nokogiri 1.11.1 → 1.12.0.rc1

data/ext/nokogiri/xml_libxml2_hacks.h

@@ -1,12 +0,0 @@
-#ifndef HAVE_XMLFIRSTELEMENTCHILD
-
-#ifndef XML_LIBXML2_HACKS
-#define XML_LIBXML2_HACKS
-
-xmlNodePtr xmlFirstElementChild(xmlNodePtr parent);
-xmlNodePtr xmlNextElementSibling(xmlNodePtr node);
-xmlNodePtr xmlLastElementChild(xmlNodePtr parent);
-
-#endif
-
-#endif

data/ext/nokogiri/xml_namespace.h

@@ -1,14 +0,0 @@
-#ifndef NOKOGIRI_XML_NAMESPACE
-#define NOKOGIRI_XML_NAMESPACE
-
-#include <nokogiri.h>
-
-void init_xml_namespace();
-
-extern VALUE cNokogiriXmlNamespace ;
-
-VALUE Nokogiri_wrap_xml_namespace(xmlDocPtr doc, xmlNsPtr node);
-
-#define NOKOGIRI_NAMESPACE_EH(node) ((node)->type == XML_NAMESPACE_DECL)
-
-#endif

data/ext/nokogiri/xml_node.h

@@ -1,13 +0,0 @@
-#ifndef NOKOGIRI_XML_NODE
-#define NOKOGIRI_XML_NODE
-
-#include <nokogiri.h>
-
-void init_xml_node();
-
-extern VALUE cNokogiriXmlNode ;
-extern VALUE cNokogiriXmlElement ;
-
-VALUE Nokogiri_wrap_xml_node(VALUE klass, xmlNodePtr node) ;
-void Nokogiri_xml_node_properties(xmlNodePtr node, VALUE attr_hash) ;
-#endif

data/ext/nokogiri/xml_node_set.h

@@ -1,12 +0,0 @@
-#ifndef NOKOGIRI_XML_NODE_SET
-#define NOKOGIRI_XML_NODE_SET
-
-#include <nokogiri.h>
-void init_xml_node_set();
-
-extern VALUE cNokogiriXmlNodeSet ;
-VALUE Nokogiri_wrap_xml_node_set(xmlNodeSetPtr node_set, VALUE document) ;
-VALUE Nokogiri_wrap_xml_node_set_node(xmlNodePtr node, VALUE node_set) ;
-VALUE Nokogiri_wrap_xml_node_set_namespace(xmlNsPtr node, VALUE node_set) ;
-
-#endif

data/ext/nokogiri/xml_processing_instruction.h

@@ -1,9 +0,0 @@
-#ifndef NOKOGIRI_XML_PROCESSING_INSTRUCTION
-#define NOKOGIRI_XML_PROCESSING_INSTRUCTION
-
-#include <nokogiri.h>
-
-void init_xml_processing_instruction();
-
-extern VALUE cNokogiriXmlProcessingInstruction;
-#endif

data/ext/nokogiri/xml_reader.h

@@ -1,10 +0,0 @@
-#ifndef NOKOGIRI_XML_READER
-#define NOKOGIRI_XML_READER
-
-#include <nokogiri.h>
-
-void init_xml_reader();
-
-extern VALUE cNokogiriXmlReader;
-
-#endif

data/ext/nokogiri/xml_relax_ng.h

@@ -1,9 +0,0 @@
-#ifndef NOKOGIRI_XML_RELAX_NG
-#define NOKOGIRI_XML_RELAX_NG
-
-#include <nokogiri.h>
-
-void init_xml_relax_ng();
-
-extern VALUE cNokogiriXmlRelaxNG;
-#endif

