RubyGems - nokogiri - Versions diffs - 1.5.10 → 1.12.5 - Mend

nokogiri 1.5.10 → 1.12.5

Potentially problematic release.

This version of nokogiri might be problematic. Click here for more details.

Files changed (328) hide show

checksums.yaml +7 -0
data/Gemfile +3 -0
data/LICENSE-DEPENDENCIES.md +1903 -0
data/LICENSE.md +9 -0
data/README.md +278 -0
data/bin/nokogiri +50 -10
data/dependencies.yml +74 -0
data/ext/nokogiri/depend +38 -358
data/ext/nokogiri/extconf.rb +944 -100
data/ext/nokogiri/gumbo.c +584 -0
data/ext/nokogiri/html4_document.c +166 -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 +120 -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 +232 -87
data/ext/nokogiri/nokogiri.h +188 -129
data/ext/nokogiri/test_global_handlers.c +40 -0
data/ext/nokogiri/xml_attr.c +49 -40
data/ext/nokogiri/xml_attribute_decl.c +18 -18
data/ext/nokogiri/xml_cdata.c +24 -23
data/ext/nokogiri/xml_comment.c +29 -21
data/ext/nokogiri/xml_document.c +305 -201
data/ext/nokogiri/xml_document_fragment.c +13 -15
data/ext/nokogiri/xml_dtd.c +54 -48
data/ext/nokogiri/xml_element_content.c +31 -26
data/ext/nokogiri/xml_element_decl.c +22 -22
data/ext/nokogiri/xml_encoding_handler.c +30 -19
data/ext/nokogiri/xml_entity_decl.c +32 -30
data/ext/nokogiri/xml_entity_reference.c +16 -18
data/ext/nokogiri/xml_namespace.c +74 -32
data/ext/nokogiri/xml_node.c +808 -503
data/ext/nokogiri/xml_node_set.c +239 -208
data/ext/nokogiri/xml_processing_instruction.c +17 -19
data/ext/nokogiri/xml_reader.c +198 -186
data/ext/nokogiri/xml_relax_ng.c +52 -28
data/ext/nokogiri/xml_sax_parser.c +123 -125
data/ext/nokogiri/xml_sax_parser_context.c +138 -79
data/ext/nokogiri/xml_sax_push_parser.c +88 -35
data/ext/nokogiri/xml_schema.c +112 -33
data/ext/nokogiri/xml_syntax_error.c +50 -23
data/ext/nokogiri/xml_text.c +14 -18
data/ext/nokogiri/xml_xpath_context.c +162 -98
data/ext/nokogiri/xslt_stylesheet.c +162 -168
data/gumbo-parser/CHANGES.md +63 -0
data/gumbo-parser/Makefile +101 -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/gumbo.h +943 -0
data/gumbo-parser/src/insertion_mode.h +33 -0
data/gumbo-parser/src/macros.h +91 -0
data/gumbo-parser/src/parser.c +4886 -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 +222 -0
data/gumbo-parser/src/tag_lookup.c +382 -0
data/gumbo-parser/src/tag_lookup.gperf +169 -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 +68 -0
data/gumbo-parser/src/util.h +30 -0
data/gumbo-parser/src/vector.c +111 -0
data/gumbo-parser/src/vector.h +45 -0
data/lib/nokogiri/css/node.rb +1 -50
data/lib/nokogiri/css/parser.rb +317 -286
data/lib/nokogiri/css/parser.y +57 -43
data/lib/nokogiri/css/parser_extras.rb +39 -36
data/lib/nokogiri/css/syntax_error.rb +2 -1
data/lib/nokogiri/css/tokenizer.rb +105 -103
data/lib/nokogiri/css/tokenizer.rex +5 -5
data/lib/nokogiri/css/xpath_visitor.rb +137 -48
data/lib/nokogiri/css.rb +15 -14
data/lib/nokogiri/decorators/slop.rb +13 -5
data/lib/nokogiri/extension.rb +31 -0
data/lib/nokogiri/gumbo.rb +14 -0
data/lib/nokogiri/html.rb +32 -27
data/lib/nokogiri/{html → html4}/builder.rb +3 -2
data/lib/nokogiri/{html → html4}/document.rb +118 -50
data/lib/nokogiri/{html → html4}/document_fragment.rb +20 -11
data/lib/nokogiri/{html → html4}/element_description.rb +2 -1
data/lib/nokogiri/{html → html4}/element_description_defaults.rb +2 -1
data/lib/nokogiri/{html → html4}/entity_lookup.rb +2 -1
data/lib/nokogiri/{html → html4}/sax/parser.rb +22 -14
data/lib/nokogiri/html4/sax/parser_context.rb +19 -0
data/lib/nokogiri/html4/sax/push_parser.rb +37 -0
data/lib/nokogiri/html4.rb +40 -0
data/lib/nokogiri/html5/document.rb +74 -0
data/lib/nokogiri/html5/document_fragment.rb +80 -0
data/lib/nokogiri/html5/node.rb +93 -0
data/lib/nokogiri/html5.rb +473 -0
data/lib/nokogiri/jruby/dependencies.rb +20 -0
data/lib/nokogiri/syntax_error.rb +1 -0
data/lib/nokogiri/version/constant.rb +5 -0
data/lib/nokogiri/version/info.rb +215 -0
data/lib/nokogiri/version.rb +3 -91
data/lib/nokogiri/xml/attr.rb +1 -0
data/lib/nokogiri/xml/attribute_decl.rb +1 -0
data/lib/nokogiri/xml/builder.rb +75 -33
data/lib/nokogiri/xml/cdata.rb +1 -0
data/lib/nokogiri/xml/character_data.rb +1 -0
data/lib/nokogiri/xml/document.rb +157 -54
