nokogiri 1.12.0 → 1.13.3

data/patches/libxml2/0008-htmlParseComment-handle-abruptly-closed-comments.patch

@@ -0,0 +1,61 @@
+From 3ea8d08da310b645e37940eaae5cc28e251b155b Mon Sep 17 00:00:00 2001
+From: Mike Dalessio <mike.dalessio@gmail.com>
+Date: Sat, 17 Jul 2021 14:36:53 -0400
+Subject: [PATCH] htmlParseComment: handle abruptly-closed comments
+
+See guidance provided on abrutply-closed comments here:
+
+https://html.spec.whatwg.org/multipage/parsing.html#parse-error-abrupt-closing-of-empty-comment
+---
+ HTMLparser.c              | 11 +++++++++++
+ include/libxml/xmlerror.h |  1 +
+ 2 files changed, 12 insertions(+)
+
+diff --git a/HTMLparser.c b/HTMLparser.c
+index b56363a..f0bf294 100644
+--- a/HTMLparser.c
++++ b/HTMLparser.c
+@@ -3485,10 +3485,20 @@ htmlParseComment(htmlParserCtxtPtr ctxt) {
+     q = CUR_CHAR(ql);
+     if (q == 0)
+         goto unfinished;
++    if (q == '>') {
++        htmlParseErr(ctxt, XML_ERR_COMMENT_ABRUPTLY_ENDED, "Comment abruptly ended", NULL, NULL);
++        cur = '>';
++        goto finished;
++    }
+     NEXTL(ql);
+     r = CUR_CHAR(rl);
+     if (r == 0)
+         goto unfinished;
++    if (q == '-' && r == '>') {
++        htmlParseErr(ctxt, XML_ERR_COMMENT_ABRUPTLY_ENDED, "Comment abruptly ended", NULL, NULL);
++        cur = '>';
++        goto finished;
++    }
+     NEXTL(rl);
+     cur = CUR_CHAR(l);
+     while ((cur != 0) &&
+@@ -3536,6 +3546,7 @@ htmlParseComment(htmlParserCtxtPtr ctxt) {
+ 	cur = next;
+ 	l = nl;
+     }
++finished:
+     buf[len] = 0;
+     if (cur == '>') {
+         NEXT;
+diff --git a/include/libxml/xmlerror.h b/include/libxml/xmlerror.h
+index c101997..7b68e40 100644
+--- a/include/libxml/xmlerror.h
++++ b/include/libxml/xmlerror.h
+@@ -209,6 +209,7 @@ typedef enum {
+     XML_ERR_VERSION_MISMATCH, /* 109 */
+     XML_ERR_NAME_TOO_LONG, /* 110 */
+     XML_ERR_USER_STOP, /* 111 */
++    XML_ERR_COMMENT_ABRUPTLY_ENDED, /* 112 */
+     XML_NS_ERR_XML_NAMESPACE = 200,
+     XML_NS_ERR_UNDEFINED_NAMESPACE, /* 201 */
+     XML_NS_ERR_QNAME, /* 202 */
+-- 
+2.31.0
+

data/patches/libxml2/0009-allow-wildcard-namespaces.patch

@@ -0,0 +1,77 @@
+From 74c95ec5932c737d4fcb06b8646b0017364ada14 Mon Sep 17 00:00:00 2001
+From: Mike Dalessio <mike.dalessio@gmail.com>
+Date: Fri, 24 Dec 2021 19:08:01 -0500
+Subject: [PATCH] attempt to hack in wildcard namespaces to xpath
+
+I'm not confident this is a bulletproof patch.
+---
+ xpath.c | 24 ++++++++++++++++++------
+ 1 file changed, 18 insertions(+), 6 deletions(-)
+
+diff --git a/xpath.c b/xpath.c
+index 1aa2f1a..c7f0885 100644
+--- a/xpath.c
++++ b/xpath.c
+@@ -146,6 +146,9 @@
+ #define XPATH_MAX_RECURSION_DEPTH 5000
+ #endif
+ 
++#define WILDCARD_PREFIX "*"
++#define IS_WILDCARD_PREFIX(p) xmlStrEqual((xmlChar*)WILDCARD_PREFIX, p)
++
+ /*
+  * TODO:
+  * There are a few spots where some tests are done which depend upon ascii
+@@ -11073,12 +11076,15 @@ xmlXPathCompNodeTest(xmlXPathParserContextPtr ctxt, xmlXPathTestVal *test,
+     SKIP_BLANKS;
+ 
+     if ((name == NULL) && (CUR == '*')) {
+-	/*
+-	 * All elements
+-	 */
+ 	NEXT;
+-	*test = NODE_TEST_ALL;
+-	return(NULL);
++	if (CUR != ':') {
++	    /*
++	     * All elements
++	     */
++	    *test = NODE_TEST_ALL;
++	    return(NULL);
++	}
++	name = xmlCharStrdup(WILDCARD_PREFIX);
+     }
+ 
+     if (name == NULL)
+@@ -11327,6 +11333,10 @@ xmlXPathCompStep(xmlXPathParserContextPtr ctxt) {
+ 	}
+ #endif
+ 	if (CUR == '*') {
++	    if (NXT(1) == ':') {
++		NEXT;
++		name = xmlCharStrdup(WILDCARD_PREFIX);
++	    }
+ 	    axis = AXIS_CHILD;
+ 	} else {
+ 	    if (name == NULL)
+@@ -12030,7 +12040,7 @@ xmlXPathNodeCollectAndTest(xmlXPathParserContextPtr ctxt,
+     /*
+     * Setup namespaces.
+     */
+-    if (prefix != NULL) {
++    if (prefix != NULL && !IS_WILDCARD_PREFIX(prefix)) {
+         URI = xmlXPathNsLookup(xpctxt, prefix);
+         if (URI == NULL) {
+ 	    xmlXPathReleaseObject(xpctxt, obj);
+@@ -12369,6 +12379,8 @@ xmlXPathNodeCollectAndTest(xmlXPathParserContextPtr ctxt,
+ 				    {
+ 					XP_TEST_HIT
+                                     }
++                                } else if (IS_WILDCARD_PREFIX(prefix)) {
++                                    XP_TEST_HIT
+                                 } else {
+                                     if ((cur->ns != NULL) &&
+                                         (xmlStrEqual(URI, cur->ns->href)))
+-- 
+2.31.0
+

data/patches/libxml2/0010-Revert-Different-approach-to-fix-quadratic-behavior.patch

@@ -0,0 +1,45 @@
+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
+