data/ext/nokogiri/xml_sax_parser.h

@@ -1,39 +0,0 @@
-#ifndef NOKOGIRI_XML_SAX_PARSER
-#define NOKOGIRI_XML_SAX_PARSER
-
-#include <nokogiri.h>
-
-void init_xml_sax_parser();
-
-extern VALUE cNokogiriXmlSaxParser ;
-
-typedef struct _nokogiriSAXTuple {
-  xmlParserCtxtPtr  ctxt;
-  VALUE             self;
-} nokogiriSAXTuple;
-
-typedef nokogiriSAXTuple * nokogiriSAXTuplePtr;
-
-#define NOKOGIRI_SAX_SELF(_ctxt) \
-  ((nokogiriSAXTuplePtr)(_ctxt))->self
-
-#define NOKOGIRI_SAX_CTXT(_ctxt) \
-  ((nokogiriSAXTuplePtr)(_ctxt))->ctxt
-
-#define NOKOGIRI_SAX_TUPLE_NEW(_ctxt, _self) \
-  nokogiri_sax_tuple_new(_ctxt, _self)
-
-static inline nokogiriSAXTuplePtr
-nokogiri_sax_tuple_new(xmlParserCtxtPtr ctxt, VALUE self)
-{
-  nokogiriSAXTuplePtr tuple = malloc(sizeof(nokogiriSAXTuple));
-  tuple->self = self;
-  tuple->ctxt = ctxt;
-  return tuple;
-}
-
-#define NOKOGIRI_SAX_TUPLE_DESTROY(_tuple) \
-  free(_tuple) \
-
-#endif
-

data/ext/nokogiri/xml_sax_parser_context.h

@@ -1,10 +0,0 @@
-#ifndef NOKOGIRI_XML_SAX_PARSER_CONTEXT
-#define NOKOGIRI_XML_SAX_PARSER_CONTEXT
-
-#include <nokogiri.h>
-
-extern VALUE cNokogiriXmlSaxParserContext;
-
-void init_xml_sax_parser_context();
-
-#endif

data/ext/nokogiri/xml_sax_push_parser.h

@@ -1,9 +0,0 @@
-#ifndef NOKOGIRI_XML_SAX_PUSH_PARSER
-#define NOKOGIRI_XML_SAX_PUSH_PARSER
-
-#include <nokogiri.h>
-
-void init_xml_sax_push_parser();
-
-extern VALUE cNokogiriXmlSaxPushParser ;
-#endif

data/ext/nokogiri/xml_schema.h

@@ -1,9 +0,0 @@
-#ifndef NOKOGIRI_XML_SCHEMA
-#define NOKOGIRI_XML_SCHEMA
-
-#include <nokogiri.h>
-
-void init_xml_schema();
-
-extern VALUE cNokogiriXmlSchema;
-#endif

data/ext/nokogiri/xml_syntax_error.h

@@ -1,25 +0,0 @@
-#ifndef NOKOGIRI_XML_SYNTAX_ERROR
-#define NOKOGIRI_XML_SYNTAX_ERROR
-
-#include <nokogiri.h>
-
-typedef struct _libxmlStructuredErrorHandlerState {
-  void *user_data;
-  xmlStructuredErrorFunc handler;
-} libxmlStructuredErrorHandlerState ;
-
-void init_xml_syntax_error();
-
-void Nokogiri_structured_error_func_save(libxmlStructuredErrorHandlerState *handler_state);
-void Nokogiri_structured_error_func_save_and_set(libxmlStructuredErrorHandlerState *handler_state,
-                                                 void *user_data,
-                                                 xmlStructuredErrorFunc handler);
-void Nokogiri_structured_error_func_restore(libxmlStructuredErrorHandlerState *handler_state);
-
-VALUE Nokogiri_wrap_xml_syntax_error(xmlErrorPtr error);
-void Nokogiri_error_array_pusher(void *ctx, xmlErrorPtr error);
-NORETURN(void Nokogiri_error_raise(void *ctx, xmlErrorPtr error));
-
-extern VALUE cNokogiriXmlSyntaxError;
-
-#endif /* NOKOGIRI_XML_SYNTAX_ERROR */

