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.
- checksums.yaml +4 -4
- data/Gemfile +41 -0
- data/LICENSE-DEPENDENCIES.md +830 -509
- data/LICENSE.md +1 -1
- data/README.md +23 -14
- data/bin/nokogiri +63 -50
- data/dependencies.yml +33 -66
- data/ext/nokogiri/extconf.rb +159 -63
- data/ext/nokogiri/gumbo.c +21 -11
- data/ext/nokogiri/html4_document.c +2 -2
- data/ext/nokogiri/html4_element_description.c +1 -1
- data/ext/nokogiri/html4_entity_lookup.c +2 -2
- data/ext/nokogiri/html4_sax_parser_context.c +3 -9
- data/ext/nokogiri/html4_sax_push_parser.c +1 -1
- data/ext/nokogiri/nokogiri.c +38 -51
- data/ext/nokogiri/nokogiri.h +26 -14
- data/ext/nokogiri/test_global_handlers.c +1 -1
- data/ext/nokogiri/xml_attr.c +3 -3
- data/ext/nokogiri/xml_attribute_decl.c +5 -5
- data/ext/nokogiri/xml_cdata.c +3 -3
- data/ext/nokogiri/xml_comment.c +1 -1
- data/ext/nokogiri/xml_document.c +53 -44
- data/ext/nokogiri/xml_document_fragment.c +1 -3
- data/ext/nokogiri/xml_dtd.c +11 -11
- data/ext/nokogiri/xml_element_content.c +3 -3
- data/ext/nokogiri/xml_element_decl.c +5 -5
- data/ext/nokogiri/xml_encoding_handler.c +28 -14
- data/ext/nokogiri/xml_entity_decl.c +6 -6
- data/ext/nokogiri/xml_entity_reference.c +1 -1
- data/ext/nokogiri/xml_namespace.c +80 -14
- data/ext/nokogiri/xml_node.c +982 -396
- data/ext/nokogiri/xml_node_set.c +4 -6
- data/ext/nokogiri/xml_processing_instruction.c +1 -1
- data/ext/nokogiri/xml_reader.c +133 -32
- data/ext/nokogiri/xml_relax_ng.c +1 -3
- data/ext/nokogiri/xml_sax_parser.c +23 -17
- data/ext/nokogiri/xml_sax_parser_context.c +11 -9
- data/ext/nokogiri/xml_sax_push_parser.c +1 -3
- data/ext/nokogiri/xml_schema.c +4 -6
- data/ext/nokogiri/xml_syntax_error.c +1 -1
- data/ext/nokogiri/xml_text.c +2 -2
- data/ext/nokogiri/xml_xpath_context.c +144 -114
- data/ext/nokogiri/xslt_stylesheet.c +122 -23
- data/gumbo-parser/Makefile +10 -0
- data/gumbo-parser/src/attribute.h +1 -1
- data/gumbo-parser/src/error.c +2 -2
- data/gumbo-parser/src/error.h +1 -1
- data/gumbo-parser/src/foreign_attrs.c +2 -2
- data/gumbo-parser/src/{gumbo.h → nokogiri_gumbo.h} +1 -0
- data/gumbo-parser/src/parser.c +8 -16
- data/gumbo-parser/src/replacement.h +1 -1
- data/gumbo-parser/src/string_buffer.h +1 -1
- data/gumbo-parser/src/string_piece.c +1 -1
- data/gumbo-parser/src/svg_attrs.c +2 -2
- data/gumbo-parser/src/svg_tags.c +2 -2
- data/gumbo-parser/src/tag.c +2 -1
- data/gumbo-parser/src/tag_lookup.c +7 -7
- data/gumbo-parser/src/tag_lookup.gperf +1 -0
- data/gumbo-parser/src/tag_lookup.h +1 -1
- data/gumbo-parser/src/token_buffer.h +1 -1
- data/gumbo-parser/src/tokenizer.c +1 -1
- data/gumbo-parser/src/tokenizer.h +1 -1
- data/gumbo-parser/src/utf8.c +1 -1
- data/gumbo-parser/src/utf8.h +1 -1
- data/gumbo-parser/src/util.c +1 -3
