nokogiri-maglev- 1.5.0.1
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.
- data/.autotest +26 -0
- data/.gemtest +0 -0
- data/CHANGELOG.ja.rdoc +544 -0
- data/CHANGELOG.rdoc +532 -0
- data/Manifest.txt +283 -0
- data/README.ja.rdoc +106 -0
- data/README.rdoc +174 -0
- data/Rakefile +171 -0
- data/bin/nokogiri +53 -0
- data/ext/nokogiri/depend +358 -0
- data/ext/nokogiri/extconf.rb +124 -0
- data/ext/nokogiri/html_document.c +154 -0
- data/ext/nokogiri/html_document.h +10 -0
- 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 +32 -0
- data/ext/nokogiri/html_entity_lookup.h +8 -0
- data/ext/nokogiri/html_sax_parser_context.c +94 -0
- data/ext/nokogiri/html_sax_parser_context.h +11 -0
- data/ext/nokogiri/nokogiri.c +115 -0
- data/ext/nokogiri/nokogiri.h +160 -0
- data/ext/nokogiri/st.c +576 -0
- data/ext/nokogiri/xml_attr.c +94 -0
- data/ext/nokogiri/xml_attr.h +9 -0
- data/ext/nokogiri/xml_attribute_decl.c +70 -0
- data/ext/nokogiri/xml_attribute_decl.h +9 -0
- data/ext/nokogiri/xml_cdata.c +56 -0
- data/ext/nokogiri/xml_cdata.h +9 -0
- data/ext/nokogiri/xml_comment.c +54 -0
- data/ext/nokogiri/xml_comment.h +9 -0
- data/ext/nokogiri/xml_document.c +478 -0
- data/ext/nokogiri/xml_document.h +23 -0
- data/ext/nokogiri/xml_document_fragment.c +48 -0
- data/ext/nokogiri/xml_document_fragment.h +10 -0
- data/ext/nokogiri/xml_dtd.c +202 -0
- data/ext/nokogiri/xml_dtd.h +10 -0
- 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 +52 -0
- data/ext/nokogiri/xml_entity_reference.h +9 -0
- data/ext/nokogiri/xml_io.c +56 -0
- data/ext/nokogiri/xml_io.h +11 -0
- 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 +1397 -0
- data/ext/nokogiri/xml_node.h +13 -0
- data/ext/nokogiri/xml_node_set.c +418 -0
- data/ext/nokogiri/xml_node_set.h +9 -0
- data/ext/nokogiri/xml_processing_instruction.c +56 -0
- data/ext/nokogiri/xml_processing_instruction.h +9 -0
- data/ext/nokogiri/xml_reader.c +684 -0
- data/ext/nokogiri/xml_reader.h +10 -0
- data/ext/nokogiri/xml_relax_ng.c +162 -0
- data/ext/nokogiri/xml_relax_ng.h +9 -0
- data/ext/nokogiri/xml_sax_parser.c +293 -0
- data/ext/nokogiri/xml_sax_parser.h +39 -0
- 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 +115 -0
- data/ext/nokogiri/xml_sax_push_parser.h +9 -0
- data/ext/nokogiri/xml_schema.c +205 -0
- data/ext/nokogiri/xml_schema.h +9 -0
- data/ext/nokogiri/xml_syntax_error.c +58 -0
- data/ext/nokogiri/xml_syntax_error.h +13 -0
- data/ext/nokogiri/xml_text.c +50 -0
- data/ext/nokogiri/xml_text.h +9 -0
- data/ext/nokogiri/xml_xpath_context.c +315 -0
- data/ext/nokogiri/xml_xpath_context.h +9 -0
- data/ext/nokogiri/xslt_stylesheet.c +265 -0
- data/ext/nokogiri/xslt_stylesheet.h +9 -0
- data/lib/nokogiri.rb +127 -0
- data/lib/nokogiri/css.rb +27 -0
- data/lib/nokogiri/css/node.rb +99 -0
- data/lib/nokogiri/css/parser.rb +677 -0
- data/lib/nokogiri/css/parser.y +237 -0
- data/lib/nokogiri/css/parser_extras.rb +91 -0
- data/lib/nokogiri/css/syntax_error.rb +7 -0
- data/lib/nokogiri/css/tokenizer.rb +152 -0
- data/lib/nokogiri/css/tokenizer.rex +55 -0
- data/lib/nokogiri/css/xpath_visitor.rb +171 -0
- data/lib/nokogiri/decorators/slop.rb +35 -0
- data/lib/nokogiri/html.rb +36 -0
- data/lib/nokogiri/html/builder.rb +35 -0
- data/lib/nokogiri/html/document.rb +213 -0
- data/lib/nokogiri/html/document_fragment.rb +41 -0
- data/lib/nokogiri/html/element_description.rb +23 -0
- data/lib/nokogiri/html/element_description_defaults.rb +671 -0
- data/lib/nokogiri/html/entity_lookup.rb +13 -0
- data/lib/nokogiri/html/sax/parser.rb +52 -0
- data/lib/nokogiri/html/sax/parser_context.rb +16 -0
- data/lib/nokogiri/syntax_error.rb +4 -0
- data/lib/nokogiri/version.rb +88 -0
- data/lib/nokogiri/xml.rb +67 -0
- data/lib/nokogiri/xml/attr.rb +14 -0
- data/lib/nokogiri/xml/attribute_decl.rb +18 -0
- data/lib/nokogiri/xml/builder.rb +426 -0
- data/lib/nokogiri/xml/cdata.rb +11 -0
- data/lib/nokogiri/xml/character_data.rb +7 -0
- data/lib/nokogiri/xml/document.rb +234 -0
- data/lib/nokogiri/xml/document_fragment.rb +98 -0
- data/lib/nokogiri/xml/dtd.rb +22 -0
- 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 +915 -0
- data/lib/nokogiri/xml/node/save_options.rb +61 -0
- data/lib/nokogiri/xml/node_set.rb +357 -0
- data/lib/nokogiri/xml/notation.rb +6 -0
- 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 +8 -0
- data/lib/nokogiri/xml/reader.rb +112 -0
- data/lib/nokogiri/xml/relax_ng.rb +32 -0
- data/lib/nokogiri/xml/sax.rb +4 -0
- data/lib/nokogiri/xml/sax/document.rb +164 -0
- data/lib/nokogiri/xml/sax/parser.rb +115 -0
- data/lib/nokogiri/xml/sax/parser_context.rb +16 -0
- data/lib/nokogiri/xml/sax/push_parser.rb +60 -0
- data/lib/nokogiri/xml/schema.rb +63 -0
- data/lib/nokogiri/xml/syntax_error.rb +47 -0
- data/lib/nokogiri/xml/text.rb +9 -0
- data/lib/nokogiri/xml/xpath.rb +10 -0
