Stop HTML encoding unicode characters when serializing XForm (#685)

getodk · May 31, 2022 · adde512 · adde512
1 parent 660331f
commit adde512
Show file tree

Hide file tree

Showing 2 changed files with 50 additions and 6 deletions.
diff --git a/src/main/java/org/javarosa/xform/util/XFormSerializer.java b/src/main/java/org/javarosa/xform/util/XFormSerializer.java
@@ -19,14 +19,13 @@
 import org.kxml2.io.KXmlSerializer;
 import org.kxml2.kdom.Document;
 import org.kxml2.kdom.Element;
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
 
 import java.io.ByteArrayOutputStream;
 import java.io.DataOutputStream;
-import java.io.OutputStreamWriter;
 import java.io.UnsupportedEncodingException;
-import java.io.Writer;
-import org.slf4j.Logger;
-import org.slf4j.LoggerFactory;
+import java.nio.charset.StandardCharsets;
 
 /* this is just a big dump of serialization-related code */
 
@@ -88,8 +87,7 @@ public static byte[] getUtfBytes(Document doc) {
         KXmlSerializer serializer = new KXmlSerializer();
         ByteArrayOutputStream bos = new ByteArrayOutputStream();
         try {
-            Writer osw = new OutputStreamWriter(bos, "UTF-8");
-            serializer.setOutput(osw);
+            serializer.setOutput(bos, StandardCharsets.UTF_8.name());
             doc.write(serializer);
             serializer.flush();
             return bos.toByteArray();

diff --git a/src/test/java/org/javarosa/model/xform/XFormSerializingVisitorTest.java b/src/test/java/org/javarosa/model/xform/XFormSerializingVisitorTest.java
@@ -0,0 +1,46 @@
+package org.javarosa.model.xform;
+
+import org.javarosa.core.test.Scenario;
+import org.javarosa.core.util.XFormsElement;
+import org.junit.Test;
+
+import java.io.IOException;
+
+import static org.hamcrest.MatcherAssert.assertThat;
+import static org.hamcrest.Matchers.containsString;
+import static org.javarosa.core.util.BindBuilderXFormsElement.bind;
+import static org.javarosa.core.util.XFormsElement.body;
+import static org.javarosa.core.util.XFormsElement.head;
+import static org.javarosa.core.util.XFormsElement.html;
+import static org.javarosa.core.util.XFormsElement.input;
+import static org.javarosa.core.util.XFormsElement.mainInstance;
+import static org.javarosa.core.util.XFormsElement.model;
+import static org.javarosa.core.util.XFormsElement.t;
+import static org.javarosa.core.util.XFormsElement.title;
+
+public class XFormSerializingVisitorTest {
+
+    @Test
+    public void serializeInstance_preservesUnicodeCharacters() throws IOException {
+        XFormsElement formDef = html(
+            head(
+                title("Some form"),
+                model(
+                    mainInstance(t("data id=\"some-form\"",
+                        t("text")
+                    )),
+                    bind("/data/text").type("string")
+                )
+            ),
+            body(input("/data/text"))
+        );
+
+        Scenario scenario = Scenario.init("Some form", formDef);
+        scenario.next();
+        scenario.answer("\uD83E\uDDDB");
+
+        XFormSerializingVisitor visitor = new XFormSerializingVisitor();
+        byte[] serializedInstance = visitor.serializeInstance(scenario.getFormDef().getMainInstance());
+        assertThat(new String(serializedInstance), containsString("<text>\uD83E\uDDDB</text>"));
+    }
+}