nokogiri 1.8.2 → 1.8.3

data/lib/nokogiri/css/parser.y

@@ -221,8 +221,9 @@ rule
     : HASH { result = Node.new(:ID, [unescape_css_identifier(val.first)]) }
     ;
   attrib_val_0or1
-    : eql_incl_dash IDENT { result = [val.first, val[1]] }
-    | eql_incl_dash STRING { result = [val.first, val[1]] }
+    : eql_incl_dash IDENT { result = [val.first, unescape_css_identifier(val[1])] }
+    | eql_incl_dash STRING { result = [val.first, unescape_css_string(val[1])] }
+    | eql_incl_dash NUMBER { result = [val.first, val[1]] }
     |
     ;
   eql_incl_dash
@@ -259,3 +260,13 @@ require 'nokogiri/css/parser_extras'
 def unescape_css_identifier(identifier)
   identifier.gsub(/\\(?:([^0-9a-fA-F])|([0-9a-fA-F]{1,6})\s?)/){ |m| $1 || [$2.hex].pack('U') }
 end
+
+def unescape_css_string(str)
+  str.gsub(/\\(?:([^0-9a-fA-F])|([0-9a-fA-F]{1,6})\s?)/) do |m|
+    if $1=="\n"
+      ''
+    else
+      $1 || [$2.hex].pack('U')
+    end
+  end
+end

data/lib/nokogiri/css/tokenizer.rb

@@ -130,7 +130,7 @@ class Tokenizer # :nodoc:
       when (text = @ss.scan(/[\s]+/))
          action { [:S, text] }
 
-      when (text = @ss.scan(/"([^\n\r\f"]|\n|\r\n|\r|\f|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])*"|'([^\n\r\f']|\n|\r\n|\r|\f|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])*'/))
+      when (text = @ss.scan(/"([^\n\r\f"]|\n|\r\n|\r|\f|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])*(?<!\\)(?:\\{2})*"|'([^\n\r\f']|\n|\r\n|\r|\f|[^\0-\177]|\\[0-9A-Fa-f]{1,6}(\r\n|[\s])?|\\[^\n\r\f0-9A-Fa-f])*(?<!\\)(?:\\{2})*'/))
          action { [:STRING, text] }
 
       when (text = @ss.scan(/./))

data/lib/nokogiri/css/tokenizer.rex

@@ -14,8 +14,8 @@ macro
   nmstart   [_A-Za-z]|{nonascii}|{escape}
   ident     [-@]?({nmstart})({nmchar})*
   name      ({nmchar})+
-  string1   "([^\n\r\f"]|{nl}|{nonascii}|{escape})*"
-  string2   '([^\n\r\f']|{nl}|{nonascii}|{escape})*'
+  string1   "([^\n\r\f"]|{nl}|{nonascii}|{escape})*(?<!\\)(?:\\{2})*"
+  string2   '([^\n\r\f']|{nl}|{nonascii}|{escape})*(?<!\\)(?:\\{2})*'
   string    {string1}|{string2}
 
 rule
@@ -44,9 +44,9 @@ rule
             {num}            { [:NUMBER, text] }
             {w}\/\/{w}       { [:DOUBLESLASH, text] }
             {w}\/{w}         { [:SLASH, text] }
-            
+
             U\+[0-9a-f?]{1,6}(-[0-9a-f]{1,6})?  {[:UNICODE_RANGE, text] }
-            
+
             [\s]+            { [:S, text] }
             {string}         { [:STRING, text] }
             .                { [text, text] }

data/lib/nokogiri/css/xpath_visitor.rb

@@ -88,6 +88,13 @@ module Nokogiri
         value = node.value.last
         value = "'#{value}'" if value !~ /^['"]/
 
