Nokogiri_precompiled_aarch64_dedshit 1.14.5
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/Gemfile +44 -0
- data/LICENSE-DEPENDENCIES.md +2224 -0
- data/LICENSE.md +9 -0
- data/README.md +287 -0
- data/bin/nokogiri +131 -0
- data/dependencies.yml +41 -0
- data/ext/java/nokogiri/Html4Document.java +157 -0
- data/ext/java/nokogiri/Html4ElementDescription.java +133 -0
- data/ext/java/nokogiri/Html4EntityLookup.java +63 -0
- data/ext/java/nokogiri/Html4SaxParserContext.java +289 -0
- data/ext/java/nokogiri/Html4SaxPushParser.java +213 -0
- data/ext/java/nokogiri/NokogiriService.java +613 -0
- data/ext/java/nokogiri/XmlAttr.java +154 -0
- data/ext/java/nokogiri/XmlAttributeDecl.java +119 -0
- data/ext/java/nokogiri/XmlCdata.java +60 -0
- data/ext/java/nokogiri/XmlComment.java +77 -0
- data/ext/java/nokogiri/XmlDocument.java +705 -0
- data/ext/java/nokogiri/XmlDocumentFragment.java +163 -0
- data/ext/java/nokogiri/XmlDtd.java +516 -0
- data/ext/java/nokogiri/XmlElement.java +44 -0
- data/ext/java/nokogiri/XmlElementContent.java +412 -0
- data/ext/java/nokogiri/XmlElementDecl.java +148 -0
- data/ext/java/nokogiri/XmlEntityDecl.java +151 -0
- data/ext/java/nokogiri/XmlEntityReference.java +79 -0
- data/ext/java/nokogiri/XmlNamespace.java +193 -0
- data/ext/java/nokogiri/XmlNode.java +1938 -0
- data/ext/java/nokogiri/XmlNodeSet.java +463 -0
- data/ext/java/nokogiri/XmlProcessingInstruction.java +79 -0
- data/ext/java/nokogiri/XmlReader.java +615 -0
- data/ext/java/nokogiri/XmlRelaxng.java +133 -0
- data/ext/java/nokogiri/XmlSaxParserContext.java +329 -0
- data/ext/java/nokogiri/XmlSaxPushParser.java +288 -0
- data/ext/java/nokogiri/XmlSchema.java +423 -0
- data/ext/java/nokogiri/XmlSyntaxError.java +137 -0
- data/ext/java/nokogiri/XmlText.java +90 -0
- data/ext/java/nokogiri/XmlXpathContext.java +305 -0
- data/ext/java/nokogiri/XsltStylesheet.java +368 -0
- data/ext/java/nokogiri/internals/ClosedStreamException.java +13 -0
- data/ext/java/nokogiri/internals/HtmlDomParserContext.java +252 -0
- data/ext/java/nokogiri/internals/IgnoreSchemaErrorsErrorHandler.java +27 -0
- data/ext/java/nokogiri/internals/NokogiriBlockingQueueInputStream.java +178 -0
- data/ext/java/nokogiri/internals/NokogiriDomParser.java +99 -0
- data/ext/java/nokogiri/internals/NokogiriEntityResolver.java +140 -0
- data/ext/java/nokogiri/internals/NokogiriErrorHandler.java +65 -0
- data/ext/java/nokogiri/internals/NokogiriHandler.java +339 -0
- data/ext/java/nokogiri/internals/NokogiriHelpers.java +817 -0
- data/ext/java/nokogiri/internals/NokogiriNamespaceCache.java +228 -0
- data/ext/java/nokogiri/internals/NokogiriNamespaceContext.java +110 -0
- data/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler.java +86 -0
- data/ext/java/nokogiri/internals/NokogiriNonStrictErrorHandler4NekoHtml.java +107 -0
- data/ext/java/nokogiri/internals/NokogiriStrictErrorHandler.java +62 -0
- data/ext/java/nokogiri/internals/NokogiriXPathFunction.java +165 -0
- data/ext/java/nokogiri/internals/NokogiriXPathFunctionResolver.java +50 -0
- data/ext/java/nokogiri/internals/NokogiriXPathVariableResolver.java +37 -0
- data/ext/java/nokogiri/internals/NokogiriXsltErrorListener.java +70 -0
- data/ext/java/nokogiri/internals/ParserContext.java +262 -0
- data/ext/java/nokogiri/internals/ReaderNode.java +564 -0
- data/ext/java/nokogiri/internals/SaveContextVisitor.java +865 -0
- data/ext/java/nokogiri/internals/SchemaErrorHandler.java +50 -0
- data/ext/java/nokogiri/internals/XalanDTMManagerPatch.java +174 -0
- data/ext/java/nokogiri/internals/XmlDeclHandler.java +11 -0
- data/ext/java/nokogiri/internals/XmlDomParserContext.java +265 -0
- data/ext/java/nokogiri/internals/XmlSaxParser.java +40 -0
- data/ext/java/nokogiri/internals/c14n/AttrCompare.java +122 -0
