[sup-devel] [PATCH 05/10] fixup Iconv#easy_decode for Ruby 1.9

From: Rich Lane <rlane@club.cc.cmu.edu>
To: sup-devel@rubyforge.org
Subject: [sup-devel] [PATCH 05/10] fixup Iconv#easy_decode for Ruby 1.9
Date: Thu, 31 Dec 2009 15:36:53 -0800	[thread overview]
Message-ID: <1262302618-20503-6-git-send-email-rlane@club.cc.cmu.edu> (raw)
In-Reply-To: <1262302618-20503-5-git-send-email-rlane@club.cc.cmu.edu>

---
 lib/sup/util.rb |   21 +++++++++++++--------
 1 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/lib/sup/util.rb b/lib/sup/util.rb
index 508bcee..560ac73 100644
--- a/lib/sup/util.rb
+++ b/lib/sup/util.rb
@@ -664,21 +664,26 @@ class FinishLine
 end
 
 class Iconv
-  def self.easy_decode target, charset, text
-    return text if charset =~ /^(x-unknown|unknown[-_ ]?8bit|ascii[-_ ]?7[-_ ]?bit)$/i
-    charset = case charset
+  def self.easy_decode target, orig_charset, text
+    if text.respond_to? :force_encoding
+      text = text.dup
+      text.force_encoding Encoding::BINARY
+    end
+    charset = case orig_charset
       when /UTF[-_ ]?8/i then "utf-8"
       when /(iso[-_ ])?latin[-_ ]?1$/i then "ISO-8859-1"
       when /iso[-_ ]?8859[-_ ]?15/i then 'ISO-8859-15'
       when /unicode[-_ ]1[-_ ]1[-_ ]utf[-_]7/i then "utf-7"
-      else charset
+      when /^euc$/i then 'EUC-JP' # XXX try them all?
+      when /^(x-unknown|unknown[-_ ]?8bit|ascii[-_ ]?7[-_ ]?bit)$/i then 'ASCII'
+      else orig_charset
     end
 
     begin
-      Iconv.iconv(target + "//IGNORE", charset, text + " ").join[0 .. -2]
-    rescue Errno::EINVAL, Iconv::InvalidEncoding, Iconv::InvalidCharacter, Iconv::IllegalSequence => e
-      warn "couldn't transcode text from #{charset} to #{target} (\"#{text[0 ... 20]}\"...) (got #{e.message}); using original as is"
-      text
+      returning(Iconv.iconv(target, charset, text + " ").join[0 .. -2]) { |str| str.check }
+    rescue Errno::EINVAL, Iconv::InvalidEncoding, Iconv::InvalidCharacter, Iconv::IllegalSequence, String::CheckError
+      warn "couldn't transcode text from #{orig_charset} (#{charset}) to #{target}) (#{text[0 ... 20].inspect}...) (got #{$!.message} (#{$!.class}))"
+      text.ascii
     end
   end
 end
-- 
1.6.3.3

_______________________________________________
Sup-devel mailing list
Sup-devel@rubyforge.org
http://rubyforge.org/mailman/listinfo/sup-devel

