caring-nokogiri 1.4.1.pre1

Sign up to get free protection for your applications and to get access to all the features.
Files changed (270) hide show
  1. data/.autotest +27 -0
  2. data/CHANGELOG.ja.rdoc +330 -0
  3. data/CHANGELOG.rdoc +324 -0
  4. data/Manifest.txt +269 -0
  5. data/README.ja.rdoc +105 -0
  6. data/README.rdoc +118 -0
  7. data/Rakefile +248 -0
  8. data/bin/nokogiri +49 -0
  9. data/ext/nokogiri/extconf.rb +147 -0
  10. data/ext/nokogiri/html_document.c +145 -0
  11. data/ext/nokogiri/html_document.h +10 -0
  12. data/ext/nokogiri/html_element_description.c +272 -0
  13. data/ext/nokogiri/html_element_description.h +10 -0
  14. data/ext/nokogiri/html_entity_lookup.c +32 -0
  15. data/ext/nokogiri/html_entity_lookup.h +8 -0
  16. data/ext/nokogiri/html_sax_parser_context.c +92 -0
  17. data/ext/nokogiri/html_sax_parser_context.h +11 -0
  18. data/ext/nokogiri/nokogiri.c +95 -0
  19. data/ext/nokogiri/nokogiri.h +145 -0
  20. data/ext/nokogiri/xml_attr.c +92 -0
  21. data/ext/nokogiri/xml_attr.h +9 -0
  22. data/ext/nokogiri/xml_attribute_decl.c +67 -0
  23. data/ext/nokogiri/xml_attribute_decl.h +9 -0
  24. data/ext/nokogiri/xml_cdata.c +54 -0
  25. data/ext/nokogiri/xml_cdata.h +9 -0
  26. data/ext/nokogiri/xml_comment.c +52 -0
  27. data/ext/nokogiri/xml_comment.h +9 -0
  28. data/ext/nokogiri/xml_document.c +388 -0
  29. data/ext/nokogiri/xml_document.h +24 -0
  30. data/ext/nokogiri/xml_document_fragment.c +46 -0
  31. data/ext/nokogiri/xml_document_fragment.h +10 -0
  32. data/ext/nokogiri/xml_dtd.c +192 -0
  33. data/ext/nokogiri/xml_dtd.h +10 -0
  34. data/ext/nokogiri/xml_element_content.c +123 -0
  35. data/ext/nokogiri/xml_element_content.h +10 -0
  36. data/ext/nokogiri/xml_element_decl.c +69 -0
  37. data/ext/nokogiri/xml_element_decl.h +9 -0
  38. data/ext/nokogiri/xml_entity_decl.c +97 -0
  39. data/ext/nokogiri/xml_entity_decl.h +10 -0
  40. data/ext/nokogiri/xml_entity_reference.c +50 -0
  41. data/ext/nokogiri/xml_entity_reference.h +9 -0
  42. data/ext/nokogiri/xml_io.c +31 -0
  43. data/ext/nokogiri/xml_io.h +11 -0
  44. data/ext/nokogiri/xml_namespace.c +74 -0
  45. data/ext/nokogiri/xml_namespace.h +12 -0
  46. data/ext/nokogiri/xml_node.c +1060 -0
  47. data/ext/nokogiri/xml_node.h +13 -0
  48. data/ext/nokogiri/xml_node_set.c +397 -0
  49. data/ext/nokogiri/xml_node_set.h +9 -0
  50. data/ext/nokogiri/xml_processing_instruction.c +54 -0
  51. data/ext/nokogiri/xml_processing_instruction.h +9 -0
  52. data/ext/nokogiri/xml_reader.c +593 -0
  53. data/ext/nokogiri/xml_reader.h +10 -0
  54. data/ext/nokogiri/xml_relax_ng.c +159 -0
  55. data/ext/nokogiri/xml_relax_ng.h +9 -0
  56. data/ext/nokogiri/xml_sax_parser.c +286 -0
  57. data/ext/nokogiri/xml_sax_parser.h +43 -0
  58. data/ext/nokogiri/xml_sax_parser_context.c +155 -0
  59. data/ext/nokogiri/xml_sax_parser_context.h +10 -0
  60. data/ext/nokogiri/xml_sax_push_parser.c +91 -0
  61. data/ext/nokogiri/xml_sax_push_parser.h +9 -0
  62. data/ext/nokogiri/xml_schema.c +156 -0
  63. data/ext/nokogiri/xml_schema.h +9 -0
  64. data/ext/nokogiri/xml_syntax_error.c +261 -0
  65. data/ext/nokogiri/xml_syntax_error.h +13 -0
  66. data/ext/nokogiri/xml_text.c +48 -0
  67. data/ext/nokogiri/xml_text.h +9 -0
  68. data/ext/nokogiri/xml_xpath.c +53 -0
  69. data/ext/nokogiri/xml_xpath.h +11 -0
  70. data/ext/nokogiri/xml_xpath_context.c +239 -0
  71. data/ext/nokogiri/xml_xpath_context.h +9 -0
  72. data/ext/nokogiri/xslt_stylesheet.c +131 -0
  73. data/ext/nokogiri/xslt_stylesheet.h +9 -0
  74. data/lib/nokogiri.rb +116 -0
  75. data/lib/nokogiri/css.rb +25 -0
  76. data/lib/nokogiri/css/generated_parser.rb +646 -0
  77. data/lib/nokogiri/css/generated_tokenizer.rb +143 -0
  78. data/lib/nokogiri/css/node.rb +99 -0
  79. data/lib/nokogiri/css/parser.rb +82 -0
