nokogiri 1.11.4 → 1.12.5

data/lib/nokogiri/xml/node.rb

@@ -1,7 +1,6 @@
 # encoding: UTF-8
 # frozen_string_literal: true
 require "stringio"
-require "nokogiri/xml/node/save_options"
 
 module Nokogiri
   module XML
@@ -837,7 +836,7 @@ module Nokogiri
         node_set = in_context(contents, options.to_i)
         if (node_set.empty? && (document.errors.length > error_count))
           if options.recover?
-            fragment = Nokogiri::HTML::DocumentFragment.parse contents
+            fragment = Nokogiri::HTML4::DocumentFragment.parse contents
             node_set = fragment.children
           else
             raise document.errors[error_count]
@@ -883,7 +882,7 @@ module Nokogiri
         type == DOCUMENT_NODE
       end
 
-      # Returns true if this is an HTML::Document node
+      # Returns true if this is an HTML4::Document node
       def html?
         type == HTML_DOCUMENT_NODE
       end
@@ -909,11 +908,11 @@ module Nokogiri
       end
 
       ###
-      # Fetch the Nokogiri::HTML::ElementDescription for this node.  Returns
+      # Fetch the Nokogiri::HTML4::ElementDescription for this node.  Returns
       # nil on XML documents and on unknown tags.
       def description
         return nil if document.xml?
-        Nokogiri::HTML::ElementDescription[name]
+        Nokogiri::HTML4::ElementDescription[name]
       end
 
       ###
@@ -1235,3 +1234,5 @@ Requires a Node, NodeSet or String argument, and cannot accept a #{data.class}.
     end
   end
 end
+
+require_relative "node/save_options"

data/lib/nokogiri/xml/parse_options.rb

@@ -71,6 +71,8 @@ module Nokogiri
 
       # the default options used for parsing XML documents
       DEFAULT_XML  = RECOVER | NONET
+      # the default options used for parsing XSLT stylesheets
+      DEFAULT_XSLT = RECOVER | NONET | NOENT | DTDLOAD | DTDATTR | NOCDATA
       # the default options used for parsing HTML documents
       DEFAULT_HTML = RECOVER | NOERROR | NOWARNING | NONET
       # the default options used for parsing XML schemas

data/lib/nokogiri/xml/pp.rb

@@ -1,3 +1,3 @@
 # frozen_string_literal: true
-require 'nokogiri/xml/pp/node'
-require 'nokogiri/xml/pp/character_data'
+require_relative "pp/node"
+require_relative "pp/character_data"

