Don't try to get child nodes if there aren't any yet

Fixes #2266
jhy · Jan 28, 2025 · 5d31cac · 5d31cac
1 parent 8086b1e
commit 5d31cac
Show file tree

Hide file tree

Showing 3 changed files with 15 additions and 2 deletions.
diff --git a/CHANGES.md b/CHANGES.md
@@ -58,6 +58,8 @@
   special tags. [2258](https://github.com/jhy/jsoup/issues/2258)
 * An `:nth-child` selector with a negative digit-less step, such as `:nth-child(-n+2)`, would be parsed incorrectly as a
   positive step, and so would not match as expected. [1147](https://github.com/jhy/jsoup/issues/1147)
+* Calling `doc.charset(charset)` on an empty XML document would throw an
+  `IndexOutOfBoundsException`. [2266](https://github.com/jhy/jsoup/issues/2266)
 
 ## 1.18.3 (2024-Dec-02)
 

diff --git a/src/main/java/org/jsoup/nodes/Document.java b/src/main/java/org/jsoup/nodes/Document.java
@@ -53,7 +53,7 @@ public Document(String baseUri) {
     }
 
     /**
-     Create a valid, empty shell of a document, suitable for adding more elements to.
+     Create a valid, empty shell of an HTML document, suitable for adding more elements to.
      @param baseUri baseUri of document
      @return document with html, head, and body elements.
      */
@@ -326,7 +326,7 @@ private void ensureMetaCharsetElement() {
     }
 
     private XmlDeclaration ensureXmlDecl() {
-        Node node = ensureChildNodes().get(0);
+        Node node = firstChild();
         if (node instanceof XmlDeclaration) {
             XmlDeclaration decl = (XmlDeclaration) node;
             if (decl.name().equals("xml")) return decl;

diff --git a/src/test/java/org/jsoup/nodes/DocumentTest.java b/src/test/java/org/jsoup/nodes/DocumentTest.java
@@ -434,6 +434,17 @@ private Document createXmlDocument(String version, String charset, boolean addDe
         return doc;
     }
 
+    @Test void charsetOnEmptyDoc() {
+        Document xml = new Document(Parser.NamespaceXml, "https://example.com"); // no nodes
+        xml.outputSettings().syntax(Syntax.xml);
+        xml.charset(StandardCharsets.UTF_8);
+        assertEquals("<?xml version=\"1.0\" encoding=\"UTF-8\"?>", xml.html());
+
+        Document html = new Document("https://example.com");
+        html.charset(StandardCharsets.UTF_8);
+        assertEquals("<html><head><meta charset=\"UTF-8\"></head></html>", TextUtil.stripNewlines(html.html()));
+    }
+
     @Test
     public void testShiftJisRoundtrip() throws Exception {
         String input =