nokogiri 1.12.3 → 1.13.1

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

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 module Nokogiri
   module XML
     module SAX
@@ -36,29 +37,29 @@ module Nokogiri
 
         # Encodinds this parser supports
         ENCODINGS = {
-          'NONE'        => 0, # No char encoding detected
-          'UTF-8'       => 1, # UTF-8
-          'UTF16LE'     => 2, # UTF-16 little endian
-          'UTF16BE'     => 3, # UTF-16 big endian
-          'UCS4LE'      => 4, # UCS-4 little endian
-          'UCS4BE'      => 5, # UCS-4 big endian
-          'EBCDIC'      => 6, # EBCDIC uh!
-          'UCS4-2143'   => 7, # UCS-4 unusual ordering
-          'UCS4-3412'   => 8, # UCS-4 unusual ordering
-          'UCS2'        => 9, # UCS-2
-          'ISO-8859-1'  => 10, # ISO-8859-1 ISO Latin 1
-          'ISO-8859-2'  => 11, # ISO-8859-2 ISO Latin 2
-          'ISO-8859-3'  => 12, # ISO-8859-3
-          'ISO-8859-4'  => 13, # ISO-8859-4
-          'ISO-8859-5'  => 14, # ISO-8859-5
-          'ISO-8859-6'  => 15, # ISO-8859-6
-          'ISO-8859-7'  => 16, # ISO-8859-7
-          'ISO-8859-8'  => 17, # ISO-8859-8
-          'ISO-8859-9'  => 18, # ISO-8859-9
-          'ISO-2022-JP' => 19, # ISO-2022-JP
-          'SHIFT-JIS'   => 20, # Shift_JIS
-          'EUC-JP'      => 21, # EUC-JP
-          'ASCII'       => 22, # pure ASCII
+          "NONE" => 0, # No char encoding detected
+          "UTF-8" => 1, # UTF-8
+          "UTF16LE" => 2, # UTF-16 little endian
+          "UTF16BE" => 3, # UTF-16 big endian
+          "UCS4LE" => 4, # UCS-4 little endian
+          "UCS4BE" => 5, # UCS-4 big endian
+          "EBCDIC" => 6, # EBCDIC uh!
+          "UCS4-2143" => 7, # UCS-4 unusual ordering
+          "UCS4-3412" => 8, # UCS-4 unusual ordering
+          "UCS2" => 9, # UCS-2
+          "ISO-8859-1" => 10, # ISO-8859-1 ISO Latin 1
+          "ISO-8859-2" => 11, # ISO-8859-2 ISO Latin 2
+          "ISO-8859-3" => 12, # ISO-8859-3
+          "ISO-8859-4" => 13, # ISO-8859-4
+          "ISO-8859-5" => 14, # ISO-8859-5
+          "ISO-8859-6" => 15, # ISO-8859-6
+          "ISO-8859-7" => 16, # ISO-8859-7
+          "ISO-8859-8" => 17, # ISO-8859-8
+          "ISO-8859-9" => 18, # ISO-8859-9
+          "ISO-2022-JP" => 19, # ISO-2022-JP
+          "SHIFT-JIS" => 20, # Shift_JIS
+          "EUC-JP" => 21, # EUC-JP
+          "ASCII" => 22, # pure ASCII
         }
 
         # The Nokogiri::XML::SAX::Document where events will be sent.
@@ -68,7 +69,7 @@ module Nokogiri
         attr_accessor :encoding
 
         # Create a new Parser with +doc+ and +encoding+
-        def initialize doc = Nokogiri::XML::SAX::Document.new, encoding = 'UTF-8'
+        def initialize(doc = Nokogiri::XML::SAX::Document.new, encoding = "UTF-8")
           @encoding = check_encoding(encoding)
           @document = doc
           @warned   = false
@@ -77,7 +78,7 @@ module Nokogiri
         ###
         # Parse given +thing+ which may be a string containing xml, or an
         # IO object.
-        def parse thing, &block
+        def parse(thing, &block)
           if thing.respond_to?(:read) && thing.respond_to?(:close)
             parse_io(thing, &block)
           else
@@ -87,34 +88,35 @@ module Nokogiri
 
