nokogiri 1.12.5 → 1.14.3

Sign up to get free protection for your applications and to get access to all the features.

Potentially problematic release.


This version of nokogiri might be problematic. Click here for more details.

Files changed (156) hide show
  1. checksums.yaml +4 -4
  2. data/Gemfile +41 -0
  3. data/LICENSE-DEPENDENCIES.md +830 -509
  4. data/LICENSE.md +1 -1
  5. data/README.md +23 -14
  6. data/bin/nokogiri +63 -50
  7. data/dependencies.yml +33 -66
  8. data/ext/nokogiri/extconf.rb +159 -63
  9. data/ext/nokogiri/gumbo.c +21 -11
  10. data/ext/nokogiri/html4_document.c +2 -2
  11. data/ext/nokogiri/html4_element_description.c +1 -1
  12. data/ext/nokogiri/html4_entity_lookup.c +2 -2
  13. data/ext/nokogiri/html4_sax_parser_context.c +3 -9
  14. data/ext/nokogiri/html4_sax_push_parser.c +1 -1
  15. data/ext/nokogiri/nokogiri.c +38 -51
  16. data/ext/nokogiri/nokogiri.h +26 -14
  17. data/ext/nokogiri/test_global_handlers.c +1 -1
  18. data/ext/nokogiri/xml_attr.c +3 -3
  19. data/ext/nokogiri/xml_attribute_decl.c +5 -5
  20. data/ext/nokogiri/xml_cdata.c +3 -3
  21. data/ext/nokogiri/xml_comment.c +1 -1
  22. data/ext/nokogiri/xml_document.c +53 -44
  23. data/ext/nokogiri/xml_document_fragment.c +1 -3
  24. data/ext/nokogiri/xml_dtd.c +11 -11
  25. data/ext/nokogiri/xml_element_content.c +3 -3
  26. data/ext/nokogiri/xml_element_decl.c +5 -5
  27. data/ext/nokogiri/xml_encoding_handler.c +28 -14
  28. data/ext/nokogiri/xml_entity_decl.c +6 -6
  29. data/ext/nokogiri/xml_entity_reference.c +1 -1
  30. data/ext/nokogiri/xml_namespace.c +80 -14
  31. data/ext/nokogiri/xml_node.c +982 -396
  32. data/ext/nokogiri/xml_node_set.c +4 -6
  33. data/ext/nokogiri/xml_processing_instruction.c +1 -1
  34. data/ext/nokogiri/xml_reader.c +133 -32
  35. data/ext/nokogiri/xml_relax_ng.c +1 -3
  36. data/ext/nokogiri/xml_sax_parser.c +23 -17
  37. data/ext/nokogiri/xml_sax_parser_context.c +11 -9
  38. data/ext/nokogiri/xml_sax_push_parser.c +1 -3
  39. data/ext/nokogiri/xml_schema.c +4 -6
  40. data/ext/nokogiri/xml_syntax_error.c +1 -1
  41. data/ext/nokogiri/xml_text.c +2 -2
  42. data/ext/nokogiri/xml_xpath_context.c +144 -114
  43. data/ext/nokogiri/xslt_stylesheet.c +122 -23
  44. data/gumbo-parser/Makefile +10 -0
  45. data/gumbo-parser/src/attribute.h +1 -1
  46. data/gumbo-parser/src/error.c +2 -2
  47. data/gumbo-parser/src/error.h +1 -1
  48. data/gumbo-parser/src/foreign_attrs.c +2 -2
  49. data/gumbo-parser/src/{gumbo.h → nokogiri_gumbo.h} +1 -0
  50. data/gumbo-parser/src/parser.c +8 -16
  51. data/gumbo-parser/src/replacement.h +1 -1
  52. data/gumbo-parser/src/string_buffer.h +1 -1
