nokogiri 1.8.1 → 1.8.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: bb5ae2f309f32e6299e28f8163ccde42dd7194c6
-  data.tar.gz: fe6d320fb028811a39297771a9b5da13836a57ce
+  metadata.gz: 8eda887f0620302cc831ef126a36321b38a294b6
+  data.tar.gz: c16a8f4170ccb1bb77dca63b595371a806eb49de
 SHA512:
-  metadata.gz: f77a7df358ec08fa9f1c78e2a9d7fd0414c15022b42066208af6724db1087ef74a9e21d8750d9411f726311947618a81625713ce4c8064641ed490a014c99950
-  data.tar.gz: 57adf86c265c43453c50e72b9470a164738eb3c74b229cdfc2eb1c8a8e2b657fdd569c85e01d92c9b63e43da1ef6730937c6c40e666747fd5ee3717ae2713bd4
+  metadata.gz: 742e024c0c7d28ae1be933a52f42abeda71eca9b971bd314885c95559e531d8fbb009917e272f418ae6bb5decfe70eabcc9031f83adb1e360e27f18d7d97003f
+  data.tar.gz: 44cf0e20486485ea7e586ad87100f8f4df7dd4afbe46f4df8217c513e92bde898ed427403388c7931a8da1e7390f4786c1189154ca881bae1f1b2544706e6fff

data/.cross_rubies

@@ -1,3 +1,5 @@
+2.5.0:i686-w64-mingw32
+2.5.0:x86_64-w64-mingw32
 2.4.0:i686-w64-mingw32
 2.4.0:x86_64-w64-mingw32
 2.3.0:i686-w64-mingw32

data/CHANGELOG.md

@@ -1,3 +1,29 @@
+# 1.8.2 / 2018-01-29
+
+## Security Notes
+
+[MRI] The update of vendored libxml2 from 2.9.5 to 2.9.7 addresses at least one published vulnerability, CVE-2017-15412. [#1714 has complete details]
+
+
+## Dependencies
+
+* [MRI] libxml2 is updated from 2.9.5 to 2.9.7
+* [MRI] libxml2 is updated from 1.1.30 to 1.1.32
+
+
+## Features
+
+* [MRI] OpenBSD installation should be a bit easier now. [#1685] (Thanks, @jeremyevans!)
+* [MRI] Cross-built Windows gems now support Ruby 2.5
+
+
+## Bug fixes
+
+* Node#serialize once again returns UTF-8-encoded strings. [#1659]
+* [JRuby] made SAX parsing of characters consistent with C implementation [#1676] (Thanks, @andrew-aladev!)
+* [MRI] Predefined entities, when inspected, no longer cause a segfault. [#1238]
+
+
 # 1.8.1 / 2017-09-19
 
 ## Dependencies

data/Gemfile

@@ -13,10 +13,10 @@ gem "hoe-git", "~>1.6", :group => [:development, :test]
 gem "minitest", "~>5.8.4", :group => [:development, :test]
 gem "rake", "~>12.0", :group => [:development, :test]
 gem "rake-compiler", "~>1.0.3", :group => [:development, :test]
-gem "rake-compiler-dock", "~>0.6.0", :group => [:development, :test]
+gem "rake-compiler-dock", "~>0.6.2", :group => [:development, :test]
 gem "racc", "~>1.4.14", :group => [:development, :test], :platform => [:ruby, :mingw, :x64_mingw]
 gem "rexical", "~>1.0.5", :group => [:development, :test], :platform => [:ruby, :mingw, :x64_mingw]
-gem "concourse", "~>0.11", :group => [:development, :test]
+gem "concourse", "~>0.15", :group => [:development, :test]
 gem "rdoc", "~>4.0", :group => [:development, :test]
 gem "hoe", "~>3.16", :group => [:development, :test]
 