         ###
         # Parse given +io+
-        def parse_io io, encoding = 'ASCII'
+        def parse_io(io, encoding = "ASCII")
           @encoding = check_encoding(encoding)
           ctx = ParserContext.io(io, ENCODINGS[@encoding])
           yield ctx if block_given?
-          ctx.parse_with self
+          ctx.parse_with(self)
         end
 
         ###
         # Parse a file with +filename+
-        def parse_file filename
+        def parse_file(filename)
           raise ArgumentError unless filename
           raise Errno::ENOENT unless File.exist?(filename)
           raise Errno::EISDIR if File.directory?(filename)
-          ctx = ParserContext.file filename
+          ctx = ParserContext.file(filename)
           yield ctx if block_given?
-          ctx.parse_with self
+          ctx.parse_with(self)
         end
 
-        def parse_memory data
-          ctx = ParserContext.memory data
+        def parse_memory(data)
+          ctx = ParserContext.memory(data)
           yield ctx if block_given?
-          ctx.parse_with self
+          ctx.parse_with(self)
         end
 
         private
+
         def check_encoding(encoding)
           encoding.upcase.tap do |enc|
-            raise ArgumentError.new("'#{enc}' is not a valid encoding") unless ENCODINGS[enc]
+            raise ArgumentError, "'#{enc}' is not a valid encoding" unless ENCODINGS[enc]
           end
         end
       end

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

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 module Nokogiri
   module XML
     module SAX
@@ -7,9 +8,12 @@ module Nokogiri
       # by the user.  Instead, you should be looking at
       # Nokogiri::XML::SAX::Parser
       class ParserContext
-        def self.new thing, encoding = 'UTF-8'
-          [:read, :close].all? { |x| thing.respond_to?(x) } ?
-            io(thing, Parser::ENCODINGS[encoding]) : memory(thing)
+        def self.new(thing, encoding = "UTF-8")
+          if [:read, :close].all? { |x| thing.respond_to?(x) }
+            io(thing, Parser::ENCODINGS[encoding])
+          else
+            memory(thing)
+          end
         end
       end
     end

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

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 module Nokogiri
   module XML
     module SAX
@@ -24,7 +25,6 @@ module Nokogiri
       #   parser << "/div>"
       #   parser.finish
       class PushParser
-
         # The Nokogiri::XML::SAX::Document on which the PushParser will be
         # operating
         attr_accessor :document
@@ -32,7 +32,7 @@ module Nokogiri
         ###
         # Create a new PushParser with +doc+ as the SAX Document, providing
         # an optional +file_name+ and +encoding+
-        def initialize(doc = XML::SAX::Document.new, file_name = nil, encoding = 'UTF-8')
+        def initialize(doc = XML::SAX::Document.new, file_name = nil, encoding = "UTF-8")
           @document = doc
           @encoding = encoding
           @sax_parser = XML::SAX::Parser.new(doc)
@@ -44,16 +44,16 @@ module Nokogiri
         ###
         # Write a +chunk+ of XML to the PushParser.  Any callback methods
         # that can be called will be called immediately.
-        def write chunk, last_chunk = false
+        def write(chunk, last_chunk = false)
           native_write(chunk, last_chunk)
         end
-        alias :<< :write
+        alias_method :<<, :write
 
         ###
         # Finish the parsing.  This method is only necessary for
         # Nokogiri::XML::SAX::Document#end_document to be called.
         def finish
-          write '', true
+          write("", true)
         end
       end
     end

data/lib/nokogiri/xml/sax.rb

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 require_relative "sax/document"
 require_relative "sax/parser_context"
 require_relative "sax/parser"

data/lib/nokogiri/xml/schema.rb

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 module Nokogiri
   module XML
     class << self
@@ -42,7 +43,7 @@ module Nokogiri
       ###
       # Create a new Nokogiri::XML::Schema object using a +string_or_io+
       # object.
-      def self.new string_or_io, options = ParseOptions::DEFAULT_SCHEMA
+      def self.new(string_or_io, options = ParseOptions::DEFAULT_SCHEMA)
         from_document(Nokogiri::XML(string_or_io), options)
       end
 