  53. data/gumbo-parser/src/string_piece.c +1 -1
  54. data/gumbo-parser/src/svg_attrs.c +2 -2
  55. data/gumbo-parser/src/svg_tags.c +2 -2
  56. data/gumbo-parser/src/tag.c +2 -1
  57. data/gumbo-parser/src/tag_lookup.c +7 -7
  58. data/gumbo-parser/src/tag_lookup.gperf +1 -0
  59. data/gumbo-parser/src/tag_lookup.h +1 -1
  60. data/gumbo-parser/src/token_buffer.h +1 -1
  61. data/gumbo-parser/src/tokenizer.c +1 -1
  62. data/gumbo-parser/src/tokenizer.h +1 -1
  63. data/gumbo-parser/src/utf8.c +1 -1
  64. data/gumbo-parser/src/utf8.h +1 -1
  65. data/gumbo-parser/src/util.c +1 -3
  66. data/gumbo-parser/src/util.h +4 -0
  67. data/gumbo-parser/src/vector.h +1 -1
  68. data/lib/nokogiri/class_resolver.rb +67 -0
  69. data/lib/nokogiri/css/node.rb +9 -8
  70. data/lib/nokogiri/css/parser.rb +360 -341
  71. data/lib/nokogiri/css/parser.y +249 -244
  72. data/lib/nokogiri/css/parser_extras.rb +22 -20
  73. data/lib/nokogiri/css/syntax_error.rb +1 -0
  74. data/lib/nokogiri/css/tokenizer.rb +4 -3
  75. data/lib/nokogiri/css/tokenizer.rex +3 -2
  76. data/lib/nokogiri/css/xpath_visitor.rb +184 -85
  77. data/lib/nokogiri/css.rb +44 -6
  78. data/lib/nokogiri/decorators/slop.rb +8 -7
  79. data/lib/nokogiri/encoding_handler.rb +57 -0
  80. data/lib/nokogiri/extension.rb +4 -3
  81. data/lib/nokogiri/gumbo.rb +1 -0
  82. data/lib/nokogiri/html.rb +16 -10
  83. data/lib/nokogiri/html4/builder.rb +1 -0
  84. data/lib/nokogiri/html4/document.rb +56 -164
  85. data/lib/nokogiri/html4/document_fragment.rb +11 -7
  86. data/lib/nokogiri/html4/element_description.rb +1 -0
  87. data/lib/nokogiri/html4/element_description_defaults.rb +432 -532
  88. data/lib/nokogiri/html4/encoding_reader.rb +121 -0
  89. data/lib/nokogiri/html4/entity_lookup.rb +2 -1
  90. data/lib/nokogiri/html4/sax/parser.rb +5 -2
  91. data/lib/nokogiri/html4/sax/parser_context.rb +1 -0
  92. data/lib/nokogiri/html4/sax/push_parser.rb +7 -7
  93. data/lib/nokogiri/html4.rb +12 -5
  94. data/lib/nokogiri/html5/document.rb +126 -32
  95. data/lib/nokogiri/html5/document_fragment.rb +14 -4
  96. data/lib/nokogiri/html5/node.rb +12 -7
  97. data/lib/nokogiri/html5.rb +138 -222
  98. data/lib/nokogiri/jruby/dependencies.rb +2 -19
  99. data/lib/nokogiri/jruby/nokogiri_jars.rb +43 -0
  100. data/lib/nokogiri/syntax_error.rb +1 -0
  101. data/lib/nokogiri/version/constant.rb +2 -1
  102. data/lib/nokogiri/version/info.rb +32 -24
  103. data/lib/nokogiri/version.rb +1 -0
  104. data/lib/nokogiri/xml/attr.rb +54 -3
  105. data/lib/nokogiri/xml/attribute_decl.rb +2 -1
  106. data/lib/nokogiri/xml/builder.rb +35 -33
  107. data/lib/nokogiri/xml/cdata.rb +2 -1