- data/lib/nokogiri/xml/xpath/syntax_error.rb +11 -0
- data/lib/nokogiri/xml/xpath_context.rb +16 -0
- data/lib/nokogiri/xslt.rb +52 -0
- data/lib/nokogiri/xslt/stylesheet.rb +25 -0
- data/lib/xsd/xmlparser/nokogiri.rb +90 -0
- data/nokogiri_help_responses.md +40 -0
- data/tasks/cross_compile.rb +152 -0
- data/tasks/nokogiri.org.rb +18 -0
- data/tasks/test.rb +94 -0
- data/test/css/test_nthiness.rb +159 -0
- data/test/css/test_parser.rb +303 -0
- data/test/css/test_tokenizer.rb +198 -0
- data/test/css/test_xpath_visitor.rb +85 -0
- data/test/decorators/test_slop.rb +16 -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/dont_hurt_em_why.xml +422 -0
- data/test/files/encoding.html +82 -0
- data/test/files/encoding.xhtml +84 -0
- data/test/files/exslt.xml +8 -0
- data/test/files/exslt.xslt +35 -0
- data/test/files/foo/foo.xsd +4 -0
- data/test/files/metacharset.html +10 -0
- data/test/files/noencoding.html +47 -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/staff.xml +59 -0
- data/test/files/staff.xslt +32 -0
- data/test/files/tlm.html +850 -0
- data/test/files/valid_bar.xml +2 -0
- data/test/helper.rb +173 -0
- data/test/html/sax/test_parser.rb +139 -0
- data/test/html/sax/test_parser_context.rb +48 -0
- data/test/html/test_builder.rb +165 -0
- data/test/html/test_document.rb +472 -0
- data/test/html/test_document_encoding.rb +138 -0
- data/test/html/test_document_fragment.rb +255 -0
- data/test/html/test_element_description.rb +101 -0
- data/test/html/test_named_characters.rb +14 -0
- data/test/html/test_node.rb +193 -0
- data/test/html/test_node_encoding.rb +27 -0
- data/test/test_convert_xpath.rb +135 -0
- data/test/test_css_cache.rb +45 -0
- data/test/test_encoding_handler.rb +46 -0
- data/test/test_memory_leak.rb +72 -0
- data/test/test_nokogiri.rb +133 -0
- data/test/test_reader.rb +425 -0
- data/test/test_soap4r_sax.rb +52 -0
- data/test/test_xslt_transforms.rb +193 -0
- data/test/xml/node/test_save_options.rb +28 -0
- data/test/xml/node/test_subclass.rb +44 -0
- data/test/xml/sax/test_parser.rb +338 -0
- data/test/xml/sax/test_parser_context.rb +113 -0
- data/test/xml/sax/test_push_parser.rb +156 -0
- data/test/xml/test_attr.rb +65 -0
- data/test/xml/test_attribute_decl.rb +86 -0
- data/test/xml/test_builder.rb +227 -0
- data/test/xml/test_cdata.rb +50 -0
- data/test/xml/test_comment.rb +29 -0
- data/test/xml/test_document.rb +697 -0
- data/test/xml/test_document_encoding.rb +26 -0
- data/test/xml/test_document_fragment.rb +192 -0
- data/test/xml/test_dtd.rb +107 -0
- data/test/xml/test_dtd_encoding.rb +33 -0
- 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 +122 -0
- data/test/xml/test_entity_reference.rb +21 -0
- data/test/xml/test_namespace.rb +70 -0
- data/test/xml/test_node.rb +917 -0
- data/test/xml/test_node_attributes.rb +34 -0
- data/test/xml/test_node_encoding.rb +107 -0
- data/test/xml/test_node_reparenting.rb +334 -0
- data/test/xml/test_node_set.rb +742 -0
- data/test/xml/test_parse_options.rb +52 -0
- data/test/xml/test_processing_instruction.rb +30 -0
- data/test/xml/test_reader_encoding.rb +126 -0
- 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 +47 -0
- data/test/xml/test_unparented_node.rb +381 -0
- data/test/xml/test_xpath.rb +237 -0
- data/test/xslt/test_custom_functions.rb +94 -0
- data/test/xslt/test_exception_handling.rb +37 -0
- metadata +548 -0
@@ -0,0 +1,32 @@
|
|
1
|
+
#include <html_entity_lookup.h>
|
2
|
+
|
3
|
+
/*
|
4
|
+
* call-seq:
|
5
|
+
* get(key)
|
6
|
+
*
|
7
|
+
* Get the HTML::EntityDescription for +key+
|
8
|
+
*/
|
9
|
+
static VALUE get(VALUE self, VALUE key)
|
10
|
+
{
|
11
|
+
const htmlEntityDesc * desc =
|
12
|
+
htmlEntityLookup((const xmlChar *)StringValuePtr(key));
|
13
|
+
VALUE klass, args[3];
|
14
|
+
|
15
|
+
if(NULL == desc) return Qnil;
|
16
|
+
klass = rb_const_get(mNokogiriHtml, rb_intern("EntityDescription"));
|
17
|
+
|
18
|
+
args[0] = INT2NUM((long)desc->value);
|
19
|
+
args[1] = NOKOGIRI_STR_NEW2(desc->name);
|
20
|
+
args[2] = NOKOGIRI_STR_NEW2(desc->desc);
|
21
|
+
|
22
|
+
return rb_class_new_instance(3, args, klass);
|
23
|
+
}
|
24
|
+
|
25
|
+
void init_html_entity_lookup()
|
26
|
+
{
|
27
|
+
VALUE nokogiri = rb_define_module("Nokogiri");
|
28
|
+
VALUE html = rb_define_module_under(nokogiri, "HTML");
|
29
|
+
VALUE klass = rb_define_class_under(html, "EntityLookup", rb_cObject);
|
30
|
+
|
31
|
+
rb_define_method(klass, "get", get, 1);
|
32
|
+
}
|
@@ -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
|
+
}
|
@@ -0,0 +1,115 @@
|
|
1
|
+
#include <nokogiri.h>
|
2
|
+
|
3
|
+
VALUE mNokogiri ;
|
4
|
+
VALUE mNokogiriXml ;
|
5
|
+
VALUE mNokogiriHtml ;
|
6
|
+
VALUE mNokogiriXslt ;
|
7
|
+
VALUE mNokogiriXmlSax ;
|
8
|
+
VALUE mNokogiriHtmlSax ;
|
9
|
+
|
10
|
+
#ifdef USE_INCLUDED_VASPRINTF
|
11
|
+
/*
|
12
|
+
* I srsly hate windows. it doesn't have vasprintf.