data/lib/nokogiri/xml/sax/document.rb

@@ -2,20 +2,19 @@
 module Nokogiri
   module XML
     ###
-    # SAX Parsers are event driven parsers.  Nokogiri provides two different
-    # event based parsers when dealing with XML.  If you want to do SAX style
-    # parsing using HTML, check out Nokogiri::HTML::SAX.
+    # SAX Parsers are event driven parsers. Nokogiri provides two different event based parsers when
+    # dealing with XML. If you want to do SAX style parsing using HTML, check out
+    # Nokogiri::HTML4::SAX.
     #
-    # The basic way a SAX style parser works is by creating a parser,
-    # telling the parser about the events we're interested in, then giving
-    # the parser some XML to process.  The parser will notify you when
-    # it encounters events you said you would like to know about.
+    # The basic way a SAX style parser works is by creating a parser, telling the parser about the
+    # events we're interested in, then giving the parser some XML to process. The parser will notify
+    # you when it encounters events you said you would like to know about.
     #
-    # To register for events, you simply subclass Nokogiri::XML::SAX::Document,
-    # and implement the methods for which you would like notification.
+    # To register for events, you simply subclass Nokogiri::XML::SAX::Document, and implement the
+    # methods for which you would like notification.
     #
-    # For example, if I want to be notified when a document ends, and when an
-    # element starts, I would write a class like this:
+    # For example, if I want to be notified when a document ends, and when an element starts, I
+    # would write a class like this:
     #
     #   class MyDocument < Nokogiri::XML::SAX::Document
     #     def end_document
@@ -27,8 +26,7 @@ module Nokogiri
     #     end
     #   end
     #
-    # Then I would instantiate a SAX parser with this document, and feed the
-    # parser some XML
+    # Then I would instantiate a SAX parser with this document, and feed the parser some XML
     #
     #   # Create a new parser
     #   parser = Nokogiri::XML::SAX::Parser.new(MyDocument.new)
@@ -36,25 +34,21 @@ module Nokogiri
     #   # Feed the parser some XML
     #   parser.parse(File.open(ARGV[0]))
     #
-    # Now my document handler will be called when each node starts, and when
-    # then document ends.  To see what kinds of events are available, take
-    # a look at Nokogiri::XML::SAX::Document.
+    # Now my document handler will be called when each node starts, and when then document ends. To
+    # see what kinds of events are available, take a look at Nokogiri::XML::SAX::Document.
     #
-    # Two SAX parsers for XML are available, a parser that reads from a string
-    # or IO object as it feels necessary, and a parser that lets you spoon
-    # feed it XML.  If you want to let Nokogiri deal with reading your XML,
-    # use the Nokogiri::XML::SAX::Parser.  If you want to have fine grain
+    # Two SAX parsers for XML are available, a parser that reads from a string or IO object as it
+    # feels necessary, and a parser that lets you spoon feed it XML. If you want to let Nokogiri
+    # deal with reading your XML, use the Nokogiri::XML::SAX::Parser. If you want to have fine grain
     # control over the XML input, use the Nokogiri::XML::SAX::PushParser.
     module SAX
       ###
-      # This class is used for registering types of events you are interested
-      # in handling.  All of the methods on this class are available as
-      # possible events while parsing an XML document.  To register for any
-      # particular event, just subclass this class and implement the methods
-      # you are interested in knowing about.
+      # This class is used for registering types of events you are interested in handling. All of
+      # the methods on this class are available as possible events while parsing an XML document. To
+      # register for any particular event, just subclass this class and implement the methods you
+      # are interested in knowing about.
       #
-      # To only be notified about start and end element events, write a class
-      # like this:
+      # To only be notified about start and end element events, write a class like this:
       #
       #   class MyDocument < Nokogiri::XML::SAX::Document
       #     def start_element name, attrs = []
@@ -66,8 +60,8 @@ module Nokogiri
       #     end
       #   end
       #
-      # You can use this event handler for any SAX style parser included with
-      # Nokogiri.  See Nokogiri::XML::SAX, and Nokogiri::HTML::SAX.
+      # You can use this event handler for any SAX style parser included with Nokogiri. See
+      # Nokogiri::XML::SAX, and Nokogiri::HTML4::SAX.
       class Document
         ###
         # Called when an XML declaration is parsed
@@ -129,7 +123,7 @@ module Nokogiri
         end
 
         ###
-        # Characters read between a tag.  This method might be called multiple
+        # Characters read between a tag. This method might be called multiple
         # times given one contiguous string of characters.
         #
         # +string+ contains the character data

data/lib/nokogiri/xml/sax.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
-require 'nokogiri/xml/sax/document'
-require 'nokogiri/xml/sax/parser_context'
-require 'nokogiri/xml/sax/parser'
-require 'nokogiri/xml/sax/push_parser'
+require_relative "sax/document"
+require_relative "sax/parser_context"
+require_relative "sax/parser"
+require_relative "sax/push_parser"

data/lib/nokogiri/xml/xpath.rb

@@ -1,9 +1,9 @@
 # frozen_string_literal: true
-require 'nokogiri/xml/xpath/syntax_error'
-
 module Nokogiri
   module XML
     module XPath
     end
   end
 end
+
+require_relative "xpath/syntax_error"