- data/ext/java/nokogiri/internals/c14n/C14nHelper.java +178 -0
- data/ext/java/nokogiri/internals/c14n/CanonicalFilter.java +43 -0
- data/ext/java/nokogiri/internals/c14n/CanonicalizationException.java +106 -0
- data/ext/java/nokogiri/internals/c14n/Canonicalizer.java +278 -0
- data/ext/java/nokogiri/internals/c14n/Canonicalizer11.java +664 -0
- data/ext/java/nokogiri/internals/c14n/Canonicalizer11_OmitComments.java +45 -0
- data/ext/java/nokogiri/internals/c14n/Canonicalizer11_WithComments.java +45 -0
- data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315.java +388 -0
- data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315Excl.java +308 -0
- data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315ExclOmitComments.java +47 -0
- data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315ExclWithComments.java +51 -0
- data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315OmitComments.java +51 -0
- data/ext/java/nokogiri/internals/c14n/Canonicalizer20010315WithComments.java +50 -0
- data/ext/java/nokogiri/internals/c14n/CanonicalizerBase.java +660 -0
- data/ext/java/nokogiri/internals/c14n/CanonicalizerPhysical.java +194 -0
- data/ext/java/nokogiri/internals/c14n/CanonicalizerSpi.java +77 -0
- data/ext/java/nokogiri/internals/c14n/Constants.java +45 -0
- data/ext/java/nokogiri/internals/c14n/ElementProxy.java +325 -0
- data/ext/java/nokogiri/internals/c14n/HelperNodeList.java +106 -0
- data/ext/java/nokogiri/internals/c14n/IgnoreAllErrorHandler.java +86 -0
- data/ext/java/nokogiri/internals/c14n/InclusiveNamespaces.java +181 -0
- data/ext/java/nokogiri/internals/c14n/InvalidCanonicalizerException.java +87 -0
- data/ext/java/nokogiri/internals/c14n/NameSpaceSymbTable.java +452 -0
- data/ext/java/nokogiri/internals/c14n/NodeFilter.java +52 -0
- data/ext/java/nokogiri/internals/c14n/UtfHelpper.java +190 -0
- data/ext/java/nokogiri/internals/c14n/XMLUtils.java +540 -0
- data/ext/java/nokogiri/internals/dom2dtm/DOM2DTM.java +1712 -0
- data/ext/java/nokogiri/internals/dom2dtm/DOM2DTMdefaultNamespaceDeclarationNode.java +737 -0
- data/ext/nokogiri/depend +38 -0
- data/ext/nokogiri/extconf.rb +1086 -0
- data/ext/nokogiri/gumbo.c +594 -0
- data/ext/nokogiri/html4_document.c +167 -0
- data/ext/nokogiri/html4_element_description.c +294 -0
- data/ext/nokogiri/html4_entity_lookup.c +37 -0
- data/ext/nokogiri/html4_sax_parser_context.c +116 -0
- data/ext/nokogiri/html4_sax_push_parser.c +95 -0
- data/ext/nokogiri/libxml2_backwards_compat.c +121 -0
- data/ext/nokogiri/nokogiri.c +265 -0
- data/ext/nokogiri/nokogiri.h +235 -0
- data/ext/nokogiri/test_global_handlers.c +42 -0
- data/ext/nokogiri/xml_attr.c +103 -0
- data/ext/nokogiri/xml_attribute_decl.c +70 -0
- data/ext/nokogiri/xml_cdata.c +57 -0
- data/ext/nokogiri/xml_comment.c +62 -0
- data/ext/nokogiri/xml_document.c +689 -0
- data/ext/nokogiri/xml_document_fragment.c +44 -0
- data/ext/nokogiri/xml_dtd.c +210 -0
- data/ext/nokogiri/xml_element_content.c +128 -0
- data/ext/nokogiri/xml_element_decl.c +69 -0
- data/ext/nokogiri/xml_encoding_handler.c +104 -0
- data/ext/nokogiri/xml_entity_decl.c +112 -0
- data/ext/nokogiri/xml_entity_reference.c +50 -0
- data/ext/nokogiri/xml_namespace.c +186 -0
- data/ext/nokogiri/xml_node.c +2426 -0
- data/ext/nokogiri/xml_node_set.c +496 -0
- data/ext/nokogiri/xml_processing_instruction.c +54 -0
- data/ext/nokogiri/xml_reader.c +794 -0
- data/ext/nokogiri/xml_relax_ng.c +164 -0
- data/ext/nokogiri/xml_sax_parser.c +316 -0
- data/ext/nokogiri/xml_sax_parser_context.c +283 -0
- data/ext/nokogiri/xml_sax_push_parser.c +166 -0
- data/ext/nokogiri/xml_schema.c +260 -0
- data/ext/nokogiri/xml_syntax_error.c +85 -0
- data/ext/nokogiri/xml_text.c +48 -0
- data/ext/nokogiri/xml_xpath_context.c +415 -0
