rubyjedi-nokogiri_java 1.4.0.20100513161003-java

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (285) hide show
  1. data/.autotest +26 -0
  2. data/CHANGELOG.ja.rdoc +330 -0
  3. data/CHANGELOG.rdoc +341 -0
  4. data/Manifest.txt +277 -0
  5. data/README.ja.rdoc +105 -0
  6. data/README.rdoc +125 -0
  7. data/Rakefile +307 -0
  8. data/bin/nokogiri +49 -0
  9. data/deps.rip +5 -0
  10. data/ext/nokogiri/extconf.rb +149 -0
  11. data/ext/nokogiri/html_document.c +145 -0
  12. data/ext/nokogiri/html_document.h +10 -0
  13. data/ext/nokogiri/html_element_description.c +272 -0
  14. data/ext/nokogiri/html_element_description.h +10 -0
  15. data/ext/nokogiri/html_entity_lookup.c +32 -0
  16. data/ext/nokogiri/html_entity_lookup.h +8 -0
  17. data/ext/nokogiri/html_sax_parser_context.c +92 -0
  18. data/ext/nokogiri/html_sax_parser_context.h +11 -0
  19. data/ext/nokogiri/nokogiri.c +96 -0
  20. data/ext/nokogiri/nokogiri.h +148 -0
  21. data/ext/nokogiri/xml_attr.c +92 -0
  22. data/ext/nokogiri/xml_attr.h +9 -0
  23. data/ext/nokogiri/xml_attribute_decl.c +67 -0
  24. data/ext/nokogiri/xml_attribute_decl.h +9 -0
  25. data/ext/nokogiri/xml_cdata.c +54 -0
  26. data/ext/nokogiri/xml_cdata.h +9 -0
  27. data/ext/nokogiri/xml_comment.c +52 -0
  28. data/ext/nokogiri/xml_comment.h +9 -0
  29. data/ext/nokogiri/xml_document.c +386 -0
  30. data/ext/nokogiri/xml_document.h +24 -0
  31. data/ext/nokogiri/xml_document_fragment.c +46 -0
  32. data/ext/nokogiri/xml_document_fragment.h +10 -0
  33. data/ext/nokogiri/xml_dtd.c +192 -0
  34. data/ext/nokogiri/xml_dtd.h +10 -0
  35. data/ext/nokogiri/xml_element_content.c +123 -0
  36. data/ext/nokogiri/xml_element_content.h +10 -0
  37. data/ext/nokogiri/xml_element_decl.c +69 -0
  38. data/ext/nokogiri/xml_element_decl.h +9 -0
  39. data/ext/nokogiri/xml_encoding_handler.c +79 -0
  40. data/ext/nokogiri/xml_encoding_handler.h +8 -0
  41. data/ext/nokogiri/xml_entity_decl.c +97 -0
  42. data/ext/nokogiri/xml_entity_decl.h +10 -0
  43. data/ext/nokogiri/xml_entity_reference.c +50 -0
  44. data/ext/nokogiri/xml_entity_reference.h +9 -0
  45. data/ext/nokogiri/xml_io.c +31 -0
  46. data/ext/nokogiri/xml_io.h +11 -0
  47. data/ext/nokogiri/xml_namespace.c +82 -0
  48. data/ext/nokogiri/xml_namespace.h +13 -0
  49. data/ext/nokogiri/xml_node.c +1080 -0
  50. data/ext/nokogiri/xml_node.h +13 -0
  51. data/ext/nokogiri/xml_node_set.c +405 -0
  52. data/ext/nokogiri/xml_node_set.h +9 -0
  53. data/ext/nokogiri/xml_processing_instruction.c +54 -0
  54. data/ext/nokogiri/xml_processing_instruction.h +9 -0
  55. data/ext/nokogiri/xml_reader.c +593 -0
  56. data/ext/nokogiri/xml_reader.h +10 -0
  57. data/ext/nokogiri/xml_relax_ng.c +159 -0
  58. data/ext/nokogiri/xml_relax_ng.h +9 -0
  59. data/ext/nokogiri/xml_sax_parser.c +283 -0
  60. data/ext/nokogiri/xml_sax_parser.h +43 -0
  61. data/ext/nokogiri/xml_sax_parser_context.c +157 -0
  62. data/ext/nokogiri/xml_sax_parser_context.h +10 -0
  63. data/ext/nokogiri/xml_sax_push_parser.c +114 -0
  64. data/ext/nokogiri/xml_sax_push_parser.h +9 -0
  65. data/ext/nokogiri/xml_schema.c +156 -0
  66. data/ext/nokogiri/xml_schema.h +9 -0
  67. data/ext/nokogiri/xml_syntax_error.c +52 -0
  68. data/ext/nokogiri/xml_syntax_error.h +13 -0
  69. data/ext/nokogiri/xml_text.c +48 -0
  70. data/ext/nokogiri/xml_text.h +9 -0
  71. data/ext/nokogiri/xml_xpath.c +53 -0
  72. data/ext/nokogiri/xml_xpath.h +11 -0
  73. data/ext/nokogiri/xml_xpath_context.c +239 -0
  74. data/ext/nokogiri/xml_xpath_context.h +9 -0
  75. data/ext/nokogiri/xslt_stylesheet.c +131 -0
  76. data/ext/nokogiri/xslt_stylesheet.h +9 -0
