Menu
▾
▴
SF.net SVN: xmlunit:[481] trunk/xmlunit/src
|
From: <bo...@us...> - 2010-09-17 11:50:37
|
Revision: 481
http://xmlunit.svn.sourceforge.net/xmlunit/?rev=481&view=rev
Author: bodewig
Date: 2010-09-17 11:50:31 +0000 (Fri, 17 Sep 2010)
Log Message:
-----------
implement whitespace nomalization
Modified Paths:
--------------
trunk/xmlunit/src/main/java-core/net/sf/xmlunit/util/Nodes.java
trunk/xmlunit/src/main/java-legacy/org/custommonkey/xmlunit/Diff.java
trunk/xmlunit/src/main/java-legacy/org/custommonkey/xmlunit/NewDifferenceEngine.java
trunk/xmlunit/src/main/net-core/util/Nodes.cs
trunk/xmlunit/src/tests/java-core/net/sf/xmlunit/util/NodesTest.java
trunk/xmlunit/src/tests/net-core/util/NodesTest.cs
Added Paths:
-----------
trunk/xmlunit/src/main/java-core/net/sf/xmlunit/input/WhitespaceNormalizedSource.java
trunk/xmlunit/src/main/net-core/input/WhitespaceNormalizedSource.cs
Copied: trunk/xmlunit/src/main/java-core/net/sf/xmlunit/input/WhitespaceNormalizedSource.java (from rev 479, trunk/xmlunit/src/main/java-core/net/sf/xmlunit/input/WhitespaceStrippedSource.java)
===================================================================
--- trunk/xmlunit/src/main/java-core/net/sf/xmlunit/input/WhitespaceNormalizedSource.java (rev 0)
+++ trunk/xmlunit/src/main/java-core/net/sf/xmlunit/input/WhitespaceNormalizedSource.java 2010-09-17 11:50:31 UTC (rev 481)
@@ -0,0 +1,35 @@
+/*
+ This file is licensed to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+*/
+package net.sf.xmlunit.input;
+
+import javax.xml.transform.Source;
+import javax.xml.transform.dom.DOMSource;
+import net.sf.xmlunit.util.Convert;
+import net.sf.xmlunit.util.Nodes;
+
+/**
+ * A source that is obtained from a different source by removing all
+ * empty text nodes and normalizing the non-empty ones.
+ *
+ * <p>"normalized" in this context means all whitespace characters
+ * are replaced by space characters and consecutive whitespace
+ * characaters are collapsed.</p>
+ */
+public class WhitespaceNormalizedSource extends DOMSource {
+
+ public WhitespaceNormalizedSource(Source originalSource) {
+ super(Nodes.normalizeWhitespace(Convert.toDocument(originalSource)));
+ setSystemId(originalSource.getSystemId());
+ }
+}
Modified: trunk/xmlunit/src/main/java-core/net/sf/xmlunit/util/Nodes.java
===================================================================
--- trunk/xmlunit/src/main/java-core/net/sf/xmlunit/util/Nodes.java 2010-09-16 15:13:39 UTC (rev 480)
+++ trunk/xmlunit/src/main/java-core/net/sf/xmlunit/util/Nodes.java 2010-09-17 11:50:31 UTC (rev 481)
@@ -91,21 +91,43 @@
public static Node stripWhitespace(Node original) {
Node cloned = original.cloneNode(true);
cloned.normalize();
- stripWsRec(cloned);
+ handleWsRec(cloned, false);
return cloned;
}
/**
+ * Creates a new Node (of the same type as the original node) that
+ * is similar to the orginal but doesn't contain any empty text or
+ * CDATA nodes and where all textual content including attribute
+ * values or comments are trimmed and normalized.
+ *
+ * <p>"normalized" in this context means all whitespace characters
+ * are replaced by space characters and consecutive whitespace
+ * characaters are collapsed.</p>
+ */
+ public static Node normalizeWhitespace(Node original) {
+ Node cloned = original.cloneNode(true);
+ cloned.normalize();
+ handleWsRec(cloned, true);
+ return cloned;
+ }
+
+ /**
* Trims textual content of this node, removes empty text and
* CDATA children, recurses into its child nodes.
