From 06f2b5b1d890253cdc4de78a326369a10d22595b Mon Sep 17 00:00:00 2001
From: ser <ser@b2dd03c8-39d4-4d8f-98ff-823fe69b080e>
Date: Sun, 4 Nov 2007 04:52:08 +0000
Subject:   Fixes ticket:110 (more UTF-16 problems)   Missing include for
 UndefinedNamespaceException was causing errors in some     cases.

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@13816 b2dd03c8-39d4-4d8f-98ff-823fe69b080e
---
 lib/rexml/encoding.rb           |  9 +++++++--
 lib/rexml/parsers/baseparser.rb |  2 ++
 lib/rexml/parsers/treeparser.rb |  1 +
 lib/rexml/source.rb             | 12 ++++++++----
 4 files changed, 18 insertions(+), 6 deletions(-)

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 5f7a5ec43b..fc2354a67f 100644
--- a/lib/rexml/parsers/baseparser.rb
+++ b/lib/rexml/parsers/baseparser.rb
@@ -1,4 +1,5 @@
 require 'rexml/parseexception'
+require 'rexml/undefinednamespaceexception'
 require 'rexml/source'
 require 'set'
 
@@ -191,6 +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
diff --git a/lib/rexml/parsers/treeparser.rb b/lib/rexml/parsers/treeparser.rb
index ff8261cedf..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
diff --git a/lib/rexml/source.rb b/lib/rexml/source.rb
index 659bcdc195..e05460fea1 100644
--- a/lib/rexml/source.rb
+++ b/lib/rexml/source.rb
@@ -135,6 +135,7 @@ 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
@@ -146,13 +147,16 @@ 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
-- 
cgit v1.2.3