- data/ext/nokogiri/xslt_stylesheet.c +363 -0
- data/gumbo-parser/CHANGES.md +63 -0
- data/gumbo-parser/Makefile +111 -0
- data/gumbo-parser/THANKS +27 -0
- data/gumbo-parser/src/Makefile +34 -0
- data/gumbo-parser/src/README.md +41 -0
- data/gumbo-parser/src/ascii.c +75 -0
- data/gumbo-parser/src/ascii.h +115 -0
- data/gumbo-parser/src/attribute.c +42 -0
- data/gumbo-parser/src/attribute.h +17 -0
- data/gumbo-parser/src/char_ref.c +22225 -0
- data/gumbo-parser/src/char_ref.h +29 -0
- data/gumbo-parser/src/char_ref.rl +2154 -0
- data/gumbo-parser/src/error.c +626 -0
- data/gumbo-parser/src/error.h +148 -0
- data/gumbo-parser/src/foreign_attrs.c +104 -0
- data/gumbo-parser/src/foreign_attrs.gperf +27 -0
- data/gumbo-parser/src/insertion_mode.h +33 -0
- data/gumbo-parser/src/macros.h +91 -0
- data/gumbo-parser/src/nokogiri_gumbo.h +944 -0
- data/gumbo-parser/src/parser.c +4878 -0
- data/gumbo-parser/src/parser.h +41 -0
- data/gumbo-parser/src/replacement.h +33 -0
- data/gumbo-parser/src/string_buffer.c +103 -0
- data/gumbo-parser/src/string_buffer.h +68 -0
- data/gumbo-parser/src/string_piece.c +48 -0
- data/gumbo-parser/src/svg_attrs.c +174 -0
- data/gumbo-parser/src/svg_attrs.gperf +77 -0
- data/gumbo-parser/src/svg_tags.c +137 -0
- data/gumbo-parser/src/svg_tags.gperf +55 -0
- data/gumbo-parser/src/tag.c +223 -0
- data/gumbo-parser/src/tag_lookup.c +382 -0
- data/gumbo-parser/src/tag_lookup.gperf +170 -0
- data/gumbo-parser/src/tag_lookup.h +13 -0
- data/gumbo-parser/src/token_buffer.c +79 -0
- data/gumbo-parser/src/token_buffer.h +71 -0
- data/gumbo-parser/src/token_type.h +17 -0
- data/gumbo-parser/src/tokenizer.c +3463 -0
- data/gumbo-parser/src/tokenizer.h +112 -0
- data/gumbo-parser/src/tokenizer_states.h +339 -0
- data/gumbo-parser/src/utf8.c +245 -0
- data/gumbo-parser/src/utf8.h +164 -0
- data/gumbo-parser/src/util.c +66 -0
- data/gumbo-parser/src/util.h +34 -0
- data/gumbo-parser/src/vector.c +111 -0
- data/gumbo-parser/src/vector.h +45 -0
- data/lib/nokogiri/class_resolver.rb +67 -0
- data/lib/nokogiri/css/node.rb +54 -0
- data/lib/nokogiri/css/parser.rb +770 -0
- data/lib/nokogiri/css/parser.y +277 -0
- data/lib/nokogiri/css/parser_extras.rb +96 -0
- data/lib/nokogiri/css/syntax_error.rb +9 -0
- data/lib/nokogiri/css/tokenizer.rb +155 -0
- data/lib/nokogiri/css/tokenizer.rex +56 -0
- data/lib/nokogiri/css/xpath_visitor.rb +359 -0
- data/lib/nokogiri/css.rb +66 -0
- data/lib/nokogiri/decorators/slop.rb +44 -0
- data/lib/nokogiri/encoding_handler.rb +57 -0
- data/lib/nokogiri/extension.rb +32 -0
- data/lib/nokogiri/gumbo.rb +15 -0
- data/lib/nokogiri/html.rb +48 -0
- data/lib/nokogiri/html4/builder.rb +37 -0
- data/lib/nokogiri/html4/document.rb +214 -0
- data/lib/nokogiri/html4/document_fragment.rb +54 -0
- data/lib/nokogiri/html4/element_description.rb +25 -0
- data/lib/nokogiri/html4/element_description_defaults.rb +572 -0
- data/lib/nokogiri/html4/encoding_reader.rb +121 -0
- data/lib/nokogiri/html4/entity_lookup.rb +15 -0
- data/lib/nokogiri/html4/sax/parser.rb +63 -0
- data/lib/nokogiri/html4/sax/parser_context.rb +20 -0
- data/lib/nokogiri/html4/sax/push_parser.rb +37 -0
- data/lib/nokogiri/html4.rb +47 -0
- data/lib/nokogiri/html5/document.rb +168 -0
- data/lib/nokogiri/html5/document_fragment.rb +90 -0
- data/lib/nokogiri/html5/node.rb +98 -0
- data/lib/nokogiri/html5.rb +389 -0
- data/lib/nokogiri/jruby/dependencies.rb +3 -0
- data/lib/nokogiri/jruby/isorelax/isorelax/20030108/isorelax-20030108.jar +0 -0
- data/lib/nokogiri/jruby/net/sf/saxon/Saxon-HE/9.6.0-4/Saxon-HE-9.6.0-4.jar +0 -0
- data/lib/nokogiri/jruby/net/sourceforge/htmlunit/neko-htmlunit/2.63.0/neko-htmlunit-2.63.0.jar +0 -0
- data/lib/nokogiri/jruby/nokogiri_jars.rb +43 -0
