Avoid processing entities after encoding conversion failures

For https://bugzilla.gnome.org/show_bug.cgi?id=756527
and was also raised by Chromium team in the past

When we hit a convwersion failure when switching encoding
it is bestter to stop parsing there, this was treated as a
fatal error but the parser was continuing to process to extract
more errors, unfortunately that makes little sense as the data
is obviously corrupt and can potentially lead to unexpected behaviour.

2 files changed, 15 insertions, 3 deletions

diff --git a/parser.c b/parser.c
index 134afe70..c79b4e85 100644
--- a/parser.c
+++ b/parser.c
@@ -10665,7 +10665,8 @@ xmlParseXMLDecl(xmlParserCtxtPtr ctxt) {
 	xmlFatalErrMsg(ctxt, XML_ERR_SPACE_REQUIRED, "Blank needed here\n");
     }
     xmlParseEncodingDecl(ctxt);
-    if (ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) {
+    if ((ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) ||
+         (ctxt->instate == XML_PARSER_EOF)) {
 	/*
 	 * The XML REC instructs us to stop parsing right here
 	 */
@@ -10789,6 +10790,7 @@ xmlParseDocument(xmlParserCtxtPtr ctxt) {
 
     if (CUR == 0) {
 	xmlFatalErr(ctxt, XML_ERR_DOCUMENT_EMPTY, NULL);
+	return(-1);
     }
 
     /*
@@ -10806,7 +10808,8 @@ xmlParseDocument(xmlParserCtxtPtr ctxt) {
 	 * Note that we will switch encoding on the fly.
 	 */
 	xmlParseXMLDecl(ctxt);
-	if (ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) {
+	if ((ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) ||
+	    (ctxt->instate == XML_PARSER_EOF)) {
 	    /*
 	     * The XML REC instructs us to stop parsing right here
 	     */
diff --git a/parserInternals.c b/parserInternals.c
index df204fde..c8230c1c 100644
--- a/parserInternals.c
+++ b/parserInternals.c
@@ -937,6 +937,7 @@ xmlSwitchEncoding(xmlParserCtxtPtr ctxt, xmlCharEncoding enc)
 {
     xmlCharEncodingHandlerPtr handler;
     int len = -1;
+    int ret;
 
     if (ctxt == NULL) return(-1);
     switch (enc) {
@@ -1097,7 +1098,15 @@ xmlSwitchEncoding(xmlParserCtxtPtr ctxt, xmlCharEncoding enc)
     if (handler == NULL)
 	return(-1);
     ctxt->charset = XML_CHAR_ENCODING_UTF8;
-    return(xmlSwitchToEncodingInt(ctxt, handler, len));
+    ret = xmlSwitchToEncodingInt(ctxt, handler, len);
+    if ((ret < 0) || (ctxt->errNo == XML_I18N_CONV_FAILED)) {
+        /*
+	 * on encoding conversion errors, stop the parser
+	 */
+        xmlStopParser(ctxt);
+	ctxt->errNo = XML_I18N_CONV_FAILED;
+    }
+    return(ret);
 }
 
 /**