|
13
|
+
* Thank you Geoffroy Couprie for this implementation of vasprintf!
|
14
|
+
*/
|
15
|
+
int vasprintf (char **strp, const char *fmt, va_list ap)
|
16
|
+
{
|
17
|
+
int len = vsnprintf (NULL, 0, fmt, ap) + 1;
|
18
|
+
char *res = (char *)malloc((unsigned int)len);
|
19
|
+
if (res == NULL)
|
20
|
+
return -1;
|
21
|
+
*strp = res;
|
22
|
+
return vsnprintf(res, (unsigned int)len, fmt, ap);
|
23
|
+
}
|
24
|
+
#endif
|
25
|
+
|
26
|
+
#ifdef USING_SYSTEM_ALLOCATOR_LIBRARY /* Ruby Enterprise Edition with tcmalloc */
|
27
|
+
void vasprintf_free (void *p)
|
28
|
+
{
|
29
|
+
system_free(p);
|
30
|
+
}
|
31
|
+
#else
|
32
|
+
void vasprintf_free (void *p)
|
33
|
+
{
|
34
|
+
free(p);
|
35
|
+
}
|
36
|
+
#endif
|
37
|
+
|
38
|
+
#ifndef __MACRUBY__
|
39
|
+
/* Allocate strdupped strings with the same memory allocator Ruby uses. */
|
40
|
+
static char *ruby_strdup(const char *s)
|
41
|
+
{
|
42
|
+
size_t len = strlen(s);
|
43
|
+
char *result = ruby_xmalloc((ssize_t) (len + 1));
|
44
|
+
memcpy(result, s, len + 1);
|
45
|
+
return result;
|
46
|
+
}
|
47
|
+
#endif
|
48
|
+
|
49
|
+
void Init_nokogiri()
|
50
|
+
{
|
51
|
+
#ifndef __MACRUBY__
|
52
|
+
xmlMemSetup(
|
53
|
+
(xmlFreeFunc)ruby_xfree,
|
54
|
+
(xmlMallocFunc)ruby_xmalloc,
|
55
|
+
(xmlReallocFunc)ruby_xrealloc,
|
56
|
+
ruby_strdup
|
57
|
+
);
|
58
|
+
#endif
|
59
|
+
|
60
|
+
mNokogiri = rb_define_module("Nokogiri");
|
61
|
+
mNokogiriXml = rb_define_module_under(mNokogiri, "XML");
|
62
|
+
mNokogiriHtml = rb_define_module_under(mNokogiri, "HTML");
|
63
|
+
mNokogiriXslt = rb_define_module_under(mNokogiri, "XSLT");
|
64
|
+
mNokogiriXmlSax = rb_define_module_under(mNokogiriXml, "SAX");
|
65
|
+
mNokogiriHtmlSax = rb_define_module_under(mNokogiriHtml, "SAX");
|
66
|
+
|
67
|
+
rb_const_set( mNokogiri,
|
68
|
+
rb_intern("LIBXML_VERSION"),
|
69
|
+
NOKOGIRI_STR_NEW2(LIBXML_DOTTED_VERSION)
|
70
|
+
);
|
71
|
+
rb_const_set( mNokogiri,
|
72
|
+
rb_intern("LIBXML_PARSER_VERSION"),
|
73
|
+
NOKOGIRI_STR_NEW2(xmlParserVersion)
|
74
|
+
);
|
75
|
+
|
76
|
+
#ifdef LIBXML_ICONV_ENABLED
|
77
|
+
rb_const_set(mNokogiri, rb_intern("LIBXML_ICONV_ENABLED"), Qtrue);
|
78
|
+
#else
|
79
|
+
rb_const_set(mNokogiri, rb_intern("LIBXML_ICONV_ENABLED"), Qfalse);
|
80
|
+
#endif
|
81
|
+
|
82
|
+
xmlInitParser();
|
83
|
+
|
84
|
+
init_xml_document();
|
85
|
+
init_html_document();
|
86
|
+
init_xml_node();
|
87
|
+
init_xml_document_fragment();
|
88
|
+
init_xml_text();
|
89
|
+
init_xml_cdata();
|
90
|
+
init_xml_processing_instruction();
|
91
|
+
init_xml_attr();
|
92
|
+
init_xml_entity_reference();
|
93
|
+
init_xml_comment();
|
94
|
+
init_xml_node_set();
|
95
|
+
init_xml_xpath_context();
|
96
|
+
init_xml_sax_parser_context();
|
97
|
+
init_xml_sax_parser();
|
98
|
+
init_xml_sax_push_parser();
|
99
|
+
init_xml_reader();
|
100
|
+
init_xml_dtd();
|
101
|
+
init_xml_element_content();
|
102
|
+
init_xml_attribute_decl();
|
103
|
+
init_xml_element_decl();
|
104
|
+
init_xml_entity_decl();
|
105
|
+
init_xml_namespace();
|
106
|
+
init_html_sax_parser_context();
|
107
|
+
init_xslt_stylesheet();
|
108
|
+
init_xml_syntax_error();
|
109
|
+
init_html_entity_lookup();
|
110
|
+
init_html_element_description();
|
111
|
+
init_xml_schema();
|
112
|
+
init_xml_relax_ng();
|
113
|
+
init_nokogiri_io();
|
114
|
+
init_xml_encoding_handler();
|
115
|
+
}
|
@@ -0,0 +1,160 @@
|
|
1
|
+
#ifndef NOKOGIRI_NATIVE
|
2
|
+
#define NOKOGIRI_NATIVE
|
3
|
+
|
4
|
+
#include <stdlib.h>
|
5
|
+
#include <string.h>
|
6
|
+
#include <assert.h>
|
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