@@ -51,9 +52,9 @@ module Nokogiri
       # Nokogiri::XML::Document object, or a filename.  An Array of
       # Nokogiri::XML::SyntaxError objects found while validating the
       # +thing+ is returned.
-      def validate thing
-        if thing.is_a?(Nokogiri::XML::Document) 
-          validate_document(thing) 
+      def validate(thing)
+        if thing.is_a?(Nokogiri::XML::Document)
+          validate_document(thing)
         elsif File.file?(thing)
           validate_file(thing)
         else
@@ -64,8 +65,8 @@ module Nokogiri
       ###
       # Returns true if +thing+ is a valid Nokogiri::XML::Document or
       # file.
-      def valid? thing
-        validate(thing).length == 0
+      def valid?(thing)
+        validate(thing).empty?
       end
     end
   end

data/lib/nokogiri/xml/searchable.rb

@@ -1,22 +1,25 @@
+# coding: utf-8
 # frozen_string_literal: true
+
 module Nokogiri
   module XML
     #
     #  The Searchable module declares the interface used for searching your DOM.
     #
-    #  It implements the public methods `search`, `css`, and `xpath`,
+    #  It implements the public methods #search, #css, and #xpath,
     #  as well as allowing specific implementations to specialize some
     #  of the important behaviors.
     #
     module Searchable
       # Regular expression used by Searchable#search to determine if a query
       # string is CSS or XPath
-      LOOKS_LIKE_XPATH = /^(\.\/|\/|\.\.|\.$)/
+      LOOKS_LIKE_XPATH = %r{^(\./|/|\.\.|\.$)}
 
-      # @!group Searching via XPath or CSS Queries
+      # :section: Searching via XPath or CSS Queries
 
       ###
-      # call-seq: search *paths, [namespace-bindings, xpath-variable-bindings, custom-handler-class]
+      # call-seq:
+      #   search(*paths, [namespace-bindings, xpath-variable-bindings, custom-handler-class])
       #
       # Search this object for +paths+. +paths+ must be one or more XPath or CSS queries:
       #
@@ -27,41 +30,39 @@ module Nokogiri
       #   node.search('.//bike:tire', {'bike' => 'http://schwinn.com/'})
       #   node.search('bike|tire', {'bike' => 'http://schwinn.com/'})
       #
-      # For XPath queries, a hash of variable bindings may also be
-      # appended to the namespace bindings. For example:
+      # For XPath queries, a hash of variable bindings may also be appended to the namespace
+      # bindings. For example:
       #
       #   node.search('.//address[@domestic=$value]', nil, {:value => 'Yes'})
       #
-      # Custom XPath functions and CSS pseudo-selectors may also be
-      # defined. To define custom functions create a class and
-      # implement the function you want to define.  The first argument
-      # to the method will be the current matching NodeSet.  Any other
-      # arguments are ones that you pass in.  Note that this class may
-      # appear anywhere in the argument list.  For example:
-      #
-      #   node.search('.//title[regex(., "\w+")]', 'div.employee:regex("[0-9]+")'
-      #     Class.new {
-      #       def regex node_set, regex
-      #         node_set.find_all { |node| node['some_attribute'] =~ /#{regex}/ }
-      #       end
-      #     }.new
-      #   )
+      # 💡 Custom XPath functions and CSS pseudo-selectors may also be defined. To define custom
+      # functions create a class and implement the function you want to define. The first argument
+      # to the method will be the current matching NodeSet. Any other arguments are ones that you
+      # pass in. Note that this class may appear anywhere in the argument list. For example:
+      #
+      #   handler = Class.new {
+      #     def regex node_set, regex
+      #       node_set.find_all { |node| node['some_attribute'] =~ /#{regex}/ }
+      #     end
+      #   }.new
+      #   node.search('.//title[regex(., "\w+")]', 'div.employee:regex("[0-9]+")', handler)
       #
       # See Searchable#xpath and Searchable#css for further usage help.
       def search(*args)
         paths, handler, ns, binds = extract_params(args)
 