  77. data/lib/isorelax.jar +0 -0
  78. data/lib/jing.jar +0 -0
  79. data/lib/nekodtd.jar +0 -0
  80. data/lib/nekohtml.jar +0 -0
  81. data/lib/nokogiri.rb +123 -0
  82. data/lib/nokogiri/css.rb +25 -0
  83. data/lib/nokogiri/css/generated_parser.rb +659 -0
  84. data/lib/nokogiri/css/generated_tokenizer.rb +145 -0
  85. data/lib/nokogiri/css/node.rb +99 -0
  86. data/lib/nokogiri/css/parser.rb +82 -0
  87. data/lib/nokogiri/css/parser.y +230 -0
  88. data/lib/nokogiri/css/syntax_error.rb +7 -0
  89. data/lib/nokogiri/css/tokenizer.rb +7 -0
  90. data/lib/nokogiri/css/tokenizer.rex +55 -0
  91. data/lib/nokogiri/css/xpath_visitor.rb +164 -0
  92. data/lib/nokogiri/decorators/slop.rb +33 -0
  93. data/lib/nokogiri/ffi/encoding_handler.rb +42 -0
  94. data/lib/nokogiri/ffi/html/document.rb +28 -0
  95. data/lib/nokogiri/ffi/html/element_description.rb +81 -0
  96. data/lib/nokogiri/ffi/html/entity_lookup.rb +16 -0
  97. data/lib/nokogiri/ffi/html/sax/parser_context.rb +38 -0
  98. data/lib/nokogiri/ffi/io_callbacks.rb +42 -0
  99. data/lib/nokogiri/ffi/libxml.rb +372 -0
  100. data/lib/nokogiri/ffi/structs/common_node.rb +26 -0
  101. data/lib/nokogiri/ffi/structs/html_elem_desc.rb +24 -0
  102. data/lib/nokogiri/ffi/structs/html_entity_desc.rb +13 -0
  103. data/lib/nokogiri/ffi/structs/xml_alloc.rb +16 -0
  104. data/lib/nokogiri/ffi/structs/xml_attr.rb +19 -0
  105. data/lib/nokogiri/ffi/structs/xml_attribute.rb +27 -0
  106. data/lib/nokogiri/ffi/structs/xml_buffer.rb +16 -0
  107. data/lib/nokogiri/ffi/structs/xml_char_encoding_handler.rb +11 -0
  108. data/lib/nokogiri/ffi/structs/xml_document.rb +108 -0
  109. data/lib/nokogiri/ffi/structs/xml_dtd.rb +28 -0
  110. data/lib/nokogiri/ffi/structs/xml_element.rb +26 -0
  111. data/lib/nokogiri/ffi/structs/xml_element_content.rb +17 -0
  112. data/lib/nokogiri/ffi/structs/xml_entity.rb +32 -0
  113. data/lib/nokogiri/ffi/structs/xml_enumeration.rb +12 -0
  114. data/lib/nokogiri/ffi/structs/xml_node.rb +28 -0
  115. data/lib/nokogiri/ffi/structs/xml_node_set.rb +53 -0
  116. data/lib/nokogiri/ffi/structs/xml_notation.rb +11 -0
  117. data/lib/nokogiri/ffi/structs/xml_ns.rb +15 -0
  118. data/lib/nokogiri/ffi/structs/xml_parser_context.rb +19 -0
  119. data/lib/nokogiri/ffi/structs/xml_relax_ng.rb +14 -0
  120. data/lib/nokogiri/ffi/structs/xml_sax_handler.rb +51 -0
  121. data/lib/nokogiri/ffi/structs/xml_sax_push_parser_context.rb +124 -0
  122. data/lib/nokogiri/ffi/structs/xml_schema.rb +13 -0
  123. data/lib/nokogiri/ffi/structs/xml_syntax_error.rb +31 -0
  124. data/lib/nokogiri/ffi/structs/xml_text_reader.rb +12 -0
  125. data/lib/nokogiri/ffi/structs/xml_xpath_context.rb +37 -0
  126. data/lib/nokogiri/ffi/structs/xml_xpath_object.rb +35 -0
  127. data/lib/nokogiri/ffi/structs/xml_xpath_parser_context.rb +20 -0
  128. data/lib/nokogiri/ffi/structs/xslt_stylesheet.rb +13 -0
  129. data/lib/nokogiri/ffi/xml/attr.rb +41 -0
  130. data/lib/nokogiri/ffi/xml/attribute_decl.rb +27 -0
  131. data/lib/nokogiri/ffi/xml/cdata.rb +19 -0
  132. data/lib/nokogiri/ffi/xml/comment.rb +18 -0
  133. data/lib/nokogiri/ffi/xml/document.rb +135 -0
  134. data/lib/nokogiri/ffi/xml/document_fragment.rb +21 -0
  135. data/lib/nokogiri/ffi/xml/dtd.rb +67 -0
  136. data/lib/nokogiri/ffi/xml/element_content.rb +43 -0
  137. data/lib/nokogiri/ffi/xml/element_decl.rb +19 -0
  138. data/lib/nokogiri/ffi/xml/entity_decl.rb +27 -0
  139. data/lib/nokogiri/ffi/xml/entity_reference.rb +19 -0
  140. data/lib/nokogiri/ffi/xml/namespace.rb +44 -0
  141. data/lib/nokogiri/ffi/xml/node.rb +465 -0
  142. data/lib/nokogiri/ffi/xml/node_set.rb +146 -0