|
+
|
19
|
+
#include <libxml/parser.h>
|
20
|
+
#include <libxml/entities.h>
|
21
|
+
#include <libxml/parserInternals.h>
|
22
|
+
#include <libxml/xpath.h>
|
23
|
+
#include <libxml/xpathInternals.h>
|
24
|
+
#include <libxml/xmlreader.h>
|
25
|
+
#include <libxml/xmlsave.h>
|
26
|
+
#include <libxml/xmlschemas.h>
|
27
|
+
#include <libxml/HTMLparser.h>
|
28
|
+
#include <libxml/HTMLtree.h>
|
29
|
+
#include <libxml/relaxng.h>
|
30
|
+
#include <libxslt/extensions.h>
|
31
|
+
#include <ruby.h>
|
32
|
+
|
33
|
+
#ifdef HAVE_RUBY_ENCODING_H
|
34
|
+
#include <ruby/st.h>
|
35
|
+
#else
|
36
|
+
#include <st.h>
|
37
|
+
#endif
|
38
|
+
|
39
|
+
#ifndef UNUSED
|
40
|
+
# if defined(__GNUC__)
|
41
|
+
# define MAYBE_UNUSED(name) name __attribute__((unused))
|
42
|
+
# define UNUSED(name) MAYBE_UNUSED(UNUSED_ ## name)
|
43
|
+
# else
|
44
|
+
# define MAYBE_UNUSED(name) name
|
45
|
+
# define UNUSED(name) name
|
46
|
+
# endif
|
47
|
+
#endif
|
48
|
+
|
49
|
+
#ifndef NORETURN
|
50
|
+
# if defined(__GNUC__)
|
51
|
+
# define NORETURN(name) __attribute__((noreturn)) name
|
52
|
+
# else
|
53
|
+
# define NORETURN(name) name
|
54
|
+
# endif
|
55
|
+
#endif
|
56
|
+
|
57
|
+
#ifdef HAVE_RUBY_ENCODING_H
|
58
|
+
|
59
|
+
#include <ruby/encoding.h>
|
60
|
+
|
61
|
+
#define NOKOGIRI_STR_NEW2(str) \
|
62
|
+
NOKOGIRI_STR_NEW(str, strlen((const char *)(str)))
|
63
|
+
|
64
|
+
#define NOKOGIRI_STR_NEW(str, len) \
|
65
|
+
rb_external_str_new_with_enc((const char *)(str), (long)(len), rb_utf8_encoding())
|
66
|
+
|
67
|
+
#else
|
68
|
+
|
69
|
+
#define NOKOGIRI_STR_NEW2(str) \
|
70
|
+
rb_str_new2((const char *)(str))
|
71
|
+
|
72
|
+
#define NOKOGIRI_STR_NEW(str, len) \
|
73
|
+
rb_str_new((const char *)(str), (long)(len))
|
74
|
+
#endif
|
75
|
+
|
76
|
+
#define RBSTR_OR_QNIL(_str) \
|
77
|
+
(_str ? NOKOGIRI_STR_NEW2(_str) : Qnil)
|
78
|
+
|
79
|
+
#include <xml_libxml2_hacks.h>
|
80
|
+
|
81
|
+
#include <xml_io.h>
|
82
|
+
#include <xml_document.h>
|
83
|
+
#include <html_entity_lookup.h>
|
84
|
+
#include <html_document.h>
|
85
|
+
#include <xml_node.h>
|
86
|
+
#include <xml_text.h>
|
87
|
+
#include <xml_cdata.h>
|
88
|
+
#include <xml_attr.h>
|
89
|
+
#include <xml_processing_instruction.h>
|
90
|
+
#include <xml_entity_reference.h>
|
91
|
+
#include <xml_document_fragment.h>
|
92
|
+
#include <xml_comment.h>
|
93
|
+
#include <xml_node_set.h>
|
94
|
+
#include <xml_dtd.h>
|
95
|
+
#include <xml_attribute_decl.h>
|
96
|
+
#include <xml_element_decl.h>
|
97
|
+
#include <xml_entity_decl.h>
|
98
|
+
#include <xml_xpath_context.h>
|
99
|
+
#include <xml_element_content.h>
|
100
|
+
#include <xml_sax_parser_context.h>
|
101
|
+
#include <xml_sax_parser.h>
|
102
|
+
#include <xml_sax_push_parser.h>
|
103
|
+
#include <xml_reader.h>
|
104
|
+
#include <html_sax_parser_context.h>
|
105
|
+
#include <xslt_stylesheet.h>
|
106
|
+
#include <xml_syntax_error.h>
|
107
|
+
#include <xml_schema.h>
|
108
|
+
#include <xml_relax_ng.h>
|
109
|
+
#include <html_element_description.h>
|
110
|
+
#include <xml_namespace.h>
|
111
|
+
#include <xml_encoding_handler.h>
|
112
|
+
|
113
|
+
extern VALUE mNokogiri ;
|
114
|
+
extern VALUE mNokogiriXml ;
|
115
|
+
extern VALUE mNokogiriXmlSax ;
|
116
|
+
extern VALUE mNokogiriHtml ;
|
117
|
+
extern VALUE mNokogiriHtmlSax ;
|
118
|
+
extern VALUE mNokogiriXslt ;
|
119
|
+
|
120
|
+
#define NOKOGIRI_ROOT_NODE(_node) \
|
121
|
+
st_insert(((nokogiriTuplePtr)(_node)->doc->_private)->unlinkedNodes, (st_data_t)(_node), (st_data_t)(_node))
|
122
|
+
|
123
|
+
