nokogiri 1.10.3 → 1.13.2

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 (223) hide show
  1. checksums.yaml +4 -4
  2. data/Gemfile +5 -0
  3. data/LICENSE-DEPENDENCIES.md +1173 -884
  4. data/LICENSE.md +1 -1
  5. data/README.md +178 -96
  6. data/bin/nokogiri +63 -50
  7. data/dependencies.yml +11 -60
  8. data/ext/nokogiri/depend +38 -358
  9. data/ext/nokogiri/extconf.rb +752 -423
  10. data/ext/nokogiri/gumbo.c +584 -0
  11. data/ext/nokogiri/html4_document.c +166 -0
  12. data/ext/nokogiri/html4_element_description.c +294 -0
  13. data/ext/nokogiri/html4_entity_lookup.c +37 -0
  14. data/ext/nokogiri/html4_sax_parser_context.c +120 -0
  15. data/ext/nokogiri/html4_sax_push_parser.c +95 -0
  16. data/ext/nokogiri/libxml2_backwards_compat.c +121 -0
  17. data/ext/nokogiri/nokogiri.c +228 -91
  18. data/ext/nokogiri/nokogiri.h +191 -89
  19. data/ext/nokogiri/test_global_handlers.c +40 -0
  20. data/ext/nokogiri/xml_attr.c +15 -15
  21. data/ext/nokogiri/xml_attribute_decl.c +18 -18
  22. data/ext/nokogiri/xml_cdata.c +13 -18
  23. data/ext/nokogiri/xml_comment.c +19 -26
  24. data/ext/nokogiri/xml_document.c +291 -219
  25. data/ext/nokogiri/xml_document_fragment.c +12 -16
  26. data/ext/nokogiri/xml_dtd.c +56 -50
  27. data/ext/nokogiri/xml_element_content.c +31 -26
  28. data/ext/nokogiri/xml_element_decl.c +22 -22
  29. data/ext/nokogiri/xml_encoding_handler.c +43 -18
  30. data/ext/nokogiri/xml_entity_decl.c +32 -30
  31. data/ext/nokogiri/xml_entity_reference.c +16 -18
  32. data/ext/nokogiri/xml_namespace.c +60 -51
  33. data/ext/nokogiri/xml_node.c +1001 -610
  34. data/ext/nokogiri/xml_node_set.c +174 -162
  35. data/ext/nokogiri/xml_processing_instruction.c +17 -19
  36. data/ext/nokogiri/xml_reader.c +226 -175
  37. data/ext/nokogiri/xml_relax_ng.c +52 -28
  38. data/ext/nokogiri/xml_sax_parser.c +112 -112
  39. data/ext/nokogiri/xml_sax_parser_context.c +105 -86
  40. data/ext/nokogiri/xml_sax_push_parser.c +36 -27
  41. data/ext/nokogiri/xml_schema.c +112 -33
  42. data/ext/nokogiri/xml_syntax_error.c +42 -21
  43. data/ext/nokogiri/xml_text.c +13 -17
  44. data/ext/nokogiri/xml_xpath_context.c +223 -115
  45. data/ext/nokogiri/xslt_stylesheet.c +265 -173
  46. data/gumbo-parser/CHANGES.md +63 -0
  47. data/gumbo-parser/Makefile +101 -0
  48. data/gumbo-parser/THANKS +27 -0
  49. data/gumbo-parser/src/Makefile +34 -0
  50. data/gumbo-parser/src/README.md +41 -0
  51. data/gumbo-parser/src/ascii.c +75 -0
  52. data/gumbo-parser/src/ascii.h +115 -0
  53. data/gumbo-parser/src/attribute.c +42 -0
  54. data/gumbo-parser/src/attribute.h +17 -0
  55. data/gumbo-parser/src/char_ref.c +22225 -0
  56. data/gumbo-parser/src/char_ref.h +29 -0