- data/lib/nokogiri/jruby/nu/validator/jing/20200702VNU/jing-20200702VNU.jar +0 -0
- data/lib/nokogiri/jruby/org/nokogiri/nekodtd/0.1.11.noko2/nekodtd-0.1.11.noko2.jar +0 -0
- data/lib/nokogiri/jruby/xalan/serializer/2.7.3/serializer-2.7.3.jar +0 -0
- data/lib/nokogiri/jruby/xalan/xalan/2.7.3/xalan-2.7.3.jar +0 -0
- data/lib/nokogiri/jruby/xerces/xercesImpl/2.12.2/xercesImpl-2.12.2.jar +0 -0
- data/lib/nokogiri/jruby/xml-apis/xml-apis/1.4.01/xml-apis-1.4.01.jar +0 -0
- data/lib/nokogiri/syntax_error.rb +6 -0
- data/lib/nokogiri/version/constant.rb +6 -0
- data/lib/nokogiri/version/info.rb +223 -0
- data/lib/nokogiri/version.rb +4 -0
- data/lib/nokogiri/xml/attr.rb +66 -0
- data/lib/nokogiri/xml/attribute_decl.rb +20 -0
- data/lib/nokogiri/xml/builder.rb +487 -0
- data/lib/nokogiri/xml/cdata.rb +13 -0
- data/lib/nokogiri/xml/character_data.rb +9 -0
- data/lib/nokogiri/xml/document.rb +471 -0
- data/lib/nokogiri/xml/document_fragment.rb +205 -0
- data/lib/nokogiri/xml/dtd.rb +34 -0
- data/lib/nokogiri/xml/element_content.rb +38 -0
- data/lib/nokogiri/xml/element_decl.rb +15 -0
- data/lib/nokogiri/xml/entity_decl.rb +21 -0
- data/lib/nokogiri/xml/entity_reference.rb +20 -0
- data/lib/nokogiri/xml/namespace.rb +58 -0
- data/lib/nokogiri/xml/node/save_options.rb +68 -0
- data/lib/nokogiri/xml/node.rb +1563 -0
- data/lib/nokogiri/xml/node_set.rb +447 -0
- data/lib/nokogiri/xml/notation.rb +19 -0
- data/lib/nokogiri/xml/parse_options.rb +213 -0
- data/lib/nokogiri/xml/pp/character_data.rb +21 -0
- data/lib/nokogiri/xml/pp/node.rb +57 -0
- data/lib/nokogiri/xml/pp.rb +4 -0
- data/lib/nokogiri/xml/processing_instruction.rb +11 -0
- data/lib/nokogiri/xml/reader.rb +105 -0
- data/lib/nokogiri/xml/relax_ng.rb +38 -0
- data/lib/nokogiri/xml/sax/document.rb +167 -0
- data/lib/nokogiri/xml/sax/parser.rb +125 -0
- data/lib/nokogiri/xml/sax/parser_context.rb +21 -0
- data/lib/nokogiri/xml/sax/push_parser.rb +61 -0
- data/lib/nokogiri/xml/sax.rb +6 -0
- data/lib/nokogiri/xml/schema.rb +73 -0
- data/lib/nokogiri/xml/searchable.rb +270 -0
- data/lib/nokogiri/xml/syntax_error.rb +72 -0
- data/lib/nokogiri/xml/text.rb +11 -0
- data/lib/nokogiri/xml/xpath/syntax_error.rb +13 -0
- data/lib/nokogiri/xml/xpath.rb +21 -0
- data/lib/nokogiri/xml/xpath_context.rb +16 -0
- data/lib/nokogiri/xml.rb +76 -0
- data/lib/nokogiri/xslt/stylesheet.rb +27 -0
- data/lib/nokogiri/xslt.rb +65 -0
- data/lib/nokogiri.rb +120 -0
- data/lib/xsd/xmlparser/nokogiri.rb +106 -0
- metadata +391 -0
@@ -0,0 +1,389 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
#
|
5
|
+
# Copyright 2013-2021 Sam Ruby, Stephen Checkoway
|
6
|
+
#
|
7
|
+
# Licensed under the Apache License, Version 2.0 (the "License");
|
8
|
+
# you may not use this file except in compliance with the License.
|
9
|
+
# You may obtain a copy of the License at
|
10
|
+
#
|
11
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
12
|
+
#
|
13
|
+
# Unless required by applicable law or agreed to in writing, software
|
14
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
15
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
16
|
+
# See the License for the specific language governing permissions and
|
17
|
+
# limitations under the License.
|
18
|
+
#
|
19
|
+
|
20
|
+
require_relative "html5/document"
|
21
|
+
require_relative "html5/document_fragment"
|
22
|
+
require_relative "html5/node"
|
23
|
+
|
24
|
+
module Nokogiri
|
25
|
+
# Since v1.12.0
|
26
|
+
#
|
27
|
+
# ⚠ HTML5 functionality is not available when running JRuby.
|
28
|
+
#
|
29
|
+
# Parse an HTML5 document. Convenience method for {Nokogiri::HTML5::Document.parse}
|
30
|
+
def self.HTML5(input, url = nil, encoding = nil, **options, &block)
|
31
|
+
Nokogiri::HTML5::Document.parse(input, url, encoding, **options, &block)