#define NOKOGIRI_ROOT_NSDEF(_nsDef, _doc) \
|
124
|
+
st_insert(((nokogiriTuplePtr)(_doc)->_private)->unlinkedNodes, (st_data_t)(_nsDef), (st_data_t)(_nsDef))
|
125
|
+
|
126
|
+
#ifdef DEBUG
|
127
|
+
|
128
|
+
#define NOKOGIRI_DEBUG_START(p) if (getenv("NOKOGIRI_NO_FREE")) return ; if (getenv("NOKOGIRI_DEBUG")) fprintf(stderr,"nokogiri: %s:%d %p start\n", __FILE__, __LINE__, p);
|
129
|
+
#define NOKOGIRI_DEBUG_END(p) if (getenv("NOKOGIRI_DEBUG")) fprintf(stderr,"nokogiri: %s:%d %p end\n", __FILE__, __LINE__, p);
|
130
|
+
|
131
|
+
#else
|
132
|
+
|
133
|
+
#define NOKOGIRI_DEBUG_START(p)
|
134
|
+
#define NOKOGIRI_DEBUG_END(p)
|
135
|
+
|
136
|
+
#endif
|
137
|
+
|
138
|
+
#ifndef RSTRING_PTR
|
139
|
+
#define RSTRING_PTR(s) (RSTRING(s)->ptr)
|
140
|
+
#endif
|
141
|
+
|
142
|
+
#ifndef RSTRING_LEN
|
143
|
+
#define RSTRING_LEN(s) (RSTRING(s)->len)
|
144
|
+
#endif
|
145
|
+
|
146
|
+
#if !defined(RARRAY_PTR) && defined(RARRAY)
|
147
|
+
#define RARRAY_PTR(a) RARRAY(a)->ptr
|
148
|
+
#endif
|
149
|
+
|
150
|
+
#ifndef RARRAY_LEN
|
151
|
+
#define RARRAY_LEN(a) RARRAY(a)->len
|
152
|
+
#endif
|
153
|
+
|
154
|
+
#ifndef __builtin_expect
|
155
|
+
# if defined(__GNUC__)
|
156
|
+
# define __builtin_expect(expr, c) __builtin_expect((long)(expr), (long)(c))
|
157
|
+
# endif
|
158
|
+
#endif
|
159
|
+
|
160
|
+
#endif
|
data/ext/nokogiri/st.c
ADDED
@@ -0,0 +1,576 @@
|
|
1
|
+
/* This is a public domain general purpose hash table package written by Peter Moore @ UCB. */
|
2
|
+
|
3
|
+
/* static char sccsid[] = "@(#) st.c 5.1 89/12/14 Crucible"; */
|
4
|
+
|
5
|
+
// #include "defines.h"
|
6
|
+
#include "ruby.h"
|
7
|
+
|
8
|
+
#include <stdio.h>
|
9
|
+
#ifdef HAVE_STDLIB_H
|
10
|
+
#include <stdlib.h>
|
11
|
+
#endif
|
12
|
+
#include <string.h>
|
13
|
+
#include "st.h"
|
14
|
+
|
15
|
+
typedef struct st_table_entry st_table_entry;
|
16
|
+
|
17
|
+
struct st_table_entry {
|
18
|
+
unsigned int hash;
|
19
|
+
st_data_t key;
|
20
|
+
st_data_t record;
|
21
|
+
st_table_entry *next;
|
22
|
+
};
|
23
|
+
|
24
|
+
#define ST_DEFAULT_MAX_DENSITY 5
|
25
|
+
#define ST_DEFAULT_INIT_TABLE_SIZE 11
|
26
|
+
|
27
|
+
/*
|
28
|
+
* DEFAULT_MAX_DENSITY is the default for the largest we allow the
|
29
|
+
* average number of items per bin before increasing the number of
|
30
|
+
* bins
|
31
|
+
*
|
32
|
+
* DEFAULT_INIT_TABLE_SIZE is the default for the number of bins
|
33
|
+
* allocated initially
|
34
|
+
*
|
35
|
+
*/
|
36
|
+
static int numcmp(long, long);
|
37
|
+
static int numhash(long);
|
38
|
+
static struct st_hash_type type_numhash = {
|
39
|
+
numcmp,
|
40
|
+
numhash,
|
41
|
+
};
|
42
|
+
|
43
|
+
/* extern int strcmp(const char *, const char *); */
|
44
|
+
static int strhash(const char *);
|
45
|
+
static struct st_hash_type type_strhash = {
|
46
|
+
strcmp,
|
47
|
+
strhash,
|
48
|
+
};
|
49
|
+
|
50
|
+
static void rehash(st_table *);
|
51
|
+
|
52
|
+
#ifdef RUBY
|
53
|
+
#define malloc xmalloc
|
54
|
+
#define calloc xcalloc
|
55
|
+
#endif
|
56
|
+
|
57
|
+
#define alloc(type) (type*)malloc((unsigned)sizeof(type))
|
58
|
+
#define Calloc(n,s) (char*)calloc((n),(s))
|
59
|
+
|
60
|
+
#define EQUAL(table,x,y) ((x)==(y) || (*table->type->compare)((x),(y)) == 0)
|
61
|
+
|
62
|
+
#define do_hash(key,table) (unsigned int)(*(table)->type->hash)((key))
|
63
|
+
#define do_hash_bin(key,table) (do_hash(key, table)%(table)->num_bins)
|
64
|
+
|
65
|
+
/*
|
66
|
+
* MINSIZE is the minimum size of a dictionary.
|
67
|
+
*/
|
68
|
+
|
69
|
+
#define MINSIZE 8
|
70
|
+
|
71
|
+
/*
|
72
|
+
Table of prime numbers 2^n+a, 2<=n<=30.
