleanup

Fixed the removal of superfluous namespace declarations

canonicalize.go

@@ -25,8 +25,7 @@ func (c *NullCanonicalizer) Algorithm() AlgorithmID {
 }
 
 func (c *NullCanonicalizer) Canonicalize(el *etree.Element) ([]byte, error) {
-	scope := make(map[string]struct{})
-	return canonicalSerialize(canonicalPrep(el, scope, false, true))
+	return canonicalSerialize(canonicalPrep(el, false, true))
 }
 
 type c14N10ExclusiveCanonicalizer struct {
@@ -89,8 +88,7 @@ func MakeC14N11WithCommentsCanonicalizer() Canonicalizer {
 
 // Canonicalize transforms the input Element into a serialized XML document in canonical form.
 func (c *c14N11Canonicalizer) Canonicalize(el *etree.Element) ([]byte, error) {
-	scope := make(map[string]struct{})
-	return canonicalSerialize(canonicalPrep(el, scope, true, c.comments))
+	return canonicalSerialize(canonicalPrep(el, true, c.comments))
 }
 
 func (c *c14N11Canonicalizer) Algorithm() AlgorithmID {
@@ -123,8 +121,7 @@ func (c *c14N10RecCanonicalizer) Canonicalize(inputXML *etree.Element) ([]byte,
 	parentNamespaceAttributes, parentXmlAttributes := getParentNamespaceAndXmlAttributes(inputXML)
 	inputXMLCopy := inputXML.Copy()
 	enhanceNamespaceAttributes(inputXMLCopy, parentNamespaceAttributes, parentXmlAttributes)
-	scope := make(map[string]struct{})
-	return canonicalSerialize(canonicalPrep(inputXMLCopy, scope, true, c.comments))
+	return canonicalSerialize(canonicalPrep(inputXMLCopy, true, c.comments))
 }
 
 func (c *c14N10RecCanonicalizer) Algorithm() AlgorithmID {
@@ -161,8 +158,12 @@ const nsSpace = "xmlns"
 //
 // TODO(russell_h): This is very similar to excCanonicalPrep - perhaps they should
 // be unified into one parameterized function?
-func canonicalPrep(el *etree.Element, seenSoFar map[string]struct{}, strip bool, comments bool) *etree.Element {
-	_seenSoFar := make(map[string]struct{})
+func canonicalPrep(el *etree.Element, strip bool, comments bool) *etree.Element {
+	return canonicalPrepInner(el, make(map[string]string), strip, comments)
+}
+
+func canonicalPrepInner(el *etree.Element, seenSoFar map[string]string, strip bool, comments bool) *etree.Element {
+	_seenSoFar := make(map[string]string)
 	for k, v := range seenSoFar {
 		_seenSoFar[k] = v
 	}
@@ -171,16 +172,25 @@ func canonicalPrep(el *etree.Element, seenSoFar map[string]struct{}, strip bool,
 	sort.Sort(etreeutils.SortedAttrs(ne.Attr))
 	n := 0
 	for _, attr := range ne.Attr {
-		if attr.Space != nsSpace {
+		if attr.Space != nsSpace && !(attr.Space == "" && attr.Key == nsSpace) {
 			ne.Attr[n] = attr
 			n++
 			continue
 		}
-		key := attr.Space + ":" + attr.Key
-		if _, seen := _seenSoFar[key]; !seen {
-			ne.Attr[n] = attr
-			n++
-			_seenSoFar[key] = struct{}{}
+
+		if attr.Space == nsSpace {
+			key := attr.Space + ":" + attr.Key
+			if uri, seen := _seenSoFar[key]; !seen || attr.Value != uri {
+				ne.Attr[n] = attr
+				n++
+				_seenSoFar[key] = attr.Value
+			}
+		} else {
+			if uri, seen := _seenSoFar[nsSpace]; (!seen && attr.Value != "") || attr.Value != uri {
+				ne.Attr[n] = attr
+				n++
+				_seenSoFar[nsSpace] = attr.Value
+			}
 		}
 	}
 	ne.Attr = ne.Attr[:n]
@@ -199,7 +209,7 @@ func canonicalPrep(el *etree.Element, seenSoFar map[string]struct{}, strip bool,
 	for i, token := range ne.Child {
 		childElement, ok := token.(*etree.Element)
 		if ok {
-			ne.Child[i] = canonicalPrep(childElement, _seenSoFar, strip, comments)
+			ne.Child[i] = canonicalPrepInner(childElement, _seenSoFar, strip, comments)
 		}
 	}
 

canonicalize_test.go

@@ -82,6 +82,44 @@ func TestExcC14nRedeclareDefaultNamespace(t *testing.T) {
 	runCanonicalizationTest(t, canonicalizer, input, expected)
 }
 