  143. data/lib/nokogiri/ffi/xml/processing_instruction.rb +20 -0
  144. data/lib/nokogiri/ffi/xml/reader.rb +227 -0
  145. data/lib/nokogiri/ffi/xml/relax_ng.rb +85 -0
  146. data/lib/nokogiri/ffi/xml/sax/parser.rb +135 -0
  147. data/lib/nokogiri/ffi/xml/sax/parser_context.rb +67 -0
  148. data/lib/nokogiri/ffi/xml/sax/push_parser.rb +55 -0
  149. data/lib/nokogiri/ffi/xml/schema.rb +92 -0
  150. data/lib/nokogiri/ffi/xml/syntax_error.rb +98 -0
  151. data/lib/nokogiri/ffi/xml/text.rb +18 -0
  152. data/lib/nokogiri/ffi/xml/xpath.rb +19 -0
  153. data/lib/nokogiri/ffi/xml/xpath_context.rb +135 -0
  154. data/lib/nokogiri/ffi/xslt/stylesheet.rb +50 -0
  155. data/lib/nokogiri/html.rb +36 -0
  156. data/lib/nokogiri/html/builder.rb +35 -0
  157. data/lib/nokogiri/html/document.rb +88 -0
  158. data/lib/nokogiri/html/document_fragment.rb +15 -0
  159. data/lib/nokogiri/html/element_description.rb +23 -0
  160. data/lib/nokogiri/html/element_description_defaults.rb +671 -0
  161. data/lib/nokogiri/html/entity_lookup.rb +13 -0
  162. data/lib/nokogiri/html/sax/parser.rb +48 -0
  163. data/lib/nokogiri/html/sax/parser_context.rb +16 -0
  164. data/lib/nokogiri/nokogiri.jar +0 -0
  165. data/lib/nokogiri/syntax_error.rb +4 -0
  166. data/lib/nokogiri/version.rb +33 -0
  167. data/lib/nokogiri/version_warning.rb +11 -0
  168. data/lib/nokogiri/xml.rb +67 -0
  169. data/lib/nokogiri/xml/attr.rb +14 -0
  170. data/lib/nokogiri/xml/attribute_decl.rb +18 -0
  171. data/lib/nokogiri/xml/builder.rb +405 -0
  172. data/lib/nokogiri/xml/cdata.rb +11 -0
  173. data/lib/nokogiri/xml/character_data.rb +7 -0
  174. data/lib/nokogiri/xml/document.rb +163 -0
  175. data/lib/nokogiri/xml/document_fragment.rb +73 -0
  176. data/lib/nokogiri/xml/dtd.rb +11 -0
  177. data/lib/nokogiri/xml/element_content.rb +36 -0
  178. data/lib/nokogiri/xml/element_decl.rb +13 -0
  179. data/lib/nokogiri/xml/entity_decl.rb +15 -0
  180. data/lib/nokogiri/xml/fragment_handler.rb +73 -0
  181. data/lib/nokogiri/xml/namespace.rb +13 -0
  182. data/lib/nokogiri/xml/node.rb +730 -0
  183. data/lib/nokogiri/xml/node/save_options.rb +42 -0
  184. data/lib/nokogiri/xml/node_set.rb +318 -0
  185. data/lib/nokogiri/xml/notation.rb +6 -0
  186. data/lib/nokogiri/xml/parse_options.rb +85 -0
  187. data/lib/nokogiri/xml/pp.rb +2 -0
  188. data/lib/nokogiri/xml/pp/character_data.rb +18 -0
  189. data/lib/nokogiri/xml/pp/node.rb +56 -0
  190. data/lib/nokogiri/xml/processing_instruction.rb +8 -0
  191. data/lib/nokogiri/xml/reader.rb +74 -0
  192. data/lib/nokogiri/xml/relax_ng.rb +32 -0
  193. data/lib/nokogiri/xml/sax.rb +4 -0
  194. data/lib/nokogiri/xml/sax/document.rb +160 -0
  195. data/lib/nokogiri/xml/sax/parser.rb +115 -0
  196. data/lib/nokogiri/xml/sax/parser_context.rb +16 -0
  197. data/lib/nokogiri/xml/sax/push_parser.rb +60 -0
  198. data/lib/nokogiri/xml/schema.rb +61 -0
  199. data/lib/nokogiri/xml/syntax_error.rb +43 -0
  200. data/lib/nokogiri/xml/xpath.rb +10 -0
  201. data/lib/nokogiri/xml/xpath/syntax_error.rb +8 -0
  202. data/lib/nokogiri/xml/xpath_context.rb +16 -0
  203. data/lib/nokogiri/xslt.rb +48 -0
  204. data/lib/nokogiri/xslt/stylesheet.rb +25 -0
  205. data/lib/xercesImpl.jar +0 -0
  206. data/lib/xsd/xmlparser/nokogiri.rb +90 -0
  207. data/tasks/test.rb +100 -0
  208. data/test/css/test_nthiness.rb +159 -0
  209. data/test/css/test_parser.rb +282 -0
  210. data/test/css/test_tokenizer.rb +190 -0
  211. data/test/css/test_xpath_visitor.rb +76 -0
  212. data/test/ffi/test_document.rb +35 -0
  213. data/test/files/2ch.html +108 -0
  214. data/test/files/address_book.rlx +12 -0
