ruby-changes:65784
From: usa <ko1@a...>
Date: Mon, 5 Apr 2021 20:45:49 +0900 (JST)
Subject: [ruby-changes:65784] 4870620450 (ruby_2_5): REXML 3.1.7.4
https://git.ruby-lang.org/ruby.git/commit/?id=4870620450 From 48706204503ee83a9925f2a482bcf37ddcc7fa48 Mon Sep 17 00:00:00 2001 From: usa <usa@b2dd03c8-39d4-4d8f-98ff-823fe69b080e> Date: Mon, 5 Apr 2021 11:45:31 +0000 Subject: REXML 3.1.7.4 git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/branches/ruby_2_5@67937 b2dd03c8-39d4-4d8f-98ff-823fe69b080e --- lib/rexml/doctype.rb | 50 +++- lib/rexml/parsers/baseparser.rb | 323 ++++++++++++++++----- lib/rexml/rexml.rb | 2 +- test/rexml/parse/test_document_type_declaration.rb | 193 +++++++++++- test/rexml/parse/test_notation_declaration.rb | 181 ++++++++++++ test/rexml/parser/test_tree.rb | 2 +- test/rexml/parser/test_ultra_light.rb | 1 - test/rexml/test_core.rb | 17 +- test/rexml/test_doctype.rb | 151 +++++++--- version.h | 8 +- 10 files changed, 782 insertions(+), 146 deletions(-) diff --git a/lib/rexml/doctype.rb b/lib/rexml/doctype.rb index 1eb1f5b..cb9bf57 100644 --- a/lib/rexml/doctype.rb +++ b/lib/rexml/doctype.rb @@ -7,6 +7,39 @@ require 'rexml/attlistdecl' https://github.com/ruby/ruby/blob/trunk/lib/rexml/doctype.rb#L7 require 'rexml/xmltokens' module REXML + class ReferenceWriter + def initialize(id_type, + public_id_literal, + system_literal) + @id_type = id_type + @public_id_literal = public_id_literal + @system_literal = system_literal + @default_quote = "\"" + end + + def write(output) + output << " #{@id_type}" + if @public_id_literal + if @public_id_literal.include?("'") + quote = "\"" + else + quote = @default_quote + end + output << " #{quote}#{@public_id_literal}#{quote}" + end + if @system_literal + if @system_literal.include?("'") + quote = "\"" + elsif @system_literal.include?("\"") + quote = "'" + else + quote = @default_quote + end + output << " #{quote}#{@system_literal}#{quote}" + end + end + end + # Represents an XML DOCTYPE declaration; that is, the contents of <!DOCTYPE # ... >. DOCTYPES can be used to declare the DTD of a document, as well as # being used to declare entities used in the document. @@ -50,6 +83,8 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/doctype.rb#L83 super( parent ) @name = first.name @external_id = first.external_id + @long_name = first.instance_variable_get(:@long_name) + @uri = first.instance_variable_get(:@uri) elsif first.kind_of? Array super( parent ) @name = first[0] @@ -112,9 +147,12 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/doctype.rb#L147 output << START output << ' ' output << @name - output << " #@external_id" if @external_id - output << " #{@long_name.inspect}" if @long_name - output << " #{@uri.inspect}" if @uri + if @external_id + reference_writer = ReferenceWriter.new(@external_id, + @long_name, + @uri) + reference_writer.write(output) + end unless @children.empty? output << ' [' @children.each { |child| @@ -249,9 +287,9 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/doctype.rb#L287 end def to_s - notation = "<!NOTATION #{@name} #{@middle}" - notation << " #{@public.inspect}" if @public - notation << " #{@system.inspect}" if @system + notation = "<!NOTATION #{@name}" + reference_writer = ReferenceWriter.new(@middle, @public, @system) + reference_writer.write(notation) notation << ">" notation end diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb index 80eeb0f..e7ef695 100644 --- a/lib/rexml/parsers/baseparser.rb +++ b/lib/rexml/parsers/baseparser.rb @@ -1,4 +1,7 @@ https://github.com/ruby/ruby/blob/trunk/lib/rexml/parsers/baseparser.rb#L1 # frozen_string_literal: false + +require "strscan" + require 'rexml/parseexception' require 'rexml/undefinednamespaceexception' require 'rexml/source' @@ -32,8 +35,12 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/parsers/baseparser.rb#L35 COMBININGCHAR = '' # TODO EXTENDER = '' # TODO - NCNAME_STR= "[#{LETTER}_:][-[:alnum:]._:#{COMBININGCHAR}#{EXTENDER}]*" - NAME_STR= "(?:(#{NCNAME_STR}):)?(#{NCNAME_STR})" + NCNAME_STR= "[#{LETTER}_][-[:alnum:]._#{COMBININGCHAR}#{EXTENDER}]*" + QNAME_STR= "(?:(#{NCNAME_STR}):)?(#{NCNAME_STR})" + QNAME = /(#{QNAME_STR})/ + + # Just for backward compatibility. For example, kramdown uses this. + # It's not used in REXML. UNAME_STR= "(?:#{NCNAME_STR}:)?#{NCNAME_STR}" NAMECHAR = '[\-\w\.:]' @@ -45,8 +52,7 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/parsers/baseparser.rb#L52 DOCTYPE_START = /\A\s*<!DOCTYPE\s/um DOCTYPE_END = /\A\s*\]\s*>/um - DOCTYPE_PATTERN = /\s*<!DOCTYPE\s+(.*?)(\[|>)/um - ATTRIBUTE_PATTERN = /\s*(#{NAME_STR})\s*=\s*(["'])(.*?)\4/um + ATTRIBUTE_PATTERN = /\s*(#{QNAME_STR})\s*=\s*(["'])(.*?)\4/um COMMENT_START = /\A<!--/u COMMENT_PATTERN = /<!--(.*?)-->/um CDATA_START = /\A<!\[CDATA\[/u @@ -56,15 +62,14 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/parsers/baseparser.rb#L62 XMLDECL_PATTERN = /<\?xml\s+(.*?)\?>/um INSTRUCTION_START = /\A<\?/u INSTRUCTION_PATTERN = /<\?(.*?)(\s+.*?)?\?>/um - TAG_MATCH = /^<((?>#{NAME_STR}))\s*((?>\s+#{UNAME_STR}\s*=\s*(["']).*?\5)*)\s*(\/)?>/um - CLOSE_MATCH = /^\s*<\/(#{NAME_STR})\s*>/um + TAG_MATCH = /\A<((?>#{QNAME_STR}))/um + CLOSE_MATCH = /\A\s*<\/(#{QNAME_STR})\s*>/um VERSION = /\bversion\s*=\s*["'](.*?)['"]/um ENCODING = /\bencoding\s*=\s*["'](.*?)['"]/um STANDALONE = /\bstandalone\s*=\s*["'](.*?)['"]/um ENTITY_START = /\A\s*<!ENTITY/ - IDENTITY = /^([!\*\w\-]+)(\s+#{NCNAME_STR})?(\s+["'](.*?)['"])?(\s+['"](.*?)["'])?/u ELEMENTDECL_START = /\A\s*<!ELEMENT/um ELEMENTDECL_PATTERN = /\A\s*(<!ELEMENT.*?)>/um SYSTEMENTITY = /\A\s*(%.*?;)\s*$/um @@ -78,9 +83,6 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/parsers/baseparser.rb#L83 ATTDEF_RE = /#{ATTDEF}/ ATTLISTDECL_START = /\A\s*<!ATTLIST/um ATTLISTDECL_PATTERN = /\A\s*<!ATTLIST\s+#{NAME}(?:#{ATTDEF})*\s*>/um - NOTATIONDECL_START = /\A\s*<!NOTATION/um - PUBLIC = /\A\s*<!NOTATION\s+(\w[\-\w]*)\s+(PUBLIC)\s+(["'])(.*?)\3(?:\s+(["'])(.*?)\5)?\s*>/um - SYSTEM = /\A\s*<!NOTATION\s+(\w[\-\w]*)\s+(SYSTEM)\s+(["'])(.*?)\3\s*>/um TEXT_PATTERN = /\A([^<]*)/um @@ -98,6 +100,11 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/parsers/baseparser.rb#L100 GEDECL = "<!ENTITY\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>" ENTITYDECL = /\s*(?:#{GEDECL})|(?:#{PEDECL})/um + NOTATIONDECL_START = /\A\s*<!NOTATION/um + EXTERNAL_ID_PUBLIC = /\A\s*PUBLIC\s+#{PUBIDLITERAL}\s+#{SYSTEMLITERAL}\s*/um + EXTERNAL_ID_SYSTEM = /\A\s*SYSTEM\s+#{SYSTEMLITERAL}\s*/um + PUBLIC_ID = /\A\s*PUBLIC\s+#{PUBIDLITERAL}\s*/um + EREFERENCE = /&(?!#{NAME};)/ DEFAULT_ENTITIES = { @@ -112,7 +119,7 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/parsers/baseparser.rb#L119 # These are patterns to identify common markup errors, to make the # error messages more informative. ###################################################################### - MISSING_ATTRIBUTE_QUOTES = /^<#{NAME_STR}\s+#{NAME_STR}\s*=\s*[^"']/um + MISSING_ATTRIBUTE_QUOTES = /^<#{QNAME_STR}\s+#{QNAME_STR}\s*=\s*[^"']/um def initialize( source ) self.stream = source @@ -197,11 +204,9 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/parsers/baseparser.rb#L204 return [ :end_document ] if empty? return @stack.shift if @stack.size > 0 #STDERR.puts @source.encoding - @source.read if @source.buffer.size<2 #STDERR.puts "BUFFER = #{@source.buffer.inspect}" if @document_status == nil - #@source.consume( /^\s*/um ) - word = @source.match( /^((?:\s+)|(?:<[^>]*>))/um ) + word = @source.match( /\A((?:\s+)|(?:<[^>]*>))/um ) word = word[1] unless word.nil? #STDERR.puts "WORD = #{word.inspect}" case word @@ -226,38 +231,49 @@ module REXML https://github.com/ruby/ruby/blob/trunk/lib/rexml/parsers/baseparser.rb#L231 when INSTRUCTION_START return [ :processing_instruction, *@source.match(INSTRUCTION_PATTERN, true)[1,2] ] when DOCTYPE_START - md = @source.match( DOCTYPE_PATTERN, true ) + base_error_message = "Malformed DOCTYPE" + @source.match(DOCTYPE_START, true) @nsstack.unshift(curr_ns=Set.new) - identity = md[1] - close = md[2] - identity =~ IDENTITY - name = $1 - raise REXML::ParseException.new("DOCTYPE is missing a name") if name.nil? - pub_sys = $2.nil? ? nil : $2.strip - long_name = $4.nil? ? nil : $4.strip - uri = $6.nil? ? nil : $6.strip - args = [ :start_doctype, name, pub_sys, long_name, uri ] - if close == ">" + name = parse_name(base_error_message) + if @source.match(/\A\s*\[/um, true) + id = [nil, nil, nil] + @document_status = :in_doctype + elsif @source.match(/\A\s*>/um, true) + id = [nil, nil, nil] @document_status = :after_doctype - @source.read if @source.buffer.size<2 - (... truncated) -- ML: ruby-changes@q... Info: http://www.atdot.net/~ko1/quickml/