+ * @param normalize whether to normalize whitespace as well
*/
- private static void stripWsRec(Node n) {
+ private static void handleWsRec(Node n, boolean normalize) {
if (n instanceof CharacterData || n instanceof ProcessingInstruction) {
- n.setNodeValue(n.getNodeValue().trim());
+ String s = n.getNodeValue().trim();
+ if (normalize) {
+ s = normalize(s);
+ }
+ n.setNodeValue(s);
}
List<Node> toRemove = new LinkedList<Node>();
for (Node child : new IterableNodeList(n.getChildNodes())) {
- stripWsRec(child);
+ handleWsRec(child, normalize);
if (!(n instanceof Attr)
&& (child instanceof Text || child instanceof CDATASection)
&& child.getNodeValue().length() == 0) {
@@ -119,8 +141,40 @@
if (attrs != null) {
final int len = attrs.getLength();
for (int i = 0; i < len; i++) {
- stripWsRec(attrs.item(i));
+ handleWsRec(attrs.item(i), normalize);
}
}
}
+
+ private static final char SPACE = ' ';
+
+ /**
+ * Normalize a string.
+ *
+ * <p>"normalized" in this context means all whitespace characters
+ * are replaced by space characters and consecutive whitespace
+ * characaters are collapsed.</p>
+ */
+ static String normalize(String s) {
+ StringBuilder sb = new StringBuilder();
+ boolean changed = false;
+ boolean lastCharWasWS = false;
+ final int len = s.length();
+ for (int i = 0; i < len; i++) {
+ char c = s.charAt(i);
+ if (Character.isWhitespace(c)) {
+ if (!lastCharWasWS) {
+ sb.append(SPACE);
+ changed |= (c != SPACE);
+ } else {
+ changed = true;
+ }
+ lastCharWasWS = true;
+ } else {
+ sb.append(c);
+ lastCharWasWS = false;
+ }
+ }
+ return changed ? sb.toString() : s;
+ }
}
Modified: trunk/xmlunit/src/main/java-legacy/org/custommonkey/xmlunit/Diff.java
===================================================================
--- trunk/xmlunit/src/main/java-legacy/org/custommonkey/xmlunit/Diff.java 2010-09-16 15:13:39 UTC (rev 480)
+++ trunk/xmlunit/src/main/java-legacy/org/custommonkey/xmlunit/Diff.java 2010-09-17 11:50:31 UTC (rev 481)
@@ -423,8 +423,6 @@
if (
XMLUnit.getIgnoreAttributeOrder()
&&
- !XMLUnit.getNormalizeWhitespace()
- &&
(!usesUnknownElementQualifier()
|| XMLUnit.getCompareUnmatched())
) {
Modified: trunk/xmlunit/src/main/java-legacy/org/custommonkey/xmlunit/NewDifferenceEngine.java
===================================================================
--- trunk/xmlunit/src/main/java-legacy/org/custommonkey/xmlunit/NewDifferenceEngine.java 2010-09-16 15:13:39 UTC (rev 480)
+++ trunk/xmlunit/src/main/java-legacy/org/custommonkey/xmlunit/NewDifferenceEngine.java 2010-09-17 11:50:31 UTC (rev 481)
@@ -57,6 +57,7 @@
import net.sf.xmlunit.diff.ElementSelectors;
import net.sf.xmlunit.diff.NodeMatcher;
import net.sf.xmlunit.input.CommentLessSource;
+import net.sf.xmlunit.input.WhitespaceNormalizedSource;
import net.sf.xmlunit.input.WhitespaceStrippedSource;
import net.sf.xmlunit.util.Linqy;
import org.custommonkey.xmlunit.examples.RecursiveElementNameAndTextQualifier;
@@ -200,7 +201,10 @@
ctrlSource = new CommentLessSource(ctrlSource);
tstSource = new CommentLessSource(tstSource);
}
- if (XMLUnit.getIgnoreWhitespace()) {
+ if (XMLUnit.getNormalizeWhitespace()) {
+ ctrlSource = new WhitespaceNormalizedSource(ctrlSource);
+ tstSource = new WhitespaceNormalizedSource(tstSource);
+ } else if (XMLUnit.getIgnoreWhitespace()) {
ctrlSource = new WhitespaceStrippedSource(ctrlSource);
tstSource = new WhitespaceStrippedSource(tstSource);
}
Copied: trunk/xmlunit/src/main/net-core/input/WhitespaceNormalizedSource.cs (from rev 479, trunk/xmlunit/src/main/net-core/input/WhitespaceStrippedSource.cs)
===================================================================
--- trunk/xmlunit/src/main/net-core/input/WhitespaceNormalizedSource.cs (rev 0)
+++ trunk/xmlunit/src/main/net-core/input/WhitespaceNormalizedSource.cs 2010-09-17 11:50:31 UTC (rev 481)
@@ -0,0 +1,35 @@
+/*
+ This file is licensed to You under the Apache License, Version 2.0
+ (the "License"); you may not use this file except in compliance with
+ the License. You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+*/
+
+using net.sf.xmlunit.util;
+
+namespace net.sf.xmlunit.input {
+
+ /// <summary>
+ /// A source that is obtained from a different source by removing
+ /// all empty text nodes and normalizing the non-empty ones.
