libxml-ruby 2.8.0 → 3.2.3

Sign up to get free protection for your applications and to get access to all the features.
Files changed (205) hide show
  1. checksums.yaml +5 -5
  2. data/HISTORY +859 -775
  3. data/LICENSE +20 -20
  4. data/MANIFEST +166 -166
  5. data/README.rdoc +217 -184
  6. data/Rakefile +98 -78
  7. data/ext/libxml/extconf.rb +61 -116
  8. data/ext/libxml/libxml.c +80 -76
  9. data/ext/libxml/ruby_libxml.h +67 -75
  10. data/ext/libxml/ruby_xml.c +937 -893
  11. data/ext/libxml/ruby_xml.h +10 -10
  12. data/ext/libxml/ruby_xml_attr.c +333 -333
  13. data/ext/libxml/ruby_xml_attr.h +12 -12
  14. data/ext/libxml/ruby_xml_attr_decl.c +153 -153
  15. data/ext/libxml/ruby_xml_attr_decl.h +11 -11
  16. data/ext/libxml/ruby_xml_attributes.c +275 -275
  17. data/ext/libxml/ruby_xml_attributes.h +15 -15
  18. data/ext/libxml/ruby_xml_cbg.c +85 -85
  19. data/ext/libxml/ruby_xml_document.c +1123 -1147
  20. data/ext/libxml/ruby_xml_document.h +11 -11
  21. data/ext/libxml/ruby_xml_dtd.c +248 -268
  22. data/ext/libxml/ruby_xml_dtd.h +9 -9
  23. data/ext/libxml/ruby_xml_encoding.c +250 -260
  24. data/ext/libxml/ruby_xml_encoding.h +16 -19
  25. data/ext/libxml/ruby_xml_error.c +996 -996
  26. data/ext/libxml/ruby_xml_error.h +12 -12
  27. data/ext/libxml/ruby_xml_html_parser.c +89 -92
  28. data/ext/libxml/ruby_xml_html_parser.h +10 -10
  29. data/ext/libxml/ruby_xml_html_parser_context.c +337 -338
  30. data/ext/libxml/ruby_xml_html_parser_context.h +10 -10
  31. data/ext/libxml/ruby_xml_html_parser_options.c +46 -46
  32. data/ext/libxml/ruby_xml_html_parser_options.h +10 -10
  33. data/ext/libxml/ruby_xml_input_cbg.c +191 -191
  34. data/ext/libxml/ruby_xml_input_cbg.h +20 -20
  35. data/ext/libxml/ruby_xml_io.c +47 -50
  36. data/ext/libxml/ruby_xml_io.h +10 -10
  37. data/ext/libxml/ruby_xml_namespace.c +154 -153
  38. data/ext/libxml/ruby_xml_namespace.h +10 -10
  39. data/ext/libxml/ruby_xml_namespaces.c +293 -293
  40. data/ext/libxml/ruby_xml_namespaces.h +9 -9
  41. data/ext/libxml/ruby_xml_node.c +1406 -1452
  42. data/ext/libxml/ruby_xml_node.h +13 -11
  43. data/ext/libxml/ruby_xml_parser.c +91 -94
  44. data/ext/libxml/ruby_xml_parser.h +12 -12
  45. data/ext/libxml/ruby_xml_parser_context.c +999 -1001
  46. data/ext/libxml/ruby_xml_parser_context.h +10 -10
  47. data/ext/libxml/ruby_xml_parser_options.c +66 -66
  48. data/ext/libxml/ruby_xml_parser_options.h +12 -12
  49. data/ext/libxml/ruby_xml_reader.c +1239 -1228
  50. data/ext/libxml/ruby_xml_reader.h +17 -17
  51. data/ext/libxml/ruby_xml_relaxng.c +110 -111
  52. data/ext/libxml/ruby_xml_relaxng.h +10 -10
  53. data/ext/libxml/ruby_xml_sax2_handler.c +326 -328
  54. data/ext/libxml/ruby_xml_sax2_handler.h +10 -10
  55. data/ext/libxml/ruby_xml_sax_parser.c +116 -120
  56. data/ext/libxml/ruby_xml_sax_parser.h +10 -10
  57. data/ext/libxml/ruby_xml_schema.c +350 -301
  58. data/ext/libxml/ruby_xml_schema.h +806 -809
  59. data/ext/libxml/ruby_xml_schema_attribute.c +61 -109
  60. data/ext/libxml/ruby_xml_schema_attribute.h +15 -15
  61. data/ext/libxml/ruby_xml_schema_element.c +69 -94
  62. data/ext/libxml/ruby_xml_schema_element.h +14 -14
  63. data/ext/libxml/ruby_xml_schema_facet.c +46 -52
  64. data/ext/libxml/ruby_xml_schema_facet.h +13 -13
  65. data/ext/libxml/ruby_xml_schema_type.c +214 -259
  66. data/ext/libxml/ruby_xml_schema_type.h +9 -9
  67. data/ext/libxml/ruby_xml_version.h +9 -9
  68. data/ext/libxml/ruby_xml_writer.c +1133 -1137
  69. data/ext/libxml/ruby_xml_writer.h +10 -10
  70. data/ext/libxml/ruby_xml_xinclude.c +16 -16
  71. data/ext/libxml/ruby_xml_xinclude.h +11 -11
  72. data/ext/libxml/ruby_xml_xpath.c +194 -188
  73. data/ext/libxml/ruby_xml_xpath.h +13 -13
  74. data/ext/libxml/ruby_xml_xpath_context.c +360 -361
  75. data/ext/libxml/ruby_xml_xpath_context.h +9 -9
  76. data/ext/libxml/ruby_xml_xpath_expression.c +81 -81
  77. data/ext/libxml/ruby_xml_xpath_expression.h +10 -10
  78. data/ext/libxml/ruby_xml_xpath_object.c +338 -335
  79. data/ext/libxml/ruby_xml_xpath_object.h +17 -17
  80. data/ext/libxml/ruby_xml_xpointer.c +99 -99
  81. data/ext/libxml/ruby_xml_xpointer.h +11 -11
  82. data/ext/vc/libxml_ruby.sln +17 -15
  83. data/lib/libxml/node.rb +2 -78
  84. data/lib/libxml/parser.rb +0 -266
  85. data/lib/libxml/sax_parser.rb +0 -17
  86. data/lib/libxml/schema/attribute.rb +19 -19
  87. data/lib/libxml/schema/element.rb +19 -27
  88. data/lib/libxml/schema/type.rb +21 -29
  89. data/lib/libxml/schema.rb +47 -66
  90. data/lib/libxml-ruby.rb +30 -0
  91. data/lib/libxml.rb +3 -33
  92. data/libxml-ruby.gemspec +48 -44
  93. data/script/benchmark/depixelate +634 -634
  94. data/script/benchmark/hamlet.xml +9054 -9054
  95. data/script/benchmark/parsecount +170 -170
  96. data/script/benchmark/throughput +41 -41
  97. data/script/test +6 -6
  98. data/setup.rb +0 -1
  99. data/test/c14n/given/example-1.xml +14 -14
  100. data/test/c14n/given/example-2.xml +11 -11
  101. data/test/c14n/given/example-3.xml +18 -18
  102. data/test/c14n/given/example-4.xml +9 -9
  103. data/test/c14n/given/example-5.xml +12 -12
  104. data/test/c14n/given/example-6.xml +2 -2
  105. data/test/c14n/given/example-7.xml +11 -11
  106. data/test/c14n/given/example-8.xml +11 -11
  107. data/test/c14n/given/example-8.xpath +9 -9
  108. data/test/c14n/result/1-1-without-comments/example-1 +3 -3
  109. data/test/c14n/result/1-1-without-comments/example-2 +10 -10
  110. data/test/c14n/result/1-1-without-comments/example-3 +13 -13
  111. data/test/c14n/result/1-1-without-comments/example-4 +8 -8
  112. data/test/c14n/result/1-1-without-comments/example-5 +2 -2
  113. data/test/c14n/result/with-comments/example-1 +5 -5
  114. data/test/c14n/result/with-comments/example-2 +10 -10
  115. data/test/c14n/result/with-comments/example-3 +13 -13
  116. data/test/c14n/result/with-comments/example-4 +8 -8
  117. data/test/c14n/result/with-comments/example-5 +3 -3
  118. data/test/c14n/result/without-comments/example-1 +3 -3
  119. data/test/c14n/result/without-comments/example-2 +10 -10
  120. data/test/c14n/result/without-comments/example-3 +13 -13
  121. data/test/c14n/result/without-comments/example-4 +8 -8
  122. data/test/c14n/result/without-comments/example-5 +2 -2
  123. data/test/model/atom.xml +12 -12
  124. data/test/model/bands.iso-8859-1.xml +4 -4
  125. data/test/model/bands.utf-8.xml +4 -4
  126. data/test/model/bands.xml +4 -4
  127. data/test/model/books.xml +153 -153
  128. data/test/model/cwm_1_0.xml +11336 -0
  129. data/test/model/merge_bug_data.xml +58 -58
  130. data/test/model/ruby-lang.html +238 -238
  131. data/test/model/rubynet.xml +79 -79
  132. data/test/model/shiporder.rnc +28 -28
  133. data/test/model/shiporder.rng +86 -86
  134. data/test/model/shiporder.xml +22 -22
  135. data/test/model/shiporder.xsd +44 -40
  136. data/test/model/shiporder_bad.xsd +40 -0
  137. data/test/model/shiporder_import.xsd +45 -0
  138. data/test/model/soap.xml +27 -27
  139. data/test/model/xinclude.xml +4 -4
  140. data/test/{tc_attr.rb → test_attr.rb} +23 -25
  141. data/test/{tc_attr_decl.rb → test_attr_decl.rb} +13 -14
  142. data/test/{tc_attributes.rb → test_attributes.rb} +11 -18
  143. data/test/{tc_canonicalize.rb → test_canonicalize.rb} +36 -41
  144. data/test/test_deprecated_require.rb +12 -0
  145. data/test/{tc_document.rb → test_document.rb} +33 -27
  146. data/test/test_document_write.rb +146 -0
  147. data/test/{tc_dtd.rb → test_dtd.rb} +29 -29
  148. data/test/{tc_encoding.rb → test_encoding.rb} +129 -126
  149. data/test/{tc_encoding_sax.rb → test_encoding_sax.rb} +7 -6
  150. data/test/test_error.rb +178 -0
  151. data/test/test_helper.rb +4 -9
  152. data/test/test_html_parser.rb +162 -0
  153. data/test/test_html_parser_context.rb +23 -0
  154. data/test/test_namespace.rb +60 -0
  155. data/test/{tc_namespaces.rb → test_namespaces.rb} +34 -44
  156. data/test/{tc_node.rb → test_node.rb} +68 -47
  157. data/test/{tc_node_cdata.rb → test_node_cdata.rb} +12 -13
  158. data/test/{tc_node_comment.rb → test_node_comment.rb} +7 -8
  159. data/test/{tc_node_copy.rb → test_node_copy.rb} +4 -6
  160. data/test/{tc_node_edit.rb → test_node_edit.rb} +23 -41
  161. data/test/{tc_node_pi.rb → test_node_pi.rb} +37 -40
  162. data/test/{tc_node_text.rb → test_node_text.rb} +10 -12
  163. data/test/{tc_node_write.rb → test_node_write.rb} +18 -29
  164. data/test/test_node_xlink.rb +28 -0
  165. data/test/test_parser.rb +324 -0
  166. data/test/{tc_parser_context.rb → test_parser_context.rb} +42 -49
  167. data/test/{tc_properties.rb → test_properties.rb} +6 -7
  168. data/test/test_reader.rb +364 -0
  169. data/test/test_relaxng.rb +53 -0
  170. data/test/{tc_sax_parser.rb → test_sax_parser.rb} +44 -38
  171. data/test/test_schema.rb +231 -0
  172. data/test/test_suite.rb +38 -40
  173. data/test/{tc_traversal.rb → test_traversal.rb} +5 -6
  174. data/test/{tc_writer.rb → test_writer.rb} +468 -448
  175. data/test/{tc_xinclude.rb → test_xinclude.rb} +4 -5
  176. data/test/test_xml.rb +263 -0
  177. data/test/{tc_xpath.rb → test_xpath.rb} +31 -32
  178. data/test/{tc_xpath_context.rb → test_xpath_context.rb} +8 -9
  179. data/test/test_xpath_expression.rb +37 -0
  180. data/test/{tc_xpointer.rb → test_xpointer.rb} +16 -18
  181. metadata +122 -100
  182. data/lib/libxml/ns.rb +0 -22
  183. data/lib/libxml/properties.rb +0 -23
  184. data/lib/libxml/reader.rb +0 -29
  185. data/lib/libxml/xpath_object.rb +0 -16
  186. data/test/etc_doc_to_s.rb +0 -21
  187. data/test/ets_doc_file.rb +0 -17
  188. data/test/ets_doc_to_s.rb +0 -23
  189. data/test/ets_gpx.rb +0 -28
  190. data/test/ets_node_gc.rb +0 -23
  191. data/test/ets_test.xml +0 -2
  192. data/test/ets_tsr.rb +0 -11
  193. data/test/tc_deprecated_require.rb +0 -13
  194. data/test/tc_document_write.rb +0 -196
  195. data/test/tc_error.rb +0 -180
  196. data/test/tc_html_parser.rb +0 -153
  197. data/test/tc_html_parser_context.rb +0 -24
  198. data/test/tc_namespace.rb +0 -62
  199. data/test/tc_node_xlink.rb +0 -29
  200. data/test/tc_parser.rb +0 -381
  201. data/test/tc_reader.rb +0 -400
  202. data/test/tc_relaxng.rb +0 -54
  203. data/test/tc_schema.rb +0 -162
  204. data/test/tc_xml.rb +0 -226
  205. data/test/tc_xpath_expression.rb +0 -38
@@ -1,170 +1,170 @@
1
- #!/usr/bin/env ruby
2
- #
3
- # Each test has an XML Parser open a 98k XML document and count one type of leaf
4
- # element (466 entries). This is repeated a total of 100 times, twice for each Parser.
5
- # Summary measurements are from the second test.
6
- #
7
- # Tests run on a MacBook Pro, Mac OS X 10.5.5, 4GB memory, 2.5 GHz Intel Core 2 Duo.
8
- #
9
- # Library versions:
10
- # hpricot 0.6.164
11
- # libxml: 0.9.2
12
- #
13
- # All benchmarks were run twice in sequence and the measurements presented here are from
14
- # the second run. Java automatically optimizes JRuby code which is run many times and the
15
- # speedup from the first to the second test is from 40 to 75%. There is no essential
16
- # difference in the speed of the C version of Ruby between the first test and the second.
17
- #
18
- # Summary:
19
- #
20
- # 100 times: Open 98k XML document and count one type of leaf element (466 entries)
21
- #
22
- # JRuby (Java 1.6.0_03-p3-Soylatte using server mode): jdom_document_builder 0.360
23
- # MRI: libxml v0.9.2 0.383
24
- # JRuby (Java 1.6.0_07): jdom_document_builder 0.401
25
- # JRuby (Java 1.5.0_16): jdom_document_builder 0.428
26
- # JRuby (Java 1.6.0_03-p3-Soylatte using server mode): hpricot 1.977
27
- # JRuby (Java 1.5.0_16): hpricot 2.027
28
- # JRuby (Java 1.6.0_07): hpricot 2.094
29
- # MRI: hpricot 2.140
30
- # JRuby (Java 1.6.0_03-p3-Soylatte using server mode): rexml 5.488
31
- # JRuby (Java 1.5.0_16): rexml 5.569
32
- # JRuby (Java 1.5.0_16): rexml 5.578
33
- # MRI: rexml 8.606
34
- #
35
- # Ruby version: MRI 1.8.6 (2008-03-03 rev 114), platform: universal-darwin9.0
36
- # --------------------------------------------------------------------------------
37
- # user system total real
38
- # rexml 8.170000 0.100000 8.270000 ( 8.606676)
39
- # hpricot 1.990000 0.040000 2.030000 ( 2.140865)
40
- # libxml 0.350000 0.020000 0.370000 ( 0.383475)
41
- #
42
- # JRuby 1.1.5 (svn r8078) on Java 1.5.0_16
43
- # --------------------------------------------------------------------------------
44
- # user system total real
45
- # rexml 5.578000 0.000000 5.578000 ( 5.578371)
46
- # hpricot 2.028000 0.000000 2.028000 ( 2.027348)
47
- # jdom_document_builder 0.429000 0.000000 0.429000 ( 0.428713)
48
- #
49
- # JRuby 1.1.5 (svn r8078) on Java 1.6.0_07
50
- # --------------------------------------------------------------------------------
51
- # user system total real
52
- # rexml 5.569000 0.000000 5.569000 ( 5.569135)
53
- # hpricot 2.094000 0.000000 2.094000 ( 2.093635)
54
- # jdom_document_builder 0.401000 0.000000 0.401000 ( 0.401115)
55
- #
56
- # JRuby 1.1.5 (svn r8078) on Java 1.6.0_07 using server mode (-J-server)
57
- # --------------------------------------------------------------------------------
58
- # user system total real
59
- # rexml 5.489000 0.000000 5.489000 ( 5.488560)
60
- # hpricot 1.977000 0.000000 1.977000 ( 1.976845)
61
- # jdom_document_builder 0.377000 0.000000 0.377000 ( 0.377808)
62
- #
63
- # JRuby 1.1.5 (svn r8078) on Java 1.6.0_03-p3 (Soylatte) using server mode (-J-server)
64
- # --------------------------------------------------------------------------------
65
- # user system total real
66
- # rexml 5.596000 0.000000 5.596000 ( 5.596212)
67
- # hpricot 1.937000 0.000000 1.937000 ( 1.937312)
68
- # jdom_document_builder 0.360000 0.000000 0.360000 ( 0.360068)
69
-
70
- require 'rubygems'
71
- require 'benchmark'
72
- require "rexml/document"
73
- require 'hpricot'
74
-
75
- if RUBY_PLATFORM =~ /java/
76
- include Java
77
- import javax.xml.parsers.DocumentBuilder
78
- import javax.xml.parsers.DocumentBuilderFactory
79
- @dbf = DocumentBuilderFactory.new_instance
80
- @ruby_info = "Ruby version: JRuby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE} rev #{RUBY_PATCHLEVEL}) [i386-jruby#{JRUBY_VERSION}]"
81
- @ruby_info << ", platform: Java, version #{java.lang.System.getProperty('java.version')}"
82
- else
83
- @ruby_info = "Ruby version: MRI #{RUBY_VERSION} (#{RUBY_RELEASE_DATE} rev #{RUBY_PATCHLEVEL})"
84
- @ruby_info << ", platform: #{RUBY_PLATFORM}"
85
-
86
- gem 'nokogiri', '>= 1.0.6'
87
- require 'nokogiri'
88
-
89
- gem 'libxml-ruby', '>= 0.9.2'
90
- require 'libxml'
91
- @xml_parser = LibXML::XML::Parser.new
92
- end
93
-
94
- file = File.expand_path(File.join(File.dirname(__FILE__), "sock_entries.xml"))
95
- @bundle_with_466_sock_entries = File.read(file)
96
-
97
- def rexml_count_socks
98
- doc = REXML::Document.new(@bundle_with_466_sock_entries).root
99
- socks = doc.elements.to_a('./sockEntries').length
100
- end
101
-
102
- unless RUBY_PLATFORM =~ /java/
103
- def nokogiri_count_socks
104
- #doc = Nokogiri(@bundle_with_466_sock_entries)
105
- #socks = doc.search('//sockEntries').length
106
- end
107
-
108
- def libxml_count_socks
109
- @xml_parser = LibXML::XML::Parser.new
110
- @xml_parser.string = @bundle_with_466_sock_entries
111
- doc = @xml_parser.parse
112
- socks = doc.find('//sockEntries').length
113
- end
114
- end
115
-
116
- def hpricot_count_socks
117
- doc = Hpricot.XML(@bundle_with_466_sock_entries)
118
- socks = doc.search("//sockEntries").length
119
- end
120
-
121
- if RUBY_PLATFORM =~ /java/
122
- def jdom_document_builder_count_socks
123
- file = File.expand_path(File.join(File.dirname(__FILE__), "sock_entries.xml"))
124
- doc = @dbf.new_document_builder.parse(file).get_document_element
125
- socks = doc.getElementsByTagName("sockEntries")
126
- socks.get_length
127
- end
128
- end
129
-
130
- n = 100
131
- test_iterations = ARGV.first.to_i
132
- test_iterations = 1 unless test_iterations > 1
133
- puts
134
- puts @ruby_info
135
- puts
136
- puts "#{n} times: Open 98k XML document and count one type of leaf element (466 entries)"
137
- puts
138
- print "running benchmark "
139
- if test_iterations == 1
140
- puts "once.\n\n"
141
- else
142
- puts "#{test_iterations} times.\n\n"
143
- end
144
- test_iterations.times do
145
- Benchmark.bmbm do |x|
146
- x.report("rexml") { n.times {rexml_count_socks} }
147
- x.report("hpricot") { n.times {hpricot_count_socks} }
148
- x.report("jdom_document_builder") { n.times {jdom_document_builder_count_socks} } if RUBY_PLATFORM =~ /java/
149
- #x.report("nokogiri") { n.times {nokogiri_count_socks} } unless RUBY_PLATFORM =~ /java/
150
- x.report("libxml") { n.times {libxml_count_socks} } unless RUBY_PLATFORM =~ /java/
151
- end
152
- puts
153
- end
154
-
155
- #
156
- # jrexml doesn't appear to have any speedup in this test
157
- #
158
- # if RUBY_PLATFORM =~ /java/
159
- # require 'jrexml'
160
- # def rexml_with_jrexml_count_socks
161
- # doc = REXML::Document.new(@bundle_with_466_sock_entries).root
162
- # socks = doc.elements.to_a('./sockEntries').length
163
- # end
164
- #
165
- # puts "\nNow add in JREXML to see if it speeds up rexml\n"
166
- # Benchmark.bmbm do |x|
167
- # x.report("rexml+jrexml") { n.times {rexml_with_jrexml_count_socks} }
168
- # end
169
- # puts
170
- # end
1
+ #!/usr/bin/env ruby
2
+ #
3
+ # Each test has an XML Parser open a 98k XML document and count one type of leaf
4
+ # element (466 entries). This is repeated a total of 100 times, twice for each Parser.
5
+ # Summary measurements are from the second test.
6
+ #
7
+ # Tests run on a MacBook Pro, Mac OS X 10.5.5, 4GB memory, 2.5 GHz Intel Core 2 Duo.
8
+ #
9
+ # Library versions:
10
+ # hpricot 0.6.164
11
+ # libxml: 0.9.2
12
+ #
13
+ # All benchmarks were run twice in sequence and the measurements presented here are from
14
+ # the second run. Java automatically optimizes JRuby code which is run many times and the
15
+ # speedup from the first to the second test is from 40 to 75%. There is no essential
16
+ # difference in the speed of the C version of Ruby between the first test and the second.
17
+ #
18
+ # Summary:
19
+ #
20
+ # 100 times: Open 98k XML document and count one type of leaf element (466 entries)
21
+ #
22
+ # JRuby (Java 1.6.0_03-p3-Soylatte using server mode): jdom_document_builder 0.360
23
+ # MRI: libxml v0.9.2 0.383
24
+ # JRuby (Java 1.6.0_07): jdom_document_builder 0.401
25
+ # JRuby (Java 1.5.0_16): jdom_document_builder 0.428
26
+ # JRuby (Java 1.6.0_03-p3-Soylatte using server mode): hpricot 1.977
27
+ # JRuby (Java 1.5.0_16): hpricot 2.027
28
+ # JRuby (Java 1.6.0_07): hpricot 2.094
29
+ # MRI: hpricot 2.140
30
+ # JRuby (Java 1.6.0_03-p3-Soylatte using server mode): rexml 5.488
31
+ # JRuby (Java 1.5.0_16): rexml 5.569
32
+ # JRuby (Java 1.5.0_16): rexml 5.578
33
+ # MRI: rexml 8.606
34
+ #
35
+ # Ruby version: MRI 1.8.6 (2008-03-03 rev 114), platform: universal-darwin9.0
36
+ # --------------------------------------------------------------------------------
37
+ # user system total real
38
+ # rexml 8.170000 0.100000 8.270000 ( 8.606676)
39
+ # hpricot 1.990000 0.040000 2.030000 ( 2.140865)
40
+ # libxml 0.350000 0.020000 0.370000 ( 0.383475)
41
+ #
42
+ # JRuby 1.1.5 (svn r8078) on Java 1.5.0_16
43
+ # --------------------------------------------------------------------------------
44
+ # user system total real
45
+ # rexml 5.578000 0.000000 5.578000 ( 5.578371)
46
+ # hpricot 2.028000 0.000000 2.028000 ( 2.027348)
47
+ # jdom_document_builder 0.429000 0.000000 0.429000 ( 0.428713)
48
+ #
49
+ # JRuby 1.1.5 (svn r8078) on Java 1.6.0_07
50
+ # --------------------------------------------------------------------------------
51
+ # user system total real
52
+ # rexml 5.569000 0.000000 5.569000 ( 5.569135)
53
+ # hpricot 2.094000 0.000000 2.094000 ( 2.093635)
54
+ # jdom_document_builder 0.401000 0.000000 0.401000 ( 0.401115)
55
+ #
56
+ # JRuby 1.1.5 (svn r8078) on Java 1.6.0_07 using server mode (-J-server)
57
+ # --------------------------------------------------------------------------------
58
+ # user system total real
59
+ # rexml 5.489000 0.000000 5.489000 ( 5.488560)
60
+ # hpricot 1.977000 0.000000 1.977000 ( 1.976845)
61
+ # jdom_document_builder 0.377000 0.000000 0.377000 ( 0.377808)
62
+ #
63
+ # JRuby 1.1.5 (svn r8078) on Java 1.6.0_03-p3 (Soylatte) using server mode (-J-server)
64
+ # --------------------------------------------------------------------------------
65
+ # user system total real
66
+ # rexml 5.596000 0.000000 5.596000 ( 5.596212)
67
+ # hpricot 1.937000 0.000000 1.937000 ( 1.937312)
68
+ # jdom_document_builder 0.360000 0.000000 0.360000 ( 0.360068)
69
+
70
+ require 'rubygems'
71
+ require 'benchmark'
72
+ require "rexml/document"
73
+ require 'hpricot'
74
+
75
+ if RUBY_PLATFORM =~ /java/
76
+ include Java
77
+ import javax.xml.parsers.DocumentBuilder
78
+ import javax.xml.parsers.DocumentBuilderFactory
79
+ @dbf = DocumentBuilderFactory.new_instance
80
+ @ruby_info = "Ruby version: JRuby #{RUBY_VERSION} (#{RUBY_RELEASE_DATE} rev #{RUBY_PATCHLEVEL}) [i386-jruby#{JRUBY_VERSION}]"
81
+ @ruby_info << ", platform: Java, version #{java.lang.System.getProperty('java.version')}"
82
+ else
83
+ @ruby_info = "Ruby version: MRI #{RUBY_VERSION} (#{RUBY_RELEASE_DATE} rev #{RUBY_PATCHLEVEL})"
84
+ @ruby_info << ", platform: #{RUBY_PLATFORM}"
85
+
86
+ gem 'nokogiri', '>= 1.0.6'
87
+ require 'nokogiri'
88
+
89
+ gem 'libxml-ruby', '>= 0.9.2'
90
+ require 'libxml'
91
+ @xml_parser = LibXML::XML::Parser.new
92
+ end
93
+
94
+ file = File.expand_path(File.join(File.dirname(__FILE__), "sock_entries.xml"))
95
+ @bundle_with_466_sock_entries = File.read(file)
96
+
97
+ def rexml_count_socks
98
+ doc = REXML::Document.new(@bundle_with_466_sock_entries).root
99
+ socks = doc.elements.to_a('./sockEntries').length
100
+ end
101
+
102
+ unless RUBY_PLATFORM =~ /java/
103
+ def nokogiri_count_socks
104
+ #doc = Nokogiri(@bundle_with_466_sock_entries)
105
+ #socks = doc.search('//sockEntries').length
106
+ end
107
+
108
+ def libxml_count_socks
109
+ @xml_parser = LibXML::XML::Parser.new
110
+ @xml_parser.string = @bundle_with_466_sock_entries
111
+ doc = @xml_parser.parse
112
+ socks = doc.find('//sockEntries').length
113
+ end
114
+ end
115
+
116
+ def hpricot_count_socks
117
+ doc = Hpricot.XML(@bundle_with_466_sock_entries)
118
+ socks = doc.search("//sockEntries").length
119
+ end
120
+
121
+ if RUBY_PLATFORM =~ /java/
122
+ def jdom_document_builder_count_socks
123
+ file = File.expand_path(File.join(File.dirname(__FILE__), "sock_entries.xml"))
124
+ doc = @dbf.new_document_builder.parse(file).get_document_element
125
+ socks = doc.getElementsByTagName("sockEntries")
126
+ socks.get_length
127
+ end
128
+ end
129
+
130
+ n = 100
131
+ test_iterations = ARGV.first.to_i
132
+ test_iterations = 1 unless test_iterations > 1
133
+ puts
134
+ puts @ruby_info
135
+ puts
136
+ puts "#{n} times: Open 98k XML document and count one type of leaf element (466 entries)"
137
+ puts
138
+ print "running benchmark "
139
+ if test_iterations == 1
140
+ puts "once.\n\n"
141
+ else
142
+ puts "#{test_iterations} times.\n\n"
143
+ end
144
+ test_iterations.times do
145
+ Benchmark.bmbm do |x|
146
+ x.report("rexml") { n.times {rexml_count_socks} }
147
+ x.report("hpricot") { n.times {hpricot_count_socks} }
148
+ x.report("jdom_document_builder") { n.times {jdom_document_builder_count_socks} } if RUBY_PLATFORM =~ /java/
149
+ #x.report("nokogiri") { n.times {nokogiri_count_socks} } unless RUBY_PLATFORM =~ /java/
150
+ x.report("libxml") { n.times {libxml_count_socks} } unless RUBY_PLATFORM =~ /java/
151
+ end
152
+ puts
153
+ end
154
+
155
+ #
156
+ # jrexml doesn't appear to have any speedup in this test
157
+ #
158
+ # if RUBY_PLATFORM =~ /java/
159
+ # require 'jrexml'
160
+ # def rexml_with_jrexml_count_socks
161
+ # doc = REXML::Document.new(@bundle_with_466_sock_entries).root
162
+ # socks = doc.elements.to_a('./sockEntries').length
163
+ # end
164
+ #
165
+ # puts "\nNow add in JREXML to see if it speeds up rexml\n"
166
+ # Benchmark.bmbm do |x|
167
+ # x.report("rexml+jrexml") { n.times {rexml_with_jrexml_count_socks} }
168
+ # end
169
+ # puts
170
+ # end
@@ -1,41 +1,41 @@
1
- #!/usr/bin/env ruby
2
-
3
- require 'rubygems'
4
- require 'hpricot'
5
- require 'xml'
6
- require 'rexml/document'
7
-
8
- ITERATIONS = 3
9
- NESTED_ITERATIONS = 5
10
-
11
- def bm(name, filename, &block)
12
- text = File.open(filename).read
13
- length = text.length / 1024.0 / 1024.0
14
- puts "#{filename}: #{name} (#{(length * 1024).round} kb)"
15
- for j in 0 .. NESTED_ITERATIONS
16
- s = Time.now.to_f
17
- for i in 0 .. ITERATIONS
18
- block.call(text)
19
- end
20
- timer = Time.now.to_f - s
21
- puts "\t#{length * ITERATIONS / timer} MB/s"
22
- end
23
- end
24
-
25
- def bm_suite(filenames)
26
- filenames.each do |filename|
27
- bm("LIBXML THROUGHPUT:", filename) do |text|
28
- XML::Document.file(filename)
29
- end
30
-
31
- bm("HPRICOT THROUGHPUT:", filename) do |text|
32
- Hpricot.XML(text)
33
- end
34
-
35
- bm("REXML THROUGHPUT:", filename) do |text|
36
- REXML::Document.new(text)
37
- end
38
- end
39
- end
40
-
41
- bm_suite("hamlet.xml")
1
+ #!/usr/bin/env ruby
2
+
3
+ require 'rubygems'
4
+ require 'hpricot'
5
+ require 'xml'
6
+ require 'rexml/document'
7
+
8
+ ITERATIONS = 3
9
+ NESTED_ITERATIONS = 5
10
+
11
+ def bm(name, filename, &block)
12
+ text = File.open(filename).read
13
+ length = text.length / 1024.0 / 1024.0
14
+ puts "#{filename}: #{name} (#{(length * 1024).round} kb)"
15
+ for j in 0 .. NESTED_ITERATIONS
16
+ s = Time.now.to_f
17
+ for i in 0 .. ITERATIONS
18
+ block.call(text)
19
+ end
20
+ timer = Time.now.to_f - s
21
+ puts "\t#{length * ITERATIONS / timer} MB/s"
22
+ end
23
+ end
24
+
25
+ def bm_suite(filenames)
26
+ filenames.each do |filename|
27
+ bm("LIBXML THROUGHPUT:", filename) do |text|
28
+ XML::Document.file(filename)
29
+ end
30
+
31
+ bm("HPRICOT THROUGHPUT:", filename) do |text|
32
+ Hpricot.XML(text)
33
+ end
34
+
35
+ bm("REXML THROUGHPUT:", filename) do |text|
36
+ REXML::Document.new(text)
37
+ end
38
+ end
39
+ end
40
+
41
+ bm_suite("hamlet.xml")
data/script/test CHANGED
@@ -1,6 +1,6 @@
1
- #!/usr/bin/env ruby
2
-
3
- %w{test lib ext/libxml}.each{ |path| $LOAD_PATH.unshift(path) }
4
-
5
- load './test/test_suite.rb'
6
-
1
+ #!/usr/bin/env ruby
2
+
3
+ %w{test lib ext/libxml}.each{ |path| $LOAD_PATH.unshift(path) }
4
+
5
+ load './test/test_suite.rb'
6
+
data/setup.rb CHANGED
@@ -281,7 +281,6 @@ class ConfigTable
281
281
  'site-ruby-common' => 'siteruby', # For backward compatibility
282
282
  'site-ruby' => 'siterubyver', # For backward compatibility
283
283
  'bin-dir' => 'bindir',
284
- 'bin-dir' => 'bindir',
285
284
  'rb-dir' => 'rbdir',
286
285
  'so-dir' => 'sodir',
287
286
  'data-dir' => 'datadir',
@@ -1,14 +1,14 @@
1
- <?xml version="1.0"?>
2
-
3
- <?xml-stylesheet href="doc.xsl"
4
- type="text/xsl" ?>
5
-
6
- <!DOCTYPE doc SYSTEM "doc.dtd">
7
-
8
- <doc>Hello, world!<!-- Comment 1 --></doc>
9
-
10
- <?pi-without-data ?>
11
-
12
- <!-- Comment 2 -->
13
-
14
- <!-- Comment 3 -->
1
+ <?xml version="1.0"?>
2
+
3
+ <?xml-stylesheet href="doc.xsl"
4
+ type="text/xsl" ?>
5
+
6
+ <!DOCTYPE doc SYSTEM "doc.dtd">
7
+
8
+ <doc>Hello, world!<!-- Comment 1 --></doc>
9
+
10
+ <?pi-without-data ?>
11
+
12
+ <!-- Comment 2 -->
13
+
14
+ <!-- Comment 3 -->
@@ -1,11 +1,11 @@
1
- <doc>
2
- <clean> </clean>
3
- <dirty> A B </dirty>
4
- <mixed>
5
- A
6
- <clean> </clean>
7
- B
8
- <dirty> A B </dirty>
9
- C
10
- </mixed>
11
- </doc>
1
+ <doc>
2
+ <clean> </clean>
3
+ <dirty> A B </dirty>
4
+ <mixed>
5
+ A
6
+ <clean> </clean>
7
+ B
8
+ <dirty> A B </dirty>
9
+ C
10
+ </mixed>
11
+ </doc>
@@ -1,18 +1,18 @@
1
- <!DOCTYPE doc [<!ATTLIST e9 attr CDATA "default">]>
2
- <doc>
3
- <e1 />
4
- <e2 ></e2>
5
- <e3 name = "elem3" id="elem3" />
6
- <e4 name="elem4" id="elem4" ></e4>
7
- <e5 a:attr="out" b:attr="sorted" attr2="all" attr="I'm"
8
- xmlns:b="http://www.ietf.org"
9
- xmlns:a="http://www.w3.org"
10
- xmlns="http://www.uvic.ca"/>
11
- <e6 xmlns="" xmlns:a="http://www.w3.org">
12
- <e7 xmlns="http://www.ietf.org">
13
- <e8 xmlns="" xmlns:a="http://www.w3.org">
14
- <e9 xmlns="" xmlns:a="http://www.ietf.org" attr="default"/>
15
- </e8>
16
- </e7>
17
- </e6>
18
- </doc>
1
+ <!DOCTYPE doc [<!ATTLIST e9 attr CDATA "default">]>
2
+ <doc>
3
+ <e1 />
4
+ <e2 ></e2>
5
+ <e3 name = "elem3" id="elem3" />
6
+ <e4 name="elem4" id="elem4" ></e4>
7
+ <e5 a:attr="out" b:attr="sorted" attr2="all" attr="I'm"
8
+ xmlns:b="http://www.ietf.org"
9
+ xmlns:a="http://www.w3.org"
10
+ xmlns="http://www.uvic.ca"/>
11
+ <e6 xmlns="" xmlns:a="http://www.w3.org">
12
+ <e7 xmlns="http://www.ietf.org">
13
+ <e8 xmlns="" xmlns:a="http://www.w3.org">
14
+ <e9 xmlns="" xmlns:a="http://www.ietf.org" attr="default"/>
15
+ </e8>
16
+ </e7>
17
+ </e6>
18
+ </doc>
@@ -1,9 +1,9 @@
1
- <!DOCTYPE doc [<!ATTLIST normId id ID #IMPLIED>]>
2
- <doc>
3
- <text>First line&#x0d;&#10;Second line</text>
4
- <value>&#x32;</value>
5
- <compute><![CDATA[value>"0" && value<"10" ?"valid":"error"]]></compute>
6
- <compute expr='value>"0" &amp;&amp; value&lt;"10" ?"valid":"error"'>valid</compute>
7
- <norm attr=' &apos; &#x20;&#13;&#xa;&#9; &apos; '/>
8
- <normId id=' &apos; &#x20;&#13;&#xa;&#9; &apos; '/>
9
- </doc>
1
+ <!DOCTYPE doc [<!ATTLIST normId id ID #IMPLIED>]>
2
+ <doc>
3
+ <text>First line&#x0d;&#10;Second line</text>
4
+ <value>&#x32;</value>
5
+ <compute><![CDATA[value>"0" && value<"10" ?"valid":"error"]]></compute>
6
+ <compute expr='value>"0" &amp;&amp; value&lt;"10" ?"valid":"error"'>valid</compute>
7
+ <norm attr=' &apos; &#x20;&#13;&#xa;&#9; &apos; '/>
8
+ <normId id=' &apos; &#x20;&#13;&#xa;&#9; &apos; '/>
9
+ </doc>
@@ -1,12 +1,12 @@
1
- <!DOCTYPE doc [
2
- <!ATTLIST doc attrExtEnt ENTITY #IMPLIED>
3
- <!ENTITY ent1 "Hello">
4
- <!ENTITY ent2 SYSTEM "world.txt">
5
- <!ENTITY entExt SYSTEM "earth.gif" NDATA gif>
6
- <!NOTATION gif SYSTEM "viewgif.exe">
7
- ]>
8
- <doc attrExtEnt="entExt">
9
- &ent1;, &ent2;!
10
- </doc>
11
-
12
- <!-- Let world.txt contain "world" (excluding the quotes) -->
1
+ <!DOCTYPE doc [
2
+ <!ATTLIST doc attrExtEnt ENTITY #IMPLIED>
3
+ <!ENTITY ent1 "Hello">
4
+ <!ENTITY ent2 SYSTEM "world.txt">
5
+ <!ENTITY entExt SYSTEM "earth.gif" NDATA gif>
6
+ <!NOTATION gif SYSTEM "viewgif.exe">
7
+ ]>
8
+ <doc attrExtEnt="entExt">
9
+ &ent1;, &ent2;!
10
+ </doc>
11
+
12
+ <!-- Let world.txt contain "world" (excluding the quotes) -->
@@ -1,2 +1,2 @@
1
- <?xml version="1.0" encoding="ISO-8859-1"?>
2
- <doc>&#169;</doc>
1
+ <?xml version="1.0" encoding="ISO-8859-1"?>
2
+ <doc>&#169;</doc>
@@ -1,11 +1,11 @@
1
- <!DOCTYPE doc [
2
- <!ATTLIST e2 xml:space (default|preserve) 'preserve'>
3
- <!ATTLIST e3 id ID #IMPLIED>
4
- ]>
5
- <doc xmlns="http://www.ietf.org" xmlns:w3c="http://www.w3.org">
6
- <e1>
7
- <e2 xmlns="">
8
- <e3 id="E3"/>
9
- </e2>
10
- </e1>
11
- </doc>
1
+ <!DOCTYPE doc [
2
+ <!ATTLIST e2 xml:space (default|preserve) 'preserve'>
3
+ <!ATTLIST e3 id ID #IMPLIED>
4
+ ]>
5
+ <doc xmlns="http://www.ietf.org" xmlns:w3c="http://www.w3.org">
6
+ <e1>
7
+ <e2 xmlns="">
8
+ <e3 id="E3"/>
9
+ </e2>
10
+ </e1>
11
+ </doc>
@@ -1,11 +1,11 @@
1
- <!DOCTYPE doc [
2
- <!ATTLIST e2 xml:space (default|preserve) 'preserve'>
3
- <!ATTLIST e3 id ID #IMPLIED>
4
- ]>
5
- <doc xmlns="http://www.ietf.org" xmlns:w3c="http://www.w3.org" xml:base="something/else">
6
- <e1>
7
- <e2 xmlns="" xml:id="abc" xml:base="bar/">
8
- <e3 id="E3" xml:base="foo"/>
9
- </e2>
10
- </e1>
11
- </doc>
1
+ <!DOCTYPE doc [
2
+ <!ATTLIST e2 xml:space (default|preserve) 'preserve'>
3
+ <!ATTLIST e3 id ID #IMPLIED>
4
+ ]>
5
+ <doc xmlns="http://www.ietf.org" xmlns:w3c="http://www.w3.org" xml:base="something/else">
6
+ <e1>
7
+ <e2 xmlns="" xml:id="abc" xml:base="bar/">
8
+ <e3 id="E3" xml:base="foo"/>
9
+ </e2>
10
+ </e1>
11
+ </doc>