  80. data/lib/nokogiri/css/parser.y +227 -0
  81. data/lib/nokogiri/css/syntax_error.rb +7 -0
  82. data/lib/nokogiri/css/tokenizer.rb +7 -0
  83. data/lib/nokogiri/css/tokenizer.rex +54 -0
  84. data/lib/nokogiri/css/xpath_visitor.rb +162 -0
  85. data/lib/nokogiri/decorators/slop.rb +33 -0
  86. data/lib/nokogiri/ffi/html/document.rb +28 -0
  87. data/lib/nokogiri/ffi/html/element_description.rb +85 -0
  88. data/lib/nokogiri/ffi/html/entity_lookup.rb +16 -0
  89. data/lib/nokogiri/ffi/html/sax/parser_context.rb +38 -0
  90. data/lib/nokogiri/ffi/io_callbacks.rb +42 -0
  91. data/lib/nokogiri/ffi/libxml.rb +356 -0
  92. data/lib/nokogiri/ffi/structs/common_node.rb +26 -0
  93. data/lib/nokogiri/ffi/structs/html_elem_desc.rb +24 -0
  94. data/lib/nokogiri/ffi/structs/html_entity_desc.rb +13 -0
  95. data/lib/nokogiri/ffi/structs/xml_alloc.rb +16 -0
  96. data/lib/nokogiri/ffi/structs/xml_attr.rb +19 -0
  97. data/lib/nokogiri/ffi/structs/xml_attribute.rb +27 -0
  98. data/lib/nokogiri/ffi/structs/xml_buffer.rb +16 -0
  99. data/lib/nokogiri/ffi/structs/xml_document.rb +108 -0
  100. data/lib/nokogiri/ffi/structs/xml_dtd.rb +28 -0
  101. data/lib/nokogiri/ffi/structs/xml_element.rb +26 -0
  102. data/lib/nokogiri/ffi/structs/xml_element_content.rb +17 -0
  103. data/lib/nokogiri/ffi/structs/xml_entity.rb +32 -0
  104. data/lib/nokogiri/ffi/structs/xml_enumeration.rb +12 -0
  105. data/lib/nokogiri/ffi/structs/xml_node.rb +28 -0
  106. data/lib/nokogiri/ffi/structs/xml_node_set.rb +53 -0
  107. data/lib/nokogiri/ffi/structs/xml_notation.rb +11 -0
  108. data/lib/nokogiri/ffi/structs/xml_ns.rb +15 -0
  109. data/lib/nokogiri/ffi/structs/xml_parser_context.rb +19 -0
  110. data/lib/nokogiri/ffi/structs/xml_relax_ng.rb +14 -0
  111. data/lib/nokogiri/ffi/structs/xml_sax_handler.rb +51 -0
  112. data/lib/nokogiri/ffi/structs/xml_sax_push_parser_context.rb +15 -0
  113. data/lib/nokogiri/ffi/structs/xml_schema.rb +13 -0
  114. data/lib/nokogiri/ffi/structs/xml_syntax_error.rb +31 -0
  115. data/lib/nokogiri/ffi/structs/xml_text_reader.rb +12 -0
  116. data/lib/nokogiri/ffi/structs/xml_xpath_context.rb +37 -0
  117. data/lib/nokogiri/ffi/structs/xml_xpath_object.rb +35 -0
  118. data/lib/nokogiri/ffi/structs/xml_xpath_parser_context.rb +20 -0
  119. data/lib/nokogiri/ffi/structs/xslt_stylesheet.rb +13 -0
  120. data/lib/nokogiri/ffi/xml/attr.rb +41 -0
  121. data/lib/nokogiri/ffi/xml/attribute_decl.rb +27 -0
  122. data/lib/nokogiri/ffi/xml/cdata.rb +19 -0
  123. data/lib/nokogiri/ffi/xml/comment.rb +18 -0
  124. data/lib/nokogiri/ffi/xml/document.rb +135 -0
  125. data/lib/nokogiri/ffi/xml/document_fragment.rb +21 -0
  126. data/lib/nokogiri/ffi/xml/dtd.rb +69 -0
  127. data/lib/nokogiri/ffi/xml/element_content.rb +43 -0
  128. data/lib/nokogiri/ffi/xml/element_decl.rb +19 -0
  129. data/lib/nokogiri/ffi/xml/entity_decl.rb +27 -0
  130. data/lib/nokogiri/ffi/xml/entity_reference.rb +19 -0
  131. data/lib/nokogiri/ffi/xml/namespace.rb +44 -0
  132. data/lib/nokogiri/ffi/xml/node.rb +444 -0
  133. data/lib/nokogiri/ffi/xml/node_set.rb +133 -0
  134. data/lib/nokogiri/ffi/xml/processing_instruction.rb +20 -0
  135. data/lib/nokogiri/ffi/xml/reader.rb +227 -0
  136. data/lib/nokogiri/ffi/xml/relax_ng.rb +85 -0
  137. data/lib/nokogiri/ffi/xml/sax/parser.rb +142 -0
  138. data/lib/nokogiri/ffi/xml/sax/parser_context.rb +67 -0
  139. data/lib/nokogiri/ffi/xml/sax/push_parser.rb +39 -0
  140. data/lib/nokogiri/ffi/xml/schema.rb +92 -0
  141. data/lib/nokogiri/ffi/xml/syntax_error.rb +91 -0
  142. data/lib/nokogiri/ffi/xml/text.rb +18 -0
  143. data/lib/nokogiri/ffi/xml/xpath.rb +19 -0
  144. data/lib/nokogiri/ffi/xml/xpath_context.rb +135 -0
  145. data/lib/nokogiri/ffi/xslt/stylesheet.rb +47 -0
  146. data/lib/nokogiri/html.rb +35 -0
