nokogiri 1.5.10 → 1.10.4

Sign up to get free protection for your applications and to get access to all the features.

Potentially problematic release.


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

Files changed (182) hide show
  1. checksums.yaml +7 -0
  2. data/LICENSE-DEPENDENCIES.md +1614 -0
  3. data/LICENSE.md +9 -0
  4. data/README.md +198 -0
  5. data/bin/nokogiri +50 -10
  6. data/dependencies.yml +72 -0
  7. data/ext/nokogiri/extconf.rb +634 -92
  8. data/ext/nokogiri/html_document.c +8 -8
  9. data/ext/nokogiri/html_element_description.c +15 -15
  10. data/ext/nokogiri/html_entity_lookup.c +1 -1
  11. data/ext/nokogiri/html_sax_parser_context.c +4 -4
  12. data/ext/nokogiri/html_sax_push_parser.c +2 -2
  13. data/ext/nokogiri/nokogiri.c +20 -12
  14. data/ext/nokogiri/nokogiri.h +1 -44
  15. data/ext/nokogiri/xml_attr.c +34 -25
  16. data/ext/nokogiri/xml_cdata.c +12 -6
  17. data/ext/nokogiri/xml_comment.c +18 -3
  18. data/ext/nokogiri/xml_document.c +64 -32
  19. data/ext/nokogiri/xml_dtd.c +2 -2
  20. data/ext/nokogiri/xml_encoding_handler.c +3 -3
  21. data/ext/nokogiri/xml_entity_reference.c +1 -1
  22. data/ext/nokogiri/xml_io.c +11 -6
  23. data/ext/nokogiri/xml_namespace.c +50 -17
  24. data/ext/nokogiri/xml_namespace.h +3 -2
  25. data/ext/nokogiri/xml_node.c +459 -240
  26. data/ext/nokogiri/xml_node_set.c +166 -147
  27. data/ext/nokogiri/xml_node_set.h +2 -4
  28. data/ext/nokogiri/xml_processing_instruction.c +2 -2
  29. data/ext/nokogiri/xml_reader.c +6 -19
  30. data/ext/nokogiri/xml_sax_parser.c +11 -13
  31. data/ext/nokogiri/xml_sax_parser_context.c +41 -1
  32. data/ext/nokogiri/xml_sax_push_parser.c +56 -12
  33. data/ext/nokogiri/xml_schema.c +1 -1
  34. data/ext/nokogiri/xml_syntax_error.c +11 -5
  35. data/ext/nokogiri/xml_syntax_error.h +1 -1
  36. data/ext/nokogiri/xml_text.c +1 -1
  37. data/ext/nokogiri/xml_xpath_context.c +17 -38
  38. data/ext/nokogiri/xslt_stylesheet.c +10 -10
  39. data/lib/nokogiri/css/node.rb +0 -50
  40. data/lib/nokogiri/css/parser.rb +263 -233
  41. data/lib/nokogiri/css/parser.y +54 -40
  42. data/lib/nokogiri/css/tokenizer.rb +104 -103
  43. data/lib/nokogiri/css/tokenizer.rex +5 -5
  44. data/lib/nokogiri/css/xpath_visitor.rb +78 -19
  45. data/lib/nokogiri/decorators/slop.rb +12 -5
  46. data/lib/nokogiri/html/document.rb +102 -21
  47. data/lib/nokogiri/html/document_fragment.rb +11 -3
  48. data/lib/nokogiri/html/sax/parser.rb +12 -2
  49. data/lib/nokogiri/html/sax/push_parser.rb +22 -2
  50. data/lib/nokogiri/version.rb +40 -22
  51. data/lib/nokogiri/xml/builder.rb +34 -31
  52. data/lib/nokogiri/xml/document.rb +20 -14
  53. data/lib/nokogiri/xml/document_fragment.rb +50 -2
  54. data/lib/nokogiri/xml/dtd.rb +14 -4
  55. data/lib/nokogiri/xml/entity_reference.rb +18 -0
  56. data/lib/nokogiri/xml/node.rb +148 -203
  57. data/lib/nokogiri/xml/node_set.rb +139 -123
  58. data/lib/nokogiri/xml/parse_options.rb +22 -0
  59. data/lib/nokogiri/xml/sax/document.rb +1 -1
  60. data/lib/nokogiri/xml/sax/parser.rb +7 -8
  61. data/lib/nokogiri/xml/searchable.rb +230 -0
  62. data/lib/nokogiri/xml/syntax_error.rb +24 -1
  63. data/lib/nokogiri/xml.rb +3 -1
  64. data/lib/nokogiri.rb +40 -24
  65. data/patches/libxml2/0001-Revert-Do-not-URI-escape-in-server-side-includes.patch +78 -0