data/Manifest.txt

@@ -217,6 +217,7 @@ lib/nokogiri/xml/dtd.rb
 lib/nokogiri/xml/element_content.rb
 lib/nokogiri/xml/element_decl.rb
 lib/nokogiri/xml/entity_decl.rb
+lib/nokogiri/xml/entity_reference.rb
 lib/nokogiri/xml/namespace.rb
 lib/nokogiri/xml/node.rb
 lib/nokogiri/xml/node/save_options.rb
@@ -297,6 +298,7 @@ test/files/xinclude.xml
 test/helper.rb
 test/html/sax/test_parser.rb
 test/html/sax/test_parser_context.rb
+test/html/sax/test_parser_text.rb
 test/html/sax/test_push_parser.rb
 test/html/test_builder.rb
 test/html/test_document.rb
@@ -324,6 +326,7 @@ test/xml/node/test_save_options.rb
 test/xml/node/test_subclass.rb
 test/xml/sax/test_parser.rb
 test/xml/sax/test_parser_context.rb
+test/xml/sax/test_parser_text.rb
 test/xml/sax/test_push_parser.rb
 test/xml/test_attr.rb
 test/xml/test_attribute_decl.rb

data/Rakefile

@@ -137,10 +137,10 @@ HOE = Hoe.spec 'nokogiri' do
     ["minitest",           "~> 5.8.4"],
     ["rake",               "~> 12.0"],
     ["rake-compiler",      "~> 1.0.3"],
-    ["rake-compiler-dock", "~> 0.6.0"],
+    ["rake-compiler-dock", "~> 0.6.2"],
     ["racc",               "~> 1.4.14"],
     ["rexical",            "~> 1.0.5"],
-    ["concourse",          "~> 0.11"],
+    ["concourse",          "~> 0.15"],
   ]
 
   if java?
@@ -264,10 +264,7 @@ task 'bundler:gemfile' do
 end
 
 file GENERATED_PARSER => "lib/nokogiri/css/parser.y" do |t|
-  racc = RbConfig::CONFIG['target_os'] =~ /mswin32/ ? '' : `which racc`.strip
-  racc = "#{::RbConfig::CONFIG['bindir']}/racc" if racc.empty?
-  racc = %x{command -v racc}.strip if racc.empty?
-  sh "#{racc} -l -o #{t.name} #{t.prerequisites.first}"
+  sh "racc -l -o #{t.name} #{t.prerequisites.first}"
 end
 
 file GENERATED_TOKENIZER => "lib/nokogiri/css/tokenizer.rex" do |t|

data/appveyor.yml

@@ -1,24 +1,29 @@
 install:
-  - SET PATH=C:\Ruby%ruby_version%\bin;%PATH%
-  - SET PATH=C:\MinGW\bin;%PATH%
-  - SET RAKEOPT=-rdevkit
+  - SET PATH=C:\ruby%ruby_version%\bin;%PATH%
+  - ps: |
+      if ($env:ruby_version -like "*head*") {
+        $(new-object net.webclient).DownloadFile("https://github.com/oneclick/rubyinstaller2/releases/download/rubyinstaller-head/rubyinstaller-$env:ruby_version.exe", "$pwd/ruby-setup.exe")
+        cmd /c ruby-setup.exe /verysilent /dir=C:/Ruby$env:ruby_version
+      }
   - ruby --version
   - gem --version
+  - gem install bundler --conservative
   - bundle install
 
 build: off
 
 test_script:
-  - bundle exec rake
+  - bundle exec rake -rdevkit
 
 environment:
   matrix:
-    - ruby_version: "23"
-    - ruby_version: "23-x64"
-    - ruby_version: "22"
-    - ruby_version: "22-x64"
-    - ruby_version: "21"
-    - ruby_version: "21-x64"
-    - ruby_version: "200"
-    - ruby_version: "200-x64"
-    - ruby_version: "193"
+    - ruby_version: head-x64
+    - ruby_version: 24
+    - ruby_version: 23-x64
+    - ruby_version: 22
+    - ruby_version: 21-x64
+    - ruby_version: 200
+
+matrix:
+  allow_failures:
+    - ruby_version: head

