Add extractingText, which extracts text content of given nodes #192

xmlunit-assertj/src/main/java/org/xmlunit/assertj/MultipleNodeAssert.java

@@ -241,6 +241,33 @@ public AbstractListAssert<?, List<? extends String>, String, ObjectAssert<String
         return newListAssertInstance(values).as(description);
     }
 
+    /**
+     * Extracting text content of given nodes.
+     * If a node doesn't have the text then an empty string is returned.
+     *
+     * @throws AssertionError if the actual nodes iterable is {@code null}.
+     * @since XMLUnit 2.8.0
+     */
+    public AbstractListAssert<?, List<? extends String>, String, ObjectAssert<String>> extractingText() {
+        isNotNull();
+
+        List<String> values = new ArrayList<>();
+
+        for (Node node : actual) {
+            String textContent = node.getTextContent();
+            if (textContent != null) {
+                textContent = textContent.trim();
+            }
+            values.add(textContent);
+        }
+
+        String extractedDescription = "Extracted text content";
+        String description = Description.mostRelevantDescription(this.info.description(), extractedDescription);
+
+        return newListAssertInstance(values).as(description);
+    }
+
+
     private void allSatisfy(SingleNodeAssertConsumer consumer) {
         int index = 0;
         for (Node node : actual) {

xmlunit-assertj/src/test/java/org/xmlunit/assertj/MultipleNodeAssertTest.java

@@ -115,4 +115,90 @@ public void testExtractingAttribute_shouldPass() {
                 .extractingAttribute("attr1")
                 .containsExactly("value1", "value2", null, "value4");
     }
+
+    @Test
+    public void testExtractingTextSingleNode_shouldPass() {
+
+        String xml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>" +
+                "<feed>" +
+                "   <title>My Simple Feed</title>" +
+                "   <entry attr1=\"value1\" />" +
+                "   <entry attr1=\"value2\"/>" +
+                "   <entry />" +
+                "   <entry attr1=\"value4\" />" +
+                "</feed>";
+
+        assertThat(xml)
+                .nodesByXPath("/feed/title")
+                .extractingText()
+                .containsExactly("My Simple Feed");
+    }
+
+    @Test
+    public void testExtractingTextSingleNodeWithWhiteSpace_shouldPass() {
+
+        String xml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>" +
+                "<feed>" +
+                "   <title>" +
+                "           My Simple Feed" +
+                "   </title>" +
+                "   <entry attr1=\"value1\" />" +
+                "   <entry attr1=\"value2\"/>" +
+                "   <entry />" +
+                "   <entry attr1=\"value4\" />" +
+                "</feed>";
+
+        assertThat(xml)
+                .nodesByXPath("/feed/title")
+                .extractingText()
+                .containsExactly("My Simple Feed");
+    }
+
+    @Test
+    public void testExtractingTextMultipleNodes_shouldPass() {
+
+        String xml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>" +
+                "<document>" +
+                "   <h2> A header</h2>" +
+                " <h2>Just another header</h2>" +
+                "</document>";
+
+        assertThat(xml)
+                .nodesByXPath("/document/h2")
+                .extractingText()
+                .containsExactly("A header", "Just another header");
+    }
+
+    @Test
+    public void testExtractingTextMultipleNodesOneEmpty_shouldPass() {
+
+        String xml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>" +
+                "<document>" +
+                "   <h2> A header</h2>" +
+                " <h2/>" +
+                "</document>";
+
+        assertThat(xml)
+                .nodesByXPath("/document/h2")
+                .extractingText()
+                .containsExactly("A header", "");
+    }
+
+    @Test
+    public void testExtractingTextMultipleNodes_shouldFailed() {
+
+        thrown.expectAssertionError("[XPath \"/document/h2\" evaluated to node set] ");
+
+        String xml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>" +
+                "<document>" +
+                "   <h2> Matching header</h2>" +
+                " <h2>Not matching</h2>" +
+                "</document>";
+
+        assertThat(xml)
+                .nodesByXPath("/document/h2")
+                .extractingText()
+                .containsExactly("Matching header", "Header not matching");
+    }
+
 }