- data/gumbo-parser/src/util.h +4 -0
- data/gumbo-parser/src/vector.h +1 -1
- data/lib/nokogiri/class_resolver.rb +67 -0
- data/lib/nokogiri/css/node.rb +9 -8
- data/lib/nokogiri/css/parser.rb +360 -341
- data/lib/nokogiri/css/parser.y +249 -244
- data/lib/nokogiri/css/parser_extras.rb +22 -20
- data/lib/nokogiri/css/syntax_error.rb +1 -0
- data/lib/nokogiri/css/tokenizer.rb +4 -3
- data/lib/nokogiri/css/tokenizer.rex +3 -2
- data/lib/nokogiri/css/xpath_visitor.rb +184 -85
- data/lib/nokogiri/css.rb +44 -6
- data/lib/nokogiri/decorators/slop.rb +8 -7
- data/lib/nokogiri/encoding_handler.rb +57 -0
- data/lib/nokogiri/extension.rb +4 -3
- data/lib/nokogiri/gumbo.rb +1 -0
- data/lib/nokogiri/html.rb +16 -10
- data/lib/nokogiri/html4/builder.rb +1 -0
- data/lib/nokogiri/html4/document.rb +56 -164
- data/lib/nokogiri/html4/document_fragment.rb +11 -7
- data/lib/nokogiri/html4/element_description.rb +1 -0
- data/lib/nokogiri/html4/element_description_defaults.rb +432 -532
- data/lib/nokogiri/html4/encoding_reader.rb +121 -0
- data/lib/nokogiri/html4/entity_lookup.rb +2 -1
- data/lib/nokogiri/html4/sax/parser.rb +5 -2
- data/lib/nokogiri/html4/sax/parser_context.rb +1 -0
- data/lib/nokogiri/html4/sax/push_parser.rb +7 -7
- data/lib/nokogiri/html4.rb +12 -5
- data/lib/nokogiri/html5/document.rb +126 -32
- data/lib/nokogiri/html5/document_fragment.rb +14 -4
- data/lib/nokogiri/html5/node.rb +12 -7
- data/lib/nokogiri/html5.rb +138 -222
- data/lib/nokogiri/jruby/dependencies.rb +2 -19
- data/lib/nokogiri/jruby/nokogiri_jars.rb +43 -0
- data/lib/nokogiri/syntax_error.rb +1 -0
- data/lib/nokogiri/version/constant.rb +2 -1
- data/lib/nokogiri/version/info.rb +32 -24
- data/lib/nokogiri/version.rb +1 -0
- data/lib/nokogiri/xml/attr.rb +54 -3
- data/lib/nokogiri/xml/attribute_decl.rb +2 -1
- data/lib/nokogiri/xml/builder.rb +35 -33
- data/lib/nokogiri/xml/cdata.rb +2 -1
- data/lib/nokogiri/xml/character_data.rb +1 -0
- data/lib/nokogiri/xml/document.rb +232 -143
- data/lib/nokogiri/xml/document_fragment.rb +88 -42
- data/lib/nokogiri/xml/dtd.rb +3 -2
- data/lib/nokogiri/xml/element_content.rb +1 -0
- data/lib/nokogiri/xml/element_decl.rb +2 -1
- data/lib/nokogiri/xml/entity_decl.rb +3 -2
- data/lib/nokogiri/xml/entity_reference.rb +1 -0
- data/lib/nokogiri/xml/namespace.rb +44 -0
- data/lib/nokogiri/xml/node/save_options.rb +14 -8
- data/lib/nokogiri/xml/node.rb +708 -383
- data/lib/nokogiri/xml/node_set.rb +134 -59
- data/lib/nokogiri/xml/notation.rb +12 -0
- data/lib/nokogiri/xml/parse_options.rb +140 -56
- data/lib/nokogiri/xml/pp/character_data.rb +8 -6
- data/lib/nokogiri/xml/pp/node.rb +26 -26
- data/lib/nokogiri/xml/pp.rb +1 -0
- data/lib/nokogiri/xml/processing_instruction.rb +3 -1
- data/lib/nokogiri/xml/reader.rb +20 -24