  57. data/gumbo-parser/src/char_ref.rl +2154 -0
  58. data/gumbo-parser/src/error.c +626 -0
  59. data/gumbo-parser/src/error.h +148 -0
  60. data/gumbo-parser/src/foreign_attrs.c +104 -0
  61. data/gumbo-parser/src/foreign_attrs.gperf +27 -0
  62. data/gumbo-parser/src/gumbo.h +943 -0
  63. data/gumbo-parser/src/insertion_mode.h +33 -0
  64. data/gumbo-parser/src/macros.h +91 -0
  65. data/gumbo-parser/src/parser.c +4875 -0
  66. data/gumbo-parser/src/parser.h +41 -0
  67. data/gumbo-parser/src/replacement.h +33 -0
  68. data/gumbo-parser/src/string_buffer.c +103 -0
  69. data/gumbo-parser/src/string_buffer.h +68 -0
  70. data/gumbo-parser/src/string_piece.c +48 -0
  71. data/gumbo-parser/src/svg_attrs.c +174 -0
  72. data/gumbo-parser/src/svg_attrs.gperf +77 -0
  73. data/gumbo-parser/src/svg_tags.c +137 -0
  74. data/gumbo-parser/src/svg_tags.gperf +55 -0
  75. data/gumbo-parser/src/tag.c +222 -0
  76. data/gumbo-parser/src/tag_lookup.c +382 -0
  77. data/gumbo-parser/src/tag_lookup.gperf +169 -0
  78. data/gumbo-parser/src/tag_lookup.h +13 -0
  79. data/gumbo-parser/src/token_buffer.c +79 -0
  80. data/gumbo-parser/src/token_buffer.h +71 -0
  81. data/gumbo-parser/src/token_type.h +17 -0
  82. data/gumbo-parser/src/tokenizer.c +3463 -0
  83. data/gumbo-parser/src/tokenizer.h +112 -0
  84. data/gumbo-parser/src/tokenizer_states.h +339 -0
  85. data/gumbo-parser/src/utf8.c +245 -0
  86. data/gumbo-parser/src/utf8.h +164 -0
  87. data/gumbo-parser/src/util.c +68 -0
  88. data/gumbo-parser/src/util.h +30 -0
  89. data/gumbo-parser/src/vector.c +111 -0
  90. data/gumbo-parser/src/vector.h +45 -0
  91. data/lib/nokogiri/class_resolver.rb +67 -0
  92. data/lib/nokogiri/css/node.rb +10 -8
  93. data/lib/nokogiri/css/parser.rb +397 -377
  94. data/lib/nokogiri/css/parser.y +250 -245
  95. data/lib/nokogiri/css/parser_extras.rb +52 -49
  96. data/lib/nokogiri/css/syntax_error.rb +3 -1
  97. data/lib/nokogiri/css/tokenizer.rb +107 -104
  98. data/lib/nokogiri/css/tokenizer.rex +3 -2
  99. data/lib/nokogiri/css/xpath_visitor.rb +218 -91
  100. data/lib/nokogiri/css.rb +50 -17
  101. data/lib/nokogiri/decorators/slop.rb +9 -7
  102. data/lib/nokogiri/extension.rb +31 -0
  103. data/lib/nokogiri/gumbo.rb +15 -0
  104. data/lib/nokogiri/html.rb +38 -27
  105. data/lib/nokogiri/{html → html4}/builder.rb +4 -2
  106. data/lib/nokogiri/{html → html4}/document.rb +99 -103
  107. data/lib/nokogiri/html4/document_fragment.rb +54 -0
  108. data/lib/nokogiri/{html → html4}/element_description.rb +3 -1
  109. data/lib/nokogiri/html4/element_description_defaults.rb +578 -0
  110. data/lib/nokogiri/{html → html4}/entity_lookup.rb +4 -2
  111. data/lib/nokogiri/{html → html4}/sax/parser.rb +14 -15