+ /// </summary>
+ /// <remarks>
+ /// "normalized" in this context means all whitespace characters
+ /// are replaced by space characters and consecutive whitespace
+ /// characaters are collapsed.
+ /// </remarks>
+ public class WhitespaceNormalizedSource : DOMSource {
+ public WhitespaceNormalizedSource(ISource originalSource) :
+ base(Nodes.NormalizeWhitespace(Convert.ToDocument(originalSource)))
+ {
+ SystemId = originalSource.SystemId;
+ }
+ }
+}
Modified: trunk/xmlunit/src/main/net-core/util/Nodes.cs
===================================================================
--- trunk/xmlunit/src/main/net-core/util/Nodes.cs 2010-09-16 15:13:39 UTC (rev 480)
+++ trunk/xmlunit/src/main/net-core/util/Nodes.cs 2010-09-17 11:50:31 UTC (rev 481)
@@ -74,21 +74,45 @@
public static XmlNode StripWhitespace(XmlNode original) {
XmlNode cloned = original.CloneNode(true);
cloned.Normalize();
- StripWsRec(cloned);
+ HandleWsRec(cloned, false);
return cloned;
}
/// <summary>
+ /// Creates a new Node (of the same type as the original node)
+ /// that is similar to the orginal but doesn't contain any
+ /// empty text or CDATA nodes and where all textual content
+ /// including attribute values or comments are normalized.
+ /// </summary>
+ /// <remarks>
+ /// "normalized" in this context means all whitespace
+ /// characters are replaced by space characters and
+ /// consecutive whitespace characaters are collapsed.
+ /// </remarks>
+ public static XmlNode NormalizeWhitespace(XmlNode original) {
+ XmlNode cloned = original.CloneNode(true);
+ cloned.Normalize();
+ HandleWsRec(cloned, true);
+ return cloned;
+ }
+
+ /// <summary>
/// Trims textual content of this node, removes empty text and
/// CDATA children, recurses into its child nodes.
/// </summary>
- private static void StripWsRec(XmlNode n) {
+ /// <parameter name="normalize">whether to normalize
+ /// whitespace as well</parameter>
+ private static void HandleWsRec(XmlNode n, bool normalize) {
if (n is XmlCharacterData || n is XmlProcessingInstruction) {
- n.Value = n.Value.Trim();
+ string s = n.Value.Trim();
+ if (normalize) {
+ s = Normalize(s);
+ }
+ n.Value = s;
}
LinkedList<XmlNode> toRemove = new LinkedList<XmlNode>();
foreach (XmlNode child in n.ChildNodes) {
- StripWsRec(child);
+ HandleWsRec(child, normalize);
if (!(n is XmlAttribute)
&& (child is XmlText || child is XmlCDataSection)
&& child.Value.Length == 0) {
@@ -101,10 +125,40 @@
XmlNamedNodeMap attrs = n.Attributes;
if (attrs != null) {
foreach (XmlAttribute a in attrs) {
- StripWsRec(a);
+ HandleWsRec(a, normalize);
}
}
}
+ private const char SPACE = ' ';
+
+ /// <summary>
+ /// Normalize a string.
+ /// <summary>
+ /// <remarks>
+ /// "normalized" in this context means all whitespace
+ /// characters are replaced by space characters and
+ /// consecutive whitespace characaters are collapsed.
