nokogiri 1.4.3.1-java → 1.5.0-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 (231) hide show
  1. data/.gemtest +0 -0
  2. data/CHANGELOG.ja.rdoc +113 -0
  3. data/CHANGELOG.rdoc +113 -1
  4. data/Manifest.txt +72 -68
  5. data/README.ja.rdoc +4 -4
  6. data/README.rdoc +31 -7
  7. data/Rakefile +110 -132
  8. data/bin/nokogiri +7 -3
  9. data/ext/java/nokogiri/EncodingHandler.java +124 -0
  10. data/ext/java/nokogiri/HtmlDocument.java +119 -0
  11. data/ext/java/nokogiri/HtmlElementDescription.java +145 -0
  12. data/ext/java/nokogiri/HtmlEntityLookup.java +79 -0
  13. data/ext/java/nokogiri/HtmlSaxParserContext.java +259 -0
  14. data/ext/java/nokogiri/NokogiriService.java +590 -0
  15. data/ext/java/nokogiri/XmlAttr.java +180 -0
  16. data/ext/java/nokogiri/XmlAttributeDecl.java +130 -0
  17. data/ext/java/nokogiri/XmlCdata.java +84 -0
  18. data/ext/java/nokogiri/XmlComment.java +86 -0
  19. data/ext/java/nokogiri/XmlDocument.java +519 -0
  20. data/ext/java/nokogiri/XmlDocumentFragment.java +223 -0
  21. data/ext/java/nokogiri/XmlDtd.java +469 -0
  22. data/ext/java/nokogiri/XmlElement.java +195 -0
  23. data/ext/java/nokogiri/XmlElementContent.java +382 -0
  24. data/ext/java/nokogiri/XmlElementDecl.java +152 -0
  25. data/ext/java/nokogiri/XmlEntityDecl.java +162 -0
  26. data/ext/java/nokogiri/XmlEntityReference.java +97 -0
  27. data/ext/java/nokogiri/XmlNamespace.java +183 -0
  28. data/ext/java/nokogiri/XmlNode.java +1378 -0
  29. data/ext/java/nokogiri/XmlNodeSet.java +267 -0
  30. data/ext/java/nokogiri/XmlProcessingInstruction.java +99 -0
  31. data/ext/java/nokogiri/XmlReader.java +408 -0
  32. data/ext/java/nokogiri/XmlRelaxng.java +144 -0
  33. data/ext/java/nokogiri/XmlSaxParserContext.java +367 -0
  34. data/ext/java/nokogiri/XmlSaxPushParser.java +184 -0
  35. data/ext/java/nokogiri/XmlSchema.java +324 -0
  36. data/ext/java/nokogiri/XmlSyntaxError.java +119 -0
  37. data/ext/java/nokogiri/XmlText.java +119 -0
  38. data/ext/java/nokogiri/XmlXpathContext.java +199 -0
  39. data/ext/java/nokogiri/XsltStylesheet.java +197 -0
  40. data/ext/java/nokogiri/internals/HtmlDomParserContext.java +204 -0
  41. data/ext/java/nokogiri/internals/NokogiriDocumentCache.java +73 -0
  42. data/ext/java/nokogiri/internals/NokogiriErrorHandler.java +86 -0
  43. data/ext/java/nokogiri/internals/NokogiriHandler.java +327 -0
  44. data/ext/java/nokogiri/internals/NokogiriHelpers.java +639 -0
  45. data/ext/java/nokogiri/internals/NokogiriNamespaceCache.java +167 -0
  46. data/ext/java/nokogiri/internals/NokogiriNamespaceContext.java +130 -0
  47. data/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler.java +74 -0
  48. data/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler4NekoHtml.java +121 -0
  49. data/ext/java/nokogiri/internals/NokogiriStrictErrorHandler.java +79 -0
  50. data/ext/java/nokogiri/internals/NokogiriXPathFunction.java +141 -0
  51. data/ext/java/nokogiri/internals/NokogiriXPathFunctionResolver.java +73 -0
  52. data/ext/java/nokogiri/internals/NokogiriXPathVariableResolver.java +67 -0
  53. data/ext/java/nokogiri/internals/NokogiriXsltErrorListener.java +86 -0
  54. data/ext/java/nokogiri/internals/ParserContext.java +276 -0
  55. data/ext/java/nokogiri/internals/PushInputStream.java +411 -0
  56. data/ext/java/nokogiri/internals/ReaderNode.java +531 -0
  57. data/ext/java/nokogiri/internals/SaveContextVisitor.java +567 -0
  58. data/ext/java/nokogiri/internals/SchemaErrorHandler.java +76 -0
  59. data/ext/java/nokogiri/internals/XmlDeclHandler.java +42 -0
  60. data/ext/java/nokogiri/internals/XmlDomParser.java +76 -0
  61. data/ext/java/nokogiri/internals/XmlDomParserContext.java +244 -0
  62. data/ext/java/nokogiri/internals/XmlSaxParser.java +65 -0
  63. data/ext/java/nokogiri/internals/XsltExtensionFunction.java +72 -0
  64. data/ext/nokogiri/depend +358 -32
  65. data/ext/nokogiri/extconf.rb +10 -6
  66. data/ext/nokogiri/nokogiri.c +23 -3
  67. data/ext/nokogiri/nokogiri.h +7 -2
  68. data/ext/nokogiri/xml_document.c +9 -0
  69. data/ext/nokogiri/xml_dtd.c +2 -2
  70. data/ext/nokogiri/xml_io.c +32 -7
  71. data/ext/nokogiri/xml_node.c +45 -25
  72. data/ext/nokogiri/xml_node_set.c +1 -1
