nokogiri 1.12.5 → 1.13.8

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 (113) hide show
  1. checksums.yaml +4 -4
  2. data/Gemfile +2 -0
  3. data/README.md +9 -7
  4. data/bin/nokogiri +63 -50
  5. data/dependencies.yml +13 -64
  6. data/ext/nokogiri/extconf.rb +66 -44
  7. data/ext/nokogiri/gumbo.c +1 -1
  8. data/ext/nokogiri/html4_sax_parser_context.c +2 -3
  9. data/ext/nokogiri/nokogiri.h +8 -0
  10. data/ext/nokogiri/xml_attr.c +2 -2
  11. data/ext/nokogiri/xml_attribute_decl.c +3 -3
  12. data/ext/nokogiri/xml_cdata.c +1 -1
  13. data/ext/nokogiri/xml_document.c +36 -36
  14. data/ext/nokogiri/xml_document_fragment.c +0 -2
  15. data/ext/nokogiri/xml_dtd.c +10 -10
  16. data/ext/nokogiri/xml_element_decl.c +3 -3
  17. data/ext/nokogiri/xml_encoding_handler.c +25 -11
  18. data/ext/nokogiri/xml_entity_decl.c +5 -5
  19. data/ext/nokogiri/xml_node.c +707 -381
  20. data/ext/nokogiri/xml_node_set.c +4 -4
  21. data/ext/nokogiri/xml_reader.c +88 -11
  22. data/ext/nokogiri/xml_sax_parser_context.c +10 -3
  23. data/ext/nokogiri/xml_schema.c +3 -3
  24. data/ext/nokogiri/xml_text.c +1 -1
  25. data/ext/nokogiri/xml_xpath_context.c +73 -50
  26. data/ext/nokogiri/xslt_stylesheet.c +107 -9
  27. data/gumbo-parser/src/parser.c +0 -11
  28. data/lib/nokogiri/class_resolver.rb +67 -0
  29. data/lib/nokogiri/css/node.rb +9 -8
  30. data/lib/nokogiri/css/parser.rb +360 -341
  31. data/lib/nokogiri/css/parser.y +249 -244
  32. data/lib/nokogiri/css/parser_extras.rb +22 -20
  33. data/lib/nokogiri/css/syntax_error.rb +1 -0
  34. data/lib/nokogiri/css/tokenizer.rb +4 -3
  35. data/lib/nokogiri/css/tokenizer.rex +3 -2
  36. data/lib/nokogiri/css/xpath_visitor.rb +179 -82
  37. data/lib/nokogiri/css.rb +38 -6
  38. data/lib/nokogiri/decorators/slop.rb +8 -7
  39. data/lib/nokogiri/extension.rb +1 -1
  40. data/lib/nokogiri/gumbo.rb +1 -0
  41. data/lib/nokogiri/html.rb +16 -10
  42. data/lib/nokogiri/html4/builder.rb +1 -0
  43. data/lib/nokogiri/html4/document.rb +88 -77
  44. data/lib/nokogiri/html4/document_fragment.rb +11 -7
  45. data/lib/nokogiri/html4/element_description.rb +1 -0
  46. data/lib/nokogiri/html4/element_description_defaults.rb +426 -520
  47. data/lib/nokogiri/html4/entity_lookup.rb +2 -1
  48. data/lib/nokogiri/html4/sax/parser.rb +5 -2
  49. data/lib/nokogiri/html4/sax/parser_context.rb +1 -0
  50. data/lib/nokogiri/html4/sax/push_parser.rb +7 -7
  51. data/lib/nokogiri/html4.rb +11 -5
  52. data/lib/nokogiri/html5/document.rb +27 -10
  53. data/lib/nokogiri/html5/document_fragment.rb +5 -2
  54. data/lib/nokogiri/html5/node.rb +10 -3
  55. data/lib/nokogiri/html5.rb +69 -64
  56. data/lib/nokogiri/jruby/dependencies.rb +10 -9
  57. data/lib/nokogiri/syntax_error.rb +1 -0
  58. data/lib/nokogiri/version/constant.rb +2 -1
  59. data/lib/nokogiri/version/info.rb +20 -13
  60. data/lib/nokogiri/version.rb +1 -0
  61. data/lib/nokogiri/xml/attr.rb +5 -3
  62. data/lib/nokogiri/xml/attribute_decl.rb +2 -1
