nokogiri 1.2.3-x86-mswin32-60 → 1.4.5-x86-mswin32-60
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.
Potentially problematic release.
This version of nokogiri might be problematic. Click here for more details.
- data/.autotest +18 -7
- data/.gemtest +0 -0
- data/CHANGELOG.ja.rdoc +297 -3
- data/CHANGELOG.rdoc +289 -0
- data/Manifest.txt +148 -37
- data/README.ja.rdoc +20 -20
- data/README.rdoc +53 -22
- data/Rakefile +127 -211
- data/bin/nokogiri +54 -0
- data/ext/nokogiri/depend +358 -0
- data/ext/nokogiri/extconf.rb +89 -54
- data/ext/nokogiri/html_document.c +34 -27
- data/ext/nokogiri/html_document.h +1 -1
- data/ext/nokogiri/html_element_description.c +276 -0
- data/ext/nokogiri/html_element_description.h +10 -0
- data/ext/nokogiri/html_entity_lookup.c +7 -5
- data/ext/nokogiri/html_entity_lookup.h +1 -1
- data/ext/nokogiri/html_sax_parser_context.c +94 -0
- data/ext/nokogiri/html_sax_parser_context.h +11 -0
- data/ext/nokogiri/{native.c → nokogiri.c} +31 -7
- data/ext/nokogiri/{native.h → nokogiri.h} +68 -41
- data/ext/nokogiri/xml_attr.c +20 -9
- data/ext/nokogiri/xml_attr.h +1 -1
- data/ext/nokogiri/xml_attribute_decl.c +70 -0
- data/ext/nokogiri/xml_attribute_decl.h +9 -0
- data/ext/nokogiri/xml_cdata.c +21 -9
- data/ext/nokogiri/xml_cdata.h +1 -1
- data/ext/nokogiri/xml_comment.c +18 -6
- data/ext/nokogiri/xml_comment.h +1 -1
- data/ext/nokogiri/xml_document.c +247 -68
- data/ext/nokogiri/xml_document.h +5 -3
- data/ext/nokogiri/xml_document_fragment.c +15 -7
- data/ext/nokogiri/xml_document_fragment.h +1 -1
- data/ext/nokogiri/xml_dtd.c +110 -10
- data/ext/nokogiri/xml_dtd.h +3 -1
- data/ext/nokogiri/xml_element_content.c +123 -0
- data/ext/nokogiri/xml_element_content.h +10 -0
- data/ext/nokogiri/xml_element_decl.c +69 -0
- data/ext/nokogiri/xml_element_decl.h +9 -0
- data/ext/nokogiri/xml_encoding_handler.c +79 -0
- data/ext/nokogiri/xml_encoding_handler.h +8 -0
- data/ext/nokogiri/xml_entity_decl.c +110 -0
- data/ext/nokogiri/xml_entity_decl.h +10 -0
- data/ext/nokogiri/xml_entity_reference.c +16 -5
- data/ext/nokogiri/xml_entity_reference.h +1 -1
- data/ext/nokogiri/xml_io.c +40 -8
- data/ext/nokogiri/xml_io.h +2 -1
- data/ext/nokogiri/xml_libxml2_hacks.c +112 -0
- data/ext/nokogiri/xml_libxml2_hacks.h +12 -0
- data/ext/nokogiri/xml_namespace.c +84 -0
- data/ext/nokogiri/xml_namespace.h +13 -0
- data/ext/nokogiri/xml_node.c +782 -225
- data/ext/nokogiri/xml_node.h +2 -4
- data/ext/nokogiri/xml_node_set.c +253 -34
- data/ext/nokogiri/xml_node_set.h +2 -2
- data/ext/nokogiri/xml_processing_instruction.c +17 -5
- data/ext/nokogiri/xml_processing_instruction.h +1 -1
- data/ext/nokogiri/xml_reader.c +277 -85
- data/ext/nokogiri/xml_reader.h +1 -1
- data/ext/nokogiri/xml_relax_ng.c +168 -0
- data/ext/nokogiri/xml_relax_ng.h +9 -0
- data/ext/nokogiri/xml_sax_parser.c +183 -111
- data/ext/nokogiri/xml_sax_parser.h +30 -1
- data/ext/nokogiri/xml_sax_parser_context.c +199 -0
- data/ext/nokogiri/xml_sax_parser_context.h +10 -0
- data/ext/nokogiri/xml_sax_push_parser.c +42 -12
- data/ext/nokogiri/xml_sax_push_parser.h +1 -1
- data/ext/nokogiri/xml_schema.c +205 -0
- data/ext/nokogiri/xml_schema.h +9 -0
- data/ext/nokogiri/xml_syntax_error.c +28 -173
- data/ext/nokogiri/xml_syntax_error.h +2 -1
- data/ext/nokogiri/xml_text.c +16 -6
- data/ext/nokogiri/xml_text.h +1 -1
- data/ext/nokogiri/xml_xpath_context.c +104 -47
- data/ext/nokogiri/xml_xpath_context.h +1 -1
- data/ext/nokogiri/xslt_stylesheet.c +161 -19
- data/ext/nokogiri/xslt_stylesheet.h +1 -1
- data/lib/nokogiri.rb +47 -8
- data/lib/nokogiri/1.8/nokogiri.so +0 -0
- data/lib/nokogiri/1.9/nokogiri.so +0 -0
- data/lib/nokogiri/css.rb +6 -3