  66. data/patches/libxml2/0002-Remove-script-macro-support.patch +40 -0
  67. data/patches/libxml2/0003-Update-entities-to-remove-handling-of-ssi.patch +44 -0
  68. data/patches/libxslt/0001-Fix-security-framework-bypass.patch +120 -0
  69. data/ports/archives/libxml2-2.9.9.tar.gz +0 -0
  70. data/ports/archives/libxslt-1.1.33.tar.gz +0 -0
  71. metadata +252 -388
  72. data/.autotest +0 -26
  73. data/.gemtest +0 -0
  74. data/CHANGELOG.ja.rdoc +0 -785
  75. data/CHANGELOG.rdoc +0 -783
  76. data/C_CODING_STYLE.rdoc +0 -33
  77. data/Manifest.txt +0 -303
  78. data/README.ja.rdoc +0 -106
  79. data/README.rdoc +0 -175
  80. data/ROADMAP.md +0 -90
  81. data/Rakefile +0 -228
  82. data/STANDARD_RESPONSES.md +0 -47
  83. data/Y_U_NO_GEMSPEC.md +0 -155
  84. data/build_all +0 -105
  85. data/tasks/cross_compile.rb +0 -150
  86. data/tasks/nokogiri.org.rb +0 -24
  87. data/tasks/test.rb +0 -95
  88. data/test/css/test_nthiness.rb +0 -159
  89. data/test/css/test_parser.rb +0 -341
  90. data/test/css/test_tokenizer.rb +0 -198
  91. data/test/css/test_xpath_visitor.rb +0 -91
  92. data/test/decorators/test_slop.rb +0 -16
  93. data/test/files/2ch.html +0 -108
  94. data/test/files/address_book.rlx +0 -12
  95. data/test/files/address_book.xml +0 -10
  96. data/test/files/bar/bar.xsd +0 -4
  97. data/test/files/dont_hurt_em_why.xml +0 -422
  98. data/test/files/encoding.html +0 -82
  99. data/test/files/encoding.xhtml +0 -84
  100. data/test/files/exslt.xml +0 -8
  101. data/test/files/exslt.xslt +0 -35
  102. data/test/files/foo/foo.xsd +0 -4
  103. data/test/files/metacharset.html +0 -10
  104. data/test/files/noencoding.html +0 -47
  105. data/test/files/po.xml +0 -32
  106. data/test/files/po.xsd +0 -66
  107. data/test/files/shift_jis.html +0 -10
  108. data/test/files/shift_jis.xml +0 -5
  109. data/test/files/snuggles.xml +0 -3
  110. data/test/files/staff.dtd +0 -10
  111. data/test/files/staff.xml +0 -59
  112. data/test/files/staff.xslt +0 -32
  113. data/test/files/test_document_url/bar.xml +0 -2
  114. data/test/files/test_document_url/document.dtd +0 -4
  115. data/test/files/test_document_url/document.xml +0 -6
  116. data/test/files/tlm.html +0 -850
  117. data/test/files/to_be_xincluded.xml +0 -2
  118. data/test/files/valid_bar.xml +0 -2
  119. data/test/files/xinclude.xml +0 -4
  120. data/test/helper.rb +0 -154
  121. data/test/html/sax/test_parser.rb +0 -141
  122. data/test/html/sax/test_parser_context.rb +0 -46
  123. data/test/html/test_builder.rb +0 -164
  124. data/test/html/test_document.rb +0 -552
  125. data/test/html/test_document_encoding.rb +0 -138
  126. data/test/html/test_document_fragment.rb +0 -261
  127. data/test/html/test_element_description.rb +0 -105
  128. data/test/html/test_named_characters.rb +0 -14
  129. data/test/html/test_node.rb +0 -196
  130. data/test/html/test_node_encoding.rb +0 -27
  131. data/test/namespaces/test_additional_namespaces_in_builder_doc.rb +0 -14
  132. data/test/namespaces/test_namespaces_in_builder_doc.rb +0 -75
  133. data/test/namespaces/test_namespaces_in_created_doc.rb +0 -75
  134. data/test/namespaces/test_namespaces_in_parsed_doc.rb +0 -66
  135. data/test/test_convert_xpath.rb +0 -135