  73. data/ext/nokogiri/xml_relax_ng.c +0 -7
  74. data/ext/nokogiri/xml_sax_parser.c +14 -7
  75. data/ext/nokogiri/xml_sax_parser_context.c +40 -0
  76. data/ext/nokogiri/xml_xpath_context.c +33 -2
  77. data/ext/nokogiri/xslt_stylesheet.c +128 -6
  78. data/lib/isorelax.jar +0 -0
  79. data/lib/jing.jar +0 -0
  80. data/lib/nekodtd.jar +0 -0
  81. data/lib/nekohtml.jar +0 -0
  82. data/lib/nokogiri/css/parser.rb +665 -70
  83. data/lib/nokogiri/css/parser.y +3 -1
  84. data/lib/nokogiri/css/parser_extras.rb +91 -0
  85. data/lib/nokogiri/css/tokenizer.rb +148 -3
  86. data/lib/nokogiri/css/tokenizer.rex +1 -1
  87. data/lib/nokogiri/css/xpath_visitor.rb +15 -7
  88. data/lib/nokogiri/css.rb +5 -3
  89. data/lib/nokogiri/decorators/slop.rb +5 -3
  90. data/lib/nokogiri/html/document.rb +142 -19
  91. data/lib/nokogiri/html/document_fragment.rb +19 -17
  92. data/lib/nokogiri/html/element_description_defaults.rb +671 -0
  93. data/lib/nokogiri/html/sax/parser.rb +6 -2
  94. data/lib/nokogiri/html.rb +1 -0
  95. data/lib/nokogiri/nokogiri.jar +0 -0
  96. data/lib/nokogiri/version.rb +76 -26
  97. data/lib/nokogiri/xml/attribute_decl.rb +1 -1
  98. data/lib/nokogiri/xml/builder.rb +7 -0
  99. data/lib/nokogiri/xml/document.rb +43 -2
  100. data/lib/nokogiri/xml/document_fragment.rb +16 -2
  101. data/lib/nokogiri/xml/dtd.rb +12 -1
  102. data/lib/nokogiri/xml/element_decl.rb +1 -1
  103. data/lib/nokogiri/xml/entity_decl.rb +1 -1
  104. data/lib/nokogiri/xml/node/save_options.rb +20 -1
  105. data/lib/nokogiri/xml/node.rb +198 -78
  106. data/lib/nokogiri/xml/node_set.rb +10 -3
  107. data/lib/nokogiri/xml/parse_options.rb +8 -0
  108. data/lib/nokogiri/xml/reader.rb +42 -6
  109. data/lib/nokogiri/xml/sax/document.rb +4 -2
  110. data/lib/nokogiri/xml/schema.rb +7 -1
  111. data/lib/nokogiri/xslt/stylesheet.rb +1 -1
  112. data/lib/nokogiri/xslt.rb +9 -5
  113. data/lib/nokogiri.rb +19 -25
  114. data/lib/xercesImpl.jar +0 -0
  115. data/nokogiri_help_responses.md +40 -0
  116. data/tasks/cross_compile.rb +130 -136
  117. data/tasks/nokogiri.org.rb +18 -0
  118. data/tasks/test.rb +2 -2
  119. data/test/css/test_parser.rb +29 -18
  120. data/test/css/test_tokenizer.rb +8 -0
  121. data/test/decorators/test_slop.rb +16 -0
  122. data/test/files/encoding.html +82 -0
  123. data/test/files/encoding.xhtml +84 -0
  124. data/test/files/metacharset.html +10 -0
  125. data/test/files/noencoding.html +47 -0
  126. data/test/helper.rb +5 -1
  127. data/test/html/sax/test_parser.rb +65 -3
  128. data/test/html/test_document.rb +75 -1
  129. data/test/html/test_document_encoding.rb +61 -0
  130. data/test/html/test_document_fragment.rb +50 -5
  131. data/test/html/test_element_description.rb +4 -2
  132. data/test/html/test_node.rb +9 -0
  133. data/test/test_memory_leak.rb +20 -35
  134. data/test/test_nokogiri.rb +14 -20
  135. data/test/test_reader.rb +23 -6
  136. data/test/test_xslt_transforms.rb +6 -2
  137. data/test/xml/node/test_save_options.rb +10 -2
  138. data/test/xml/sax/test_parser.rb +39 -8
  139. data/test/xml/sax/test_parser_context.rb +50 -0
  140. data/test/xml/sax/test_push_parser.rb +18 -1
  141. data/test/xml/test_attribute_decl.rb +7 -3
  142. data/test/xml/test_builder.rb +17 -0
  143. data/test/xml/test_document.rb +34 -5
  144. data/test/xml/test_document_fragment.rb +14 -2
  145. data/test/xml/test_dtd.rb +28 -3
  146. data/test/xml/test_element_content.rb +1 -1
  147. data/test/xml/test_element_decl.rb +1 -1
  148. data/test/xml/test_entity_decl.rb +12 -10
  149. data/test/xml/test_namespace.rb +7 -5
  150. data/test/xml/test_node.rb +65 -13
  151. data/test/xml/test_node_reparenting.rb +72 -31
  152. data/test/xml/test_node_set.rb +57 -0
  153. data/test/xml/test_schema.rb +5 -0
  154. data/test/xml/test_xpath.rb +32 -0
  155. data/test/xslt/test_custom_functions.rb +94 -0
  156. data/test/xslt/test_exception_handling.rb +37 -0
  157. metadata +512 -517
  158. data/deps.rip +0 -5
  159. data/ext/nokogiri/libcharset-1.dll +0 -0
  160. data/ext/nokogiri/libexslt.dll +0 -0
  161. data/ext/nokogiri/libiconv-2.dll +0 -0
  162. data/ext/nokogiri/libxml2.dll +0 -0
  163. data/ext/nokogiri/libxslt.dll +0 -0