  112. data/lib/nokogiri/html4/sax/parser_context.rb +20 -0
  113. data/lib/nokogiri/{html → html4}/sax/push_parser.rb +12 -11
  114. data/lib/nokogiri/html4.rb +46 -0
  115. data/lib/nokogiri/html5/document.rb +88 -0
  116. data/lib/nokogiri/html5/document_fragment.rb +83 -0
  117. data/lib/nokogiri/html5/node.rb +96 -0
  118. data/lib/nokogiri/html5.rb +477 -0
  119. data/lib/nokogiri/jruby/dependencies.rb +21 -0
  120. data/lib/nokogiri/syntax_error.rb +2 -0
  121. data/lib/nokogiri/version/constant.rb +6 -0
  122. data/lib/nokogiri/version/info.rb +221 -0
  123. data/lib/nokogiri/version.rb +3 -108
  124. data/lib/nokogiri/xml/attr.rb +6 -3
  125. data/lib/nokogiri/xml/attribute_decl.rb +3 -1
  126. data/lib/nokogiri/xml/builder.rb +95 -53
  127. data/lib/nokogiri/xml/cdata.rb +3 -1
  128. data/lib/nokogiri/xml/character_data.rb +2 -0
  129. data/lib/nokogiri/xml/document.rb +219 -86
  130. data/lib/nokogiri/xml/document_fragment.rb +46 -44
  131. data/lib/nokogiri/xml/dtd.rb +4 -2
  132. data/lib/nokogiri/xml/element_content.rb +2 -0
  133. data/lib/nokogiri/xml/element_decl.rb +3 -1
  134. data/lib/nokogiri/xml/entity_decl.rb +4 -2
  135. data/lib/nokogiri/xml/entity_reference.rb +2 -0
  136. data/lib/nokogiri/xml/namespace.rb +3 -0
  137. data/lib/nokogiri/xml/node/save_options.rb +8 -4
  138. data/lib/nokogiri/xml/node.rb +876 -376
  139. data/lib/nokogiri/xml/node_set.rb +47 -54
  140. data/lib/nokogiri/xml/notation.rb +13 -0
  141. data/lib/nokogiri/xml/parse_options.rb +21 -8
  142. data/lib/nokogiri/xml/pp/character_data.rb +9 -6
  143. data/lib/nokogiri/xml/pp/node.rb +25 -26
  144. data/lib/nokogiri/xml/pp.rb +4 -2
  145. data/lib/nokogiri/xml/processing_instruction.rb +3 -1
  146. data/lib/nokogiri/xml/reader.rb +23 -28
  147. data/lib/nokogiri/xml/relax_ng.rb +8 -2
  148. data/lib/nokogiri/xml/sax/document.rb +45 -49
  149. data/lib/nokogiri/xml/sax/parser.rb +37 -34
  150. data/lib/nokogiri/xml/sax/parser_context.rb +8 -3
  151. data/lib/nokogiri/xml/sax/push_parser.rb +6 -5
  152. data/lib/nokogiri/xml/sax.rb +6 -4
  153. data/lib/nokogiri/xml/schema.rb +19 -9
  154. data/lib/nokogiri/xml/searchable.rb +112 -72
  155. data/lib/nokogiri/xml/syntax_error.rb +5 -4
  156. data/lib/nokogiri/xml/text.rb +2 -0
  157. data/lib/nokogiri/xml/xpath/syntax_error.rb +4 -2
  158. data/lib/nokogiri/xml/xpath.rb +15 -4
  159. data/lib/nokogiri/xml/xpath_context.rb +3 -3
  160. data/lib/nokogiri/xml.rb +37 -37
  161. data/lib/nokogiri/xslt/stylesheet.rb +3 -1
  162. data/lib/nokogiri/xslt.rb +29 -20
  163. data/lib/nokogiri.rb +49 -65
  164. data/lib/xsd/xmlparser/nokogiri.rb +26 -24