         xpaths = paths.map(&:to_s).map do |path|
-          (path =~ LOOKS_LIKE_XPATH) ? path : xpath_query_from_css_rule(path, ns)
+          LOOKS_LIKE_XPATH.match?(path) ? path : xpath_query_from_css_rule(path, ns)
         end.flatten.uniq
 
         xpath(*(xpaths + [ns, handler, binds].compact))
       end
 
-      alias :/ :search
+      alias_method :/, :search
 
       ###
-      # call-seq: search *paths, [namespace-bindings, xpath-variable-bindings, custom-handler-class]
+      # call-seq:
+      #   at(*paths, [namespace-bindings, xpath-variable-bindings, custom-handler-class])
       #
       # Search this object for +paths+, and return only the first
       # result. +paths+ must be one or more XPath or CSS queries.
@@ -71,10 +72,11 @@ module Nokogiri
         search(*args).first
       end
 
-      alias :% :at
+      alias_method :%, :at
 
       ###
-      # call-seq: css *rules, [namespace-bindings, custom-pseudo-class]
+      # call-seq:
+      #   css(*rules, [namespace-bindings, custom-pseudo-class])
       #
       # Search this object for CSS +rules+. +rules+ must be one or more CSS
       # selectors. For example:
@@ -87,33 +89,49 @@ module Nokogiri
       #
       #   node.css('bike|tire', {'bike' => 'http://schwinn.com/'})
       #
-      # Custom CSS pseudo classes may also be defined.  To define
-      # custom pseudo classes, create a class and implement the custom
-      # pseudo class you want defined.  The first argument to the
-      # method will be the current matching NodeSet.  Any other
-      # arguments are ones that you pass in.  For example:
+      # 💡 Custom CSS pseudo classes may also be defined which are mapped to a custom XPath
+      # function.  To define custom pseudo classes, create a class and implement the custom pseudo
+      # class you want defined. The first argument to the method will be the matching context
+      # NodeSet. Any other arguments are ones that you pass in. For example:
       #
-      #   node.css('title:regex("\w+")', Class.new {
-      #     def regex node_set, regex
+      #   handler = Class.new {
+      #     def regex(node_set, regex)
       #       node_set.find_all { |node| node['some_attribute'] =~ /#{regex}/ }
       #     end
-      #   }.new)
+      #   }.new
+      #   node.css('title:regex("\w+")', handler)
+      #
+      # 💡 Some XPath syntax is supported in CSS queries. For example, to query for an attribute:
+      #
+      #   node.css('img > @href') # returns all +href+ attributes on an +img+ element
+      #   node.css('img / @href') # same
+      #
+      #   # ⚠ this returns +class+ attributes from all +div+ elements AND THEIR CHILDREN!
+      #   node.css('div @class')
       #
-      # Note that the CSS query string is case-sensitive with regards
-      # to your document type. That is, if you're looking for "H1" in
-      # an HTML document, you'll never find anything, since HTML tags
-      # will match only lowercase CSS queries. However, "H1" might be
-      # found in an XML document, where tags names are case-sensitive
-      # (e.g., "H1" is distinct from "h1").
+      #   node.css
       #
+      # 💡 Array-like syntax is supported in CSS queries as an alternative to using +:nth-child()+.
+      #
+      # ⚠ NOTE that indices are 1-based like +:nth-child+ and not 0-based like Ruby Arrays. For
+      # example:
+      #
+      #   # equivalent to 'li:nth-child(2)'
+      #   node.css('li[2]') # retrieve the second li element in a list
+      #
+      # ⚠ NOTE that the CSS query string is case-sensitive with regards to your document type. HTML
+      # tags will match only lowercase CSS queries, so if you search for "H1" in an HTML document,
+      # you'll never find anything. However, "H1" might be found in an XML document, where tags
+      # names are case-sensitive (e.g., "H1" is distinct from "h1").
       def css(*args)
         rules, handler, ns, _ = extract_params(args)
 