- data/lib/nokogiri/css/node.rb +14 -12
- data/lib/nokogiri/css/parser.rb +665 -62
- data/lib/nokogiri/css/parser.y +20 -10
- data/lib/nokogiri/css/parser_extras.rb +91 -0
- data/lib/nokogiri/css/tokenizer.rb +148 -5
- data/lib/nokogiri/css/tokenizer.rex +10 -9
- data/lib/nokogiri/css/xpath_visitor.rb +47 -44
- data/lib/nokogiri/decorators/slop.rb +8 -4
- data/lib/nokogiri/ffi/encoding_handler.rb +42 -0
- data/lib/nokogiri/ffi/html/document.rb +28 -0
- data/lib/nokogiri/ffi/html/element_description.rb +81 -0
- data/lib/nokogiri/ffi/html/entity_lookup.rb +16 -0
- data/lib/nokogiri/ffi/html/sax/parser_context.rb +38 -0
- data/lib/nokogiri/ffi/io_callbacks.rb +42 -0
- data/lib/nokogiri/ffi/libxml.rb +420 -0
- data/lib/nokogiri/ffi/structs/common_node.rb +38 -0
- data/lib/nokogiri/ffi/structs/html_elem_desc.rb +24 -0
- data/lib/nokogiri/ffi/structs/html_entity_desc.rb +13 -0
- data/lib/nokogiri/ffi/structs/xml_alloc.rb +16 -0
- data/lib/nokogiri/ffi/structs/xml_attr.rb +20 -0
- data/lib/nokogiri/ffi/structs/xml_attribute.rb +27 -0
- data/lib/nokogiri/ffi/structs/xml_buffer.rb +16 -0
- data/lib/nokogiri/ffi/structs/xml_char_encoding_handler.rb +11 -0
- data/lib/nokogiri/ffi/structs/xml_document.rb +117 -0
- data/lib/nokogiri/ffi/structs/xml_dtd.rb +28 -0
- data/lib/nokogiri/ffi/structs/xml_element.rb +26 -0
- data/lib/nokogiri/ffi/structs/xml_element_content.rb +17 -0
- data/lib/nokogiri/ffi/structs/xml_entity.rb +32 -0
- data/lib/nokogiri/ffi/structs/xml_enumeration.rb +12 -0
- data/lib/nokogiri/ffi/structs/xml_node.rb +28 -0
- data/lib/nokogiri/ffi/structs/xml_node_set.rb +53 -0
- data/lib/nokogiri/ffi/structs/xml_notation.rb +11 -0
- data/lib/nokogiri/ffi/structs/xml_ns.rb +15 -0
- data/lib/nokogiri/ffi/structs/xml_parser_context.rb +20 -0
- data/lib/nokogiri/ffi/structs/xml_parser_input.rb +19 -0
- data/lib/nokogiri/ffi/structs/xml_relax_ng.rb +14 -0
- data/lib/nokogiri/ffi/structs/xml_sax_handler.rb +51 -0
- data/lib/nokogiri/ffi/structs/xml_sax_push_parser_context.rb +124 -0
- data/lib/nokogiri/ffi/structs/xml_schema.rb +13 -0
- data/lib/nokogiri/ffi/structs/xml_syntax_error.rb +31 -0
- data/lib/nokogiri/ffi/structs/xml_text_reader.rb +12 -0
- data/lib/nokogiri/ffi/structs/xml_xpath_context.rb +38 -0
- data/lib/nokogiri/ffi/structs/xml_xpath_object.rb +35 -0
- data/lib/nokogiri/ffi/structs/xml_xpath_parser_context.rb +20 -0
- data/lib/nokogiri/ffi/structs/xslt_stylesheet.rb +13 -0
- data/lib/nokogiri/ffi/weak_bucket.rb +40 -0
- data/lib/nokogiri/ffi/xml/attr.rb +41 -0
- data/lib/nokogiri/ffi/xml/attribute_decl.rb +27 -0
- data/lib/nokogiri/ffi/xml/cdata.rb +19 -0
- data/lib/nokogiri/ffi/xml/comment.rb +18 -0
- data/lib/nokogiri/ffi/xml/document.rb +174 -0
- data/lib/nokogiri/ffi/xml/document_fragment.rb +21 -0
- data/lib/nokogiri/ffi/xml/dtd.rb +67 -0
- data/lib/nokogiri/ffi/xml/element_content.rb +43 -0
- data/lib/nokogiri/ffi/xml/element_decl.rb +19 -0
- data/lib/nokogiri/ffi/xml/entity_decl.rb +36 -0
- data/lib/nokogiri/ffi/xml/entity_reference.rb +19 -0
- data/lib/nokogiri/ffi/xml/namespace.rb +44 -0
- data/lib/nokogiri/ffi/xml/node.rb +559 -0
- data/lib/nokogiri/ffi/xml/node_set.rb +150 -0
- data/lib/nokogiri/ffi/xml/processing_instruction.rb +20 -0
- data/lib/nokogiri/ffi/xml/reader.rb +236 -0
- data/lib/nokogiri/ffi/xml/relax_ng.rb +85 -0
- data/lib/nokogiri/ffi/xml/sax/parser.rb +143 -0
- data/lib/nokogiri/ffi/xml/sax/parser_context.rb +79 -0
- data/lib/nokogiri/ffi/xml/sax/push_parser.rb +51 -0
- data/lib/nokogiri/ffi/xml/schema.rb +109 -0
- data/lib/nokogiri/ffi/xml/syntax_error.rb +98 -0
- data/lib/nokogiri/ffi/xml/text.rb +18 -0
- data/lib/nokogiri/ffi/xml/xpath.rb +9 -0