  147. data/lib/nokogiri/html/builder.rb +35 -0
  148. data/lib/nokogiri/html/document.rb +88 -0
  149. data/lib/nokogiri/html/document_fragment.rb +15 -0
  150. data/lib/nokogiri/html/element_description.rb +23 -0
  151. data/lib/nokogiri/html/entity_lookup.rb +13 -0
  152. data/lib/nokogiri/html/sax/parser.rb +48 -0
  153. data/lib/nokogiri/html/sax/parser_context.rb +16 -0
  154. data/lib/nokogiri/syntax_error.rb +4 -0
  155. data/lib/nokogiri/version.rb +33 -0
  156. data/lib/nokogiri/version_warning.rb +11 -0
  157. data/lib/nokogiri/xml.rb +67 -0
  158. data/lib/nokogiri/xml/attr.rb +14 -0
  159. data/lib/nokogiri/xml/attribute_decl.rb +18 -0
  160. data/lib/nokogiri/xml/builder.rb +405 -0
  161. data/lib/nokogiri/xml/cdata.rb +11 -0
  162. data/lib/nokogiri/xml/character_data.rb +7 -0
  163. data/lib/nokogiri/xml/document.rb +131 -0
  164. data/lib/nokogiri/xml/document_fragment.rb +73 -0
  165. data/lib/nokogiri/xml/dtd.rb +11 -0
  166. data/lib/nokogiri/xml/element_content.rb +36 -0
  167. data/lib/nokogiri/xml/element_decl.rb +13 -0
  168. data/lib/nokogiri/xml/entity_decl.rb +15 -0
  169. data/lib/nokogiri/xml/fragment_handler.rb +73 -0
  170. data/lib/nokogiri/xml/namespace.rb +13 -0
  171. data/lib/nokogiri/xml/node.rb +665 -0
  172. data/lib/nokogiri/xml/node/save_options.rb +42 -0
  173. data/lib/nokogiri/xml/node_set.rb +307 -0
  174. data/lib/nokogiri/xml/notation.rb +6 -0
  175. data/lib/nokogiri/xml/parse_options.rb +85 -0
  176. data/lib/nokogiri/xml/pp.rb +2 -0
  177. data/lib/nokogiri/xml/pp/character_data.rb +18 -0
  178. data/lib/nokogiri/xml/pp/node.rb +56 -0
  179. data/lib/nokogiri/xml/processing_instruction.rb +8 -0
  180. data/lib/nokogiri/xml/reader.rb +74 -0
  181. data/lib/nokogiri/xml/relax_ng.rb +32 -0
  182. data/lib/nokogiri/xml/sax.rb +4 -0
  183. data/lib/nokogiri/xml/sax/document.rb +160 -0
  184. data/lib/nokogiri/xml/sax/parser.rb +115 -0
  185. data/lib/nokogiri/xml/sax/parser_context.rb +16 -0
  186. data/lib/nokogiri/xml/sax/push_parser.rb +60 -0
  187. data/lib/nokogiri/xml/schema.rb +61 -0
  188. data/lib/nokogiri/xml/syntax_error.rb +38 -0
  189. data/lib/nokogiri/xml/xpath.rb +10 -0
  190. data/lib/nokogiri/xml/xpath/syntax_error.rb +8 -0
  191. data/lib/nokogiri/xml/xpath_context.rb +16 -0
  192. data/lib/nokogiri/xslt.rb +48 -0
  193. data/lib/nokogiri/xslt/stylesheet.rb +25 -0
  194. data/lib/xsd/xmlparser/nokogiri.rb +71 -0
  195. data/tasks/test.rb +100 -0
  196. data/test/css/test_nthiness.rb +159 -0
  197. data/test/css/test_parser.rb +277 -0
  198. data/test/css/test_tokenizer.rb +183 -0
  199. data/test/css/test_xpath_visitor.rb +76 -0
  200. data/test/ffi/test_document.rb +35 -0
  201. data/test/files/2ch.html +108 -0
  202. data/test/files/address_book.rlx +12 -0
  203. data/test/files/address_book.xml +10 -0
  204. data/test/files/bar/bar.xsd +4 -0
  205. data/test/files/dont_hurt_em_why.xml +422 -0
  206. data/test/files/exslt.xml +8 -0
  207. data/test/files/exslt.xslt +35 -0
  208. data/test/files/foo/foo.xsd +4 -0
  209. data/test/files/po.xml +32 -0
  210. data/test/files/po.xsd +66 -0
  211. data/test/files/shift_jis.html +10 -0
  212. data/test/files/shift_jis.xml +5 -0
  213. data/test/files/snuggles.xml +3 -0
  214. data/test/files/staff.dtd +10 -0
  215. data/test/files/staff.xml +59 -0
  216. data/test/files/staff.xslt +32 -0
  217. data/test/files/tlm.html +850 -0
  218. data/test/files/valid_bar.xml +2 -0
  219. data/test/helper.rb +136 -0
  220. data/test/html/sax/test_parser.rb +64 -0
  221. data/test/html/sax/test_parser_context.rb +48 -0
  222. data/test/html/test_builder.rb +164 -0
  223. data/test/html/test_document.rb +390 -0
  224. data/test/html/test_document_encoding.rb +77 -0
  225. data/test/html/test_document_fragment.rb +142 -0
