nokogiri 1.15.5 → 1.16.5

data/lib/nokogiri/css/parser_extras.rb

@@ -23,7 +23,7 @@ module Nokogiri
 
         # Get the css selector in +string+ from the cache
         def [](string)
-          return nil unless cache_on?
+          return unless cache_on?
 
           @mutex.synchronize { @cache[string] }
         end

data/lib/nokogiri/css/xpath_visitor.rb

@@ -302,7 +302,7 @@ module Nokogiri
       end
 
       def read_a_and_positive_b(values)
-        op = values[2]
+        op = values[2].strip
         if op == "+"
           a = values[0].to_i
           b = values[3].to_i
@@ -335,25 +335,5 @@ module Nokogiri
         end
       end
     end
-
-    module XPathVisitorAlwaysUseBuiltins # :nodoc:
-      def self.new
-        warn(
-          "Nokogiri::CSS::XPathVisitorAlwaysUseBuiltins is deprecated and will be removed in a future version of Nokogiri",
-          { uplevel: 1 },
-        )
-        XPathVisitor.new(builtins: :always)
-      end
-    end
-
-    module XPathVisitorOptimallyUseBuiltins # :nodoc:
-      def self.new
-        warn(
-          "Nokogiri::CSS::XPathVisitorOptimallyUseBuiltins is deprecated and will be removed in a future version of Nokogiri",
-          { uplevel: 1 },
-        )
-        XPathVisitor.new(builtins: :optimal)
-      end
-    end
   end
 end

data/lib/nokogiri/html4/document.rb

@@ -92,7 +92,7 @@ module Nokogiri
         title = XML::Node.new("title", self) << tnode
         if (head = at_xpath("//head"))
           head << title
-        elsif (meta = (at_xpath("//meta[@charset]") || meta_content_type))
+        elsif (meta = at_xpath("//meta[@charset]") || meta_content_type)
           # better put after charset declaration
           meta.add_next_sibling(title)
         else

data/lib/nokogiri/html4/encoding_reader.rb

@@ -94,7 +94,7 @@ module Nokogiri
         # no support for a call without len
 
         unless @firstchunk
-          (@firstchunk = @io.read(len)) || (return nil)
+          (@firstchunk = @io.read(len)) || return
 
           # This implementation expects that the first call from
           # htmlReadIO() is made with a length long enough (~1KB) to

data/lib/nokogiri/html5.rb

@@ -239,23 +239,6 @@ module Nokogiri
         DocumentFragment.parse(string, encoding, options)
       end
 
-      # Fetch and parse a HTML document from the web, following redirects,
-      # handling https, and determining the character encoding using HTML5
-      # rules.  +uri+ may be a +String+ or a +URI+.  +options+ contains
-      # http headers and special options.  Everything which is not a
-      # special option is considered a header.  Special options include:
-      #  * :follow_limit => number of redirects which are followed
-      #  * :basic_auth => [username, password]
-      def get(uri, options = {})
-        # TODO: deprecate
-        warn(
-          "Nokogiri::HTML5.get is deprecated and will be removed in a future version of Nokogiri.",
-          uplevel: 1,
-          category: :deprecated,
-        )
-        get_impl(uri, options)
-      end
-
       # :nodoc:
       def read_and_encode(string, encoding)
         # Read the string with the given encoding.
@@ -283,55 +266,6 @@ module Nokogiri
 