  215. data/test/files/address_book.xml +10 -0
  216. data/test/files/bar/bar.xsd +4 -0
  217. data/test/files/dont_hurt_em_why.xml +422 -0
  218. data/test/files/exslt.xml +8 -0
  219. data/test/files/exslt.xslt +35 -0
  220. data/test/files/foo/foo.xsd +4 -0
  221. data/test/files/po.xml +32 -0
  222. data/test/files/po.xsd +66 -0
  223. data/test/files/shift_jis.html +10 -0
  224. data/test/files/shift_jis.xml +5 -0
  225. data/test/files/snuggles.xml +3 -0
  226. data/test/files/staff.dtd +10 -0
  227. data/test/files/staff.xml +59 -0
  228. data/test/files/staff.xslt +32 -0
  229. data/test/files/tlm.html +850 -0
  230. data/test/files/valid_bar.xml +2 -0
  231. data/test/helper.rb +137 -0
  232. data/test/html/sax/test_parser.rb +83 -0
  233. data/test/html/sax/test_parser_context.rb +48 -0
  234. data/test/html/test_builder.rb +164 -0
  235. data/test/html/test_document.rb +385 -0
  236. data/test/html/test_document_encoding.rb +77 -0
  237. data/test/html/test_document_fragment.rb +157 -0
  238. data/test/html/test_element_description.rb +98 -0
  239. data/test/html/test_named_characters.rb +14 -0
  240. data/test/html/test_node.rb +242 -0
  241. data/test/html/test_node_encoding.rb +27 -0
  242. data/test/test_convert_xpath.rb +135 -0
  243. data/test/test_css_cache.rb +45 -0
  244. data/test/test_encoding_handler.rb +46 -0
  245. data/test/test_jruby.rb +40 -0
  246. data/test/test_memory_leak.rb +87 -0
  247. data/test/test_nokogiri.rb +140 -0
  248. data/test/test_reader.rb +358 -0
  249. data/test/test_soap4r_sax.rb +52 -0
  250. data/test/test_xslt_transforms.rb +150 -0
  251. data/test/xml/node/test_save_options.rb +20 -0
  252. data/test/xml/node/test_subclass.rb +44 -0
  253. data/test/xml/sax/test_parser.rb +314 -0
  254. data/test/xml/sax/test_parser_context.rb +63 -0
  255. data/test/xml/sax/test_push_parser.rb +135 -0
  256. data/test/xml/test_attr.rb +38 -0
  257. data/test/xml/test_attribute_decl.rb +90 -0
  258. data/test/xml/test_builder.rb +167 -0
  259. data/test/xml/test_cdata.rb +38 -0
  260. data/test/xml/test_comment.rb +29 -0
  261. data/test/xml/test_document.rb +638 -0
  262. data/test/xml/test_document_encoding.rb +26 -0
  263. data/test/xml/test_document_fragment.rb +149 -0
  264. data/test/xml/test_dtd.rb +92 -0
  265. data/test/xml/test_dtd_encoding.rb +33 -0
  266. data/test/xml/test_element_content.rb +56 -0
  267. data/test/xml/test_element_decl.rb +73 -0
  268. data/test/xml/test_entity_decl.rb +83 -0
  269. data/test/xml/test_entity_reference.rb +21 -0
  270. data/test/xml/test_namespace.rb +70 -0
  271. data/test/xml/test_node.rb +740 -0
  272. data/test/xml/test_node_attributes.rb +34 -0
  273. data/test/xml/test_node_encoding.rb +107 -0
  274. data/test/xml/test_node_reparenting.rb +279 -0
  275. data/test/xml/test_node_set.rb +577 -0
  276. data/test/xml/test_parse_options.rb +52 -0
  277. data/test/xml/test_processing_instruction.rb +30 -0
  278. data/test/xml/test_reader_encoding.rb +126 -0
  279. data/test/xml/test_relax_ng.rb +60 -0
  280. data/test/xml/test_schema.rb +89 -0
  281. data/test/xml/test_syntax_error.rb +12 -0
  282. data/test/xml/test_text.rb +30 -0
  283. data/test/xml/test_unparented_node.rb +381 -0
  284. data/test/xml/test_xpath.rb +169 -0
  285. metadata +477 -0
@@ -0,0 +1,20 @@
1
+ require "helper"
2
+
3
+ module Nokogiri
4
+ module XML
5
+ class Node
6
+ class TestSaveOptions < Nokogiri::TestCase
7
+ SaveOptions.constants.each do |constant|
8
+ class_eval %{
9
+ def test_predicate_#{constant.downcase}
10
+ options = SaveOptions.new(SaveOptions::#{constant})
11
+ assert options.#{constant.downcase}?