data/lib/nokogiri/xml/document_fragment.rb +55 -8
data/lib/nokogiri/xml/dtd.rb +15 -4
data/lib/nokogiri/xml/element_content.rb +1 -0
data/lib/nokogiri/xml/element_decl.rb +1 -0
data/lib/nokogiri/xml/entity_decl.rb +1 -0
data/lib/nokogiri/xml/entity_reference.rb +19 -0
data/lib/nokogiri/xml/namespace.rb +1 -0
data/lib/nokogiri/xml/node/save_options.rb +2 -1
data/lib/nokogiri/xml/node.rb +712 -431
data/lib/nokogiri/xml/node_set.rb +140 -123
data/lib/nokogiri/xml/notation.rb +1 -0
data/lib/nokogiri/xml/parse_options.rb +31 -0
data/lib/nokogiri/xml/pp/character_data.rb +1 -0
data/lib/nokogiri/xml/pp/node.rb +1 -0
data/lib/nokogiri/xml/pp.rb +3 -2
data/lib/nokogiri/xml/processing_instruction.rb +1 -0
data/lib/nokogiri/xml/reader.rb +9 -12
data/lib/nokogiri/xml/relax_ng.rb +7 -2
data/lib/nokogiri/xml/sax/document.rb +25 -30
data/lib/nokogiri/xml/sax/parser.rb +8 -8
data/lib/nokogiri/xml/sax/parser_context.rb +1 -0
data/lib/nokogiri/xml/sax/push_parser.rb +1 -0
data/lib/nokogiri/xml/sax.rb +5 -4
data/lib/nokogiri/xml/schema.rb +13 -4
data/lib/nokogiri/xml/searchable.rb +239 -0
data/lib/nokogiri/xml/syntax_error.rb +25 -1
data/lib/nokogiri/xml/text.rb +1 -0
data/lib/nokogiri/xml/xpath/syntax_error.rb +2 -1
data/lib/nokogiri/xml/xpath.rb +4 -5
data/lib/nokogiri/xml/xpath_context.rb +1 -0
data/lib/nokogiri/xml.rb +37 -35
data/lib/nokogiri/xslt/stylesheet.rb +2 -1
data/lib/nokogiri/xslt.rb +17 -16
data/lib/nokogiri.rb +55 -58
data/lib/xsd/xmlparser/nokogiri.rb +1 -0
data/patches/libxml2/0001-Remove-script-macro-support.patch +40 -0
data/patches/libxml2/0002-Update-entities-to-remove-handling-of-ssi.patch +44 -0
data/patches/libxml2/0003-libxml2.la-is-in-top_builddir.patch +25 -0
data/patches/libxml2/0004-use-glibc-strlen.patch +53 -0
data/patches/libxml2/0005-avoid-isnan-isinf.patch +81 -0
data/patches/libxml2/0006-update-automake-files-for-arm64.patch +2511 -0
data/patches/libxml2/0007-Fix-XPath-recursion-limit.patch +31 -0
data/patches/libxslt/0001-update-automake-files-for-arm64.patch +2511 -0
data/patches/libxslt/0002-Fix-xml2-config-check-in-configure-script.patch +19 -0
data/ports/archives/libxml2-2.9.12.tar.gz +0 -0
data/ports/archives/libxslt-1.1.34.tar.gz +0 -0
metadata +307 -459
data/.autotest +0 -26
data/.gemtest +0 -0
data/CHANGELOG.ja.rdoc +0 -785
data/CHANGELOG.rdoc +0 -783
data/C_CODING_STYLE.rdoc +0 -33
data/Manifest.txt +0 -303
data/README.ja.rdoc +0 -106
data/README.rdoc +0 -175
data/ROADMAP.md +0 -90
data/Rakefile +0 -228
data/STANDARD_RESPONSES.md +0 -47
data/Y_U_NO_GEMSPEC.md +0 -155
data/build_all +0 -105
data/ext/nokogiri/html_document.c +0 -170
data/ext/nokogiri/html_document.h +0 -10
data/ext/nokogiri/html_element_description.c +0 -279
data/ext/nokogiri/html_element_description.h +0 -10
data/ext/nokogiri/html_entity_lookup.c +0 -32
data/ext/nokogiri/html_entity_lookup.h +0 -8
data/ext/nokogiri/html_sax_parser_context.c +0 -116
data/ext/nokogiri/html_sax_parser_context.h +0 -11
data/ext/nokogiri/html_sax_push_parser.c +0 -87
data/ext/nokogiri/html_sax_push_parser.h +0 -9
data/ext/nokogiri/xml_attr.h +0 -9
data/ext/nokogiri/xml_attribute_decl.h +0 -9
data/ext/nokogiri/xml_cdata.h +0 -9
data/ext/nokogiri/xml_comment.h +0 -9
data/ext/nokogiri/xml_document.h +0 -23
data/ext/nokogiri/xml_document_fragment.h +0 -10
data/ext/nokogiri/xml_dtd.h +0 -10
data/ext/nokogiri/xml_element_content.h +0 -10
data/ext/nokogiri/xml_element_decl.h +0 -9
data/ext/nokogiri/xml_encoding_handler.h +0 -8
data/ext/nokogiri/xml_entity_decl.h +0 -10
data/ext/nokogiri/xml_entity_reference.h +0 -9
data/ext/nokogiri/xml_io.c +0 -56
data/ext/nokogiri/xml_io.h +0 -11
data/ext/nokogiri/xml_libxml2_hacks.c +0 -112
data/ext/nokogiri/xml_libxml2_hacks.h +0 -12
data/ext/nokogiri/xml_namespace.h +0 -13
data/ext/nokogiri/xml_node.h +0 -13
data/ext/nokogiri/xml_node_set.h +0 -14
data/ext/nokogiri/xml_processing_instruction.h +0 -9
data/ext/nokogiri/xml_reader.h +0 -10
data/ext/nokogiri/xml_relax_ng.h +0 -9
data/ext/nokogiri/xml_sax_parser.h +0 -39
data/ext/nokogiri/xml_sax_parser_context.h +0 -10
data/ext/nokogiri/xml_sax_push_parser.h +0 -9
data/ext/nokogiri/xml_schema.h +0 -9
data/ext/nokogiri/xml_syntax_error.h +0 -13
data/ext/nokogiri/xml_text.h +0 -9
