RubyGems - nokogiri - Versions diffs - 1.12.5 → 1.14.3 - Mend

nokogiri 1.12.5 → 1.14.3

Potentially problematic release.

This version of nokogiri might be problematic. Click here for more details.

Files changed (156) hide show

checksums.yaml +4 -4
data/Gemfile +41 -0
data/LICENSE-DEPENDENCIES.md +830 -509
data/LICENSE.md +1 -1
data/README.md +23 -14
data/bin/nokogiri +63 -50
data/dependencies.yml +33 -66
data/ext/nokogiri/extconf.rb +159 -63
data/ext/nokogiri/gumbo.c +21 -11
data/ext/nokogiri/html4_document.c +2 -2
data/ext/nokogiri/html4_element_description.c +1 -1
data/ext/nokogiri/html4_entity_lookup.c +2 -2
data/ext/nokogiri/html4_sax_parser_context.c +3 -9
data/ext/nokogiri/html4_sax_push_parser.c +1 -1
data/ext/nokogiri/nokogiri.c +38 -51
data/ext/nokogiri/nokogiri.h +26 -14
data/ext/nokogiri/test_global_handlers.c +1 -1
data/ext/nokogiri/xml_attr.c +3 -3
data/ext/nokogiri/xml_attribute_decl.c +5 -5
data/ext/nokogiri/xml_cdata.c +3 -3
data/ext/nokogiri/xml_comment.c +1 -1
data/ext/nokogiri/xml_document.c +53 -44
data/ext/nokogiri/xml_document_fragment.c +1 -3
data/ext/nokogiri/xml_dtd.c +11 -11
data/ext/nokogiri/xml_element_content.c +3 -3
data/ext/nokogiri/xml_element_decl.c +5 -5
data/ext/nokogiri/xml_encoding_handler.c +28 -14
data/ext/nokogiri/xml_entity_decl.c +6 -6
data/ext/nokogiri/xml_entity_reference.c +1 -1
data/ext/nokogiri/xml_namespace.c +80 -14
data/ext/nokogiri/xml_node.c +982 -396
data/ext/nokogiri/xml_node_set.c +4 -6
data/ext/nokogiri/xml_processing_instruction.c +1 -1
data/ext/nokogiri/xml_reader.c +133 -32
data/ext/nokogiri/xml_relax_ng.c +1 -3
data/ext/nokogiri/xml_sax_parser.c +23 -17
data/ext/nokogiri/xml_sax_parser_context.c +11 -9
data/ext/nokogiri/xml_sax_push_parser.c +1 -3
data/ext/nokogiri/xml_schema.c +4 -6
data/ext/nokogiri/xml_syntax_error.c +1 -1
data/ext/nokogiri/xml_text.c +2 -2
data/ext/nokogiri/xml_xpath_context.c +144 -114
data/ext/nokogiri/xslt_stylesheet.c +122 -23
data/gumbo-parser/Makefile +10 -0
data/gumbo-parser/src/attribute.h +1 -1
data/gumbo-parser/src/error.c +2 -2
data/gumbo-parser/src/error.h +1 -1
data/gumbo-parser/src/foreign_attrs.c +2 -2
data/gumbo-parser/src/{gumbo.h → nokogiri_gumbo.h} +1 -0
data/gumbo-parser/src/parser.c +8 -16
data/gumbo-parser/src/replacement.h +1 -1
data/gumbo-parser/src/string_buffer.h +1 -1
data/gumbo-parser/src/string_piece.c +1 -1
data/gumbo-parser/src/svg_attrs.c +2 -2
data/gumbo-parser/src/svg_tags.c +2 -2
data/gumbo-parser/src/tag.c +2 -1
data/gumbo-parser/src/tag_lookup.c +7 -7
data/gumbo-parser/src/tag_lookup.gperf +1 -0
data/gumbo-parser/src/tag_lookup.h +1 -1
data/gumbo-parser/src/token_buffer.h +1 -1
data/gumbo-parser/src/tokenizer.c +1 -1
data/gumbo-parser/src/tokenizer.h +1 -1
data/gumbo-parser/src/utf8.c +1 -1
data/gumbo-parser/src/utf8.h +1 -1
data/gumbo-parser/src/util.c +1 -3
data/gumbo-parser/src/util.h +4 -0
data/gumbo-parser/src/vector.h +1 -1
data/lib/nokogiri/class_resolver.rb +67 -0
data/lib/nokogiri/css/node.rb +9 -8
data/lib/nokogiri/css/parser.rb +360 -341
data/lib/nokogiri/css/parser.y +249 -244
data/lib/nokogiri/css/parser_extras.rb +22 -20
data/lib/nokogiri/css/syntax_error.rb +1 -0
data/lib/nokogiri/css/tokenizer.rb +4 -3
data/lib/nokogiri/css/tokenizer.rex +3 -2
data/lib/nokogiri/css/xpath_visitor.rb +184 -85
data/lib/nokogiri/css.rb +44 -6
data/lib/nokogiri/decorators/slop.rb +8 -7
data/lib/nokogiri/encoding_handler.rb +57 -0
data/lib/nokogiri/extension.rb +4 -3