  164. data/ext/nokogiri/zlib1.dll +0 -0
  165. data/lib/nokogiri/css/generated_parser.rb +0 -676
  166. data/lib/nokogiri/css/generated_tokenizer.rb +0 -146
  167. data/lib/nokogiri/ffi/encoding_handler.rb +0 -42
  168. data/lib/nokogiri/ffi/html/document.rb +0 -28
  169. data/lib/nokogiri/ffi/html/element_description.rb +0 -81
  170. data/lib/nokogiri/ffi/html/entity_lookup.rb +0 -16
  171. data/lib/nokogiri/ffi/html/sax/parser_context.rb +0 -38
  172. data/lib/nokogiri/ffi/io_callbacks.rb +0 -42
  173. data/lib/nokogiri/ffi/libxml.rb +0 -411
  174. data/lib/nokogiri/ffi/structs/common_node.rb +0 -38
  175. data/lib/nokogiri/ffi/structs/html_elem_desc.rb +0 -24
  176. data/lib/nokogiri/ffi/structs/html_entity_desc.rb +0 -13
  177. data/lib/nokogiri/ffi/structs/xml_alloc.rb +0 -16
  178. data/lib/nokogiri/ffi/structs/xml_attr.rb +0 -19
  179. data/lib/nokogiri/ffi/structs/xml_attribute.rb +0 -27
  180. data/lib/nokogiri/ffi/structs/xml_buffer.rb +0 -16
  181. data/lib/nokogiri/ffi/structs/xml_char_encoding_handler.rb +0 -11
  182. data/lib/nokogiri/ffi/structs/xml_document.rb +0 -117
  183. data/lib/nokogiri/ffi/structs/xml_dtd.rb +0 -28
  184. data/lib/nokogiri/ffi/structs/xml_element.rb +0 -26
  185. data/lib/nokogiri/ffi/structs/xml_element_content.rb +0 -17
  186. data/lib/nokogiri/ffi/structs/xml_entity.rb +0 -32
  187. data/lib/nokogiri/ffi/structs/xml_enumeration.rb +0 -12
  188. data/lib/nokogiri/ffi/structs/xml_node.rb +0 -28
  189. data/lib/nokogiri/ffi/structs/xml_node_set.rb +0 -53
  190. data/lib/nokogiri/ffi/structs/xml_notation.rb +0 -11
  191. data/lib/nokogiri/ffi/structs/xml_ns.rb +0 -15
  192. data/lib/nokogiri/ffi/structs/xml_parser_context.rb +0 -19
  193. data/lib/nokogiri/ffi/structs/xml_relax_ng.rb +0 -14
  194. data/lib/nokogiri/ffi/structs/xml_sax_handler.rb +0 -51
  195. data/lib/nokogiri/ffi/structs/xml_sax_push_parser_context.rb +0 -124
  196. data/lib/nokogiri/ffi/structs/xml_schema.rb +0 -13
  197. data/lib/nokogiri/ffi/structs/xml_syntax_error.rb +0 -31
  198. data/lib/nokogiri/ffi/structs/xml_text_reader.rb +0 -12
  199. data/lib/nokogiri/ffi/structs/xml_xpath_context.rb +0 -38
  200. data/lib/nokogiri/ffi/structs/xml_xpath_object.rb +0 -35
  201. data/lib/nokogiri/ffi/structs/xml_xpath_parser_context.rb +0 -20
  202. data/lib/nokogiri/ffi/structs/xslt_stylesheet.rb +0 -13
  203. data/lib/nokogiri/ffi/weak_bucket.rb +0 -40
  204. data/lib/nokogiri/ffi/xml/attr.rb +0 -41
  205. data/lib/nokogiri/ffi/xml/attribute_decl.rb +0 -27
  206. data/lib/nokogiri/ffi/xml/cdata.rb +0 -19
  207. data/lib/nokogiri/ffi/xml/comment.rb +0 -18
  208. data/lib/nokogiri/ffi/xml/document.rb +0 -166
  209. data/lib/nokogiri/ffi/xml/document_fragment.rb +0 -21
  210. data/lib/nokogiri/ffi/xml/dtd.rb +0 -67
  211. data/lib/nokogiri/ffi/xml/element_content.rb +0 -43
  212. data/lib/nokogiri/ffi/xml/element_decl.rb +0 -19
  213. data/lib/nokogiri/ffi/xml/entity_decl.rb +0 -36
  214. data/lib/nokogiri/ffi/xml/entity_reference.rb +0 -19
  215. data/lib/nokogiri/ffi/xml/namespace.rb +0 -44
  216. data/lib/nokogiri/ffi/xml/node.rb +0 -554
  217. data/lib/nokogiri/ffi/xml/node_set.rb +0 -149
  218. data/lib/nokogiri/ffi/xml/processing_instruction.rb +0 -20
  219. data/lib/nokogiri/ffi/xml/reader.rb +0 -236
  220. data/lib/nokogiri/ffi/xml/relax_ng.rb +0 -85
  221. data/lib/nokogiri/ffi/xml/sax/parser.rb +0 -135
  222. data/lib/nokogiri/ffi/xml/sax/parser_context.rb +0 -67
  223. data/lib/nokogiri/ffi/xml/sax/push_parser.rb +0 -51
  224. data/lib/nokogiri/ffi/xml/schema.rb +0 -109
  225. data/lib/nokogiri/ffi/xml/syntax_error.rb +0 -98
  226. data/lib/nokogiri/ffi/xml/text.rb +0 -18
  227. data/lib/nokogiri/ffi/xml/xpath.rb +0 -9
  228. data/lib/nokogiri/ffi/xml/xpath_context.rb +0 -148
  229. data/lib/nokogiri/ffi/xslt/stylesheet.rb +0 -53
  230. data/lib/nokogiri/version_warning.rb +0 -14
  231. data/test/ffi/test_document.rb +0 -35
data/Rakefile CHANGED
@@ -1,140 +1,126 @@
1
1
  # -*- ruby -*-
2
-
3
2
  require 'rubygems'
4
- gem 'hoe', '>= 2.1.0'
3
+
4
+ gem 'hoe'
5
5
  require 'hoe'
6
+ Hoe.plugin :debugging
7
+ Hoe.plugin :git
8
+ Hoe.plugin :gemspec
9
+ Hoe.plugin :bundler
10
+ Hoe.add_include_dirs '.' # for ruby 1.9.2
6
11
 