data/ext/nokogiri/xml_xpath_context.h +0 -10
data/ext/nokogiri/xslt_stylesheet.h +0 -14
data/lib/nokogiri/html/sax/parser_context.rb +0 -16
data/lib/nokogiri/html/sax/push_parser.rb +0 -16
data/tasks/cross_compile.rb +0 -150
data/tasks/nokogiri.org.rb +0 -24
data/tasks/test.rb +0 -95
data/test/css/test_nthiness.rb +0 -159
data/test/css/test_parser.rb +0 -341
data/test/css/test_tokenizer.rb +0 -198
data/test/css/test_xpath_visitor.rb +0 -91
data/test/decorators/test_slop.rb +0 -16
data/test/files/2ch.html +0 -108
data/test/files/address_book.rlx +0 -12
data/test/files/address_book.xml +0 -10
data/test/files/bar/bar.xsd +0 -4
data/test/files/dont_hurt_em_why.xml +0 -422
data/test/files/encoding.html +0 -82
data/test/files/encoding.xhtml +0 -84
data/test/files/exslt.xml +0 -8
data/test/files/exslt.xslt +0 -35
data/test/files/foo/foo.xsd +0 -4
data/test/files/metacharset.html +0 -10
data/test/files/noencoding.html +0 -47
data/test/files/po.xml +0 -32
data/test/files/po.xsd +0 -66
data/test/files/shift_jis.html +0 -10
data/test/files/shift_jis.xml +0 -5
data/test/files/snuggles.xml +0 -3
data/test/files/staff.dtd +0 -10
data/test/files/staff.xml +0 -59
data/test/files/staff.xslt +0 -32
data/test/files/test_document_url/bar.xml +0 -2
data/test/files/test_document_url/document.dtd +0 -4
data/test/files/test_document_url/document.xml +0 -6
data/test/files/tlm.html +0 -850
data/test/files/to_be_xincluded.xml +0 -2
data/test/files/valid_bar.xml +0 -2
data/test/files/xinclude.xml +0 -4
data/test/helper.rb +0 -154
data/test/html/sax/test_parser.rb +0 -141
data/test/html/sax/test_parser_context.rb +0 -46
data/test/html/test_builder.rb +0 -164
data/test/html/test_document.rb +0 -552
data/test/html/test_document_encoding.rb +0 -138
data/test/html/test_document_fragment.rb +0 -261
data/test/html/test_element_description.rb +0 -105
data/test/html/test_named_characters.rb +0 -14
data/test/html/test_node.rb +0 -196
data/test/html/test_node_encoding.rb +0 -27
data/test/namespaces/test_additional_namespaces_in_builder_doc.rb +0 -14
data/test/namespaces/test_namespaces_in_builder_doc.rb +0 -75
data/test/namespaces/test_namespaces_in_created_doc.rb +0 -75
data/test/namespaces/test_namespaces_in_parsed_doc.rb +0 -66
data/test/test_convert_xpath.rb +0 -135
data/test/test_css_cache.rb +0 -45
data/test/test_encoding_handler.rb +0 -46
data/test/test_memory_leak.rb +0 -156
data/test/test_nokogiri.rb +0 -132
data/test/test_reader.rb +0 -555
data/test/test_soap4r_sax.rb +0 -52
data/test/test_xslt_transforms.rb +0 -254
data/test/xml/node/test_save_options.rb +0 -28
data/test/xml/node/test_subclass.rb +0 -44
data/test/xml/sax/test_parser.rb +0 -366
data/test/xml/sax/test_parser_context.rb +0 -106
data/test/xml/sax/test_push_parser.rb +0 -157
data/test/xml/test_attr.rb +0 -64
data/test/xml/test_attribute_decl.rb +0 -86
data/test/xml/test_builder.rb +0 -306
data/test/xml/test_c14n.rb +0 -151
data/test/xml/test_cdata.rb +0 -48
data/test/xml/test_comment.rb +0 -29
data/test/xml/test_document.rb +0 -828
data/test/xml/test_document_encoding.rb +0 -28
data/test/xml/test_document_fragment.rb +0 -223
data/test/xml/test_dtd.rb +0 -103
data/test/xml/test_dtd_encoding.rb +0 -33
data/test/xml/test_element_content.rb +0 -56
data/test/xml/test_element_decl.rb +0 -73
data/test/xml/test_entity_decl.rb +0 -122
data/test/xml/test_entity_reference.rb +0 -245
data/test/xml/test_namespace.rb +0 -95
data/test/xml/test_node.rb +0 -1137
data/test/xml/test_node_attributes.rb +0 -96
data/test/xml/test_node_encoding.rb +0 -107
data/test/xml/test_node_inheritance.rb +0 -32
data/test/xml/test_node_reparenting.rb +0 -374
data/test/xml/test_node_set.rb +0 -755
data/test/xml/test_parse_options.rb +0 -64
data/test/xml/test_processing_instruction.rb +0 -30
data/test/xml/test_reader_encoding.rb +0 -142
data/test/xml/test_relax_ng.rb +0 -60
data/test/xml/test_schema.rb +0 -103
data/test/xml/test_syntax_error.rb +0 -12
data/test/xml/test_text.rb +0 -45
data/test/xml/test_unparented_node.rb +0 -422
data/test/xml/test_xinclude.rb +0 -83
data/test/xml/test_xpath.rb +0 -295
data/test/xslt/test_custom_functions.rb +0 -133
data/test/xslt/test_exception_handling.rb +0 -37
data/test_all +0 -81