|
73
|
+
*/
|
74
|
+
static const long primes[] = {
|
75
|
+
8 + 3,
|
76
|
+
16 + 3,
|
77
|
+
32 + 5,
|
78
|
+
64 + 3,
|
79
|
+
128 + 3,
|
80
|
+
256 + 27,
|
81
|
+
512 + 9,
|
82
|
+
1024 + 9,
|
83
|
+
2048 + 5,
|
84
|
+
4096 + 3,
|
85
|
+
8192 + 27,
|
86
|
+
16384 + 43,
|
87
|
+
32768 + 3,
|
88
|
+
65536 + 45,
|
89
|
+
131072 + 29,
|
90
|
+
262144 + 3,
|
91
|
+
524288 + 21,
|
92
|
+
1048576 + 7,
|
93
|
+
2097152 + 17,
|
94
|
+
4194304 + 15,
|
95
|
+
8388608 + 9,
|
96
|
+
16777216 + 43,
|
97
|
+
33554432 + 35,
|
98
|
+
67108864 + 15,
|
99
|
+
134217728 + 29,
|
100
|
+
268435456 + 3,
|
101
|
+
536870912 + 11,
|
102
|
+
1073741824 + 85,
|
103
|
+
0
|
104
|
+
};
|
105
|
+
|
106
|
+
static int
|
107
|
+
new_size(size)
|
108
|
+
int size;
|
109
|
+
{
|
110
|
+
int i;
|
111
|
+
|
112
|
+
#if 0
|
113
|
+
for (i=3; i<31; i++) {
|
114
|
+
if ((1<<i) > size) return 1<<i;
|
115
|
+
}
|
116
|
+
return -1;
|
117
|
+
#else
|
118
|
+
int newsize;
|
119
|
+
|
120
|
+
for (i = 0, newsize = MINSIZE;
|
121
|
+
i < sizeof(primes)/sizeof(primes[0]);
|
122
|
+
i++, newsize <<= 1)
|
123
|
+
{
|
124
|
+
if (newsize > size) return primes[i];
|
125
|
+
}
|
126
|
+
/* Ran out of polynomials */
|
127
|
+
return -1; /* should raise exception */
|
128
|
+
#endif
|
129
|
+
}
|
130
|
+
|
131
|
+
#ifdef HASH_LOG
|
132
|
+
static int collision = 0;
|
133
|
+
static int init_st = 0;
|
134
|
+
|
135
|
+
static void
|
136
|
+
stat_col()
|
137
|
+
{
|
138
|
+
FILE *f = fopen("/tmp/col", "w");
|
139
|
+
fprintf(f, "collision: %d\n", collision);
|
140
|
+
fclose(f);
|
141
|
+
}
|
142
|
+
#endif
|
143
|
+
|
144
|
+
st_table*
|
145
|
+
st_init_table_with_size(type, size)
|
146
|
+
struct st_hash_type *type;
|
147
|
+
int size;
|
148
|
+
{
|
149
|
+
st_table *tbl;
|
150
|
+
|
151
|
+
#ifdef HASH_LOG
|
152
|
+
if (init_st == 0) {
|
153
|
+
init_st = 1;
|
154
|
+
atexit(stat_col);
|
155
|
+
}
|
156
|
+
#endif
|
157
|
+
|
158
|
+
size = new_size(size); /* round up to prime number */
|
159
|
+
|
160
|
+
tbl = alloc(st_table);
|
161
|
+
tbl->type = type;
|
162
|
+
tbl->num_entries = 0;
|
163
|
+
tbl->num_bins = size;
|
164
|
+
tbl->bins = (st_table_entry **)Calloc(size, sizeof(st_table_entry*));
|
165
|
+
|
166
|
+
return tbl;
|
167
|
+
}
|
168
|
+
|
169
|
+
st_table*
|
170
|
+
st_init_table(type)
|
171
|
+
struct st_hash_type *type;
|
172
|
+
{
|
173
|
+
return st_init_table_with_size(type, 0);
|
174
|
+
}
|
175
|
+
|
176
|
+
st_table*
|
177
|
+
st_init_numtable(void)
|
178
|
+
{
|
179
|
+
return st_init_table(&type_numhash);
|
180
|
+
}
|
181
|
+
|
182
|
+
st_table*
|
183
|
+
st_init_numtable_with_size(size)
|
184
|
+
int size;
|
185
|
+
{
|
186
|
+
return st_init_table_with_size(&type_numhash, size);
|
187
|
+
}
|
188
|
+
|
189
|
+
st_table*
|
190
|
+
st_init_strtable(void)
|
191
|
+
{
|
192
|
+
return st_init_table(&type_strhash);
|
193
|
+
}
|
194
|
+
|
195
|
+
st_table*
|
196
|
+
st_init_strtable_with_size(size)
|
197
|
+
int size;
|
198
|
+
{
|
199
|
+
return st_init_table_with_size(&type_strhash, size);
|
200
|
+
}
|
201
|
+
|
202
|
+
void
|
203
|
+
st_free_table(table)
|
204
|
+
st_table *table;
|
205
|
+
{
|
206
|
+
register st_table_entry *ptr, *next;
|
207
|
+
int i;
|
208
|
+
|
209
|
+
for(i = 0; i < table->num_bins; i++) {
|
210
|
+
ptr = table->bins[i];
|
211
|
+
while (ptr != 0) {
|
212
|
+
next = ptr->next;
|
213
|
+
free(ptr);
|
214
|
+
ptr = next;
|
215
|
+
}
|
216
|
+
}
|
217
|
+
free(table->bins);
|
218
|
+
free(table);
|
219
|
+
}
|
220
|
+
|
221
|
+
#define PTR_NOT_EQUAL(table, ptr, hash_val, key) \
|
222
|
+
((ptr) != 0 && (ptr->hash != (hash_val) || !EQUAL((table), (key), (ptr)->key)))
|
223
|
+
|
224
|
+
#ifdef HASH_LOG
|
225
|
+
#define COLLISION collision++
|
226
|
+
#else
|
227
|
+
#define COLLISION
|
228
|
+
#endif
|
229
|
+
|
230
|
+
#define FIND_ENTRY(table, ptr, hash_val, bin_pos) do {\
|
231
|
+
bin_pos = hash_val%(table)->num_bins;\
|
232
|
+
ptr = (table)->bins[bin_pos];\
|
233
|
+
if (PTR_NOT_EQUAL(table, ptr, hash_val, key)) {\
|
234
|
+
COLLISION;\
|
235
|
+
while (PTR_NOT_EQUAL(table, ptr->next, hash_val, key)) {\
|
236
|
+
ptr = ptr->next;\
|
237
|
+
}\
|
238
|
+
ptr = ptr->next;\
|
239
|
+
}\
|
240
|
+
} while (0)
|
241
|
+
|
242
|
+
int
|
243
|
+
st_lookup(table, key, value)
|
244
|
+
st_table *table;
|
245
|
+
register st_data_t key;
|
246
|
+
st_data_t *value;
|
247
|
+
{
|
248
|
+
unsigned int hash_val, bin_pos;
|
249
