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
@@ -0,0 +1,367 @@
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.rubyStringToString;
36
+ import static org.jruby.javasupport.util.RuntimeHelpers.invoke;
37
+
38
+ import java.io.IOException;
39
+ import java.io.InputStream;
40
+
41
+ import nokogiri.internals.NokogiriHandler;
42
+ import nokogiri.internals.ParserContext;
43
+ import nokogiri.internals.XmlSaxParser;
44
+
45
+ import org.apache.xerces.parsers.AbstractSAXParser;
46
+ import org.jruby.Ruby;
47
+ import org.jruby.RubyClass;
48
+ import org.jruby.RubyFixnum;
49
+ import org.jruby.RubyModule;
50
+ import org.jruby.RubyObjectAdapter;
51
+ import org.jruby.anno.JRubyClass;
52
+ import org.jruby.anno.JRubyMethod;
53
+ import org.jruby.exceptions.RaiseException;
54
+ import org.jruby.javasupport.JavaEmbedUtils;
55
+ import org.jruby.runtime.ThreadContext;
56
+ import org.jruby.runtime.builtin.IRubyObject;
57
+ import org.xml.sax.ContentHandler;
58
+ import org.xml.sax.ErrorHandler;
59
+ import org.xml.sax.SAXException;
60
+ import org.xml.sax.SAXNotRecognizedException;
61
+ import org.xml.sax.SAXNotSupportedException;
62
+ import org.xml.sax.SAXParseException;
63
+
64
+ /**
65
+ * Base class for the SAX parsers.
66
+ *
67
+ * @author Patrick Mahoney <pat@polycrystal.org>
68
+ * @author Yoko Harada <yokolet@gmail.com>
69
+ */
70
+ @JRubyClass(name="Nokogiri::XML::SAX::ParserContext")
71
+ public class XmlSaxParserContext extends ParserContext {
72
+ protected static final String FEATURE_NAMESPACES =
73
+ "http://xml.org/sax/features/namespaces";
74
+ protected static final String FEATURE_NAMESPACE_PREFIXES =
75
+ "http://xml.org/sax/features/namespace-prefixes";
76
+ protected static final String FEATURE_LOAD_EXTERNAL_DTD =
77
+ "http://apache.org/xml/features/nonvalidating/load-external-dtd";
78
+
79
+ protected AbstractSAXParser parser;
80
+
81
+ protected NokogiriHandler handler = null;
82
+ private IRubyObject replaceEntities;
83
+
84
+ public XmlSaxParserContext(final Ruby ruby, RubyClass rubyClass) {
85
+ super(ruby, rubyClass);
86
+ }
87
+
88
+ protected void initialize(Ruby runtime) {
89
+ replaceEntities = runtime.getTrue();
90
+ try {
91
+ parser = createParser();
92
+ } catch (SAXException se) {
93
+ throw RaiseException.createNativeRaiseException(runtime, se);
94
+ }
95
+ }
96
+
97
+ /**
98
+ * Create and return a copy of this object.
99
+ *
100
+ * @return a clone of this object
101
+ */
102
+ @Override
103
+ public Object clone() throws CloneNotSupportedException {
104
+ return super.clone();
105
+ }
106
+
107
+ protected AbstractSAXParser createParser() throws SAXException {
108
+ XmlSaxParser parser = new XmlSaxParser();
109
+ parser.setFeature(FEATURE_NAMESPACE_PREFIXES, true);
110
+ parser.setFeature(FEATURE_LOAD_EXTERNAL_DTD, false);
111
+ return parser;
112
+ }
113
+
114
+ /**
115
+ * Create a new parser context that will parse the string
116
+ * <code>data</code>.