|
32
|
+
end
|
33
|
+
|
34
|
+
# == Usage
|
35
|
+
#
|
36
|
+
# ⚠ HTML5 functionality is not available when running JRuby.
|
37
|
+
#
|
38
|
+
# Parse an HTML5 document:
|
39
|
+
#
|
40
|
+
# doc = Nokogiri.HTML5(string)
|
41
|
+
#
|
42
|
+
# Parse an HTML5 fragment:
|
43
|
+
#
|
44
|
+
# fragment = Nokogiri::HTML5.fragment(string)
|
45
|
+
#
|
46
|
+
# == Parsing options
|
47
|
+
#
|
48
|
+
# The document and fragment parsing methods support options that are different from Nokogiri's.
|
49
|
+
#
|
50
|
+
# - <tt>Nokogiri.HTML5(html, url = nil, encoding = nil, options = {})</tt>
|
51
|
+
# - <tt>Nokogiri::HTML5.parse(html, url = nil, encoding = nil, options = {})</tt>
|
52
|
+
# - <tt>Nokogiri::HTML5::Document.parse(html, url = nil, encoding = nil, options = {})</tt>
|
53
|
+
# - <tt>Nokogiri::HTML5.fragment(html, encoding = nil, options = {})</tt>
|
54
|
+
# - <tt>Nokogiri::HTML5::DocumentFragment.parse(html, encoding = nil, options = {})</tt>
|
55
|
+
#
|
56
|
+
# The three currently supported options are +:max_errors+, +:max_tree_depth+ and
|
57
|
+
# +:max_attributes+, described below.
|
58
|
+
#
|
59
|
+
# === Error reporting
|
60
|
+
#
|
61
|
+
# Nokogiri contains an experimental HTML5 parse error reporting facility. By default, no parse
|
62
|
+
# errors are reported but this can be configured by passing the +:max_errors+ option to
|
63
|
+
# {HTML5.parse} or {HTML5.fragment}.
|
64
|
+
#
|
65
|
+
# For example, this script:
|
66
|
+
#
|
67
|
+
# doc = Nokogiri::HTML5.parse('<span/>Hi there!</span foo=bar />', max_errors: 10)
|
68
|
+
# doc.errors.each do |err|
|
69
|
+
# puts(err)
|
70
|
+
# end
|
71
|
+
#
|
72
|
+
# Emits:
|
73
|
+
#
|
74
|
+
# 1:1: ERROR: Expected a doctype token
|
75
|
+
# <span/>Hi there!</span foo=bar />
|
76
|
+
# ^
|
77
|
+
# 1:1: ERROR: Start tag of nonvoid HTML element ends with '/>', use '>'.
|
78
|
+
# <span/>Hi there!</span foo=bar />
|
79
|
+
# ^
|
80
|
+
# 1:17: ERROR: End tag ends with '/>', use '>'.
|
81
|
+
# <span/>Hi there!</span foo=bar />
|
82
|
+
# ^
|
83
|
+
# 1:17: ERROR: End tag contains attributes.
|
84
|
+
# <span/>Hi there!</span foo=bar />
|
85
|
+
# ^
|
86
|
+
#
|
87
|
+
# Using <tt>max_errors: -1</tt> results in an unlimited number of errors being returned.
|
88
|
+
#
|
89
|
+
# The errors returned by {HTML5::Document#errors} are instances of {Nokogiri::XML::SyntaxError}.
|
90
|
+
#
|
91
|
+
# The {https://html.spec.whatwg.org/multipage/parsing.html#parse-errors HTML standard} defines a
|
92
|
+
# number of standard parse error codes. These error codes only cover the "tokenization" stage of
|
93
|
+
# parsing HTML. The parse errors in the "tree construction" stage do not have standardized error
|
94
|
+
# codes (yet).
|
95
|
+
#
|
96
|
+
# As a convenience to Nokogiri users, the defined error codes are available via
|
97
|
+
# {Nokogiri::XML::SyntaxError#str1} method.
|
98
|
+
#
|
99
|
+
# doc = Nokogiri::HTML5.parse('<span/>Hi there!</span foo=bar />', max_errors: 10)
|
100
|
+
# doc.errors.each do |err|
|
101
|
+
# puts("#{err.line}:#{err.column}: #{err.str1}")
|
102
|
+
# end
|
103
|
+
# # => 1:1: generic-parser
|
104
|
+
# # 1:1: non-void-html-element-start-tag-with-trailing-solidus
|
105
|
+
# # 1:17: end-tag-with-trailing-solidus
|
106
|
+
# # 1:17: end-tag-with-attributes
|
107
|
+
#
|
108
|
+
# Note that the first error is +generic-parser+ because it's an error from the tree construction
|
109
|
+
# stage and doesn't have a standardized error code.
|
110
|
+
#
|
111
|
+
# For the purposes of semantic versioning, the error messages, error locations, and error codes
|
112
|
+
# are not part of Nokogiri's public API. That is, these are subject to change without Nokogiri's
|
113
|
+
# major version number changing. These may be stabilized in the future.
|
114
|
+
#
|
115
|
+
# === Maximum tree depth
|
116
|
+
#
|
117
|
+
# The maximum depth of the DOM tree parsed by the various parsing methods is configurable by the
|
118
|
+
# +:max_tree_depth+ option. If the depth of the tree would exceed this limit, then an
|
119
|
+
# {::ArgumentError} is thrown.
|
120
|
+
#
|
121
|
+
# This limit (which defaults to <tt>Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH = 400</tt>) can be
|
122
|
+
# removed by giving the option <tt>max_tree_depth: -1</tt>.
|
123
|
+
#
|
124
|
+
# html = '<!DOCTYPE html>' + '<div>' * 1000
|
125
|
+
# doc = Nokogiri.HTML5(html)
|
126
|
+
# # raises ArgumentError: Document tree depth limit exceeded
|
127
|
+
# doc = Nokogiri.HTML5(html, max_tree_depth: -1)
|
128
|
+
#
|
129
|
+
# === Attribute limit per element
|
130
|
+
#
|
131
|
+
# The maximum number of attributes per DOM element is configurable by the +:max_attributes+
|
132
|
+
# option. If a given element would exceed this limit, then an {::ArgumentError} is thrown.
|
133
|
+
#
|
134
|
+
# This limit (which defaults to <tt>Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES = 400</tt>) can be
|
135
|
+
# removed by giving the option <tt>max_attributes: -1</tt>.
|
136
|
+
#
|
137
|
+
# html = '<!DOCTYPE html><div ' + (1..1000).map { |x| "attr-#{x}" }.join(' ') + '>'
|
138
|
+