+        if (value[0]==value[-1]) && %q{"'}.include?(value[0])
+          str_value = value[1..-2]
+          if str_value.include?(value[0])
+            value = 'concat("' + str_value.split('"', -1).join(%q{", '"', "}) + '", "")'
+          end
+        end
+
         case node.value[1]
         when :equal
           attribute + " = " + "#{value}"
@@ -145,7 +152,7 @@ module Nokogiri
           "#{node.value.first.accept(self) if node.value.first} and #{node.value.last.accept(self)}"
         end
       end
-      
+
       {
         'direct_adjacent_selector'  => "/following-sibling::*[1]/self::",
         'following_selector'        => "/following-sibling::",
@@ -208,7 +215,7 @@ module Nokogiri
         end
         [a, b]
       end
-      
+
       def is_of_type_pseudo_class? node
         if node.type==:PSEUDO_CLASS
           if node.value[0].is_a?(Nokogiri::CSS::Node) and node.value[0].type == :FUNCTION
@@ -216,7 +223,7 @@ module Nokogiri
           else
             node.value[0]
           end =~ /(nth|first|last|only)-of-type(\()?/
-        end   
+        end
       end
     end
   end

data/lib/nokogiri/html/document_fragment.rb

@@ -6,7 +6,17 @@ module Nokogiri
       def self.parse tags, encoding = nil
         doc = HTML::Document.new
 
-        encoding ||= tags.respond_to?(:encoding) ? tags.encoding.name : 'UTF-8'
+        encoding ||= if tags.respond_to?(:encoding)
+                       encoding = tags.encoding
+                       if encoding == ::Encoding::ASCII_8BIT
+                         'UTF-8'
+                       else
+                         encoding.name
+                       end
+                     else
+                       'UTF-8'
+                     end
+
         doc.encoding = encoding
 
         new(doc, tags)

data/lib/nokogiri/version.rb

@@ -1,6 +1,6 @@
 module Nokogiri
   # The version of Nokogiri you are using
-  VERSION = '1.8.2'
+  VERSION = '1.8.3'
 
   class VersionInfo # :nodoc:
     def jruby?

data/lib/nokogiri/xml/node.rb

@@ -350,6 +350,64 @@ module Nokogiri
         }
       end
 
+      ###
+      # Get the list of class names of this Node, without
+      # deduplication or sorting.
+      def classes
+        self['class'].to_s.scan(/\S+/)
+      end
+
+      ###
+      # Add +name+ to the "class" attribute value of this Node and
+      # return self.  If the value is already in the current value, it
+      # is not added.  If no "class" attribute exists yet, one is
+      # created with the given value.
+      #
+      # More than one class may be added at a time, separated by a
+      # space.
+      def add_class name
+        names = classes
+        self['class'] = (names + (name.scan(/\S+/) - names)).join(' ')
+        self
+      end
+
+      ###
+      # Append +name+ to the "class" attribute value of this Node and
+      # return self.  The value is simply appended without checking if
+      # it is already in the current value.  If no "class" attribute
+      # exists yet, one is created with the given value.
+      #
+      # More than one class may be appended at a time, separated by a
+      # space.
+      def append_class name
+        self['class'] = (classes + name.scan(/\S+/)).join(' ')
+        self
+      end
+
+      ###
+      # Remove +name+ from the "class" attribute value of this Node
+      # and return self.  If there are many occurrences of the name,
+      # they are all removed.
+      #
+      # More than one class may be removed at a time, separated by a
+      # space.
+      #
+      # If no class name is left after removal, or when +name+ is nil,
+      # the "class" attribute is removed from this Node.
+      def remove_class name = nil
+        if name
+          names = classes - name.scan(/\S+/)
+          if names.empty?
+            delete 'class'
+          else
+            self['class'] = names.join(' ')
+          end
+        else
+          delete "class"
+        end
+        self
+      end
+
       ###
       # Remove the attribute named +name+
       def remove_attribute name

data/lib/nokogiri/xml/node_set.rb

@@ -43,9 +43,14 @@ module Nokogiri
       end
 
       ###
-      # Returns the index of the first node in self that is == to +node+. Returns nil if no match is found.
-      def index(node)
-        each_with_index { |member, j| return j if member == node }
+      # Returns the index of the first node in self that is == to +node+ or meets the given block. Returns nil if no match is found.
+      def index(node = nil, &block)
+        if node
+          warn "given block not used" if block_given?
+          each_with_index { |member, j| return j if member == node }
+        elsif block_given?
+          each_with_index { |member, j| return j if yield(member) }
+        end
         nil
       end
 