117
+ */
118
+ @JRubyMethod(name="memory", meta=true)
119
+ public static IRubyObject parse_memory(ThreadContext context,
120
+ IRubyObject klazz,
121
+ IRubyObject data) {
122
+ XmlSaxParserContext ctx = (XmlSaxParserContext) NokogiriService.XML_SAXPARSER_CONTEXT_ALLOCATOR.allocate(context.getRuntime(), (RubyClass) klazz);
123
+ ctx.initialize(context.getRuntime());
124
+ ctx.setInputSource(context, data, context.getRuntime().getNil());
125
+ return ctx;
126
+ }
127
+
128
+ /**
129
+ * Create a new parser context that will read from the file
130
+ * <code>data</code> and parse.
131
+ */
132
+ @JRubyMethod(name="file", meta=true)
133
+ public static IRubyObject parse_file(ThreadContext context,
134
+ IRubyObject klazz,
135
+ IRubyObject data) {
136
+ XmlSaxParserContext ctx = (XmlSaxParserContext) NokogiriService.XML_SAXPARSER_CONTEXT_ALLOCATOR.allocate(context.getRuntime(), (RubyClass) klazz);
137
+ ctx.initialize(context.getRuntime());
138
+ ctx.setInputSourceFile(context, data);
139
+ return ctx;
140
+ }
141
+
142
+ /**
143
+ * Create a new parser context that will read from the IO or
144
+ * StringIO <code>data</code> and parse.
145
+ *
146
+ * TODO: Currently ignores encoding <code>enc</code>.
147
+ */
148
+ @JRubyMethod(name="io", meta=true)
149
+ public static IRubyObject parse_io(ThreadContext context,
150
+ IRubyObject klazz,
151
+ IRubyObject data,
152
+ IRubyObject enc) {
153
+ //int encoding = (int)enc.convertToInteger().getLongValue();
154
+ XmlSaxParserContext ctx = (XmlSaxParserContext) NokogiriService.XML_SAXPARSER_CONTEXT_ALLOCATOR.allocate(context.getRuntime(), (RubyClass) klazz);
155
+ ctx.initialize(context.getRuntime());
156
+ ctx.setInputSource(context, data, context.getRuntime().getNil());
157
+ return ctx;
158
+ }
159
+
160
+ /**
161
+ * Create a new parser context that will read from a raw input
162
+ * stream. Not a JRuby method. Meant to be run in a separate
163
+ * thread by XmlSaxPushParser.
164
+ */
165
+ public static IRubyObject parse_stream(ThreadContext context,
166
+ IRubyObject klazz,
167
+ InputStream stream) {
168
+ XmlSaxParserContext ctx = (XmlSaxParserContext) NokogiriService.XML_SAXPARSER_CONTEXT_ALLOCATOR.allocate(context.getRuntime(), (RubyClass) klazz);
169
+ ctx.initialize(context.getRuntime());
170
+ ctx.setInputSource(stream);
171
+ return ctx;
172
+ }
173
+
174
+ /**
175
+ * Set a property of the underlying parser.
176
+ */
177
+ protected void setProperty(String key, Object val)
178
+ throws SAXNotRecognizedException, SAXNotSupportedException {
179
+ parser.setProperty(key, val);
180
+ }
181
+
182
+ protected void setContentHandler(ContentHandler handler) {
183
+ parser.setContentHandler(handler);
184
+ }
185
+
186
+ protected void setErrorHandler(ErrorHandler handler) {
187
+ parser.setErrorHandler(handler);
188
+ }
189
+
190
+ public NokogiriHandler getNokogiriHandler() {
191
+ return handler;
192
+ }
193
+
194
+ /**
195
+ * Perform any initialization prior to parsing with the handler
196
+ * <code>handlerRuby</code>. Convenience hook for subclasses.