# # "<!DOCTYPE html><div attr-1 attr-2 attr-3 ... attr-1000>"
|
139
|
+
# doc = Nokogiri.HTML5(html)
|
140
|
+
# # raises ArgumentError: Attributes per element limit exceeded
|
141
|
+
# doc = Nokogiri.HTML5(html, max_attributes: -1)
|
142
|
+
#
|
143
|
+
# == HTML Serialization
|
144
|
+
#
|
145
|
+
# After parsing HTML, it may be serialized using any of the {Nokogiri::XML::Node} serialization
|
146
|
+
# methods. In particular, {XML::Node#serialize}, {XML::Node#to_html}, and {XML::Node#to_s} will
|
147
|
+
# serialize a given node and its children. (This is the equivalent of JavaScript's
|
148
|
+
# +Element.outerHTML+.) Similarly, {XML::Node#inner_html} will serialize the children of a given
|
149
|
+
# node. (This is the equivalent of JavaScript's +Element.innerHTML+.)
|
150
|
+
#
|
151
|
+
# doc = Nokogiri::HTML5("<!DOCTYPE html><span>Hello world!</span>")
|
152
|
+
# puts doc.serialize
|
153
|
+
# # => <!DOCTYPE html><html><head></head><body><span>Hello world!</span></body></html>
|
154
|
+
#
|
155
|
+
# Due to quirks in how HTML is parsed and serialized, it's possible for a DOM tree to be
|
156
|
+
# serialized and then re-parsed, resulting in a different DOM. Mostly, this happens with DOMs
|
157
|
+
# produced from invalid HTML. Unfortunately, even valid HTML may not survive serialization and
|
158
|
+
# re-parsing.
|
159
|
+
#
|
160
|
+
# In particular, a newline at the start of +pre+, +listing+, and +textarea+ elements is ignored by
|
161
|
+
# the parser.
|
162
|
+
#
|
163
|
+
# doc = Nokogiri::HTML5(<<-EOF)
|
164
|
+
# <!DOCTYPE html>
|
165
|
+
# <pre>
|
166
|
+
# Content</pre>
|
167
|
+
# EOF
|
168
|
+
# puts doc.at('/html/body/pre').serialize
|
169
|
+
# # => <pre>Content</pre>
|
170
|
+
#
|
171
|
+
# In this case, the original HTML is semantically equivalent to the serialized version. If the
|
172
|
+
# +pre+, +listing+, or +textarea+ content starts with two newlines, the first newline will be
|
173
|
+
# stripped on the first parse and the second newline will be stripped on the second, leading to
|
174
|
+
# semantically different DOMs. Passing the parameter <tt>preserve_newline: true</tt> will cause
|
175
|
+
# two or more newlines to be preserved. (A single leading newline will still be removed.)
|
176
|
+
#
|
177
|
+
# doc = Nokogiri::HTML5(<<-EOF)
|
178
|
+
# <!DOCTYPE html>
|
179
|
+
# <listing>
|
180
|
+
#
|
181
|
+
# Content</listing>
|
182
|
+
# EOF
|
183
|
+
# puts doc.at('/html/body/listing').serialize(preserve_newline: true)
|
184
|
+
# # => <listing>
|
185
|
+
# #
|
186
|
+
# # Content</listing>
|
187
|
+
#
|
188
|
+
# == Encodings
|
189
|
+
#
|
190
|
+
# Nokogiri always parses HTML5 using {https://en.wikipedia.org/wiki/UTF-8 UTF-8}; however, the
|
191
|
+
# encoding of the input can be explicitly selected via the optional +encoding+ parameter. This is
|
192
|
+
# most useful when the input comes not from a string but from an IO object.
|
193
|
+
#
|
194
|
+
# When serializing a document or node, the encoding of the output string can be specified via the
|
195
|
+
# +:encoding+ options. Characters that cannot be encoded in the selected encoding will be encoded
|
196
|
+
# as {https://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references HTML numeric
|
197
|
+
# entities}.
|
198
|
+
#
|
199
|
+
# frag = Nokogiri::HTML5.fragment('<span>아는 길도 물어가라</span>')
|
200
|
+
# html = frag.serialize(encoding: 'US-ASCII')
|
201
|
+
# puts html
|
202
|
+
# # => <span>아는 길도 물어가라</span>
|
203
|
+
# frag = Nokogiri::HTML5.fragment(html)
|
204
|
+
# puts frag.serialize
|
205
|
+
# # => <span>아는 길도 물어가라</span>
|
206
|
+
#
|
207
|
+
# (There's a {https://bugs.ruby-lang.org/issues/15033 bug} in all current versions of Ruby that
|
208
|
+
# can cause the entity encoding to fail. Of the mandated supported encodings for HTML, the only
|
209
|
+
# encoding I'm aware of that has this bug is <tt>'ISO-2022-JP'</tt>. We recommend avoiding this
|
210
|
+
# encoding.)
|
211
|
+
#
|
212
|
+
# == Notes
|
213
|
+
#
|
214
|
+
# * The {Nokogiri::HTML5.fragment} function takes a string and parses it
|
215
|
+
# as a HTML5 document. The +<html>+, +<head>+, and +<body>+ elements are
|
216
|
+
# removed from this document, and any children of these elements that remain
|
217
|
+
# are returned as a {Nokogiri::HTML5::DocumentFragment}.
|
218
|
+
#
|
219
|
+
# * The {Nokogiri::HTML5.parse} function takes a string and passes it to the
|
220
|
+
# <code>gumbo_parse_with_options</code> method, using the default options.
|
221
|
+
# The resulting Gumbo parse tree is then walked.
|
222
|
+
#
|
223
|
+
# * Instead of uppercase element names, lowercase element names are produced.
|
224
|
+
#
|
225
|
+
# * Instead of returning +unknown+ as the element name for unknown tags, the
|
226
|
+
# original tag name is returned verbatim.
|
227
|
+
#
|
228
|
+
# Since v1.12.0
|
229
|
+
module HTML5
|
230
|
+
class << self
|
231
|
+
# Parse an HTML 5 document. Convenience method for {Nokogiri::HTML5::Document.parse}
|
232
|
+
def parse(string, url = nil, encoding = nil, **options, &block)
|
233
|
+
Document.parse(string, url, encoding, **options, &block)