data/dependencies.yml

@@ -1,10 +1,10 @@
 libxml2:
-  version: "2.9.5"
-  sha256: "4031c1ecee9ce7ba4f313e91ef6284164885cdb69937a123f6a83bb6a72dcd38"
+  version: "2.9.7"
+  sha256: "f63c5e7d30362ed28b38bfa1ac6313f9a80230720b7fb6c80575eeab3ff5900c"
   # manually verified checksum:
   #
-  #   $ gpg --verify libxml2-2.9.5.tar.gz.asc libxml2-2.9.5.tar.gz
-  #   gpg: Signature made Mon 04 Sep 2017 09:00:53 AM EDT using RSA key ID 596BEA5D
+  #   $ gpg --verify libxml2-2.9.7.tar.gz.asc libxml2-2.9.7.tar.gz
+  #   gpg: Signature made Thu 02 Nov 2017 04:17:54 PM EDT using RSA key ID 596BEA5D
   #   gpg: Good signature from "Daniel Veillard (Red Hat work email) <veillard@redhat.com>"
   #   gpg:                 aka "Daniel Veillard <Daniel.Veillard@w3.org>"
   #   gpg: WARNING: This key is not certified with a trusted signature!
@@ -13,25 +13,25 @@ libxml2:
   #        Subkey fingerprint: DB46 681B B91A DCEA 170F  A2D4 1558 8B26 596B EA5D
   #
   # using this pgp signature:
-  #
   #   -----BEGIN PGP SIGNATURE-----
   #
-  #   iQEcBAABAgAGBQJZrU6FAAoJEBVYiyZZa+pd73cIAMZpWcbiWwFqPgEJtscDfUqs
-  #   V0LjMKYXMDZCUs9/SPV/d6yXbOWSx2PgQ0wa7eCq2KmitIKYlcwnqB1WfAgSvNc+
-  #   cK8rVwIF4MfZQTzWie6uBvwukDn3224b3qjXxJtPS6J8HmiyK6suwDX5auEgEF8f
-  #   Ac1xy0K/hfAo+W5x7bm+suPHUduI7d6pWo1hNMwW/lyPiQthT4pPElkMBeKTi4vl
-  #   HTRTVEJKjVkdQ2tJ9b5pUYE0Aa6T54SVpCyBRmTu4d/MoOX5VnXBoiZIJDbSA5cD
-  #   GLQeXjDg/tYdq9DpYuT3otYd+6VWuWdH+f6jM6L2+82rAMtOAjBm97Z45XxH31I=
-  #   =T2TF
+  #   iQEcBAABAgAGBQJZ+31yAAoJEBVYiyZZa+pd+MMH/RTsPCo8CegAHsSUlNCae2Ay
+  #   HpM6J7sNWs0b2xwaYRtwhewJ5z/rsCcM5nn7MeGiU8dX7W5MKF69uGXUywufRxzO
+  #   GFoQSxO0a1z5mtGu7jC/W6DTYHFBeOJcEfMa3zUZjZ0RXqrENRhX55okse4pJPmG
+  #   dWQphbu9G3qoCuWD7QpyI7Mjhjemmyi4Ai/4vJPO8WtB7VDfdtpuZFVCRLG2cp0X
+  #   90SZde+0oWJcN8oIG3FaTd7O4OuJPAceqNhTvF90dLvqSqRBd0RqZNnjYNYZ6uRy
+  #   FQSlQBVCxdLY0AI7Yooq79TJD+0vcqiQNwQwH7L+hBWgvPos4DKN1M9LaJc/RTk=
+  #   =5Qzo
   #   -----END PGP SIGNATURE-----
+  #
 