- data/lib/nokogiri/ffi/xml/xpath_context.rb +153 -0
- data/lib/nokogiri/ffi/xslt/stylesheet.rb +77 -0
- data/lib/nokogiri/html.rb +13 -47
- data/lib/nokogiri/html/builder.rb +27 -1
- data/lib/nokogiri/html/document.rb +201 -7
- data/lib/nokogiri/html/document_fragment.rb +41 -0
- data/lib/nokogiri/html/element_description.rb +23 -0
- data/lib/nokogiri/html/entity_lookup.rb +2 -0
- data/lib/nokogiri/html/sax/parser.rb +34 -3
- data/lib/nokogiri/html/sax/parser_context.rb +16 -0
- data/lib/nokogiri/nokogiri.rb +1 -0
- data/lib/nokogiri/version.rb +40 -1
- data/lib/nokogiri/version_warning.rb +14 -0
- data/lib/nokogiri/xml.rb +32 -53
- data/lib/nokogiri/xml/attr.rb +5 -0
- data/lib/nokogiri/xml/attribute_decl.rb +18 -0
- data/lib/nokogiri/xml/builder.rb +349 -29
- data/lib/nokogiri/xml/cdata.rb +3 -1
- data/lib/nokogiri/xml/character_data.rb +7 -0
- data/lib/nokogiri/xml/document.rb +166 -14
- data/lib/nokogiri/xml/document_fragment.rb +76 -1
- data/lib/nokogiri/xml/dtd.rb +16 -3
- data/lib/nokogiri/xml/element_content.rb +36 -0
- data/lib/nokogiri/xml/element_decl.rb +13 -0
- data/lib/nokogiri/xml/entity_decl.rb +19 -0
- data/lib/nokogiri/xml/namespace.rb +13 -0
- data/lib/nokogiri/xml/node.rb +561 -166
- data/lib/nokogiri/xml/node/save_options.rb +22 -2
- data/lib/nokogiri/xml/node_set.rb +202 -40
- data/lib/nokogiri/xml/parse_options.rb +93 -0
- data/lib/nokogiri/xml/pp.rb +2 -0
- data/lib/nokogiri/xml/pp/character_data.rb +18 -0
- data/lib/nokogiri/xml/pp/node.rb +56 -0
- data/lib/nokogiri/xml/processing_instruction.rb +2 -0
- data/lib/nokogiri/xml/reader.rb +93 -8
- data/lib/nokogiri/xml/relax_ng.rb +32 -0
- data/lib/nokogiri/xml/sax.rb +1 -7
- data/lib/nokogiri/xml/sax/document.rb +107 -2
- data/lib/nokogiri/xml/sax/parser.rb +57 -7
- data/lib/nokogiri/xml/sax/parser_context.rb +16 -0
- data/lib/nokogiri/xml/sax/push_parser.rb +13 -1
- data/lib/nokogiri/xml/schema.rb +63 -0
- data/lib/nokogiri/xml/syntax_error.rb +25 -1
- data/lib/nokogiri/xml/text.rb +4 -1
- data/lib/nokogiri/xml/xpath.rb +1 -1
- data/lib/nokogiri/xml/xpath/syntax_error.rb +3 -0
- data/lib/nokogiri/xml/xpath_context.rb +2 -0
- data/lib/nokogiri/xslt.rb +26 -2
- data/lib/nokogiri/xslt/stylesheet.rb +19 -0
- data/lib/xsd/xmlparser/nokogiri.rb +45 -9
- data/tasks/cross_compile.rb +173 -0
- data/tasks/test.rb +25 -69
- data/test/css/test_nthiness.rb +3 -4
- data/test/css/test_parser.rb +75 -20
- data/test/css/test_tokenizer.rb +23 -1
- data/test/css/test_xpath_visitor.rb +10 -1
- data/test/decorators/test_slop.rb +16 -0
- data/test/ffi/test_document.rb +35 -0
- data/test/files/2ch.html +108 -0
- data/test/files/address_book.rlx +12 -0
- data/test/files/address_book.xml +10 -0
- data/test/files/bar/bar.xsd +4 -0
- data/test/files/encoding.html +82 -0
- data/test/files/encoding.xhtml +84 -0
- data/test/files/foo/foo.xsd +4 -0
- data/test/files/po.xml +32 -0
- data/test/files/po.xsd +66 -0
- data/test/files/shift_jis.html +10 -0
- data/test/files/shift_jis.xml +5 -0
- data/test/files/snuggles.xml +3 -0
- data/test/files/staff.dtd +10 -0
- data/test/files/valid_bar.xml +2 -0
- data/test/helper.rb +101 -23
- data/test/html/sax/test_parser.rb +81 -2
- data/test/html/sax/test_parser_context.rb +48 -0
- data/test/html/test_builder.rb +39 -8
- data/test/html/test_document.rb +186 -23
- data/test/html/test_document_encoding.rb +78 -1
- data/test/html/test_document_fragment.rb +253 -0
- data/test/html/test_element_description.rb +98 -0
- data/test/html/test_named_characters.rb +1 -1
- data/test/html/test_node.rb +124 -36
- data/test/html/test_node_encoding.rb +27 -0
- data/test/test_convert_xpath.rb +1 -52
- data/test/test_css_cache.rb +2 -13