|
234
|
+
end
|
235
|
+
|
236
|
+
# Parse a fragment from +string+. Convenience method for
|
237
|
+
# {Nokogiri::HTML5::DocumentFragment.parse}.
|
238
|
+
def fragment(string, encoding = nil, **options)
|
239
|
+
DocumentFragment.parse(string, encoding, options)
|
240
|
+
end
|
241
|
+
|
242
|
+
# Fetch and parse a HTML document from the web, following redirects,
|
243
|
+
# handling https, and determining the character encoding using HTML5
|
244
|
+
# rules. +uri+ may be a +String+ or a +URI+. +options+ contains
|
245
|
+
# http headers and special options. Everything which is not a
|
246
|
+
# special option is considered a header. Special options include:
|
247
|
+
# * :follow_limit => number of redirects which are followed
|
248
|
+
# * :basic_auth => [username, password]
|
249
|
+
def get(uri, options = {})
|
250
|
+
# TODO: deprecate
|
251
|
+
warn("Nokogiri::HTML5.get is deprecated and will be removed in a future version of Nokogiri.",
|
252
|
+
uplevel: 1, category: :deprecated)
|
253
|
+
get_impl(uri, options)
|
254
|
+
end
|
255
|
+
|
256
|
+
# :nodoc:
|
257
|
+
def read_and_encode(string, encoding)
|
258
|
+
# Read the string with the given encoding.
|
259
|
+
if string.respond_to?(:read)
|
260
|
+
string = if encoding.nil?
|
261
|
+
string.read
|
262
|
+
else
|
263
|
+
string.read(encoding: encoding)
|
264
|
+
end
|
265
|
+
else
|
266
|
+
# Otherwise the string has the given encoding.
|
267
|
+
string = string.to_s
|
268
|
+
if encoding
|
269
|
+
string = string.dup
|
270
|
+
string.force_encoding(encoding)
|
271
|
+
end
|
272
|
+
end
|
273
|
+
|
274
|
+
# convert to UTF-8
|
275
|
+
if string.encoding != Encoding::UTF_8
|
276
|
+
string = reencode(string)
|
277
|
+
end
|
278
|
+
string
|
279
|
+
end
|
280
|
+
|
281
|
+
private
|
282
|
+
|
283
|
+
def get_impl(uri, options = {})
|
284
|
+
headers = options.clone
|
285
|
+
headers = { follow_limit: headers } if Numeric === headers # deprecated
|
286
|
+
limit = headers[:follow_limit] ? headers.delete(:follow_limit).to_i : 10
|
287
|
+
|
288
|
+
require "net/http"
|
289
|
+
uri = URI(uri) unless URI === uri
|
290
|
+
|
291
|
+
http = Net::HTTP.new(uri.host, uri.port)
|
292
|
+
|
293
|
+
# TLS / SSL support
|
294
|
+
http.use_ssl = true if uri.scheme == "https"
|
295
|
+
|
296
|
+
# Pass through Net::HTTP override values, which currently include:
|
297
|
+
# :ca_file, :ca_path, :cert, :cert_store, :ciphers,
|
298
|
+
# :close_on_empty_response, :continue_timeout, :key, :open_timeout,
|
299
|
+
# :read_timeout, :ssl_timeout, :ssl_version, :use_ssl,
|
300
|
+
# :verify_callback, :verify_depth, :verify_mode
|
301
|
+
options.each do |key, _value|
|
302
|
+
http.send("#{key}=", headers.delete(key)) if http.respond_to?("#{key}=")
|
303
|
+
end
|
304
|
+
|
305
|
+
request = Net::HTTP::Get.new(uri.request_uri)
|
306
|
+
|
307
|
+
# basic authentication
|
308
|
+
auth = headers.delete(:basic_auth)
|
309
|
+
auth ||= [uri.user, uri.password] if uri.user && uri.password
|
310
|
+
request.basic_auth(auth.first, auth.last) if auth
|
311
|
+
|
312
|
+
# remaining options are treated as headers
|
313
|
+
headers.each { |key, value| request[key.to_s] = value.to_s }
|
314
|
+
|
315
|
+
response = http.request(request)
|
316
|
+
|
317
|
+
case response
|
318
|
+
when Net::HTTPSuccess
|
319
|
+
doc = parse(reencode(response.body, response["content-type"]), options)
|
320
|
+
doc.instance_variable_set(:@response, response)
|
321
|
+
doc.class.send(:attr_reader, :response)
|
322
|
+
doc
|
323
|
+
when Net::HTTPRedirection
|
324
|
+
response.value if limit <= 1
|
325
|
+
location = URI.join(uri, response["location"])
|
326
|
+
get_impl(location, options.merge(follow_limit: limit - 1))
