nokogiri 1.12.0.rc1 → 1.12.0
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/ext/nokogiri/gumbo.c +5 -32
- data/lib/nokogiri/html5.rb +10 -10
- data/lib/nokogiri/version/constant.rb +1 -1
- metadata +4 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 17bab3034390c1ad985dc83bf28815a626570ba5ccc32ff1867cef4e622aa81d
|
4
|
+
data.tar.gz: 7ca9165fda9e22bd0d7e5338216e4bad38f0989736f1cc369817554d7d1f128f
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8b74271769a605d2d91abaf4818846dd8e95ca8efbd1eddab7505a3bc0ed7b1f87042c702a26d9f4b7eebf5a9e4922207b64dd003f5cc2a9c045d3b7ecf7615e
|
7
|
+
data.tar.gz: 9b2c4c957b9c5fde4a31910952149db8a96d0dd370e3a8966606b5c3db4c3e27e6320a2653af7c346cdd19136a2d1ff180c61394d0a86beba84362d3846c55a7
|
data/ext/nokogiri/gumbo.c
CHANGED
@@ -300,35 +300,10 @@ typedef struct {
|
|
300
300
|
xmlDocPtr doc;
|
301
301
|
} ParseArgs;
|
302
302
|
|
303
|
-
static void
|
304
|
-
parse_args_mark(void *parse_args)
|
305
|
-
{
|
306
|
-
ParseArgs *args = parse_args;
|
307
|
-
rb_gc_mark_maybe(args->input);
|
308
|
-
rb_gc_mark_maybe(args->url_or_frag);
|
309
|
-
}
|
310
|
-
|
311
|
-
// Wrap a ParseArgs pointer. The underlying ParseArgs must outlive the
|
312
|
-
// wrapper.
|
313
|
-
static VALUE
|
314
|
-
wrap_parse_args(ParseArgs *args)
|
315
|
-
{
|
316
|
-
return Data_Wrap_Struct(rb_cObject, parse_args_mark, RUBY_NEVER_FREE, args);
|
317
|
-
}
|
318
|
-
|
319
|
-
// Returnsd the underlying ParseArgs wrapped by wrap_parse_args.
|
320
|
-
static ParseArgs *
|
321
|
-
unwrap_parse_args(VALUE obj)
|
322
|
-
{
|
323
|
-
ParseArgs *args;
|
324
|
-
Data_Get_Struct(obj, ParseArgs, args);
|
325
|
-
return args;
|
326
|
-
}
|
327
|
-
|
328
303
|
static VALUE
|
329
304
|
parse_cleanup(VALUE parse_args)
|
330
305
|
{
|
331
|
-
ParseArgs *args =
|
306
|
+
ParseArgs *args = (ParseArgs*)parse_args;
|
332
307
|
gumbo_destroy_output(args->output);
|
333
308
|
// Make sure garbage collection doesn't mark the objects as being live based
|
334
309
|
// on references from the ParseArgs. This may be unnecessary.
|
@@ -360,15 +335,14 @@ parse(VALUE self, VALUE input, VALUE url, VALUE max_attributes, VALUE max_errors
|
|
360
335
|
.url_or_frag = url,
|
361
336
|
.doc = NULL,
|
362
337
|
};
|
363
|
-
VALUE parse_args = wrap_parse_args(&args);
|
364
338
|
|
365
|
-
return rb_ensure(parse_continue,
|
339
|
+
return rb_ensure(parse_continue, (VALUE)(&args), parse_cleanup, (VALUE)(&args));
|
366
340
|
}
|
367
341
|
|
368
342
|
static VALUE
|
369
343
|
parse_continue(VALUE parse_args)
|
370
344
|
{
|
371
|
-
ParseArgs *args =
|
345
|
+
ParseArgs *args = (ParseArgs*)parse_args;
|
372
346
|
GumboOutput *output = args->output;
|
373
347
|
xmlDocPtr doc;
|
374
348
|
if (output->document->v.document.has_doctype) {
|
@@ -571,15 +545,14 @@ error:
|
|
571
545
|
.url_or_frag = doc_fragment,
|
572
546
|
.doc = (xmlDocPtr)extract_xml_node(doc),
|
573
547
|
};
|
574
|
-
VALUE
|
575
|
-
rb_ensure(fragment_continue, parse_args, parse_cleanup, parse_args);
|
548
|
+
rb_ensure(fragment_continue, (VALUE)(&args), parse_cleanup, (VALUE)(&args));
|
576
549
|
return Qnil;
|
577
550
|
}
|
578
551
|
|
579
552
|
static VALUE
|
580
553
|
fragment_continue(VALUE parse_args)
|
581
554
|
{
|
582
|
-
ParseArgs *args =
|
555
|
+
ParseArgs *args = (ParseArgs*)parse_args;
|
583
556
|
GumboOutput *output = args->output;
|
584
557
|
VALUE doc_fragment = args->url_or_frag;
|
585
558
|
xmlDocPtr xml_doc = args->doc;
