#38 Support for supplementary unicode characters in XMLWriter.

dom4j · Jul 1, 2018 · 75e59b1 · 75e59b1
1 parent 351bfef
commit 75e59b1
Show file tree

Hide file tree

Showing 2 changed files with 76 additions and 31 deletions.
diff --git a/src/main/java/org/dom4j/io/XMLWriter.java b/src/main/java/org/dom4j/io/XMLWriter.java
@@ -1645,44 +1645,37 @@ protected String escapeElementEntities(String text) {
 
         for (i = 0; i < size; i++) {
             String entity = null;
-            char c = text.charAt(i);
 
+            int c = text.codePointAt(i);
             switch (c) {
                 case '<':
                     entity = "&lt;";
-
                     break;
-
                 case '>':
                     entity = "&gt;";
-
                     break;
-
                 case '&':
                     entity = "&amp;";
-
                     break;
-
                 case '\t':
                 case '\n':
                 case '\r':
-
                     // don't encode standard whitespace characters
                     if (preserve) {
                         entity = String.valueOf(c);
                     }
-
                     break;
 
                 default:
 
                     if ((c < 32) || shouldEncodeChar(c)) {
-                        entity = "&#" + (int) c + ";";
+                        entity = "&#" + c + ";";
                     }
 
                     break;
             }
 
+
             if (entity != null) {
                 if (block == null) {
                     block = text.toCharArray();
@@ -1691,6 +1684,12 @@ protected String escapeElementEntities(String text) {
                 buffer.append(block, last, i - last);
                 buffer.append(entity);
                 last = i + 1;
+                if (Character.isSupplementaryCodePoint(c)) {
+                    last++;
+                }
+            }
+            if (Character.isSupplementaryCodePoint(c)) {
+                i++;
             }
         }
 
@@ -1739,53 +1738,37 @@ protected String escapeAttributeEntities(String text) {
 
         for (i = 0; i < size; i++) {
             String entity = null;
-            char c = text.charAt(i);
+            int c = text.codePointAt(i);
 
             switch (c) {
                 case '<':
                     entity = "&lt;";
-
                     break;
-
                 case '>':
                     entity = "&gt;";
-
                     break;
-
                 case '\'':
-
                     if (quote == '\'') {
                         entity = "&apos;";
                     }
-
                     break;
-
                 case '\"':
-
                     if (quote == '\"') {
                         entity = "&quot;";
                     }
-
                     break;
-
                 case '&':
                     entity = "&amp;";
-
                     break;
-
                 case '\t':
                 case '\n':
                 case '\r':
-
                     // don't encode standard whitespace characters
                     break;
-
                 default:
-
                     if ((c < 32) || shouldEncodeChar(c)) {
-                        entity = "&#" + (int) c + ";";
+                        entity = "&#" + c + ";";
                     }
-
                     break;
             }
 
@@ -1797,6 +1780,12 @@ protected String escapeAttributeEntities(String text) {
                 buffer.append(block, last, i - last);
                 buffer.append(entity);
                 last = i + 1;
+                if(Character.isSupplementaryCodePoint(c)) {
+                    last++;
+                }
+            }
+            if(Character.isSupplementaryCodePoint(c)) {
+                i++;
             }
         }
 
@@ -1822,15 +1811,15 @@ protected String escapeAttributeEntities(String text) {
      * Should the given character be escaped. This depends on the encoding of
      * the document.
      * 
-     * @param c
+     * @param codepoint Unicode codepoint.
      *            DOCUMENT ME!
      * 
      * @return boolean
      */
-    protected boolean shouldEncodeChar(char c) {
+    protected boolean shouldEncodeChar(int codepoint) {
         int max = getMaximumAllowedCharacter();
 
-        return (max > 0) && (c > max);
+        return (max > 0) && (codepoint > max);
     }
 
     /**

diff --git a/src/test/java/org/dom4j/XMLWriterTest.java b/src/test/java/org/dom4j/XMLWriterTest.java
@@ -631,6 +631,62 @@ public void testElementNamespaceAttributesWriteOpen() throws IOException {
         Assert.assertEquals(stringWriter.toString(), "<rss xmlns:g=\"http://base.google.com/ns/1.0\" xmlns:c=\"http://base.google.com/cns/1.0\" nons=\"value\" g:ns=\"value\">");
     }
 
+    public void testPenguin() throws IOException {
+        // U+1F427 PENGUIN
+        final String penguin = "\ud83d\udc27";
+
+        Document document = DocumentHelper.createDocument();
+        document.addElement("doc").setText(penguin);
+
+        OutputFormat outputFormat = OutputFormat.createCompactFormat();
+        outputFormat.setSuppressDeclaration(true);
+
+        StringWriter stringWriter = new StringWriter();
+        XMLWriter writer = new XMLWriter(stringWriter, outputFormat);
+        writer.write(document);
+        writer.close();
+
+        Assert.assertEquals(stringWriter.toString(), "<doc>"+penguin+"</doc>");
+    }
+
+    public void testSurrogatePairElement() throws IOException {
+        // U+1F427 PENGUIN
+        final String penguin = "\ud83d\udc27";
+
+        Document document = DocumentHelper.createDocument();
+        document.addElement("doc").setText(penguin);
+
+        OutputFormat outputFormat = OutputFormat.createCompactFormat();
+        outputFormat.setSuppressDeclaration(true);
+        outputFormat.setEncoding("US-ASCII");
+
+        StringWriter stringWriter = new StringWriter();
+        XMLWriter writer = new XMLWriter(stringWriter, outputFormat);
+        writer.write(document);
+        writer.close();
+
+        Assert.assertEquals(stringWriter.toString(), "<doc>&#128039;</doc>");
+    }
+
+    public void testSurrogatePairAttribute() throws IOException {
+        // U+1F427 PENGUIN
+        final String penguin = "\ud83d\udc27";
+
+        Document document = DocumentHelper.createDocument();
+        document.addElement("doc").addAttribute("penguin", penguin);
+
+        OutputFormat outputFormat = OutputFormat.createCompactFormat();
+        outputFormat.setSuppressDeclaration(true);
+        outputFormat.setEncoding("US-ASCII");
+
+        StringWriter stringWriter = new StringWriter();
+        XMLWriter writer = new XMLWriter(stringWriter, outputFormat);
+        writer.write(document);
+        writer.close();
+
+        Assert.assertEquals(stringWriter.toString(), "<doc penguin=\"&#128039;\"/>");
+    }
+
     protected void generateXML(ContentHandler handler) throws SAXException {
         handler.startDocument();