Sha256: 0bfbb604b490dc7de516d158c9668aa6b2ff9c555a032e30a0cfb56464fc80b0
Contents?: true
Size: 1.63 KB
Versions: 2
Compression:
Stored size: 1.63 KB
Contents
From ddc5f3d22644e0f6fbcc20541c86825757ffee62 Mon Sep 17 00:00:00 2001
From: Mike Dalessio <mike.dalessio@gmail.com>
Date: Mon, 21 Feb 2022 18:27:45 -0500
Subject: [PATCH] Revert "Different approach to fix quadratic behavior in HTML
push parser"
This reverts commit 798bdf13f6964a650b9a0b7b4b3a769f6f1d509a.
---
HTMLparser.c | 14 +-------------
1 file changed, 1 insertion(+), 13 deletions(-)
diff --git a/HTMLparser.c b/HTMLparser.c
index eba2d7c..c0b8119 100644
--- a/HTMLparser.c
+++ b/HTMLparser.c
@@ -3960,25 +3960,13 @@ htmlParseStartTag(htmlParserCtxtPtr ctxt) {
htmlParseErr(ctxt, XML_ERR_NAME_REQUIRED,
"htmlParseStartTag: invalid element name\n",
NULL, NULL);
- /*
- * The recovery code is disabled for now as it can result in
- * quadratic behavior with the push parser. htmlParseStartTag
- * must consume all content up to the final '>' in order to avoid
- * rescanning for this terminator.
- *
- * For a proper fix in line with HTML5, htmlParseStartTag and
- * htmlParseElement should only be called when there's an ASCII
- * alpha character following the initial '<'. Otherwise, the '<'
- * should be emitted as text (unless followed by '!', '/' or '?').
- */
-#if 0
/* if recover preserve text on classic misconstructs */
if ((ctxt->recovery) && ((IS_BLANK_CH(CUR)) || (CUR == '<') ||
(CUR == '=') || (CUR == '>') || (((CUR >= '0') && (CUR <= '9'))))) {
htmlParseCharDataInternal(ctxt, '<');
return(-1);
}
-#endif
+
/* Dump the bogus tag like browsers do */
while ((CUR != 0) && (CUR != '>') &&
--
2.31.0
Version data entries
2 entries across 2 versions & 1 rubygems