       private
 
-      def get_impl(uri, options = {})
-        headers = options.clone
-        headers = { follow_limit: headers } if Numeric === headers # deprecated
-        limit = headers[:follow_limit] ? headers.delete(:follow_limit).to_i : 10
-
-        require "net/http"
-        uri = URI(uri) unless URI === uri
-
-        http = Net::HTTP.new(uri.host, uri.port)
-
-        # TLS / SSL support
-        http.use_ssl = true if uri.scheme == "https"
-
-        # Pass through Net::HTTP override values, which currently include:
-        #   :ca_file, :ca_path, :cert, :cert_store, :ciphers,
-        #   :close_on_empty_response, :continue_timeout, :key, :open_timeout,
-        #   :read_timeout, :ssl_timeout, :ssl_version, :use_ssl,
-        #   :verify_callback, :verify_depth, :verify_mode
-        options.each do |key, _value|
-          http.send("#{key}=", headers.delete(key)) if http.respond_to?("#{key}=")
-        end
-
-        request = Net::HTTP::Get.new(uri.request_uri)
-
-        # basic authentication
-        auth = headers.delete(:basic_auth)
-        auth ||= [uri.user, uri.password] if uri.user && uri.password
-        request.basic_auth(auth.first, auth.last) if auth
-
-        # remaining options are treated as headers
-        headers.each { |key, value| request[key.to_s] = value.to_s }
-
-        response = http.request(request)
-
-        case response
-        when Net::HTTPSuccess
-          doc = parse(reencode(response.body, response["content-type"]), options)
-          doc.instance_variable_set(:@response, response)
-          doc.class.send(:attr_reader, :response)
-          doc
-        when Net::HTTPRedirection
-          response.value if limit <= 1
-          location = URI.join(uri, response["location"])
-          get_impl(location, options.merge(follow_limit: limit - 1))
-        else
-          response.value
-        end
-      end
-
       # Charset sniffing is a complex and controversial topic that understandably isn't done _by
       # default_ by the Ruby Net::HTTP library.  This being said, it is a very real problem for
       # consumers of HTML as the default for HTML is iso-8859-1, most "good" producers use utf-8, and

data/lib/nokogiri/version/constant.rb

@@ -2,5 +2,5 @@
 
 module Nokogiri
   # The version of Nokogiri you are using
-  VERSION = "1.15.5"
+  VERSION = "1.16.5"
 end

data/lib/nokogiri/version/info.rb

@@ -94,11 +94,14 @@ module Nokogiri
           nokogiri["version"] = Nokogiri::VERSION
 
           unless jruby?
-            #  enable gems like nokogumbo to build with the following in their extconf.rb:
+            #  enable gems to build against Nokogiri with the following in their extconf.rb:
             #
             #    append_cflags(Nokogiri::VERSION_INFO["nokogiri"]["cppflags"])
             #    append_ldflags(Nokogiri::VERSION_INFO["nokogiri"]["ldflags"])
             #
+            #  though, this won't work on all platform and versions of Ruby, and won't be supported
+            #  forever, see https://github.com/sparklemotion/nokogiri/discussions/2746 for context.
+            #
             cppflags = ["-I#{header_directory.shellescape}"]
             ldflags = []
 
@@ -108,7 +111,8 @@ module Nokogiri
             end
 
             if windows?
-              # on windows, nokogumbo needs to link against nokogiri.so to resolve symbols. see #2167
+              # on windows, third party libraries that wish to link against nokogiri
+              # should link against nokogiri.so to resolve symbols. see #2167
               lib_directory = File.expand_path(File.join(File.dirname(__FILE__), "../#{ruby_minor}"))
               unless File.exist?(lib_directory)
                 lib_directory = File.expand_path(File.join(File.dirname(__FILE__), ".."))
@@ -136,9 +140,6 @@ module Nokogiri
               libxml["source"] = "packaged"
               libxml["precompiled"] = libxml2_precompiled?
               libxml["patches"] = Nokogiri::LIBXML2_PATCHES
-
-              # this is for nokogumbo and shouldn't be forever
-              libxml["libxml2_path"] = header_directory
             else
               libxml["source"] = "system"
             end

data/lib/nokogiri/xml/attr.rb

@@ -18,8 +18,6 @@ module Nokogiri
       #  - +value+ → (String) The value of the attribute.
       #  - +namespace+ → (Namespace, nil) The Namespace of the attribute, or +nil+ if there is no namespace.
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
-      #
       #  *Example*
       #
       #    doc = Nokogiri::XML.parse(<<~XML)
@@ -52,6 +50,8 @@ module Nokogiri
       #    #        href = "http://nokogiri.org/ns/noko"
       #    #        })}
       #
+      #  Since v1.14.0
+      #
       def deconstruct_keys(keys)
         { name: name, value: value, namespace: namespace }
       end