-        css_internal self, rules, handler, ns
+        css_internal(self, rules, handler, ns)
       end
 
       ##
-      # call-seq: css *rules, [namespace-bindings, custom-pseudo-class]
+      # call-seq:
+      #   at_css(*rules, [namespace-bindings, custom-pseudo-class])
       #
       # Search this object for CSS +rules+, and return only the first
       # match. +rules+ must be one or more CSS selectors.
@@ -124,7 +142,8 @@ module Nokogiri
       end
 
       ###
-      # call-seq: xpath *paths, [namespace-bindings, variable-bindings, custom-handler-class]
+      # call-seq:
+      #   xpath(*paths, [namespace-bindings, variable-bindings, custom-handler-class])
       #
       # Search this node for XPath +paths+. +paths+ must be one or more XPath
       # queries.
@@ -140,27 +159,27 @@ module Nokogiri
       #
       #   node.xpath('.//address[@domestic=$value]', nil, {:value => 'Yes'})
       #
-      # Custom XPath functions may also be defined.  To define custom
-      # functions create a class and implement the function you want
-      # to define.  The first argument to the method will be the
-      # current matching NodeSet.  Any other arguments are ones that
-      # you pass in.  Note that this class may appear anywhere in the
-      # argument list.  For example:
+      # 💡 Custom XPath functions may also be defined. To define custom functions create a class and
+      # implement the function you want to define. The first argument to the method will be the
+      # current matching NodeSet. Any other arguments are ones that you pass in. Note that this
+      # class may appear anywhere in the argument list. For example:
       #
-      #   node.xpath('.//title[regex(., "\w+")]', Class.new {
-      #     def regex node_set, regex
+      #   handler = Class.new {
+      #     def regex(node_set, regex)
       #       node_set.find_all { |node| node['some_attribute'] =~ /#{regex}/ }
       #     end
-      #   }.new)
+      #   }.new
+      #   node.xpath('.//title[regex(., "\w+")]', handler)
       #
       def xpath(*args)
         paths, handler, ns, binds = extract_params(args)
 
-        xpath_internal self, paths, handler, ns, binds
+        xpath_internal(self, paths, handler, ns, binds)
       end
 
       ##
-      # call-seq: xpath *paths, [namespace-bindings, variable-bindings, custom-handler-class]
+      # call-seq:
+      #   at_xpath(*paths, [namespace-bindings, variable-bindings, custom-handler-class])
       #
       # Search this node for XPath +paths+, and return only the first
       # match. +paths+ must be one or more XPath queries.
@@ -170,12 +189,21 @@ module Nokogiri
         xpath(*args).first
       end
 
-      # @!endgroup
+      # :call-seq:
+      #   >(selector) → NodeSet
+      #
+      # Search this node's immediate children using CSS selector +selector+
+      def >(selector) # rubocop:disable Naming/BinaryOperatorParameterName
+        ns = (document.root&.namespaces || {})
+        xpath(CSS.xpath_for(selector, prefix: "./", ns: ns).first)
+      end
+
+      # :section:
 
       private
 
       def css_internal(node, rules, handler, ns)
-        xpath_internal node, css_rules_to_xpath(rules, ns), handler, ns, nil
+        xpath_internal(node, css_rules_to_xpath(rules, ns), handler, ns, nil)
       end
 
       def xpath_internal(node, paths, handler, ns, binds)
@@ -198,9 +226,9 @@ module Nokogiri
         ctx.register_namespaces(ns)
         path = path.gsub(/xmlns:/, " :") unless Nokogiri.uses_libxml?
 
