Merge pull request #1070 from dong0713/fix/xml-unescape-whitespace-control-chars

Fix XML.unescape rejecting valid whitespace numeric character references

Author: stleary

src/main/java/org/json/XML.java

@@ -172,8 +172,14 @@ static boolean mustEscape(int cp) {
                 && cp != 0xA
                 && cp != 0xD
             ) || !(
-                // valid the range of acceptable characters that aren't control
-                (cp >= 0x20 && cp <= 0xD7FF)
+                // Valid character range per W3C XML 1.0 spec:
+                // #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
+                // Previously omitted #x9/#xA/#xD, causing unescape("&#10;") etc.
+                // to reject valid LF/TAB/CR as illegal (see #1059)
+                cp == 0x9
+                || cp == 0xA
+                || cp == 0xD
+                || (cp >= 0x20 && cp <= 0xD7FF)
                 || (cp >= 0xE000 && cp <= 0xFFFD)
                 || (cp >= 0x10000 && cp <= 0x10FFFF)
             )

src/test/java/org/json/junit/XMLTest.java

@@ -1537,6 +1537,43 @@ public void testValidUppercaseHexEntity() {
         assertEquals("A", jsonObject.getString("a"));
     }
 
+    /**
+     * Tests that valid XML numeric character references for whitespace
+     * control characters (TAB, LF, CR) are correctly unescaped. These
+     * codepoints are explicitly allowed by the XML 1.0 spec
+     * (https://www.w3.org/TR/REC-xml/#charsets) but were previously rejected
+     * as invalid. See issue #1059.
+     */
+    @Test
+    public void testValidWhitespaceNumericEntityUnescape() {
+        // decimal references for the three allowed control characters
+        assertEquals("\t", XML.unescape("	"));
+        assertEquals("\n", XML.unescape("
"));
+        assertEquals("\r", XML.unescape("
"));
+        // hex references for the same codepoints
+        assertEquals("\t", XML.unescape("	"));
+        assertEquals("\n", XML.unescape("
"));
+        assertEquals("\r", XML.unescape("
"));
+    }
+
+    /**
+     * Tests that {@code XML.toJSONObject} accepts numeric character references
+     * for the XML-allowed control characters (TAB, LF, CR) without throwing.
+     * Regression test for #1059, where {@code XML.toJSONObject("<a>&#10;</a>")}
+     * threw JSONException in versions after 20251224.
+     */
+    @Test
+    public void testValidWhitespaceNumericEntityToJSONObject() {
+        // LF reference should round-trip through toJSONObject without throwing
+        JSONObject jsonObject = XML.toJSONObject("<a>&#10;</a>");
+        // the value is the LF character (possibly trimmed by the JSON path,
+        // but the call must not throw)
+        assertTrue(jsonObject.has("a"));
+        // TAB and CR references also accepted
+        XML.toJSONObject("<a>&#9;</a>");
+        XML.toJSONObject("<a>&#13;</a>");
+    }
+
 }