 libxslt:
-  version: "1.1.30"
-  sha256: "ba65236116de8326d83378b2bd929879fa185195bc530b9d1aba72107910b6b3"
+  version: "1.1.32"
+  sha256: "526ecd0abaf4a7789041622c3950c0e7f2c4c8835471515fd77eec684a355460"
   # manually verified checksum:
   #
-  #   $ gpg --verify libxslt-1.1.30.tar.gz.asc libxslt-1.1.30.tar.gz
-  #   gpg: Signature made Mon 04 Sep 2017 09:36:06 AM EDT using RSA key ID 596BEA5D
+  #   $ gpg --verify libxslt-1.1.32.tar.gz.asc libxslt-1.1.32.tar.gz
+  #   gpg: Signature made Thu 02 Nov 2017 04:35:04 PM EDT using RSA key ID 596BEA5D
   #   gpg: Good signature from "Daniel Veillard (Red Hat work email) <veillard@redhat.com>"
   #   gpg:                 aka "Daniel Veillard <Daniel.Veillard@w3.org>"
   #   gpg: WARNING: This key is not certified with a trusted signature!
@@ -43,13 +43,13 @@ libxslt:
   #
   #   -----BEGIN PGP SIGNATURE-----
   #
-  #   iQEcBAABAgAGBQJZrVbGAAoJEBVYiyZZa+pdVrMH/Ru0J8zvwx8Geu6PX8ykvdEU
-  #   o5U/izwg8C8a1mtI9M8PcVUsERQinBcngO14Vk0V0dXHLp7/IEpRuXksCYkcTJL9
-  #   HawU2uDXTE/VwUl9aM2OXJOCk9W/JUkElbqEG11LCfU6uGlV+mFpLVO+eMDPxlRZ
-  #   v2LMs/yBFSiwNw757771ADShdRe3QxqhRscikK/yz/BRESdqls3/3y6GSEV2rx2n
-  #   VKVvsuHFisviwEn+1pvqcAGNCm0pIkPX6/nr+ayK3rBX7tmS493Stp6e/qUYKo6e
-  #   5cmdTkPhpzICQH2yqeUlfMp1M1nN50oShpvQqyjmpI+SV1udw08suIxVTDUCTRc=
-  #   =LjYD
+  #   iQEcBAABAgAGBQJZ+4F4AAoJEBVYiyZZa+pdy1IIAMX1DpzYGdnv6GCPSKeZ0woD
+  #   sHmSkygJep0/sUQD1cYunNsNZnGDgWhnsLAvHOn3opJgsiaZhmhJ8Uo7QNlT+ni1
+  #   AvRFgQoSXLWSF5kkun4u7RvnpDI6jYfCuYSwb9SO4EAYFAQQJXQaKCeFq71gad+p
+  #   XGHJFAy2TqUVLNZ5I1mQz/oBeDsJ7RzHpYqaBxsLDqrCzRQ9ai23q+dFGS3jvLBr
+  #   0gXw0MK73ceOwW12L5aLj4erNbATWmMFMDYZZwftysv3bgx2YfiOoZUTzufrB/Bc
+  #   MG8hP76aYBwIKNbhiDFGa2qdHGZGF7YQ4mi1/ZDX1K1G2tKKeEYxscM13JwiGb8=
+  #   =NuQO
   #   -----END PGP SIGNATURE-----
   #
 

data/ext/nokogiri/extconf.rb

@@ -393,8 +393,11 @@ when arg_config('--clean')
 end
 
 if openbsd? && !using_system_libraries?
-  ENV['CC'] ||= find_executable('egcc') or
-    abort "Please install gcc 4.9+ from ports using `pkg_add -v gcc`"
+  if `#{ENV['CC'] || '/usr/bin/cc'} -v 2>&1` !~ /clang/
+    ENV['CC'] ||= find_executable('egcc') or
+      abort "Please install gcc 4.9+ from ports using `pkg_add -v gcc`"
+  end
+  ENV['CFLAGS'] = "#{ENV['CFLAGS']} -I /usr/local/include"
 end
 
 RbConfig::MAKEFILE_CONFIG['CC'] = ENV['CC'] if ENV['CC']

data/lib/nokogiri/version.rb

@@ -1,6 +1,6 @@
 module Nokogiri
   # The version of Nokogiri you are using
-  VERSION = '1.8.1'
+  VERSION = '1.8.2'
 
   class VersionInfo # :nodoc:
     def jruby?