data/lib/nokogiri/{html → html4}/document.rb RENAMED Viewed

@@ -1,28 +1,67 @@
+# frozen_string_literal: true
+require 'pathname'
 module Nokogiri
-  module HTML
+  module HTML4
     class Document < Nokogiri::XML::Document
       ###
       # Get the meta tag encoding for this document.  If there is no meta tag,
       # then nil is returned.
       def meta_encoding
-        meta = meta_content_type and
-          match = /charset\s*=\s*([\w-]+)/i.match(meta['content']) and
-          match[1]
+        case
+        when meta = at('//meta[@charset]')
+          meta[:charset]
+        when meta = meta_content_type
+          meta['content'][/charset\s*=\s*([\w-]+)/i, 1]
+        end
       end
       ###
-      # Set the meta tag encoding for this document.  If there is no meta
-      # content tag, the encoding is not set.
+      # Set the meta tag encoding for this document.
+      #
+      # If an meta encoding tag is already present, its content is
+      # replaced with the given text.
+      #
+      # Otherwise, this method tries to create one at an appropriate
+      # place supplying head and/or html elements as necessary, which
+      # is inside a head element if any, and before any text node or
+      # content element (typically <body>) if any.
+      #
+      # The result when trying to set an encoding that is different
+      # from the document encoding is undefined.
+      #
+      # Beware in CRuby, that libxml2 automatically inserts a meta tag
+      # into a head element.
       def meta_encoding= encoding
-        meta = meta_content_type and
-          meta['content'] = "text/html; charset=%s" % encoding
+        case
+        when meta = meta_content_type
+          meta['content'] = 'text/html; charset=%s' % encoding
+          encoding
+        when meta = at('//meta[@charset]')
+          meta['charset'] = encoding
+        else
+          meta = XML::Node.new('meta', self)
+          if dtd = internal_subset and dtd.html5_dtd?
+            meta['charset'] = encoding
+          else
+            meta['http-equiv'] = 'Content-Type'
+            meta['content'] = 'text/html; charset=%s' % encoding
+          end
+          case
+          when head = at('//head')
+            head.prepend_child(meta)
+          else
+            set_metadata_element(meta)
+          end
+          encoding
+        end
       end
       def meta_content_type
-        css('meta[@http-equiv]').find { |node|
-          node['http-equiv'] =~ /\AContent-Type\z/i and
-            !node['content'].nil? and
-            !node['content'].empty?
+        xpath('//meta[@http-equiv and boolean(@content)]').find { |node|
+          node['http-equiv'] =~ /\AContent-Type\z/i
         }
       end
       private :meta_content_type
@@ -31,21 +70,65 @@ module Nokogiri
       # Get the title string of this document.  Return nil if there is
       # no title tag.
       def title
-        title = at('title') and title.inner_text
+        title = at('//title') and title.inner_text
       end
       ###
-      # Set the title string of this document.  If there is no head
-      # element, the title is not set.
+      # Set the title string of this document.
+      #
+      # If a title element is already present, its content is replaced
+      # with the given text.
+      #
+      # Otherwise, this method tries to create one at an appropriate
+      # place supplying head and/or html elements as necessary, which
+      # is inside a head element if any, right after a meta
+      # encoding/charset tag if any, and before any text node or
+      # content element (typically <body>) if any.
       def title=(text)
-        unless title = at('title')
-          head = at('head') or return nil
-          title = Nokogiri::XML::Node.new('title', self)
+        tnode = XML::Text.new(text, self)
+        if title = at('//title')
+          title.children = tnode
+          return text
+        end
+        title = XML::Node.new('title', self) << tnode
+        case
+        when head = at('//head')
           head << title
+        when meta = at('//meta[@charset]') || meta_content_type
+          # better put after charset declaration
+          meta.add_next_sibling(title)
+        else
+          set_metadata_element(title)
         end
-        title.children = XML::Text.new(text, self)
+        text
       end
+      def set_metadata_element(element)
+        case
+        when head = at('//head')
+          head << element
+        when html = at('//html')
+          head = html.prepend_child(XML::Node.new('head', self))
+          head.prepend_child(element)
+        when first = children.find { |node|