|
+
register st_table_entry *ptr;
|
250
|
+
|
251
|
+
hash_val = do_hash(key, table);
|
252
|
+
FIND_ENTRY(table, ptr, hash_val, bin_pos);
|
253
|
+
|
254
|
+
if (ptr == 0) {
|
255
|
+
return 0;
|
256
|
+
}
|
257
|
+
else {
|
258
|
+
if (value != 0) *value = ptr->record;
|
259
|
+
return 1;
|
260
|
+
}
|
261
|
+
}
|
262
|
+
|
263
|
+
#define ADD_DIRECT(table, key, value, hash_val, bin_pos)\
|
264
|
+
do {\
|
265
|
+
st_table_entry *entry;\
|
266
|
+
if (table->num_entries/(table->num_bins) > ST_DEFAULT_MAX_DENSITY) {\
|
267
|
+
rehash(table);\
|
268
|
+
bin_pos = hash_val % table->num_bins;\
|
269
|
+
}\
|
270
|
+
\
|
271
|
+
entry = alloc(st_table_entry);\
|
272
|
+
\
|
273
|
+
entry->hash = hash_val;\
|
274
|
+
entry->key = key;\
|
275
|
+
entry->record = value;\
|
276
|
+
entry->next = table->bins[bin_pos];\
|
277
|
+
table->bins[bin_pos] = entry;\
|
278
|
+
table->num_entries++;\
|
279
|
+
} while (0)
|
280
|
+
|
281
|
+
int
|
282
|
+
st_insert(table, key, value)
|
283
|
+
register st_table *table;
|
284
|
+
register st_data_t key;
|
285
|
+
st_data_t value;
|
286
|
+
{
|
287
|
+
unsigned int hash_val, bin_pos;
|
288
|
+
register st_table_entry *ptr;
|
289
|
+
|
290
|
+
hash_val = do_hash(key, table);
|
291
|
+
FIND_ENTRY(table, ptr, hash_val, bin_pos);
|
292
|
+
|
293
|
+
if (ptr == 0) {
|
294
|
+
ADD_DIRECT(table, key, value, hash_val, bin_pos);
|
295
|
+
return 0;
|
296
|
+
}
|
297
|
+
else {
|
298
|
+
ptr->record = value;
|
299
|
+
return 1;
|
300
|
+
}
|
301
|
+
}
|
302
|
+
|
303
|
+
void
|
304
|
+
st_add_direct(table, key, value)
|
305
|
+
st_table *table;
|
306
|
+
st_data_t key;
|
307
|
+
st_data_t value;
|
308
|
+
{
|
309
|
+
unsigned int hash_val, bin_pos;
|
310
|
+
|
311
|
+
hash_val = do_hash(key, table);
|
312
|
+
bin_pos = hash_val % table->num_bins;
|
313
|
+
ADD_DIRECT(table, key, value, hash_val, bin_pos);
|
314
|
+
}
|
315
|
+
|
316
|
+
static void
|
317
|
+
rehash(table)
|
318
|
+
register st_table *table;
|
319
|
+
{
|
320
|
+
register st_table_entry *ptr, *next, **new_bins;
|
321
|
+
int i, old_num_bins = table->num_bins, new_num_bins;
|
322
|
+
unsigned int hash_val;
|
323
|
+
|
324
|
+
new_num_bins = new_size(old_num_bins+1);
|
325
|
+
new_bins = (st_table_entry**)Calloc(new_num_bins, sizeof(st_table_entry*));
|
326
|
+
|
327
|
+
for(i = 0; i < old_num_bins; i++) {
|
328
|
+
ptr = table->bins[i];
|
329
|
+
while (ptr != 0) {
|
330
|
+
next = ptr->next;
|
331
|
+
hash_val = ptr->hash % new_num_bins;
|
332
|
+
ptr->next = new_bins[hash_val];
|
333
|
+
new_bins[hash_val] = ptr;
|
334
|
+
ptr = next;
|
335
|
+
}
|
336
|
+
}
|
337
|
+
free(table->bins);
|
338
|
+
table->num_bins = new_num_bins;
|
339
|
+
table->bins = new_bins;
|
340
|
+
}
|
341
|
+
|
342
|
+
st_table*
|
343
|
+
st_copy(old_table)
|
344
|
+
st_table *old_table;
|
345
|
+
{
|
346
|
+
st_table *new_table;
|
347
|
+
st_table_entry *ptr, *entry;
|
348
|
+
int i, num_bins = old_table->num_bins;
|
349
|
+
|
350
|
+
new_table = alloc(st_table);
|
351
|
+
if (new_table == 0) {
|
352
|
+
return 0;
|
353
|
+
}
|
354
|
+
|
355
|
+
*new_table = *old_table;
|
356
|
+
new_table->bins = (st_table_entry**)
|
357
|
+
Calloc((unsigned)num_bins, sizeof(st_table_entry*));
|
358
|
+
|
359
|
+
if (new_table->bins == 0) {
|
360
|
+
free(new_table);
|
361
|
+
return 0;
|
362
|
+
}
|
363
|
+
|
364
|
+
for(i = 0; i < num_bins; i++) {
|
365
|
+
new_table->bins[i] = 0;
|
366
|
+
ptr = old_table->bins[i];
|
367
|
+
while (ptr != 0) {
|
368
|
+
entry = alloc(st_table_entry);
|
369
|
+
if (entry == 0) {
|
370
|
+
free(new_table->bins);
|
371
|
+
free(new_table);
|
372
|
+
return 0;
|
373
|
+
}
|
374
|
+
*entry = *ptr;
|
375
|
+
entry->next = new_table->bins[i];
|
376
|
+
new_table->bins[i] = entry;
|
377
|
+
ptr = ptr->next;
|
378
|
+
}
|
379
|
+
}
|
380
|
+
return new_table;
|
381
|
+
}
|
382
|
+
|
383
|
+
int
|
384
|
+
st_delete(table, key, value)
|
385
|
+
register st_table *table;
|
386
|
+
register st_data_t *key;
|
387
|
+
st_data_t *value;
|
388
|
+
{
|
389
|
+
unsigned int hash_val;
|
390
|
+
st_table_entry *tmp;
|
391
|
+
register st_table_entry *ptr;
|
392
|
+
|
393
|
+
hash_val = do_hash_bin(*key, table);
|
394
|
+
ptr = table->bins[hash_val];
|
395
|
+
|
396
|
+
if (ptr == 0) {
|
397
|
+
if (value != 0) *value = 0;
|
398
|
+
return 0;
|
399
|
+
}
|
400
|
+
|
401
|
+
if (EQUAL(table, *key, ptr->key)) {
|
402
|
+
table->bins[hash_val] = ptr->next;