data/lib/nokogiri/xml.rb

@@ -23,6 +23,7 @@ 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'
 

data/lib/nokogiri/xml/entity_reference.rb

@@ -0,0 +1,18 @@
+module Nokogiri
+  module XML
+    class EntityReference < Nokogiri::XML::Node
+      def children
+        # libxml2 will create a malformed child node for predefined
+        # entities. because any use of that child is likely to cause a
+        # segfault, we shall pretend that it doesn't exist.
+        #
+        # see https://github.com/sparklemotion/nokogiri/issues/1238 for details
+        NodeSet.new(document)
+      end
+
+      def inspect_attributes
+        [:name]
+      end
+    end
+  end
+end

data/lib/nokogiri/xml/node.rb

@@ -624,9 +624,7 @@ module Nokogiri
         options[:encoding] = encoding
 
         outstring = String.new
-        if encoding && outstring.respond_to?(:force_encoding)
-          outstring.force_encoding(Encoding.find(encoding))
-        end
+        outstring.force_encoding(Encoding.find(encoding || 'utf-8'))
         io = StringIO.new(outstring)
         write_to io, options, &block
         io.string

data/test/helper.rb

@@ -186,6 +186,86 @@ module Nokogiri
           @processing_instructions << [name, content]
         end
       end
+
+      # This document will help us to test the strict order of items.
+
+      class DocWithOrderedItems < XML::SAX::Document
+        attr_reader :items
+
+        def initialize
+          # [
+          #   [ :method_1, argument_1, ... ],
+          #   [ :method_2, argument_2, ... ],
+          #   ...
+          # ]
+          @items = Items.new
+        end
+
+        [
+          :xmldecl,
+          :start_document, :end_document,
+          :start_element, :end_element,
+          :start_element_namespace, :end_element_namespace,
+          :characters, :comment, :cdata_block,
+          :processing_instruction,
+          :error, :warning
+        ]
+        .each do |name|
+          define_method name do |*arguments|
+            @items << [name, *arguments]
+            super *arguments
+          end
+        end
+
+        class Items < Array
+          def get_root_content root_name
+            items          = clone
+            is_inside_root = false
+
+            items.select! do |item|
+              method_name  = item[0]
+              element_name = item[1]
+
+              case method_name
+              when :start_element, :start_element_namespace
+                if element_name == root_name
+                  is_inside_root = true
+                  next false
+                end
+
+              when :end_element, :end_element_namespace
+                is_inside_root = false if element_name == root_name and is_inside_root
+              end
+
+              is_inside_root
+            end
+
+            items
+          end
+
+          def select_methods(names)
+            items = clone
+
+            items.select! do |item|
+              name = item[0]
+              names.include? name
+            end
+
+            items
+          end
+
+          def strip_text! method_names
+            each do |item|
+              method_name = item[0]
+              text        = item[1]
+
+              text.strip! if method_names.include? method_name
+            end
+
+            nil
+          end
+        end
+      end
     end
   end
 end