  226. data/test/html/test_element_description.rb +94 -0
  227. data/test/html/test_named_characters.rb +14 -0
  228. data/test/html/test_node.rb +228 -0
  229. data/test/html/test_node_encoding.rb +27 -0
  230. data/test/test_convert_xpath.rb +135 -0
  231. data/test/test_css_cache.rb +45 -0
  232. data/test/test_gc.rb +15 -0
  233. data/test/test_memory_leak.rb +77 -0
  234. data/test/test_nokogiri.rb +138 -0
  235. data/test/test_reader.rb +358 -0
  236. data/test/test_xslt_transforms.rb +131 -0
  237. data/test/xml/node/test_save_options.rb +20 -0
  238. data/test/xml/node/test_subclass.rb +44 -0
  239. data/test/xml/sax/test_parser.rb +307 -0
  240. data/test/xml/sax/test_parser_context.rb +56 -0
  241. data/test/xml/sax/test_push_parser.rb +106 -0
  242. data/test/xml/test_attr.rb +38 -0
  243. data/test/xml/test_attribute_decl.rb +82 -0
  244. data/test/xml/test_builder.rb +167 -0
  245. data/test/xml/test_cdata.rb +38 -0
  246. data/test/xml/test_comment.rb +29 -0
  247. data/test/xml/test_document.rb +607 -0
  248. data/test/xml/test_document_encoding.rb +26 -0
  249. data/test/xml/test_document_fragment.rb +144 -0
  250. data/test/xml/test_dtd.rb +82 -0
  251. data/test/xml/test_dtd_encoding.rb +33 -0
  252. data/test/xml/test_element_content.rb +56 -0
  253. data/test/xml/test_element_decl.rb +73 -0
  254. data/test/xml/test_entity_decl.rb +83 -0
  255. data/test/xml/test_entity_reference.rb +21 -0
  256. data/test/xml/test_namespace.rb +68 -0
  257. data/test/xml/test_node.rb +889 -0
  258. data/test/xml/test_node_attributes.rb +34 -0
  259. data/test/xml/test_node_encoding.rb +107 -0
  260. data/test/xml/test_node_set.rb +531 -0
  261. data/test/xml/test_parse_options.rb +52 -0
  262. data/test/xml/test_processing_instruction.rb +30 -0
  263. data/test/xml/test_reader_encoding.rb +126 -0
  264. data/test/xml/test_relax_ng.rb +60 -0
  265. data/test/xml/test_schema.rb +89 -0
  266. data/test/xml/test_syntax_error.rb +27 -0
  267. data/test/xml/test_text.rb +30 -0
  268. data/test/xml/test_unparented_node.rb +381 -0
  269. data/test/xml/test_xpath.rb +106 -0
  270. metadata +428 -0
data/Rakefile ADDED
@@ -0,0 +1,248 @@
1
+ # -*- ruby -*-
2
+
3
+ require 'rubygems'
4
+ gem 'hoe', '>= 2.1.0'
5
+ require 'hoe'
6
+
7
+ windows = RUBY_PLATFORM =~ /(mswin|mingw)/i
8
+ java = RUBY_PLATFORM =~ /java/
9
+
10
+ GENERATED_PARSER = "lib/nokogiri/css/generated_parser.rb"
11
+ GENERATED_TOKENIZER = "lib/nokogiri/css/generated_tokenizer.rb"
12
+
13
+ # Make sure hoe-debugging is installed
14
+ Hoe.plugin :debugging
15
+
16
+ HOE = Hoe.spec 'caring-nokogiri' do
17
+ developer('Aaron Patterson', 'aaronp@rubyforge.org')
18
+ developer('Mike Dalessio', 'mike.dalessio@gmail.com')
19
+ self.readme_file = ['README', ENV['HLANG'], 'rdoc'].compact.join('.')
20
+ self.history_file = ['CHANGELOG', ENV['HLANG'], 'rdoc'].compact.join('.')
21
+ self.extra_rdoc_files = FileList['*.rdoc']
22
+ self.clean_globs = [
23
+ 'lib/nokogiri/*.{o,so,bundle,a,log,dll}',
24
+ 'lib/nokogiri/nokogiri.rb',
25
+ 'lib/nokogiri/1.{8,9}',
26
+ GENERATED_PARSER,
27
+ GENERATED_TOKENIZER,
28
+ 'cross',
29
+ ]
30
+
31
+ %w{ racc rexical rake-compiler }.each do |dep|
32
+ self.extra_dev_deps << [dep, '>= 0']
33
+ end
34
+
35
+ self.spec_extras = { :extensions => ["ext/nokogiri/extconf.rb"] }
36
+ end
37
+
38
+ task :ws_docs do
39
+ title = "#{HOE.name}-#{HOE.version} Documentation"
40
+
41
+ options = []
42
+ options << "--main=#{HOE.readme_file}"
43
+ options << '--format=activerecord'
44
+ options << '--threads=1'
45
+ options << "--title=#{title.inspect}"
46
+
47
+ options += HOE.spec.require_paths
48
+ options += HOE.spec.extra_rdoc_files
49
+ require 'rdoc/rdoc'
50
+ ENV['RAILS_ROOT'] ||= File.expand_path(File.join('..', 'nokogiri_ws'))
51