data/ext/nokogiri/xml_text.h

@@ -1,9 +0,0 @@
-#ifndef NOKOGIRI_XML_TEXT
-#define NOKOGIRI_XML_TEXT
-
-#include <nokogiri.h>
-
-void init_xml_text();
-
-extern VALUE cNokogiriXmlText ;
-#endif

data/ext/nokogiri/xml_xpath_context.h

@@ -1,10 +0,0 @@
-#ifndef NOKOGIRI_XML_XPATH_CONTEXT
-#define NOKOGIRI_XML_XPATH_CONTEXT
-
-#include <nokogiri.h>
-
-void init_xml_xpath_context();
-void Nokogiri_marshal_xpath_funcall_and_return_values(xmlXPathParserContextPtr ctx, int nargs, VALUE handler, const char* function_name) ;
-
-extern VALUE cNokogiriXmlXpathContext;
-#endif

data/ext/nokogiri/xslt_stylesheet.h

@@ -1,14 +0,0 @@
-#ifndef NOKOGIRI_XSLT_STYLESHEET
-#define NOKOGIRI_XSLT_STYLESHEET
-
-#include <nokogiri.h>
-
-void init_xslt_stylesheet();
-
-extern VALUE cNokogiriXsltStylesheet ;
-
-typedef struct _nokogiriXsltStylesheetTuple {
-  xsltStylesheetPtr ss;
-  VALUE func_instances;
-} nokogiriXsltStylesheetTuple;
-#endif

data/lib/nokogiri/html/sax/parser_context.rb

@@ -1,17 +0,0 @@
-# frozen_string_literal: true
-module Nokogiri
-  module HTML
-    module SAX
-      ###
-      # Context for HTML SAX parsers.  This class is usually not instantiated
-      # by the user.  Instead, you should be looking at
-      # Nokogiri::HTML::SAX::Parser
-      class ParserContext < Nokogiri::XML::SAX::ParserContext
-        def self.new thing, encoding = 'UTF-8'
-          [:read, :close].all? { |x| thing.respond_to?(x) } ?  super :
-            memory(thing, encoding)
-        end
-      end
-    end
-  end
-end