  108. data/lib/nokogiri/xml/character_data.rb +1 -0
  109. data/lib/nokogiri/xml/document.rb +232 -143
  110. data/lib/nokogiri/xml/document_fragment.rb +88 -42
  111. data/lib/nokogiri/xml/dtd.rb +3 -2
  112. data/lib/nokogiri/xml/element_content.rb +1 -0
  113. data/lib/nokogiri/xml/element_decl.rb +2 -1
  114. data/lib/nokogiri/xml/entity_decl.rb +3 -2
  115. data/lib/nokogiri/xml/entity_reference.rb +1 -0
  116. data/lib/nokogiri/xml/namespace.rb +44 -0
  117. data/lib/nokogiri/xml/node/save_options.rb +14 -8
  118. data/lib/nokogiri/xml/node.rb +708 -383
  119. data/lib/nokogiri/xml/node_set.rb +134 -59
  120. data/lib/nokogiri/xml/notation.rb +12 -0
  121. data/lib/nokogiri/xml/parse_options.rb +140 -56
  122. data/lib/nokogiri/xml/pp/character_data.rb +8 -6
  123. data/lib/nokogiri/xml/pp/node.rb +26 -26
  124. data/lib/nokogiri/xml/pp.rb +1 -0
  125. data/lib/nokogiri/xml/processing_instruction.rb +3 -1
  126. data/lib/nokogiri/xml/reader.rb +20 -24
  127. data/lib/nokogiri/xml/relax_ng.rb +1 -0
  128. data/lib/nokogiri/xml/sax/document.rb +20 -19
  129. data/lib/nokogiri/xml/sax/parser.rb +38 -36
  130. data/lib/nokogiri/xml/sax/parser_context.rb +7 -3
  131. data/lib/nokogiri/xml/sax/push_parser.rb +5 -5
  132. data/lib/nokogiri/xml/sax.rb +1 -0
  133. data/lib/nokogiri/xml/schema.rb +7 -6
  134. data/lib/nokogiri/xml/searchable.rb +93 -62
  135. data/lib/nokogiri/xml/syntax_error.rb +5 -4
  136. data/lib/nokogiri/xml/text.rb +1 -0
  137. data/lib/nokogiri/xml/xpath/syntax_error.rb +2 -1
  138. data/lib/nokogiri/xml/xpath.rb +12 -0
  139. data/lib/nokogiri/xml/xpath_context.rb +2 -3
  140. data/lib/nokogiri/xml.rb +4 -3
  141. data/lib/nokogiri/xslt/stylesheet.rb +1 -0
  142. data/lib/nokogiri/xslt.rb +21 -13
  143. data/lib/nokogiri.rb +22 -27
  144. data/lib/xsd/xmlparser/nokogiri.rb +28 -25
  145. data/patches/libxml2/0009-allow-wildcard-namespaces.patch +77 -0
  146. data/patches/libxslt/0001-update-automake-files-for-arm64.patch +2445 -1919
  147. data/ports/archives/libxml2-2.10.4.tar.xz +0 -0
  148. data/ports/archives/libxslt-1.1.37.tar.xz +0 -0
  149. metadata +20 -171
  150. data/patches/libxml2/0004-use-glibc-strlen.patch +0 -53
  151. data/patches/libxml2/0005-avoid-isnan-isinf.patch +0 -81
  152. data/patches/libxml2/0006-update-automake-files-for-arm64.patch +0 -2511
  153. data/patches/libxml2/0007-Fix-XPath-recursion-limit.patch +0 -31
  154. data/patches/libxslt/0002-Fix-xml2-config-check-in-configure-script.patch +0 -19
  155. data/ports/archives/libxml2-2.9.12.tar.gz +0 -0
  156. data/ports/archives/libxslt-1.1.34.tar.gz +0 -0
@@ -1,8 +1,9 @@
1
1
  # frozen_string_literal: true
2
- require 'nokogiri'
3
2
 