  165. data/patches/libxml2/{0002-Remove-script-macro-support.patch → 0001-Remove-script-macro-support.patch} +0 -0
  166. data/patches/libxml2/{0003-Update-entities-to-remove-handling-of-ssi.patch → 0002-Update-entities-to-remove-handling-of-ssi.patch} +0 -0
  167. data/patches/libxml2/0003-libxml2.la-is-in-top_builddir.patch +25 -0
  168. data/patches/libxml2/0004-use-glibc-strlen.patch +53 -0
  169. data/patches/libxml2/0005-avoid-isnan-isinf.patch +81 -0
  170. data/patches/libxml2/0006-update-automake-files-for-arm64.patch +3040 -0
  171. data/patches/libxml2/0008-htmlParseComment-handle-abruptly-closed-comments.patch +61 -0
  172. data/patches/libxml2/0009-allow-wildcard-namespaces.patch +77 -0
  173. data/patches/libxslt/0001-update-automake-files-for-arm64.patch +3037 -0
  174. data/ports/archives/libxml2-2.9.13.tar.xz +0 -0
  175. data/ports/archives/libxslt-1.1.35.tar.xz +0 -0
  176. metadata +207 -137
  177. data/ext/nokogiri/html_document.c +0 -170
  178. data/ext/nokogiri/html_document.h +0 -10
  179. data/ext/nokogiri/html_element_description.c +0 -279
  180. data/ext/nokogiri/html_element_description.h +0 -10
  181. data/ext/nokogiri/html_entity_lookup.c +0 -32
  182. data/ext/nokogiri/html_entity_lookup.h +0 -8
  183. data/ext/nokogiri/html_sax_parser_context.c +0 -116
  184. data/ext/nokogiri/html_sax_parser_context.h +0 -11
  185. data/ext/nokogiri/html_sax_push_parser.c +0 -87
  186. data/ext/nokogiri/html_sax_push_parser.h +0 -9
  187. data/ext/nokogiri/xml_attr.h +0 -9
  188. data/ext/nokogiri/xml_attribute_decl.h +0 -9
  189. data/ext/nokogiri/xml_cdata.h +0 -9
  190. data/ext/nokogiri/xml_comment.h +0 -9
  191. data/ext/nokogiri/xml_document.h +0 -23
  192. data/ext/nokogiri/xml_document_fragment.h +0 -10
  193. data/ext/nokogiri/xml_dtd.h +0 -10
  194. data/ext/nokogiri/xml_element_content.h +0 -10
  195. data/ext/nokogiri/xml_element_decl.h +0 -9
  196. data/ext/nokogiri/xml_encoding_handler.h +0 -8
  197. data/ext/nokogiri/xml_entity_decl.h +0 -10
  198. data/ext/nokogiri/xml_entity_reference.h +0 -9
  199. data/ext/nokogiri/xml_io.c +0 -61
  200. data/ext/nokogiri/xml_io.h +0 -11
  201. data/ext/nokogiri/xml_libxml2_hacks.c +0 -112
  202. data/ext/nokogiri/xml_libxml2_hacks.h +0 -12
  203. data/ext/nokogiri/xml_namespace.h +0 -14
  204. data/ext/nokogiri/xml_node.h +0 -13
  205. data/ext/nokogiri/xml_node_set.h +0 -12
  206. data/ext/nokogiri/xml_processing_instruction.h +0 -9
  207. data/ext/nokogiri/xml_reader.h +0 -10
  208. data/ext/nokogiri/xml_relax_ng.h +0 -9
  209. data/ext/nokogiri/xml_sax_parser.h +0 -39
  210. data/ext/nokogiri/xml_sax_parser_context.h +0 -10
  211. data/ext/nokogiri/xml_sax_push_parser.h +0 -9
  212. data/ext/nokogiri/xml_schema.h +0 -9