7
- windows = RUBY_PLATFORM =~ /(mswin|mingw)/i
8
- java = RUBY_PLATFORM =~ /java/
12
+ GENERATED_PARSER = "lib/nokogiri/css/parser.rb"
13
+ GENERATED_TOKENIZER = "lib/nokogiri/css/tokenizer.rb"
14
+ CROSS_DIR = File.join(File.dirname(__FILE__), 'ports')
9
15
 
10
- GENERATED_PARSER = "lib/nokogiri/css/generated_parser.rb"
11
- GENERATED_TOKENIZER = "lib/nokogiri/css/generated_tokenizer.rb"
12
- CROSS_DIR = File.join(File.dirname(__FILE__), 'tmp', 'cross')
16
+ def java?
17
+ !! (RUBY_PLATFORM =~ /java/)
18
+ end
13
19
 
14
- # Make sure hoe-debugging is installed
15
- Hoe.plugin :debugging
20
+ require 'tasks/nokogiri.org'
16
21
 
17
22
  HOE = Hoe.spec 'nokogiri' do
18
- developer('Aaron Patterson', 'aaronp@rubyforge.org')
19
- developer('Mike Dalessio', 'mike.dalessio@gmail.com')
20
- self.readme_file = ['README', ENV['HLANG'], 'rdoc'].compact.join('.')
21
- self.history_file = ['CHANGELOG', ENV['HLANG'], 'rdoc'].compact.join('.')
22
- self.extra_rdoc_files = FileList['*.rdoc','ext/nokogiri/*.c']
23
- self.clean_globs = [
23
+ developer 'Aaron Patterson', 'aaronp@rubyforge.org'
24
+ developer 'Mike Dalessio', 'mike.dalessio@gmail.com'
25
+ developer 'Yoko Harada', 'yokolet@gmail.com'
26
+
27
+ self.readme_file = ['README', ENV['HLANG'], 'rdoc'].compact.join('.')
28
+ self.history_file = ['CHANGELOG', ENV['HLANG'], 'rdoc'].compact.join('.')
29
+
30
+ self.extra_rdoc_files = FileList['*.rdoc','ext/nokogiri/*.c']
31
+
32
+ self.clean_globs += [
33
+ 'nokogiri.gemspec',
24
34
  'lib/nokogiri/*.{o,so,bundle,a,log,dll}',
35
+ 'lib/nokogiri/nokogiri.{so,dylib,rb,bundle}',
25
36
  'lib/nokogiri/nokogiri.rb',
26
37
  'lib/nokogiri/1.{8,9}',
27
38
  GENERATED_PARSER,
28
- GENERATED_TOKENIZER,
29
- 'cross',
39
+ GENERATED_TOKENIZER
30
40
  ]
31
41
 
32
- %w{ racc rexical rake-compiler }.each do |dep|
33
- self.extra_dev_deps << [dep, '>= 0']
34
- end
35
- self.extra_dev_deps << ["minitest", ">= 1.6.0"]
42
+ self.extra_dev_deps += [
43
+ ["racc", ">= 1.4.6"],
44
+ ["rexical", ">= 1.0.5"],
45
+ ["rake-compiler", ">= 0.7.9"],
46
+ ["minitest", "~> 2.2.2"],
47
+ ["mini_portile", ">= 0.2.2"],
48
+ ["hoe-debugging", ">= 0"],
49
+ ["hoe-git", ">= 0"],
50
+ ["hoe-gemspec", ">= 0"],
51
+ ["hoe-bundler", ">= 0"]
52
+ ]
36
53
 
37
- self.spec_extras = { :extensions => ["ext/nokogiri/extconf.rb"] }
54
+ if java?
55
+ self.spec_extras = { :platform => 'java' }
56
+ else
57
+ self.spec_extras = {
58
+ :extensions => ["ext/nokogiri/extconf.rb"],
59
+ :required_ruby_version => '>= 1.8.7'
60
+ }
61
+ end
38
62
 
39
63
  self.testlib = :minitest
40
64
  end
41
- Hoe.add_include_dirs '.'
42
-
43
- task :ws_docs do
44
- title = "#{HOE.name}-#{HOE.version} Documentation"
45
-
46
- options = []
47
- options << "--main=#{HOE.readme_file}"
48
- options << '--format=activerecord'
49
- options << '--threads=1'
50
- options << "--title=#{title.inspect}"
51
-
52
- options += HOE.spec.require_paths
53
- options += HOE.spec.extra_rdoc_files
54
- require 'rdoc/rdoc'
55
- ENV['RAILS_ROOT'] ||= File.expand_path(File.join('..', 'nokogiri_ws'))
56
- RDoc::RDoc.new.document options
57
- end
58
65
 