data/lib/nokogiri/xml.rb

@@ -1,38 +1,9 @@
 # frozen_string_literal: true
-require 'nokogiri/xml/pp'
-require 'nokogiri/xml/parse_options'
-require 'nokogiri/xml/sax'
-require 'nokogiri/xml/searchable'
-require 'nokogiri/xml/node'
-require 'nokogiri/xml/attribute_decl'
-require 'nokogiri/xml/element_decl'
-require 'nokogiri/xml/element_content'
-require 'nokogiri/xml/character_data'
-require 'nokogiri/xml/namespace'
-require 'nokogiri/xml/attr'
-require 'nokogiri/xml/dtd'
-require 'nokogiri/xml/cdata'
-require 'nokogiri/xml/text'
-require 'nokogiri/xml/document'
-require 'nokogiri/xml/document_fragment'
-require 'nokogiri/xml/processing_instruction'
-require 'nokogiri/xml/node_set'
-require 'nokogiri/xml/syntax_error'
-require 'nokogiri/xml/xpath'
-require 'nokogiri/xml/xpath_context'
-require 'nokogiri/xml/builder'
-require 'nokogiri/xml/reader'
-require 'nokogiri/xml/notation'
-require 'nokogiri/xml/entity_decl'
-require 'nokogiri/xml/entity_reference'
-require 'nokogiri/xml/schema'
-require 'nokogiri/xml/relax_ng'
-
 module Nokogiri
   class << self
     ###
     # Parse XML.  Convenience method for Nokogiri::XML::Document.parse
-    def XML thing, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_XML, &block
+    def XML(thing, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_XML, &block)
       Nokogiri::XML::Document.parse(thing, url, encoding, options, &block)
     end
   end
@@ -41,20 +12,19 @@ module Nokogiri
     # Original C14N 1.0 spec canonicalization
     XML_C14N_1_0 =       0
     # Exclusive C14N 1.0 spec canonicalization
-    XML_C14N_EXCLUSIVE_1_0 =     1
+    XML_C14N_EXCLUSIVE_1_0 = 1
     # C14N 1.1 spec canonicalization
     XML_C14N_1_1 = 2
     class << self
       ###
       # Parse an XML document using the Nokogiri::XML::Reader API.  See
       # Nokogiri::XML::Reader for mor information
-      def Reader string_or_io, url = nil, encoding = nil, options = ParseOptions::STRICT
-
+      def Reader(string_or_io, url = nil, encoding = nil, options = ParseOptions::STRICT)
         options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
         # Give the options to the user
         yield options if block_given?
 
-        if string_or_io.respond_to? :read
+        if string_or_io.respond_to?(:read)
           return Reader.from_io(string_or_io, url, encoding, options.to_i)
         end
         Reader.from_memory(string_or_io, url, encoding, options.to_i)
@@ -62,15 +32,44 @@ module Nokogiri
 
       ###
       # Parse XML.  Convenience method for Nokogiri::XML::Document.parse
-      def parse thing, url = nil, encoding = nil, options = ParseOptions::DEFAULT_XML, &block
+      def parse(thing, url = nil, encoding = nil, options = ParseOptions::DEFAULT_XML, &block)
         Document.parse(thing, url, encoding, options, &block)
       end
 
       ####
       # Parse a fragment from +string+ in to a NodeSet.
-      def fragment string
+      def fragment(string)
         XML::DocumentFragment.parse(string)
       end
     end
   end
 end
+
+require_relative "xml/pp"
+require_relative "xml/parse_options"
+require_relative "xml/sax"
+require_relative "xml/searchable"
+require_relative "xml/node"
+require_relative "xml/attribute_decl"
+require_relative "xml/element_decl"
+require_relative "xml/element_content"
+require_relative "xml/character_data"
+require_relative "xml/namespace"
+require_relative "xml/attr"
+require_relative "xml/dtd"
+require_relative "xml/cdata"
+require_relative "xml/text"
+require_relative "xml/document"
+require_relative "xml/document_fragment"
+require_relative "xml/processing_instruction"
+require_relative "xml/node_set"
+require_relative "xml/syntax_error"
+require_relative "xml/xpath"
+require_relative "xml/xpath_context"
+require_relative "xml/builder"
+require_relative "xml/reader"
+require_relative "xml/notation"
+require_relative "xml/entity_decl"
+require_relative "xml/entity_reference"
+require_relative "xml/schema"
+require_relative "xml/relax_ng"

data/lib/nokogiri/xslt/stylesheet.rb

@@ -18,7 +18,7 @@ module Nokogiri
       # Apply an XSLT stylesheet to an XML::Document.
       # +params+ is an array of strings used as XSLT parameters.
       # returns serialized document
-      def apply_to document, params = []
+      def apply_to(document, params = [])
         serialize(transform(document, params))
       end
     end