4
- module XSD # :nodoc:
5
- module XMLParser # :nodoc:
3
+ require "nokogiri"
4
+
5
+ module XSD
6
+ module XMLParser
6
7
  ###
7
8
  # Nokogiri XML parser for soap4r.
8
9
  #
@@ -27,40 +28,40 @@ module XSD # :nodoc:
27
28
  class Nokogiri < XSD::XMLParser::Parser
28
29
  ###
29
30
  # Create a new XSD parser with +host+ and +opt+
30
- def initialize host, opt = {}
31
+ def initialize(host, opt = {})
31
32
  super
32
- @parser = ::Nokogiri::XML::SAX::Parser.new(self, @charset || 'UTF-8')
33
+ @parser = ::Nokogiri::XML::SAX::Parser.new(self, @charset || "UTF-8")
33
34
  end
34
35
 
35
36
  ###
36
37
  # Start parsing +string_or_readable+
37
- def do_parse string_or_readable
38
+ def do_parse(string_or_readable)
38
39
  @parser.parse(string_or_readable)
39
40
  end
40
41
 
41
42
  ###
42
43
  # Handle the start_element event with +name+ and +attrs+
43
- def start_element name, attrs = []
44
+ def start_element(name, attrs = [])
44
45
  super(name, Hash[*attrs.flatten])
45
46
  end
46
47
 
47
48
  ###
48
49
  # Handle the end_element event with +name+
49
- def end_element name
50
+ def end_element(name)
50
51
  super
51
52
  end
52
53
 
53
54
  ###
54
55
  # Handle errors with message +msg+
55
- def error msg
56
- raise ParseError.new(msg)
56
+ def error(msg)
57
+ raise ParseError, msg
57
58
  end
58
- alias :warning :error
59
+ alias_method :warning, :error
59
60
 
60
61
  ###
61
62
  # Handle cdata_blocks containing +string+
62
- def cdata_block string
63
- characters string
63
+ def cdata_block(string)
64
+ characters(string)
64
65
  end
65
66
 
66
67
  ###
@@ -70,16 +71,16 @@ module XSD # :nodoc:
70
71
  # +prefix+ is the namespace prefix for the element
71
72
  # +uri+ is the associated namespace URI
72
73
  # +ns+ is a hash of namespace prefix:urls associated with the element
73
- def start_element_namespace name, attrs = [], prefix = nil, uri = nil, ns = []
74
+ def start_element_namespace(name, attrs = [], prefix = nil, uri = nil, ns = [])
74
75
  ###
75
76
  # Deal with SAX v1 interface
76
- name = [prefix, name].compact.join(':')
77
- attributes = ns.map { |ns_prefix,ns_uri|
78
- [['xmlns', ns_prefix].compact.join(':'), ns_uri]
79
- } + attrs.map { |attr|
80
- [[attr.prefix, attr.localname].compact.join(':'), attr.value]
81
- }.flatten
82
- start_element name, attributes
77
+ name = [prefix, name].compact.join(":")
78
+ attributes = ns.map do |ns_prefix, ns_uri|
79
+ [["xmlns", ns_prefix].compact.join(":"), ns_uri]
80
+ end + attrs.map do |attr|
81
+ [[attr.prefix, attr.localname].compact.join(":"), attr.value]
82
+ end.flatten
83
+ start_element(name, attributes)
83
84
  end
84
85
 
85
86
  ###
@@ -87,14 +88,16 @@ module XSD # :nodoc:
87
88
  # +name+ is the element's name
88
89
  # +prefix+ is the namespace prefix associated with the element
89
90
  # +uri+ is the associated namespace URI
90
- def end_element_namespace name, prefix = nil, uri = nil
91
+ def end_element_namespace(name, prefix = nil, uri = nil)
91
92
  ###
92
93
  # Deal with SAX v1 interface
93
- end_element [prefix, name].compact.join(':')
94
+ end_element([prefix, name].compact.join(":"))
94
95
  end
95
96
 