+ /// </remarks>
+ internal static string Normalize(string s) {
+ StringBuilder sb = new StringBuilder();
+ bool changed = false;
+ bool lastCharWasWS = false;
+ foreach (char c in s) {
+ if (char.IsWhiteSpace(c)) {
+ if (!lastCharWasWS) {
+ sb.Append(SPACE);
+ changed |= (c != SPACE);
+ } else {
+ changed = true;
+ }
+ lastCharWasWS = true;
+ } else {
+ sb.Append(c);
+ lastCharWasWS = false;
+ }
+ }
+ return changed ? sb.ToString() : s;
+ }
}
}
Modified: trunk/xmlunit/src/tests/java-core/net/sf/xmlunit/util/NodesTest.java
===================================================================
--- trunk/xmlunit/src/tests/java-core/net/sf/xmlunit/util/NodesTest.java 2010-09-16 15:13:39 UTC (rev 480)
+++ trunk/xmlunit/src/tests/java-core/net/sf/xmlunit/util/NodesTest.java 2010-09-17 11:50:31 UTC (rev 481)
@@ -144,16 +144,20 @@
assertEquals(BAR, m.get(new QName(SOME_URI, FOO, BAR)));
}
- private Map.Entry<Document, Node> stripWsSetup() {
- final Document toTest = Convert.toDocument(Input.fromMemory(
+ private Document handleWsSetup() {
+ return Convert.toDocument(Input.fromMemory(
"<root>\n"
- + "<!-- trim me -->\n"
+ + "<!-- trim\tme -->\n"
+ "<child attr=' trim me ' attr2='not me'>\n"
+ " trim me \n"
+ "</child><![CDATA[ trim me ]]>\n"
+ "<?target trim me ?>\n"
+ "<![CDATA[ ]]>\n"
+ "</root>").build());
+ }
+
+ private Map.Entry<Document, Node> stripWsSetup() {
+ final Document toTest = handleWsSetup();
final Node stripped = Nodes.stripWhitespace(toTest);
return new Map.Entry<Document, Node>() {
public Document getKey() {
@@ -168,8 +172,32 @@
};
}
+ private Map.Entry<Document, Node> normalizeWsSetup() {
+ final Document toTest = handleWsSetup();
+ final Node stripped = Nodes.normalizeWhitespace(toTest);
+ return new Map.Entry<Document, Node>() {
+ public Document getKey() {
+ return toTest;
+ }
+ public Node getValue() {
+ return stripped;
+ }
+ public Node setValue(Node n) {
+ throw new UnsupportedOperationException();
+ }
+ };
+ }
+
@Test public void stripWhitespaceWorks() {
- Map.Entry<Document, Node> s = stripWsSetup();
+ handleWsWorks(stripWsSetup(), "trim\tme");
+ }
+
+ @Test public void normalizeWhitespaceWorks() {
+ handleWsWorks(normalizeWsSetup(), "trim me");
+ }
+
+ private void handleWsWorks(Map.Entry<Document, Node> s,
+ String commentContent) {
assertTrue(s.getValue() instanceof Document);
NodeList top = s.getValue().getChildNodes();
assertEquals(1, top.getLength());
@@ -179,7 +207,8 @@
assertEquals(4, rootsChildren.getLength());
assertTrue("should be comment, is " + rootsChildren.item(0).getClass(),
rootsChildren.item(0) instanceof Comment);
- assertEquals("trim me", ((Comment) rootsChildren.item(0)).getData());
+ assertEquals(commentContent,
+ ((Comment) rootsChildren.item(0)).getData());
assertTrue("should be element, is " + rootsChildren.item(1).getClass(),
rootsChildren.item(1) instanceof Element);
assertEquals("child", rootsChildren.item(1).getNodeName());
@@ -206,7 +235,14 @@
}
@Test public void stripWhitespaceDoesntAlterOriginal() {
- Map.Entry<Document, Node> s = stripWsSetup();
+ handleWsDoesntAlterOriginal(stripWsSetup());
+ }
+
+ @Test public void normalizeWhitespaceDoesntAlterOriginal() {
+ handleWsDoesntAlterOriginal(normalizeWsSetup());
+ }
+
+ private void handleWsDoesntAlterOriginal(Map.Entry<Document, Node> s) {
NodeList top = s.getKey().getChildNodes();
assertEquals(1, top.getLength());
assertTrue(top.item(0) instanceof Element);
@@ -216,7 +252,7 @@
assertNewlineTextNode(rootsChildren.item(0));
assertTrue("should be comment, is " + rootsChildren.item(1).getClass(),
rootsChildren.item(1) instanceof Comment);
- assertEquals(" trim me ", ((Comment) rootsChildren.item(1)).getData());
+ assertEquals(" trim\tme ", ((Comment) rootsChildren.item(1)).getData());
assertNewlineTextNode(rootsChildren.item(2));