data/test/html/sax/test_parser_text.rb

@@ -0,0 +1,163 @@
+# -*- coding: utf-8 -*-
+require "helper"
+
+module Nokogiri
+  module HTML
+    module SAX
+      class TestParserText < Nokogiri::SAX::TestCase
+        def setup
+          super
+          @doc    = DocWithOrderedItems.new
+          @parser = HTML::SAX::Parser.new @doc
+        end
+
+        def test_texts_order
+          html = <<-eohtml
+            <!DOCTYPE html>
+            <html>
+              <head></head>
+              <body>
+                text 0
+                <p>
+                  text 1
+                  <span>text 2</span>
+                  text 3
+                </p>
+
+                text 4
+                <!--
+                text 5
+                -->
+
+                <p>
+                  <!-- text 6 -->
+                  <span><!-- text 7 --></span>
+                  <!-- text 8 -->
+                </p>
+
+                <!-- text 9 -->
+              </body>
+            </html>
+          eohtml
+
+          @parser.parse html
+          items = @doc.items.get_root_content "body"
+          items = items.select_methods [
+            :start_element, :end_element,
+            :characters, :comment
+          ]
+          items.strip_text! [:characters, :comment]
+
+          assert_equal [
+            [:characters, 'text 0'],
+
+            [:start_element, 'p', []],
+            [:characters, 'text 1'],
+
+            [:start_element, 'span', []],
+            [:characters, 'text 2'],
+            [:end_element, 'span'],
+
+            [:characters, 'text 3'],
+            [:end_element, 'p'],
+
+            [:characters, 'text 4'],
+            [:comment, 'text 5'],
+            [:characters, ''],
+
+            [:start_element, 'p', []],
+            [:characters, ''],
+            [:comment, 'text 6'],
+            [:characters, ''],
+
+            [:start_element, 'span', []],
+            [:comment, 'text 7'],
+            [:end_element, 'span'],
+            [:characters, ''],
+
+            [:comment, 'text 8'],
+            [:characters, ''],
+            [:end_element, 'p'],
+            [:characters, ''],
+
+            [:comment, 'text 9'],
+            [:characters, '']
+          ], items
+
+          nil
+        end
+
+        def text_whitespace
+          html = <<-eohtml
+            <!DOCTYPE html>
+            <html>
+              <head></head>
+              <body>
+                <p>
+                  <span></span>
+                  <span> </span>
+                  <span>
+
+                  </span>
+                </p>
+                <p>
+                  <!---->
+                  <!-- -->
+                  <!--
+
+                  -->
+                </p>
+              </body>
+            </html>
+          eohtml
+
+          @parser.parse html
+          items = @doc.items.get_root_content "body"
+          items = items.select_methods [
+            :start_element, :end_element,
+            :characters, :comment
+          ]
+          items.strip_text! [:characters, :comment]
+
+          assert_equal [
+            [:characters, ''],
+            [:start_element, 'p', []],
+
+            [:characters, ''],
+            [:start_element, 'span', []],
+            [:end_element, 'span'],
+            [:characters, ''],
+
+            [:start_element, 'span', []],
+            [:characters, ''],
+            [:end_element, 'span'],
+            [:characters, ''],
+
+            [:start_element, 'span', []],
+            [:characters, ''],
+            [:end_element, 'span'],
+            [:characters, ''],
+
+            [:end_element, 'p'],
+            [:characters, ''],
+
+            [:start_element, 'p', []],
+            [:characters, ''],
+
+            [:comment, ''],
+            [:characters, ''],
+            [:comment, ''],
+            [:characters, ''],
+            [:comment, ''],
+            [:characters, ''],
+
+            [:end_element, 'p'],
+            [:characters, '']
+          ], items
+
+          nil
+        end
+      end
+    end
+  end
+end

data/test/html/test_node_encoding.rb

@@ -26,6 +26,12 @@ module Nokogiri
         assert_equal @html.serialize, @doc.serialize
       end
 
+      def test_default_encoding
+        doc = Nokogiri::HTML(nil)
+        assert_nil doc.encoding
+        assert_equal 'UTF-8', doc.serialize.encoding.name
+      end
+
       def test_encode_special_chars
         foo = @html.css('a').first.encode_special_chars('foo')
         assert_equal 'UTF-8', foo.encoding.name

data/test/xml/sax/test_parser_text.rb

@@ -0,0 +1,202 @@
+# -*- coding: utf-8 -*-
+require "helper"
+
+module Nokogiri
+  module XML
+    module SAX
+      class TestParserText < Nokogiri::SAX::TestCase
+        def setup
+          super
+          @doc    = DocWithOrderedItems.new
+          @parser = XML::SAX::Parser.new @doc
+        end
+
+        def test_texts_order
+          xml = <<-eoxml
+<?xml version="1.0" ?>
+<root>
+  text 0
+  <p>
+    text 1
+    <span>text 2</span>
+    text 3
+  </p>
+
+  text 4
+  <!--
+  text 5
+  -->
+
+  <p>
+    <!-- text 6 -->
+    <span><!-- text 7 --></span>
+    <!-- text 8 -->
+  </p>
+
+  <!-- text 9 -->
+  <![CDATA[ text 10 ]]>
+
+  <p>
+    <![CDATA[ text 11 ]]>
+    <span><![CDATA[ text 12 ]]></span>
+    <![CDATA[ text 13 ]]>
+  </p>
+</root>
+          eoxml
+
+          @parser.parse xml
+          items = @doc.items.get_root_content "root"
+          items = items.select_methods [
+            :start_element, :end_element,
+            :characters, :comment, :cdata_block
+          ]
+          items.strip_text! [:characters, :comment, :cdata_block]
+
+          assert_equal [
+            [:characters, 'text 0'],
+
+            [:start_element, 'p', []],
+            [:characters, 'text 1'],
+
+            [:start_element, 'span', []],
+            [:characters, 'text 2'],
+            [:end_element, 'span'],
+
+            [:characters, 'text 3'],
+            [:end_element, 'p'],
+
+            [:characters, 'text 4'],
+            [:comment, 'text 5'],
+            [:characters, ''],
+
+            [:start_element, 'p', []],
+            [:characters, ''],
+            [:comment, 'text 6'],
+            [:characters, ''],
+
+            [:start_element, 'span', []],
+            [:comment, 'text 7'],
+            [:end_element, 'span'],
+            [:characters, ''],
+
+            [:comment, 'text 8'],
+            [:characters, ''],
+            [:end_element, 'p'],
+            [:characters, ''],
+
+            [:comment, 'text 9'],
+            [:characters, ''],
+            [:cdata_block, 'text 10'],
+            [:characters, ''],
+
+            [:start_element, 'p', []],
+            [:characters, ''],
+            [:cdata_block, 'text 11'],
+            [:characters, ''],
+
+            [:start_element, 'span', []],
+            [:cdata_block, 'text 12'],
+            [:end_element, 'span'],
+            [:characters, ''],
+
+            [:cdata_block, 'text 13'],
+            [:characters, ''],
+
+            [:end_element, 'p'],
+            [:characters, '']
+          ], items
+
+          nil
+        end
+
+        def text_whitespace
+          xml = <<-eoxml
+<?xml version="1.0" ?>
+<root>
+  <p>
+    <span></span>
+    <span> </span>
+    <span>
+
+    </span>
+  </p>
+  <p>
+    <!---->
+    <!-- -->
+    <!--
+
+    -->
+  </p>
+  <p>
+    <![CDATA[]]>
+    <![CDATA[ ]]>
+    <![CDATA[
+
+    ]]>
+  </p>
+</root>
+          eoxml
+
+          @parser.parse xml
+          items = @doc.items.get_root_content "root"
+          items = items.select_methods [
+            :start_element, :end_element,
+            :characters, :comment, :cdata_block
+          ]
+          items.strip_text! [:characters, :comment, :cdata_block]
+
+          assert_equal [
+            [:characters, ''],
+            [:start_element, 'p', []],
+
+            [:characters, ''],
+            [:start_element, 'span', []],
+            [:end_element, 'span'],
+            [:characters, ''],
+
+            [:start_element, 'span', []],
+            [:characters, ''],
+            [:end_element, 'span'],
+            [:characters, ''],
+
+            [:start_element, 'span', []],
+            [:characters, ''],
+            [:end_element, 'span'],
+            [:characters, ''],
+
+            [:end_element, 'p'],
+            [:characters, ''],
+
+            [:start_element, 'p', []],
+            [:characters, ''],
+
+            [:comment, ''],
+            [:characters, ''],
+            [:comment, ''],
+            [:characters, ''],
+            [:comment, ''],
+            [:characters, ''],
+
+            [:end_element, 'p'],
+            [:characters, ''],
+
+            [:start_element, 'p', []],
+            [:characters, ''],
+
+            [:cdata_block, ''],
+            [:characters, ''],
+            [:cdata_block, ''],
+            [:characters, ''],
+            [:cdata_block, ''],
+            [:characters, ''],
+
+            [:end_element, 'p'],
+            [:characters, '']
+          ], items
+
+          nil
+        end
+      end
+    end
+  end
+end