- data/lib/nokogiri/xml/relax_ng.rb +1 -0
- data/lib/nokogiri/xml/sax/document.rb +20 -19
- data/lib/nokogiri/xml/sax/parser.rb +38 -36
- data/lib/nokogiri/xml/sax/parser_context.rb +7 -3
- data/lib/nokogiri/xml/sax/push_parser.rb +5 -5
- data/lib/nokogiri/xml/sax.rb +1 -0
- data/lib/nokogiri/xml/schema.rb +7 -6
- data/lib/nokogiri/xml/searchable.rb +93 -62
- data/lib/nokogiri/xml/syntax_error.rb +5 -4
- data/lib/nokogiri/xml/text.rb +1 -0
- data/lib/nokogiri/xml/xpath/syntax_error.rb +2 -1
- data/lib/nokogiri/xml/xpath.rb +12 -0
- data/lib/nokogiri/xml/xpath_context.rb +2 -3
- data/lib/nokogiri/xml.rb +4 -3
- data/lib/nokogiri/xslt/stylesheet.rb +1 -0
- data/lib/nokogiri/xslt.rb +21 -13
- data/lib/nokogiri.rb +22 -27
- data/lib/xsd/xmlparser/nokogiri.rb +28 -25
- data/patches/libxml2/0009-allow-wildcard-namespaces.patch +77 -0
- data/patches/libxslt/0001-update-automake-files-for-arm64.patch +2445 -1919
- data/ports/archives/libxml2-2.10.4.tar.xz +0 -0
- data/ports/archives/libxslt-1.1.37.tar.xz +0 -0
- metadata +20 -171
- data/patches/libxml2/0004-use-glibc-strlen.patch +0 -53
- data/patches/libxml2/0005-avoid-isnan-isinf.patch +0 -81
- data/patches/libxml2/0006-update-automake-files-for-arm64.patch +0 -2511
- data/patches/libxml2/0007-Fix-XPath-recursion-limit.patch +0 -31
- data/patches/libxslt/0002-Fix-xml2-config-check-in-configure-script.patch +0 -19
- data/ports/archives/libxml2-2.9.12.tar.gz +0 -0
- data/ports/archives/libxslt-1.1.34.tar.gz +0 -0
Binary file
|
Binary file
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: nokogiri
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.
|
4
|
+
version: 1.14.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Mike Dalessio
|
@@ -20,194 +20,42 @@ authors:
|
|
20
20
|
autorequire:
|
21
21
|
bindir: bin
|
22
22
|
cert_chain: []
|
23
|
-
date:
|
23
|
+
date: 2023-04-11 00:00:00.000000000 Z
|
24
24
|
dependencies:
|
25
|
-
- !ruby/object:Gem::Dependency
|
26
|
-
name: racc
|
27
|
-
requirement: !ruby/object:Gem::Requirement
|
28
|
-
requirements:
|
29
|
-
- - "~>"
|
30
|
-
- !ruby/object:Gem::Version
|
31
|
-
version: '1.4'
|
32
|
-
type: :runtime
|
33
|
-
prerelease: false
|
34
|
-
version_requirements: !ruby/object:Gem::Requirement
|
35
|
-
requirements:
|
36
|
-
- - "~>"
|
37
|
-
- !ruby/object:Gem::Version
|
38
|
-
version: '1.4'
|
39
25
|
- !ruby/object:Gem::Dependency
|
40
26
|
name: mini_portile2
|
41
27
|
requirement: !ruby/object:Gem::Requirement
|
42
28
|
requirements:
|
43
29
|
- - "~>"
|
44
30
|
- !ruby/object:Gem::Version
|
45
|
-
version: 2.
|
31
|
+
version: 2.8.0
|
46
32
|
type: :runtime
|
47
33
|
prerelease: false
|
48
34
|
version_requirements: !ruby/object:Gem::Requirement
|
49
35
|
requirements:
|
50
36
|
- - "~>"
|
51
37
|
- !ruby/object:Gem::Version
|
52
|
-
version: 2.