assertTrue("should be element, is " + rootsChildren.item(3).getClass(),
rootsChildren.item(3) instanceof Element);
@@ -255,4 +291,11 @@
n instanceof Text);
assertEquals("\n", ((Text) n).getData());
}
+
+ @Test public void normalize() {
+ assertSame("foo", Nodes.normalize("foo"));
+ assertSame("foo bar", Nodes.normalize("foo bar"));
+ assertEquals("foo bar", Nodes.normalize("foo\nbar"));
+ assertEquals("foo bar", Nodes.normalize("foo \r\n\t bar"));
+ }
}
Modified: trunk/xmlunit/src/tests/net-core/util/NodesTest.cs
===================================================================
--- trunk/xmlunit/src/tests/net-core/util/NodesTest.cs 2010-09-16 15:13:39 UTC (rev 480)
+++ trunk/xmlunit/src/tests/net-core/util/NodesTest.cs 2010-09-17 11:50:31 UTC (rev 481)
@@ -123,23 +123,42 @@
Assert.AreEqual(BAR, m[new XmlQualifiedName(FOO, SOME_URI)]);
}
- private KeyValuePair<XmlDocument, XmlNode> StripWsSetup() {
- XmlDocument toTest = Convert.ToDocument(Input.FromMemory(
+ private XmlDocument HandleWsSetup() {
+ return Convert.ToDocument(Input.FromMemory(
"<root>\n"
- + "<!-- trim me -->\n"
+ + "<!-- trim\tme -->\n"
+ "<child attr=' trim me ' attr2='not me'>\n"
+ " trim me \n"
+ "</child><![CDATA[ trim me ]]>\n"
+ "<?target trim me ?>\n"
+ "<![CDATA[ ]]>\n"
+ "</root>").Build());
+ }
+
+ private KeyValuePair<XmlDocument, XmlNode> StripWsSetup() {
+ XmlDocument toTest = HandleWsSetup();
return new KeyValuePair<XmlDocument,
XmlNode>(toTest, Nodes.StripWhitespace(toTest));
}
+ private KeyValuePair<XmlDocument, XmlNode> NormalizeWsSetup() {
+ XmlDocument toTest = HandleWsSetup();
+ return new KeyValuePair<XmlDocument,
+ XmlNode>(toTest, Nodes.NormalizeWhitespace(toTest));
+ }
+
[Test]
public void StripWhitespaceWorks() {
- KeyValuePair<XmlDocument, XmlNode> s = StripWsSetup();
+ HandleWsWorks(StripWsSetup(), "trim\tme");
+ }
+
+ [Test]
+ public void NormalizeWhitespaceWorks() {
+ HandleWsWorks(NormalizeWsSetup(), "trim me");
+ }
+
+ private void HandleWsWorks(KeyValuePair<XmlDocument, XmlNode> s,
+ string commentContent) {
Assert.IsTrue(s.Value is XmlDocument);
XmlNodeList top = s.Value.ChildNodes;
Assert.AreEqual(1, top.Count);
@@ -149,7 +168,7 @@
Assert.AreEqual(4, rootsChildren.Count);
Assert.IsTrue(rootsChildren[0] is XmlComment,
"should be comment, is " + rootsChildren[0].GetType());
- Assert.AreEqual("trim me",
+ Assert.AreEqual(commentContent,
((XmlComment) rootsChildren[0]).Data);
Assert.IsTrue(rootsChildren[1] is XmlElement,
"should be element, is " + rootsChildren[1].GetType());
@@ -178,7 +197,16 @@
[Test]
public void StripWhitespaceDoesntAlterOriginal() {
- KeyValuePair<XmlDocument, XmlNode> s = StripWsSetup();
+ HandleWsDoesntAlterOriginal(StripWsSetup());
+ }
+
+ [Test]
+ public void NormalizeWhitespaceDoesntAlterOriginal() {
+ HandleWsDoesntAlterOriginal(NormalizeWsSetup());
+ }
+
+ private void HandleWsDoesntAlterOriginal(KeyValuePair<XmlDocument,
+ XmlNode> s) {
XmlNodeList top = s.Key.ChildNodes;
Assert.AreEqual(1, top.Count);
Assert.IsTrue(top[0] is XmlElement);
@@ -187,7 +215,7 @@
Assert.AreEqual(5, rootsChildren.Count);
Assert.IsTrue(rootsChildren[0] is XmlComment,
"should be comment, is " + rootsChildren[0].GetType());
- Assert.AreEqual(" trim me ",
+ Assert.AreEqual(" trim\tme ",
((XmlComment) rootsChildren[0]).Data);
Assert.IsTrue(rootsChildren[1] is XmlElement,
"should be element, is " + rootsChildren[1].GetType());
@@ -217,5 +245,13 @@
XmlAttribute a2 = (XmlAttribute) attrs.GetNamedItem("attr2");
Assert.AreEqual("not me", a2.Value);
}
+
+ [Test]
+ public void Normalize() {
+ Assert.AreSame("foo", Nodes.Normalize("foo"));
+ Assert.AreSame("foo bar", Nodes.Normalize("foo bar"));
+ Assert.AreEqual("foo bar", Nodes.Normalize("foo\nbar"));
+ Assert.AreEqual("foo bar", Nodes.Normalize("foo \r\n\t bar"));
+ }
}
}
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
|