data/lib/nokogiri/gumbo.rb +1 -0
data/lib/nokogiri/html.rb +16 -10
data/lib/nokogiri/html4/builder.rb +1 -0
data/lib/nokogiri/html4/document.rb +56 -164
data/lib/nokogiri/html4/document_fragment.rb +11 -7
data/lib/nokogiri/html4/element_description.rb +1 -0
data/lib/nokogiri/html4/element_description_defaults.rb +432 -532
data/lib/nokogiri/html4/encoding_reader.rb +121 -0
data/lib/nokogiri/html4/entity_lookup.rb +2 -1
data/lib/nokogiri/html4/sax/parser.rb +5 -2
data/lib/nokogiri/html4/sax/parser_context.rb +1 -0
data/lib/nokogiri/html4/sax/push_parser.rb +7 -7
data/lib/nokogiri/html4.rb +12 -5
data/lib/nokogiri/html5/document.rb +126 -32
data/lib/nokogiri/html5/document_fragment.rb +14 -4
data/lib/nokogiri/html5/node.rb +12 -7
data/lib/nokogiri/html5.rb +138 -222
data/lib/nokogiri/jruby/dependencies.rb +2 -19
data/lib/nokogiri/jruby/nokogiri_jars.rb +43 -0
data/lib/nokogiri/syntax_error.rb +1 -0
data/lib/nokogiri/version/constant.rb +2 -1
data/lib/nokogiri/version/info.rb +32 -24
data/lib/nokogiri/version.rb +1 -0
data/lib/nokogiri/xml/attr.rb +54 -3
data/lib/nokogiri/xml/attribute_decl.rb +2 -1
data/lib/nokogiri/xml/builder.rb +35 -33
data/lib/nokogiri/xml/cdata.rb +2 -1
data/lib/nokogiri/xml/character_data.rb +1 -0
data/lib/nokogiri/xml/document.rb +232 -143
data/lib/nokogiri/xml/document_fragment.rb +88 -42
data/lib/nokogiri/xml/dtd.rb +3 -2
data/lib/nokogiri/xml/element_content.rb +1 -0
data/lib/nokogiri/xml/element_decl.rb +2 -1
data/lib/nokogiri/xml/entity_decl.rb +3 -2
data/lib/nokogiri/xml/entity_reference.rb +1 -0
data/lib/nokogiri/xml/namespace.rb +44 -0
data/lib/nokogiri/xml/node/save_options.rb +14 -8
data/lib/nokogiri/xml/node.rb +708 -383
data/lib/nokogiri/xml/node_set.rb +134 -59
data/lib/nokogiri/xml/notation.rb +12 -0
data/lib/nokogiri/xml/parse_options.rb +140 -56
data/lib/nokogiri/xml/pp/character_data.rb +8 -6
data/lib/nokogiri/xml/pp/node.rb +26 -26
data/lib/nokogiri/xml/pp.rb +1 -0
data/lib/nokogiri/xml/processing_instruction.rb +3 -1
data/lib/nokogiri/xml/reader.rb +20 -24
data/lib/nokogiri/xml/relax_ng.rb +1 -0
data/lib/nokogiri/xml/sax/document.rb +20 -19
data/lib/nokogiri/xml/sax/parser.rb +38 -36
data/lib/nokogiri/xml/sax/parser_context.rb +7 -3
data/lib/nokogiri/xml/sax/push_parser.rb +5 -5
data/lib/nokogiri/xml/sax.rb +1 -0
data/lib/nokogiri/xml/schema.rb +7 -6
data/lib/nokogiri/xml/searchable.rb +93 -62
data/lib/nokogiri/xml/syntax_error.rb +5 -4
data/lib/nokogiri/xml/text.rb +1 -0
data/lib/nokogiri/xml/xpath/syntax_error.rb +2 -1
data/lib/nokogiri/xml/xpath.rb +12 -0
data/lib/nokogiri/xml/xpath_context.rb +2 -3
data/lib/nokogiri/xml.rb +4 -3
data/lib/nokogiri/xslt/stylesheet.rb +1 -0
data/lib/nokogiri/xslt.rb +21 -13
data/lib/nokogiri.rb +22 -27
data/lib/xsd/xmlparser/nokogiri.rb +28 -25
data/patches/libxml2/0009-allow-wildcard-namespaces.patch +77 -0
data/patches/libxslt/0001-update-automake-files-for-arm64.patch +2445 -1919
data/ports/archives/libxml2-2.10.4.tar.xz +0 -0
data/ports/archives/libxslt-1.1.37.tar.xz +0 -0
metadata +20 -171
data/patches/libxml2/0004-use-glibc-strlen.patch +0 -53
data/patches/libxml2/0005-avoid-isnan-isinf.patch +0 -81
data/patches/libxml2/0006-update-automake-files-for-arm64.patch +0 -2511
data/patches/libxml2/0007-Fix-XPath-recursion-limit.patch +0 -31
data/patches/libxslt/0002-Fix-xml2-config-check-in-configure-script.patch +0 -19
data/ports/archives/libxml2-2.9.12.tar.gz +0 -0
data/ports/archives/libxslt-1.1.34.tar.gz +0 -0