+            case node
+            when XML::Element, XML::Text
+              true
+            end
+          }
+          # We reach here only if the underlying document model
+          # allows <html>/<head> elements to be omitted and does not
+          # automatically supply them.
+          first.add_previous_sibling(element)
+        else
+          html = add_child(XML::Node.new('html', self))
+          head = html.add_child(XML::Node.new('head', self))
+          head.prepend_child(element)
+        end
+      end
+      private :set_metadata_element
       ####
       # Serialize Node using +options+.  Save options can also be set using a
       # block. See SaveOptions.
@@ -81,11 +164,12 @@ module Nokogiri
         # Nokogiri::XML::ParseOptions::RECOVER.  See the constants in
         # Nokogiri::XML::ParseOptions.
         def parse string_or_io, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML
+          options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
-          options = Nokogiri::XML::ParseOptions.new(options) if Fixnum === options
-          # Give the options to the user
           yield options if block_given?
+          url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil
           if string_or_io.respond_to?(:encoding)
             unless string_or_io.encoding.name == "ASCII-8BIT"
               encoding ||= string_or_io.encoding.name
@@ -93,8 +177,13 @@ module Nokogiri
           end
           if string_or_io.respond_to?(:read)
-            url ||= string_or_io.respond_to?(:path) ? string_or_io.path : nil
-            if !encoding
+            if string_or_io.is_a?(Pathname)
+              # resolve the Pathname to the file and open it as an IO object, see #2110
+              string_or_io = string_or_io.expand_path.open
+              url ||= string_or_io.path
+            end
+            unless encoding
               # Libxml2's parser has poor support for encoding
               # detection.  First, it does not recognize the HTML5
               # style meta charset declaration.  Secondly, even if it
@@ -117,7 +206,9 @@ module Nokogiri
           end
           # read_memory pukes on empty docs
-          return new if string_or_io.nil? or string_or_io.empty?
+          if string_or_io.nil? or string_or_io.empty?
+            return encoding ? new.tap { |i| i.encoding = encoding } : new
+          end
           encoding ||= EncodingReader.detect_encoding(string_or_io)
@@ -170,9 +261,6 @@ module Nokogiri
         end
         def self.detect_encoding(chunk)
-          if Nokogiri.jruby? && EncodingReader.is_jruby_without_fix?
-            return EncodingReader.detect_encoding_for_jruby_without_fix(chunk)
-          end
           m = chunk.match(/\A(<\?xml[ \t\r\n]+[^>]*>)/) and
             return Nokogiri.XML(m[1]).encoding
@@ -180,37 +268,17 @@ module Nokogiri
             m = chunk.match(/(<meta\s)(.*)(charset\s*=\s*([\w-]+))(.*)/i) and
               return m[4]
             catch(:encoding_found) {
-              Nokogiri::HTML::SAX::Parser.new(JumpSAXHandler.new(:encoding_found)).parse(chunk)
+              Nokogiri::HTML4::SAX::Parser.new(JumpSAXHandler.new(:encoding_found)).parse(chunk)
               nil
             }
           else
             handler = SAXHandler.new
-            parser = Nokogiri::HTML::SAX::PushParser.new(handler)
+            parser = Nokogiri::HTML4::SAX::PushParser.new(handler)
             parser << chunk rescue Nokogiri::SyntaxError
             handler.encoding
           end
         end
-        def self.is_jruby_without_fix?
-          JRUBY_VERSION.split('.').join.to_i < 165
-        end
-        def self.detect_encoding_for_jruby_without_fix(chunk)
-          m = chunk.match(/\A(<\?xml[ \t\r\n]+[^>]*>)/) and
-            return Nokogiri.XML(m[1]).encoding
-          m = chunk.match(/(<meta\s)(.*)(charset\s*=\s*([\w-]+))(.*)/i) and
-            return m[4]
-          catch(:encoding_found) {
-            Nokogiri::HTML::SAX::Parser.new(JumpSAXHandler.new(:encoding_found.to_s)).parse(chunk)
-            nil
-          }
-        rescue Nokogiri::SyntaxError, RuntimeError
-          # Ignore parser errors that nokogiri may raise
-          nil
-        end
         def initialize(io)
           @io = io
           @firstchunk = nil
@@ -218,7 +286,7 @@ module Nokogiri
         end
         # This method is used by the C extension so that
-        # Nokogiri::HTML::Document#read_io() does not leak memory when
+        # Nokogiri::HTML4::Document#read_io() does not leak memory when
         # EncodingFound is raised.
         attr_reader :encoding_found