|
53
|
-
|
54
|
-
name: bundler
|
55
|
-
requirement: !ruby/object:Gem::Requirement
|
56
|
-
requirements:
|
57
|
-
- - "~>"
|
58
|
-
- !ruby/object:Gem::Version
|
59
|
-
version: '2.2'
|
60
|
-
type: :development
|
61
|
-
prerelease: false
|
62
|
-
version_requirements: !ruby/object:Gem::Requirement
|
63
|
-
requirements:
|
64
|
-
- - "~>"
|
65
|
-
- !ruby/object:Gem::Version
|
66
|
-
version: '2.2'
|
38
|
+
version: 2.8.0
|
39
|
+
force_ruby_platform: false
|
67
40
|
- !ruby/object:Gem::Dependency
|
68
|
-
name:
|
69
|
-
requirement: !ruby/object:Gem::Requirement
|
70
|
-
requirements:
|
71
|
-
- - "~>"
|
72
|
-
- !ruby/object:Gem::Version
|
73
|
-
version: '1.4'
|
74
|
-
type: :development
|
75
|
-
prerelease: false
|
76
|
-
version_requirements: !ruby/object:Gem::Requirement
|
77
|
-
requirements:
|
78
|
-
- - "~>"
|
79
|
-
- !ruby/object:Gem::Version
|
80
|
-
version: '1.4'
|
81
|
-
- !ruby/object:Gem::Dependency
|
82
|
-
name: minitest
|
83
|
-
requirement: !ruby/object:Gem::Requirement
|
84
|
-
requirements:
|
85
|
-
- - "~>"
|
86
|
-
- !ruby/object:Gem::Version
|
87
|
-
version: '5.8'
|
88
|
-
type: :development
|
89
|
-
prerelease: false
|
90
|
-
version_requirements: !ruby/object:Gem::Requirement
|
91
|
-
requirements:
|
92
|
-
- - "~>"
|
93
|
-
- !ruby/object:Gem::Version
|
94
|
-
version: '5.8'
|
95
|
-
- !ruby/object:Gem::Dependency
|
96
|
-
name: minitest-reporters
|
41
|
+
name: racc
|
97
42
|
requirement: !ruby/object:Gem::Requirement
|
98
43
|
requirements:
|
99
44
|
- - "~>"
|
100
45
|
- !ruby/object:Gem::Version
|
101
46
|
version: '1.4'
|
102
|
-
type: :
|
47
|
+
type: :runtime
|
103
48
|
prerelease: false
|
104
49
|
version_requirements: !ruby/object:Gem::Requirement
|
105
50
|
requirements:
|
106
51
|
- - "~>"
|
107
52
|
- !ruby/object:Gem::Version
|
108
53
|
version: '1.4'
|
109
|
-
|
110
|
-
name: rake
|
111
|
-
requirement: !ruby/object:Gem::Requirement
|
112
|
-
requirements:
|
113
|
-
- - "~>"
|
114
|
-
- !ruby/object:Gem::Version
|
115
|
-
version: '13.0'
|
116
|
-
type: :development
|
117
|
-
prerelease: false
|
118
|
-
version_requirements: !ruby/object:Gem::Requirement
|
119
|
-
requirements:
|
120
|
-
- - "~>"
|
121
|
-
- !ruby/object:Gem::Version
|
122
|
-
version: '13.0'
|
123
|
-
- !ruby/object:Gem::Dependency
|
124
|
-
name: rake-compiler
|
125
|
-
requirement: !ruby/object:Gem::Requirement
|
126
|
-
requirements:
|
127
|
-
- - "~>"
|
128
|
-
- !ruby/object:Gem::Version
|
129
|
-
version: '1.1'
|
130
|
-
type: :development
|
131
|
-
prerelease: false
|
132
|
-
version_requirements: !ruby/object:Gem::Requirement
|
133
|
-
requirements:
|
134
|
-
- - "~>"
|
135
|
-
- !ruby/object:Gem::Version
|
136
|
-
version: '1.1'
|
137
