From d3cf93cf042bf57ce8b22dd2ee537bc51d45f3ce Mon Sep 17 00:00:00 2001
From: James Agnew <jamesagnew@gmail.com>
Date: Tue, 7 Jan 2020 09:53:43 -0500
Subject: [PATCH] Work on https://github.com/jamesagnew/hapi-fhir/issues/1658 -
 Make sure we preserve lang attribute on narrative div

---
 .../hl7/fhir/utilities/xhtml/XhtmlNode.java   | 13 +++++-----
 .../hl7/fhir/utilities/xhtml/XhtmlParser.java |  7 ++---
 .../fhir/utilities/tests/XhtmlNodeTest.java   | 26 ++++++++++++++++---
 3 files changed, 33 insertions(+), 13 deletions(-)

diff --git a/org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/xhtml/XhtmlNode.java b/org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/xhtml/XhtmlNode.java
index 8543406f5..0b01556d3 100644
--- a/org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/xhtml/XhtmlNode.java
+++ b/org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/xhtml/XhtmlNode.java
@@ -394,13 +394,12 @@ public class XhtmlNode implements IBaseXhtml {
     val = XhtmlDt.preprocessXhtmlNamespaceDeclaration(val);
 
     try {
-      // TODO: this is ugly
-      XhtmlNode fragment = new XhtmlParser().parseFragment(val);
-      this.attributes = fragment.attributes;
-      this.childNodes = fragment.childNodes;
-      this.content = fragment.content;
-      this.name = fragment.name;
-      this.nodeType= fragment.nodeType;
+      XhtmlDocument fragment = new XhtmlParser().parse(val, "div");
+      this.attributes = fragment.getAttributes();
+      this.childNodes = fragment.getChildNodes();
+      this.content = fragment.getContent();
+      this.name = fragment.getName();
+      this.nodeType= fragment.getNodeType();
     } catch (Exception e) {
       // TODO: composer shouldn't throw exception like this
       throw new RuntimeException(e);
diff --git a/org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/xhtml/XhtmlParser.java b/org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/xhtml/XhtmlParser.java
index 9d1e1d519..75442e02f 100644
--- a/org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/xhtml/XhtmlParser.java
+++ b/org.hl7.fhir.utilities/src/main/java/org/hl7/fhir/utilities/xhtml/XhtmlParser.java
@@ -54,6 +54,7 @@ import java.io.InputStream;
 import java.io.InputStreamReader;
 import java.io.Reader;
 import java.io.StringReader;
+import java.nio.charset.StandardCharsets;
 import java.util.ArrayList;
 import java.util.HashMap;
 import java.util.HashSet;
@@ -446,7 +447,7 @@ private boolean elementIsOk(String name) throws FHIRFormatError  {
   }
   
   public XhtmlDocument parse(InputStream input, String entryName) throws FHIRFormatError, IOException  {
-    rdr = new InputStreamReader(input, "UTF-8");
+    rdr = new InputStreamReader(input, StandardCharsets.UTF_8);
     return parse(entryName);
   }
    
@@ -1176,7 +1177,7 @@ private boolean elementIsOk(String name) throws FHIRFormatError  {
     String n = readName().toLowerCase();
     readToTagEnd();
     XhtmlNode result = new XhtmlNode(NodeType.Element);
-    
+
     int colonIndex = n.indexOf(':');
     if (colonIndex != -1) {
       n = n.substring(colonIndex + 1);
@@ -1184,7 +1185,7 @@ private boolean elementIsOk(String name) throws FHIRFormatError  {
     
     result.setName(n);
     unwindPoint = null;
-    List<XhtmlNode> p = new ArrayList<XhtmlNode>();
+    List<XhtmlNode> p = new ArrayList<>();
     parseElementInner(result, p, null, true);
 
     return result;
diff --git a/org.hl7.fhir.utilities/src/test/java/org/hl7/fhir/utilities/tests/XhtmlNodeTest.java b/org.hl7.fhir.utilities/src/test/java/org/hl7/fhir/utilities/tests/XhtmlNodeTest.java
index b10221493..9a405349a 100644
--- a/org.hl7.fhir.utilities/src/test/java/org/hl7/fhir/utilities/tests/XhtmlNodeTest.java
+++ b/org.hl7.fhir.utilities/src/test/java/org/hl7/fhir/utilities/tests/XhtmlNodeTest.java
@@ -1,10 +1,9 @@
 package org.hl7.fhir.utilities.tests;
 
+import org.hl7.fhir.utilities.xhtml.XhtmlNode;
 import org.junit.Test;
 
-import static org.junit.Assert.*;
-
-import org.hl7.fhir.utilities.xhtml.XhtmlNode;
+import static org.junit.Assert.assertEquals;
 
 public class XhtmlNodeTest {
 
@@ -26,5 +25,26 @@ public class XhtmlNodeTest {
 
   }
 
+  /**
+   * See https://github.com/jamesagnew/hapi-fhir/issues/1658
+   */
+  @Test
+  public void testLangAttributePreserved() {
+    XhtmlNode dt = new XhtmlNode();
+    dt.setValueAsString("<div xmlns=\"http://www.w3.org/1999/xhtml\" lang=\"en-US\">help i'm a bug</div>");
+    assertEquals("<div xmlns=\"http://www.w3.org/1999/xhtml\" lang=\"en-US\">help i'm a bug</div>", dt.getValueAsString());
+    assertEquals("<div xmlns=\"http://www.w3.org/1999/xhtml\" lang=\"en-US\">help i'm a bug</div>", new XhtmlNode().setValue(dt.getValue()).getValueAsString());
+  }
+
+
+  @Test
+  public void testParseRsquo() {
+    XhtmlNode dt = new XhtmlNode();
+    dt.setValueAsString("It&rsquo;s January again");
+    assertEquals("<div xmlns=\"http://www.w3.org/1999/xhtml\">It’s January again</div>", dt.getValueAsString());
+    assertEquals("<div xmlns=\"http://www.w3.org/1999/xhtml\">It’s January again</div>", new XhtmlNode().setValue(dt.getValue()).getValueAsString());
+  }
+
+
 
 }
\ No newline at end of file