data/lib/nokogiri/xml/document.rb

@@ -329,7 +329,7 @@ module Nokogiri
       # Validate this Document against it's DTD.  Returns a list of errors on
       # the document or +nil+ when there is no DTD.
       def validate
-        return nil unless internal_subset
+        return unless internal_subset
 
         internal_subset.validate(self)
       end
@@ -426,8 +426,6 @@ module Nokogiri
       #  instructions. If you have a use case and would like this functionality, please let us know
       #  by opening an issue or a discussion on the github project.
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
-      #
       #  *Example*
       #
       #    doc = Nokogiri::XML.parse(<<~XML)
@@ -454,6 +452,8 @@ module Nokogiri
       #    doc.deconstruct_keys([:root])
       #    # => {:root=>nil}
       #
+      #  Since v1.14.0
+      #
       def deconstruct_keys(keys)
         { root: root }
       end

data/lib/nokogiri/xml/document_fragment.rb

@@ -154,8 +154,6 @@ module Nokogiri
       #  root elements, you should deconstruct the array returned by
       #  <tt>DocumentFragment#elements</tt>.
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
-      #
       #  *Example*
       #
       #    frag = Nokogiri::HTML5.fragment(<<~HTML)
@@ -187,6 +185,8 @@ module Nokogiri
       #    #       }),
       #    #     #(Element:0x398 { name = "div", children = [ #(Text "End")] })]
       #
+      #  Since v1.14.0
+      #
       def deconstruct
         children.to_a
       end

data/lib/nokogiri/xml/namespace.rb

@@ -16,8 +16,6 @@ module Nokogiri
       #  - +prefix+ → (String, nil) The namespace's prefix, or +nil+ if there is no prefix (e.g., default namespace).
       #  - +href+ → (String) The namespace's URI
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
-      #
       #  *Example*
       #
       #    doc = Nokogiri::XML.parse(<<~XML)
@@ -43,6 +41,7 @@ module Nokogiri
       #    doc.root.elements.last.namespace.deconstruct_keys([:prefix, :href])
       #    # => {:prefix=>"noko", :href=>"http://nokogiri.org/ns/noko"}
       #
+      #  Since v1.14.0
       #
       def deconstruct_keys(keys)
         { prefix: prefix, href: href }

data/lib/nokogiri/xml/node.rb

@@ -1049,29 +1049,35 @@ module Nokogiri
 
         return Nokogiri::XML::NodeSet.new(document) if contents.empty?
 