12
+
13
+ assert SaveOptions.new.#{constant.downcase}.#{constant.downcase}?
14
+ end
15
+ }
16
+ end
17
+ end
18
+ end
19
+ end
20
+ end
@@ -0,0 +1,44 @@
1
+ require "helper"
2
+
3
+ module Nokogiri
4
+ module XML
5
+ class Node
6
+ class TestSubclass < Nokogiri::TestCase
7
+ {
8
+ Nokogiri::XML::CDATA => 'doc, "foo"',
9
+ Nokogiri::XML::Attr => 'doc, "foo"',
10
+ Nokogiri::XML::Comment => 'doc, "foo"',
11
+ Nokogiri::XML::EntityReference => 'doc, "foo"',
12
+ Nokogiri::XML::ProcessingInstruction => 'doc, "foo", "bar"',
13
+ Nokogiri::XML::DocumentFragment => 'doc',
14
+ Nokogiri::XML::Node => '"foo", doc',
15
+ Nokogiri::XML::Text => '"foo", doc',
16
+ }.each do |klass, constructor|
17
+ class_eval %{
18
+ def test_subclass_#{klass.name.gsub('::', '_')}
19
+ doc = Nokogiri::XML::Document.new
20
+ klass = Class.new(#{klass.name})
21
+ node = klass.new(#{constructor})
22
+ assert_instance_of klass, node
23
+ end
24
+ }
25
+
26
+ class_eval <<-eocode, __FILE__, __LINE__ + 1
27
+ def test_subclass_initialize_#{klass.name.gsub('::', '_')}
28
+ doc = Nokogiri::XML::Document.new
29
+ klass = Class.new(#{klass.name}) do
30
+ attr_accessor :initialized_with
31
+
32
+ def initialize *args
33
+ @initialized_with = args
34
+ end
35
+ end
36
+ node = klass.new(#{constructor}, 1)
37
+ assert_equal [#{constructor}, 1], node.initialized_with
38
+ end
39
+ eocode
40
+ end
41
+ end
42
+ end
43
+ end
44
+ end
@@ -0,0 +1,314 @@
1
+ # -*- coding: utf-8 -*-
2
+
3
+ require "helper"
4
+
5
+ module Nokogiri
6
+ module XML
7
+ module SAX
8
+ class TestParser < Nokogiri::SAX::TestCase
9
+ def setup
10
+ super
11
+ @parser = XML::SAX::Parser.new(Doc.new)
12
+ end
13
+
14
+ def test_parser_context_yielded_io
15
+ doc = Doc.new
16
+ parser = XML::SAX::Parser.new doc
17
+ xml = "<foo a='&amp;b'/>"
18
+
19
+ block_called = false
20
+ parser.parse(StringIO.new(xml)) { |ctx|
21
+ block_called = true
22
+ ctx.replace_entities = true
23
+ }
24
+
25
+ assert block_called
26
+
27
+ assert_equal ['a', '&b'], doc.start_elements.first.last
28
+ end
29
+
30
+ def test_parser_context_yielded_in_memory
31
+ doc = Doc.new
32
+ parser = XML::SAX::Parser.new doc
33
+ xml = "<foo a='&amp;b'/>"
34
+
35
+ block_called = false
36
+ parser.parse(xml) { |ctx|
37
+ block_called = true
38
+ ctx.replace_entities = true
39
+ }
40
+
41
+ assert block_called
42
+
43
+ assert_equal ['a', '&b'], doc.start_elements.first.last
44
+ end
45
+
46
+ def test_xml_decl
47
+ {
48
+ '' => nil,
49
+ '<?xml version="1.0" ?>' => ['1.0'],
50
+ '<?xml version="1.0" encoding="UTF-8" ?>' => ['1.0', 'UTF-8'],
51
+ '<?xml version="1.0" standalone="yes"?>' => ['1.0', 'yes'],
52
+ '<?xml version="1.0" standalone="no"?>' => ['1.0', 'no'],
53
+ }.each do |decl,value|
54
+ parser = XML::SAX::Parser.new(Doc.new)
55
+
56
+ xml = "#{decl}\n<root />"
57
+ parser.parse xml
58
+ assert parser.document.start_document_called, xml
59
+ assert_equal value, parser.document.xmldecls, xml
60
+ end
61
+ end
62
+
63
+ def test_parse_empty
64
+ assert_raises RuntimeError do
65
+ @parser.parse('')
66
+ end
67
+ end
68
+
69
+ def test_namespace_declaration_order_is_saved
70
+ @parser.parse <<-eoxml
71
+ <root xmlns:foo='http://foo.example.com/' xmlns='http://example.com/'>
72
+ <a foo:bar='hello' />
73
+ </root>
74
+ eoxml
75
+ assert_equal 2, @parser.document.start_elements_namespace.length
76
+ el = @parser.document.start_elements_namespace.first
77
+ namespaces = el.last
78
+ assert_equal ['foo', 'http://foo.example.com/'], namespaces.first
79
+ assert_equal [nil, 'http://example.com/'], namespaces.last
80
+ end
81
+
82
+ def test_bad_document_calls_error_handler
83
+ @parser.parse('<foo><bar></foo>')
84
+ assert @parser.document.errors
85
+ assert @parser.document.errors.length > 0
86
+ end
87
+
88