data/patches/libxml2/0001-Revert-Do-not-URI-escape-in-server-side-includes.patch

@@ -1,78 +0,0 @@
-From c5538465c08a8ea248a370bf55bc39cd3385e4af Mon Sep 17 00:00:00 2001
-From: Mike Dalessio <mike.dalessio@gmail.com>
-Date: Thu, 29 Mar 2018 14:09:00 -0400
-Subject: [PATCH] Revert "Do not URI escape in server side includes"
-
-This reverts commit 960f0e275616cadc29671a218d7fb9b69eb35588.
----
- HTMLtree.c | 49 +++++++++++--------------------------------------
- 1 file changed, 11 insertions(+), 38 deletions(-)
-
-diff --git a/HTMLtree.c b/HTMLtree.c
-index 2fd0c9c..67160c5 100644
---- a/HTMLtree.c
-+++ b/HTMLtree.c
-@@ -717,49 +717,22 @@ htmlAttrDumpOutput(xmlOutputBufferPtr buf, xmlDocPtr doc, xmlAttrPtr cur,
- 		 (!xmlStrcasecmp(cur->name, BAD_CAST "src")) ||
- 		 ((!xmlStrcasecmp(cur->name, BAD_CAST "name")) &&
- 		  (!xmlStrcasecmp(cur->parent->name, BAD_CAST "a"))))) {
-+		xmlChar *escaped;
- 		xmlChar *tmp = value;
--		/* xmlURIEscapeStr() escapes '"' so it can be safely used. */
--		xmlBufCCat(buf->buffer, "\"");
- 
- 		while (IS_BLANK_CH(*tmp)) tmp++;
- 
--		/* URI Escape everything, except server side includes. */
--		for ( ; ; ) {
--		    xmlChar *escaped;
--		    xmlChar endChar;
--		    xmlChar *end = NULL;
--		    xmlChar *start = (xmlChar *)xmlStrstr(tmp, BAD_CAST "<!--");
--		    if (start != NULL) {
--			end = (xmlChar *)xmlStrstr(tmp, BAD_CAST "-->");
--			if (end != NULL) {
--			    *start = '\0';
--			}
--		    }
--
--		    /* Escape the whole string, or until start (set to '\0'). */
--		    escaped = xmlURIEscapeStr(tmp, BAD_CAST"@/:=?;#%&,+");
--		    if (escaped != NULL) {
--		        xmlBufCat(buf->buffer, escaped);
--		        xmlFree(escaped);
--		    } else {
--		        xmlBufCat(buf->buffer, tmp);
--		    }
--
--		    if (end == NULL) { /* Everything has been written. */
--			break;
--		    }
--
--		    /* Do not escape anything within server side includes. */
--		    *start = '<'; /* Restore the first character of "<!--". */
--		    end += 3; /* strlen("-->") */
--		    endChar = *end;
--		    *end = '\0';
--		    xmlBufCat(buf->buffer, start);
--		    *end = endChar;
--		    tmp = end;
-+		/*
-+		 * the < and > have already been escaped at the entity level
-+		 * And doing so here breaks server side includes
-+		 */
-+		escaped = xmlURIEscapeStr(tmp, BAD_CAST"@/:=?;#%&,+<>");
-+		if (escaped != NULL) {
-+		    xmlBufWriteQuotedString(buf->buffer, escaped);
-+		    xmlFree(escaped);
-+		} else {
-+		    xmlBufWriteQuotedString(buf->buffer, value);
- 		}
--
--		xmlBufCCat(buf->buffer, "\"");
- 	    } else {
- 		xmlBufWriteQuotedString(buf->buffer, value);
- 	    }
--- 
-2.9.5
-

data/patches/libxml2/0005-Fix-infinite-loop-in-xmlStringLenDecodeEntities.patch

@@ -1,32 +0,0 @@
-From 0e1a49c8907645d2e155f0d89d4d9895ac5112b5 Mon Sep 17 00:00:00 2001
-From: Zhipeng Xie <xiezhipeng1@huawei.com>
-Date: Thu, 12 Dec 2019 17:30:55 +0800
-Subject: [PATCH] Fix infinite loop in xmlStringLenDecodeEntities
-
-When ctxt->instate == XML_PARSER_EOF,xmlParseStringEntityRef
-return NULL which cause a infinite loop in xmlStringLenDecodeEntities
-
-Found with libFuzzer.
-
-Signed-off-by: Zhipeng Xie <xiezhipeng1@huawei.com>
----
- parser.c | 3 ++-
- 1 file changed, 2 insertions(+), 1 deletion(-)
-
-diff --git a/parser.c b/parser.c
-index d1c3196..a34bb6c 100644
---- a/parser.c
-+++ b/parser.c
-@@ -2646,7 +2646,8 @@ xmlStringLenDecodeEntities(xmlParserCtxtPtr ctxt, const xmlChar *str, int len,
-     else
-         c = 0;
-     while ((c != 0) && (c != end) && /* non input consuming loop */
--	   (c != end2) && (c != end3)) {
-+           (c != end2) && (c != end3) &&
-+           (ctxt->instate != XML_PARSER_EOF)) {
- 
- 	if (c == 0) break;
-         if ((c == '&') && (str[1] == '#')) {
--- 
-2.17.1
-

data/patches/libxml2/0006-htmlParseComment-treat-as-if-it-closed-the-comment.patch