59
- unless java
60
- gem 'rake-compiler', '>= 0.4.1'
61
- require "rake/extensiontask"
66
+ # ----------------------------------------
67
+
68
+ if java?
69
+ # TODO: clean this section up.
70
+ require "rake/javaextensiontask"
71
+ Rake::JavaExtensionTask.new("nokogiri", HOE.spec) do |ext|
72
+ jruby_home = RbConfig::CONFIG['prefix']
73
+ ext.ext_dir = 'ext/java'
74
+ ext.lib_dir = 'lib/nokogiri'
75
+ jars = ["#{jruby_home}/lib/jruby.jar"] + FileList['lib/*.jar']
76
+ ext.classpath = jars.map { |x| File.expand_path x }.join ':'
77
+ end
62
78
 
63
- RET = Rake::ExtensionTask.new("nokogiri", HOE.spec) do |ext|
64
- ext.lib_dir = File.join(*['lib', 'nokogiri', ENV['FAT_DIR']].compact)
79
+ gem_build_path = File.join 'pkg', HOE.spec.full_name
65
80
 
81
+ task gem_build_path => [:compile] do
82
+ cp 'lib/nokogiri/nokogiri.jar', File.join(gem_build_path, 'lib', 'nokogiri')
83
+ HOE.spec.files += ['lib/nokogiri/nokogiri.jar']
84
+ end
85
+ else
86
+ require 'tasks/cross_compile'
87
+ require "rake/extensiontask"
88
+ Rake::ExtensionTask.new("nokogiri", HOE.spec) do |ext|
89
+ ext.lib_dir = File.join(*['lib', 'nokogiri', ENV['FAT_DIR']].compact)
66
90
  ext.config_options << ENV['EXTOPTS']
67
- ext.cross_compile = true
68
- ext.cross_platform = 'i386-mingw32'
69
- ext.cross_config_options <<
70
- "--with-xml2-include=#{File.join(CROSS_DIR, 'include', 'libxml2')}"
71
- ext.cross_config_options <<
72
- "--with-xml2-lib=#{File.join(CROSS_DIR, 'lib')}"
73
- ext.cross_config_options << "--with-iconv-dir=#{CROSS_DIR}"
74
- ext.cross_config_options << "--with-xslt-dir=#{CROSS_DIR}"
91
+ ext.cross_compile = true
92
+ ext.cross_platform = ["x86-mswin32-60", "x86-mingw32"]
93
+ ext.cross_config_options << "--with-xml2-include=#{File.join($recipes[:libxml2].path, 'include', 'libxml2')}"
94
+ ext.cross_config_options << "--with-xml2-lib=#{File.join($recipes[:libxml2].path, 'lib')}"
95
+ ext.cross_config_options << "--with-iconv-dir=#{$recipes[:libiconv].path}"
96
+ ext.cross_config_options << "--with-xslt-dir=#{$recipes[:libxslt].path}"
75
97
  ext.cross_config_options << "--with-zlib-dir=#{CROSS_DIR}"
76
98
  end
77
99
  end
78
100
 
79
- namespace :gem do
80
- namespace :dev do
81
- task :spec => [ GENERATED_PARSER, GENERATED_TOKENIZER ] do
82
- File.open("#{HOE.name}.gemspec", 'w') do |f|
83
- HOE.spec.version = "#{HOE.version}.#{Time.now.strftime("%Y%m%d%H%M%S")}"
84
- f.write(HOE.spec.to_ruby)
85
- end
86
- end
87
- end
88
-
89
- desc "Build a gem targetted for JRuby"
90
- task :jruby => ['gem:jruby:spec'] do
91
- system "gem build nokogiri.gemspec"
92
- FileUtils.mkdir_p "pkg"
93
- FileUtils.mv Dir.glob("nokogiri*-java.gem"), "pkg"
94
- end
95
-
96
- namespace :jruby do
97
- task :spec => [GENERATED_PARSER, GENERATED_TOKENIZER] do
98
- File.open("#{HOE.name}.gemspec", 'w') do |f|
99
- HOE.spec.platform = 'java'
100
- HOE.spec.files << GENERATED_PARSER
101
- HOE.spec.files << GENERATED_TOKENIZER
102
- HOE.spec.files += Dir["ext/nokogiri/*.dll"]
103
- HOE.spec.extensions = []
104
- HOE.spec.add_dependency 'weakling', '>= 0.0.3'
105
- f.write(HOE.spec.to_ruby)
106
- end
107
- end
108
- end
101
+ # ----------------------------------------
109
102
 
110
- task :spec => ['gem:dev:spec']
111
- end
103
+ desc "Generate css/parser.rb and css/tokenizer.rex"
104
+ task 'generate' => [GENERATED_PARSER, GENERATED_TOKENIZER]
105
+ task 'gem:spec' => 'generate' if Rake::Task.task_defined?("gem:spec")
112
106
 