data/lib/nokogiri/{html → html4}/document_fragment.rb RENAMED Viewed

@@ -1,20 +1,29 @@
+# frozen_string_literal: true
 module Nokogiri
-  module HTML
+  module HTML4
     class DocumentFragment < Nokogiri::XML::DocumentFragment
-      attr_accessor :errors
       ####
       # Create a Nokogiri::XML::DocumentFragment from +tags+, using +encoding+
-      def self.parse tags, encoding = nil
-        doc = HTML::Document.new
+      def self.parse(tags, encoding = nil)
+        doc = HTML4::Document.new
+        encoding ||= if tags.respond_to?(:encoding)
+          encoding = tags.encoding
+          if encoding == ::Encoding::ASCII_8BIT
+            'UTF-8'
+          else
+            encoding.name
+          end
+        else
+          'UTF-8'
+        end
-        encoding ||= tags.respond_to?(:encoding) ? tags.encoding.name : 'UTF-8'
         doc.encoding = encoding
         new(doc, tags)
       end
-      def initialize document, tags = nil, ctx = nil
+      def initialize(document, tags = nil, ctx = nil)
         return self unless tags
         if ctx
@@ -24,13 +33,13 @@ module Nokogiri
           self.errors = document.errors - preexisting_errors
         else
           # This is a horrible hack, but I don't care
-          if tags.strip =~ /^<body/i
-            path = "/html/body"
+          path = if /^\s*?<body/i.match?(tags)
+            "/html/body"
           else
-            path = "/html/body/node()"
+            "/html/body/node()"
           end
-          temp_doc = HTML::Document.parse "<html><body>#{tags}", nil, document.encoding
+          temp_doc = HTML4::Document.parse("<html><body>#{tags}", nil, document.encoding)
           temp_doc.xpath(path).each { |child| child.parent = self }
           self.errors = temp_doc.errors
         end

data/lib/nokogiri/{html → html4}/element_description.rb RENAMED Viewed

@@ -1,5 +1,6 @@
+# frozen_string_literal: true
 module Nokogiri
-  module HTML
+  module HTML4
     class ElementDescription
       ###
       # Is this element a block element?

data/lib/nokogiri/{html → html4}/element_description_defaults.rb RENAMED Viewed

@@ -1,5 +1,6 @@
+# frozen_string_literal: true
 module Nokogiri
-  module HTML
+  module HTML4
     class ElementDescription
       # Methods are defined protected by method_defined? because at

data/lib/nokogiri/{html → html4}/entity_lookup.rb RENAMED Viewed

@@ -1,5 +1,6 @@
+# frozen_string_literal: true
 module Nokogiri
-  module HTML
+  module HTML4
     class EntityDescription < Struct.new(:value, :name, :description); end
     class EntityLookup