  136. data/test/test_css_cache.rb +0 -45
  137. data/test/test_encoding_handler.rb +0 -46
  138. data/test/test_memory_leak.rb +0 -156
  139. data/test/test_nokogiri.rb +0 -132
  140. data/test/test_reader.rb +0 -555
  141. data/test/test_soap4r_sax.rb +0 -52
  142. data/test/test_xslt_transforms.rb +0 -254
  143. data/test/xml/node/test_save_options.rb +0 -28
  144. data/test/xml/node/test_subclass.rb +0 -44
  145. data/test/xml/sax/test_parser.rb +0 -366
  146. data/test/xml/sax/test_parser_context.rb +0 -106
  147. data/test/xml/sax/test_push_parser.rb +0 -157
  148. data/test/xml/test_attr.rb +0 -64
  149. data/test/xml/test_attribute_decl.rb +0 -86
  150. data/test/xml/test_builder.rb +0 -306
  151. data/test/xml/test_c14n.rb +0 -151
  152. data/test/xml/test_cdata.rb +0 -48
  153. data/test/xml/test_comment.rb +0 -29
  154. data/test/xml/test_document.rb +0 -828
  155. data/test/xml/test_document_encoding.rb +0 -28
  156. data/test/xml/test_document_fragment.rb +0 -223
  157. data/test/xml/test_dtd.rb +0 -103
  158. data/test/xml/test_dtd_encoding.rb +0 -33
  159. data/test/xml/test_element_content.rb +0 -56
  160. data/test/xml/test_element_decl.rb +0 -73
  161. data/test/xml/test_entity_decl.rb +0 -122
  162. data/test/xml/test_entity_reference.rb +0 -245
  163. data/test/xml/test_namespace.rb +0 -95
  164. data/test/xml/test_node.rb +0 -1137
  165. data/test/xml/test_node_attributes.rb +0 -96
  166. data/test/xml/test_node_encoding.rb +0 -107
  167. data/test/xml/test_node_inheritance.rb +0 -32
  168. data/test/xml/test_node_reparenting.rb +0 -374
  169. data/test/xml/test_node_set.rb +0 -755
  170. data/test/xml/test_parse_options.rb +0 -64
  171. data/test/xml/test_processing_instruction.rb +0 -30
  172. data/test/xml/test_reader_encoding.rb +0 -142
  173. data/test/xml/test_relax_ng.rb +0 -60
  174. data/test/xml/test_schema.rb +0 -103
  175. data/test/xml/test_syntax_error.rb +0 -12
  176. data/test/xml/test_text.rb +0 -45
  177. data/test/xml/test_unparented_node.rb +0 -422
  178. data/test/xml/test_xinclude.rb +0 -83
  179. data/test/xml/test_xpath.rb +0 -295
  180. data/test/xslt/test_custom_functions.rb +0 -133
  181. data/test/xslt/test_exception_handling.rb +0 -37
  182. data/test_all +0 -81
@@ -1,245 +0,0 @@
1
- require "helper"
2
-
3
- module Nokogiri
4
- module XML
5
- class TestEntityReference < Nokogiri::TestCase
6
- def setup
7
- super
8
- @xml = Nokogiri::XML(File.open(XML_FILE), XML_FILE)
9
- end
10
-
11
- def test_new
12
- assert ref = EntityReference.new(@xml, 'ent4')
13
- assert_instance_of EntityReference, ref
14
- end
15
-
16
- def test_many_references
17
- 100.times { EntityReference.new(@xml, 'foo') }
18
- end
19
-
20
- def test_newline_node
21
- # issue 719
22
- xml = <<EOF
23
- <?xml version="1.0" ?>
24
- <item></item>
25
- EOF
26
- doc = Nokogiri::XML xml
27
- lf_node = Nokogiri::XML::EntityReference.new(doc, "#xa")
28
- doc.xpath('/item').first.add_child(lf_node)
29
- assert_match /&#xa;/, doc.to_xml
30
- end
31
- end
32
-
33
- module Common
34
- PATH = 'test/files/test_document_url/'
35
-
36
- attr_accessor :path, :parser
37
-
38
- def xml_document
39
- File.join path, 'document.xml'
40
- end
41
-
42
- def self.included base
43
- def base.test_relative_and_absolute_path method_name, &block
44