@@ -130,31 +135,37 @@ module Nokogiri
       end
 
       ###
-      # Append the class attribute +name+ to all Node objects in the NodeSet.
+      # Add the class attribute +name+ to all Node objects in the
+      # NodeSet.
+      #
+      # See Nokogiri::XML::Node#add_class for more information.
       def add_class name
         each do |el|
-          classes = el['class'].to_s.split(/\s+/)
-          el['class'] = classes.push(name).uniq.join " "
+          el.add_class(name)
+        end
+        self
+      end
+
+      ###
+      # Append the class attribute +name+ to all Node objects in the
+      # NodeSet.
+      #
+      # See Nokogiri::XML::Node#append_class for more information.
+      def append_class name
+        each do |el|
+          el.append_class(name)
         end
         self
       end
 
       ###
-      # Remove the class attribute +name+ from all Node objects in the NodeSet.
-      # If +name+ is nil, remove the class attribute from all Nodes in the
+      # Remove the class attribute +name+ from all Node objects in the
       # NodeSet.
+      #
+      # See Nokogiri::XML::Node#remove_class for more information.
       def remove_class name = nil
         each do |el|
-          if name
-            classes = el['class'].to_s.split(/\s+/)
-            if classes.empty?
-              el.delete 'class'
-            else
-              el['class'] = (classes - [name]).uniq.join " "
-            end
-          else
-            el.delete "class"
-          end
+          el.remove_class(name)
         end
         self
       end
@@ -182,10 +193,13 @@ module Nokogiri
         each { |el| el.delete name }
         self
       end
+      alias remove_attribute remove_attr
 
       ###
       # Iterate over each node, yielding  to +block+
       def each(&block)
+        return to_enum unless block_given?
+
         0.upto(length - 1) do |x|
           yield self[x]
         end

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

@@ -0,0 +1,78 @@
+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/test/css/test_nthiness.rb

@@ -71,83 +71,83 @@ EOF
 
 
       def test_even
-        assert_result_rows [2,4,6,8,10,12,14], @parser.search("table/tr:nth(even)")
+        assert_result_rows [2,4,6,8,10,12,14], @parser.search("table//tr:nth(even)")
       end
 
       def test_odd
-        assert_result_rows [1,3,5,7,9,11,13], @parser.search("table/tr:nth(odd)")
+        assert_result_rows [1,3,5,7,9,11,13], @parser.search("table//tr:nth(odd)")
       end
 
       def test_n
-        assert_result_rows((1..14).to_a, @parser.search("table/tr:nth(n)"))
+        assert_result_rows((1..14).to_a, @parser.search("table//tr:nth(n)"))
       end
 
       def test_2n
-        assert_equal @parser.search("table/tr:nth(even)").inner_text, @parser.search("table/tr:nth(2n)").inner_text
+        assert_equal @parser.search("table//tr:nth(even)").inner_text, @parser.search("table//tr:nth(2n)").inner_text
       end
 
       def test_2np1
-        assert_equal @parser.search("table/tr:nth(odd)").inner_text, @parser.search("table/tr:nth(2n+1)").inner_text
+        assert_equal @parser.search("table//tr:nth(odd)").inner_text, @parser.search("table//tr:nth(2n+1)").inner_text
       end
 
       def test_4np3
-        assert_result_rows [3,7,11], @parser.search("table/tr:nth(4n+3)")
+        assert_result_rows [3,7,11], @parser.search("table//tr:nth(4n+3)")
       end
 
       def test_3np4
-        assert_result_rows [4,7,10,13], @parser.search("table/tr:nth(3n+4)")
+        assert_result_rows [4,7,10,13], @parser.search("table//tr:nth(3n+4)")
       end
 
       def test_mnp3
-        assert_result_rows [1,2,3], @parser.search("table/tr:nth(-n+3)")
+        assert_result_rows [1,2,3], @parser.search("table//tr:nth(-n+3)")
       end
 