  213. data/ext/nokogiri/xml_syntax_error.h +0 -13
  214. data/ext/nokogiri/xml_text.h +0 -9
  215. data/ext/nokogiri/xml_xpath_context.h +0 -10
  216. data/ext/nokogiri/xslt_stylesheet.h +0 -14
  217. data/lib/nokogiri/html/document_fragment.rb +0 -49
  218. data/lib/nokogiri/html/element_description_defaults.rb +0 -671
  219. data/lib/nokogiri/html/sax/parser_context.rb +0 -16
  220. data/patches/libxml2/0001-Revert-Do-not-URI-escape-in-server-side-includes.patch +0 -78
  221. data/patches/libxslt/0001-Fix-security-framework-bypass.patch +0 -120
  222. data/ports/archives/libxml2-2.9.9.tar.gz +0 -0
  223. data/ports/archives/libxslt-1.1.33.tar.gz +0 -0
@@ -0,0 +1,61 @@
1
+ From 3ea8d08da310b645e37940eaae5cc28e251b155b Mon Sep 17 00:00:00 2001
2
+ From: Mike Dalessio <mike.dalessio@gmail.com>
3
+ Date: Sat, 17 Jul 2021 14:36:53 -0400
4
+ Subject: [PATCH] htmlParseComment: handle abruptly-closed comments
5
+
6
+ See guidance provided on abrutply-closed comments here:
7
+
8
+ https://html.spec.whatwg.org/multipage/parsing.html#parse-error-abrupt-closing-of-empty-comment
9
+ ---
10
+ HTMLparser.c | 11 +++++++++++
11
+ include/libxml/xmlerror.h | 1 +
12
+ 2 files changed, 12 insertions(+)
13
+
14
+ diff --git a/HTMLparser.c b/HTMLparser.c
15
+ index b56363a..f0bf294 100644
16
+ --- a/HTMLparser.c
17
+ +++ b/HTMLparser.c
18
+ @@ -3485,10 +3485,20 @@ htmlParseComment(htmlParserCtxtPtr ctxt) {
19
+ q = CUR_CHAR(ql);
20
+ if (q == 0)
21
+ goto unfinished;
22
+ + if (q == '>') {
23
+ + htmlParseErr(ctxt, XML_ERR_COMMENT_ABRUPTLY_ENDED, "Comment abruptly ended", NULL, NULL);
24
+ + cur = '>';
25
+ + goto finished;
26
+ + }
27
+ NEXTL(ql);
28
+ r = CUR_CHAR(rl);
29
+ if (r == 0)
30
+ goto unfinished;
31
+ + if (q == '-' && r == '>') {
32
+ + htmlParseErr(ctxt, XML_ERR_COMMENT_ABRUPTLY_ENDED, "Comment abruptly ended", NULL, NULL);
33
+ + cur = '>';
34
+ + goto finished;
35
+ + }
36
+ NEXTL(rl);
37
+ cur = CUR_CHAR(l);
38
+ while ((cur != 0) &&
39
+ @@ -3536,6 +3546,7 @@ htmlParseComment(htmlParserCtxtPtr ctxt) {
40
+ cur = next;
41
+ l = nl;
42
+ }
43
+ +finished:
44
+ buf[len] = 0;
45
+ if (cur == '>') {
46
+ NEXT;
47
+ diff --git a/include/libxml/xmlerror.h b/include/libxml/xmlerror.h
48
+ index c101997..7b68e40 100644
49
+ --- a/include/libxml/xmlerror.h
50
+ +++ b/include/libxml/xmlerror.h
51
+ @@ -209,6 +209,7 @@ typedef enum {
52
+ XML_ERR_VERSION_MISMATCH, /* 109 */
53
+ XML_ERR_NAME_TOO_LONG, /* 110 */
54
+ XML_ERR_USER_STOP, /* 111 */
55
+ + XML_ERR_COMMENT_ABRUPTLY_ENDED, /* 112 */
56
+ XML_NS_ERR_XML_NAMESPACE = 200,
57
+ XML_NS_ERR_UNDEFINED_NAMESPACE, /* 201 */
58
+ XML_NS_ERR_QNAME, /* 202 */
59
+ --
60
+ 2.31.0
61
+
@@ -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
+