Index: HTMLparser.c
===================================================================
--- HTMLparser.c	(revision 3797)
+++ HTMLparser.c	(working copy)
@@ -4120,6 +4120,8 @@ htmlParseElement(htmlParserCtxtPtr ctxt)
 
 int
 htmlParseDocument(htmlParserCtxtPtr ctxt) {
+    xmlChar start[4];
+    xmlCharEncoding enc;
     xmlDtdPtr dtd;
 
     xmlInitParser();
@@ -4139,6 +4141,23 @@ htmlParseDocument(htmlParserCtxtPtr ctxt
     if ((ctxt->sax) && (ctxt->sax->setDocumentLocator))
         ctxt->sax->setDocumentLocator(ctxt->userData, &xmlDefaultSAXLocator);
 
+    if ((ctxt->encoding == (const xmlChar *)XML_CHAR_ENCODING_NONE) &&
+        ((ctxt->input->end - ctxt->input->cur) >= 4)) {
+	/*
+	 * Get the 4 first bytes and decode the charset
+	 * if enc != XML_CHAR_ENCODING_NONE
+	 * plug some encoding conversion routines.
+	 */
+	start[0] = RAW;
+	start[1] = NXT(1);
+	start[2] = NXT(2);
+	start[3] = NXT(3);
+	enc = xmlDetectCharEncoding(&start[0], 4);
+	if (enc != XML_CHAR_ENCODING_NONE) {
+	    xmlSwitchEncoding(ctxt, enc);
+	}
+    }
+
     /*
      * Wipe out everything which is before the first '<'
      */