96
- %w{ xmldecl start_document end_document comment }.each do |name|
97
- class_eval %{ def #{name}(*args); end }
97
+ ["xmldecl", "start_document", "end_document", "comment"].each do |name|
98
+ class_eval <<~RUBY, __FILE__, __LINE__ + 1
99
+ def #{name}(*args); end
100
+ RUBY
98
101
  end
99
102
 
100
103
  add_factory(self)
@@ -0,0 +1,77 @@
1
+ From 74c95ec5932c737d4fcb06b8646b0017364ada14 Mon Sep 17 00:00:00 2001
2
+ From: Mike Dalessio <mike.dalessio@gmail.com>
3
+ Date: Fri, 24 Dec 2021 19:08:01 -0500
4
+ Subject: [PATCH] attempt to hack in wildcard namespaces to xpath
5
+
6
+ I'm not confident this is a bulletproof patch.
7
+ ---
8
+ xpath.c | 24 ++++++++++++++++++------
9
+ 1 file changed, 18 insertions(+), 6 deletions(-)
10
+
11
+ diff --git a/xpath.c b/xpath.c
12
+ index 1aa2f1a..c7f0885 100644
13
+ --- a/xpath.c
14
+ +++ b/xpath.c
15
+ @@ -146,6 +146,9 @@
16
+ #define XPATH_MAX_RECURSION_DEPTH 5000
17
+ #endif
18
+
19
+ +#define WILDCARD_PREFIX "*"
20
+ +#define IS_WILDCARD_PREFIX(p) xmlStrEqual((xmlChar*)WILDCARD_PREFIX, p)
21
+ +
22
+ /*
23
+ * TODO:
24
+ * There are a few spots where some tests are done which depend upon ascii
25
+ @@ -11073,12 +11076,15 @@ xmlXPathCompNodeTest(xmlXPathParserContextPtr ctxt, xmlXPathTestVal *test,
26
+ SKIP_BLANKS;
27
+
28
+ if ((name == NULL) && (CUR == '*')) {
29
+ - /*
30
+ - * All elements
31
+ - */
32
+ NEXT;
33
+ - *test = NODE_TEST_ALL;
34
+ - return(NULL);
35
+ + if (CUR != ':') {
36
+ + /*
37
+ + * All elements
38
+ + */
39
+ + *test = NODE_TEST_ALL;
40
+ + return(NULL);
41
+ + }
42
+ + name = xmlCharStrdup(WILDCARD_PREFIX);
43
+ }
44
+
45
+ if (name == NULL)
46
+ @@ -11327,6 +11333,10 @@ xmlXPathCompStep(xmlXPathParserContextPtr ctxt) {
47
+ }
48
+ #endif
49
+ if (CUR == '*') {
50
+ + if (NXT(1) == ':') {
51
+ + NEXT;
52
+ + name = xmlCharStrdup(WILDCARD_PREFIX);
53
+ + }
54
+ axis = AXIS_CHILD;
55
+ } else {
56
+ if (name == NULL)
57
+ @@ -12030,7 +12040,7 @@ xmlXPathNodeCollectAndTest(xmlXPathParserContextPtr ctxt,
58
+ /*
59
+ * Setup namespaces.
60
+ */
61
+ - if (prefix != NULL) {
62
+ + if (prefix != NULL && !IS_WILDCARD_PREFIX(prefix)) {
63
+ URI = xmlXPathNsLookup(xpctxt, prefix);
64
+ if (URI == NULL) {
65
+ xmlXPathReleaseObject(xpctxt, obj);
66
+ @@ -12369,6 +12379,8 @@ xmlXPathNodeCollectAndTest(xmlXPathParserContextPtr ctxt,
67
+ {
68
+ XP_TEST_HIT
69
+ }
70
+ + } else if (IS_WILDCARD_PREFIX(prefix)) {
71
+ + XP_TEST_HIT
72
+ } else {
73
+ if ((cur->ns != NULL) &&
74
+ (xmlStrEqual(URI, cur->ns->href)))
75
+ --
76
+ 2.31.0
77
+