data/lib/nokogiri/xslt.rb

@@ -1,6 +1,4 @@
 # frozen_string_literal: true
-require 'nokogiri/xslt/stylesheet'
-
 module Nokogiri
   class << self
     ###
@@ -22,32 +20,32 @@ module Nokogiri
     class << self
       ###
       # Parse the stylesheet in +string+, register any +modules+
-      def parse string, modules = {}
+      def parse(string, modules = {})
         modules.each do |url, klass|
-          XSLT.register url, klass
+          XSLT.register(url, klass)
         end
 
+        doc = XML::Document.parse(string, nil, nil, XML::ParseOptions::DEFAULT_XSLT)
         if Nokogiri.jruby?
-          Stylesheet.parse_stylesheet_doc(XML.parse(string), string)
+          Stylesheet.parse_stylesheet_doc(doc, string)
         else
-          Stylesheet.parse_stylesheet_doc(XML.parse(string))
+          Stylesheet.parse_stylesheet_doc(doc)
         end
       end
 
       ###
       # Quote parameters in +params+ for stylesheet safety
-      def quote_params params
+      def quote_params(params)
         parray = (params.instance_of?(Hash) ? params.to_a.flatten : params).dup
-        parray.each_with_index do |v,i|
-          if i % 2 > 0
-            parray[i]=
-              if v =~ /'/
-                "concat('#{ v.gsub(/'/, %q{', "'", '}) }')"
-              else
-                "'#{v}'";
-              end
+        parray.each_with_index do |v, i|
+          parray[i] = if i % 2 > 0
+            if v =~ /'/
+              "concat('#{v.gsub(/'/, %q{', "'", '})}')"
+            else
+              "'#{v}'"
+            end
           else
-            parray[i] = v.to_s
+            v.to_s
           end
         end
         parray.flatten
@@ -55,3 +53,5 @@ module Nokogiri
     end
   end
 end
+
+require_relative "xslt/stylesheet"

data/lib/nokogiri.rb

@@ -2,38 +2,29 @@
 # frozen_string_literal: true
 # Modify the PATH on windows so that the external DLLs will get loaded.
 
-require 'rbconfig'
+require "rbconfig"
 
 if defined?(RUBY_ENGINE) && RUBY_ENGINE == "jruby"
-  require 'nokogiri/jruby/dependencies'
+  require_relative "nokogiri/jruby/dependencies"
 end
 
-require 'nokogiri/extension'
-
-require 'nokogiri/version'
-require 'nokogiri/syntax_error'
-require 'nokogiri/xml'
-require 'nokogiri/xslt'
-require 'nokogiri/html'
-require 'nokogiri/decorators/slop'
-require 'nokogiri/css'
-require 'nokogiri/html/builder'
+require_relative "nokogiri/extension"
 
 # Nokogiri parses and searches XML/HTML very quickly, and also has
 # correctly implemented CSS3 selector support as well as XPath 1.0
 # support.
 #
 # Parsing a document returns either a Nokogiri::XML::Document, or a
-# Nokogiri::HTML::Document depending on the kind of document you parse.
+# Nokogiri::HTML4::Document depending on the kind of document you parse.
 #
 # Here is an example:
 #
 #   require 'nokogiri'
 #   require 'open-uri'
 #
-#   # Get a Nokogiri::HTML:Document for the page we’re interested in...
+#   # Get a Nokogiri::HTML4::Document for the page we’re interested in...
 #
-#   doc = Nokogiri::HTML(URI.open('http://www.google.com/search?q=tenderlove'))
+#   doc = Nokogiri::HTML4(URI.open('http://www.google.com/search?q=tenderlove'))
 #
 #   # Do funky things with it using Nokogiri::XML::Node methods...
 #
@@ -49,27 +40,27 @@ module Nokogiri
   class << self
     ###
     # Parse an HTML or XML document.  +string+ contains the document.
-    def parse string, url = nil, encoding = nil, options = nil
+    def parse(string, url = nil, encoding = nil, options = nil)
       if string.respond_to?(:read) ||
           /^\s*<(?:!DOCTYPE\s+)?html[\s>]/i === string[0, 512]
         # Expect an HTML indicator to appear within the first 512
         # characters of a document. (<?xml ?> + <?xml-stylesheet ?>
         # shouldn't be that long)
-        Nokogiri.HTML(string, url, encoding,
+        Nokogiri.HTML4(string, url, encoding,
           options || XML::ParseOptions::DEFAULT_HTML)
       else
         Nokogiri.XML(string, url, encoding,
           options || XML::ParseOptions::DEFAULT_XML)
-      end.tap { |doc|
+      end.tap do |doc|
         yield doc if block_given?
-      }
+      end
     end
 