-        binds.each do |key, value|
-          ctx.register_variable key.to_s, value
-        end if binds
+        binds&.each do |key, value|
+          ctx.register_variable(key.to_s, value)
+        end
 
         ctx.evaluate(path, handler)
       end
@@ -210,10 +238,13 @@ module Nokogiri
       end
 
       def xpath_query_from_css_rule(rule, ns)
-        visitor = Nokogiri::CSS::XPathVisitorOptimallyUseBuiltins.new
+        visitor = Nokogiri::CSS::XPathVisitor.new(
+          builtins: Nokogiri::CSS::XPathVisitor::BuiltinsConfig::OPTIMAL,
+          doctype: document.xpath_doctype,
+        )
         self.class::IMPLIED_XPATH_CONTEXTS.map do |implied_xpath_context|
-          CSS.xpath_for(rule.to_s, {:prefix => implied_xpath_context, :ns => ns,
-                                    :visitor => visitor})
+          CSS.xpath_for(rule.to_s, { prefix: implied_xpath_context, ns: ns,
+                                     visitor: visitor, })
         end.join(" | ")
       end
 
@@ -230,7 +261,7 @@ module Nokogiri
         end
         ns, binds = hashes.reverse
 
-        ns ||= document.root ? document.root.namespaces : {}
+        ns ||= (document.root&.namespaces || {})
 
         [params, handler, ns, binds]
       end

data/lib/nokogiri/xml/syntax_error.rb

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 module Nokogiri
   module XML
     ###
@@ -42,9 +43,9 @@ module Nokogiri
 
       def to_s
         message = super.chomp
-        [location_to_s, level_to_s, message].
-          compact.join(": ").
-          force_encoding(message.encoding)
+        [location_to_s, level_to_s, message]
+          .compact.join(": ")
+          .force_encoding(message.encoding)
       end
 
       private
@@ -54,7 +55,6 @@ module Nokogiri
         when 3 then "FATAL"
         when 2 then "ERROR"
         when 1 then "WARNING"
-        else nil
         end
       end
 

data/lib/nokogiri/xml/text.rb

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 module Nokogiri
   module XML
     class Text < Nokogiri::XML::CharacterData

data/lib/nokogiri/xml/xpath/syntax_error.rb

@@ -1,10 +1,11 @@
 # frozen_string_literal: true
+
 module Nokogiri
   module XML
     module XPath
       class SyntaxError < XML::SyntaxError
         def to_s
-          [super.chomp, str1].compact.join(': ')
+          [super.chomp, str1].compact.join(": ")
         end
       end
     end

data/lib/nokogiri/xml/xpath.rb

@@ -1,7 +1,19 @@
 # frozen_string_literal: true
+
 module Nokogiri
   module XML
     module XPath
+      # The XPath search prefix to search globally, +//+
+      GLOBAL_SEARCH_PREFIX = "//"
+
+      # The XPath search prefix to search direct descendants of the root element, +/+
+      ROOT_SEARCH_PREFIX = "/"
+
+      # The XPath search prefix to search direct descendants of the current element, +./+
+      CURRENT_SEARCH_PREFIX = "./"
+
+      # The XPath search prefix to search anywhere in the current element's subtree, +.//+
+      SUBTREE_SEARCH_PREFIX = ".//"
     end
   end
 end

data/lib/nokogiri/xml/xpath_context.rb

@@ -1,17 +1,16 @@
 # frozen_string_literal: true
+
 module Nokogiri
   module XML
     class XPathContext
-
       ###
       # Register namespaces in +namespaces+
       def register_namespaces(namespaces)
         namespaces.each do |k, v|
-          k = k.to_s.gsub(/.*:/,'') # strip off 'xmlns:' or 'xml:'
+          k = k.to_s.gsub(/.*:/, "") # strip off 'xmlns:' or 'xml:'
           register_ns(k, v)
         end
       end
-
     end
   end
 end

data/lib/nokogiri/xml.rb

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 module Nokogiri
   class << self
     ###
@@ -21,7 +22,6 @@ module Nokogiri
       # Nokogiri::XML::Reader for mor information
       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)
@@ -38,8 +38,8 @@ module Nokogiri
 
       ####
       # Parse a fragment from +string+ in to a NodeSet.
-      def fragment(string)
-        XML::DocumentFragment.parse(string)
+      def fragment(string, options = ParseOptions::DEFAULT_XML, &block)
+        XML::DocumentFragment.parse(string, options, &block)
       end
     end
   end

data/lib/nokogiri/xslt/stylesheet.rb

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
+
 module Nokogiri
   module XSLT
     ###