197
+ */
198
+ protected void preParse(ThreadContext context,
199
+ IRubyObject handlerRuby,
200
+ NokogiriHandler handler) {
201
+ ((XmlSaxParser) parser).setXmlDeclHandler(handler);
202
+ }
203
+
204
+ protected void postParse(ThreadContext context,
205
+ IRubyObject handlerRuby,
206
+ NokogiriHandler handler) {
207
+ // noop
208
+ }
209
+
210
+ protected void do_parse() throws SAXException, IOException {
211
+ parser.parse(getInputSource());
212
+ }
213
+
214
+ @JRubyMethod
215
+ public IRubyObject parse_with(ThreadContext context,
216
+ IRubyObject handlerRuby) {
217
+ Ruby ruby = context.getRuntime();
218
+
219
+ if(!invoke(context, handlerRuby, "respond_to?",
220
+ ruby.newSymbol("document")).isTrue()) {
221
+ String msg = "argument must respond_to document";
222
+ throw ruby.newArgumentError(msg);
223
+ }
224
+
225
+ handler = new NokogiriHandler(ruby, handlerRuby);
226
+ preParse(context, handlerRuby, handler);
227
+
228
+ setContentHandler(handler);
229
+ setErrorHandler(handler);
230
+
231
+ try{
232
+ setProperty("http://xml.org/sax/properties/lexical-handler",
233
+ handler);
234
+ } catch(Exception ex) {
235
+ throw ruby.newRuntimeError(
236
+ "Problem while creating XML SAX Parser: " + ex.toString());
237
+ }
238
+
239
+ try{
240
+ try {
241
+ do_parse();
242
+ } catch(SAXParseException spe) {
243
+ // A bad document (<foo><bar></foo>) should call the
244
+ // error handler instead of raising a SAX exception.
245
+
246
+ // However, an EMPTY document should raise a
247
+ // RuntimeError. This is a bit kludgy, but AFAIK SAX
248
+ // doesn't distinguish between empty and bad whereas
249
+ // Nokogiri does.
250
+ String message = spe.getMessage();
251
+ if ("Premature end of file.".matches(message)) {
252
+ throw ruby.newRuntimeError(
253
+ "couldn't parse document: " + message);
254
+ } else {
255
+ handler.error(spe);
256
+ }
257
+
258
+ }
259
+ } catch(SAXException se) {
260
+ throw RaiseException.createNativeRaiseException(ruby, se);
261
+ } catch(IOException ioe) {
262
+ throw ruby.newIOErrorFromException(ioe);
263
+ }
264
+
265
+ postParse(context, handlerRuby, handler);
266
+
267
+ //maybeTrimLeadingAndTrailingWhitespace(context, handlerRuby);
268
+
269
+ return ruby.getNil();
270
+ }
271
+
272
+ /**
273
+ * Can take a boolean assignment.
274
+ *
275
+ * @param context
276
+ * @param value
277
+ * @return
278
+ */
279
+ @JRubyMethod(name = "replace_entities=")
280
+ public IRubyObject set_replace_entities(ThreadContext context,
281
+ IRubyObject value) {
282
+ if (!value.isTrue()) replaceEntities = context.getRuntime().getFalse();
283
+ else replaceEntities = context.getRuntime().getTrue();
284
+
285
+ return this;
286
+ }
287
+
288
+ @JRubyMethod(name="replace_entities")
289
+ public IRubyObject get_replace_entities(ThreadContext context) {
290
+ return replaceEntities;
291
+ }
292
+
293
+
294
+ /**
295
+ * If the handler's document is a FragmentHandler, attempt to trim
296
+ * leading and trailing whitespace.
297
+ *
298
+ * This is a bit hackish and depends heavily on the internals of
299
+ * FragmentHandler.