113
107
  file GENERATED_PARSER => "lib/nokogiri/css/parser.y" do |t|
114
- begin
115
- racc = Config::CONFIG['target_os'] =~ /mswin32/ ? '' : `which racc`.strip
116
- racc = "#{::Config::CONFIG['bindir']}/racc" if racc.empty?
117
- sh "#{racc} -l -o #{t.name} #{t.prerequisites.first}"
118
- rescue
119
- abort "need racc, sudo gem install racc"
120
- end
108
+ racc = RbConfig::CONFIG['target_os'] =~ /mswin32/ ? '' : `which racc`.strip
109
+ racc = "#{::RbConfig::CONFIG['bindir']}/racc" if racc.empty?
110
+ sh "#{racc} -l -o #{t.name} #{t.prerequisites.first}"
121
111
  end
122
112
 
123
113
  file GENERATED_TOKENIZER => "lib/nokogiri/css/tokenizer.rex" do |t|
124
- begin
125
- sh "rex --independent -o #{t.name} #{t.prerequisites.first}"
126
- rescue
127
- abort "need rexical, sudo gem install rexical"
128
- end
114
+ sh "rex --independent -o #{t.name} #{t.prerequisites.first}"
129
115
  end
130
116
 
131
- require 'tasks/test'
132
- begin
133
- require 'tasks/cross_compile' unless java
134
- rescue RuntimeError => e
135
- warn "WARNING: Could not perform some cross-compiling: #{e}"
117
+ [:compile, :check_manifest].each do |task_name|
118
+ Rake::Task[task_name].prerequisites << GENERATED_PARSER
119
+ Rake::Task[task_name].prerequisites << GENERATED_TOKENIZER
136
120
  end
137
121
 
122
+ # ----------------------------------------
123
+
138
124
  desc "set environment variables to build and/or test with debug options"
139
125
  task :debug do
140
126
  ENV['NOKOGIRI_DEBUG'] = "true"
@@ -142,45 +128,37 @@ task :debug do
142
128
  ENV['CFLAGS'] += " -DDEBUG"
143
129
  end
144
130
 
145
- # required_ruby_version
146
-
147
- # Only do this on unix, since we can't build on windows
148
- unless windows || java || ENV['NOKOGIRI_FFI']
149
- [:compile, :check_manifest].each do |task_name|
150
- Rake::Task[task_name].prerequisites << GENERATED_PARSER
151
- Rake::Task[task_name].prerequisites << GENERATED_TOKENIZER
152
- end
131
+ require 'tasks/test'
153
132
 
154
- Rake::Task[:test].prerequisites << :compile
155
- if Hoe.plugins.include?(:debugging)
156
- ['valgrind', 'valgrind:mem', 'valgrind:mem0'].each do |task_name|
157
- Rake::Task["test:#{task_name}"].prerequisites << :compile
158
- end
159
- end
160
- else
161
- [:test, :check_manifest].each do |task_name|
162
- if Rake::Task[task_name]
163
- Rake::Task[task_name].prerequisites << GENERATED_PARSER
164
- Rake::Task[task_name].prerequisites << GENERATED_TOKENIZER
165
- end
133
+ Rake::Task[:test].prerequisites << :compile
134
+ Rake::Task[:test].prerequisites << :check_extra_deps unless java?
135
+ if Hoe.plugins.include?(:debugging)
136
+ ['valgrind', 'valgrind:mem', 'valgrind:mem0'].each do |task_name|
137
+ Rake::Task["test:#{task_name}"].prerequisites << :compile
166
138
  end
167
139
  end
168
140
 
169
- namespace :install do
170
- desc "Install rex and racc for development"
171
- task :deps => %w(rexical racc)
141
+ # ----------------------------------------
172
142
 
173
- task :racc do |t|
174
- sh "sudo gem install racc"
175
- end
143
+ desc "build a windows gem without all the ceremony."
144
+ task "gem:windows" do
145
+ rake_compiler_config = YAML.load_file("#{ENV['HOME']}/.rake-compiler/config.yml")
176
146
 
177
- task :rexical do
178
- sh "sudo gem install rexical"
147
+ # check that rake-compiler config contains the right patchlevels of 1.8.6 and 1.9.1. see #279.
148
+ ["1.8.6-p383", "1.9.1-p243"].each do |version|
149
+ majmin, patchlevel = version.split("-")
150
+ rbconfig = "rbconfig-#{majmin}"
151
+ unless rake_compiler_config.key?(rbconfig) && rake_compiler_config[rbconfig] =~ /-#{patchlevel}/
152
+ raise "rake-compiler '#{rbconfig}' not #{patchlevel}. try running 'env --unset=HOST rake-compiler cross-ruby VERSION=#{version}'"
153
+ end
179
154
  end
180
- end
181
155
 
182
- namespace :rip do
183
- task :install => [GENERATED_TOKENIZER, GENERATED_PARSER]
156
+ # verify that --export-all is in the 1.9.1 rbconfig. see #279,#374,#375.
157
+ rbconfig_191 = rake_compiler_config["rbconfig-1.9.1"]
158
+ raise "rbconfig #{rbconfig_191} needs --export-all in its DLDFLAGS value" if File.read(rbconfig_191).grep(/CONFIG\["DLDFLAGS"\].*--export-all/).empty?
159
+
160
+ pkg_config_path = [:libxslt, :libxml2].collect { |pkg| File.join($recipes[pkg].path, "lib/pkgconfig") }.join(":")
161
+ sh("env PKG_CONFIG_PATH=#{pkg_config_path} RUBY_CC_VERSION=1.8.6:1.9.1 rake cross native gem") || raise("build failed!")
184
162
  end
185
163
 
186
164
  # vim: syntax=Ruby
data/bin/nokogiri CHANGED
@@ -7,6 +7,7 @@ require 'rubygems'
7
7
  require 'nokogiri'
8
8
 