|
403
|
+
table->num_entries--;
|
404
|
+
if (value != 0) *value = ptr->record;
|
405
|
+
*key = ptr->key;
|
406
|
+
free(ptr);
|
407
|
+
return 1;
|
408
|
+
}
|
409
|
+
|
410
|
+
for(; ptr->next != 0; ptr = ptr->next) {
|
411
|
+
if (EQUAL(table, ptr->next->key, *key)) {
|
412
|
+
tmp = ptr->next;
|
413
|
+
ptr->next = ptr->next->next;
|
414
|
+
table->num_entries--;
|
415
|
+
if (value != 0) *value = tmp->record;
|
416
|
+
*key = tmp->key;
|
417
|
+
free(tmp);
|
418
|
+
return 1;
|
419
|
+
}
|
420
|
+
}
|
421
|
+
|
422
|
+
return 0;
|
423
|
+
}
|
424
|
+
|
425
|
+
int
|
426
|
+
st_delete_safe(table, key, value, never)
|
427
|
+
register st_table *table;
|
428
|
+
register st_data_t *key;
|
429
|
+
st_data_t *value;
|
430
|
+
st_data_t never;
|
431
|
+
{
|
432
|
+
unsigned int hash_val;
|
433
|
+
register st_table_entry *ptr;
|
434
|
+
|
435
|
+
hash_val = do_hash_bin(*key, table);
|
436
|
+
ptr = table->bins[hash_val];
|
437
|
+
|
438
|
+
if (ptr == 0) {
|
439
|
+
if (value != 0) *value = 0;
|
440
|
+
return 0;
|
441
|
+
}
|
442
|
+
|
443
|
+
for(; ptr != 0; ptr = ptr->next) {
|
444
|
+
if ((ptr->key != never) && EQUAL(table, ptr->key, *key)) {
|
445
|
+
table->num_entries--;
|
446
|
+
*key = ptr->key;
|
447
|
+
if (value != 0) *value = ptr->record;
|
448
|
+
ptr->key = ptr->record = never;
|
449
|
+
return 1;
|
450
|
+
}
|
451
|
+
}
|
452
|
+
|
453
|
+
return 0;
|
454
|
+
}
|
455
|
+
|
456
|
+
static int
|
457
|
+
delete_never(key, value, never)
|
458
|
+
st_data_t key, value, never;
|
459
|
+
{
|
460
|
+
if (value == never) return ST_DELETE;
|
461
|
+
return ST_CONTINUE;
|
462
|
+
}
|
463
|
+
|
464
|
+
void
|
465
|
+
st_cleanup_safe(table, never)
|
466
|
+
st_table *table;
|
467
|
+
st_data_t never;
|
468
|
+
{
|
469
|
+
int num_entries = table->num_entries;
|
470
|
+
|
471
|
+
st_foreach(table, delete_never, never);
|
472
|
+
table->num_entries = num_entries;
|
473
|
+
}
|
474
|
+
|
475
|
+
int
|
476
|
+
st_foreach(table, func, arg)
|
477
|
+
st_table *table;
|
478
|
+
int (*func)();
|
479
|
+
st_data_t arg;
|
480
|
+
{
|
481
|
+
st_table_entry *ptr, *last, *tmp;
|
482
|
+
enum st_retval retval;
|
483
|
+
int i;
|
484
|
+
|
485
|
+
for(i = 0; i < table->num_bins; i++) {
|
486
|
+
last = 0;
|
487
|
+
for(ptr = table->bins[i]; ptr != 0;) {
|
488
|
+
retval = (*func)(ptr->key, ptr->record, arg);
|
489
|
+
switch (retval) {
|
490
|
+
case ST_CHECK: /* check if hash is modified during iteration */
|
491
|
+
tmp = 0;
|
492
|
+
if (i < table->num_bins) {
|
493
|
+
for (tmp = table->bins[i]; tmp; tmp=tmp->next) {
|
494
|
+
if (tmp == ptr) break;
|
495
|
+
}
|
496
|
+
}
|
497
|
+
if (!tmp) {
|
498
|
+
/* call func with error notice */
|
499
|
+
return 1;
|
500
|
+
}
|
501
|
+
/* fall through */
|
502
|
+
case ST_CONTINUE:
|
503
|
+
last = ptr;
|
504
|
+
ptr = ptr->next;
|
505
|
+
break;
|
506
|
+
case ST_STOP:
|
507
|
+
return 0;
|
508
|
+
case ST_DELETE:
|
509
|
+
tmp = ptr;
|
510
|
+
if (last == 0) {
|
511
|
+
table->bins[i] = ptr->next;
|
512
|
+
}
|
513
|
+
else {
|
514
|
+
last->next = ptr->next;
|
515
|
+
}
|
516
|
+
ptr = ptr->next;
|
517
|
+
free(tmp);
|
518
|
+
table->num_entries--;
|
519
|
+
}
|
520
|
+
}
|
521
|
+
}
|
522
|
+
return 0;
|
523
|
+
}
|
524
|
+
|
525
|
+
static int
|
526
|
+
strhash(string)
|
527
|
+
register const char *string;
|
528
|
+
{
|
529
|
+
register int c;
|
530
|
+
|
531
|
+
#ifdef HASH_ELFHASH
|
532
|
+
register unsigned int h = 0, g;
|
533
|
+
|
534
|
+
while ((c = *string++) != '\0') {
|
535
|
+
h = ( h << 4 ) + c;
|
536
|
+
if ( g = h & 0xF0000000 )
|
537
|
+
h ^= g >> 24;
|
538
|
+
h &= ~g;
|
539
|
+
}
|
540
|
+
return h;
|
541
|
+
#elif defined(HASH_PERL)
|
542
|
+
register int val = 0;
|
543
|
+
|
544
|
+
while ((c = *string++) != '\0') {
|
545
|
+
val += c;
|
546
|
+
val += (val << 10);
|
547
|
+
val ^= (val >> 6);
|
548
|
+
}
|
549
|
+
val += (val << 3);
|
550
|
+
val ^= (val >> 11);
|
551
|
+
|
552
|
+
return val + (val << 15);
|
553
|
+
#else
|
554
|
+
register int val = 0;
|
555
|
+
|
556
|
+
while ((c = *string++) != '\0') {
|
557
|
+
val = val*997 + c;
|
558
|
+
}
|
559
|
+
|
560
|
+
return val + (val>>5);
|
561
|
+
#endif
|
562
|
+
}
|
563
|
+
|
564
|
+
static int
|
565
|
+
numcmp(x, y)
|
566
|
+
long x, y;
|
567
|
+
{
|
568
|
+
return x != y;
|
569
|
+
}
|
570
|
+
|
571
|
+
static int
|
572
|
+
numhash(n)
|
573
|
+
long n;
|
574
|
+
{
|
575
|
+
return n;
|
576
|
+
}
|