|
-
- !ruby/object:Gem::Dependency
|
138
|
-
name: rake-compiler-dock
|
139
|
-
requirement: !ruby/object:Gem::Requirement
|
140
|
-
requirements:
|
141
|
-
- - "~>"
|
142
|
-
- !ruby/object:Gem::Version
|
143
|
-
version: '1.1'
|
144
|
-
type: :development
|
145
|
-
prerelease: false
|
146
|
-
version_requirements: !ruby/object:Gem::Requirement
|
147
|
-
requirements:
|
148
|
-
- - "~>"
|
149
|
-
- !ruby/object:Gem::Version
|
150
|
-
version: '1.1'
|
151
|
-
- !ruby/object:Gem::Dependency
|
152
|
-
name: rexical
|
153
|
-
requirement: !ruby/object:Gem::Requirement
|
154
|
-
requirements:
|
155
|
-
- - "~>"
|
156
|
-
- !ruby/object:Gem::Version
|
157
|
-
version: 1.0.5
|
158
|
-
type: :development
|
159
|
-
prerelease: false
|
160
|
-
version_requirements: !ruby/object:Gem::Requirement
|
161
|
-
requirements:
|
162
|
-
- - "~>"
|
163
|
-
- !ruby/object:Gem::Version
|
164
|
-
version: 1.0.5
|
165
|
-
- !ruby/object:Gem::Dependency
|
166
|
-
name: rubocop
|
167
|
-
requirement: !ruby/object:Gem::Requirement
|
168
|
-
requirements:
|
169
|
-
- - "~>"
|
170
|
-
- !ruby/object:Gem::Version
|
171
|
-
version: '1.7'
|
172
|
-
type: :development
|
173
|
-
prerelease: false
|
174
|
-
version_requirements: !ruby/object:Gem::Requirement
|
175
|
-
requirements:
|
176
|
-
- - "~>"
|
177
|
-
- !ruby/object:Gem::Version
|
178
|
-
version: '1.7'
|
179
|
-
- !ruby/object:Gem::Dependency
|
180
|
-
name: simplecov
|
181
|
-
requirement: !ruby/object:Gem::Requirement
|
182
|
-
requirements:
|
183
|
-
- - "~>"
|
184
|
-
- !ruby/object:Gem::Version
|
185
|
-
version: '0.20'
|
186
|
-
type: :development
|
187
|
-
prerelease: false
|
188
|
-
version_requirements: !ruby/object:Gem::Requirement
|
189
|
-
requirements:
|
190
|
-
- - "~>"
|
191
|
-
- !ruby/object:Gem::Version
|
192
|
-
version: '0.20'
|
193
|
-
- !ruby/object:Gem::Dependency
|
194
|
-
name: yard
|
195
|
-
requirement: !ruby/object:Gem::Requirement
|
196
|
-
requirements:
|
197
|
-
- - "~>"
|
198
|
-
- !ruby/object:Gem::Version
|
199
|
-
version: '0.9'
|
200
|
-
type: :development
|
201
|
-
prerelease: false
|
202
|
-
version_requirements: !ruby/object:Gem::Requirement
|
203
|
-
requirements:
|
204
|
-
- - "~>"
|
205
|
-
- !ruby/object:Gem::Version
|
206
|
-
version: '0.9'
|
54
|
+
force_ruby_platform: false
|
207
55
|
description: |
|
208
56
|
Nokogiri (鋸) makes it easy and painless to work with XML and HTML from Ruby. It provides a
|
209
57
|
sensible, easy-to-understand API for reading, writing, modifying, and querying documents. It is
|
210
|
-
fast and standards-compliant by relying on native parsers like libxml2
|
58
|
+
fast and standards-compliant by relying on native parsers like libxml2, libgumbo, or xerces.