-        # libxml2 does not obey the +recover+ option after encountering errors during +in_context+
-        # parsing, and so this horrible hack is here to try to emulate recovery behavior.
-        #
-        # Unfortunately, this means we're no longer parsing "in context" and so namespaces that
-        # would have been inherited from the context node won't be handled correctly. This hack was
-        # written in 2010, and I regret it, because it's silently degrading functionality in a way
-        # that's not easily prevented (or even detected).
-        #
-        # I think preferable behavior would be to either:
-        #
-        # a. add an error noting that we "fell back" and pointing the user to turning off the +recover+ option
-        # b. don't recover, but raise a sensible exception
-        #
-        # For context and background: https://github.com/sparklemotion/nokogiri/issues/313
-        # FIXME bug report: https://github.com/sparklemotion/nokogiri/issues/2092
         error_count = document.errors.length
         node_set = in_context(contents, options.to_i)
-        if node_set.empty? && (document.errors.length > error_count)
-          if options.recover?
+        if document.errors.length > error_count
+          raise document.errors[error_count] unless options.recover?
+
+          if node_set.empty?
+            # libxml2 < 2.13 does not obey the +recover+ option after encountering errors during
+            # +in_context+ parsing, and so this horrible hack is here to try to emulate recovery
+            # behavior.
+            #
+            # (Note that HTML4 fragment parsing seems to have been fixed in abd74186, and XML
+            # fragment parsing is fixed in 1c106edf. Both are in 2.13.)
+            #
+            # Unfortunately, this means we're no longer parsing "in context" and so namespaces that
+            # would have been inherited from the context node won't be handled correctly. This hack
+            # was written in 2010, and I regret it, because it's silently degrading functionality in
+            # a way that's not easily prevented (or even detected).
+            #
+            # I think preferable behavior would be to either:
+            #
+            # a. add an error noting that we "fell back" and pointing the user to turning off the
+            #    +recover+ option
+            # b. don't recover, but raise a sensible exception
+            #
+            # For context and background:
+            # - https://github.com/sparklemotion/nokogiri/issues/313
+            # - https://github.com/sparklemotion/nokogiri/issues/2092
             fragment = document.related_class("DocumentFragment").parse(contents)
             node_set = fragment.children
-          else
-            raise document.errors[error_count]
           end
         end
         node_set
@@ -1165,7 +1171,7 @@ module Nokogiri
       # Fetch the Nokogiri::HTML4::ElementDescription for this node.  Returns
       # nil on XML documents and on unknown tags.
       def description
-        return nil if document.xml?
+        return if document.xml?
 
         Nokogiri::HTML4::ElementDescription[name]
       end
@@ -1254,8 +1260,8 @@ module Nokogiri
       # Compare two Node objects with respect to their Document.  Nodes from
       # different documents cannot be compared.
       def <=>(other)
-        return nil unless other.is_a?(Nokogiri::XML::Node)
-        return nil unless document == other.document
+        return unless other.is_a?(Nokogiri::XML::Node)
+        return unless document == other.document
 
         compare(other)
       end
@@ -1278,6 +1284,7 @@ module Nokogiri
       #   end
       #
       def serialize(*args, &block)
+        # TODO: deprecate non-hash options, see 46c68ed 2009-06-20 for context
         options = if args.first.is_a?(Hash)
           args.shift
         else
@@ -1429,8 +1436,6 @@ module Nokogiri
       #  - +content+ → (String) The contents of all the text nodes in this node's subtree. See #content.
       #  - +inner_html+ → (String) The inner markup for the children of this node. See #inner_html.
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
-      #
       #  *Example*
       #
       #    doc = Nokogiri::XML.parse(<<~XML)
@@ -1465,6 +1470,8 @@ module Nokogiri
       #    #         value = "def"
       #    #         })]}
       #
+      #  Since v1.14.0
+      #
       def deconstruct_keys(keys)
         requested_keys = DECONSTRUCT_KEYS & keys
         {}.tap do |values|

data/lib/nokogiri/xml/node_set.rb

@@ -372,7 +372,7 @@ module Nokogiri
       # Removes the last element from set and returns it, or +nil+ if
       # the set is empty
       def pop
-        return nil if length == 0
+        return if length == 0
 
         delete(last)
       end
@@ -381,7 +381,7 @@ module Nokogiri
       # Returns the first element of the NodeSet and removes it.  Returns
       # +nil+ if the set is empty.
       def shift
-        return nil if length == 0
+        return if length == 0
 
         delete(first)
       end
@@ -435,7 +435,7 @@ module Nokogiri
       #
       #  Returns the members of this NodeSet as an array, to use in pattern matching.
       #
-      #  ⚡ This is an experimental feature, available since v1.14.0
+      #  Since v1.14.0
       #
       def deconstruct
         to_a