+func TestC14N10RecCanonicalizer(t *testing.T) {
+	// From https://www.w3.org/TR/2001/REC-xml-c14n-20010315#Example-SETags
+	input := `<doc>
+   <e1   />
+   <e2   ></e2>
+   <e3   name = "elem3"   id="elem3"   />
+   <e4   name="elem4"   id="elem4"   ></e4>
+   <e5 a:attr="out" b:attr="sorted" attr2="all" attr="I'm"
+      xmlns:b="http://www.ietf.org"
+      xmlns:a="http://www.w3.org"
+      xmlns="http://example.org"/>
+   <e6 xmlns="" xmlns:a="http://www.w3.org">
+      <e7 xmlns="http://www.ietf.org">
+         <e8 xmlns="" xmlns:a="http://www.w3.org">
+            <e9 xmlns="" xmlns:a="http://www.ietf.org"/>
+         </e8>
+      </e7>
+   </e6>
+</doc>`
+	expected := `<doc>
+   <e1></e1>
+   <e2></e2>
+   <e3 id="elem3" name="elem3"></e3>
+   <e4 id="elem4" name="elem4"></e4>
+   <e5 xmlns="http://example.org" xmlns:a="http://www.w3.org" xmlns:b="http://www.ietf.org" attr="I'm" attr2="all" b:attr="sorted" a:attr="out"></e5>
+   <e6 xmlns:a="http://www.w3.org">
+      <e7 xmlns="http://www.ietf.org">
+         <e8 xmlns="">
+            <e9 xmlns:a="http://www.ietf.org"></e9>
+         </e8>
+      </e7>
+   </e6>
+</doc>`
+
+	canonicalizer := MakeC14N10RecCanonicalizer()
+	runCanonicalizationTest(t, canonicalizer, input, expected)
+}
+
 func TestC14N10RecCanonicalizerWithNamespaceInheritance(t *testing.T) {
 	input := `<RootElement xmlns="http://www.example.com/ns1" xmlns:ns2="http://www.example.com/ns2">
 		<ns2:ChildElement>

etreeutils/sort.go

@@ -61,6 +61,10 @@ func (a SortedAttrs) Less(i, j int) bool {
 	}
 
 	// Attributes in the same namespace are sorted by their Namespace URI, not the prefix.
+	// NOTE: This implementation is not complete because it does not consider namespace
+	// prefixes declared in ancestor elements. A complete solution would ideally use the
+	// Attribute.NamespaceURI() method obtain a namespace URI for sorting, but the
+	// beevik/etree library needs to be fixed to provide the correct value first.
 	if a[i].Key == a[j].Key {
 		var leftNS, rightNS etree.Attr
 		for n := range a {

validate.go

@@ -363,10 +363,10 @@ func (ctx *ValidationContext) findSignature(root *etree.Element) (*types.Signatu
 					canonicalSignedInfo = detachedSignedInfo
 
 				case CanonicalXML11AlgorithmId, CanonicalXML10RecAlgorithmId:
-					canonicalSignedInfo = canonicalPrep(detachedSignedInfo, map[string]struct{}{}, true, false)
+					canonicalSignedInfo = canonicalPrep(detachedSignedInfo, true, false)
 
 				case CanonicalXML11WithCommentsAlgorithmId, CanonicalXML10WithCommentsAlgorithmId:
-					canonicalSignedInfo = canonicalPrep(detachedSignedInfo, map[string]struct{}{}, true, true)
+					canonicalSignedInfo = canonicalPrep(detachedSignedInfo, true, true)
 
 				default:
 					return fmt.Errorf("invalid CanonicalizationMethod on Signature: %s", c14NAlgorithm)