|
211
59
|
email: nokogiri-talk@googlegroups.com
|
212
60
|
executables:
|
213
61
|
- nokogiri
|
@@ -311,9 +159,9 @@ files:
|
|
311
159
|
- gumbo-parser/src/error.h
|
312
160
|
- gumbo-parser/src/foreign_attrs.c
|
313
161
|
- gumbo-parser/src/foreign_attrs.gperf
|
314
|
-
- gumbo-parser/src/gumbo.h
|
315
162
|
- gumbo-parser/src/insertion_mode.h
|
316
163
|
- gumbo-parser/src/macros.h
|
164
|
+
- gumbo-parser/src/nokogiri_gumbo.h
|
317
165
|
- gumbo-parser/src/parser.c
|
318
166
|
- gumbo-parser/src/parser.h
|
319
167
|
- gumbo-parser/src/replacement.h
|
@@ -341,6 +189,7 @@ files:
|
|
341
189
|
- gumbo-parser/src/vector.c
|
342
190
|
- gumbo-parser/src/vector.h
|
343
191
|
- lib/nokogiri.rb
|
192
|
+
- lib/nokogiri/class_resolver.rb
|
344
193
|
- lib/nokogiri/css.rb
|
345
194
|
- lib/nokogiri/css/node.rb
|
346
195
|
- lib/nokogiri/css/parser.rb
|
@@ -351,6 +200,7 @@ files:
|
|
351
200
|
- lib/nokogiri/css/tokenizer.rex
|
352
201
|
- lib/nokogiri/css/xpath_visitor.rb
|
353
202
|
- lib/nokogiri/decorators/slop.rb
|
203
|
+
- lib/nokogiri/encoding_handler.rb
|
354
204
|
- lib/nokogiri/extension.rb
|
355
205
|
- lib/nokogiri/gumbo.rb
|
356
206
|
- lib/nokogiri/html.rb
|
@@ -360,6 +210,7 @@ files:
|
|
360
210
|
- lib/nokogiri/html4/document_fragment.rb
|
361
211
|
- lib/nokogiri/html4/element_description.rb
|
362
212
|
- lib/nokogiri/html4/element_description_defaults.rb
|
213
|
+
- lib/nokogiri/html4/encoding_reader.rb
|
363
214
|
- lib/nokogiri/html4/entity_lookup.rb
|
364
215
|
- lib/nokogiri/html4/sax/parser.rb
|
365
216
|
- lib/nokogiri/html4/sax/parser_context.rb
|
@@ -369,6 +220,7 @@ files:
|
|
369
220
|
- lib/nokogiri/html5/document_fragment.rb
|
370
221
|
- lib/nokogiri/html5/node.rb
|
371
222
|
- lib/nokogiri/jruby/dependencies.rb
|
223
|
+
- lib/nokogiri/jruby/nokogiri_jars.rb
|
372
224
|
- lib/nokogiri/syntax_error.rb
|
373
225
|
- lib/nokogiri/version.rb
|
374
226
|
- lib/nokogiri/version/constant.rb
|
@@ -416,14 +268,10 @@ files:
|
|
416
268
|
- patches/libxml2/0001-Remove-script-macro-support.patch
|
417
269
|
- patches/libxml2/0002-Update-entities-to-remove-handling-of-ssi.patch
|
418
270
|
- patches/libxml2/0003-libxml2.la-is-in-top_builddir.patch
|
419
|
-
- patches/libxml2/
|
420
|
-
- patches/libxml2/0005-avoid-isnan-isinf.patch
|
421
|
-
- patches/libxml2/0006-update-automake-files-for-arm64.patch
|
422
|
-
- patches/libxml2/0007-Fix-XPath-recursion-limit.patch
|
271
|
+
- patches/libxml2/0009-allow-wildcard-namespaces.patch
|
423
272
|
- patches/libxslt/0001-update-automake-files-for-arm64.patch
|
424
|
-
-
|
425
|
-
- ports/archives/
|
426
|
-
- ports/archives/libxslt-1.1.34.tar.gz
|
273
|
+
- ports/archives/libxml2-2.10.4.tar.xz
|
274
|
+
- ports/archives/libxslt-1.1.37.tar.xz
|
427
275
|
homepage: https://nokogiri.org
|
428
276
|
licenses:
|
429
277
|
- MIT
|
@@ -433,6 +281,7 @@ metadata:
|
|
433
281
|
documentation_uri: https://nokogiri.org/rdoc/index.html
|
434
282
|
changelog_uri: https://nokogiri.org/CHANGELOG.html
|
435
283
|
source_code_uri: https://github.com/sparklemotion/nokogiri
|
284
|
+
rubygems_mfa_required: 'true'
|
436
285
|
post_install_message:
|
437
286
|
rdoc_options:
|
438
287
|
- "--main"
|
@@ -443,14 +292,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
443
292
|
requirements:
|
444
293
|
- - ">="
|
445
294
|
- !ruby/object:Gem::Version
|
446
|
-
version: 2.