+ def test_namespace_are_super_fun_to_parse
89
+ @parser.parse <<-eoxml
90
+ <root xmlns:foo='http://foo.example.com/'>
91
+ <a foo:bar='hello' />
92
+ <b xmlns:foo='http://bar.example.com/'>
93
+ <a foo:bar='hello' />
94
+ </b>
95
+ <foo:bar>hello world</foo:bar>
96
+ </root>
97
+ eoxml
98
+
99
+ assert @parser.document.start_elements_namespace.length > 0
100
+ el = @parser.document.start_elements_namespace[1]
101
+ assert_equal 'a', el.first
102
+ assert_equal 1, el[1].length
103
+
104
+ attribute = el[1].first
105
+ assert_equal 'bar', attribute.localname
106
+ assert_equal 'foo', attribute.prefix
107
+ assert_equal 'hello', attribute.value
108
+ assert_equal 'http://foo.example.com/', attribute.uri
109
+ end
110
+
111
+ def test_sax_v1_namespace_attribute_declarations
112
+ @parser.parse <<-eoxml
113
+ <root xmlns:foo='http://foo.example.com/' xmlns='http://example.com/'>
114
+ <a foo:bar='hello' />
115
+ <b xmlns:foo='http://bar.example.com/'>
116
+ <a foo:bar='hello' />
117
+ </b>
118
+ <foo:bar>hello world</foo:bar>
119
+ </root>
120
+ eoxml
121
+ assert @parser.document.start_elements.length > 0
122
+ elm = @parser.document.start_elements.first
123
+ assert_equal 'root', elm.first
124
+ assert elm[1].include?(['xmlns:foo', 'http://foo.example.com/'])
125
+ assert elm[1].include?(['xmlns', 'http://example.com/'])
126
+ end
127
+
128
+ def test_sax_v1_namespace_nodes
129
+ @parser.parse <<-eoxml
130
+ <root xmlns:foo='http://foo.example.com/' xmlns='http://example.com/'>
131
+ <a foo:bar='hello' />
132
+ <b xmlns:foo='http://bar.example.com/'>
133
+ <a foo:bar='hello' />
134
+ </b>
135
+ <foo:bar>hello world</foo:bar>
136
+ </root>
137
+ eoxml
138
+ assert_equal 5, @parser.document.start_elements.length
139
+ assert @parser.document.start_elements.map { |se|
140
+ se.first
141
+ }.include?('foo:bar')
142
+ assert @parser.document.end_elements.map { |se|
143
+ se.first
144
+ }.include?('foo:bar')
145
+ end
146
+
147
+ def test_start_is_called_without_namespace
148
+ @parser.parse(<<-eoxml)
149
+ <root xmlns:foo='http://foo.example.com/' xmlns='http://example.com/'>
150
+ <foo:f><bar></foo:f>
151
+ </root>
152
+ eoxml
153
+ assert_equal ['root', 'foo:f', 'bar'],
154
+ @parser.document.start_elements.map { |x| x.first }
155
+ end
156
+
157
+ def test_parser_sets_encoding
158
+ parser = XML::SAX::Parser.new(Doc.new, 'UTF-8')
159
+ assert_equal 'UTF-8', parser.encoding
160
+ end
161
+
162
+ def test_errors_set_after_parsing_bad_dom
163
+ doc = Nokogiri::XML('<foo><bar></foo>')
164
+ assert doc.errors
165
+
166
+ @parser.parse('<foo><bar></foo>')
167
+ assert @parser.document.errors
168
+ assert @parser.document.errors.length > 0
169
+
170
+ if RUBY_VERSION =~ /^1\.9/
171
+ doc.errors.each do |error|
172
+ assert_equal 'UTF-8', error.message.encoding.name
173
+ end
174
+ end
175
+
176
+ assert_equal doc.errors.length, @parser.document.errors.length
177
+ end
178
+
179
+ def test_parse_with_memory_argument
180
+ @parser.parse(File.read(XML_FILE))
181
+ assert(@parser.document.cdata_blocks.length > 0)
182
+ end
183
+
184
+ def test_parse_with_io_argument
185
+ File.open(XML_FILE, 'rb') { |f|
186
+ @parser.parse(f)
187
+ }
188
+ assert(@parser.document.cdata_blocks.length > 0)
189
+ end
190
+
191
+ def test_parse_io
192
+ File.open(XML_FILE, 'rb') { |f|
193
+ @parser.parse_io(f, 'UTF-8')
194
+ }
195
+ assert(@parser.document.cdata_blocks.length > 0)
196
+ if RUBY_VERSION =~ /^1\.9/
197
+ called = false
198
+ @parser.document.start_elements.flatten.each do |thing|
199
+ assert_equal 'UTF-8', thing.encoding.name
200
+ called = true
201
+ end
202
+ assert called
203
+
204
+ called = false
205
+ @parser.document.end_elements.flatten.each do |thing|
206
+ assert_equal 'UTF-8', thing.encoding.name
207
+ called = true
208