@@ -1,73 +0,0 @@
-From 4f51a6d2b1755ce5b36c524c215aad70d864ac1d Mon Sep 17 00:00:00 2001
-From: Mike Dalessio <mike.dalessio@gmail.com>
-Date: Mon, 3 Aug 2020 17:36:05 -0400
-Subject: [PATCH 1/2] htmlParseComment: treat `--!>` as if it closed the
- comment
-
-See guidance provided on incorrectly-closed comments here:
-
-https://html.spec.whatwg.org/multipage/parsing.html#parse-error-incorrectly-closed-comment
----
- HTMLparser.c | 28 ++++++++++++++++++++--------
- 1 file changed, 20 insertions(+), 8 deletions(-)
-
-diff --git a/HTMLparser.c b/HTMLparser.c
-index 7b6d689..4d43479 100644
---- a/HTMLparser.c
-+++ b/HTMLparser.c
-@@ -3300,6 +3300,7 @@ htmlParseComment(htmlParserCtxtPtr ctxt) {
-     int q, ql;
-     int r, rl;
-     int cur, l;
-+    int next, nl;
-     xmlParserInputState state;
- 
-     /*
-@@ -3332,6 +3333,21 @@ htmlParseComment(htmlParserCtxtPtr ctxt) {
-     while (IS_CHAR(cur) &&
-            ((cur != '>') ||
- 	    (r != '-') || (q != '-'))) {
-+	NEXTL(l);
-+	next = CUR_CHAR(nl);
-+	if (next == 0) {
-+	    SHRINK;
-+	    GROW;
-+	    next = CUR_CHAR(nl);
-+	}
-+
-+	if ((q == '-') && (r == '-') && (cur == '!') && (next == '>')) {
-+	  htmlParseErr(ctxt, XML_ERR_COMMENT_NOT_FINISHED,
-+		       "Comment incorrectly closed by '--!>'", NULL, NULL);
-+	  cur = '>';
-+	  break;
-+	}
-+
- 	if (len + 5 >= size) {
- 	    xmlChar *tmp;
- 
-@@ -3345,18 +3361,14 @@ htmlParseComment(htmlParserCtxtPtr ctxt) {
- 	    }
- 	    buf = tmp;
- 	}
--	COPY_BUF(ql,buf,len,q);
-+        COPY_BUF(ql,buf,len,q);
-+
- 	q = r;
- 	ql = rl;
- 	r = cur;
- 	rl = l;
--	NEXTL(l);
--	cur = CUR_CHAR(l);
--	if (cur == 0) {
--	    SHRINK;
--	    GROW;
--	    cur = CUR_CHAR(l);
--	}
-+	cur = next;
-+	l = nl;
-     }
-     buf[len] = 0;
-     if (IS_CHAR(cur)) {
--- 
-2.25.1
-

data/patches/libxml2/0007-use-new-htmlParseLookupCommentEnd-to-find-comment-en.patch