|
data/lib/nokogiri/html5.rb
CHANGED
@@ -53,9 +53,9 @@ module Nokogiri
|
|
53
53
|
#
|
54
54
|
# === Error reporting
|
55
55
|
#
|
56
|
-
#
|
57
|
-
# are reported but this can be configured by passing the +:max_errors+ option to
|
58
|
-
# {HTML5.fragment}.
|
56
|
+
# Nokogiri contains an experimental HTML5 parse error reporting facility. By default, no parse
|
57
|
+
# errors are reported but this can be configured by passing the +:max_errors+ option to
|
58
|
+
# {HTML5.parse} or {HTML5.fragment}.
|
59
59
|
#
|
60
60
|
# For example, this script:
|
61
61
|
#
|
@@ -88,7 +88,7 @@ module Nokogiri
|
|
88
88
|
# parsing HTML. The parse errors in the "tree construction" stage do not have standardized error
|
89
89
|
# codes (yet).
|
90
90
|
#
|
91
|
-
# As a convenience to
|
91
|
+
# As a convenience to Nokogiri users, the defined error codes are available via
|
92
92
|
# {Nokogiri::XML::SyntaxError#str1} method.
|
93
93
|
#
|
94
94
|
# doc = Nokogiri::HTML5.parse('<span/>Hi there!</span foo=bar />', max_errors: 10)
|
@@ -104,7 +104,7 @@ module Nokogiri
|
|
104
104
|
# stage and doesn't have a standardized error code.
|
105
105
|
#
|
106
106
|
# For the purposes of semantic versioning, the error messages, error locations, and error codes
|
107
|
-
# are not part of
|
107
|
+
# are not part of Nokogiri's public API. That is, these are subject to change without Nokogiri's
|
108
108
|
# major version number changing. These may be stabilized in the future.
|
109
109
|
#
|
110
110
|
# === Maximum tree depth
|
@@ -113,8 +113,8 @@ module Nokogiri
|
|
113
113
|
# +:max_tree_depth+ option. If the depth of the tree would exceed this limit, then an
|
114
114
|
# {::ArgumentError} is thrown.
|
115
115
|
#
|
116
|
-
# This limit (which defaults to <tt>
|
117
|
-
# by giving the option <tt>max_tree_depth: -1</tt>.
|
116
|
+
# This limit (which defaults to <tt>Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH = 400</tt>) can be
|
117
|
+
# removed by giving the option <tt>max_tree_depth: -1</tt>.
|
118
118
|
#
|
119
119
|
# html = '<!DOCTYPE html>' + '<div>' * 1000
|
120
120
|
# doc = Nokogiri.HTML5(html)
|
@@ -126,8 +126,8 @@ module Nokogiri
|
|
126
126
|
# The maximum number of attributes per DOM element is configurable by the +:max_attributes+
|
127
127
|
# option. If a given element would exceed this limit, then an {::ArgumentError} is thrown.
|
128
128
|
#
|
129
|
-
# This limit (which defaults to <tt>
|
130
|
-
# by giving the option <tt>max_attributes: -1</tt>.
|
129
|
+
# This limit (which defaults to <tt>Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES = 400</tt>) can be
|
130
|
+
# removed by giving the option <tt>max_attributes: -1</tt>.
|
131
131
|
#
|
132
132
|
# html = '<!DOCTYPE html><div ' + (1..1000).map { |x| "attr-#{x}" }.join(' ') + '>'
|
133
133
|
# # "<!DOCTYPE html><div attr-1 attr-2 attr-3 ... attr-1000>"
|
@@ -182,7 +182,7 @@ module Nokogiri
|
|
182
182
|
#
|
183
183
|
# == Encodings
|
184
184
|
#
|
185
|
-
#
|
185
|
+
# Nokogiri always parses HTML5 using {https://en.wikipedia.org/wiki/UTF-8 UTF-8}; however, the
|
186
186
|
# encoding of the input can be explicitly selected via the optional +encoding+ parameter. This is
|
187
187
|
# most useful when the input comes not from a string but from an IO object.
|
188
188
|
#
|
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: 1.12.0
|
4
|
+
version: 1.12.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Mike Dalessio
|
@@ -20,7 +20,7 @@ authors:
|
|
20
20
|
autorequire:
|
21
21
|
bindir: bin
|
22
22
|
cert_chain: []
|
23
|
-
date: 2021-
|
23
|
+
date: 2021-08-02 00:00:00.000000000 Z
|
24
24
|
dependencies:
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: racc
|
@@ -446,9 +446,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
446
446
|
version: 2.5.0
|
447
447
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
448
448
|
requirements:
|
449
|
-
- - "
|
449
|
+
- - ">="
|
450
450
|
- !ruby/object:Gem::Version
|
451
|
-
version:
|
451
|
+
version: '0'
|
452
452
|
requirements: []
|
453
453
|
rubygems_version: 3.2.15
|
454
454
|
signing_key:
|