- data/test/test_encoding_handler.rb +46 -0
- data/test/test_memory_leak.rb +88 -19
- data/test/test_nokogiri.rb +38 -5
- data/test/test_reader.rb +188 -6
- data/test/test_soap4r_sax.rb +52 -0
- data/test/test_xslt_transforms.rb +183 -83
- data/test/xml/node/test_save_options.rb +1 -1
- data/test/xml/node/test_subclass.rb +44 -0
- data/test/xml/sax/test_parser.rb +175 -4
- data/test/xml/sax/test_parser_context.rb +113 -0
- data/test/xml/sax/test_push_parser.rb +90 -2
- data/test/xml/test_attr.rb +35 -1
- data/test/xml/test_attribute_decl.rb +82 -0
- data/test/xml/test_builder.rb +186 -1
- data/test/xml/test_cdata.rb +32 -1
- data/test/xml/test_comment.rb +13 -1
- data/test/xml/test_document.rb +415 -43
- data/test/xml/test_document_encoding.rb +1 -1
- data/test/xml/test_document_fragment.rb +173 -5
- data/test/xml/test_dtd.rb +61 -6
- data/test/xml/test_dtd_encoding.rb +3 -1
- data/test/xml/test_element_content.rb +56 -0
- data/test/xml/test_element_decl.rb +73 -0
- data/test/xml/test_entity_decl.rb +120 -0
- data/test/xml/test_entity_reference.rb +5 -1
- data/test/xml/test_namespace.rb +68 -0
- data/test/xml/test_node.rb +546 -201
- data/test/xml/test_node_attributes.rb +34 -0
- data/test/xml/test_node_encoding.rb +33 -3
- data/test/xml/test_node_reparenting.rb +321 -0
- data/test/xml/test_node_set.rb +538 -2
- data/test/xml/test_parse_options.rb +52 -0
- data/test/xml/test_processing_instruction.rb +6 -1
- data/test/xml/test_reader_encoding.rb +1 -1
- data/test/xml/test_relax_ng.rb +60 -0
- data/test/xml/test_schema.rb +94 -0
- data/test/xml/test_syntax_error.rb +12 -0
- data/test/xml/test_text.rb +35 -1
- data/test/xml/test_unparented_node.rb +5 -5
- data/test/xml/test_xpath.rb +142 -11
- data/test/xslt/test_custom_functions.rb +94 -0
- metadata +328 -92
- data/ext/nokogiri/html_sax_parser.c +0 -57
- data/ext/nokogiri/html_sax_parser.h +0 -11
- data/ext/nokogiri/iconv.dll +0 -0
- data/ext/nokogiri/libexslt.dll +0 -0
- data/ext/nokogiri/libxml2.dll +0 -0
- data/ext/nokogiri/libxslt.dll +0 -0
- data/ext/nokogiri/native.so +0 -0
- data/ext/nokogiri/xml_xpath.c +0 -53
- data/ext/nokogiri/xml_xpath.h +0 -11
- data/ext/nokogiri/zlib1.dll +0 -0
- data/lib/action-nokogiri.rb +0 -30
- data/lib/nokogiri/css/generated_parser.rb +0 -713
- data/lib/nokogiri/css/generated_tokenizer.rb +0 -144
- data/lib/nokogiri/decorators.rb +0 -2
- data/lib/nokogiri/decorators/hpricot.rb +0 -3
- data/lib/nokogiri/decorators/hpricot/node.rb +0 -56
- data/lib/nokogiri/decorators/hpricot/node_set.rb +0 -54
- data/lib/nokogiri/decorators/hpricot/xpath_visitor.rb +0 -28
- data/lib/nokogiri/hpricot.rb +0 -51
- data/lib/nokogiri/xml/comment.rb +0 -6
- data/lib/nokogiri/xml/element.rb +0 -6
- data/lib/nokogiri/xml/entity_declaration.rb +0 -9
- data/lib/nokogiri/xml/fragment_handler.rb +0 -34
- data/test/hpricot/files/basic.xhtml +0 -17
- data/test/hpricot/files/boingboing.html +0 -2266
- data/test/hpricot/files/cy0.html +0 -3653
- data/test/hpricot/files/immob.html +0 -400
- data/test/hpricot/files/pace_application.html +0 -1320
- data/test/hpricot/files/tenderlove.html +0 -16
- data/test/hpricot/files/uswebgen.html +0 -220
- data/test/hpricot/files/utf8.html +0 -1054
- data/test/hpricot/files/week9.html +0 -1723
- data/test/hpricot/files/why.xml +0 -19
- data/test/hpricot/load_files.rb +0 -11
- data/test/hpricot/test_alter.rb +0 -68
- data/test/hpricot/test_builder.rb +0 -20
- data/test/hpricot/test_parser.rb +0 -426
- data/test/hpricot/test_paths.rb +0 -15
- data/test/hpricot/test_preserved.rb +0 -77
- data/test/hpricot/test_xml.rb +0 -30
- data/test/test_gc.rb +0 -15
@@ -0,0 +1,94 @@
|
|
1
|
+