+ end
209
+ assert called
210
+
211
+ called = false
212
+ @parser.document.data.each do |thing|
213
+ assert_equal 'UTF-8', thing.encoding.name
214
+ called = true
215
+ end
216
+ assert called
217
+
218
+ called = false
219
+ @parser.document.comments.flatten.each do |thing|
220
+ assert_equal 'UTF-8', thing.encoding.name
221
+ called = true
222
+ end
223
+ assert called
224
+
225
+ called = false
226
+ @parser.document.cdata_blocks.flatten.each do |thing|
227
+ assert_equal 'UTF-8', thing.encoding.name
228
+ called = true
229
+ end
230
+ assert called
231
+ end
232
+ end
233
+
234
+ def test_parse_file
235
+ @parser.parse_file(XML_FILE)
236
+
237
+ assert_raises(ArgumentError) {
238
+ @parser.parse_file(nil)
239
+ }
240
+
241
+ assert_raises(Errno::ENOENT) {
242
+ @parser.parse_file('')
243
+ }
244
+ assert_raises(Errno::EISDIR) {
245
+ @parser.parse_file(File.expand_path(File.dirname(__FILE__)))
246
+ }
247
+ end
248
+
249
+ def test_render_parse_nil_param
250
+ assert_raises(ArgumentError) { @parser.parse_memory(nil) }
251
+ end
252
+
253
+ def test_ctag
254
+ @parser.parse_memory(<<-eoxml)
255
+ <p id="asdfasdf">
256
+ <![CDATA[ This is a comment ]]>
257
+ Paragraph 1
258
+ </p>
259
+ eoxml
260
+ assert_equal [' This is a comment '], @parser.document.cdata_blocks
261
+ end
262
+
263
+ def test_comment
264
+ @parser.parse_memory(<<-eoxml)
265
+ <p id="asdfasdf">
266
+ <!-- This is a comment -->
267
+ Paragraph 1
268
+ </p>
269
+ eoxml
270
+ assert_equal [' This is a comment '], @parser.document.comments
271
+ end
272
+
273
+ def test_characters
274
+ @parser.parse_memory(<<-eoxml)
275
+ <p id="asdfasdf">Paragraph 1</p>
276
+ eoxml
277
+ assert_equal ['Paragraph 1'], @parser.document.data
278
+ end
279
+
280
+ def test_end_document
281
+ @parser.parse_memory(<<-eoxml)
282
+ <p id="asdfasdf">Paragraph 1</p>
283
+ eoxml
284
+ assert @parser.document.end_document_called
285
+ end
286
+
287
+ def test_end_element
288
+ @parser.parse_memory(<<-eoxml)
289
+ <p id="asdfasdf">Paragraph 1</p>
290
+ eoxml
291
+ assert_equal [["p"]],
292
+ @parser.document.end_elements
293
+ end
294
+
295
+ def test_start_element_attrs
296
+ @parser.parse_memory(<<-eoxml)
297
+ <p id="asdfasdf">Paragraph 1</p>
298
+ eoxml
299
+ assert_equal [["p", ["id", "asdfasdf"]]],
300
+ @parser.document.start_elements
301
+ end
302
+
303
+ if Nokogiri.uses_libxml? # JRuby SAXParser only parses well-formed XML documents
304
+ def test_parse_document
305
+ @parser.parse_memory(<<-eoxml)
306
+ <p>Paragraph 1</p>
307
+ <p>Paragraph 2</p>
308
+ eoxml
309
+ end
310
+ end
311
+ end
312
+ end
313
+ end
314
+ end
@@ -0,0 +1,63 @@
1
+ # -*- coding: utf-8 -*-
2
+
3
+ require "helper"
4
+
5
+ module Nokogiri
6
+ module XML
7
+ module SAX
8
+ class TestParserContext < Nokogiri::SAX::TestCase
9
+ def test_replace_entities
10
+ pc = ParserContext.new StringIO.new('<root />'), 'UTF-8'
11
+ pc.replace_entities = false
12
+ assert_equal false, pc.replace_entities
13
+
14
+ pc.replace_entities = true
15
+ assert_equal true, pc.replace_entities
16
+ end
17
+
18
+ def test_from_io
19
+ assert_nothing_raised do
20
+ ParserContext.new StringIO.new('fo'), 'UTF-8'
21
+ end
22
+ end
23
+
24
+ def test_from_string
25
+ assert_nothing_raised do
26
+ ParserContext.new 'blah blah'
27
+ end
28
+ end
29
+
30
+ def test_parse_with
31
+ ctx = ParserContext.new 'blah'
32
+ assert_raises ArgumentError do
33
+ ctx.parse_with nil
34
+ end
35
+ end
36
+
37
+ def test_parse_with_sax_parser
38
+ assert_nothing_raised do
39
+ xml = "<root />"
40
+ ctx = ParserContext.new xml
41
+ parser = Parser.new Doc.new
42
+ ctx.parse_with parser
43
+ end
44
+ end
45
+
46
+ def test_from_file
47
+ assert_nothing_raised do
48
+ ctx = ParserContext.file XML_FILE
49
+ parser = Parser.new Doc.new
50