data/lib/nokogiri/{html → html4}/sax/parser.rb RENAMED Viewed

@@ -1,17 +1,15 @@
+# frozen_string_literal: true
 module Nokogiri
-  module HTML
+  module HTML4
     ###
-    # Nokogiri lets you write a SAX parser to process HTML but get HTML
-    # correction features.
+    # Nokogiri lets you write a SAX parser to process HTML but get HTML correction features.
     #
-    # See Nokogiri::HTML::SAX::Parser for a basic example of using a
-    # SAX parser with HTML.
+    # See Nokogiri::HTML4::SAX::Parser for a basic example of using a SAX parser with HTML.
     #
     # For more information on SAX parsers, see Nokogiri::XML::SAX
     module SAX
       ###
-      # This class lets you perform SAX style parsing on HTML with HTML
-      # error correction.
+      # This class lets you perform SAX style parsing on HTML with HTML error correction.
       #
       # Here is a basic usage example:
       #
@@ -21,30 +19,40 @@ module Nokogiri
       #     end
       #   end
       #
-      #   parser = Nokogiri::HTML::SAX::Parser.new(MyDoc.new)
-      #   parser.parse(File.read(ARGV[0], 'rb'))
+      #   parser = Nokogiri::HTML4::SAX::Parser.new(MyDoc.new)
+      #   parser.parse(File.read(ARGV[0], mode: 'rb'))
       #
       # For more information on SAX parsers, see Nokogiri::XML::SAX
       class Parser < Nokogiri::XML::SAX::Parser
         ###
         # Parse html stored in +data+ using +encoding+
-        def parse_memory data, encoding = 'UTF-8'
+        def parse_memory(data, encoding = "UTF-8")
           raise ArgumentError unless data
           return unless data.length > 0
           ctx = ParserContext.memory(data, encoding)
           yield ctx if block_given?
-          ctx.parse_with self
+          ctx.parse_with(self)
+        end
+        ###
+        # Parse given +io+
+        def parse_io(io, encoding = "UTF-8")
+          check_encoding(encoding)
+          @encoding = encoding
+          ctx = ParserContext.io(io, ENCODINGS[encoding])
+          yield ctx if block_given?
+          ctx.parse_with(self)
         end
         ###
         # Parse a file with +filename+
-        def parse_file filename, encoding = 'UTF-8'
+        def parse_file(filename, encoding = "UTF-8")
           raise ArgumentError unless filename
-          raise Errno::ENOENT unless File.exists?(filename)
+          raise Errno::ENOENT unless File.exist?(filename)
           raise Errno::EISDIR if File.directory?(filename)
           ctx = ParserContext.file(filename, encoding)
           yield ctx if block_given?
-          ctx.parse_with self
+          ctx.parse_with(self)
         end
       end
     end

data/lib/nokogiri/html4/sax/parser_context.rb ADDED Viewed

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+module Nokogiri
+  module HTML4
+    module SAX
+      ###
+      # Context for HTML SAX parsers. This class is usually not instantiated by the user. Instead,
+      # you should be looking at Nokogiri::HTML4::SAX::Parser
+      class ParserContext < Nokogiri::XML::SAX::ParserContext
+        def self.new(thing, encoding = "UTF-8")
+          if [:read, :close].all? { |x| thing.respond_to?(x) }
+            super
+          else
+            memory(thing, encoding)
+          end
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/html4/sax/push_parser.rb ADDED Viewed

@@ -0,0 +1,37 @@
+# frozen_string_literal: true
+module Nokogiri
+  module HTML4
+    module SAX
+      class PushParser
+        # The Nokogiri::HTML4::SAX::Document on which the PushParser will be
+        # operating
+        attr_accessor :document
+        def initialize(doc = HTML4::SAX::Document.new, file_name = nil, encoding = 'UTF-8')
+          @document = doc
+          @encoding = encoding
+          @sax_parser = HTML4::SAX::Parser.new(doc, @encoding)
+          ## Create our push parser context
+          initialize_native(@sax_parser, file_name, encoding)
+        end
+        ###
+        # Write a +chunk+ of HTML to the PushParser.  Any callback methods
+        # that can be called will be called immediately.
+        def write chunk, last_chunk = false
+          native_write(chunk, last_chunk)
+        end
+        alias :<< :write
+        ###
+        # Finish the parsing.  This method is only necessary for
+        # Nokogiri::HTML4::SAX::Document#end_document to be called.
+        def finish
+          write '', true
+        end
+      end
+    end
+  end
+end

data/lib/nokogiri/html4.rb ADDED Viewed

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+module Nokogiri
+  class << self
+    ###
+    # Parse HTML. Convenience method for Nokogiri::HTML4::Document.parse
+    def HTML4(input, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML, &block)
+      Nokogiri::HTML4::Document.parse(input, url, encoding, options, &block)
+    end
+  end
+  # @since v1.12.0
+  # @note Before v1.12.0, {Nokogiri::HTML4} did not exist, and {Nokogiri::HTML} was the module/namespace for parsing HTML.
+  module HTML4
+    class << self
+      ###
+      # Parse HTML. Convenience method for Nokogiri::HTML4::Document.parse
+      def parse(input, url = nil, encoding = nil, options = XML::ParseOptions::DEFAULT_HTML, &block)
+        Document.parse(input, url, encoding, options, &block)
+      end
+      ####
+      # Parse a fragment from +string+ in to a NodeSet.
+      def fragment(string, encoding = nil)
+        HTML4::DocumentFragment.parse(string, encoding)
+      end
+    end
+    # Instance of Nokogiri::HTML4::EntityLookup
+    NamedCharacters = EntityLookup.new
+  end
+end
+require_relative "html4/entity_lookup"
+require_relative "html4/document"
+require_relative "html4/document_fragment"
+require_relative "html4/sax/parser_context"
+require_relative "html4/sax/parser"
+require_relative "html4/sax/push_parser"
+require_relative "html4/element_description"
+require_relative "html4/element_description_defaults"