     ###
     # Create a new Nokogiri::XML::DocumentFragment
-    def make input = nil, opts = {}, &blk
+    def make(input = nil, opts = {}, &blk)
       if input
-        Nokogiri::HTML.fragment(input).children.first
+        Nokogiri::HTML4.fragment(input).children.first
       else
         Nokogiri(&blk)
       end
@@ -98,10 +89,10 @@ module Nokogiri
       # Make sure to support some popular encoding aliases not known by
       # all iconv implementations.
       {
-        'Windows-31J' => 'CP932',	# Windows-31J is the IANA registered name of CP932.
-      }.each { |alias_name, name|
+        "Windows-31J" => "CP932",	# Windows-31J is the IANA registered name of CP932.
+      }.each do |alias_name, name|
         EncodingHandler.alias(name, alias_name) if EncodingHandler[alias_name].nil?
-      }
+      end
     end
   end
 
@@ -109,15 +100,26 @@ module Nokogiri
 end
 
 ###
-# Parse a document contained in +args+.  Nokogiri will try to guess what
-# type of document you are attempting to parse.  For more information, see
-# Nokogiri.parse
+# Parse a document contained in +args+.  Nokogiri will try to guess what type of document you are
+# attempting to parse.  For more information, see Nokogiri.parse
 #
-# To specify the type of document, use Nokogiri.XML or Nokogiri.HTML.
+# To specify the type of document, use {Nokogiri.XML}, {Nokogiri.HTML4}, or {Nokogiri.HTML5}.
 def Nokogiri(*args, &block)
   if block_given?
-    Nokogiri::HTML::Builder.new(&block).doc.root
+    Nokogiri::HTML4::Builder.new(&block).doc.root
   else
     Nokogiri.parse(*args)
   end
 end
+
+require_relative "nokogiri/version"
+require_relative "nokogiri/syntax_error"
+require_relative "nokogiri/xml"
+require_relative "nokogiri/xslt"
+require_relative "nokogiri/html4"
+require_relative "nokogiri/html"
+require_relative "nokogiri/decorators/slop"
+require_relative "nokogiri/css"
+require_relative "nokogiri/html4/builder"
+
+require_relative "nokogiri/html5" if Nokogiri.uses_gumbo?

data/patches/libxml2/0007-Fix-XPath-recursion-limit.patch

@@ -0,0 +1,31 @@
+From 3e1aad4fe584747fd7d17cc7b2863a78e2d21a77 Mon Sep 17 00:00:00 2001
+From: Nick Wellnhofer <wellnhofer@aevum.de>
+Date: Wed, 2 Jun 2021 17:31:49 +0200
+Subject: [PATCH] Fix XPath recursion limit
+
+Fix accounting of recursion depth when parsing XPath expressions.
+
+This silly bug introduced in commit 804c5297 could lead to spurious
+errors when parsing larger expressions or XSLT documents.
+
+Should fix #264.
+---
+ xpath.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/xpath.c b/xpath.c
+index 7497ba0..1aa2f1a 100644
+--- a/xpath.c
++++ b/xpath.c
+@@ -10983,7 +10983,7 @@ xmlXPathCompileExpr(xmlXPathParserContextPtr ctxt, int sort) {
+     }
+ 
+     if (xpctxt != NULL)
+-        xpctxt->depth -= 1;
++        xpctxt->depth -= 10;
+ }
+ 
+ /**
+-- 
+2.31.0
+