+ RDoc::RDoc.new.document options
52
+ end
53
+
54
+ unless java
55
+ gem 'rake-compiler', '>= 0.4.1'
56
+ require "rake/extensiontask"
57
+
58
+ RET = Rake::ExtensionTask.new("nokogiri", HOE.spec) do |ext|
59
+ ext.lib_dir = File.join(*['lib', 'nokogiri', ENV['FAT_DIR']].compact)
60
+
61
+ ext.config_options << ENV['EXTOPTS']
62
+ cross_dir = File.join(File.dirname(__FILE__), 'tmp', 'cross')
63
+ ext.cross_compile = true
64
+ ext.cross_platform = 'i386-mingw32'
65
+ ext.cross_config_options <<
66
+ "--with-iconv-dir=#{File.join(cross_dir, 'iconv')}"
67
+ ext.cross_config_options <<
68
+ "--with-xml2-dir=#{File.join(cross_dir, 'libxml2')}"
69
+ ext.cross_config_options <<
70
+ "--with-xslt-dir=#{File.join(cross_dir, 'libxslt')}"
71
+ end
72
+
73
+ file 'lib/nokogiri/nokogiri.rb' do
74
+ File.open("lib/#{HOE.name}/#{HOE.name}.rb", 'wb') do |f|
75
+ f.write <<-eoruby
76
+ require "#{HOE.name}/\#{RUBY_VERSION.sub(/\\.\\d+$/, '')}/#{HOE.name}"
77
+ eoruby
78
+ end
79
+ end
80
+
81
+ namespace :cross do
82
+ task :file_list do
83
+ HOE.spec.platform = 'x86-mingw32'
84
+ HOE.spec.extensions = []
85
+ HOE.spec.files += Dir["lib/#{HOE.name}/#{HOE.name}.rb"]
86
+ HOE.spec.files += Dir["lib/#{HOE.name}/1.{8,9}/#{HOE.name}.so"]
87
+ HOE.spec.files += Dir["ext/nokogiri/*.dll"]
88
+ end
89
+ end
90
+
91
+ CLOBBER.include("lib/nokogiri/nokogiri.{so,dylib,rb,bundle}")
92
+ CLOBBER.include("lib/nokogiri/1.{8,9}")
93
+ CLOBBER.include("ext/nokogiri/*.dll")
94
+ end
95
+
96
+ namespace :gem do
97
+ namespace :dev do
98
+ task :spec => [ GENERATED_PARSER, GENERATED_TOKENIZER ] do
99
+ File.open("#{HOE.name}.gemspec", 'w') do |f|
100
+ HOE.spec.version = "#{HOE.version}.#{Time.now.strftime("%Y%m%d%H%M%S")}"
101
+ f.write(HOE.spec.to_ruby)
102
+ end
103
+ end
104
+ end
105
+
106
+ desc "Build a gem targetted for JRuby"
107
+ task :jruby => ['gem:jruby:spec'] do
108
+ system "gem build nokogiri.gemspec"
109
+ FileUtils.mkdir_p "pkg"
110
+ FileUtils.mv Dir.glob("nokogiri*-java.gem"), "pkg"
111
+ end
112
+
113
+ namespace :jruby do
114
+ task :spec => [GENERATED_PARSER, GENERATED_TOKENIZER] do
115
+ File.open("#{HOE.name}.gemspec", 'w') do |f|
116
+ HOE.spec.platform = 'java'
117
+ HOE.spec.files << GENERATED_PARSER
118
+ HOE.spec.files << GENERATED_TOKENIZER
119
+ HOE.spec.files += Dir["ext/nokogiri/*.dll"]
120
+ HOE.spec.extensions = []
121
+ f.write(HOE.spec.to_ruby)
122
+ end
123
+ end
124
+ end
125
+
126
+ task :spec => ['gem:dev:spec']
127
+ end
128
+
129
+ file GENERATED_PARSER => "lib/nokogiri/css/parser.y" do |t|
130
+ begin
131
+ racc = `which racc`.strip
132
+ racc = "#{::Config::CONFIG['bindir']}/racc" if racc.empty?
133
+ sh "#{racc} -l -o #{t.name} #{t.prerequisites.first}"
134
+ rescue
135
+ abort "need racc, sudo gem install racc"
136
+ end
137
+ end
138
+
139
+ file GENERATED_TOKENIZER => "lib/nokogiri/css/tokenizer.rex" do |t|
140
+ begin
141
+ sh "rex --independent -o #{t.name} #{t.prerequisites.first}"
142
+ rescue
143
+ abort "need rexical, sudo gem install rexical"
144
+ end
145
+ end
146
+
147
+ libs = %w{
148
+ iconv-1.9.2.win32
149
+ zlib-1.2.3.win32
150
+ libxml2-2.7.3.win32
151
+ libxslt-1.1.24.win32
152
+ }
153
+
154
+ lib_dlls = {
155
+ 'iconv-1.9.2.win32' => 'iconv.dll',
156
+ 'zlib-1.2.3.win32' => 'zlib1.dll',
157
+ 'libxml2-2.7.3.win32' => 'libxml2.dll',
158
+ 'libxslt-1.1.24.win32' => 'libxslt.dll',
159
+ }
160
+
161
+ libs.each do |lib|
162
+ libname = lib.split('-').first
163
+
164
+ file "tmp/stash/#{lib}.zip" do |t|
165
+ puts "downloading #{lib}"
166
+ FileUtils.mkdir_p('tmp/stash')
167
+ Dir.chdir('tmp/stash') do
168
+ url = "ftp://ftp.xmlsoft.org/libxml2/win32/#{lib}.zip"
169
+ system("wget #{url} || curl -O #{url}")
170
+ end
171
+ end
172
+
173
+ file "tmp/cross/#{libname}" => ["tmp/stash/#{lib}.zip"] do |t|
174