|
295
|
+
version: 2.7.0
|
447
296
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
448
297
|
requirements:
|
449
298
|
- - ">="
|
450
299
|
- !ruby/object:Gem::Version
|
451
300
|
version: '0'
|
452
301
|
requirements: []
|
453
|
-
rubygems_version: 3.
|
302
|
+
rubygems_version: 3.4.10
|
454
303
|
signing_key:
|
455
304
|
specification_version: 4
|
456
305
|
summary: Nokogiri (鋸) makes it easy and painless to work with XML and HTML from Ruby.
|
@@ -1,53 +0,0 @@
|
|
1
|
-
From c94172d2a4451368530db2186190d70be8a1d9e5 Mon Sep 17 00:00:00 2001
|
2
|
-
From: Ilya Zub <ilya@serpapi.com>
|
3
|
-
Date: Wed, 23 Dec 2020 12:45:29 +0200
|
4
|
-
Subject: Use glibc strlen to speed up xmlStrlen
|
5
|
-
MIME-Version: 1.0
|
6
|
-
Content-Type: text/plain; charset=UTF-8
|
7
|
-
Content-Transfer-Encoding: 8bit
|
8
|
-
|
9
|
-
xmlStrlen (entire HTML file): 926171.936981 μs
|
10
|
-
glibc_xmlStrlen (entire HTML file): 36905.903992 μs
|
11
|
-
delta (xmlStrlen ÷ glibc_xmlStrlen): 25.094584 times
|
12
|
-
|
13
|
-
xmlStrlen (average string): 57479.204010 μs
|
14
|
-
glibc_xmlStrlen (average string): 5802.069000 μs
|
15
|
-
delta (xmlStrlen ÷ glibc_xmlStrlen): 9.905937 times
|
16
|
-
|
17
|
-
xmlStrlen (bigger string): 388056.315979 μs
|
18
|
-
glibc_xmlStrlen (bigger string): 12797.856995 μs
|
19
|
-
delta (xmlStrlen ÷ glibc_xmlStrlen): 30.318382 times
|
20
|
-
|
21
|
-
xmlStrlen (smallest string): 15870.046021 μs
|
22
|
-
glibc_xmlStrlen (smallest string): 6282.208984 μs
|
23
|
-
delta (xmlStrlen ÷ glibc_xmlStrlen): 2.527903 times
|
24
|
-
|
25
|
-
See https://gitlab.gnome.org/GNOME/libxml2/-/issues/212 for reference.
|
26
|
-
---
|
27
|
-
xmlstring.c | 9 ++-------
|
28
|
-
1 file changed, 2 insertions(+), 7 deletions(-)
|
29
|
-
|
30
|
-
diff --git a/xmlstring.c b/xmlstring.c
|
31
|
-
index e8a1e45d..df247dff 100644
|
32
|
-
--- a/xmlstring.c
|
33
|
-
+++ b/xmlstring.c
|
34
|
-
@@ -423,14 +423,9 @@ xmlStrsub(const xmlChar *str, int start, int len) {
|
35
|
-
|
36
|
-
int
|
37
|
-
xmlStrlen(const xmlChar *str) {
|
38
|
-
- int len = 0;
|
39
|
-
-
|
40
|
-
if (str == NULL) return(0);
|
41
|
-
- while (*str != 0) { /* non input consuming */
|
42
|
-
- str++;
|
43
|
-
- len++;
|
44
|
-
- }
|
45
|
-
- return(len);
|
46
|
-
+
|
47
|
-
+ return strlen((const char*)str);
|
48
|
-
}
|
49
|
-
|
50
|
-
/**
|
51
|
-
--
|
52
|
-
2.29.2
|
53
|
-
|
@@ -1,81 +0,0 @@
|
|
1
|
-
This patch is a result of rake-compiler-dock using centos 7 (manylinux2014) to cross-compile.