#include <html_sax_parser_context.h>
|
2
|
+
|
3
|
+
VALUE cNokogiriHtmlSaxParserContext ;
|
4
|
+
|
5
|
+
static void deallocate(xmlParserCtxtPtr ctxt)
|
6
|
+
{
|
7
|
+
NOKOGIRI_DEBUG_START(handler);
|
8
|
+
|
9
|
+
ctxt->sax = NULL;
|
10
|
+
|
11
|
+
htmlFreeParserCtxt(ctxt);
|
12
|
+
|
13
|
+
NOKOGIRI_DEBUG_END(handler);
|
14
|
+
}
|
15
|
+
|
16
|
+
static VALUE parse_memory(VALUE klass, VALUE data, VALUE encoding)
|
17
|
+
{
|
18
|
+
htmlParserCtxtPtr ctxt;
|
19
|
+
|
20
|
+
if(NIL_P(data)) rb_raise(rb_eArgError, "data cannot be nil");
|
21
|
+
if(!(int)RSTRING_LEN(data))
|
22
|
+
rb_raise(rb_eRuntimeError, "data cannot be empty");
|
23
|
+
|
24
|
+
ctxt = htmlCreateMemoryParserCtxt(
|
25
|
+
StringValuePtr(data),
|
26
|
+
(int)RSTRING_LEN(data)
|
27
|
+
);
|
28
|
+
|
29
|
+
if(RTEST(encoding)) {
|
30
|
+
xmlCharEncodingHandlerPtr enc = xmlFindCharEncodingHandler(StringValuePtr(encoding));
|
31
|
+
if(enc != NULL) {
|
32
|
+
xmlSwitchToEncoding(ctxt, enc);
|
33
|
+
if(ctxt->errNo == XML_ERR_UNSUPPORTED_ENCODING) {
|
34
|
+
rb_raise(rb_eRuntimeError, "Unsupported encoding %s",
|
35
|
+
StringValuePtr(encoding));
|
36
|
+
}
|
37
|
+
}
|
38
|
+
}
|
39
|
+
|
40
|
+
return Data_Wrap_Struct(klass, NULL, deallocate, ctxt);
|
41
|
+
}
|
42
|
+
|
43
|
+
static VALUE parse_file(VALUE klass, VALUE filename, VALUE encoding)
|
44
|
+
{
|
45
|
+
htmlParserCtxtPtr ctxt = htmlCreateFileParserCtxt(
|
46
|
+
StringValuePtr(filename),
|
47
|
+
StringValuePtr(encoding)
|
48
|
+
);
|
49
|
+
return Data_Wrap_Struct(klass, NULL, deallocate, ctxt);
|
50
|
+
}
|
51
|
+
|
52
|
+
static VALUE parse_with(VALUE self, VALUE sax_handler)
|
53
|
+
{
|
54
|
+
htmlParserCtxtPtr ctxt;
|
55
|
+
htmlSAXHandlerPtr sax;
|
56
|
+
|
57
|
+
if(!rb_obj_is_kind_of(sax_handler, cNokogiriXmlSaxParser))
|
58
|
+
rb_raise(rb_eArgError, "argument must be a Nokogiri::XML::SAX::Parser");
|
59
|
+
|
60
|
+
Data_Get_Struct(self, htmlParserCtxt, ctxt);
|
61
|
+
Data_Get_Struct(sax_handler, htmlSAXHandler, sax);
|
62
|
+
|
63
|
+
/* Free the sax handler since we'll assign our own */
|
64
|
+
if(ctxt->sax && ctxt->sax != (xmlSAXHandlerPtr)&xmlDefaultSAXHandler)
|
65
|
+
xmlFree(ctxt->sax);
|
66
|
+
|
67
|
+
ctxt->sax = sax;
|
68
|
+
ctxt->userData = (void *)NOKOGIRI_SAX_TUPLE_NEW(ctxt, sax_handler);
|
69
|
+
|
70
|
+
htmlParseDocument(ctxt);
|
71
|
+
|
72
|
+
if(NULL != ctxt->myDoc) xmlFreeDoc(ctxt->myDoc);
|
73
|
+
|
74
|
+
NOKOGIRI_SAX_TUPLE_DESTROY(ctxt->userData);
|
75
|
+
return self;
|
76
|
+
}
|
77
|
+
|
78
|
+
void init_html_sax_parser_context()
|
79
|
+
{
|
80
|
+
VALUE nokogiri = rb_define_module("Nokogiri");
|
81
|
+
VALUE xml = rb_define_module_under(nokogiri, "XML");
|
82
|
+
VALUE html = rb_define_module_under(nokogiri, "HTML");
|
83
|
+
VALUE sax = rb_define_module_under(xml, "SAX");
|
84
|
+
VALUE hsax = rb_define_module_under(html, "SAX");
|
85
|
+
VALUE pc = rb_define_class_under(sax, "ParserContext", rb_cObject);
|
86
|
+
VALUE klass = rb_define_class_under(hsax, "ParserContext", pc);
|
87
|
+
|
88
|
+
cNokogiriHtmlSaxParserContext = klass;
|
89
|
+
|
90
|
+
rb_define_singleton_method(klass, "memory", parse_memory, 2);
|
91
|
+
rb_define_singleton_method(klass, "file", parse_file, 2);
|
92
|
+
|
93
|
+
rb_define_method(klass, "parse_with", parse_with, 1);
|
94
|
+
}
|
@@ -1,4 +1,4 @@
|
|
1
|
-
#include <
|
1
|
+
#include <nokogiri.h>
|
2
2
|
|
3
3
|
VALUE mNokogiri ;
|
4
4
|
VALUE mNokogiriXml ;
|
@@ -7,7 +7,7 @@ VALUE mNokogiriXslt ;
|
|
7
7
|
VALUE mNokogiriXmlSax ;
|
8
8
|
VALUE mNokogiriHtmlSax ;
|
9
9
|
|
10
|
-
#ifdef
|
10
|
+
#ifdef USE_INCLUDED_VASPRINTF
|
11
11
|
/*
|
12
12
|
* I srsly hate windows. it doesn't have vasprintf.