|
327
|
+
else
|
328
|
+
response.value
|
329
|
+
end
|
330
|
+
end
|
331
|
+
|
332
|
+
# Charset sniffing is a complex and controversial topic that understandably isn't done _by
|
333
|
+
# default_ by the Ruby Net::HTTP library. This being said, it is a very real problem for
|
334
|
+
# consumers of HTML as the default for HTML is iso-8859-1, most "good" producers use utf-8, and
|
335
|
+
# the Gumbo parser *only* supports utf-8.
|
336
|
+
#
|
337
|
+
# Accordingly, Nokogiri::HTML4::Document.parse provides limited encoding detection. Following
|
338
|
+
# this lead, Nokogiri::HTML5 attempts to do likewise, while attempting to more closely follow
|
339
|
+
# the HTML5 standard.
|
340
|
+
#
|
341
|
+
# http://bugs.ruby-lang.org/issues/2567
|
342
|
+
# http://www.w3.org/TR/html5/syntax.html#determining-the-character-encoding
|
343
|
+
#
|
344
|
+
def reencode(body, content_type = nil)
|
345
|
+
if body.encoding == Encoding::ASCII_8BIT
|
346
|
+
encoding = nil
|
347
|
+
|
348
|
+
# look for a Byte Order Mark (BOM)
|
349
|
+
initial_bytes = body[0..2].bytes
|
350
|
+
if initial_bytes[0..2] == [0xEF, 0xBB, 0xBF]
|
351
|
+
encoding = Encoding::UTF_8
|
352
|
+
elsif initial_bytes[0..1] == [0xFE, 0xFF]
|
353
|
+
encoding = Encoding::UTF_16BE
|
354
|
+
elsif initial_bytes[0..1] == [0xFF, 0xFE]
|
355
|
+
encoding = Encoding::UTF_16LE
|
356
|
+
end
|
357
|
+
|
358
|
+
# look for a charset in a content-encoding header
|
359
|
+
if content_type
|
360
|
+
encoding ||= content_type[/charset=["']?(.*?)($|["';\s])/i, 1]
|
361
|
+
end
|
362
|
+
|
363
|
+
# look for a charset in a meta tag in the first 1024 bytes
|
364
|
+
unless encoding
|
365
|
+
data = body[0..1023].gsub(/<!--.*?(-->|\Z)/m, "")
|
366
|
+
data.scan(/<meta.*?>/im).each do |meta|
|
367
|
+
encoding ||= meta[/charset=["']?([^>]*?)($|["'\s>])/im, 1]
|
368
|
+
end
|
369
|
+
end
|
370
|
+
|
371
|
+
# if all else fails, default to the official default encoding for HTML
|
372
|
+
encoding ||= Encoding::ISO_8859_1
|
373
|
+
|
374
|
+
# change the encoding to match the detected or inferred encoding
|
375
|
+
body = body.dup
|
376
|
+
begin
|
377
|
+
body.force_encoding(encoding)
|
378
|
+
rescue ArgumentError
|
379
|
+
body.force_encoding(Encoding::ISO_8859_1)
|
380
|
+
end
|
381
|
+
end
|
382
|
+
|
383
|
+
body.encode(Encoding::UTF_8)
|
384
|
+
end
|
385
|
+
end
|
386
|
+
end
|
387
|
+
end
|
388
|
+
|
389
|
+
require_relative "gumbo"
|
Binary file
|
data/lib/nokogiri/jruby/net/sourceforge/htmlunit/neko-htmlunit/2.63.0/neko-htmlunit-2.63.0.jar
ADDED
Binary file
|
@@ -0,0 +1,43 @@
|
|
1
|
+
# this is a generated file, to avoid over-writing it just delete this comment
|
2
|
+
begin
|
3
|
+
require 'jar_dependencies'
|
4
|
+
rescue LoadError
|
5
|
+
require 'xalan/serializer/2.7.3/serializer-2.7.3.jar'
|
6
|
+
require 'net/sourceforge/htmlunit/neko-htmlunit/2.63.0/neko-htmlunit-2.63.0.jar'
|
7
|
+
require 'nu/validator/jing/20200702VNU/jing-20200702VNU.jar'
|
8
|
+
require 'xerces/xercesImpl/2.12.2/xercesImpl-2.12.2.jar'
|
9
|
+
require 'net/sf/saxon/Saxon-HE/9.6.0-4/Saxon-HE-9.6.0-4.jar'
|
10
|
+
require 'xalan/xalan/2.7.3/xalan-2.7.3.jar'
|
11
|
+
require 'xml-apis/xml-apis/1.4.01/xml-apis-1.4.01.jar'
|
12
|
+
require 'org/nokogiri/nekodtd/0.1.11.noko2/nekodtd-0.1.11.noko2.jar'
|
13
|
+
require 'isorelax/isorelax/20030108/isorelax-20030108.jar'
|
14
|
+
end
|
15
|
+
|
16
|
+
if defined? Jars
|
17
|
+
require_jar 'xalan', 'serializer', '2.7.3'
|
18
|
+
require_jar 'net.sourceforge.htmlunit', 'neko-htmlunit', '2.63.0'
|
19
|
+
require_jar 'nu.validator', 'jing', '20200702VNU'
|
20
|
+
require_jar 'xerces', 'xercesImpl', '2.12.2'
|
21
|
+
require_jar 'net.sf.saxon', 'Saxon-HE', '9.6.0-4'
|
22
|
+
require_jar 'xalan', 'xalan', '2.7.3'
|
23
|
+
require_jar 'xml-apis', 'xml-apis', '1.4.01'
|
24
|
+
require_jar 'org.nokogiri', 'nekodtd', '0.1.11.noko2'
|
25
|
+
require_jar 'isorelax', 'isorelax', '20030108'
|
26
|
+
end
|
27
|
+
|
28
|
+
module Nokogiri
|
29
|
+
# generated by the :vendor_jars rake task
|
30
|
+
JAR_DEPENDENCIES = {
|
31
|
+
"isorelax:isorelax" => "20030108",
|
32
|
+
"net.sf.saxon:Saxon-HE" => "9.6.0-4",
|
33
|
+
"net.sourceforge.htmlunit:neko-htmlunit" => "2.63.0",
|
34
|
+
"nu.validator:jing" => "20200702VNU",
|
35
|
+
"org.nokogiri:nekodtd" => "0.1.11.noko2",
|
36
|
+
"xalan:serializer" => "2.7.3",
|
37
|
+
"xalan:xalan" => "2.7.3",
|
38
|
+
"xerces:xercesImpl" => "2.12.2",
|
39
|
+
"xml-apis:xml-apis" => "1.4.01",
|
40
|
+
}.freeze
|
41
|
+
XERCES_VERSION = JAR_DEPENDENCIES["xerces:xercesImpl"]
|
42
|
+
NEKO_VERSION = JAR_DEPENDENCIES["net.sourceforge.htmlunit:neko-htmlunit"]
|
43
|
+
end
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|
Binary file
|