data/lib/nokogiri/xml/reader.rb

@@ -3,9 +3,11 @@
 module Nokogiri
   module XML
     ###
-    # Nokogiri::XML::Reader parses an XML document similar to the way a cursor
-    # would move.  The Reader is given an XML document, and yields nodes
-    # to an each block.
+    # Nokogiri::XML::Reader parses an XML document similar to the way a cursor would move. The
+    # Reader is given an XML document, and yields nodes to an each block.
+    #
+    # The Reader parser might be good for when you need the speed and low memory usage of the SAX
+    # parser, but do not want to write a Document handler.
     #
     # Here is an example of usage:
     #
@@ -22,13 +24,12 @@ module Nokogiri
     #
     #     end
     #
-    # Note that Nokogiri::XML::Reader#each can only be called once!!  Once
-    # the cursor moves through the entire document, you must parse the
-    # document again.  So make sure that you capture any information you
-    # need during the first iteration.
+    # ⚠ Nokogiri::XML::Reader#each can only be called once! Once the cursor moves through the entire
+    # document, you must parse the document again. It may be better to capture all information you
+    # need during a single iteration.
     #
-    # The Reader parser is good for when you need the speed of a SAX parser,
-    # but do not want to write a Document handler.
+    # ⚠ libxml2 does not support error recovery in the Reader parser. The `RECOVER` ParseOption is
+    # ignored. If a syntax error is encountered during parsing, an exception will be raised.
     class Reader
       include Enumerable
 

data/lib/nokogiri/xml/searchable.rb

@@ -199,7 +199,7 @@ module Nokogiri
       #
       # Search this node's immediate children using CSS selector +selector+
       def >(selector) # rubocop:disable Naming/BinaryOperatorParameterName
-        ns = (document.root&.namespaces || {})
+        ns = document.root&.namespaces || {}
         xpath(CSS.xpath_for(selector, prefix: "./", ns: ns).first)
       end
 
@@ -229,7 +229,7 @@ module Nokogiri
       def xpath_impl(node, path, handler, ns, binds)
         ctx = XPathContext.new(node)
         ctx.register_namespaces(ns)
-        path = path.gsub(/xmlns:/, " :") unless Nokogiri.uses_libxml?
+        path = path.gsub("xmlns:", " :") unless Nokogiri.uses_libxml?
 
         binds&.each do |key, value|
           ctx.register_variable(key.to_s, value)
@@ -269,7 +269,7 @@ module Nokogiri
         end
         ns, binds = hashes.reverse
 
-        ns ||= (document.root&.namespaces || {})
+        ns ||= document.root&.namespaces || {}
 
         [params, handler, ns, binds]
       end

data/lib/nokogiri/xml/syntax_error.rb

@@ -63,7 +63,7 @@ module Nokogiri
       end
 
       def location_to_s
-        return nil if nil_or_zero?(line) && nil_or_zero?(column)
+        return if nil_or_zero?(line) && nil_or_zero?(column)
 
         "#{line}:#{column}"
       end

data/lib/nokogiri/xml.rb

@@ -11,7 +11,7 @@ module Nokogiri
 
   module XML
     # Original C14N 1.0 spec canonicalization
-    XML_C14N_1_0 =       0
+    XML_C14N_1_0 = 0
     # Exclusive C14N 1.0 spec canonicalization
     XML_C14N_EXCLUSIVE_1_0 = 1
     # C14N 1.1 spec canonicalization