+ puts "unzipping #{lib}.zip"
175
+ FileUtils.mkdir_p('tmp/cross')
176
+ Dir.chdir('tmp/cross') do
177
+ sh "unzip ../stash/#{lib}.zip"
178
+ sh "cp #{lib}/bin/* #{lib}/lib" # put DLL in lib, so dirconfig works
179
+ sh "mv #{lib} #{lib.split('-').first}"
180
+ sh "touch #{lib.split('-').first}"
181
+ end
182
+ end
183
+
184
+ file "ext/nokogiri/#{lib_dlls[lib]}" => "tmp/cross/#{libname}" do |t|
185
+ Dir.chdir('tmp/cross') do
186
+ sh "cp #{libname}/bin/*.dll ../../ext/nokogiri/"
187
+ end
188
+ end
189
+
190
+ if Rake::Task.task_defined?(:cross)
191
+ Rake::Task[:cross].prerequisites << "ext/nokogiri/#{lib_dlls[lib]}"
192
+ Rake::Task[:cross].prerequisites << "lib/nokogiri/nokogiri.rb"
193
+ Rake::Task[:cross].prerequisites << "cross:file_list"
194
+ end
195
+ Rake::Task['gem:jruby:spec'].prerequisites << "ext/nokogiri/#{lib_dlls[lib]}"
196
+ end
197
+
198
+ require 'tasks/test'
199
+
200
+ desc "set environment variables to build and/or test with debug options"
201
+ task :debug do
202
+ ENV['NOKOGIRI_DEBUG'] = "true"
203
+ ENV['CFLAGS'] ||= ""
204
+ ENV['CFLAGS'] += " -DDEBUG"
205
+ end
206
+
207
+ # required_ruby_version
208
+
209
+ # Only do this on unix, since we can't build on windows
210
+ unless windows || java || ENV['NOKOGIRI_FFI']
211
+ [:compile, :check_manifest].each do |task_name|
212
+ Rake::Task[task_name].prerequisites << GENERATED_PARSER
213
+ Rake::Task[task_name].prerequisites << GENERATED_TOKENIZER
214
+ end
215
+
216
+ Rake::Task[:test].prerequisites << :compile
217
+ if Hoe.plugins.include?(:debugging)
218
+ ['valgrind', 'valgrind:mem', 'valgrind:mem0'].each do |task_name|
219
+ Rake::Task["test:#{task_name}"].prerequisites << :compile
220
+ end
221
+ end
222
+ else
223
+ [:test, :check_manifest].each do |task_name|
224
+ if Rake::Task[task_name]
225
+ Rake::Task[task_name].prerequisites << GENERATED_PARSER
226
+ Rake::Task[task_name].prerequisites << GENERATED_TOKENIZER
227
+ end
228
+ end
229
+ end
230
+
231
+ namespace :install do
232
+ desc "Install rex and racc for development"
233
+ task :deps => %w(rexical racc)
234
+
235
+ task :racc do |t|
236
+ sh "sudo gem install racc"
237
+ end
238
+
239
+ task :rexical do
240
+ sh "sudo gem install rexical"
241
+ end
242
+ end
243
+
244
+ namespace :rip do
245
+ task :install => [GENERATED_TOKENIZER, GENERATED_PARSER]
246
+ end
247
+
248
+ # vim: syntax=Ruby
data/bin/nokogiri ADDED
@@ -0,0 +1,49 @@
1
+ #!/usr/bin/env ruby
2
+ require 'optparse'
3
+ require 'open-uri'
4
+ require 'irb'
5
+ require 'uri'
6
+ require 'rubygems'
7
+ require 'nokogiri'
8
+
9
+ parse_class = Nokogiri
10
+
11
+ opts = OptionParser.new do |opts|
12
+ opts.banner = "Nokogiri: an HTML, XML, SAX, and Reader parser"
13
+ opts.define_head "Usage: nokogiri <uri|path> [options]"
14
+ opts.separator ""
15
+ opts.separator "Examples:"
16
+ opts.separator " nokogiri http://www.ruby-lang.org/"
17
+ opts.separator " nokogiri ./public/index.html"
18
+ opts.separator ""
19
+ opts.separator "Options:"
20
+
21
+ opts.on("--type [TYPE]", [:xml, :html]) do |v|
22
+ parse_class = {:xml => Nokogiri::XML, :html => Nokogiri::HTML}[v]
23
+ end
24
+
25
+ opts.on_tail("-?", "--help", "Show this message") do
26
+ puts opts
27
+ exit
28
+ end
29
+
30
+ opts.on_tail("-v", "--version", "Show version") do
31
+ require 'yaml'
32
+ puts Nokogiri::VERSION_INFO.to_yaml
33
+ exit
34
+ end
35
+ end
36
+ opts.parse!
37
+
38
+ uri = ARGV.shift
39
+
40
+ if uri.to_s.strip.empty?
41
+ puts opts
42
+ exit 1
43
+ end
44
+
45
+ @doc = parse_class.parse(open(uri).read)
46
+
47
+ puts "Your document is stored in @doc..."
48
+ IRB.start
49
+
@@ -0,0 +1,147 @@
1
+ ENV['RC_ARCHS'] = '' if RUBY_PLATFORM =~ /darwin/
2
+
3
+ # :stopdoc:
4
+
5
+ require 'mkmf'
6
+
7
+ ROOT = File.expand_path(File.join(File.dirname(__FILE__), '..', '..'))