- test_relative_path method_name, &block
45
- test_absolute_path method_name, &block
46
- end
47
-
48
- def base.test_absolute_path method_name, &block
49
- define_method "#{method_name}_with_absolute_path" do
50
- self.path = "#{File.expand_path PATH}/"
51
- instance_eval(&block)
52
- end
53
- end
54
-
55
- def base.test_relative_path method_name, &block
56
- define_method method_name do
57
- self.path = PATH
58
- instance_eval(&block)
59
- end
60
- end
61
- end
62
- end
63
-
64
- class TestDOMEntityReference < Nokogiri::TestCase
65
- include Common
66
-
67
- def setup
68
- super
69
- @parser = Nokogiri::XML::Document
70
- end
71
-
72
- test_relative_and_absolute_path :test_dom_entity_reference_with_dtdloda do
73
- # Make sure that we can parse entity references and include them in the document
74
- html = File.read xml_document
75
- doc = @parser.parse html, path do |cfg|
76
- cfg.default_xml
77
- cfg.dtdload
78
- cfg.noent
79
- end
80
- assert_equal [], doc.errors
81
- assert_equal "foobar", doc.xpath('//blah').text
82
- end
83
-
84
- test_relative_and_absolute_path :test_dom_entity_reference_with_dtdvalid do
85
- # Make sure that we can parse entity references and include them in the document
86
- html = File.read xml_document
87
- doc = @parser.parse html, path do |cfg|
88
- cfg.default_xml
89
- cfg.dtdvalid
90
- cfg.noent
91
- end
92
- assert_equal [], doc.errors
93
- assert_equal "foobar", doc.xpath('//blah').text
94
- end
95
-
96
- test_absolute_path :test_dom_dtd_loading_with_absolute_path do
97
- # Make sure that we can parse entity references and include them in the document
98
- html = %Q[<?xml version="1.0" encoding="UTF-8" ?>
99
- <!DOCTYPE document SYSTEM "#{path}/document.dtd">
100
- <document>
101
- <body>&bar;</body>
102
- </document>
103
- ]
104
- doc = @parser.parse html, xml_document do |cfg|
105
- cfg.default_xml
106
- cfg.dtdvalid
107
- cfg.noent
108
- end
109
- assert_equal [], doc.errors
110
- assert_equal "foobar", doc.xpath('//blah').text
111
- end
112
-
113
- test_relative_and_absolute_path :test_dom_entity_reference_with_io do
114
- # Make sure that we can parse entity references and include them in the document
115
- html = File.open xml_document
116
- doc = @parser.parse html, nil do |cfg|
117
- cfg.default_xml
118
- cfg.dtdload
119
- cfg.noent
120
- end
121
- assert_equal [], doc.errors
122
- assert_equal "foobar", doc.xpath('//blah').text
123
- end
124
-
125
- test_relative_and_absolute_path :test_dom_entity_reference_without_noent do
126
- # Make sure that we don't include entity references unless NOENT is set to true
127
- html = File.read xml_document
128
- doc = @parser.parse html, path do |cfg|
129
- cfg.default_xml
130
- cfg.dtdload
131
- end
132
- assert_equal [], doc.errors
133
- assert_kind_of Nokogiri::XML::EntityReference, doc.xpath('//body').first.children.first
134
- end
135
-
136
- test_relative_and_absolute_path :test_dom_entity_reference_without_dtdload do
137
- # Make sure that we don't include entity references unless NOENT is set to true
138
- html = File.read xml_document
139
- doc = @parser.parse html, path do |cfg|
140
- cfg.default_xml
141
- end
142
- assert_kind_of Nokogiri::XML::EntityReference, doc.xpath('//body').first.children.first
143
- if Nokogiri.uses_libxml?