data/lib/nokogiri/html4/document.rb CHANGED Viewed

@@ -1,6 +1,7 @@
+# coding: utf-8
 # frozen_string_literal: true
-require 'pathname'
+require "pathname"
 module Nokogiri
   module HTML4
@@ -9,11 +10,10 @@ module Nokogiri
       # Get the meta tag encoding for this document.  If there is no meta tag,
       # then nil is returned.
       def meta_encoding
-        case
-        when meta = at('//meta[@charset]')
+        if (meta = at_xpath("//meta[@charset]"))
           meta[:charset]
-        when meta = meta_content_type
-          meta['content'][/charset\s*=\s*([\w-]+)/i, 1]
+        elsif (meta = meta_content_type)
+          meta["content"][/charset\s*=\s*([\w-]+)/i, 1]
         end
       end
@@ -33,24 +33,22 @@ module Nokogiri
       #
       # Beware in CRuby, that libxml2 automatically inserts a meta tag
       # into a head element.
-      def meta_encoding= encoding
-        case
-        when meta = meta_content_type
-          meta['content'] = 'text/html; charset=%s' % encoding
+      def meta_encoding=(encoding)
+        if (meta = meta_content_type)
+          meta["content"] = format("text/html; charset=%s", encoding)
           encoding
-        when meta = at('//meta[@charset]')
-          meta['charset'] = encoding
+        elsif (meta = at_xpath("//meta[@charset]"))
+          meta["charset"] = encoding
         else
-          meta = XML::Node.new('meta', self)
-          if dtd = internal_subset and dtd.html5_dtd?
-            meta['charset'] = encoding
+          meta = XML::Node.new("meta", self)
+          if (dtd = internal_subset) && dtd.html5_dtd?
+            meta["charset"] = encoding
           else
-            meta['http-equiv'] = 'Content-Type'
-            meta['content'] = 'text/html; charset=%s' % encoding
+            meta["http-equiv"] = "Content-Type"
+            meta["content"] = format("text/html; charset=%s", encoding)
           end
-          case
-          when head = at('//head')
+          if (head = at_xpath("//head"))
             head.prepend_child(meta)
           else
             set_metadata_element(meta)
@@ -60,9 +58,9 @@ module Nokogiri
       end
       def meta_content_type
-        xpath('//meta[@http-equiv and boolean(@content)]').find { |node|
-          node['http-equiv'] =~ /\AContent-Type\z/i
-        }
+        xpath("//meta[@http-equiv and boolean(@content)]").find do |node|
+          node["http-equiv"] =~ /\AContent-Type\z/i
+        end
       end
       private :meta_content_type
@@ -70,7 +68,7 @@ module Nokogiri
       # Get the title string of this document.  Return nil if there is
       # no title tag.
       def title
-        title = at('//title') and title.inner_text
+        (title = at_xpath("//title")) && title.inner_text
       end
       ###
@@ -86,52 +84,50 @@ module Nokogiri
       # content element (typically <body>) if any.
       def title=(text)
         tnode = XML::Text.new(text, self)
-        if title = at('//title')
+        if (title = at_xpath("//title"))
           title.children = tnode
           return text
         end
-        title = XML::Node.new('title', self) << tnode
-        case
-        when head = at('//head')
+        title = XML::Node.new("title", self) << tnode
+        if (head = at_xpath("//head"))
           head << title
-        when meta = at('//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
           set_metadata_element(title)
         end
-        text
       end
-      def set_metadata_element(element)
-        case
-        when head = at('//head')
+      def set_metadata_element(element) # rubocop:disable Naming/AccessorMethodName
+        if (head = at_xpath("//head"))
           head << element
-        when html = at('//html')
-          head = html.prepend_child(XML::Node.new('head', self))
+        elsif (html = at_xpath("//html"))
+          head = html.prepend_child(XML::Node.new("head", self))
           head.prepend_child(element)
-        when first = children.find { |node|
-            case node
-            when XML::Element, XML::Text
-              true
-            end
-          }
+        elsif (first = children.find do |node|
+                 case node
+                 when XML::Element, XML::Text
+                   true
+                 end
+               end)
           # We reach here only if the underlying document model
           # allows <html>/<head> elements to be omitted and does not
           # automatically supply them.
           first.add_previous_sibling(element)
         else
-          html = add_child(XML::Node.new('html', self))
-          head = html.add_child(XML::Node.new('head', self))
+          html = add_child(XML::Node.new("html", self))
+          head = html.add_child(XML::Node.new("head", self))
           head.prepend_child(element)
         end
       end
       private :set_metadata_element
       ####
-      # Serialize Node using +options+.  Save options can also be set using a
-      # block. See SaveOptions.
+      # Serialize Node using +options+. Save options can also be set using a block.
+      #
+      # See also Nokogiri::XML::Node::SaveOptions and Node@Serialization+and+Generating+Output.
       #
       # These two statements are equivalent:
       #
@@ -143,15 +139,25 @@ module Nokogiri
       #     config.format.as_xml
       #   end
       #
-      def serialize options = {}
+      def serialize(options = {})
         options[:save_with] ||= XML::Node::SaveOptions::DEFAULT_HTML
         super
       end
       ####
       # Create a Nokogiri::XML::DocumentFragment from +tags+
-      def fragment tags = nil
-        DocumentFragment.new(self, tags, self.root)
+      def fragment(tags = nil)
+        DocumentFragment.new(self, tags, root)
+      end
+      # :call-seq:
+      #   xpath_doctype() → Nokogiri::CSS::XPathVisitor::DoctypeConfig
+      #
+      # [Returns] The document type which determines CSS-to-XPath translation.
+      #
+      # See XPathVisitor for more information.
+      def xpath_doctype
+        Nokogiri::CSS::XPathVisitor::DoctypeConfig::HTML4
       end
       class << self
@@ -163,15 +169,14 @@ module Nokogiri
         # is a number that sets options in the parser, such as
         # Nokogiri::XML::ParseOptions::RECOVER.  See the constants in
         # Nokogiri::XML::ParseOptions.
-        def parse string_or_io, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML
+        def parse(string_or_io, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML)
           options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
           yield options if block_given?
           url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil
           if string_or_io.respond_to?(:encoding)
-            unless string_or_io.encoding.name == "ASCII-8BIT"
+            unless string_or_io.encoding == Encoding::ASCII_8BIT
               encoding ||= string_or_io.encoding.name
             end
           end
@@ -184,21 +189,10 @@ module Nokogiri
             end
             unless encoding
-              # Libxml2's parser has poor support for encoding
-              # detection.  First, it does not recognize the HTML5
-              # style meta charset declaration.  Secondly, even if it
-              # successfully detects an encoding hint, it does not
-              # re-decode or re-parse the preceding part which may be
-              # garbled.
-              #
-              # EncodingReader aims to perform advanced encoding
-              # detection beyond what Libxml2 does, and to emulate
-              # rewinding of a stream and make Libxml2 redo parsing
-              # from the start when an encoding hint is found.
               string_or_io = EncodingReader.new(string_or_io)
               begin
                 return read_io(string_or_io, url, encoding, options.to_i)
-              rescue EncodingFound => e
+              rescue EncodingReader::EncodingFound => e
                 encoding = e.found_encoding
               end
             end
@@ -206,7 +200,7 @@ module Nokogiri
           end
           # read_memory pukes on empty docs
-          if string_or_io.nil? or string_or_io.empty?
+          if string_or_io.nil? || string_or_io.empty?
             return encoding ? new.tap { |i| i.encoding = encoding } : new
           end
@@ -215,108 +209,6 @@ module Nokogiri
           read_memory(string_or_io, url, encoding, options.to_i)
         end
       end
-      class EncodingFound < StandardError # :nodoc:
-        attr_reader :found_encoding
-        def initialize(encoding)
-          @found_encoding = encoding
-          super("encoding found: %s" % encoding)
-        end
-      end
-      class EncodingReader # :nodoc:
-        class SAXHandler < Nokogiri::XML::SAX::Document # :nodoc:
-          attr_reader :encoding
-          def initialize
-            @encoding = nil
-            super()
-          end
-          def start_element(name, attrs = [])
-            return unless name == 'meta'
-            attr = Hash[attrs]
-            charset = attr['charset'] and
-              @encoding = charset
-            http_equiv = attr['http-equiv'] and
-              http_equiv.match(/\AContent-Type\z/i) and
-              content = attr['content'] and
-              m = content.match(/;\s*charset\s*=\s*([\w-]+)/) and
-              @encoding = m[1]
-          end
-        end
-        class JumpSAXHandler < SAXHandler
-          def initialize(jumptag)
-            @jumptag = jumptag
-            super()
-          end
-          def start_element(name, attrs = [])
-            super
-            throw @jumptag, @encoding if @encoding
-            throw @jumptag, nil if name =~ /\A(?:div|h1|img|p|br)\z/
-          end
-        end
-        def self.detect_encoding(chunk)
-          m = chunk.match(/\A(<\?xml[ \t\r\n]+[^>]*>)/) and
-            return Nokogiri.XML(m[1]).encoding
-          if Nokogiri.jruby?
-            m = chunk.match(/(<meta\s)(.*)(charset\s*=\s*([\w-]+))(.*)/i) and
-              return m[4]
-            catch(:encoding_found) {
-              Nokogiri::HTML4::SAX::Parser.new(JumpSAXHandler.new(:encoding_found)).parse(chunk)
-              nil
-            }
-          else
-            handler = SAXHandler.new
-            parser = Nokogiri::HTML4::SAX::PushParser.new(handler)
-            parser << chunk rescue Nokogiri::SyntaxError
-            handler.encoding
-          end
-        end
-        def initialize(io)
-          @io = io
-          @firstchunk = nil
-          @encoding_found = nil
-        end
-        # This method is used by the C extension so that
-        # Nokogiri::HTML4::Document#read_io() does not leak memory when
-        # EncodingFound is raised.
-        attr_reader :encoding_found
-        def read(len)
-          # no support for a call without len
-          if !@firstchunk
-            @firstchunk = @io.read(len) or return nil
-            # This implementation expects that the first call from
-            # htmlReadIO() is made with a length long enough (~1KB) to
-            # achieve advanced encoding detection.
-            if encoding = EncodingReader.detect_encoding(@firstchunk)
-              # The first chunk is stored for the next read in retry.
-              raise @encoding_found = EncodingFound.new(encoding)
-            end
-          end
-          @encoding_found = nil
-          ret = @firstchunk.slice!(0, len)
-          if (len -= ret.length) > 0
-            rest = @io.read(len) and ret << rest
-          end
-          if ret.empty?
-            nil
-          else
-            ret
-          end
-        end
-      end
     end
   end
 end

data/lib/nokogiri/html4/document_fragment.rb CHANGED Viewed

@@ -1,34 +1,38 @@
 # frozen_string_literal: true
 module Nokogiri
   module HTML4
     class DocumentFragment < Nokogiri::XML::DocumentFragment
       ####
       # Create a Nokogiri::XML::DocumentFragment from +tags+, using +encoding+
-      def self.parse(tags, encoding = nil)
+      def self.parse(tags, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML, &block)
         doc = HTML4::Document.new
         encoding ||= if tags.respond_to?(:encoding)
           encoding = tags.encoding
           if encoding == ::Encoding::ASCII_8BIT
-            'UTF-8'
+            "UTF-8"
           else
             encoding.name
           end
         else
-          'UTF-8'
+          "UTF-8"
         end
         doc.encoding = encoding
-        new(doc, tags)
+        new(doc, tags, nil, options, &block)
       end
-      def initialize(document, tags = nil, ctx = nil)
+      def initialize(document, tags = nil, ctx = nil, options = XML::ParseOptions::DEFAULT_HTML)
         return self unless tags
+        options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
+        yield options if block_given?
         if ctx
           preexisting_errors = document.errors.dup
-          node_set = ctx.parse("<div>#{tags}</div>")
+          node_set = ctx.parse("<div>#{tags}</div>", options)
           node_set.first.children.each { |child| child.parent = self } unless node_set.empty?
           self.errors = document.errors - preexisting_errors
         else
@@ -39,7 +43,7 @@ module Nokogiri
             "/html/body/node()"
           end
-          temp_doc = HTML4::Document.parse("<html><body>#{tags}", nil, document.encoding)
+          temp_doc = HTML4::Document.parse("<html><body>#{tags}", nil, document.encoding, options)
           temp_doc.xpath(path).each { |child| child.parent = self }
           self.errors = temp_doc.errors
         end

data/lib/nokogiri/html4/element_description.rb CHANGED Viewed

@@ -1,4 +1,5 @@
 # frozen_string_literal: true
 module Nokogiri
   module HTML4
     class ElementDescription