  63. data/lib/nokogiri/xml/builder.rb +34 -32
  64. data/lib/nokogiri/xml/cdata.rb +2 -1
  65. data/lib/nokogiri/xml/character_data.rb +1 -0
  66. data/lib/nokogiri/xml/document.rb +144 -103
  67. data/lib/nokogiri/xml/document_fragment.rb +41 -38
  68. data/lib/nokogiri/xml/dtd.rb +3 -2
  69. data/lib/nokogiri/xml/element_content.rb +1 -0
  70. data/lib/nokogiri/xml/element_decl.rb +2 -1
  71. data/lib/nokogiri/xml/entity_decl.rb +3 -2
  72. data/lib/nokogiri/xml/entity_reference.rb +1 -0
  73. data/lib/nokogiri/xml/namespace.rb +2 -0
  74. data/lib/nokogiri/xml/node/save_options.rb +8 -4
  75. data/lib/nokogiri/xml/node.rb +521 -351
  76. data/lib/nokogiri/xml/node_set.rb +50 -54
  77. data/lib/nokogiri/xml/notation.rb +12 -0
  78. data/lib/nokogiri/xml/parse_options.rb +12 -7
  79. data/lib/nokogiri/xml/pp/character_data.rb +8 -6
  80. data/lib/nokogiri/xml/pp/node.rb +24 -26
  81. data/lib/nokogiri/xml/pp.rb +1 -0
  82. data/lib/nokogiri/xml/processing_instruction.rb +2 -1
  83. data/lib/nokogiri/xml/reader.rb +20 -24
  84. data/lib/nokogiri/xml/relax_ng.rb +1 -0
  85. data/lib/nokogiri/xml/sax/document.rb +20 -19
  86. data/lib/nokogiri/xml/sax/parser.rb +37 -34
  87. data/lib/nokogiri/xml/sax/parser_context.rb +7 -3
  88. data/lib/nokogiri/xml/sax/push_parser.rb +5 -5
  89. data/lib/nokogiri/xml/sax.rb +1 -0
  90. data/lib/nokogiri/xml/schema.rb +7 -6
  91. data/lib/nokogiri/xml/searchable.rb +93 -62
  92. data/lib/nokogiri/xml/syntax_error.rb +5 -4
  93. data/lib/nokogiri/xml/text.rb +1 -0
  94. data/lib/nokogiri/xml/xpath/syntax_error.rb +2 -1
  95. data/lib/nokogiri/xml/xpath.rb +12 -0
  96. data/lib/nokogiri/xml/xpath_context.rb +2 -3
  97. data/lib/nokogiri/xml.rb +4 -3
  98. data/lib/nokogiri/xslt/stylesheet.rb +1 -0
  99. data/lib/nokogiri/xslt.rb +21 -13
  100. data/lib/nokogiri.rb +19 -16
  101. data/lib/xsd/xmlparser/nokogiri.rb +25 -24
  102. data/patches/libxml2/0004-use-glibc-strlen.patch +3 -3
  103. data/patches/libxml2/0006-update-automake-files-for-arm64.patch +2443 -1914
  104. data/patches/libxml2/0008-htmlParseComment-handle-abruptly-closed-comments.patch +61 -0
  105. data/patches/libxml2/0009-allow-wildcard-namespaces.patch +77 -0
  106. data/patches/libxslt/0001-update-automake-files-for-arm64.patch +2445 -1919
  107. data/ports/archives/libxml2-2.9.14.tar.xz +0 -0
  108. data/ports/archives/libxslt-1.1.35.tar.xz +0 -0
  109. metadata +104 -32
  110. data/patches/libxml2/0007-Fix-XPath-recursion-limit.patch +0 -31
  111. data/patches/libxslt/0002-Fix-xml2-config-check-in-configure-script.patch +0 -19
  112. data/ports/archives/libxml2-2.9.12.tar.gz +0 -0
  113. data/ports/archives/libxslt-1.1.34.tar.gz +0 -0
data/patches/libxml2/0008-htmlParseComment-handle-abruptly-closed-comments.patch ADDED
@@ -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
+
data/patches/libxml2/0009-allow-wildcard-namespaces.patch ADDED
@@ -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
+