144
- assert_equal ["Entity 'bar' not defined"], doc.errors.map(&:to_s)
145
- end
146
- end
147
-
148
- test_relative_and_absolute_path :test_document_dtd_loading_with_nonet do
149
- # Make sure that we don't include remote entities unless NOENT is set to true
150
- html = %Q[<?xml version="1.0" encoding="UTF-8" ?>
151
- <!DOCTYPE document SYSTEM "http://foo.bar.com/">
152
- <document>
153
- <body>&bar;</body>
154
- </document>
155
- ]
156
- doc = @parser.parse html, path do |cfg|
157
- cfg.default_xml
158
- cfg.dtdload
159
- end
160
- assert_kind_of Nokogiri::XML::EntityReference, doc.xpath('//body').first.children.first
161
- if Nokogiri.uses_libxml?
162
- assert_equal ["Attempt to load network entity http://foo.bar.com/", "Entity 'bar' not defined"], doc.errors.map(&:to_s)
163
- else
164
- assert_equal ["Attempt to load network entity http://foo.bar.com/"], doc.errors.map(&:to_s)
165
- end
166
- end
167
- # TODO: can we retreive a resource pointing to localhost when NONET is set to true ?
168
- end
169
-
170
- class TestSaxEntityReference < Nokogiri::SAX::TestCase
171
- include Common
172
-
173
- def setup
174
- super
175
- @parser = XML::SAX::Parser.new(Doc.new) do |ctx|
176
- ctx.replace_entities = true
177
- end
178
- end
179
-
180
- test_relative_and_absolute_path :test_sax_entity_reference do
181
- # Make sure that we can parse entity references and include them in the document
182
- html = File.read xml_document
183
- @parser.parse html
184
- refute_nil @parser.document.errors
185
- assert_equal ["Entity 'bar' not defined"], @parser.document.errors.map(&:to_s).map(&:strip)
186
- end
187
-
188
- test_relative_and_absolute_path :test_more_sax_entity_reference do
189
- # Make sure that we don't include entity references unless NOENT is set to true
190
- html = %Q[<?xml version="1.0" encoding="UTF-8" ?>
191
- <!DOCTYPE document SYSTEM "http://foo.bar.com/">
192
- <document>
193
- <body>&bar;</body>
194
- </document>
195
- ]
196
- @parser.parse html
197
- refute_nil @parser.document.errors
198
- assert_equal ["Entity 'bar' not defined"], @parser.document.errors.map(&:to_s).map(&:strip)
199
- end
200
- end
201
-
202
- class TestReaderEntityReference < Nokogiri::TestCase
203
- include Common
204
-
205
- def setup
206
- super
207
- end
208
-
209
- test_relative_and_absolute_path :test_reader_entity_reference do
210
- # Make sure that we can parse entity references and include them in the document
211
- html = File.read xml_document
212
- reader = Nokogiri::XML::Reader html, path do |cfg|
213
- cfg.default_xml
214
- cfg.dtdload
215
- cfg.noent
216
- end
217
- nodes = []
218
- reader.each { |n| nodes << n.value }
219
- assert_equal ['foobar'], nodes.compact.map(&:strip).reject(&:empty?)
220
- end
221
-
222
- test_relative_and_absolute_path :test_reader_entity_reference_without_noent do
223
- # Make sure that we can parse entity references and include them in the document
224
- html = File.read xml_document
225
- reader = Nokogiri::XML::Reader html, path do |cfg|
226
- cfg.default_xml
227
- cfg.dtdload
228
- end
229
- nodes = []
230
- reader.each { |n| nodes << n.value }
231
- assert_equal [], nodes.compact.map(&:strip).reject(&:empty?)