|
13
13
|
* Thank you Geoffroy Couprie for this implementation of vasprintf!
|
@@ -23,15 +23,21 @@ int vasprintf (char **strp, const char *fmt, va_list ap)
|
|
23
23
|
}
|
24
24
|
#endif
|
25
25
|
|
26
|
+
int is_2_6_16(void)
|
27
|
+
{
|
28
|
+
return (strcmp(xmlParserVersion, "20616") <= 0) ? 1 : 0 ;
|
29
|
+
}
|
26
30
|
|
27
|
-
void
|
31
|
+
void Init_nokogiri()
|
28
32
|
{
|
33
|
+
#ifndef __MACRUBY__
|
29
34
|
xmlMemSetup(
|
30
35
|
(xmlFreeFunc)ruby_xfree,
|
31
36
|
(xmlMallocFunc)ruby_xmalloc,
|
32
37
|
(xmlReallocFunc)ruby_xrealloc,
|
33
38
|
strdup
|
34
39
|
);
|
40
|
+
#endif
|
35
41
|
|
36
42
|
mNokogiri = rb_define_module("Nokogiri");
|
37
43
|
mNokogiriXml = rb_define_module_under(mNokogiri, "XML");
|
@@ -42,13 +48,21 @@ void Init_native()
|
|
42
48
|
|
43
49
|
rb_const_set( mNokogiri,
|
44
50
|
rb_intern("LIBXML_VERSION"),
|
45
|
-
NOKOGIRI_STR_NEW2(LIBXML_DOTTED_VERSION
|
51
|
+
NOKOGIRI_STR_NEW2(LIBXML_DOTTED_VERSION)
|
46
52
|
);
|
47
53
|
rb_const_set( mNokogiri,
|
48
54
|
rb_intern("LIBXML_PARSER_VERSION"),
|
49
|
-
NOKOGIRI_STR_NEW2(xmlParserVersion
|
55
|
+
NOKOGIRI_STR_NEW2(xmlParserVersion)
|
50
56
|
);
|
51
57
|
|
58
|
+
#ifdef LIBXML_ICONV_ENABLED
|
59
|
+
rb_const_set(mNokogiri, rb_intern("LIBXML_ICONV_ENABLED"), Qtrue);
|
60
|
+
#else
|
61
|
+
rb_const_set(mNokogiri, rb_intern("LIBXML_ICONV_ENABLED"), Qfalse);
|
62
|
+
#endif
|
63
|
+
|
64
|
+
xmlInitParser();
|
65
|
+
|
52
66
|
init_xml_document();
|
53
67
|
init_html_document();
|
54
68
|
init_xml_node();
|
@@ -61,13 +75,23 @@ void Init_native()
|
|
61
75
|
init_xml_comment();
|
62
76
|
init_xml_node_set();
|
63
77
|
init_xml_xpath_context();
|
64
|
-
|
78
|
+
init_xml_sax_parser_context();
|
65
79
|
init_xml_sax_parser();
|
66
80
|
init_xml_sax_push_parser();
|
67
81
|
init_xml_reader();
|
68
82
|
init_xml_dtd();
|
69
|
-
|
83
|
+
init_xml_element_content();
|
84
|
+
init_xml_attribute_decl();
|
85
|
+
init_xml_element_decl();
|
86
|
+
init_xml_entity_decl();
|
87
|
+
init_xml_namespace();
|
88
|
+
init_html_sax_parser_context();
|
70
89
|
init_xslt_stylesheet();
|
71
90
|
init_xml_syntax_error();
|
72
91
|
init_html_entity_lookup();
|
92
|
+
init_html_element_description();
|
93
|
+
init_xml_schema();
|
94
|
+
init_xml_relax_ng();
|
95
|
+
init_nokogiri_io();
|
96
|
+
init_xml_encoding_handler();
|
73
97
|
}
|
@@ -2,16 +2,41 @@
|
|
2
2
|
#define NOKOGIRI_NATIVE
|
3
3
|
|
4
4
|
#include <stdlib.h>
|
5
|
+
#include <string.h>
|
5
6
|
#include <assert.h>
|
6
|
-
#include <
|
7
|
+
#include <stdarg.h>
|
8
|
+
|
9
|
+
#ifdef USE_INCLUDED_VASPRINTF
|
10
|
+
int vasprintf (char **strp, const char *fmt, va_list ap);
|
11
|
+
#else
|
12
|
+
|
13
|
+
#define _GNU_SOURCE
|
14
|
+
# include <stdio.h>
|
15
|
+
#undef _GNU_SOURCE
|
16
|
+
|
17
|
+
#endif
|
18
|
+
|
7
19
|
#include <libxml/parser.h>
|
20
|
+
#include <libxml/entities.h>
|
21
|
+
#include <libxml/parserInternals.h>
|
8
22
|
#include <libxml/xpath.h>
|
9
23
|
#include <libxml/xpathInternals.h>
|
10
24
|
#include <libxml/xmlreader.h>
|
11
25
|
#include <libxml/xmlsave.h>
|
26
|
+
#include <libxml/xmlschemas.h>
|
12
27
|
#include <libxml/HTMLparser.h>
|
13
28
|
#include <libxml/HTMLtree.h>
|
29
|
+
#include <libxml/relaxng.h>
|
30
|
+
#include <libxslt/extensions.h>
|
31
|
+
#include <ruby.h>
|
14
32
|
|
33
|
+
#ifdef HAVE_RUBY_ENCODING_H
|
34
|
+
#include <ruby/st.h>
|
35
|
+
#else
|
36
|
+
#include <st.h>
|
37
|
+
#endif
|
38
|
+
|
39
|
+
int is_2_6_16(void) ;
|
15
40
|
|
16
41
|
#ifndef UNUSED
|
17
42
|
# if defined(__GNUC__)
|
@@ -23,48 +48,37 @@
|
|
23
48
|
# endif
|
24
49
|
#endif
|
25
50
|
|
51
|
+
#ifndef NORETURN
|
52
|
+
# if defined(__GNUC__)
|
53
|
+
# define NORETURN(name) __attribute__((noreturn)) name
|
54
|
+
# else
|
55
|
+
# define NORETURN(name) name
|
56
|
+
# endif
|
57
|
+
#endif
|
58
|
+
|
26
59
|
#ifdef HAVE_RUBY_ENCODING_H
|
27
60
|
|
28
61
|
#include <ruby/encoding.h>
|
29
62
|
|
30
|
-
#define NOKOGIRI_STR_NEW2(str
|
31
|
-
(
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
if(_enc == -1) \
|
36
|
-
rb_enc_associate_index(_string, rb_enc_find_index("ASCII")); \
|
37
|
-
else \
|
38
|
-
rb_enc_associate_index(_string, _enc); \
|
39
|
-
} \
|
40
|
-
_string; \
|
41
|
-
})
|
42
|
-
|
43
|
-
#define NOKOGIRI_STR_NEW(str, len, encoding) \
|
44
|
-
({ \
|
45
|
-
VALUE _string = rb_str_new((const char *)str, (long)len); \
|
46
|
-
if(NULL != encoding) { \
|
47
|
-
int _enc = rb_enc_find_index(encoding); \
|
48
|
-
if(_enc == -1) \
|
49
|
-
rb_enc_associate_index(_string, rb_enc_find_index("ASCII")); \
|
50
|
-
else \
|
51
|
-
rb_enc_associate_index(_string, _enc); \
|
52
|
-
} \
|
53
|
-
_string; \
|
54
|
-
})
|
63
|
+
#define NOKOGIRI_STR_NEW2(str) \
|
64
|
+
NOKOGIRI_STR_NEW(str, strlen((const char *)(str)))
|
65
|
+
|
66
|
+
#define NOKOGIRI_STR_NEW(str, len) \
|
67
|
+
rb_external_str_new_with_enc((const char *)(str), (long)(len), rb_utf8_encoding())
|
55
68
|
|
56
69
|
#else
|
57
70
|
|
58
|
-
#define NOKOGIRI_STR_NEW2(str
|
59
|
-
rb_str_new2((const char *)str)
|
71
|
+
#define NOKOGIRI_STR_NEW2(str) \
|
72
|
+
rb_str_new2((const char *)(str))
|
60
73
|
|
61
|
-
#define NOKOGIRI_STR_NEW(str, len
|
62
|
-
rb_str_new((const char *)str, (long)len)
|
74
|
+
#define NOKOGIRI_STR_NEW(str, len) \
|
75
|
+
rb_str_new((const char *)(str), (long)(len))
|
63
76
|
#endif
|
64
77
|
|
65
|
-
#
|
66
|
-
|
67
|
-
|
78
|
+
#define RBSTR_OR_QNIL(_str) \
|
79
|
+
(_str ? NOKOGIRI_STR_NEW2(_str) : Qnil)
|
80
|
+
|
81
|
+
#include <xml_libxml2_hacks.h>
|
68
82
|
|
69
83
|
#include <xml_io.h>
|
70
84
|
#include <xml_document.h>
|
@@ -79,15 +93,24 @@ int vasprintf (char **strp, const char *fmt, va_list ap);
|
|
79
93
|
#include <xml_document_fragment.h>
|
80
94
|
#include <xml_comment.h>
|
81
95
|
#include <xml_node_set.h>
|
82
|
-
#include <xml_xpath.h>
|
83
96
|
#include <xml_dtd.h>
|
97
|
+
#include <xml_attribute_decl.h>
|
98
|
+
#include <xml_element_decl.h>
|
99
|
+
#include <xml_entity_decl.h>
|
84
100
|
#include <xml_xpath_context.h>
|
101
|
+
#include <xml_element_content.h>
|
102
|
+
#include <xml_sax_parser_context.h>
|
85
103
|
#include <xml_sax_parser.h>
|
86
104
|
#include <xml_sax_push_parser.h>
|
87
105
|
#include <xml_reader.h>
|
88
|
-
#include <
|
106
|
+
#include <html_sax_parser_context.h>
|
89
107
|
#include <xslt_stylesheet.h>
|
90
108
|
#include <xml_syntax_error.h>
|
109
|
+
#include <xml_schema.h>
|
110
|
+
#include <xml_relax_ng.h>
|
111
|
+
#include <html_element_description.h>
|
112
|
+
#include <xml_namespace.h>
|
113
|
+
#include <xml_encoding_handler.h>
|
91
114
|
|
92
115
|
extern VALUE mNokogiri ;
|
93
116
|
extern VALUE mNokogiriXml ;
|
@@ -97,12 +120,10 @@ extern VALUE mNokogiriHtmlSax ;