       def test_4nm1
-        assert_result_rows [3,7,11], @parser.search("table/tr:nth(4n-1)")
+        assert_result_rows [3,7,11], @parser.search("table//tr:nth(4n-1)")
       end
 
       def test_np3
-        assert_result_rows [3,4,5,6,7,8,9,10,11,12,13,14], @parser.search("table/tr:nth(n+3)")
+        assert_result_rows [3,4,5,6,7,8,9,10,11,12,13,14], @parser.search("table//tr:nth(n+3)")
       end
 
       def test_first
-        assert_result_rows [1], @parser.search("table/tr:first")
-        assert_result_rows [1], @parser.search("table/tr:first()")
+        assert_result_rows [1], @parser.search("table//tr:first")
+        assert_result_rows [1], @parser.search("table//tr:first()")
       end
 
       def test_last
-        assert_result_rows [14], @parser.search("table/tr:last")
-        assert_result_rows [14], @parser.search("table/tr:last()")
+        assert_result_rows [14], @parser.search("table//tr:last")
+        assert_result_rows [14], @parser.search("table//tr:last()")
       end
 
       def test_first_child
         assert_result_rows [1], @parser.search("div/b:first-child"), "bold"
-        assert_result_rows [1], @parser.search("table/tr:first-child")
+        assert_result_rows [1], @parser.search("table//tr:first-child")
         assert_result_rows [2,4],  @parser.search("div/h1.c:first-child"), "header"
       end
 
       def test_last_child
         assert_result_rows [3], @parser.search("div/b:last-child"), "bold"
-        assert_result_rows [14], @parser.search("table/tr:last-child")
+        assert_result_rows [14], @parser.search("table//tr:last-child")
         assert_result_rows [3,4], @parser.search("div/h1.c:last-child"), "header"
       end
       
       def test_nth_child
         assert_result_rows [2], @parser.search("div/b:nth-child(3)"), "bold"
-        assert_result_rows [5], @parser.search("table/tr:nth-child(5)")
+        assert_result_rows [5], @parser.search("table//tr:nth-child(5)")
         assert_result_rows [1,3], @parser.search("div/h1.c:nth-child(2)"), "header"
         assert_result_rows [3,4], @parser.search("div/i.b:nth-child(2n+1)"), "italic"
       end
 
       def test_first_of_type
-        assert_result_rows [1], @parser.search("table/tr:first-of-type")
+        assert_result_rows [1], @parser.search("table//tr:first-of-type")
         assert_result_rows [1], @parser.search("div/b:first-of-type"), "bold"
         assert_result_rows [2], @parser.search("div/b.a:first-of-type"), "bold"
         assert_result_rows [3], @parser.search("div/i.b:first-of-type"), "italic"
       end
 
       def test_last_of_type
-        assert_result_rows [14], @parser.search("table/tr:last-of-type")
+        assert_result_rows [14], @parser.search("table//tr:last-of-type")
         assert_result_rows [3], @parser.search("div/b:last-of-type"), "bold"
         assert_result_rows [2,7], @parser.search("div/i:last-of-type"), "italic"
         assert_result_rows [2,6,7], @parser.search("div i:last-of-type"), "italic"
@@ -165,8 +165,8 @@ EOF
       end
       
       def test_nth_last_of_type
-        assert_result_rows [14], @parser.search("table/tr:nth-last-of-type(1)")
-        assert_result_rows [12], @parser.search("table/tr:nth-last-of-type(3)")
+        assert_result_rows [14], @parser.search("table//tr:nth-last-of-type(1)")
+        assert_result_rows [12], @parser.search("table//tr:nth-last-of-type(3)")
         assert_result_rows [2,6,7], @parser.search("div i:nth-last-of-type(1)"), "italic"
         assert_result_rows [1,5], @parser.search("div i:nth-last-of-type(2)"), "italic"        
         assert_result_rows [4], @parser.search("div/i.b:nth-last-of-type(1)"), "italic"