|
2
|
-
|
3
|
-
Centos, for reasons I have not been able to discern, implements `isnan` and `isinf` as a function
|
4
|
-
and not as a macro. Debian knows how to resolve that function at dynamic-link time (despite using a
|
5
|
-
macro at compile time), but musl-based systems (like alpine) do not. Running `nm` on nokogiri.so
|
6
|
-
created on such a centos system shows:
|
7
|
-
|
8
|
-
```
|
9
|
-
U __isinf@@GLIBC_2.2.5
|
10
|
-
U __isnan@@GLIBC_2.2.5
|
11
|
-
```
|
12
|
-
|
13
|
-
(see https://github.com/sparklemotion/nokogiri/pull/2142 for more info)
|
14
|
-
|
15
|
-
This patch avoids using glibc's `isnan` and `isinf` calls, instead using libxml2's fallback
|
16
|
-
implementation. There's history here, see libxml2 commit 8813f39:
|
17
|
-
|
18
|
-
commit 8813f39
|
19
|
-
Author: Nick Wellnhofer <wellnhofer@aevum.de>
|
20
|
-
Date: 2017-09-21 00:11:26 +0200
|
21
|
-
|
22
|
-
Simplify XPath NaN, inf and -0 handling
|
23
|
-
|
24
|
-
Use C99 macros NAN, INFINITY, isnan, isinf. If they're not available:
|
25
|
-
|
26
|
-
- Assume that (0.0 / 0.0) generates a NaN and !(x == x) tests for NaN.
|
27
|
-
- Use C89's HUGE_VAL for INFINITY.
|
28
|
-
|
29
|
-
Remove manual handling of NaN, infinity and negative zero in functions
|
30
|
-
xmlXPathValueFlipSign and xmlXPathDivValues.
|
31
|
-
|
32
|
-
Remove xmlXPathGetSign. All the tests for negative zero can be replaced
|
33
|
-
with a test for negative or positive zero.
|
34
|
-
|
35
|
-
Simplify xmlXPathRoundFunction.
|
36
|
-
|
37
|
-
Remove Trio dependency.
|
38
|
-
|
39
|
-
This should work on IEEE 754 compliant implementations even if the C99
|
40
|
-
macros aren't available, but will likely break some ancient platforms.
|
41
|
-
If problems arise, my plan is to port the relevant trionan.c solution
|
42
|
-
to xpath.c. Note that non-compliant implementations are impossible
|
43
|
-
to fully support, anyway, since XPath requires IEEE 754.
|
44
|
-
|
45
|
-
This patch would be unnecessary if any of the following was true:
|
46
|
-
|
47
|
-
* centos implements these as macros, and doesn't generate an unresolved symbol for either in the shared library
|
48
|
-
* we had a way to ensure `__isinf` and `__isnan` resolve on musl (e.g., we implement them locally)
|
49
|
-
|
50
|
-
diff --git a/xpath.c b/xpath.c
|
51
|
-
index 9f64ab9..5b6d999 100644
|
52
|
-
--- a/xpath.c
|
53
|
-
+++ b/xpath.c
|
54
|
-
@@ -515,11 +515,7 @@ xmlXPathInit(void) {
|
55
|
-
*/
|
56
|
-
int
|
57
|
-
xmlXPathIsNaN(double val) {
|
58
|
-
-#ifdef isnan
|
59
|
-
- return isnan(val);
|
60
|
-
-#else
|
61
|
-
return !(val == val);
|
62
|
-
-#endif
|
63
|
-
}
|
64
|
-
|
65
|
-
/**
|
66
|
-
@@ -530,15 +530,11 @@ xmlXPathIsNaN(double val) {
|
67
|
-
*/
|
68
|
-
int
|
69
|
-
xmlXPathIsInf(double val) {
|
70
|
-
-#ifdef isinf
|
71
|
-
- return isinf(val) ? (val > 0 ? 1 : -1) : 0;
|
72
|
-
-#else
|
73
|
-
if (val >= xmlXPathPINF)
|
74
|
-
return 1;
|
75
|
-
if (val <= -xmlXPathPINF)
|
76
|
-
return -1;
|
77
|
-
return 0;
|
78
|
-
-#endif
|
79
|
-
}
|
80
|
-
|
81
|
-
#endif /* SCHEMAS or XPATH */
|