8
+ LIBDIR = Config::CONFIG['libdir']
9
+ INCLUDEDIR = Config::CONFIG['includedir']
10
+
11
+ if defined?(RUBY_ENGINE) && RUBY_ENGINE == 'macruby'
12
+ $LIBRUBYARG_STATIC.gsub!(/-static/, '')
13
+ end
14
+
15
+ $CFLAGS << " #{ENV["CFLAGS"]}"
16
+ $LIBS << " #{ENV["LIBS"]}"
17
+
18
+ if Config::CONFIG['target_os'] == 'mingw32'
19
+ $CFLAGS << " -DXP_WIN -DXP_WIN32 -DUSE_INCLUDED_VASPRINTF"
20
+ elsif Config::CONFIG['target_os'] == 'solaris2'
21
+ $CFLAGS << " -DUSE_INCLUDED_VASPRINTF"
22
+ else
23
+ $CFLAGS << " -g -DXP_UNIX"
24
+ end
25
+
26
+ $CFLAGS << " -O3 -Wall -Wcast-qual -Wwrite-strings -Wconversion -Wmissing-noreturn -Winline"
27
+
28
+ HEADER_DIRS = [
29
+ # First search /opt/local for macports
30
+ '/opt/local/include',
31
+ '/opt/local/include/libxml2',
32
+
33
+ # Then search /usr/local for people that installed from source
34
+ '/usr/local/include',
35
+ '/usr/local/include/libxml2',
36
+
37
+ # Check the ruby install locations
38
+ INCLUDEDIR,
39
+ File.join(INCLUDEDIR, "libxml2"),
40
+
41
+ # Finally fall back to /usr
42
+ '/usr/include',
43
+ '/usr/include/libxml2',
44
+ ]
45
+
46
+ LIB_DIRS = [
47
+ # First search /opt/local for macports
48
+ '/opt/local/lib',
49
+
50
+ # Then search /usr/local for people that installed from source
51
+ '/usr/local/lib',
52
+
53
+ # Check the ruby install locations
54
+ LIBDIR,
55
+
56
+ # Finally fall back to /usr
57
+ '/usr/lib',
58
+ ]
59
+
60
+ iconv_dirs = dir_config('iconv', '/opt/local/include', '/opt/local/lib')
61
+ unless ["", ""] == iconv_dirs
62
+ HEADER_DIRS.unshift iconv_dirs.first
63
+ LIB_DIRS.unshift iconv_dirs[1]
64
+ end
65
+
66
+ xml2_dirs = dir_config('xml2', '/opt/local/include/libxml2', '/opt/local/lib')
67
+ unless ["", ""] == xml2_dirs
68
+ HEADER_DIRS.unshift xml2_dirs.first
69
+ LIB_DIRS.unshift xml2_dirs[1]
70
+ end
71
+
72
+ xslt_dirs = dir_config('xslt', '/opt/local/include/', '/opt/local/lib')
73
+ unless ["", ""] == xslt_dirs
74
+ HEADER_DIRS.unshift xslt_dirs.first
75
+ LIB_DIRS.unshift xslt_dirs[1]
76
+ end
77
+
78
+ CUSTOM_DASH_I = []
79
+
80
+ def nokogiri_find_header header_file, *paths
81
+ # mkmf in ruby 1.8.5 does not have the "checking_message" method
82
+ message = defined?(checking_message) ?
83
+ checking_message(header_file, paths) :
84
+ header_file
85
+
86
+ header = cpp_include header_file
87
+ checking_for message do
88
+ found = false
89
+ paths.each do |dir|
90
+ if File.exists?(File.join(dir, header_file))
91
+ opt = "-I#{dir}".quote
92
+ if try_cpp header, opt
93
+ unless CUSTOM_DASH_I.include? dir
94
+ $INCFLAGS = "#{opt} #{$INCFLAGS}"
95
+ CUSTOM_DASH_I << dir
96
+ end
97
+ found = dir
98
+ break
99
+ end
100
+ end
101
+ end
102
+ found ||= try_cpp(header)
103
+ end
104
+ end
105
+
106
+ unless nokogiri_find_header('iconv.h', *HEADER_DIRS)
107
+ abort "iconv is missing. try 'port install iconv' or 'yum install iconv'"
108
+ end
109
+
110
+ unless nokogiri_find_header('libxml/parser.h', *HEADER_DIRS)
111
+ abort "libxml2 is missing. try 'port install libxml2' or 'yum install libxml2-devel'"
112
+ end
113
+
114
+ unless nokogiri_find_header('libxslt/xslt.h', *HEADER_DIRS)
115
+ abort "libxslt is missing. try 'port install libxslt' or 'yum install libxslt-devel'"
116
+ end
117
+
118
+ unless nokogiri_find_header('libexslt/exslt.h', *HEADER_DIRS)
119
+ abort "libxslt is missing. try 'port install libxslt' or 'yum install libxslt-devel'"
120
+ end
121
+
122
+ unless find_library('xml2', 'xmlParseDoc', *LIB_DIRS)
123
+ abort "libxml2 is missing. try 'port install libxml2' or 'yum install libxml2'"
124
+ end
125
+
126
+ unless find_library('xslt', 'xsltParseStylesheetDoc', *LIB_DIRS)
127
+ abort "libxslt is missing. try 'port install libxslt' or 'yum install libxslt-devel'"
128
+ end
129
+
130
+ unless find_library('exslt', 'exsltFuncRegister', *LIB_DIRS)
131
+ abort "libxslt is missing. try 'port install libxslt' or 'yum install libxslt-devel'"
132
+ end
133
+
134
+ have_func('xmlRelaxNGSetParserStructuredErrors')
135
+ have_func('xmlRelaxNGSetParserStructuredErrors')
136
+ have_func('xmlRelaxNGSetValidStructuredErrors')
137
+ have_func('xmlSchemaSetValidStructuredErrors')
138
+ have_func('xmlSchemaSetParserStructuredErrors')
139
+
140
+ if ENV['CPUPROFILE']
141
+ unless find_library('profiler', 'ProfilerEnable', *LIB_DIRS)
142
+ abort "google performance tools are not installed"
143