data/test/xml/test_entity_reference.rb

@@ -28,6 +28,17 @@ EOF
         doc.xpath('/item').first.add_child(lf_node)
         assert_match(/
/, doc.to_xml)
       end
+
+      def test_children_should_always_be_empty
+        # https://github.com/sparklemotion/nokogiri/issues/1238
+        #
+        # libxml2 will create a malformed child node for predefined
+        # entities. because any use of that child is likely to cause a
+        # segfault, we shall pretend that it doesn't exist.
+        entity = Nokogiri::XML::EntityReference.new(@xml, "amp")
+        assert_equal 0, entity.children.length
+        entity.inspect # should not segfault
+      end
     end
 
     module Common

data/test/xml/test_node_encoding.rb

@@ -13,6 +13,12 @@ module Nokogiri
         assert_equal @xml.serialize, @doc.serialize
       end
 
+      def test_default_encoding
+        doc = Nokogiri::XML(VEHICLE_XML)
+        assert_nil doc.encoding
+        assert_equal 'UTF-8', doc.serialize.encoding.name
+      end
+
       def test_encoding_GH_1113
         utf8 = '<frag>shahid ὡ 𐄣 𢂁</frag>'
         hex = '<frag>shahid &#x1f61; &#x10123; &#x22081;</frag>'

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: nokogiri
 version: !ruby/object:Gem::Version
-  version: 1.8.1
+  version: 1.8.2
 platform: ruby
 authors:
 - Aaron Patterson
@@ -12,7 +12,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-09-19 00:00:00.000000000 Z
+date: 2018-01-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: mini_portile2
@@ -132,14 +132,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.6.0
+        version: 0.6.2
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 0.6.0
+        version: 0.6.2
 - !ruby/object:Gem::Dependency
   name: racc
   requirement: !ruby/object:Gem::Requirement
@@ -174,14 +174,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.11'
+        version: '0.15'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '0.11'
+        version: '0.15'
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
@@ -398,6 +398,7 @@ files:
 - lib/nokogiri/xml/element_content.rb
 - lib/nokogiri/xml/element_decl.rb
 - lib/nokogiri/xml/entity_decl.rb
+- lib/nokogiri/xml/entity_reference.rb
 - lib/nokogiri/xml/namespace.rb
 - lib/nokogiri/xml/node.rb
 - lib/nokogiri/xml/node/save_options.rb
@@ -426,8 +427,8 @@ files:
 - lib/nokogiri/xslt/stylesheet.rb
 - lib/xsd/xmlparser/nokogiri.rb
 - patches/sort-patches-by-date
-- ports/archives/libxml2-2.9.5.tar.gz
-- ports/archives/libxslt-1.1.30.tar.gz
+- ports/archives/libxml2-2.9.7.tar.gz
+- ports/archives/libxslt-1.1.32.tar.gz
 - suppressions/README.txt
 - suppressions/nokogiri_ruby-2.supp
 - tasks/test.rb
@@ -476,6 +477,7 @@ files:
 - test/helper.rb
 - test/html/sax/test_parser.rb
 - test/html/sax/test_parser_context.rb
+- test/html/sax/test_parser_text.rb
 - test/html/sax/test_push_parser.rb
 - test/html/test_builder.rb
 - test/html/test_document.rb
@@ -503,6 +505,7 @@ files:
 - test/xml/node/test_subclass.rb
 - test/xml/sax/test_parser.rb
 - test/xml/sax/test_parser_context.rb
+- test/xml/sax/test_parser_text.rb
 - test/xml/sax/test_push_parser.rb
 - test/xml/test_attr.rb
 - test/xml/test_attribute_decl.rb