From 66aeb2f7080dea92703f10546fb3cbcc946f6fa3 Mon Sep 17 00:00:00 2001
From: ser <ser@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>
Date: Sun, 20 Jan 2008 04:31:57 +0000
Subject:  r1479@bean:  ser | 2008-01-19 14:26:31 -0500

 r1483@bean:  ser | 2008-01-19 14:47:23 -0500
 Sam's fixes:
 * Don't blow up on empty documents
 * Add a test case for sorted attributes
 * Making the output predictable simplifies unit tests, and doesn't cost
   much given that most xml element have few attributes
 * Ruby 1.9 revision 14922 is more strict
 * Complete Ticket #134
 * Fix for ticket #121
 * Fix for ticket #124
 * Fix for ticket #128
 * Fix ticket #133
 * Ticket #131 (Support Ruby 1.9)
 * Fix for ticket #127
 * Fix for ticket #123
 * Add missing data needed by test case

  r1481@bean (orig r1303):  ser | 2008-01-19 17:22:32 -0500
  Tagged for release
  r1482@bean (orig r1304):  ser | 2008-01-19 17:27:10 -0500
  Version bump



git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@15141 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
---
 lib/rexml/parsers/baseparser.rb | 38 ++++++++++++++++++++++++++++++--------
 1 file changed, 30 insertions(+), 8 deletions(-)

(limited to 'lib/rexml/parsers')

diff --git a/lib/rexml/parsers/baseparser.rb b/lib/rexml/parsers/baseparser.rb
index 854e707fae..85f2c4e46d 100644
--- a/lib/rexml/parsers/baseparser.rb
+++ b/lib/rexml/parsers/baseparser.rb
@@ -25,7 +25,20 @@ module REXML
     #
     # Nat Price gave me some good ideas for the API.
     class BaseParser
-      NCNAME_STR= '[\w:][\-\w\d.]*'
+      if String.method_defined? :encode
+        # Oniguruma / POSIX [understands unicode]
+        LETTER = '[[:alpha:]]'
+        DIGIT = '[[:digit:]]'
+      else
+        # Ruby < 1.9 [doesn't understand unicode]
+        LETTER = 'a-zA-Z'
+        DIGIT = '\d'
+      end
+
+      COMBININGCHAR = '' # TODO
+      EXTENDER = ''      # TODO
+
+      NCNAME_STR= "[#{LETTER}_:][-#{LETTER}#{DIGIT}._:#{COMBININGCHAR}#{EXTENDER}]*"
       NAME_STR= "(?:(#{NCNAME_STR}):)?(#{NCNAME_STR})"
       UNAME_STR= "(?:#{NCNAME_STR}:)?#{NCNAME_STR}"
 
@@ -33,7 +46,7 @@ module REXML
       NAME = "([\\w:]#{NAMECHAR}*)"
       NMTOKEN = "(?:#{NAMECHAR})+"
       NMTOKENS = "#{NMTOKEN}(\\s+#{NMTOKEN})*"
-      REFERENCE = "(?:&#{NAME};|&#\\d+;|&#x[0-9a-fA-F]+;)"
+      REFERENCE = "&(?:#{NAME};|#\\d+;|#x[0-9a-fA-F]+;)"
       REFERENCE_RE = /#{REFERENCE}/
 
       DOCTYPE_START = /\A\s*<!DOCTYPE\s/um
@@ -340,6 +353,12 @@ module REXML
               raise REXML::ParseException.new("Malformed node", @source) unless md
               if md[0][2] == ?-
                 md = @source.match( COMMENT_PATTERN, true )
+
+                case md[1]
+                when /--/, /-$/
+                  raise REXML::ParseException.new("Malformed comment", @source)
+                end
+
                 return [ :comment, md[1] ] if md
               else
                 md = @source.match( CDATA_PATTERN, true )
@@ -384,6 +403,12 @@ module REXML
                   elsif b
                     prefixes << b unless b == "xml"
                   end
+
+                  if attributes.has_key? a
+                    msg = "Duplicate attribute #{a.inspect}"
+                    raise REXML::ParseException.new( msg, @source, self)
+                  end
+
                   attributes[a] = e 
                 }
               end
@@ -470,15 +495,12 @@ module REXML
               if entity_value
                 re = /&#{entity_reference};/
                 rv.gsub!( re, entity_value )
+              else
+                er = DEFAULT_ENTITIES[entity_reference]
+                rv.gsub!( er[0], er[2] ) if er
               end
             end
           end
-          matches.each do |entity_reference|
-            unless filter and filter.include?(entity_reference)
-              er = DEFAULT_ENTITIES[entity_reference]
-              rv.gsub!( er[0], er[2] ) if er
-            end
-          end
           rv.gsub!( /&amp;/, '&' )
         end
         rv
-- 
cgit v1.2.3