+ end
144
+ end
145
+
146
+ create_makefile('nokogiri/nokogiri')
147
+ # :startdoc:
@@ -0,0 +1,145 @@
1
+ #include <html_document.h>
2
+
3
+ /*
4
+ * call-seq:
5
+ * new
6
+ *
7
+ * Create a new document
8
+ */
9
+ static VALUE new(int argc, VALUE *argv, VALUE klass)
10
+ {
11
+ VALUE uri, external_id, rest, rb_doc;
12
+
13
+ rb_scan_args(argc, argv, "0*", &rest);
14
+ uri = rb_ary_entry(rest, (long)0);
15
+ external_id = rb_ary_entry(rest, (long)1);
16
+
17
+ htmlDocPtr doc = htmlNewDoc(
18
+ RTEST(uri) ? (const xmlChar *)StringValuePtr(uri) : NULL,
19
+ RTEST(external_id) ? (const xmlChar *)StringValuePtr(external_id) : NULL
20
+ );
21
+ rb_doc = Nokogiri_wrap_xml_document(klass, doc);
22
+ rb_obj_call_init(rb_doc, argc, argv);
23
+ return rb_doc ;
24
+ }
25
+
26
+ /*
27
+ * call-seq:
28
+ * read_io(io, url, encoding, options)
29
+ *
30
+ * Read the HTML document from +io+ with given +url+, +encoding+,
31
+ * and +options+. See Nokogiri::HTML.parse
32
+ */
33
+ static VALUE read_io( VALUE klass,
34
+ VALUE io,
35
+ VALUE url,
36
+ VALUE encoding,
37
+ VALUE options )
38
+ {
39
+ const char * c_url = NIL_P(url) ? NULL : StringValuePtr(url);
40
+ const char * c_enc = NIL_P(encoding) ? NULL : StringValuePtr(encoding);
41
+ VALUE error_list = rb_ary_new();
42
+
43
+ xmlResetLastError();
44
+ xmlSetStructuredErrorFunc((void *)error_list, Nokogiri_error_array_pusher);
45
+
46
+ htmlDocPtr doc = htmlReadIO(
47
+ io_read_callback,
48
+ io_close_callback,
49
+ (void *)io,
50
+ c_url,
51
+ c_enc,
52
+ (int)NUM2INT(options)
53
+ );
54
+ xmlSetStructuredErrorFunc(NULL, NULL);
55
+
56
+ if(doc == NULL) {
57
+ xmlFreeDoc(doc);
58
+
59
+ xmlErrorPtr error = xmlGetLastError();
60
+ if(error)
61
+ rb_exc_raise(Nokogiri_wrap_xml_syntax_error((VALUE)NULL, error));
62
+ else
63
+ rb_raise(rb_eRuntimeError, "Could not parse document");
64
+
65
+ return Qnil;
66
+ }
67
+
68
+ VALUE document = Nokogiri_wrap_xml_document(klass, doc);
69
+ rb_iv_set(document, "@errors", error_list);
70
+ return document;
71
+ }
72
+
73
+ /*
74
+ * call-seq:
75
+ * read_memory(string, url, encoding, options)
76
+ *
77
+ * Read the HTML document contained in +string+ with given +url+, +encoding+,
78
+ * and +options+. See Nokogiri::HTML.parse
79
+ */
80
+ static VALUE read_memory( VALUE klass,
81
+ VALUE string,
82
+ VALUE url,
83
+ VALUE encoding,
84
+ VALUE options )
85
+ {
86
+ const char * c_buffer = StringValuePtr(string);
87
+ const char * c_url = NIL_P(url) ? NULL : StringValuePtr(url);
88
+ const char * c_enc = NIL_P(encoding) ? NULL : StringValuePtr(encoding);
89
+ int len = RSTRING_LEN(string);
90
+ VALUE error_list = rb_ary_new();
91
+
92
+ xmlResetLastError();
93
+ xmlSetStructuredErrorFunc((void *)error_list, Nokogiri_error_array_pusher);
94
+
95
+ htmlDocPtr doc = htmlReadMemory(c_buffer, len, c_url, c_enc, (int)NUM2INT(options));
96
+ xmlSetStructuredErrorFunc(NULL, NULL);
97
+
98
+ if(doc == NULL) {
99
+ xmlFreeDoc(doc);
100
+
101
+ xmlErrorPtr error = xmlGetLastError();
102
+ if(error)
103
+ rb_exc_raise(Nokogiri_wrap_xml_syntax_error((VALUE)NULL, error));
104
+ else
105
+ rb_raise(rb_eRuntimeError, "Could not parse document");
106
+
107
+ return Qnil;
108
+ }
109
+
110
+ VALUE document = Nokogiri_wrap_xml_document(klass, doc);
111
+ rb_iv_set(document, "@errors", error_list);
112
+ return document;
113
+ }
114
+
115
+ /*
116
+ * call-seq:
117
+ * type
118
+ *
119
+ * The type for this document
120
+ */
121
+ static VALUE type(VALUE self)
122
+ {
123
+ htmlDocPtr doc;
124
+ Data_Get_Struct(self, xmlDoc, doc);
125
+ return INT2NUM((long)doc->type);
126
+ }
127
+
128
+ VALUE cNokogiriHtmlDocument ;
129
+ void init_html_document()
130
+ {
131
+ VALUE nokogiri = rb_define_module("Nokogiri");
132
+ VALUE html = rb_define_module_under(nokogiri, "HTML");
133
+ VALUE xml = rb_define_module_under(nokogiri, "XML");
134
+ VALUE node = rb_define_class_under(xml, "Node", rb_cObject);
135
+ VALUE xml_doc = rb_define_class_under(xml, "Document", node);
136
+ VALUE klass = rb_define_class_under(html, "Document", xml_doc);
137
+
138
+ cNokogiriHtmlDocument = klass;
139
+
140
+ rb_define_singleton_method(klass, "read_memory", read_memory, 4);
141
+ rb_define_singleton_method(klass, "read_io", read_io, 4);
142
+ rb_define_singleton_method(klass, "new", new, -1);
143
+
144
+ rb_define_method(klass, "type", type, 0);
145
+ }