232
- end
233
-
234
- test_relative_and_absolute_path :test_reader_entity_reference_without_dtdload do
235
- html = File.read xml_document
236
- assert_raises(Nokogiri::XML::SyntaxError) do
237
- reader = Nokogiri::XML::Reader html, path do |cfg|
238
- cfg.default_xml
239
- end
240
- reader.each { |n| n }
241
- end
242
- end
243
- end
244
- end
245
- end
@@ -1,95 +0,0 @@
1
- require "helper"
2
-
3
- module Nokogiri
4
- module XML
5
- class TestNamespace < Nokogiri::TestCase
6
- def setup
7
- super
8
- @xml = Nokogiri::XML <<-eoxml
9
- <root xmlns="http://tenderlovemaking.com/" xmlns:foo="bar">
10
- <awesome/>
11
- </root>
12
- eoxml
13
- end
14
-
15
- if Nokogiri.uses_libxml?
16
- def test_namespace_is_in_node_cache
17
- node = @xml.root.namespace
18
- assert @xml.instance_variable_get(:@node_cache).include?(node)
19
- end
20
- end
21
-
22
- def test_built_nodes_keep_namespace_decls
23
- doc = Document.new
24
- e = Node.new 'element', doc
25
- c = Node.new 'child', doc
26
- c.default_namespace = 'woop:de:doo'
27
-
28
- assert c.namespace, 'has a namespace'
29
- e.add_child c
30
- assert c.namespace, 'has a namespace'
31
-
32
- doc.add_child e
33
- assert c.namespace, 'has a namespace'
34
- end
35
-
36
- def test_inspect
37
- ns = @xml.root.namespace
38
- assert_equal "#<#{ns.class.name}:#{sprintf("0x%x", ns.object_id)} href=#{ns.href.inspect}>", ns.inspect
39
- end
40
-
41
- def test_namespace_node_prefix
42
- namespaces = @xml.root.namespace_definitions
43
- assert_equal [nil, 'foo'], namespaces.map { |x| x.prefix }
44
- end
45
-
46
- def test_namespace_node_href
47
- namespaces = @xml.root.namespace_definitions
48
- assert_equal [
49
- 'http://tenderlovemaking.com/',
50
- 'bar'
51
- ], namespaces.map { |x| x.href }
52
- end
53
-
54
- def test_equality
55
- namespaces = @xml.root.namespace_definitions
56
- assert_equal namespaces, @xml.root.namespace_definitions
57
- end
58
-
59
- def test_add_definition
60
- @xml.root.add_namespace_definition('baz', 'bar')
61
- assert_equal 3, @xml.root.namespace_definitions.length
62
- end
63
-
64
- def test_add_definition_return
65
- ns = @xml.root.add_namespace_definition('baz', 'bar')
66
- assert_equal 'baz', ns.prefix
67
- end
68
-
69
- def test_remove_entity_namespace
70
- s = %q{<?xml version='1.0'?><!DOCTYPE schema PUBLIC "-//W3C//DTD XMLSCHEMA 200102//EN" "XMLSchema.dtd" [<!ENTITY % p ''>]>}
71
- Nokogiri::XML(s).remove_namespaces!
72
- end
73
-
74
- def test_maintain_element_namespaces
75
- doc = Document.new
76
- subject = Nokogiri::XML::Node.new 'foo', doc
77
- subject << '<foobar xmlns="barfoo"/>'
78
- child = subject.children.first
79
- assert_equal 'foobar', child.name
80
- assert_equal 'barfoo', child.namespace.href
81
- assert_empty child.attributes
82
- end
83
-
84
- def test_maintain_element_namespaces_in_urn
85
- doc = Document.new
86
- subject = Nokogiri::XML::Node.new 'foo', doc
87
- subject << '<foobar xmlns="urn:xmpp:foospec:barfoo"/>'
88
- child = subject.children.first
89
- assert_equal 'foobar', child.name
90
- assert_equal 'urn:xmpp:foospec:barfoo', child.namespace.href
91
- assert_empty child.attributes
92
- end
93
- end
94
- end
95
- end