nokogiri 1.10.9 → 1.18.3

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

@@ -1,62 +0,0 @@
-module Nokogiri
-  module HTML
-    ###
-    # Nokogiri lets you write a SAX parser to process HTML but get HTML
-    # correction features.
-    #
-    # See Nokogiri::HTML::SAX::Parser for a basic example of using a
-    # SAX parser with HTML.
-    #
-    # For more information on SAX parsers, see Nokogiri::XML::SAX
-    module SAX
-      ###
-      # This class lets you perform SAX style parsing on HTML with HTML
-      # error correction.
-      #
-      # Here is a basic usage example:
-      #
-      #   class MyDoc < Nokogiri::XML::SAX::Document
-      #     def start_element name, attributes = []
-      #       puts "found a #{name}"
-      #     end
-      #   end
-      #
-      #   parser = Nokogiri::HTML::SAX::Parser.new(MyDoc.new)
-      #   parser.parse(File.read(ARGV[0], mode: 'rb'))
-      #
-      # For more information on SAX parsers, see Nokogiri::XML::SAX
-      class Parser < Nokogiri::XML::SAX::Parser
-        ###
-        # Parse html stored in +data+ using +encoding+
-        def parse_memory data, encoding = 'UTF-8'
-          raise ArgumentError unless data
-          return unless data.length > 0
-          ctx = ParserContext.memory(data, encoding)
-          yield ctx if block_given?
-          ctx.parse_with self
-        end
-
-        ###
-        # Parse given +io+
-        def parse_io io, encoding = 'UTF-8'
-          check_encoding(encoding)
-          @encoding = encoding
-          ctx = ParserContext.io(io, ENCODINGS[encoding])
-          yield ctx if block_given?
-          ctx.parse_with self
-        end
-
-        ###
-        # Parse a file with +filename+
-        def parse_file filename, encoding = 'UTF-8'
-          raise ArgumentError unless filename
-          raise Errno::ENOENT unless File.exist?(filename)
-          raise Errno::EISDIR if File.directory?(filename)
-          ctx = ParserContext.file(filename, encoding)
-          yield ctx if block_given?
-          ctx.parse_with self
-        end
-      end
-    end
-  end
-end

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

@@ -1,16 +0,0 @@
-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/libxml2/0004-libxml2.la-is-in-top_builddir.patch

@@ -1,25 +0,0 @@
-From 0b6ae484761fa01242fe8b67b54e3eb2d282d83d Mon Sep 17 00:00:00 2001
-From: Mike Dalessio <mike.dalessio@gmail.com>
-Date: Wed, 4 Dec 2019 08:43:51 -0500
-Subject: [PATCH] fix libxml2.la's path
-
----
- Makefile.in | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/Makefile.in b/Makefile.in
-index cf96d41..1372d8b 100644
---- a/Makefile.in
-+++ b/Makefile.in
-@@ -1057,7 +1057,7 @@ clean-noinstLTLIBRARIES:
- 	  rm -f $${locs}; \
- 	}
- 
--libxml2.la: $(libxml2_la_OBJECTS) $(libxml2_la_DEPENDENCIES) $(EXTRA_libxml2_la_DEPENDENCIES) 
-+$(top_builddir)/libxml2.la: $(libxml2_la_OBJECTS) $(libxml2_la_DEPENDENCIES) $(EXTRA_libxml2_la_DEPENDENCIES) 
- 	$(AM_V_CCLD)$(libxml2_la_LINK) -rpath $(libdir) $(libxml2_la_OBJECTS) $(libxml2_la_LIBADD) $(LIBS)
- 
- testdso.la: $(testdso_la_OBJECTS) $(testdso_la_DEPENDENCIES) $(EXTRA_testdso_la_DEPENDENCIES) 
--- 
-2.17.1
-

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
-