@@ -1,103 +0,0 @@
-From b20d746fa7cbb74716171bc49d836af99927e41e Mon Sep 17 00:00:00 2001
-From: Mike Dalessio <mike.dalessio@gmail.com>
-Date: Sun, 11 Oct 2020 14:15:37 -0400
-Subject: [PATCH 2/2] use new htmlParseLookupCommentEnd to find comment ends
-
-Note that the caret in error messages generated during comment parsing
-may have moved by one byte.
-
-See guidance provided on incorrectly-closed comments here:
-
-https://html.spec.whatwg.org/multipage/parsing.html#parse-error-incorrectly-closed-comment
----
- HTMLparser.c | 46 +++++++++++++++++++++++++++++++++++++---------
- 1 file changed, 37 insertions(+), 9 deletions(-)
-
-diff --git a/HTMLparser.c b/HTMLparser.c
-index 4d43479..000dc3d 100644
---- a/HTMLparser.c
-+++ b/HTMLparser.c
-@@ -5331,6 +5331,39 @@ htmlParseLookupChars(htmlParserCtxtPtr ctxt, const xmlChar * stop,
-     return (-1);
- }
- 
-+/**
-+ * htmlParseLookupCommentEnd:
-+ * @ctxt: an HTML parser context
-+ *
-+ * Try to find a comment end tag in the input stream
-+ * The search includes "-->" as well as WHATWG-recommended incorrectly-closed tags.
-+ * (See https://html.spec.whatwg.org/multipage/parsing.html#parse-error-incorrectly-closed-comment)
-+ * This function has a side effect of (possibly) incrementing ctxt->checkIndex
-+ * to avoid rescanning sequences of bytes, it DOES change the state of the
-+ * parser, do not use liberally.
-+ * This wraps to htmlParseLookupSequence()
-+ *
-+ * Returns the index to the current parsing point if the full sequence is available, -1 otherwise.
-+ */
-+static int
-+htmlParseLookupCommentEnd(htmlParserCtxtPtr ctxt)
-+{
-+    int mark = 0;
-+    int cur = CUR_PTR - BASE_PTR;
-+
-+    while (mark >= 0) {
-+	mark = htmlParseLookupSequence(ctxt, '-', '-', 0, 1, 1);
-+	if ((mark < 0) ||
-+	    (NXT(mark+2) == '>') ||
-+	    ((NXT(mark+2) == '!') && (NXT(mark+3) == '>'))) {
-+	    return mark;
-+	}
-+	ctxt->checkIndex = cur + mark + 1;
-+    }
-+    return mark;
-+}
-+
-+
- /**
-  * htmlParseTryOrFinish:
-  * @ctxt:  an HTML parser context
-@@ -5507,8 +5540,7 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
- 		cur = in->cur[0];
- 	        if ((cur == '<') && (next == '!') &&
- 		    (in->cur[2] == '-') && (in->cur[3] == '-')) {
--		    if ((!terminate) &&
--		        (htmlParseLookupSequence(ctxt, '-', '-', '>', 1, 1) < 0))
-+		    if ((!terminate) && (htmlParseLookupCommentEnd(ctxt) < 0))
- 			goto done;
- #ifdef DEBUG_PUSH
- 		    xmlGenericError(xmlGenericErrorContext,
-@@ -5567,8 +5599,7 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
- 		next = in->cur[1];
- 		if ((cur == '<') && (next == '!') &&
- 		    (in->cur[2] == '-') && (in->cur[3] == '-')) {
--		    if ((!terminate) &&
--		        (htmlParseLookupSequence(ctxt, '-', '-', '>', 1, 1) < 0))
-+		    if ((!terminate) && (htmlParseLookupCommentEnd(ctxt) < 0))
- 			goto done;
- #ifdef DEBUG_PUSH
- 		    xmlGenericError(xmlGenericErrorContext,
-@@ -5614,8 +5645,7 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
- 		next = in->cur[1];
- 	        if ((cur == '<') && (next == '!') &&
- 		    (in->cur[2] == '-') && (in->cur[3] == '-')) {
--		    if ((!terminate) &&
--		        (htmlParseLookupSequence(ctxt, '-', '-', '>', 1, 1) < 0))
-+		    if ((!terminate) && (htmlParseLookupCommentEnd(ctxt) < 0))
- 			goto done;
- #ifdef DEBUG_PUSH
- 		    xmlGenericError(xmlGenericErrorContext,
-@@ -5871,9 +5901,7 @@ htmlParseTryOrFinish(htmlParserCtxtPtr ctxt, int terminate) {
- 			htmlParseDocTypeDecl(ctxt);
- 		    } else if ((cur == '<') && (next == '!') &&
- 			(in->cur[2] == '-') && (in->cur[3] == '-')) {
--			if ((!terminate) &&
--			    (htmlParseLookupSequence(
--				ctxt, '-', '-', '>', 1, 1) < 0))
-+			if ((!terminate) && (htmlParseLookupCommentEnd(ctxt) < 0))
- 			    goto done;
- #ifdef DEBUG_PUSH
- 			xmlGenericError(xmlGenericErrorContext,
--- 
-2.25.1
-