9
9
  parse_class = Nokogiri
10
+ encoding = nil
10
11
 
11
12
  opts = OptionParser.new do |opts|
12
13
  opts.banner = "Nokogiri: an HTML, XML, SAX, and Reader parser"
@@ -22,14 +23,17 @@ opts = OptionParser.new do |opts|
22
23
  parse_class = {:xml => Nokogiri::XML, :html => Nokogiri::HTML}[v]
23
24
  end
24
25
 
26
+ opts.on("-E", "--encoding encoding", "Read as encoding (default #{encoding})") do |v|
27
+ encoding = v
28
+ end
29
+
25
30
  opts.on_tail("-?", "--help", "Show this message") do
26
31
  puts opts
27
32
  exit
28
33
  end
29
34
 
30
35
  opts.on_tail("-v", "--version", "Show version") do
31
- require 'yaml'
32
- puts Nokogiri::VERSION_INFO.to_yaml
36
+ puts Nokogiri::VersionInfo.instance.to_markdown
33
37
  exit
34
38
  end
35
39
  end
@@ -42,7 +46,7 @@ if uri.to_s.strip.empty?
42
46
  exit 1
43
47
  end
44
48
 
45
- @doc = parse_class.parse(open(uri).read)
49
+ @doc = parse_class.parse(open(uri).read, nil, encoding)
46
50
 