+ ctx.parse_with parser
51
+ end
52
+ end
53
+
54
+ def test_parse_with_returns_nil
55
+ xml = "<root />"
56
+ ctx = ParserContext.new xml
57
+ parser = Parser.new Doc.new
58
+ assert_nil ctx.parse_with parser
59
+ end
60
+ end
61
+ end
62
+ end
63
+ end
@@ -0,0 +1,135 @@
1
+ require "helper"
2
+
3
+ module Nokogiri
4
+ module XML
5
+ module SAX
6
+ class TestPushParser < Nokogiri::SAX::TestCase
7
+ def setup
8
+ super
9
+ @parser = XML::SAX::PushParser.new(Doc.new)
10
+ end
11
+
12
+ def test_exception
13
+ assert_raises(SyntaxError) do
14
+ @parser << "<foo /><foo />"
15
+ end
16
+
17
+ assert_raises(SyntaxError) do
18
+ @parser << nil
19
+ end
20
+ end
21
+
22
+ def test_end_document_called
23
+ @parser.<<(<<-eoxml)
24
+ <p id="asdfasdf">
25
+ <!-- This is a comment -->
26
+ Paragraph 1
27
+ </p>
28
+ eoxml
29
+ assert ! @parser.document.end_document_called
30
+ @parser.finish
31
+ assert @parser.document.end_document_called
32
+ end
33
+
34
+ def test_start_element
35
+ @parser.<<(<<-eoxml)
36
+ <p id="asdfasdf">
37
+ eoxml
38
+
39
+ assert_equal [["p", ["id", "asdfasdf"]]],
40
+ @parser.document.start_elements
41
+
42
+ @parser.<<(<<-eoxml)
43
+ <!-- This is a comment -->
44
+ Paragraph 1
45
+ </p>
46
+ eoxml
47
+ assert_equal [' This is a comment '], @parser.document.comments
48
+ @parser.finish
49
+ end
50
+
51
+ def test_start_element_ns
52
+ @parser.<<(<<-eoxml)
53
+ <stream:stream xmlns='jabber:client' xmlns:stream='http://etherx.jabber.org/streams' version='1.0' size='large'></stream:stream>
54
+ eoxml
55
+
56
+ assert_equal 1, @parser.document.start_elements_namespace.length
57
+ el = @parser.document.start_elements_namespace.first
58
+
59
+ assert_equal 'stream', el.first
60
+ assert_equal 2, el[1].length
61
+ assert_equal [['version', '1.0'], ['size', 'large']],
62
+ el[1].map { |x| [x.localname, x.value] }
63
+
64
+ assert_equal 'stream', el[2]
65
+ assert_equal 'http://etherx.jabber.org/streams', el[3]
66
+ @parser.finish
67
+ end
68
+
69
+ def test_end_element_ns
70
+ @parser.<<(<<-eoxml)
71
+ <stream:stream xmlns='jabber:client' xmlns:stream='http://etherx.jabber.org/streams' version='1.0'></stream:stream>
72
+ eoxml
73
+
74
+ assert_equal [['stream', 'stream', 'http://etherx.jabber.org/streams']],
75
+ @parser.document.end_elements_namespace
76
+ @parser.finish
77
+ end
78
+
79
+ def test_chevron_partial_xml
80
+ @parser.<<(<<-eoxml)
81
+ <p id="asdfasdf">
82
+ eoxml
83
+
84
+ @parser.<<(<<-eoxml)
85
+ <!-- This is a comment -->
86
+ Paragraph 1
87
+ </p>
88
+ eoxml
89
+ assert_equal [' This is a comment '], @parser.document.comments
90
+ @parser.finish
91
+ end
92
+
93
+ def test_chevron
94
+ @parser.<<(<<-eoxml)
95
+ <p id="asdfasdf">
96
+ <!-- This is a comment -->
97
+ Paragraph 1
98
+ </p>
99
+ eoxml
100
+ @parser.finish
101
+ assert_equal [' This is a comment '], @parser.document.comments
102
+ end
103
+
104
+ def test_default_options
105
+ assert_equal 0, @parser.options
106
+ end
107
+
108
+ def test_recover
109
+ @parser.options |= XML::ParseOptions::RECOVER
110
+ @parser.<<(<<-eoxml)
111
+ <p>
112
+ Foo
113
+ <bar>
114
+ Bar
115
+ </p>
116
+ eoxml
117
+ @parser.finish
118
+ assert(@parser.document.errors.size >= 1)
119
+ assert_equal [["p", []], ["bar", []]], @parser.document.start_elements
120
+ assert_equal "FooBar", @parser.document.data.to_s.gsub(/\s/, '')
121
+ end
122
+
123
+ def test_broken_encoding
124
+ @parser.options |= XML::ParseOptions::RECOVER
125
+ # This is ISO_8859-1:
126
+ @parser.<< "<?xml version='1.0' encoding='UTF-8'?><r>Gau\337</r>"
127
+ @parser.finish
128
+ assert(@parser.document.errors.size >= 1)
129
+ assert_equal "Gau\337", @parser.document.data.to_s
130
+ assert_equal [["r"]], @parser.document.end_elements
131
+ end
132
+ end
133
+ end
134
+ end
135
+ end