data/lib/nokogiri/xslt/stylesheet.rb

@@ -10,15 +10,37 @@ module Nokogiri
     #   doc   = Nokogiri::XML(File.read('some_file.xml'))
     #   xslt  = Nokogiri::XSLT(File.read('some_transformer.xslt'))
     #
-    #   puts xslt.transform(doc)
+    #   xslt.transform(doc) # => Nokogiri::XML::Document
     #
-    # See Nokogiri::XSLT::Stylesheet#transform for more transformation
-    # information.
+    # Many XSLT transformations include serialization behavior to emit a non-XML document. For these
+    # cases, please take care to invoke the #serialize method on the result of the transformation:
+    #
+    #   doc   = Nokogiri::XML(File.read('some_file.xml'))
+    #   xslt  = Nokogiri::XSLT(File.read('some_transformer.xslt'))
+    #   xslt.serialize(xslt.transform(doc)) # => String
+    #
+    # or use the #apply_to method, which is a shortcut for `serialize(transform(document))`:
+    #
+    #   doc   = Nokogiri::XML(File.read('some_file.xml'))
+    #   xslt  = Nokogiri::XSLT(File.read('some_transformer.xslt'))
+    #   xslt.apply_to(doc) # => String
+    #
+    # See Nokogiri::XSLT::Stylesheet#transform for more information and examples.
     class Stylesheet
-      ###
-      # Apply an XSLT stylesheet to an XML::Document.
-      # +params+ is an array of strings used as XSLT parameters.
-      # returns serialized document
+      # :call-seq:
+      #   apply_to(document, params = []) -> String
+      #
+      # Apply an XSLT stylesheet to an XML::Document and serialize it properly. This method is
+      # equivalent to calling #serialize on the result of #transform.
+      #
+      # [Parameters]
+      # - +document+ is an instance of XML::Document to transform
+      # - +params+ is an array of strings used as XSLT parameters, passed into #transform
+      #
+      # [Returns]
+      #   A string containing the serialized result of the transformation.
+      #
+      # See Nokogiri::XSLT::Stylesheet#transform for more information and examples.
       def apply_to(document, params = [])
         serialize(transform(document, params))
       end

data/lib/nokogiri/xslt.rb

@@ -101,7 +101,7 @@ module Nokogiri
         params.flatten.each_slice(2).with_object([]) do |kv, quoted_params|
           key, value = kv.map(&:to_s)
           value = if value.include?("'")
-            "concat('#{value.gsub(/'/, %q{', "'", '})}')"
+            "concat('#{value.gsub("'", %q{', "'", '})}')"
           else
             "'#{value}'"
           end

data/lib/nokogiri.rb

@@ -94,7 +94,7 @@ module Nokogiri
 
     # :nodoc:
     def install_default_aliases
-      warn("Nokogiri.install_default_aliases is deprecated and will be removed in a future version of Nokogiri. Please call Nokogiri::EncodingHandler.install_default_aliases instead.")
+      warn("Nokogiri.install_default_aliases is deprecated. Please call Nokogiri::EncodingHandler.install_default_aliases instead. This will become an error in Nokogiri v1.17.0.", uplevel: 1, category: :deprecated) # deprecated in v1.14.0, remove in v1.17.0
       Nokogiri::EncodingHandler.install_default_aliases
     end
   end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: nokogiri
 version: !ruby/object:Gem::Version
-  version: 1.15.5
+  version: 1.16.5
 platform: ruby
 authors:
 - Mike Dalessio
@@ -17,10 +17,10 @@ authors:
 - Sergio Arbeo
 - Timothy Elliott
 - Nobuyoshi Nakada
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-11-17 00:00:00.000000000 Z
+date: 2024-05-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mini_portile2
@@ -272,7 +272,7 @@ files:
 - patches/libxml2/0010-update-config.guess-and-config.sub-for-libxml2.patch
 - patches/libxml2/0011-rip-out-libxml2-s-libc_single_threaded-support.patch
 - patches/libxslt/0001-update-config.guess-and-config.sub-for-libxslt.patch
-- ports/archives/libxml2-2.11.6.tar.xz
+- ports/archives/libxml2-2.12.7.tar.xz
 - ports/archives/libxslt-1.1.39.tar.xz
 homepage: https://nokogiri.org
 licenses:
@@ -284,7 +284,7 @@ metadata:
   changelog_uri: https://nokogiri.org/CHANGELOG.html
   source_code_uri: https://github.com/sparklemotion/nokogiri
   rubygems_mfa_required: 'true'
-post_install_message: 
+post_install_message:
 rdoc_options:
 - "--main"
 - README.md
@@ -294,15 +294,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 2.7.0
+      version: 3.0.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.4.19
-signing_key: 
+rubygems_version: 3.5.10
+signing_key:
 specification_version: 4
 summary: Nokogiri (鋸) makes it easy and painless to work with XML and HTML from Ruby.
 test_files: []