47
51
  puts "Your document is stored in @doc..."
48
52
  IRB.start
@@ -0,0 +1,124 @@
1
+ /**
2
+ * (The MIT License)
3
+ *
4
+ * Copyright (c) 2008 - 2011:
5
+ *
6
+ * * {Aaron Patterson}[http://tenderlovemaking.com]
7
+ * * {Mike Dalessio}[http://mike.daless.io]
8
+ * * {Charles Nutter}[http://blog.headius.com]
9
+ * * {Sergio Arbeo}[http://www.serabe.com]
10
+ * * {Patrick Mahoney}[http://polycrystal.org]
11
+ * * {Yoko Harada}[http://yokolet.blogspot.com]
12
+ *
13
+ * Permission is hereby granted, free of charge, to any person obtaining
14
+ * a copy of this software and associated documentation files (the
15
+ * 'Software'), to deal in the Software without restriction, including
16
+ * without limitation the rights to use, copy, modify, merge, publish,
17
+ * distribute, sublicense, and/or sell copies of the Software, and to
18
+ * permit persons to whom the Software is furnished to do so, subject to
19
+ * the following conditions:
20
+ *
21
+ * The above copyright notice and this permission notice shall be
22
+ * included in all copies or substantial portions of the Software.
23
+ *
24
+ * THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
25
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
26
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
27
+ * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
28
+ * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
29
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
30
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
31
+ */
32
+
33
+ package nokogiri;
34
+
35
+ import static nokogiri.internals.NokogiriHelpers.getNokogiriClass;
36
+
37
+ import java.util.HashMap;
38
+
39
+ import org.jruby.Ruby;
40
+ import org.jruby.RubyClass;
41
+ import org.jruby.RubyObject;
42
+ import org.jruby.anno.JRubyClass;
43
+ import org.jruby.anno.JRubyMethod;
44
+ import org.jruby.runtime.ThreadContext;
45
+ import org.jruby.runtime.builtin.IRubyObject;
46
+
47
+ /**
48
+ * Stub class to satisfy unit tests. I'm not sure where this class is
49
+ * meant to be used. As coded it won't really interact with any other
50
+ * classes and will have no effect on character encodings reported by
51
+ * documents being parsed.
52
+ *
53
+ * @author Patrick Mahoney <pat@polycrstal.org>
54
+ */
55
+ @JRubyClass(name="Nokogiri::EncodingHandler")
56
+ public class EncodingHandler extends RubyObject {
57
+ protected static HashMap<String,String> map = new HashMap<String,String>();
58
+ static {
59
+ addInitial();
60
+ }
61
+
62
+ protected String name;
63
+
64
+ protected static void addInitial() {
65
+ map.put("UTF-8", "UTF-8");
66
+ }
67
+
68
+ public EncodingHandler(Ruby ruby, RubyClass klass, String value) {
69
+ super(ruby, klass);
70
+ name = value;
71
+ }
72
+
73
+ @JRubyMethod(name="[]", meta=true)
74
+ public static IRubyObject get(ThreadContext context,
75
+ IRubyObject _klass,
76
+ IRubyObject keyObj) {
77
+ Ruby ruby = context.getRuntime();
78
+ String key = keyObj.toString();
79
+ String value = map.get(key);
80
+ if (value == null)
81
+ return ruby.getNil();
82
+
83
+ return new EncodingHandler(
84
+ ruby,
85
+ getNokogiriClass(ruby, "Nokogiri::EncodingHandler"),
86
+ value);
87
+ }
88
+
89
+ @JRubyMethod(meta=true)
90
+ public static IRubyObject delete(ThreadContext context,
91
+ IRubyObject _klass,
92
+ IRubyObject keyObj) {
93
+ String key = keyObj.toString();
94
+ String value = map.remove(key);
95
+ if (value == null)
96
+ return context.getRuntime().getNil();
97
+ return context.getRuntime().newString(value);
98
+ }
99
+
100
+ @JRubyMethod(name="clear_aliases!", meta=true)
101
+ public static IRubyObject clear_aliases(ThreadContext context,
102
+ IRubyObject _klass) {
103
+ map.clear();
104
+ addInitial();
105
+ return context.getRuntime().getNil();
106
+ }
107
+
108
+ @JRubyMethod(meta=true)
109
+ public static IRubyObject alias(ThreadContext context,
110
+ IRubyObject _klass,
111
+ IRubyObject orig,
112
+ IRubyObject alias) {
113
+ String value = map.get(orig.toString());
114
+ if (value != null)
115
+ map.put(alias.toString(), value);
116
+
117
+ return context.getRuntime().getNil();
118
+ }
119
+
120
+ @JRubyMethod
121
+ public IRubyObject name(ThreadContext context) {
122
+ return context.getRuntime().newString(name);
123
+ }
124
+ }
@@ -0,0 +1,119 @@
1
+ /**
2
+ * (The MIT License)
3
+ *
4
+ * Copyright (c) 2008 - 2011:
5
+ *
6
+ * * {Aaron Patterson}[http://tenderlovemaking.com]
7
+ * * {Mike Dalessio}[http://mike.daless.io]
8
+ * * {Charles Nutter}[http://blog.headius.com]
9
+ * * {Sergio Arbeo}[http://www.serabe.com]
10
+ * * {Patrick Mahoney}[http://polycrystal.org]
11
+ * * {Yoko Harada}[http://yokolet.blogspot.com]
12
+ *
13
+ * Permission is hereby granted, free of charge, to any person obtaining
14
+ * a copy of this software and associated documentation files (the
15
+ * 'Software'), to deal in the Software without restriction, including
16
+ * without limitation the rights to use, copy, modify, merge, publish,
17
+ * distribute, sublicense, and/or sell copies of the Software, and to
18
+ * permit persons to whom the Software is furnished to do so, subject to
19
+ * the following conditions:
20
+ *
21
+ * The above copyright notice and this permission notice shall be
22
+ * included in all copies or substantial portions of the Software.
23
+ *
24
+ * THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
25
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
26
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
27
+ * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
28
+ * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
29
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
30
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
31
+ */
32
+
33
+ package nokogiri;
34
+
35
+ import nokogiri.internals.HtmlDomParserContext;
36
+
37
+ import org.jruby.Ruby;
38
+ import org.jruby.RubyClass;
39
+ import org.jruby.anno.JRubyClass;
40
+ import org.jruby.anno.JRubyMethod;
41
+ import org.jruby.javasupport.util.RuntimeHelpers;
42
+ import org.jruby.runtime.Arity;
43
+ import org.jruby.runtime.ThreadContext;
44
+ import org.jruby.runtime.builtin.IRubyObject;
45
+ import org.w3c.dom.Document;
46
+
47
+ /**
48
+ * Class for Nokogiri::HTML::Document.
49
+ *
50
+ * @author sergio
51
+ * @author Yoko Harada <yokolet@gmail.com>
52
+ */
53
+ @JRubyClass(name="Nokogiri::HTML::Document", parent="Nokogiri::XML::Document")
54
+ public class HtmlDocument extends XmlDocument {
55
+
56
+ public HtmlDocument(Ruby ruby, RubyClass klazz) {
57
+ super(ruby, klazz);
58
+ }
59
+
60
+ public HtmlDocument(Ruby ruby, RubyClass klazz, Document doc) {
61
+ super(ruby, klazz, doc);
62
+ }
63
+
64
+ @JRubyMethod(name="new", meta = true, rest = true, required=0)
65
+ public static IRubyObject rbNew(ThreadContext context, IRubyObject klazz,
66
+ IRubyObject[] args) {
67
+ HtmlDocument htmlDocument = null;
68
+ try {
69
+ Document docNode = createNewDocument();
70
+ htmlDocument = (HtmlDocument) NokogiriService.HTML_DOCUMENT_ALLOCATOR.allocate(context.getRuntime(), (RubyClass) klazz);
71
+ htmlDocument.setNode(context, docNode);
72
+ } catch (Exception ex) {
73
+ throw context.getRuntime().newRuntimeError("couldn't create document: "+ex.toString());
74
+ }
75
+
76
+ RuntimeHelpers.invoke(context, htmlDocument, "initialize", args);
77
+
78
+ return htmlDocument;
79
+ }
80
+
81
+ public static IRubyObject do_parse(ThreadContext context,
82
+ IRubyObject klass,
83
+ IRubyObject[] args) {
84
+ Ruby ruby = context.getRuntime();
85
+ Arity.checkArgumentCount(ruby, args, 4, 4);
86
+ HtmlDomParserContext ctx =
87
+ new HtmlDomParserContext(ruby, args[2], args[3]);
88
+ ctx.setInputSource(context, args[0], args[1]);
89
+ return ctx.parse(context, klass, args[1]);
90
+ }
91
+
92
+ /*
93
+ * call-seq:
94
+ * read_io(io, url, encoding, options)
95
+ *
96
+ * Read the HTML document from +io+ with given +url+, +encoding+,
97
+ * and +options+. See Nokogiri::HTML.parse
98
+ */
99
+ @JRubyMethod(meta = true, rest = true)
100
+ public static IRubyObject read_io(ThreadContext context,
101
+ IRubyObject cls,
102
+ IRubyObject[] args) {
103
+ return do_parse(context, cls, args);
104
+ }
105
+
106
+ /*
107
+ * call-seq:
108
+ * read_memory(string, url, encoding, options)
109
+ *
110
+ * Read the HTML document contained in +string+ with given +url+, +encoding+,
111
+ * and +options+. See Nokogiri::HTML.parse
112
+ */
113
+ @JRubyMethod(meta = true, rest = true)
114
+ public static IRubyObject read_memory(ThreadContext context,
115
+ IRubyObject cls,
116
+ IRubyObject[] args) {
117
+ return do_parse(context, cls, args);
118
+ }
119
+ }