|
|
97
120
|
extern VALUE mNokogiriXslt ;
|
98
121
|
|
99
122
|
#define NOKOGIRI_ROOT_NODE(_node) \
|
100
|
-
(
|
101
|
-
|
102
|
-
|
103
|
-
|
104
|
-
_node; \
|
105
|
-
})
|
123
|
+
st_insert(((nokogiriTuplePtr)(_node)->doc->_private)->unlinkedNodes, (st_data_t)(_node), (st_data_t)(_node))
|
124
|
+
|
125
|
+
#define NOKOGIRI_ROOT_NSDEF(_nsDef, _doc) \
|
126
|
+
st_insert(((nokogiriTuplePtr)(_doc)->_private)->unlinkedNodes, (st_data_t)(_nsDef), (st_data_t)(_nsDef))
|
106
127
|
|
107
128
|
#ifdef DEBUG
|
108
129
|
|
@@ -114,6 +135,8 @@ extern VALUE mNokogiriXslt ;
|
|
114
135
|
#define NOKOGIRI_DEBUG_START(p)
|
115
136
|
#define NOKOGIRI_DEBUG_END(p)
|
116
137
|
|
138
|
+
#endif
|
139
|
+
|
117
140
|
#ifndef RSTRING_PTR
|
118
141
|
#define RSTRING_PTR(s) (RSTRING(s)->ptr)
|
119
142
|
#endif
|
@@ -130,6 +153,10 @@ extern VALUE mNokogiriXslt ;
|
|
130
153
|
#define RARRAY_LEN(a) RARRAY(a)->len
|
131
154
|
#endif
|
132
155
|
|
156
|
+
#ifndef __builtin_expect
|
157
|
+
# if defined(__GNUC__)
|
158
|
+
# define __builtin_expect(expr, c) __builtin_expect((long)(expr), (long)(c))
|
159
|
+
# endif
|
133
160
|
#endif
|
134
161
|
|
135
162
|
#endif
|
data/ext/nokogiri/xml_attr.c
CHANGED
@@ -19,21 +19,21 @@ static VALUE set_value(VALUE self, VALUE content)
|
|
19
19
|
xmlChar *buffer;
|
20
20
|
xmlNode *tmp;
|
21
21
|
|
22
|
-
|
22
|
+
/* Encode our content */
|
23
23
|
buffer = xmlEncodeEntitiesReentrant(attr->doc, (unsigned char *)StringValuePtr(content));
|
24
24
|
|
25
25
|
attr->children = xmlStringGetNodeList(attr->doc, buffer);
|
26
26
|
attr->last = NULL;
|
27
27
|
tmp = attr->children;
|
28
28
|
|
29
|
-
|
29
|
+
/* Loop through the children */
|
30
30
|
for(tmp = attr->children; tmp; tmp = tmp->next) {
|
31
31
|
tmp->parent = (xmlNode *)attr;
|
32
32
|
tmp->doc = attr->doc;
|
33
33
|
if(tmp->next == NULL) attr->last = tmp;
|
34
34
|
}
|
35
35
|
|
36
|
-
|
36
|
+
/* Free up memory */
|
37
37
|
xmlFree(buffer);
|
38
38
|
}
|
39
39
|
|
@@ -42,22 +42,33 @@ static VALUE set_value(VALUE self, VALUE content)
|
|
42
42
|
|
43
43
|
/*
|
44
44
|
* call-seq:
|
45
|
-
* new(document,
|
45
|
+
* new(document, name)
|
46
46
|
*
|
47
47
|
* Create a new Attr element on the +document+ with +name+
|
48
48
|
*/
|
49
|
-
static VALUE new(
|
49
|
+
static VALUE new(int argc, VALUE *argv, VALUE klass)
|
50
50
|
{
|
51
51
|
xmlDocPtr xml_doc;
|
52
|
-
|
52
|
+
VALUE document;
|
53
|
+
VALUE name;
|
54
|
+
VALUE rest;
|
55
|
+
xmlAttrPtr node;
|
56
|
+
VALUE rb_node;
|
53
57
|
|
54
|
-
|
58
|
+
rb_scan_args(argc, argv, "2*", &document, &name, &rest);
|
59
|
+
|
60
|
+
Data_Get_Struct(document, xmlDoc, xml_doc);
|
61
|
+
|
62
|
+
node = xmlNewDocProp(
|
55
63
|
xml_doc,
|
56
64
|
(const xmlChar *)StringValuePtr(name),
|
57
65
|
NULL
|
58
66
|
);
|
59
67
|
|
60
|
-
|
68
|
+
NOKOGIRI_ROOT_NODE((xmlNodePtr)node);
|
69
|
+
|
70
|
+
rb_node = Nokogiri_wrap_xml_node(klass, (xmlNodePtr)node);
|
71
|
+
rb_obj_call_init(rb_node, argc, argv);
|
61
72
|
|
62
73
|
if(rb_block_given_p()) rb_yield(rb_node);
|
63
74
|
|
@@ -78,6 +89,6 @@ void init_xml_attr()
|
|
78
89
|
|
79
90
|
cNokogiriXmlAttr = klass;
|
80
91
|
|
81
|
-
rb_define_singleton_method(klass, "new", new,
|
92
|
+
rb_define_singleton_method(klass, "new", new, -1);
|
82
93
|
rb_define_method(klass, "value=", set_value, 1);
|
83
94
|
}
|