data/lib/nokogiri/html5/document.rb ADDED Viewed

@@ -0,0 +1,74 @@
+# frozen_string_literal: true
+#
+#  Copyright 2013-2021 Sam Ruby, Stephen Checkoway
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+require_relative "../html4/document"
+module Nokogiri
+  module HTML5
+    # @since v1.12.0
+    # @note HTML5 functionality is not available when running JRuby.
+    class Document < Nokogiri::HTML4::Document
+      def self.parse(string_or_io, url = nil, encoding = nil, **options, &block)
+        yield options if block_given?
+	string_or_io = '' unless string_or_io
+        if string_or_io.respond_to?(:encoding) && string_or_io.encoding.name != 'ASCII-8BIT'
+          encoding ||= string_or_io.encoding.name
+        end
+        if string_or_io.respond_to?(:read) && string_or_io.respond_to?(:path)
+          url ||= string_or_io.path
+        end
+        unless string_or_io.respond_to?(:read) || string_or_io.respond_to?(:to_str)
+          raise ArgumentError.new("not a string or IO object")
+        end
+        do_parse(string_or_io, url, encoding, options)
+      end
+      def self.read_io(io, url = nil, encoding = nil, **options)
+        raise ArgumentError.new("io object doesn't respond to :read") unless io.respond_to?(:read)
+        do_parse(io, url, encoding, options)
+      end
+      def self.read_memory(string, url = nil, encoding = nil, **options)
+        raise ArgumentError.new("string object doesn't respond to :to_str") unless string.respond_to?(:to_str)
+        do_parse(string, url, encoding, options)
+      end
+      def fragment(tags = nil)
+        DocumentFragment.new(self, tags, self.root)
+      end
+      def to_xml(options = {}, &block)
+        # Bypass XML::Document#to_xml which doesn't add
+        # XML::Node::SaveOptions::AS_XML like XML::Node#to_xml does.
+        XML::Node.instance_method(:to_xml).bind(self).call(options, &block)
+      end
+      private
+      def self.do_parse(string_or_io, url, encoding, options)
+        string = HTML5.read_and_encode(string_or_io, encoding)
+        max_attributes = options[:max_attributes] || Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES
+        max_errors = options[:max_errors] || options[:max_parse_errors] || Nokogiri::Gumbo::DEFAULT_MAX_ERRORS
+        max_depth = options[:max_tree_depth] || Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH
+        doc = Nokogiri::Gumbo.parse(string, url, max_attributes, max_errors, max_depth)
+        doc.encoding = 'UTF-8'
+        doc
+      end
+    end
+  end
+end

data/lib/nokogiri/html5/document_fragment.rb ADDED Viewed

@@ -0,0 +1,80 @@
+# frozen_string_literal: true
+#
+#  Copyright 2013-2021 Sam Ruby, Stephen Checkoway
+#
+#  Licensed under the Apache License, Version 2.0 (the "License");
+#  you may not use this file except in compliance with the License.
+#  You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+#  Unless required by applicable law or agreed to in writing, software
+#  distributed under the License is distributed on an "AS IS" BASIS,
+#  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+#  See the License for the specific language governing permissions and
+#  limitations under the License.
+#
+require_relative "../html4/document_fragment"
+module Nokogiri
+  module HTML5
+    # @since v1.12.0
+    # @note HTML5 functionality is not available when running JRuby.
+    class DocumentFragment < Nokogiri::HTML4::DocumentFragment
+      attr_accessor :document
+      attr_accessor :errors
+      # Create a document fragment.
+      def initialize(doc, tags = nil, ctx = nil, options = {})
+        self.document = doc
+        self.errors = []
+        return self unless tags
+        max_attributes = options[:max_attributes] || Nokogiri::Gumbo::DEFAULT_MAX_ATTRIBUTES
+        max_errors = options[:max_errors] || Nokogiri::Gumbo::DEFAULT_MAX_ERRORS
+        max_depth = options[:max_tree_depth] || Nokogiri::Gumbo::DEFAULT_MAX_TREE_DEPTH
+        tags = Nokogiri::HTML5.read_and_encode(tags, nil)
+        Nokogiri::Gumbo.fragment(self, tags, ctx, max_attributes, max_errors, max_depth)
+      end
+      def serialize(options = {}, &block)
+        # Bypass XML::Document.serialize which doesn't support options even
+        # though XML::Node.serialize does!
+        XML::Node.instance_method(:serialize).bind(self).call(options, &block)
+      end
+      # Parse a document fragment from +tags+, returning a Nodeset.
+      def self.parse(tags, encoding = nil, options = {})
+        doc = HTML5::Document.new
+        tags = HTML5.read_and_encode(tags, encoding)
+        doc.encoding = "UTF-8"
+        new(doc, tags, nil, options)
+      end
+      def extract_params(params) # :nodoc:
+        handler = params.find do |param|
+          ![Hash, String, Symbol].include?(param.class)
+        end
+        params -= [handler] if handler
+        hashes = []
+        while Hash === params.last || params.last.nil?
+          hashes << params.pop
+          break if params.empty?
+        end
+        ns, binds = hashes.reverse
+        ns ||=
+          begin
+            ns = {}
+            children.each { |child| ns.merge!(child.namespaces) }
+            ns
+          end
+        [params, handler, ns, binds]
+      end
+    end
+  end
+end
+# vim: set shiftwidth=2 softtabstop=2 tabstop=8 expandtab: