diff options
| -rw-r--r-- | lib/rexml/attribute.rb | 2 | ||||
| -rw-r--r-- | lib/rexml/document.rb | 3 | ||||
| -rw-r--r-- | lib/rexml/element.rb | 11 | ||||
| -rw-r--r-- | lib/rexml/encoding.rb | 9 | ||||
| -rw-r--r-- | lib/rexml/parsers/baseparser.rb | 58 | ||||
| -rw-r--r-- | lib/rexml/parsers/treeparser.rb | 6 | ||||
| -rw-r--r-- | lib/rexml/rexml.rb | 14 | ||||
| -rw-r--r-- | lib/rexml/source.rb | 16 | ||||
| -rw-r--r-- | lib/rexml/undefinednamespaceexception.rb | 8 |
9 files changed, 95 insertions, 32 deletions
diff --git a/lib/rexml/attribute.rb b/lib/rexml/attribute.rb index 029035d675..89c1ada36c 100644 --- a/lib/rexml/attribute.rb +++ b/lib/rexml/attribute.rb @@ -50,7 +50,7 @@ module REXML @element = first.element end elsif first.kind_of? String - @element = parent if parent.kind_of? Element + @element = parent self.name = first @normalized = second.to_s else diff --git a/lib/rexml/document.rb b/lib/rexml/document.rb index 558b5d731a..81e63c60f1 100644 --- a/lib/rexml/document.rb +++ b/lib/rexml/document.rb @@ -66,6 +66,7 @@ module REXML def add( child ) if child.kind_of? XMLDecl @children.unshift child + child.parent = self elsif child.kind_of? DocType # Find first Element or DocType node and insert the decl right # before it. If there is no such node, just insert the child at the @@ -183,7 +184,7 @@ module REXML output = Output.new( output, xml_decl.encoding ) end formatter = if indent > -1 - if transitive + if trans REXML::Formatters::Transitive.new( indent, ie_hack ) else REXML::Formatters::Pretty.new( indent, ie_hack ) diff --git a/lib/rexml/element.rb b/lib/rexml/element.rb index f757cfffa8..92612036a1 100644 --- a/lib/rexml/element.rb +++ b/lib/rexml/element.rb @@ -553,6 +553,7 @@ module REXML def attribute( name, namespace=nil ) prefix = nil prefix = namespaces.index(namespace) if namespace + prefix = nil if prefix == 'xmlns' attributes.get_attribute( "#{prefix ? prefix + ':' : ''}#{name}" ) end @@ -854,15 +855,15 @@ module REXML # Source (see Element.initialize). If not supplied or nil, a # new, default Element will be constructed # Returns:: the added Element - # a = Element.new 'a' - # a.elements.add Element.new 'b' #-> <a><b/></a> - # a.elements.add 'c' #-> <a><b/><c/></a> + # a = Element.new('a') + # a.elements.add(Element.new('b')) #-> <a><b/></a> + # a.elements.add('c') #-> <a><b/><c/></a> def add element=nil rv = nil if element.nil? - Element.new "", self, @element.context + Element.new("", self, @element.context) elsif not element.kind_of?(Element) - Element.new element, self, @element.context + Element.new(element, self, @element.context) else @element << element element.context = @element.context diff --git a/lib/rexml/encoding.rb b/lib/rexml/encoding.rb index 6cae6b644d..a01763be99 100644 --- a/lib/rexml/encoding.rb +++ b/lib/rexml/encoding.rb @@ -56,8 +56,13 @@ module REXML def check_encoding str # We have to recognize UTF-16, LSB UTF-16, and UTF-8 - return UTF_16 if /\A\xfe\xff/n =~ str - return UNILE if /\A\xff\xfe/n =~ str + if str[0] == 0xfe && str[1] == 0xff + str[0,2] = "" + return UTF_16 + elsif str[0] == 0xff && str[1] == 0xfe + str[0,2] = "" + return UNILE + end str =~ /^\s*<\?xml\s+version\s*=\s*(['"]).*?\1\s+encoding\s*=\s*(["'])(.*?)\2/um return $3.upcase if $3 return UTF_8 diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb index 3782d61b2c..fc2354a67f 100644 --- a/lib/rexml/parsers/baseparser.rb +++ b/lib/rexml/parsers/baseparser.rb @@ -1,5 +1,7 @@ require 'rexml/parseexception' +require 'rexml/undefinednamespaceexception' require 'rexml/source' +require 'set' module REXML module Parsers @@ -24,7 +26,8 @@ module REXML # Nat Price gave me some good ideas for the API. class BaseParser NCNAME_STR= '[\w:][\-\w\d.]*' - NAME_STR= "(?:#{NCNAME_STR}:)?#{NCNAME_STR}" + NAME_STR= "(?:(#{NCNAME_STR}):)?(#{NCNAME_STR})" + UNAME_STR= "(?:#{NCNAME_STR}:)?#{NCNAME_STR}" NAMECHAR = '[\-\w\d\.:]' NAME = "([\\w:]#{NAMECHAR}*)" @@ -35,7 +38,7 @@ module REXML DOCTYPE_START = /\A\s*<!DOCTYPE\s/um DOCTYPE_PATTERN = /\s*<!DOCTYPE\s+(.*?)(\[|>)/um - ATTRIBUTE_PATTERN = /\s*(#{NAME_STR})\s*=\s*(["'])(.*?)\2/um + ATTRIBUTE_PATTERN = /\s*(#{NAME_STR})\s*=\s*(["'])(.*?)\4/um COMMENT_START = /\A<!--/u COMMENT_PATTERN = /<!--(.*?)-->/um CDATA_START = /\A<!\[CDATA\[/u @@ -45,7 +48,7 @@ module REXML XMLDECL_PATTERN = /<\?xml\s+(.*?)\?>/um INSTRUCTION_START = /\A<\?/u INSTRUCTION_PATTERN = /<\?(.*?)(\s+.*?)?\?>/um - TAG_MATCH = /^<((?>#{NAME_STR}))\s*((?>\s+#{NAME_STR}\s*=\s*(["']).*?\3)*)\s*(\/)?>/um + TAG_MATCH = /^<((?>#{NAME_STR}))\s*((?>\s+#{UNAME_STR}\s*=\s*(["']).*?\5)*)\s*(\/)?>/um CLOSE_MATCH = /^\s*<\/(#{NAME_STR})\s*>/um VERSION = /\bversion\s*=\s*["'](.*?)['"]/um @@ -133,6 +136,7 @@ module REXML @tags = [] @stack = [] @entities = [] + @nsstack = [] end def position @@ -188,6 +192,7 @@ module REXML end 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 @@ -213,6 +218,7 @@ module REXML return [ :processing_instruction, *@source.match(INSTRUCTION_PATTERN, true)[1,2] ] when DOCTYPE_START md = @source.match( DOCTYPE_PATTERN, true ) + @nsstack.unshift(curr_ns=Set.new) identity = md[1] close = md[2] identity =~ IDENTITY @@ -288,6 +294,9 @@ module REXML val = attdef[3] val = attdef[4] if val == "#FIXED " pairs[attdef[0]] = val + if attdef[0] =~ /^xmlns:(.*)/ + @nsstack[0] << $1 + end end end return [ :attlistdecl, element, pairs, contents ] @@ -312,6 +321,7 @@ module REXML begin if @source.buffer[0] == ?< if @source.buffer[1] == ?/ + @nsstack.shift last_tag = @tags.pop #md = @source.match_to_consume( '>', CLOSE_MATCH) md = @source.match( CLOSE_MATCH, true ) @@ -345,19 +355,47 @@ module REXML raise REXML::ParseException.new("missing attribute quote", @source) if @source.match(MISSING_ATTRIBUTE_QUOTES ) raise REXML::ParseException.new("malformed XML: missing tag start", @source) end - attrs = [] - if md[2].size > 0 - attrs = md[2].scan( ATTRIBUTE_PATTERN ) + attributes = {} + prefixes = Set.new + prefixes << md[2] if md[2] + @nsstack.unshift(curr_ns=Set.new) + if md[4].size > 0 + attrs = md[4].scan( ATTRIBUTE_PATTERN ) raise REXML::ParseException.new( "error parsing attributes: [#{attrs.join ', '}], excess = \"#$'\"", @source) if $' and $'.strip.size > 0 + attrs.each { |a,b,c,d,e| + if b == "xmlns" + if c == "xml" + if d != "http://www.w3.org/XML/1998/namespace" + msg = "The 'xml' prefix must not be bound to any other namespace "+ + "(http://www.w3.org/TR/REC-xml-names/#ns-decl)" + raise REXML::ParseException.new( msg, @source, self ) + end + elsif c == "xmlns" + msg = "The 'xmlns' prefix must not be declared "+ + "(http://www.w3.org/TR/REC-xml-names/#ns-decl)" + raise REXML::ParseException.new( msg, @source, self) + end + curr_ns << c + elsif b + prefixes << b unless b == "xml" + end + attributes[a] = e + } end - if md[4] + # Verify that all of the prefixes have been defined + for prefix in prefixes + unless @nsstack.find{|k| k.member?(prefix)} + raise UndefinedNamespaceException.new(prefix,@source,self) + end + end + + if md[6] @closed = md[1] + @nsstack.shift else @tags.push( md[1] ) end - attributes = {} - attrs.each { |a,b,c| attributes[a] = c } return [ :start_element, md[1], attributes ] end else @@ -371,6 +409,8 @@ module REXML # return PullEvent.new( :text, md[1], unnormalized ) return [ :text, md[1] ] end + rescue REXML::UndefinedNamespaceException + raise rescue REXML::ParseException raise rescue Exception, NameError => error diff --git a/lib/rexml/parsers/treeparser.rb b/lib/rexml/parsers/treeparser.rb index a53fa41925..5c3e142ea7 100644 --- a/lib/rexml/parsers/treeparser.rb +++ b/lib/rexml/parsers/treeparser.rb @@ -1,4 +1,5 @@ require 'rexml/validation/validationexception' +require 'rexml/undefinednamespaceexception' module REXML module Parsers @@ -29,8 +30,7 @@ module REXML return when :start_element tag_stack.push(event[1]) - # find the observers for namespaces - @build_context = @build_context.add_element( event[1], event[2] ) + el = @build_context = @build_context.add_element( event[1], event[2] ) when :end_element tag_stack.pop @build_context = @build_context.parent @@ -86,6 +86,8 @@ module REXML end rescue REXML::Validation::ValidationException raise + rescue REXML::UndefinedNamespaceException + raise rescue raise ParseException.new( $!.message, @parser.source, @parser, $! ) end diff --git a/lib/rexml/rexml.rb b/lib/rexml/rexml.rb index 19805d61e1..8af1697e51 100644 --- a/lib/rexml/rexml.rb +++ b/lib/rexml/rexml.rb @@ -1,3 +1,4 @@ +# -*- encoding: utf-8 -*- # REXML is an XML toolkit for Ruby[http://www.ruby-lang.org], in Ruby. # # REXML is a _pure_ Ruby, XML 1.0 conforming, @@ -10,8 +11,9 @@ # # Main page:: http://www.germane-software.com/software/rexml # Author:: Sean Russell <serATgermaneHYPHENsoftwareDOTcom> -# Version:: 3.1.7.1 -# Date:: 2007/209 +# Version:: 3.1.7.2 +# Date:: 2007/275 +# Revision:: $Revision$ # # This API documentation can be downloaded from the REXML home page, or can # be accessed online[http://www.germane-software.com/software/rexml_doc] @@ -20,10 +22,10 @@ # or can be accessed # online[http://www.germane-software.com/software/rexml/docs/tutorial.html] module REXML - COPYRIGHT = "Copyright © 2001-2007 Sean Russell <ser@germane-software.com>" - DATE = "2007/209" - VERSION = "3.1.7.1" - REVISION = "$Revision: 1270$".gsub(/\$Revision:|\$/,'').strip + COPYRIGHT = "Copyright \xC2\xA9 2001-2006 Sean Russell <ser@germane-software.com>" + VERSION = "3.1.7.2" + DATE = "2007/275" + REVISION = "$Revision$".gsub(/\$Revision:|\$/,'').strip Copyright = COPYRIGHT Version = VERSION diff --git a/lib/rexml/source.rb b/lib/rexml/source.rb index ada876cde5..ce7a2c98b0 100644 --- a/lib/rexml/source.rb +++ b/lib/rexml/source.rb @@ -17,8 +17,8 @@ module REXML elsif arg.kind_of? Source arg else - raise "#{source.class} is not a valid input stream. It must walk \n"+ - "like either a String, IO, or Source." + raise "#{arg.class} is not a valid input stream. It must walk \n"+ + "like either a String, an IO, or a Source." end end end @@ -134,6 +134,7 @@ module REXML def initialize(arg, block_size=500, encoding=nil) @er_source = @source = arg @to_utf = false + # Determining the encoding is a deceptively difficult issue to resolve. # First, we check the first two bytes for UTF-16. Then we # assume that the encoding is at least ASCII enough for the '>', and @@ -145,13 +146,16 @@ module REXML str = @source.read( 2 ) if encoding self.encoding = encoding - elsif /\A(?:\xfe\xff|\xff\xfe)/n =~ str - self.encoding = check_encoding( str ) - elsif (0xef == str[0] && 0xbb == str[1]) + elsif 0xfe == str[0] && 0xff == str[1] + @line_break = "\000>" + elsif 0xff == str[0] && 0xfe == str[1] + @line_break = ">\000" + elsif 0xef == str[0] && 0xbb == str[1] str += @source.read(1) str = '' if (0xbf == str[2]) + @line_break = ">" else - @line_break = '>' + @line_break = ">" end super str+@source.readline( @line_break ) end diff --git a/lib/rexml/undefinednamespaceexception.rb b/lib/rexml/undefinednamespaceexception.rb new file mode 100644 index 0000000000..8ebfdfd0a9 --- /dev/null +++ b/lib/rexml/undefinednamespaceexception.rb @@ -0,0 +1,8 @@ +require 'rexml/parseexception' +module REXML + class UndefinedNamespaceException < ParseException + def initialize( prefix, source, parser ) + super( "Undefined prefix #{prefix} found" ) + end + end +end |