300
+ */
301
+ protected void maybeTrimLeadingAndTrailingWhitespace(ThreadContext context,
302
+ IRubyObject parser) {
303
+ final String path = "Nokogiri::XML::FragmentHandler";
304
+ RubyObjectAdapter adapter = JavaEmbedUtils.newObjectAdapter();
305
+ RubyModule mod =
306
+ context.getRuntime().getClassFromPath(path);
307
+
308
+ IRubyObject handler = adapter.getInstanceVariable(parser, "@document");
309
+ if (handler == null || handler.isNil() || !adapter.isKindOf(handler, mod))
310
+ return;
311
+ IRubyObject stack = adapter.getInstanceVariable(handler, "@stack");
312
+ if (stack == null || stack.isNil())
313
+ return;
314
+ // doc is finally a DocumentFragment whose nodes we can check
315
+ IRubyObject doc = adapter.callMethod(stack, "first");
316
+ if (doc == null || doc.isNil())
317
+ return;
318
+
319
+ IRubyObject children;
320
+
321
+ for (;;) {
322
+ children = adapter.callMethod(doc, "children");
323
+ IRubyObject first = adapter.callMethod(children, "first");
324
+ if (isWhitespaceText(context, first))
325
+ adapter.callMethod(first, "unlink");
326
+ else
327
+ break;
328
+ }
329
+
330
+ for (;;) {
331
+ children = adapter.callMethod(doc, "children");
332
+ IRubyObject last = adapter.callMethod(children, "last");
333
+ if (isWhitespaceText(context, last))
334
+ adapter.callMethod(last, "unlink");
335
+ else
336
+ break;
337
+ }
338
+
339
+ // While we have a document, normalize it.
340
+ ((XmlNode) doc).normalize();
341
+ }
342
+
343
+ protected boolean isWhitespaceText(ThreadContext context, IRubyObject obj) {
344
+ if (obj == null || obj.isNil()) return false;
345
+
346
+ XmlNode node = (XmlNode) obj;
347
+ if (!(node instanceof XmlText))
348
+ return false;
349
+
350
+ String content = rubyStringToString(node.content(context));
351
+ return content.trim().length() == 0;
352
+ }
353
+
354
+ @JRubyMethod(name="column")
355
+ public IRubyObject column(ThreadContext context) {
356
+ Integer number = handler.getColumn();
357
+ if (number == null) return context.getRuntime().getNil();
358
+ else return RubyFixnum.newFixnum(context.getRuntime(), number.longValue());
359
+ }
360
+
361
+ @JRubyMethod(name="line")
362
+ public IRubyObject line(ThreadContext context) {
363
+ Integer number = handler.getLine();
364
+ if (number == null) return context.getRuntime().getNil();
365
+ else return RubyFixnum.newFixnum(context.getRuntime(), number.longValue());
366
+ }
367
+ }
@@ -0,0 +1,184 @@
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
+ import static org.jruby.javasupport.util.RuntimeHelpers.invoke;
37
+
38
+ import java.io.IOException;
39
+ import java.io.InputStream;
40
+ import java.nio.channels.ClosedChannelException;
41
+
42
+ import nokogiri.internals.ParserContext;
43
+ import nokogiri.internals.PushInputStream;
44
+
45
+ import org.jruby.Ruby;
46
+ import org.jruby.RubyClass;
47
+ import org.jruby.RubyException;
48
+ import org.jruby.RubyObject;
49
+ import org.jruby.RubyString;
50
+ import org.jruby.anno.JRubyClass;
51
+ import org.jruby.anno.JRubyMethod;
52
+ import org.jruby.exceptions.RaiseException;
53
+ import org.jruby.runtime.ThreadContext;
54
+ import org.jruby.runtime.builtin.IRubyObject;
55
+
56
+ /**
57
+ * Class for Nokogiri::XML::SAX::PushParser
58
+ *
59
+ * @author Patrick Mahoney <pat@polycrystal.org>
60
+ * @author Yoko Harada <yokolet@gmail.com>
61
+ */
62
+ @JRubyClass(name="Nokogiri::XML::SAX::PushParser")
63
+ public class XmlSaxPushParser extends RubyObject {
64
+ ParserContext.Options options;
65
+ IRubyObject optionsRuby;
66
+ PushInputStream stream;
67
+ Thread reader;
68
+ Runner runner;
69
+
70
+ public XmlSaxPushParser(Ruby ruby, RubyClass rubyClass) {
71
+ super(ruby, rubyClass);
72
+ }
73
+
74
+ @JRubyMethod
75
+ public IRubyObject initialize_native(final ThreadContext context,
76
+ IRubyObject _saxParser,
77
+ IRubyObject fileName) {
78
+ optionsRuby = invoke(context,
79
+ context.getRuntime().getClassFromPath("Nokogiri::XML::ParseOptions"),
80
+ "new");
81
+ options = new ParserContext.Options(0);
82
+ stream = new PushInputStream();
83
+
84
+ runner = new Runner(context, this, stream);
85
+ reader = new Thread(runner);
86
+ reader.start();
87
+
88
+ return this;
89
+ }
90
+
91
+ /**
92
+ * Returns an integer.
93
+ */
94
+ @JRubyMethod(name="options")
95
+ public IRubyObject getOptions(ThreadContext context) {
96
+ return invoke(context, optionsRuby, "options");
97
+ }
98
+
99
+ /**
100
+ * <code>val</code> is an integer.
101
+ */
102
+ @JRubyMethod(name="options=")
103
+ public IRubyObject setOptions(ThreadContext context, IRubyObject val) {
104
+ invoke(context, optionsRuby, "options=", val);
105
+ options =
106
+ new ParserContext.Options(val.convertToInteger().getLongValue());
107
+ return getOptions(context);
108
+ }
109
+
110
+ @JRubyMethod
111
+ public IRubyObject native_write(ThreadContext context, IRubyObject chunk,
112
+ IRubyObject isLast) {
113
+ byte[] data = null;
114
+ if (chunk instanceof RubyString || chunk.respondsTo("to_str")) {
115
+ data = chunk.convertToString().getBytes();
116
+ } else {
117
+ XmlSyntaxError xmlSyntaxError = (XmlSyntaxError) NokogiriService.XML_SYNTAXERROR_ALLOCATOR.allocate(context.getRuntime(), getNokogiriClass(context.getRuntime(), "Nokogiri::XML::SyntaxError"));
118
+ throw new RaiseException(xmlSyntaxError);
119
+ }
120
+
121
+ int errorCount0 = runner.getErrorCount();
122
+
123
+ try {
124
+ stream.writeAndWaitForRead(data);
125
+ } catch (ClosedChannelException e) {
126
+ // ignore
127
+ } catch (IOException e) {
128
+ throw context.getRuntime().newRuntimeError(e.toString());
129
+ }
130
+
131
+ if (isLast.isTrue()) {
132
+ try {
133
+ stream.close();
134
+ } catch (IOException e) {
135
+ // ignore
136
+ }
137
+
138
+ for (;;) {
139
+ try {
140
+ reader.join();
141
+ break;
142
+ } catch (InterruptedException e) {
143
+ // continue loop
144
+ }
145
+ }
146
+ }
147
+
148
+ if (!options.recover && runner.getErrorCount() > errorCount0) {
149
+ throw new RaiseException(runner.getLastError(), true);
150
+ }
151
+
152
+ return this;
153
+ }
154
+
155
+ protected static class Runner implements Runnable {
156
+ protected ThreadContext context;
157
+ protected IRubyObject handler;
158
+ protected XmlSaxParserContext parser;
159
+
160
+ public Runner(ThreadContext context,
161
+ IRubyObject handler,
162
+ InputStream stream) {
163
+ RubyClass klazz = getNokogiriClass(context.getRuntime(), "Nokogiri::XML::SAX::ParserContext");
164
+
165
+ this.context = context;
166
+ this.handler = handler;
167
+ this.parser = (XmlSaxParserContext) XmlSaxParserContext.parse_stream(context, klazz, stream);
168
+ }
169
+
170
+ public void run() {
171
+ parser.parse_with(context, handler);
172
+ }
173
+
174
+ public int getErrorCount() {
175
+ // check for null because thread may nto have started yet
176
+ if (parser.getNokogiriHandler() == null) return 0;
177
+ else return parser.getNokogiriHandler().getErrorCount();
178
+ }
179
+
180
+ public RubyException getLastError() {
181
+ return (RubyException) parser.getNokogiriHandler().getLastError();
182
+ }
183
+ }
184
+ }